adaption_emir_reporting_code_gen / trainer_state.json
Tonic's picture
Add 11 files
0a302b7 verified
Raw
History Blame Contribute Delete
118 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"eval_steps": 125,
"global_step": 628,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006369426751592357,
"grad_norm": 14.634740829467773,
"learning_rate": 0.0,
"loss": 1.8326416015625,
"step": 1
},
{
"epoch": 0.012738853503184714,
"grad_norm": 13.922843933105469,
"learning_rate": 9.375e-06,
"loss": 1.771697998046875,
"step": 2
},
{
"epoch": 0.01910828025477707,
"grad_norm": 14.774005889892578,
"learning_rate": 1.875e-05,
"loss": 1.85638427734375,
"step": 3
},
{
"epoch": 0.025477707006369428,
"grad_norm": 10.349848747253418,
"learning_rate": 2.8125e-05,
"loss": 1.5071837902069092,
"step": 4
},
{
"epoch": 0.03184713375796178,
"grad_norm": 6.5954909324646,
"learning_rate": 3.75e-05,
"loss": 1.4010009765625,
"step": 5
},
{
"epoch": 0.03821656050955414,
"grad_norm": 3.024427890777588,
"learning_rate": 4.6874999999999994e-05,
"loss": 1.2522125244140625,
"step": 6
},
{
"epoch": 0.044585987261146494,
"grad_norm": 1.8201521635055542,
"learning_rate": 5.625e-05,
"loss": 1.2423095703125,
"step": 7
},
{
"epoch": 0.050955414012738856,
"grad_norm": 1.9971822500228882,
"learning_rate": 6.5625e-05,
"loss": 1.1450324058532715,
"step": 8
},
{
"epoch": 0.05732484076433121,
"grad_norm": 2.0520060062408447,
"learning_rate": 7.5e-05,
"loss": 0.9954171180725098,
"step": 9
},
{
"epoch": 0.06369426751592357,
"grad_norm": 1.7549692392349243,
"learning_rate": 8.437499999999999e-05,
"loss": 1.1235504150390625,
"step": 10
},
{
"epoch": 0.07006369426751592,
"grad_norm": 1.2025140523910522,
"learning_rate": 9.374999999999999e-05,
"loss": 1.0770721435546875,
"step": 11
},
{
"epoch": 0.07643312101910828,
"grad_norm": 0.7220160961151123,
"learning_rate": 0.00010312499999999999,
"loss": 1.0740203857421875,
"step": 12
},
{
"epoch": 0.08280254777070063,
"grad_norm": 0.5354941487312317,
"learning_rate": 0.0001125,
"loss": 1.0075836181640625,
"step": 13
},
{
"epoch": 0.08917197452229299,
"grad_norm": 0.7336816787719727,
"learning_rate": 0.000121875,
"loss": 1.04559326171875,
"step": 14
},
{
"epoch": 0.09554140127388536,
"grad_norm": 0.6976461410522461,
"learning_rate": 0.00013125,
"loss": 0.9922637939453125,
"step": 15
},
{
"epoch": 0.10191082802547771,
"grad_norm": 0.4800432622432709,
"learning_rate": 0.000140625,
"loss": 0.9724864959716797,
"step": 16
},
{
"epoch": 0.10828025477707007,
"grad_norm": 0.337033748626709,
"learning_rate": 0.00015,
"loss": 0.9916305541992188,
"step": 17
},
{
"epoch": 0.11464968152866242,
"grad_norm": 0.35018786787986755,
"learning_rate": 0.00015937499999999998,
"loss": 1.01153564453125,
"step": 18
},
{
"epoch": 0.12101910828025478,
"grad_norm": 0.3646854758262634,
"learning_rate": 0.00016874999999999998,
"loss": 0.9244003295898438,
"step": 19
},
{
"epoch": 0.12738853503184713,
"grad_norm": 0.29458990693092346,
"learning_rate": 0.00017812499999999998,
"loss": 0.94232177734375,
"step": 20
},
{
"epoch": 0.1337579617834395,
"grad_norm": 0.26776453852653503,
"learning_rate": 0.00018749999999999998,
"loss": 0.948822021484375,
"step": 21
},
{
"epoch": 0.14012738853503184,
"grad_norm": 0.27545294165611267,
"learning_rate": 0.00019687499999999997,
"loss": 0.9884185791015625,
"step": 22
},
{
"epoch": 0.1464968152866242,
"grad_norm": 0.27437588572502136,
"learning_rate": 0.00020624999999999997,
"loss": 0.9786376953125,
"step": 23
},
{
"epoch": 0.15286624203821655,
"grad_norm": 0.25814566016197205,
"learning_rate": 0.00021562499999999997,
"loss": 0.9479827880859375,
"step": 24
},
{
"epoch": 0.1592356687898089,
"grad_norm": 0.20565250515937805,
"learning_rate": 0.000225,
"loss": 0.9623298645019531,
"step": 25
},
{
"epoch": 0.16560509554140126,
"grad_norm": 0.23908597230911255,
"learning_rate": 0.000234375,
"loss": 0.8784637451171875,
"step": 26
},
{
"epoch": 0.17197452229299362,
"grad_norm": 0.22095371782779694,
"learning_rate": 0.00024375,
"loss": 0.8614120483398438,
"step": 27
},
{
"epoch": 0.17834394904458598,
"grad_norm": 0.17901843786239624,
"learning_rate": 0.000253125,
"loss": 0.8215179443359375,
"step": 28
},
{
"epoch": 0.18471337579617833,
"grad_norm": 0.238013356924057,
"learning_rate": 0.0002625,
"loss": 0.925048828125,
"step": 29
},
{
"epoch": 0.1910828025477707,
"grad_norm": 0.1779915690422058,
"learning_rate": 0.000271875,
"loss": 0.865264892578125,
"step": 30
},
{
"epoch": 0.19745222929936307,
"grad_norm": 0.20595991611480713,
"learning_rate": 0.00028125,
"loss": 0.8397705554962158,
"step": 31
},
{
"epoch": 0.20382165605095542,
"grad_norm": 0.19492584466934204,
"learning_rate": 0.000290625,
"loss": 0.8128700256347656,
"step": 32
},
{
"epoch": 0.21019108280254778,
"grad_norm": 0.17935727536678314,
"learning_rate": 0.0003,
"loss": 0.8271636962890625,
"step": 33
},
{
"epoch": 0.21656050955414013,
"grad_norm": 0.23040995001792908,
"learning_rate": 0.0002999981245305545,
"loss": 0.8703155517578125,
"step": 34
},
{
"epoch": 0.2229299363057325,
"grad_norm": 0.2647894620895386,
"learning_rate": 0.00029999249817432727,
"loss": 0.8524932861328125,
"step": 35
},
{
"epoch": 0.22929936305732485,
"grad_norm": 0.15038178861141205,
"learning_rate": 0.00029998312108764537,
"loss": 0.7906417846679688,
"step": 36
},
{
"epoch": 0.2356687898089172,
"grad_norm": 0.21919266879558563,
"learning_rate": 0.0002999699935310484,
"loss": 0.8485870361328125,
"step": 37
},
{
"epoch": 0.24203821656050956,
"grad_norm": 0.15890416502952576,
"learning_rate": 0.00029995311586928215,
"loss": 0.8249359130859375,
"step": 38
},
{
"epoch": 0.2484076433121019,
"grad_norm": 0.15894381701946259,
"learning_rate": 0.0002999324885712879,
"loss": 0.75238037109375,
"step": 39
},
{
"epoch": 0.25477707006369427,
"grad_norm": 0.193678617477417,
"learning_rate": 0.0002999081122101896,
"loss": 0.847900390625,
"step": 40
},
{
"epoch": 0.2611464968152866,
"grad_norm": 0.14389629662036896,
"learning_rate": 0.0002998799874632779,
"loss": 0.7450682520866394,
"step": 41
},
{
"epoch": 0.267515923566879,
"grad_norm": 0.21948423981666565,
"learning_rate": 0.00029984811511199136,
"loss": 0.803375244140625,
"step": 42
},
{
"epoch": 0.27388535031847133,
"grad_norm": 0.16477927565574646,
"learning_rate": 0.00029981249604189484,
"loss": 0.7503585815429688,
"step": 43
},
{
"epoch": 0.2802547770700637,
"grad_norm": 0.21690034866333008,
"learning_rate": 0.0002997731312426546,
"loss": 0.79840087890625,
"step": 44
},
{
"epoch": 0.28662420382165604,
"grad_norm": 0.1361113041639328,
"learning_rate": 0.000299730021808011,
"loss": 0.76605224609375,
"step": 45
},
{
"epoch": 0.2929936305732484,
"grad_norm": 0.15949746966362,
"learning_rate": 0.0002996831689357482,
"loss": 0.7372894287109375,
"step": 46
},
{
"epoch": 0.29936305732484075,
"grad_norm": 0.13118144869804382,
"learning_rate": 0.0002996325739276609,
"loss": 0.766143798828125,
"step": 47
},
{
"epoch": 0.3057324840764331,
"grad_norm": 0.14016607403755188,
"learning_rate": 0.0002995782381895176,
"loss": 0.7620620727539062,
"step": 48
},
{
"epoch": 0.31210191082802546,
"grad_norm": 0.1928688883781433,
"learning_rate": 0.00029952016323102235,
"loss": 0.8002471923828125,
"step": 49
},
{
"epoch": 0.3184713375796178,
"grad_norm": 0.19723062217235565,
"learning_rate": 0.0002994583506657723,
"loss": 0.763778805732727,
"step": 50
},
{
"epoch": 0.3248407643312102,
"grad_norm": 0.2530524432659149,
"learning_rate": 0.00029939280221121314,
"loss": 0.7891502380371094,
"step": 51
},
{
"epoch": 0.33121019108280253,
"grad_norm": 0.20972968637943268,
"learning_rate": 0.0002993235196885911,
"loss": 0.7976531982421875,
"step": 52
},
{
"epoch": 0.3375796178343949,
"grad_norm": 0.1319575309753418,
"learning_rate": 0.0002992505050229025,
"loss": 0.75244140625,
"step": 53
},
{
"epoch": 0.34394904458598724,
"grad_norm": 0.21391642093658447,
"learning_rate": 0.0002991737602428403,
"loss": 0.6784820556640625,
"step": 54
},
{
"epoch": 0.3503184713375796,
"grad_norm": 0.24353541433811188,
"learning_rate": 0.0002990932874807378,
"loss": 0.762359619140625,
"step": 55
},
{
"epoch": 0.35668789808917195,
"grad_norm": 0.17982617020606995,
"learning_rate": 0.0002990090889725091,
"loss": 0.690155029296875,
"step": 56
},
{
"epoch": 0.3630573248407643,
"grad_norm": 0.1485365778207779,
"learning_rate": 0.0002989211670575871,
"loss": 0.7690277099609375,
"step": 57
},
{
"epoch": 0.36942675159235666,
"grad_norm": 0.23111550509929657,
"learning_rate": 0.0002988295241788589,
"loss": 0.711944580078125,
"step": 58
},
{
"epoch": 0.37579617834394907,
"grad_norm": 0.14703889191150665,
"learning_rate": 0.00029873416288259726,
"loss": 0.7354278564453125,
"step": 59
},
{
"epoch": 0.3821656050955414,
"grad_norm": 0.21715037524700165,
"learning_rate": 0.00029863508581839027,
"loss": 0.7352346181869507,
"step": 60
},
{
"epoch": 0.3885350318471338,
"grad_norm": 0.2302205115556717,
"learning_rate": 0.00029853229573906774,
"loss": 0.7104644775390625,
"step": 61
},
{
"epoch": 0.39490445859872614,
"grad_norm": 0.14830107986927032,
"learning_rate": 0.00029842579550062447,
"loss": 0.7044873237609863,
"step": 62
},
{
"epoch": 0.4012738853503185,
"grad_norm": 0.21264120936393738,
"learning_rate": 0.00029831558806214114,
"loss": 0.7453155517578125,
"step": 63
},
{
"epoch": 0.40764331210191085,
"grad_norm": 0.17891322076320648,
"learning_rate": 0.000298201676485702,
"loss": 0.7078933715820312,
"step": 64
},
{
"epoch": 0.4140127388535032,
"grad_norm": 0.1606503278017044,
"learning_rate": 0.0002980840639363095,
"loss": 0.7210578918457031,
"step": 65
},
{
"epoch": 0.42038216560509556,
"grad_norm": 0.16794052720069885,
"learning_rate": 0.0002979627536817971,
"loss": 0.6704587936401367,
"step": 66
},
{
"epoch": 0.4267515923566879,
"grad_norm": 0.14437231421470642,
"learning_rate": 0.0002978377490927377,
"loss": 0.7686614990234375,
"step": 67
},
{
"epoch": 0.43312101910828027,
"grad_norm": 0.15216439962387085,
"learning_rate": 0.00029770905364235044,
"loss": 0.7377853393554688,
"step": 68
},
{
"epoch": 0.4394904458598726,
"grad_norm": 0.15043821930885315,
"learning_rate": 0.00029757667090640386,
"loss": 0.7062454223632812,
"step": 69
},
{
"epoch": 0.445859872611465,
"grad_norm": 0.15341544151306152,
"learning_rate": 0.0002974406045631169,
"loss": 0.7042083740234375,
"step": 70
},
{
"epoch": 0.45222929936305734,
"grad_norm": 0.14280380308628082,
"learning_rate": 0.00029730085839305663,
"loss": 0.6313236951828003,
"step": 71
},
{
"epoch": 0.4585987261146497,
"grad_norm": 0.14860248565673828,
"learning_rate": 0.00029715743627903285,
"loss": 0.7414970397949219,
"step": 72
},
{
"epoch": 0.46496815286624205,
"grad_norm": 0.15411949157714844,
"learning_rate": 0.0002970103422059907,
"loss": 0.7120361328125,
"step": 73
},
{
"epoch": 0.4713375796178344,
"grad_norm": 0.1319582611322403,
"learning_rate": 0.0002968595802608997,
"loss": 0.71319580078125,
"step": 74
},
{
"epoch": 0.47770700636942676,
"grad_norm": 0.14194566011428833,
"learning_rate": 0.0002967051546326401,
"loss": 0.7166900634765625,
"step": 75
},
{
"epoch": 0.4840764331210191,
"grad_norm": 0.15048225224018097,
"learning_rate": 0.00029654706961188676,
"loss": 0.71392822265625,
"step": 76
},
{
"epoch": 0.49044585987261147,
"grad_norm": 0.1446928232908249,
"learning_rate": 0.0002963853295909896,
"loss": 0.708343505859375,
"step": 77
},
{
"epoch": 0.4968152866242038,
"grad_norm": 0.1399853229522705,
"learning_rate": 0.0002962199390638519,
"loss": 0.690521240234375,
"step": 78
},
{
"epoch": 0.5031847133757962,
"grad_norm": 0.15705810487270355,
"learning_rate": 0.0002960509026258052,
"loss": 0.7089481353759766,
"step": 79
},
{
"epoch": 0.5095541401273885,
"grad_norm": 0.1441253274679184,
"learning_rate": 0.00029587822497348175,
"loss": 0.736480712890625,
"step": 80
},
{
"epoch": 0.5159235668789809,
"grad_norm": 0.13917307555675507,
"learning_rate": 0.0002957019109046839,
"loss": 0.69671630859375,
"step": 81
},
{
"epoch": 0.5222929936305732,
"grad_norm": 0.15637345612049103,
"learning_rate": 0.0002955219653182509,
"loss": 0.7079315185546875,
"step": 82
},
{
"epoch": 0.5286624203821656,
"grad_norm": 0.17719104886054993,
"learning_rate": 0.0002953383932139227,
"loss": 0.727935791015625,
"step": 83
},
{
"epoch": 0.535031847133758,
"grad_norm": 0.16060574352741241,
"learning_rate": 0.0002951511996922012,
"loss": 0.64898681640625,
"step": 84
},
{
"epoch": 0.5414012738853503,
"grad_norm": 0.14753378927707672,
"learning_rate": 0.0002949603899542083,
"loss": 0.6824111938476562,
"step": 85
},
{
"epoch": 0.5477707006369427,
"grad_norm": 0.14623405039310455,
"learning_rate": 0.00029476596930154143,
"loss": 0.6638870239257812,
"step": 86
},
{
"epoch": 0.554140127388535,
"grad_norm": 0.2025822550058365,
"learning_rate": 0.00029456794313612657,
"loss": 0.7407073974609375,
"step": 87
},
{
"epoch": 0.5605095541401274,
"grad_norm": 0.20111721754074097,
"learning_rate": 0.0002943663169600677,
"loss": 0.634765625,
"step": 88
},
{
"epoch": 0.5668789808917197,
"grad_norm": 0.16288472712039948,
"learning_rate": 0.0002941610963754942,
"loss": 0.7083282470703125,
"step": 89
},
{
"epoch": 0.5732484076433121,
"grad_norm": 0.1873498409986496,
"learning_rate": 0.0002939522870844051,
"loss": 0.6896438598632812,
"step": 90
},
{
"epoch": 0.5796178343949044,
"grad_norm": 0.16933931410312653,
"learning_rate": 0.00029373989488851073,
"loss": 0.7074050903320312,
"step": 91
},
{
"epoch": 0.5859872611464968,
"grad_norm": 0.1743369698524475,
"learning_rate": 0.0002935239256890714,
"loss": 0.7069091796875,
"step": 92
},
{
"epoch": 0.5923566878980892,
"grad_norm": 0.1373268961906433,
"learning_rate": 0.00029330438548673366,
"loss": 0.6788864135742188,
"step": 93
},
{
"epoch": 0.5987261146496815,
"grad_norm": 0.1815701127052307,
"learning_rate": 0.0002930812803813632,
"loss": 0.66387939453125,
"step": 94
},
{
"epoch": 0.6050955414012739,
"grad_norm": 0.17448744177818298,
"learning_rate": 0.00029285461657187564,
"loss": 0.7216981649398804,
"step": 95
},
{
"epoch": 0.6114649681528662,
"grad_norm": 0.11934467405080795,
"learning_rate": 0.00029262440035606444,
"loss": 0.6801834106445312,
"step": 96
},
{
"epoch": 0.6178343949044586,
"grad_norm": 0.16852253675460815,
"learning_rate": 0.0002923906381304256,
"loss": 0.6863555908203125,
"step": 97
},
{
"epoch": 0.6242038216560509,
"grad_norm": 0.16186685860157013,
"learning_rate": 0.00029215333638997986,
"loss": 0.6582489013671875,
"step": 98
},
{
"epoch": 0.6305732484076433,
"grad_norm": 0.18058981001377106,
"learning_rate": 0.00029191250172809274,
"loss": 0.6726799011230469,
"step": 99
},
{
"epoch": 0.6369426751592356,
"grad_norm": 0.21598166227340698,
"learning_rate": 0.0002916681408362909,
"loss": 0.6689566969871521,
"step": 100
},
{
"epoch": 0.643312101910828,
"grad_norm": 0.1937216967344284,
"learning_rate": 0.00029142026050407634,
"loss": 0.6519851684570312,
"step": 101
},
{
"epoch": 0.6496815286624203,
"grad_norm": 0.1824830025434494,
"learning_rate": 0.0002911688676187377,
"loss": 0.6694857478141785,
"step": 102
},
{
"epoch": 0.6560509554140127,
"grad_norm": 0.1829107701778412,
"learning_rate": 0.00029091396916515927,
"loss": 0.7089385986328125,
"step": 103
},
{
"epoch": 0.6624203821656051,
"grad_norm": 0.1789492815732956,
"learning_rate": 0.00029065557222562616,
"loss": 0.6807861328125,
"step": 104
},
{
"epoch": 0.6687898089171974,
"grad_norm": 0.17036959528923035,
"learning_rate": 0.00029039368397962837,
"loss": 0.6617279052734375,
"step": 105
},
{
"epoch": 0.6751592356687898,
"grad_norm": 0.1865333616733551,
"learning_rate": 0.0002901283117036607,
"loss": 0.6889495849609375,
"step": 106
},
{
"epoch": 0.6815286624203821,
"grad_norm": 0.202290877699852,
"learning_rate": 0.00028985946277102094,
"loss": 0.7136383056640625,
"step": 107
},
{
"epoch": 0.6878980891719745,
"grad_norm": 0.1646660417318344,
"learning_rate": 0.0002895871446516047,
"loss": 0.6327409744262695,
"step": 108
},
{
"epoch": 0.6942675159235668,
"grad_norm": 0.15508386492729187,
"learning_rate": 0.0002893113649116981,
"loss": 0.6970291137695312,
"step": 109
},
{
"epoch": 0.7006369426751592,
"grad_norm": 0.23790733516216278,
"learning_rate": 0.00028903213121376744,
"loss": 0.701690673828125,
"step": 110
},
{
"epoch": 0.7070063694267515,
"grad_norm": 0.23440833389759064,
"learning_rate": 0.0002887494513162464,
"loss": 0.6858749389648438,
"step": 111
},
{
"epoch": 0.7133757961783439,
"grad_norm": 0.16020652651786804,
"learning_rate": 0.0002884633330733202,
"loss": 0.679046630859375,
"step": 112
},
{
"epoch": 0.7197452229299363,
"grad_norm": 0.16401633620262146,
"learning_rate": 0.00028817378443470786,
"loss": 0.6446990966796875,
"step": 113
},
{
"epoch": 0.7261146496815286,
"grad_norm": 0.1972404420375824,
"learning_rate": 0.0002878808134454407,
"loss": 0.6556560397148132,
"step": 114
},
{
"epoch": 0.732484076433121,
"grad_norm": 0.1584540456533432,
"learning_rate": 0.0002875844282456394,
"loss": 0.6459579467773438,
"step": 115
},
{
"epoch": 0.7388535031847133,
"grad_norm": 0.1724664270877838,
"learning_rate": 0.0002872846370702874,
"loss": 0.666351318359375,
"step": 116
},
{
"epoch": 0.7452229299363057,
"grad_norm": 0.15662480890750885,
"learning_rate": 0.0002869814482490023,
"loss": 0.6523818969726562,
"step": 117
},
{
"epoch": 0.7515923566878981,
"grad_norm": 0.16173236072063446,
"learning_rate": 0.00028667487020580444,
"loss": 0.6941604614257812,
"step": 118
},
{
"epoch": 0.7579617834394905,
"grad_norm": 0.15774263441562653,
"learning_rate": 0.00028636491145888276,
"loss": 0.65179443359375,
"step": 119
},
{
"epoch": 0.7643312101910829,
"grad_norm": 0.15777266025543213,
"learning_rate": 0.00028605158062035816,
"loss": 0.5868377685546875,
"step": 120
},
{
"epoch": 0.7707006369426752,
"grad_norm": 0.14408300817012787,
"learning_rate": 0.00028573488639604413,
"loss": 0.6986846923828125,
"step": 121
},
{
"epoch": 0.7770700636942676,
"grad_norm": 0.16124875843524933,
"learning_rate": 0.000285414837585205,
"loss": 0.6715621948242188,
"step": 122
},
{
"epoch": 0.7834394904458599,
"grad_norm": 0.15004760026931763,
"learning_rate": 0.0002850914430803114,
"loss": 0.6120376586914062,
"step": 123
},
{
"epoch": 0.7898089171974523,
"grad_norm": 0.17481908202171326,
"learning_rate": 0.0002847647118667931,
"loss": 0.680206298828125,
"step": 124
},
{
"epoch": 0.7961783439490446,
"grad_norm": 0.1774885207414627,
"learning_rate": 0.0002844346530227895,
"loss": 0.66265869140625,
"step": 125
},
{
"epoch": 0.802547770700637,
"grad_norm": 0.18009056150913239,
"learning_rate": 0.0002841012757188973,
"loss": 0.6852645874023438,
"step": 126
},
{
"epoch": 0.8089171974522293,
"grad_norm": 0.19692178070545197,
"learning_rate": 0.00028376458921791577,
"loss": 0.616912841796875,
"step": 127
},
{
"epoch": 0.8152866242038217,
"grad_norm": 0.21690639853477478,
"learning_rate": 0.0002834246028745892,
"loss": 0.6993408203125,
"step": 128
},
{
"epoch": 0.8152866242038217,
"eval_loss": 0.625178337097168,
"eval_runtime": 5.1564,
"eval_samples_per_second": 1.358,
"eval_steps_per_second": 0.194,
"step": 128
},
{
"epoch": 0.821656050955414,
"grad_norm": 0.19200018048286438,
"learning_rate": 0.00028308132613534716,
"loss": 0.6799163818359375,
"step": 129
},
{
"epoch": 0.8280254777070064,
"grad_norm": 0.18255098164081573,
"learning_rate": 0.0002827347685380422,
"loss": 0.62457275390625,
"step": 130
},
{
"epoch": 0.8343949044585988,
"grad_norm": 0.15668107569217682,
"learning_rate": 0.00028238493971168433,
"loss": 0.6515045166015625,
"step": 131
},
{
"epoch": 0.8407643312101911,
"grad_norm": 0.16620191931724548,
"learning_rate": 0.00028203184937617397,
"loss": 0.6193771362304688,
"step": 132
},
{
"epoch": 0.8471337579617835,
"grad_norm": 0.18261539936065674,
"learning_rate": 0.0002816755073420317,
"loss": 0.716033935546875,
"step": 133
},
{
"epoch": 0.8535031847133758,
"grad_norm": 0.1520560085773468,
"learning_rate": 0.00028131592351012555,
"loss": 0.6133193969726562,
"step": 134
},
{
"epoch": 0.8598726114649682,
"grad_norm": 0.16571491956710815,
"learning_rate": 0.00028095310787139613,
"loss": 0.6478843688964844,
"step": 135
},
{
"epoch": 0.8662420382165605,
"grad_norm": 0.17786805331707,
"learning_rate": 0.0002805870705065789,
"loss": 0.6279449462890625,
"step": 136
},
{
"epoch": 0.8726114649681529,
"grad_norm": 0.13904328644275665,
"learning_rate": 0.0002802178215859241,
"loss": 0.671142578125,
"step": 137
},
{
"epoch": 0.8789808917197452,
"grad_norm": 0.14942413568496704,
"learning_rate": 0.0002798453713689144,
"loss": 0.5923829674720764,
"step": 138
},
{
"epoch": 0.8853503184713376,
"grad_norm": 0.16308893263339996,
"learning_rate": 0.00027946973020397933,
"loss": 0.6803417205810547,
"step": 139
},
{
"epoch": 0.89171974522293,
"grad_norm": 0.1690857857465744,
"learning_rate": 0.00027909090852820814,
"loss": 0.6681976318359375,
"step": 140
},
{
"epoch": 0.8980891719745223,
"grad_norm": 0.15127228200435638,
"learning_rate": 0.0002787089168670598,
"loss": 0.65283203125,
"step": 141
},
{
"epoch": 0.9044585987261147,
"grad_norm": 0.15152615308761597,
"learning_rate": 0.0002783237658340705,
"loss": 0.6745452880859375,
"step": 142
},
{
"epoch": 0.910828025477707,
"grad_norm": 0.18258291482925415,
"learning_rate": 0.0002779354661305586,
"loss": 0.631072998046875,
"step": 143
},
{
"epoch": 0.9171974522292994,
"grad_norm": 0.18597263097763062,
"learning_rate": 0.0002775440285453276,
"loss": 0.705718994140625,
"step": 144
},
{
"epoch": 0.9235668789808917,
"grad_norm": 0.17591795325279236,
"learning_rate": 0.000277149463954366,
"loss": 0.6915283203125,
"step": 145
},
{
"epoch": 0.9299363057324841,
"grad_norm": 0.17014524340629578,
"learning_rate": 0.0002767517833205455,
"loss": 0.6183319091796875,
"step": 146
},
{
"epoch": 0.9363057324840764,
"grad_norm": 0.18762874603271484,
"learning_rate": 0.00027635099769331617,
"loss": 0.6309661865234375,
"step": 147
},
{
"epoch": 0.9426751592356688,
"grad_norm": 0.19945642352104187,
"learning_rate": 0.0002759471182083993,
"loss": 0.6492996215820312,
"step": 148
},
{
"epoch": 0.9490445859872612,
"grad_norm": 0.15386110544204712,
"learning_rate": 0.00027554015608747845,
"loss": 0.6570892333984375,
"step": 149
},
{
"epoch": 0.9554140127388535,
"grad_norm": 0.1597049981355667,
"learning_rate": 0.00027513012263788737,
"loss": 0.6250181198120117,
"step": 150
},
{
"epoch": 0.9617834394904459,
"grad_norm": 0.1697262078523636,
"learning_rate": 0.0002747170292522957,
"loss": 0.6492233276367188,
"step": 151
},
{
"epoch": 0.9681528662420382,
"grad_norm": 0.16555513441562653,
"learning_rate": 0.0002743008874083927,
"loss": 0.6356735229492188,
"step": 152
},
{
"epoch": 0.9745222929936306,
"grad_norm": 0.16877028346061707,
"learning_rate": 0.0002738817086685681,
"loss": 0.6483078002929688,
"step": 153
},
{
"epoch": 0.9808917197452229,
"grad_norm": 0.15073354542255402,
"learning_rate": 0.00027345950467959123,
"loss": 0.6661834716796875,
"step": 154
},
{
"epoch": 0.9872611464968153,
"grad_norm": 0.1822793185710907,
"learning_rate": 0.0002730342871722869,
"loss": 0.6563186645507812,
"step": 155
},
{
"epoch": 0.9936305732484076,
"grad_norm": 0.19067645072937012,
"learning_rate": 0.00027260606796120974,
"loss": 0.6632080078125,
"step": 156
},
{
"epoch": 1.0,
"grad_norm": 0.20216046273708344,
"learning_rate": 0.0002721748589443162,
"loss": 0.6433029174804688,
"step": 157
},
{
"epoch": 1.0063694267515924,
"grad_norm": 0.20415550470352173,
"learning_rate": 0.0002717406721026333,
"loss": 0.661224365234375,
"step": 158
},
{
"epoch": 1.0127388535031847,
"grad_norm": 0.20491866767406464,
"learning_rate": 0.0002713035194999264,
"loss": 0.64361572265625,
"step": 159
},
{
"epoch": 1.019108280254777,
"grad_norm": 0.24666599929332733,
"learning_rate": 0.00027086341328236356,
"loss": 0.692962646484375,
"step": 160
},
{
"epoch": 1.0254777070063694,
"grad_norm": 0.32244184613227844,
"learning_rate": 0.00027042036567817833,
"loss": 0.6512019038200378,
"step": 161
},
{
"epoch": 1.0318471337579618,
"grad_norm": 0.1902998685836792,
"learning_rate": 0.00026997438899733,
"loss": 0.650390625,
"step": 162
},
{
"epoch": 1.0382165605095541,
"grad_norm": 0.32200613617897034,
"learning_rate": 0.0002695254956311612,
"loss": 0.63275146484375,
"step": 163
},
{
"epoch": 1.0445859872611465,
"grad_norm": 0.2785264551639557,
"learning_rate": 0.00026907369805205414,
"loss": 0.6525421142578125,
"step": 164
},
{
"epoch": 1.0509554140127388,
"grad_norm": 0.22845248878002167,
"learning_rate": 0.0002686190088130837,
"loss": 0.6388189792633057,
"step": 165
},
{
"epoch": 1.0573248407643312,
"grad_norm": 0.15489083528518677,
"learning_rate": 0.0002681614405476688,
"loss": 0.560907781124115,
"step": 166
},
{
"epoch": 1.0636942675159236,
"grad_norm": 0.240184023976326,
"learning_rate": 0.0002677010059692212,
"loss": 0.6396026611328125,
"step": 167
},
{
"epoch": 1.070063694267516,
"grad_norm": 0.18049825727939606,
"learning_rate": 0.00026723771787079257,
"loss": 0.6528244018554688,
"step": 168
},
{
"epoch": 1.0764331210191083,
"grad_norm": 0.21166716516017914,
"learning_rate": 0.00026677158912471885,
"loss": 0.6523818969726562,
"step": 169
},
{
"epoch": 1.0828025477707006,
"grad_norm": 0.16770559549331665,
"learning_rate": 0.0002663026326822625,
"loss": 0.6259078979492188,
"step": 170
},
{
"epoch": 1.089171974522293,
"grad_norm": 0.25956252217292786,
"learning_rate": 0.0002658308615732529,
"loss": 0.6496734619140625,
"step": 171
},
{
"epoch": 1.0955414012738853,
"grad_norm": 0.2225719392299652,
"learning_rate": 0.00026535628890572406,
"loss": 0.6060581207275391,
"step": 172
},
{
"epoch": 1.1019108280254777,
"grad_norm": 0.16161081194877625,
"learning_rate": 0.0002648789278655507,
"loss": 0.6301555633544922,
"step": 173
},
{
"epoch": 1.10828025477707,
"grad_norm": 0.21734708547592163,
"learning_rate": 0.0002643987917160816,
"loss": 0.6493682861328125,
"step": 174
},
{
"epoch": 1.1146496815286624,
"grad_norm": 0.2155102640390396,
"learning_rate": 0.00026391589379777113,
"loss": 0.6637420654296875,
"step": 175
},
{
"epoch": 1.1210191082802548,
"grad_norm": 0.1549050211906433,
"learning_rate": 0.000263430247527809,
"loss": 0.6118888854980469,
"step": 176
},
{
"epoch": 1.127388535031847,
"grad_norm": 0.20176313817501068,
"learning_rate": 0.0002629418663997468,
"loss": 0.6287612915039062,
"step": 177
},
{
"epoch": 1.1337579617834395,
"grad_norm": 0.1534535437822342,
"learning_rate": 0.00026245076398312357,
"loss": 0.6375274658203125,
"step": 178
},
{
"epoch": 1.1401273885350318,
"grad_norm": 0.20006686449050903,
"learning_rate": 0.0002619569539230886,
"loss": 0.674957275390625,
"step": 179
},
{
"epoch": 1.1464968152866242,
"grad_norm": 0.19811393320560455,
"learning_rate": 0.0002614604499400223,
"loss": 0.6589202880859375,
"step": 180
},
{
"epoch": 1.1528662420382165,
"grad_norm": 0.1498415470123291,
"learning_rate": 0.00026096126582915506,
"loss": 0.6719207763671875,
"step": 181
},
{
"epoch": 1.1592356687898089,
"grad_norm": 0.16239678859710693,
"learning_rate": 0.0002604594154601839,
"loss": 0.68951416015625,
"step": 182
},
{
"epoch": 1.1656050955414012,
"grad_norm": 0.17865270376205444,
"learning_rate": 0.000259954912776887,
"loss": 0.620361328125,
"step": 183
},
{
"epoch": 1.1719745222929936,
"grad_norm": 0.14013227820396423,
"learning_rate": 0.00025944777179673665,
"loss": 0.6212310791015625,
"step": 184
},
{
"epoch": 1.178343949044586,
"grad_norm": 0.16241267323493958,
"learning_rate": 0.0002589380066105092,
"loss": 0.589996337890625,
"step": 185
},
{
"epoch": 1.1847133757961783,
"grad_norm": 0.1710585206747055,
"learning_rate": 0.000258425631381894,
"loss": 0.6775665283203125,
"step": 186
},
{
"epoch": 1.1910828025477707,
"grad_norm": 0.1798485517501831,
"learning_rate": 0.00025791066034709973,
"loss": 0.648040771484375,
"step": 187
},
{
"epoch": 1.197452229299363,
"grad_norm": 0.15924791991710663,
"learning_rate": 0.00025739310781445893,
"loss": 0.6225627064704895,
"step": 188
},
{
"epoch": 1.2038216560509554,
"grad_norm": 0.16327159106731415,
"learning_rate": 0.00025687298816403026,
"loss": 0.6130561828613281,
"step": 189
},
{
"epoch": 1.2101910828025477,
"grad_norm": 0.16096395254135132,
"learning_rate": 0.00025635031584719906,
"loss": 0.6268157958984375,
"step": 190
},
{
"epoch": 1.21656050955414,
"grad_norm": 0.17933563888072968,
"learning_rate": 0.0002558251053862758,
"loss": 0.67047119140625,
"step": 191
},
{
"epoch": 1.2229299363057324,
"grad_norm": 0.17421014606952667,
"learning_rate": 0.0002552973713740928,
"loss": 0.655426025390625,
"step": 192
},
{
"epoch": 1.2292993630573248,
"grad_norm": 0.16427214443683624,
"learning_rate": 0.00025476712847359833,
"loss": 0.6179428100585938,
"step": 193
},
{
"epoch": 1.2356687898089171,
"grad_norm": 0.15724951028823853,
"learning_rate": 0.0002542343914174495,
"loss": 0.6687164306640625,
"step": 194
},
{
"epoch": 1.2420382165605095,
"grad_norm": 0.17414623498916626,
"learning_rate": 0.0002536991750076031,
"loss": 0.6523513793945312,
"step": 195
},
{
"epoch": 1.2484076433121019,
"grad_norm": 0.1557365208864212,
"learning_rate": 0.00025316149411490373,
"loss": 0.5996551513671875,
"step": 196
},
{
"epoch": 1.2547770700636942,
"grad_norm": 0.16637009382247925,
"learning_rate": 0.00025262136367867134,
"loss": 0.67279052734375,
"step": 197
},
{
"epoch": 1.2611464968152866,
"grad_norm": 0.15756922960281372,
"learning_rate": 0.0002520787987062855,
"loss": 0.6026104092597961,
"step": 198
},
{
"epoch": 1.267515923566879,
"grad_norm": 0.16710138320922852,
"learning_rate": 0.00025153381427276897,
"loss": 0.647674560546875,
"step": 199
},
{
"epoch": 1.2738853503184713,
"grad_norm": 0.2063302844762802,
"learning_rate": 0.0002509864255203683,
"loss": 0.6123275756835938,
"step": 200
},
{
"epoch": 1.2802547770700636,
"grad_norm": 0.15705372393131256,
"learning_rate": 0.00025043664765813376,
"loss": 0.65216064453125,
"step": 201
},
{
"epoch": 1.286624203821656,
"grad_norm": 0.21855668723583221,
"learning_rate": 0.000249884495961496,
"loss": 0.627685546875,
"step": 202
},
{
"epoch": 1.2929936305732483,
"grad_norm": 0.17062272131443024,
"learning_rate": 0.0002493299857718424,
"loss": 0.608642578125,
"step": 203
},
{
"epoch": 1.2993630573248407,
"grad_norm": 0.18182472884655,
"learning_rate": 0.0002487731324960902,
"loss": 0.635772705078125,
"step": 204
},
{
"epoch": 1.305732484076433,
"grad_norm": 0.13383693993091583,
"learning_rate": 0.0002482139516062587,
"loss": 0.6383590698242188,
"step": 205
},
{
"epoch": 1.3121019108280254,
"grad_norm": 0.20367072522640228,
"learning_rate": 0.00024765245863903935,
"loss": 0.6681289672851562,
"step": 206
},
{
"epoch": 1.3184713375796178,
"grad_norm": 0.19795936346054077,
"learning_rate": 0.0002470886691953641,
"loss": 0.6422876715660095,
"step": 207
},
{
"epoch": 1.3248407643312101,
"grad_norm": 0.1474784016609192,
"learning_rate": 0.0002465225989399718,
"loss": 0.6637172698974609,
"step": 208
},
{
"epoch": 1.3312101910828025,
"grad_norm": 0.17597341537475586,
"learning_rate": 0.00024595426360097313,
"loss": 0.6754150390625,
"step": 209
},
{
"epoch": 1.3375796178343948,
"grad_norm": 0.1631416231393814,
"learning_rate": 0.00024538367896941347,
"loss": 0.6419448852539062,
"step": 210
},
{
"epoch": 1.3439490445859872,
"grad_norm": 0.14731177687644958,
"learning_rate": 0.00024481086089883414,
"loss": 0.5760650634765625,
"step": 211
},
{
"epoch": 1.3503184713375795,
"grad_norm": 0.16709047555923462,
"learning_rate": 0.00024423582530483205,
"loss": 0.650238037109375,
"step": 212
},
{
"epoch": 1.356687898089172,
"grad_norm": 0.16625934839248657,
"learning_rate": 0.00024365858816461736,
"loss": 0.588653564453125,
"step": 213
},
{
"epoch": 1.3630573248407643,
"grad_norm": 0.1398966759443283,
"learning_rate": 0.00024307916551656966,
"loss": 0.6564788818359375,
"step": 214
},
{
"epoch": 1.3694267515923566,
"grad_norm": 0.19118323922157288,
"learning_rate": 0.0002424975734597922,
"loss": 0.6109161376953125,
"step": 215
},
{
"epoch": 1.3757961783439492,
"grad_norm": 0.14986611902713776,
"learning_rate": 0.00024191382815366474,
"loss": 0.6364288330078125,
"step": 216
},
{
"epoch": 1.3821656050955413,
"grad_norm": 0.16663117706775665,
"learning_rate": 0.00024132794581739443,
"loss": 0.6324023008346558,
"step": 217
},
{
"epoch": 1.388535031847134,
"grad_norm": 0.17351657152175903,
"learning_rate": 0.00024073994272956535,
"loss": 0.6137542724609375,
"step": 218
},
{
"epoch": 1.394904458598726,
"grad_norm": 0.15778033435344696,
"learning_rate": 0.00024014983522768592,
"loss": 0.612584114074707,
"step": 219
},
{
"epoch": 1.4012738853503186,
"grad_norm": 0.1440693587064743,
"learning_rate": 0.00023955763970773535,
"loss": 0.6462860107421875,
"step": 220
},
{
"epoch": 1.4076433121019107,
"grad_norm": 0.20289096236228943,
"learning_rate": 0.0002389633726237077,
"loss": 0.6184577941894531,
"step": 221
},
{
"epoch": 1.4140127388535033,
"grad_norm": 0.1419222205877304,
"learning_rate": 0.00023836705048715497,
"loss": 0.6309700012207031,
"step": 222
},
{
"epoch": 1.4203821656050954,
"grad_norm": 0.1610637605190277,
"learning_rate": 0.00023776868986672824,
"loss": 0.5894508361816406,
"step": 223
},
{
"epoch": 1.426751592356688,
"grad_norm": 0.17762811481952667,
"learning_rate": 0.00023716830738771723,
"loss": 0.67620849609375,
"step": 224
},
{
"epoch": 1.4331210191082802,
"grad_norm": 0.16079476475715637,
"learning_rate": 0.00023656591973158863,
"loss": 0.649200439453125,
"step": 225
},
{
"epoch": 1.4394904458598727,
"grad_norm": 0.1589500606060028,
"learning_rate": 0.00023596154363552223,
"loss": 0.6236190795898438,
"step": 226
},
{
"epoch": 1.4458598726114649,
"grad_norm": 0.17183391749858856,
"learning_rate": 0.00023535519589194633,
"loss": 0.6195526123046875,
"step": 227
},
{
"epoch": 1.4522292993630574,
"grad_norm": 0.15588346123695374,
"learning_rate": 0.0002347468933480707,
"loss": 0.555402934551239,
"step": 228
},
{
"epoch": 1.4585987261146496,
"grad_norm": 0.17502474784851074,
"learning_rate": 0.00023413665290541888,
"loss": 0.6602363586425781,
"step": 229
},
{
"epoch": 1.4649681528662422,
"grad_norm": 0.1537683606147766,
"learning_rate": 0.00023352449151935835,
"loss": 0.6325912475585938,
"step": 230
},
{
"epoch": 1.4713375796178343,
"grad_norm": 0.14733198285102844,
"learning_rate": 0.00023291042619862944,
"loss": 0.6312789916992188,
"step": 231
},
{
"epoch": 1.4777070063694269,
"grad_norm": 0.16659300029277802,
"learning_rate": 0.00023229447400487286,
"loss": 0.6383056640625,
"step": 232
},
{
"epoch": 1.484076433121019,
"grad_norm": 0.15981443226337433,
"learning_rate": 0.00023167665205215557,
"loss": 0.6361083984375,
"step": 233
},
{
"epoch": 1.4904458598726116,
"grad_norm": 0.14432771503925323,
"learning_rate": 0.00023105697750649525,
"loss": 0.6328048706054688,
"step": 234
},
{
"epoch": 1.4968152866242037,
"grad_norm": 0.16135050356388092,
"learning_rate": 0.00023043546758538342,
"loss": 0.615264892578125,
"step": 235
},
{
"epoch": 1.5031847133757963,
"grad_norm": 0.15096795558929443,
"learning_rate": 0.00022981213955730704,
"loss": 0.6353673934936523,
"step": 236
},
{
"epoch": 1.5095541401273884,
"grad_norm": 0.15556974709033966,
"learning_rate": 0.00022918701074126855,
"loss": 0.6591110229492188,
"step": 237
},
{
"epoch": 1.515923566878981,
"grad_norm": 0.15300650894641876,
"learning_rate": 0.000228560098506305,
"loss": 0.6254730224609375,
"step": 238
},
{
"epoch": 1.5222929936305731,
"grad_norm": 0.15529441833496094,
"learning_rate": 0.0002279314202710051,
"loss": 0.6338958740234375,
"step": 239
},
{
"epoch": 1.5286624203821657,
"grad_norm": 0.18279969692230225,
"learning_rate": 0.00022730099350302548,
"loss": 0.65325927734375,
"step": 240
},
{
"epoch": 1.5350318471337578,
"grad_norm": 0.14814990758895874,
"learning_rate": 0.00022666883571860526,
"loss": 0.5859298706054688,
"step": 241
},
{
"epoch": 1.5414012738853504,
"grad_norm": 0.15196703374385834,
"learning_rate": 0.0002260349644820794,
"loss": 0.6161880493164062,
"step": 242
},
{
"epoch": 1.5477707006369426,
"grad_norm": 0.17276117205619812,
"learning_rate": 0.00022539939740539065,
"loss": 0.5977249145507812,
"step": 243
},
{
"epoch": 1.5541401273885351,
"grad_norm": 0.15233942866325378,
"learning_rate": 0.00022476215214760025,
"loss": 0.669281005859375,
"step": 244
},
{
"epoch": 1.5605095541401273,
"grad_norm": 0.18915025889873505,
"learning_rate": 0.00022412324641439722,
"loss": 0.5711135864257812,
"step": 245
},
{
"epoch": 1.5668789808917198,
"grad_norm": 0.1521741896867752,
"learning_rate": 0.0002234826979576065,
"loss": 0.641693115234375,
"step": 246
},
{
"epoch": 1.573248407643312,
"grad_norm": 0.15510298311710358,
"learning_rate": 0.00022284052457469564,
"loss": 0.6270751953125,
"step": 247
},
{
"epoch": 1.5796178343949046,
"grad_norm": 0.1505296230316162,
"learning_rate": 0.00022219674410828025,
"loss": 0.6423721313476562,
"step": 248
},
{
"epoch": 1.5859872611464967,
"grad_norm": 0.1408831775188446,
"learning_rate": 0.00022155137444562848,
"loss": 0.6417388916015625,
"step": 249
},
{
"epoch": 1.5923566878980893,
"grad_norm": 0.15832287073135376,
"learning_rate": 0.00022090443351816373,
"loss": 0.6193008422851562,
"step": 250
},
{
"epoch": 1.5987261146496814,
"grad_norm": 0.14355872571468353,
"learning_rate": 0.0002202559393009667,
"loss": 0.6025390625,
"step": 251
},
{
"epoch": 1.605095541401274,
"grad_norm": 0.1357271373271942,
"learning_rate": 0.00021960590981227562,
"loss": 0.6609556674957275,
"step": 252
},
{
"epoch": 1.611464968152866,
"grad_norm": 0.15550976991653442,
"learning_rate": 0.00021895436311298604,
"loss": 0.6230010986328125,
"step": 253
},
{
"epoch": 1.611464968152866,
"eval_loss": 0.5900869369506836,
"eval_runtime": 5.1837,
"eval_samples_per_second": 1.35,
"eval_steps_per_second": 0.193,
"step": 253
},
{
"epoch": 1.6178343949044587,
"grad_norm": 0.12509049475193024,
"learning_rate": 0.00021830131730614884,
"loss": 0.62567138671875,
"step": 254
},
{
"epoch": 1.6242038216560508,
"grad_norm": 0.15892687439918518,
"learning_rate": 0.00021764679053646696,
"loss": 0.6007156372070312,
"step": 255
},
{
"epoch": 1.6305732484076434,
"grad_norm": 0.1622859388589859,
"learning_rate": 0.00021699080098979166,
"loss": 0.6144866943359375,
"step": 256
},
{
"epoch": 1.6369426751592355,
"grad_norm": 0.13958607614040375,
"learning_rate": 0.000216333366892617,
"loss": 0.6100319623947144,
"step": 257
},
{
"epoch": 1.643312101910828,
"grad_norm": 0.1441088318824768,
"learning_rate": 0.00021567450651157363,
"loss": 0.5937881469726562,
"step": 258
},
{
"epoch": 1.6496815286624202,
"grad_norm": 0.16021880507469177,
"learning_rate": 0.00021501423815292086,
"loss": 0.6115703582763672,
"step": 259
},
{
"epoch": 1.6560509554140128,
"grad_norm": 0.1472783386707306,
"learning_rate": 0.00021435258016203857,
"loss": 0.6496505737304688,
"step": 260
},
{
"epoch": 1.662420382165605,
"grad_norm": 0.17307592928409576,
"learning_rate": 0.00021368955092291702,
"loss": 0.6234130859375,
"step": 261
},
{
"epoch": 1.6687898089171975,
"grad_norm": 0.1658814400434494,
"learning_rate": 0.00021302516885764617,
"loss": 0.6092605590820312,
"step": 262
},
{
"epoch": 1.6751592356687897,
"grad_norm": 0.15254062414169312,
"learning_rate": 0.0002123594524259041,
"loss": 0.6340408325195312,
"step": 263
},
{
"epoch": 1.6815286624203822,
"grad_norm": 0.1353813260793686,
"learning_rate": 0.00021169242012444378,
"loss": 0.6559906005859375,
"step": 264
},
{
"epoch": 1.6878980891719744,
"grad_norm": 0.5001475214958191,
"learning_rate": 0.0002110240904865794,
"loss": 0.5894927978515625,
"step": 265
},
{
"epoch": 1.694267515923567,
"grad_norm": 0.1378307044506073,
"learning_rate": 0.00021035448208167097,
"loss": 0.64129638671875,
"step": 266
},
{
"epoch": 1.700636942675159,
"grad_norm": 0.1760307401418686,
"learning_rate": 0.0002096836135146091,
"loss": 0.6464385986328125,
"step": 267
},
{
"epoch": 1.7070063694267517,
"grad_norm": 0.16313396394252777,
"learning_rate": 0.00020901150342529743,
"loss": 0.6322708129882812,
"step": 268
},
{
"epoch": 1.7133757961783438,
"grad_norm": 0.13738258183002472,
"learning_rate": 0.00020833817048813497,
"loss": 0.626708984375,
"step": 269
},
{
"epoch": 1.7197452229299364,
"grad_norm": 0.14409485459327698,
"learning_rate": 0.00020766363341149737,
"loss": 0.5970230102539062,
"step": 270
},
{
"epoch": 1.7261146496815285,
"grad_norm": 0.13851188123226166,
"learning_rate": 0.0002069879109372168,
"loss": 0.6066164374351501,
"step": 271
},
{
"epoch": 1.732484076433121,
"grad_norm": 0.17065368592739105,
"learning_rate": 0.00020631102184006148,
"loss": 0.5987091064453125,
"step": 272
},
{
"epoch": 1.7388535031847132,
"grad_norm": 0.14199481904506683,
"learning_rate": 0.000205632984927214,
"loss": 0.6181182861328125,
"step": 273
},
{
"epoch": 1.7452229299363058,
"grad_norm": 0.14062167704105377,
"learning_rate": 0.00020495381903774858,
"loss": 0.6045913696289062,
"step": 274
},
{
"epoch": 1.7515923566878981,
"grad_norm": 0.15250955522060394,
"learning_rate": 0.00020427354304210777,
"loss": 0.6445999145507812,
"step": 275
},
{
"epoch": 1.7579617834394905,
"grad_norm": 0.135915145277977,
"learning_rate": 0.00020359217584157814,
"loss": 0.6047210693359375,
"step": 276
},
{
"epoch": 1.7643312101910829,
"grad_norm": 0.1516093909740448,
"learning_rate": 0.00020290973636776522,
"loss": 0.5416183471679688,
"step": 277
},
{
"epoch": 1.7707006369426752,
"grad_norm": 0.13762444257736206,
"learning_rate": 0.00020222624358206715,
"loss": 0.6499557495117188,
"step": 278
},
{
"epoch": 1.7770700636942676,
"grad_norm": 0.1687590777873993,
"learning_rate": 0.00020154171647514819,
"loss": 0.6241416931152344,
"step": 279
},
{
"epoch": 1.78343949044586,
"grad_norm": 0.13251566886901855,
"learning_rate": 0.00020085617406641093,
"loss": 0.5679702758789062,
"step": 280
},
{
"epoch": 1.7898089171974523,
"grad_norm": 0.18555431067943573,
"learning_rate": 0.0002001696354034678,
"loss": 0.6333160400390625,
"step": 281
},
{
"epoch": 1.7961783439490446,
"grad_norm": 0.163770392537117,
"learning_rate": 0.00019948211956161198,
"loss": 0.6170425415039062,
"step": 282
},
{
"epoch": 1.802547770700637,
"grad_norm": 0.1443757861852646,
"learning_rate": 0.00019879364564328716,
"loss": 0.6390304565429688,
"step": 283
},
{
"epoch": 1.8089171974522293,
"grad_norm": 0.18300768733024597,
"learning_rate": 0.00019810423277755713,
"loss": 0.5726242065429688,
"step": 284
},
{
"epoch": 1.8152866242038217,
"grad_norm": 0.25472450256347656,
"learning_rate": 0.0001974139001195738,
"loss": 0.6520233154296875,
"step": 285
},
{
"epoch": 1.821656050955414,
"grad_norm": 0.1797504425048828,
"learning_rate": 0.00019672266685004554,
"loss": 0.63482666015625,
"step": 286
},
{
"epoch": 1.8280254777070064,
"grad_norm": 0.1460057497024536,
"learning_rate": 0.00019603055217470386,
"loss": 0.58258056640625,
"step": 287
},
{
"epoch": 1.8343949044585988,
"grad_norm": 0.17790237069129944,
"learning_rate": 0.00019533757532376987,
"loss": 0.6085662841796875,
"step": 288
},
{
"epoch": 1.8407643312101911,
"grad_norm": 0.1574649214744568,
"learning_rate": 0.00019464375555141997,
"loss": 0.5794677734375,
"step": 289
},
{
"epoch": 1.8471337579617835,
"grad_norm": 0.1627805233001709,
"learning_rate": 0.00019394911213525105,
"loss": 0.6710968017578125,
"step": 290
},
{
"epoch": 1.8535031847133758,
"grad_norm": 0.21751517057418823,
"learning_rate": 0.00019325366437574455,
"loss": 0.5721969604492188,
"step": 291
},
{
"epoch": 1.8598726114649682,
"grad_norm": 0.15928682684898376,
"learning_rate": 0.0001925574315957305,
"loss": 0.6056976318359375,
"step": 292
},
{
"epoch": 1.8662420382165605,
"grad_norm": 0.1812126487493515,
"learning_rate": 0.00019186043313985045,
"loss": 0.5887527465820312,
"step": 293
},
{
"epoch": 1.872611464968153,
"grad_norm": 0.17961861193180084,
"learning_rate": 0.00019116268837402004,
"loss": 0.6293563842773438,
"step": 294
},
{
"epoch": 1.8789808917197452,
"grad_norm": 0.15108637511730194,
"learning_rate": 0.00019046421668489108,
"loss": 0.5540173053741455,
"step": 295
},
{
"epoch": 1.8853503184713376,
"grad_norm": 0.1601364016532898,
"learning_rate": 0.00018976503747931246,
"loss": 0.6377696990966797,
"step": 296
},
{
"epoch": 1.89171974522293,
"grad_norm": 0.1697910875082016,
"learning_rate": 0.00018906517018379146,
"loss": 0.626739501953125,
"step": 297
},
{
"epoch": 1.8980891719745223,
"grad_norm": 0.16207434237003326,
"learning_rate": 0.00018836463424395377,
"loss": 0.61199951171875,
"step": 298
},
{
"epoch": 1.9044585987261147,
"grad_norm": 0.15888185799121857,
"learning_rate": 0.000187663449124003,
"loss": 0.634674072265625,
"step": 299
},
{
"epoch": 1.910828025477707,
"grad_norm": 0.1611338108778,
"learning_rate": 0.0001869616343061802,
"loss": 0.5905838012695312,
"step": 300
},
{
"epoch": 1.9171974522292994,
"grad_norm": 0.1578240692615509,
"learning_rate": 0.0001862592092902224,
"loss": 0.663848876953125,
"step": 301
},
{
"epoch": 1.9235668789808917,
"grad_norm": 0.14625748991966248,
"learning_rate": 0.00018555619359282075,
"loss": 0.6492919921875,
"step": 302
},
{
"epoch": 1.929936305732484,
"grad_norm": 0.1636236310005188,
"learning_rate": 0.0001848526067470783,
"loss": 0.580963134765625,
"step": 303
},
{
"epoch": 1.9363057324840764,
"grad_norm": 0.1456744521856308,
"learning_rate": 0.00018414846830196752,
"loss": 0.59246826171875,
"step": 304
},
{
"epoch": 1.9426751592356688,
"grad_norm": 0.15369905531406403,
"learning_rate": 0.00018344379782178662,
"loss": 0.6107025146484375,
"step": 305
},
{
"epoch": 1.9490445859872612,
"grad_norm": 0.14822807908058167,
"learning_rate": 0.00018273861488561646,
"loss": 0.6185531616210938,
"step": 306
},
{
"epoch": 1.9554140127388535,
"grad_norm": 0.14125721156597137,
"learning_rate": 0.00018203293908677638,
"loss": 0.587641716003418,
"step": 307
},
{
"epoch": 1.9617834394904459,
"grad_norm": 0.14938753843307495,
"learning_rate": 0.00018132679003227963,
"loss": 0.6090621948242188,
"step": 308
},
{
"epoch": 1.9681528662420382,
"grad_norm": 0.14207591116428375,
"learning_rate": 0.00018062018734228875,
"loss": 0.5969982147216797,
"step": 309
},
{
"epoch": 1.9745222929936306,
"grad_norm": 0.1655084788799286,
"learning_rate": 0.00017991315064957061,
"loss": 0.610321044921875,
"step": 310
},
{
"epoch": 1.980891719745223,
"grad_norm": 0.13867656886577606,
"learning_rate": 0.00017920569959895056,
"loss": 0.6256332397460938,
"step": 311
},
{
"epoch": 1.9872611464968153,
"grad_norm": 0.17831102013587952,
"learning_rate": 0.0001784978538467668,
"loss": 0.6173477172851562,
"step": 312
},
{
"epoch": 1.9936305732484076,
"grad_norm": 0.16402319073677063,
"learning_rate": 0.00017778963306032422,
"loss": 0.6257781982421875,
"step": 313
},
{
"epoch": 2.0,
"grad_norm": 0.1474248766899109,
"learning_rate": 0.00017708105691734794,
"loss": 0.6040725708007812,
"step": 314
},
{
"epoch": 2.0063694267515926,
"grad_norm": 0.16666553914546967,
"learning_rate": 0.00017637214510543662,
"loss": 0.62261962890625,
"step": 315
},
{
"epoch": 2.0127388535031847,
"grad_norm": 0.13688898086547852,
"learning_rate": 0.00017566291732151523,
"loss": 0.6058807373046875,
"step": 316
},
{
"epoch": 2.0191082802547773,
"grad_norm": 0.16342148184776306,
"learning_rate": 0.00017495339327128816,
"loss": 0.6531524658203125,
"step": 317
},
{
"epoch": 2.0254777070063694,
"grad_norm": 0.14896409213542938,
"learning_rate": 0.0001742435926686913,
"loss": 0.6147195100784302,
"step": 318
},
{
"epoch": 2.031847133757962,
"grad_norm": 0.16723397374153137,
"learning_rate": 0.00017353353523534456,
"loss": 0.61248779296875,
"step": 319
},
{
"epoch": 2.038216560509554,
"grad_norm": 0.15467697381973267,
"learning_rate": 0.00017282324070000383,
"loss": 0.5927352905273438,
"step": 320
},
{
"epoch": 2.0445859872611467,
"grad_norm": 0.16649837791919708,
"learning_rate": 0.00017211272879801272,
"loss": 0.614105224609375,
"step": 321
},
{
"epoch": 2.050955414012739,
"grad_norm": 0.15646961331367493,
"learning_rate": 0.00017140201927075448,
"loss": 0.6018040180206299,
"step": 322
},
{
"epoch": 2.0573248407643314,
"grad_norm": 0.13153059780597687,
"learning_rate": 0.00017069113186510312,
"loss": 0.5299197435379028,
"step": 323
},
{
"epoch": 2.0636942675159236,
"grad_norm": 0.16131149232387543,
"learning_rate": 0.00016998008633287514,
"loss": 0.6013641357421875,
"step": 324
},
{
"epoch": 2.070063694267516,
"grad_norm": 0.13946978747844696,
"learning_rate": 0.00016926890243028044,
"loss": 0.6163864135742188,
"step": 325
},
{
"epoch": 2.0764331210191083,
"grad_norm": 0.15631259977817535,
"learning_rate": 0.00016855759991737354,
"loss": 0.61669921875,
"step": 326
},
{
"epoch": 2.082802547770701,
"grad_norm": 0.14260679483413696,
"learning_rate": 0.0001678461985575045,
"loss": 0.5925827026367188,
"step": 327
},
{
"epoch": 2.089171974522293,
"grad_norm": 0.1451353281736374,
"learning_rate": 0.00016713471811676981,
"loss": 0.6126327514648438,
"step": 328
},
{
"epoch": 2.0955414012738856,
"grad_norm": 0.14909975230693817,
"learning_rate": 0.00016642317836346326,
"loss": 0.5706071853637695,
"step": 329
},
{
"epoch": 2.1019108280254777,
"grad_norm": 0.12686562538146973,
"learning_rate": 0.0001657115990675265,
"loss": 0.5952835083007812,
"step": 330
},
{
"epoch": 2.1082802547770703,
"grad_norm": 0.14514797925949097,
"learning_rate": 0.000165,
"loss": 0.6125946044921875,
"step": 331
},
{
"epoch": 2.1146496815286624,
"grad_norm": 0.1282668113708496,
"learning_rate": 0.00016428840093247348,
"loss": 0.627960205078125,
"step": 332
},
{
"epoch": 2.121019108280255,
"grad_norm": 0.1351773738861084,
"learning_rate": 0.00016357682163653674,
"loss": 0.5793876647949219,
"step": 333
},
{
"epoch": 2.127388535031847,
"grad_norm": 0.13832542300224304,
"learning_rate": 0.00016286528188323018,
"loss": 0.5950775146484375,
"step": 334
},
{
"epoch": 2.1337579617834397,
"grad_norm": 0.14444728195667267,
"learning_rate": 0.00016215380144249554,
"loss": 0.603790283203125,
"step": 335
},
{
"epoch": 2.140127388535032,
"grad_norm": 0.14057223498821259,
"learning_rate": 0.00016144240008262646,
"loss": 0.6406707763671875,
"step": 336
},
{
"epoch": 2.1464968152866244,
"grad_norm": 0.16499315202236176,
"learning_rate": 0.0001607310975697195,
"loss": 0.6243743896484375,
"step": 337
},
{
"epoch": 2.1528662420382165,
"grad_norm": 0.1212117075920105,
"learning_rate": 0.00016001991366712485,
"loss": 0.6379890441894531,
"step": 338
},
{
"epoch": 2.159235668789809,
"grad_norm": 0.1492306888103485,
"learning_rate": 0.00015930886813489688,
"loss": 0.6547088623046875,
"step": 339
},
{
"epoch": 2.1656050955414012,
"grad_norm": 0.13451766967773438,
"learning_rate": 0.00015859798072924552,
"loss": 0.5874404907226562,
"step": 340
},
{
"epoch": 2.171974522292994,
"grad_norm": 0.12764382362365723,
"learning_rate": 0.00015788727120198727,
"loss": 0.5901260375976562,
"step": 341
},
{
"epoch": 2.178343949044586,
"grad_norm": 0.12776774168014526,
"learning_rate": 0.00015717675929999622,
"loss": 0.5579566955566406,
"step": 342
},
{
"epoch": 2.1847133757961785,
"grad_norm": 0.14371521770954132,
"learning_rate": 0.0001564664647646554,
"loss": 0.6439208984375,
"step": 343
},
{
"epoch": 2.1910828025477707,
"grad_norm": 0.1291123330593109,
"learning_rate": 0.0001557564073313087,
"loss": 0.6156845092773438,
"step": 344
},
{
"epoch": 2.1974522292993632,
"grad_norm": 0.14865116775035858,
"learning_rate": 0.0001550466067287118,
"loss": 0.5912910103797913,
"step": 345
},
{
"epoch": 2.2038216560509554,
"grad_norm": 0.12454650551080704,
"learning_rate": 0.00015433708267848474,
"loss": 0.5834617614746094,
"step": 346
},
{
"epoch": 2.210191082802548,
"grad_norm": 0.14238691329956055,
"learning_rate": 0.0001536278548945634,
"loss": 0.59521484375,
"step": 347
},
{
"epoch": 2.21656050955414,
"grad_norm": 0.13366709649562836,
"learning_rate": 0.00015291894308265205,
"loss": 0.638397216796875,
"step": 348
},
{
"epoch": 2.2229299363057327,
"grad_norm": 0.15498606860637665,
"learning_rate": 0.00015221036693967578,
"loss": 0.6231842041015625,
"step": 349
},
{
"epoch": 2.229299363057325,
"grad_norm": 0.11907719820737839,
"learning_rate": 0.00015150214615323318,
"loss": 0.587615966796875,
"step": 350
},
{
"epoch": 2.2356687898089174,
"grad_norm": 0.15132705867290497,
"learning_rate": 0.00015079430040104946,
"loss": 0.6379165649414062,
"step": 351
},
{
"epoch": 2.2420382165605095,
"grad_norm": 0.11819170415401459,
"learning_rate": 0.00015008684935042938,
"loss": 0.61981201171875,
"step": 352
},
{
"epoch": 2.248407643312102,
"grad_norm": 0.13008859753608704,
"learning_rate": 0.00014937981265771125,
"loss": 0.570770263671875,
"step": 353
},
{
"epoch": 2.254777070063694,
"grad_norm": 0.14087627828121185,
"learning_rate": 0.00014867320996772037,
"loss": 0.6410369873046875,
"step": 354
},
{
"epoch": 2.261146496815287,
"grad_norm": 0.13328370451927185,
"learning_rate": 0.0001479670609132236,
"loss": 0.5744893550872803,
"step": 355
},
{
"epoch": 2.267515923566879,
"grad_norm": 0.1431702822446823,
"learning_rate": 0.0001472613851143835,
"loss": 0.616485595703125,
"step": 356
},
{
"epoch": 2.2738853503184715,
"grad_norm": 0.125544935464859,
"learning_rate": 0.00014655620217821338,
"loss": 0.5837287902832031,
"step": 357
},
{
"epoch": 2.2802547770700636,
"grad_norm": 0.14490914344787598,
"learning_rate": 0.0001458515316980325,
"loss": 0.622344970703125,
"step": 358
},
{
"epoch": 2.286624203821656,
"grad_norm": 0.13078181445598602,
"learning_rate": 0.00014514739325292167,
"loss": 0.5972137451171875,
"step": 359
},
{
"epoch": 2.2929936305732483,
"grad_norm": 0.12549524009227753,
"learning_rate": 0.00014444380640717927,
"loss": 0.5801162719726562,
"step": 360
},
{
"epoch": 2.299363057324841,
"grad_norm": 0.12826323509216309,
"learning_rate": 0.0001437407907097776,
"loss": 0.6066741943359375,
"step": 361
},
{
"epoch": 2.305732484076433,
"grad_norm": 0.11325585097074509,
"learning_rate": 0.00014303836569381977,
"loss": 0.6093368530273438,
"step": 362
},
{
"epoch": 2.3121019108280256,
"grad_norm": 0.14651890099048615,
"learning_rate": 0.000142336550875997,
"loss": 0.6368637084960938,
"step": 363
},
{
"epoch": 2.3184713375796178,
"grad_norm": 0.13510103523731232,
"learning_rate": 0.00014163536575604625,
"loss": 0.6129156351089478,
"step": 364
},
{
"epoch": 2.3248407643312103,
"grad_norm": 0.15134194493293762,
"learning_rate": 0.00014093482981620853,
"loss": 0.6349525451660156,
"step": 365
},
{
"epoch": 2.3312101910828025,
"grad_norm": 0.14492426812648773,
"learning_rate": 0.00014023496252068754,
"loss": 0.6451873779296875,
"step": 366
},
{
"epoch": 2.337579617834395,
"grad_norm": 0.14017923176288605,
"learning_rate": 0.00013953578331510891,
"loss": 0.6146812438964844,
"step": 367
},
{
"epoch": 2.343949044585987,
"grad_norm": 0.12434567511081696,
"learning_rate": 0.00013883731162597988,
"loss": 0.5504074096679688,
"step": 368
},
{
"epoch": 2.3503184713375798,
"grad_norm": 0.14430786669254303,
"learning_rate": 0.00013813956686014957,
"loss": 0.6216583251953125,
"step": 369
},
{
"epoch": 2.356687898089172,
"grad_norm": 0.14035926759243011,
"learning_rate": 0.00013744256840426947,
"loss": 0.5603713989257812,
"step": 370
},
{
"epoch": 2.3630573248407645,
"grad_norm": 0.16027268767356873,
"learning_rate": 0.00013674633562425542,
"loss": 0.62811279296875,
"step": 371
},
{
"epoch": 2.3694267515923566,
"grad_norm": 0.13614311814308167,
"learning_rate": 0.00013605088786474895,
"loss": 0.5830307006835938,
"step": 372
},
{
"epoch": 2.375796178343949,
"grad_norm": 0.15351149439811707,
"learning_rate": 0.00013535624444858003,
"loss": 0.6096649169921875,
"step": 373
},
{
"epoch": 2.3821656050955413,
"grad_norm": 0.14856308698654175,
"learning_rate": 0.00013466242467623013,
"loss": 0.6033905148506165,
"step": 374
},
{
"epoch": 2.388535031847134,
"grad_norm": 0.14773039519786835,
"learning_rate": 0.00013396944782529614,
"loss": 0.5866012573242188,
"step": 375
},
{
"epoch": 2.394904458598726,
"grad_norm": 0.13591283559799194,
"learning_rate": 0.0001332773331499544,
"loss": 0.5860841274261475,
"step": 376
},
{
"epoch": 2.4012738853503186,
"grad_norm": 0.14836056530475616,
"learning_rate": 0.0001325860998804262,
"loss": 0.6184158325195312,
"step": 377
},
{
"epoch": 2.4076433121019107,
"grad_norm": 0.126322939991951,
"learning_rate": 0.0001318957672224429,
"loss": 0.5914382934570312,
"step": 378
},
{
"epoch": 2.4076433121019107,
"eval_loss": 0.5761079788208008,
"eval_runtime": 5.1841,
"eval_samples_per_second": 1.35,
"eval_steps_per_second": 0.193,
"step": 378
},
{
"epoch": 2.4140127388535033,
"grad_norm": 0.12728722393512726,
"learning_rate": 0.0001312063543567128,
"loss": 0.60479736328125,
"step": 379
},
{
"epoch": 2.4203821656050954,
"grad_norm": 0.12388841807842255,
"learning_rate": 0.00013051788043838802,
"loss": 0.5649628639221191,
"step": 380
},
{
"epoch": 2.426751592356688,
"grad_norm": 0.13987895846366882,
"learning_rate": 0.00012983036459653213,
"loss": 0.648193359375,
"step": 381
},
{
"epoch": 2.43312101910828,
"grad_norm": 0.13092386722564697,
"learning_rate": 0.0001291438259335891,
"loss": 0.6219940185546875,
"step": 382
},
{
"epoch": 2.4394904458598727,
"grad_norm": 0.13954687118530273,
"learning_rate": 0.0001284582835248518,
"loss": 0.59857177734375,
"step": 383
},
{
"epoch": 2.445859872611465,
"grad_norm": 0.1246153935790062,
"learning_rate": 0.00012777375641793282,
"loss": 0.5933837890625,
"step": 384
},
{
"epoch": 2.4522292993630574,
"grad_norm": 0.12277340143918991,
"learning_rate": 0.00012709026363223475,
"loss": 0.5308800935745239,
"step": 385
},
{
"epoch": 2.4585987261146496,
"grad_norm": 0.14798641204833984,
"learning_rate": 0.00012640782415842183,
"loss": 0.6336860656738281,
"step": 386
},
{
"epoch": 2.464968152866242,
"grad_norm": 0.12471195310354233,
"learning_rate": 0.00012572645695789223,
"loss": 0.6059951782226562,
"step": 387
},
{
"epoch": 2.4713375796178343,
"grad_norm": 0.1513262540102005,
"learning_rate": 0.00012504618096225142,
"loss": 0.6048202514648438,
"step": 388
},
{
"epoch": 2.477707006369427,
"grad_norm": 0.12812772393226624,
"learning_rate": 0.000124367015072786,
"loss": 0.6125259399414062,
"step": 389
},
{
"epoch": 2.484076433121019,
"grad_norm": 0.14327804744243622,
"learning_rate": 0.00012368897815993846,
"loss": 0.6097640991210938,
"step": 390
},
{
"epoch": 2.4904458598726116,
"grad_norm": 0.11908428370952606,
"learning_rate": 0.0001230120890627832,
"loss": 0.607391357421875,
"step": 391
},
{
"epoch": 2.4968152866242037,
"grad_norm": 0.14130553603172302,
"learning_rate": 0.00012233636658850263,
"loss": 0.5897216796875,
"step": 392
},
{
"epoch": 2.5031847133757963,
"grad_norm": 0.124527208507061,
"learning_rate": 0.00012166182951186501,
"loss": 0.610468864440918,
"step": 393
},
{
"epoch": 2.5095541401273884,
"grad_norm": 0.12550397217273712,
"learning_rate": 0.00012098849657470257,
"loss": 0.633514404296875,
"step": 394
},
{
"epoch": 2.515923566878981,
"grad_norm": 0.13000504672527313,
"learning_rate": 0.0001203163864853909,
"loss": 0.60052490234375,
"step": 395
},
{
"epoch": 2.522292993630573,
"grad_norm": 0.1370246559381485,
"learning_rate": 0.00011964551791832899,
"loss": 0.607757568359375,
"step": 396
},
{
"epoch": 2.5286624203821657,
"grad_norm": 0.13777491450309753,
"learning_rate": 0.00011897590951342062,
"loss": 0.62677001953125,
"step": 397
},
{
"epoch": 2.535031847133758,
"grad_norm": 0.12364954501390457,
"learning_rate": 0.00011830757987555613,
"loss": 0.5631561279296875,
"step": 398
},
{
"epoch": 2.5414012738853504,
"grad_norm": 0.12831932306289673,
"learning_rate": 0.00011764054757409592,
"loss": 0.59246826171875,
"step": 399
},
{
"epoch": 2.5477707006369426,
"grad_norm": 0.13040588796138763,
"learning_rate": 0.00011697483114235387,
"loss": 0.573883056640625,
"step": 400
},
{
"epoch": 2.554140127388535,
"grad_norm": 0.14850574731826782,
"learning_rate": 0.00011631044907708302,
"loss": 0.6436843872070312,
"step": 401
},
{
"epoch": 2.5605095541401273,
"grad_norm": 0.14597375690937042,
"learning_rate": 0.00011564741983796142,
"loss": 0.547149658203125,
"step": 402
},
{
"epoch": 2.56687898089172,
"grad_norm": 0.13630181550979614,
"learning_rate": 0.0001149857618470791,
"loss": 0.6168670654296875,
"step": 403
},
{
"epoch": 2.573248407643312,
"grad_norm": 0.1554763913154602,
"learning_rate": 0.00011432549348842638,
"loss": 0.6039199829101562,
"step": 404
},
{
"epoch": 2.5796178343949046,
"grad_norm": 0.13245627284049988,
"learning_rate": 0.00011366663310738296,
"loss": 0.61865234375,
"step": 405
},
{
"epoch": 2.5859872611464967,
"grad_norm": 0.15205496549606323,
"learning_rate": 0.00011300919901020831,
"loss": 0.6185302734375,
"step": 406
},
{
"epoch": 2.5923566878980893,
"grad_norm": 0.1314983069896698,
"learning_rate": 0.00011235320946353301,
"loss": 0.5970535278320312,
"step": 407
},
{
"epoch": 2.5987261146496814,
"grad_norm": 0.12996293604373932,
"learning_rate": 0.00011169868269385114,
"loss": 0.579315185546875,
"step": 408
},
{
"epoch": 2.605095541401274,
"grad_norm": 0.13885636627674103,
"learning_rate": 0.00011104563688701392,
"loss": 0.637776255607605,
"step": 409
},
{
"epoch": 2.611464968152866,
"grad_norm": 0.1276111751794815,
"learning_rate": 0.00011039409018772441,
"loss": 0.6009368896484375,
"step": 410
},
{
"epoch": 2.6178343949044587,
"grad_norm": 0.1259322166442871,
"learning_rate": 0.00010974406069903332,
"loss": 0.603363037109375,
"step": 411
},
{
"epoch": 2.624203821656051,
"grad_norm": 0.13328562676906586,
"learning_rate": 0.00010909556648183624,
"loss": 0.5782546997070312,
"step": 412
},
{
"epoch": 2.6305732484076434,
"grad_norm": 0.1371515840291977,
"learning_rate": 0.00010844862555437153,
"loss": 0.5915603637695312,
"step": 413
},
{
"epoch": 2.6369426751592355,
"grad_norm": 0.14940783381462097,
"learning_rate": 0.00010780325589171974,
"loss": 0.5879232883453369,
"step": 414
},
{
"epoch": 2.643312101910828,
"grad_norm": 0.15414959192276,
"learning_rate": 0.00010715947542530436,
"loss": 0.5717010498046875,
"step": 415
},
{
"epoch": 2.6496815286624202,
"grad_norm": 0.13370585441589355,
"learning_rate": 0.0001065173020423935,
"loss": 0.5884736180305481,
"step": 416
},
{
"epoch": 2.656050955414013,
"grad_norm": 0.15515513718128204,
"learning_rate": 0.00010587675358560277,
"loss": 0.6270065307617188,
"step": 417
},
{
"epoch": 2.662420382165605,
"grad_norm": 0.1390027552843094,
"learning_rate": 0.00010523784785239976,
"loss": 0.600189208984375,
"step": 418
},
{
"epoch": 2.6687898089171975,
"grad_norm": 0.14017456769943237,
"learning_rate": 0.00010460060259460934,
"loss": 0.5880279541015625,
"step": 419
},
{
"epoch": 2.6751592356687897,
"grad_norm": 0.15275587141513824,
"learning_rate": 0.00010396503551792058,
"loss": 0.6124420166015625,
"step": 420
},
{
"epoch": 2.6815286624203822,
"grad_norm": 0.1558653861284256,
"learning_rate": 0.00010333116428139477,
"loss": 0.633819580078125,
"step": 421
},
{
"epoch": 2.6878980891719744,
"grad_norm": 0.14223134517669678,
"learning_rate": 0.00010269900649697456,
"loss": 0.5633811950683594,
"step": 422
},
{
"epoch": 2.694267515923567,
"grad_norm": 0.14403124153614044,
"learning_rate": 0.00010206857972899486,
"loss": 0.618682861328125,
"step": 423
},
{
"epoch": 2.700636942675159,
"grad_norm": 0.13735178112983704,
"learning_rate": 0.00010143990149369496,
"loss": 0.6235809326171875,
"step": 424
},
{
"epoch": 2.7070063694267517,
"grad_norm": 0.1445300281047821,
"learning_rate": 0.00010081298925873139,
"loss": 0.6098251342773438,
"step": 425
},
{
"epoch": 2.713375796178344,
"grad_norm": 0.13087211549282074,
"learning_rate": 0.00010018786044269299,
"loss": 0.604888916015625,
"step": 426
},
{
"epoch": 2.7197452229299364,
"grad_norm": 0.13033169507980347,
"learning_rate": 9.956453241461657e-05,
"loss": 0.5754013061523438,
"step": 427
},
{
"epoch": 2.7261146496815285,
"grad_norm": 0.13266202807426453,
"learning_rate": 9.894302249350474e-05,
"loss": 0.5853180885314941,
"step": 428
},
{
"epoch": 2.732484076433121,
"grad_norm": 0.1278553158044815,
"learning_rate": 9.832334794784443e-05,
"loss": 0.5773391723632812,
"step": 429
},
{
"epoch": 2.738853503184713,
"grad_norm": 0.12599490582942963,
"learning_rate": 9.770552599512712e-05,
"loss": 0.596771240234375,
"step": 430
},
{
"epoch": 2.745222929936306,
"grad_norm": 0.11981520056724548,
"learning_rate": 9.708957380137053e-05,
"loss": 0.5833053588867188,
"step": 431
},
{
"epoch": 2.7515923566878984,
"grad_norm": 0.1373886913061142,
"learning_rate": 9.647550848064164e-05,
"loss": 0.6219329833984375,
"step": 432
},
{
"epoch": 2.7579617834394905,
"grad_norm": 0.1300242841243744,
"learning_rate": 9.586334709458108e-05,
"loss": 0.584136962890625,
"step": 433
},
{
"epoch": 2.7643312101910826,
"grad_norm": 0.12002365291118622,
"learning_rate": 9.52531066519293e-05,
"loss": 0.5211181640625,
"step": 434
},
{
"epoch": 2.770700636942675,
"grad_norm": 0.12125160545110703,
"learning_rate": 9.46448041080537e-05,
"loss": 0.6281661987304688,
"step": 435
},
{
"epoch": 2.777070063694268,
"grad_norm": 0.13555943965911865,
"learning_rate": 9.403845636447773e-05,
"loss": 0.6027107238769531,
"step": 436
},
{
"epoch": 2.78343949044586,
"grad_norm": 0.12764829397201538,
"learning_rate": 9.343408026841136e-05,
"loss": 0.5479583740234375,
"step": 437
},
{
"epoch": 2.789808917197452,
"grad_norm": 0.137704998254776,
"learning_rate": 9.283169261228273e-05,
"loss": 0.6118240356445312,
"step": 438
},
{
"epoch": 2.7961783439490446,
"grad_norm": 0.12445090711116791,
"learning_rate": 9.22313101332718e-05,
"loss": 0.59619140625,
"step": 439
},
{
"epoch": 2.802547770700637,
"grad_norm": 0.13199564814567566,
"learning_rate": 9.163294951284502e-05,
"loss": 0.6183624267578125,
"step": 440
},
{
"epoch": 2.8089171974522293,
"grad_norm": 0.12737038731575012,
"learning_rate": 9.103662737629227e-05,
"loss": 0.55206298828125,
"step": 441
},
{
"epoch": 2.8152866242038215,
"grad_norm": 0.12857210636138916,
"learning_rate": 9.044236029226462e-05,
"loss": 0.6302719116210938,
"step": 442
},
{
"epoch": 2.821656050955414,
"grad_norm": 0.1327592432498932,
"learning_rate": 8.985016477231405e-05,
"loss": 0.6136627197265625,
"step": 443
},
{
"epoch": 2.8280254777070066,
"grad_norm": 0.1341818869113922,
"learning_rate": 8.926005727043465e-05,
"loss": 0.5634078979492188,
"step": 444
},
{
"epoch": 2.8343949044585988,
"grad_norm": 0.12366130203008652,
"learning_rate": 8.867205418260555e-05,
"loss": 0.587615966796875,
"step": 445
},
{
"epoch": 2.840764331210191,
"grad_norm": 0.11431681364774704,
"learning_rate": 8.808617184633525e-05,
"loss": 0.559967041015625,
"step": 446
},
{
"epoch": 2.8471337579617835,
"grad_norm": 0.12453463673591614,
"learning_rate": 8.750242654020777e-05,
"loss": 0.6495513916015625,
"step": 447
},
{
"epoch": 2.853503184713376,
"grad_norm": 0.11568041890859604,
"learning_rate": 8.692083448343036e-05,
"loss": 0.5511703491210938,
"step": 448
},
{
"epoch": 2.859872611464968,
"grad_norm": 0.11872231960296631,
"learning_rate": 8.634141183538264e-05,
"loss": 0.5853309631347656,
"step": 449
},
{
"epoch": 2.8662420382165603,
"grad_norm": 0.12179554998874664,
"learning_rate": 8.576417469516792e-05,
"loss": 0.5696792602539062,
"step": 450
},
{
"epoch": 2.872611464968153,
"grad_norm": 0.13381585478782654,
"learning_rate": 8.518913910116582e-05,
"loss": 0.6086349487304688,
"step": 451
},
{
"epoch": 2.8789808917197455,
"grad_norm": 0.11038290709257126,
"learning_rate": 8.461632103058656e-05,
"loss": 0.5354101657867432,
"step": 452
},
{
"epoch": 2.8853503184713376,
"grad_norm": 0.127372607588768,
"learning_rate": 8.404573639902685e-05,
"loss": 0.6167430877685547,
"step": 453
},
{
"epoch": 2.8917197452229297,
"grad_norm": 0.13518854975700378,
"learning_rate": 8.347740106002819e-05,
"loss": 0.6061553955078125,
"step": 454
},
{
"epoch": 2.8980891719745223,
"grad_norm": 0.12002270668745041,
"learning_rate": 8.291133080463587e-05,
"loss": 0.5920867919921875,
"step": 455
},
{
"epoch": 2.904458598726115,
"grad_norm": 0.14155139029026031,
"learning_rate": 8.234754136096062e-05,
"loss": 0.6145782470703125,
"step": 456
},
{
"epoch": 2.910828025477707,
"grad_norm": 0.1278562992811203,
"learning_rate": 8.178604839374128e-05,
"loss": 0.5713272094726562,
"step": 457
},
{
"epoch": 2.917197452229299,
"grad_norm": 0.1296142339706421,
"learning_rate": 8.122686750390976e-05,
"loss": 0.64373779296875,
"step": 458
},
{
"epoch": 2.9235668789808917,
"grad_norm": 0.12263528257608414,
"learning_rate": 8.067001422815754e-05,
"loss": 0.62957763671875,
"step": 459
},
{
"epoch": 2.9299363057324843,
"grad_norm": 0.12212619930505753,
"learning_rate": 8.011550403850392e-05,
"loss": 0.561920166015625,
"step": 460
},
{
"epoch": 2.9363057324840764,
"grad_norm": 0.11793559789657593,
"learning_rate": 7.956335234186627e-05,
"loss": 0.57391357421875,
"step": 461
},
{
"epoch": 2.9426751592356686,
"grad_norm": 0.12261152267456055,
"learning_rate": 7.901357447963167e-05,
"loss": 0.5915069580078125,
"step": 462
},
{
"epoch": 2.949044585987261,
"grad_norm": 0.12022452801465988,
"learning_rate": 7.846618572723106e-05,
"loss": 0.5995712280273438,
"step": 463
},
{
"epoch": 2.9554140127388537,
"grad_norm": 0.11820082366466522,
"learning_rate": 7.792120129371445e-05,
"loss": 0.5693140029907227,
"step": 464
},
{
"epoch": 2.961783439490446,
"grad_norm": 0.12471581995487213,
"learning_rate": 7.737863632132867e-05,
"loss": 0.5901336669921875,
"step": 465
},
{
"epoch": 2.968152866242038,
"grad_norm": 0.12360789626836777,
"learning_rate": 7.683850588509622e-05,
"loss": 0.5783553123474121,
"step": 466
},
{
"epoch": 2.9745222929936306,
"grad_norm": 0.12195241451263428,
"learning_rate": 7.630082499239692e-05,
"loss": 0.591522216796875,
"step": 467
},
{
"epoch": 2.980891719745223,
"grad_norm": 0.11922894418239594,
"learning_rate": 7.576560858255046e-05,
"loss": 0.6068878173828125,
"step": 468
},
{
"epoch": 2.9872611464968153,
"grad_norm": 0.12887009978294373,
"learning_rate": 7.523287152640168e-05,
"loss": 0.5982818603515625,
"step": 469
},
{
"epoch": 2.9936305732484074,
"grad_norm": 0.1265416294336319,
"learning_rate": 7.470262862590718e-05,
"loss": 0.6074981689453125,
"step": 470
},
{
"epoch": 3.0,
"grad_norm": 0.12172482162714005,
"learning_rate": 7.417489461372415e-05,
"loss": 0.5847549438476562,
"step": 471
},
{
"epoch": 3.0063694267515926,
"grad_norm": 0.11879237741231918,
"learning_rate": 7.364968415280093e-05,
"loss": 0.6038360595703125,
"step": 472
},
{
"epoch": 3.0127388535031847,
"grad_norm": 0.12170149385929108,
"learning_rate": 7.312701183596971e-05,
"loss": 0.5882415771484375,
"step": 473
},
{
"epoch": 3.0191082802547773,
"grad_norm": 0.12088643014431,
"learning_rate": 7.260689218554105e-05,
"loss": 0.6337738037109375,
"step": 474
},
{
"epoch": 3.0254777070063694,
"grad_norm": 0.11253787577152252,
"learning_rate": 7.208933965290024e-05,
"loss": 0.5970654487609863,
"step": 475
},
{
"epoch": 3.031847133757962,
"grad_norm": 0.12436731159687042,
"learning_rate": 7.1574368618106e-05,
"loss": 0.5939712524414062,
"step": 476
},
{
"epoch": 3.038216560509554,
"grad_norm": 0.12008056044578552,
"learning_rate": 7.106199338949081e-05,
"loss": 0.5743637084960938,
"step": 477
},
{
"epoch": 3.0445859872611467,
"grad_norm": 0.12449143081903458,
"learning_rate": 7.055222820326335e-05,
"loss": 0.5961456298828125,
"step": 478
},
{
"epoch": 3.050955414012739,
"grad_norm": 0.12028675526380539,
"learning_rate": 7.004508722311293e-05,
"loss": 0.5840814709663391,
"step": 479
},
{
"epoch": 3.0573248407643314,
"grad_norm": 0.10850632935762405,
"learning_rate": 6.954058453981609e-05,
"loss": 0.5147503018379211,
"step": 480
},
{
"epoch": 3.0636942675159236,
"grad_norm": 0.12164684385061264,
"learning_rate": 6.903873417084491e-05,
"loss": 0.5835723876953125,
"step": 481
},
{
"epoch": 3.070063694267516,
"grad_norm": 0.12288510799407959,
"learning_rate": 6.853955005997767e-05,
"loss": 0.5993270874023438,
"step": 482
},
{
"epoch": 3.0764331210191083,
"grad_norm": 0.13285133242607117,
"learning_rate": 6.804304607691137e-05,
"loss": 0.5991897583007812,
"step": 483
},
{
"epoch": 3.082802547770701,
"grad_norm": 0.12256758660078049,
"learning_rate": 6.754923601687638e-05,
"loss": 0.5762252807617188,
"step": 484
},
{
"epoch": 3.089171974522293,
"grad_norm": 0.12933403253555298,
"learning_rate": 6.705813360025316e-05,
"loss": 0.5952529907226562,
"step": 485
},
{
"epoch": 3.0955414012738856,
"grad_norm": 0.11282753199338913,
"learning_rate": 6.656975247219094e-05,
"loss": 0.5542392730712891,
"step": 486
},
{
"epoch": 3.1019108280254777,
"grad_norm": 0.11912853270769119,
"learning_rate": 6.608410620222883e-05,
"loss": 0.5784263610839844,
"step": 487
},
{
"epoch": 3.1082802547770703,
"grad_norm": 0.11849821358919144,
"learning_rate": 6.560120828391843e-05,
"loss": 0.5958251953125,
"step": 488
},
{
"epoch": 3.1146496815286624,
"grad_norm": 0.11127341538667679,
"learning_rate": 6.512107213444928e-05,
"loss": 0.6105194091796875,
"step": 489
},
{
"epoch": 3.121019108280255,
"grad_norm": 0.11595870554447174,
"learning_rate": 6.464371109427591e-05,
"loss": 0.5636520385742188,
"step": 490
},
{
"epoch": 3.127388535031847,
"grad_norm": 0.12187227606773376,
"learning_rate": 6.416913842674709e-05,
"loss": 0.5792922973632812,
"step": 491
},
{
"epoch": 3.1337579617834397,
"grad_norm": 0.11933460086584091,
"learning_rate": 6.369736731773748e-05,
"loss": 0.587799072265625,
"step": 492
},
{
"epoch": 3.140127388535032,
"grad_norm": 0.11708524078130722,
"learning_rate": 6.322841087528113e-05,
"loss": 0.6246719360351562,
"step": 493
},
{
"epoch": 3.1464968152866244,
"grad_norm": 0.12828877568244934,
"learning_rate": 6.27622821292074e-05,
"loss": 0.607208251953125,
"step": 494
},
{
"epoch": 3.1528662420382165,
"grad_norm": 0.11456846445798874,
"learning_rate": 6.229899403077878e-05,
"loss": 0.621337890625,
"step": 495
},
{
"epoch": 3.159235668789809,
"grad_norm": 0.11536476761102676,
"learning_rate": 6.183855945233125e-05,
"loss": 0.6371536254882812,
"step": 496
},
{
"epoch": 3.1656050955414012,
"grad_norm": 0.1287345588207245,
"learning_rate": 6.138099118691626e-05,
"loss": 0.571502685546875,
"step": 497
},
{
"epoch": 3.171974522292994,
"grad_norm": 0.11508220434188843,
"learning_rate": 6.0926301947945806e-05,
"loss": 0.5750579833984375,
"step": 498
},
{
"epoch": 3.178343949044586,
"grad_norm": 0.1181962639093399,
"learning_rate": 6.047450436883875e-05,
"loss": 0.5426216125488281,
"step": 499
},
{
"epoch": 3.1847133757961785,
"grad_norm": 0.1390620470046997,
"learning_rate": 6.0025611002670024e-05,
"loss": 0.6269683837890625,
"step": 500
},
{
"epoch": 3.1910828025477707,
"grad_norm": 0.11729639023542404,
"learning_rate": 5.957963432182164e-05,
"loss": 0.6000823974609375,
"step": 501
},
{
"epoch": 3.1974522292993632,
"grad_norm": 0.11855028569698334,
"learning_rate": 5.913658671763644e-05,
"loss": 0.5764329433441162,
"step": 502
},
{
"epoch": 3.2038216560509554,
"grad_norm": 0.116395965218544,
"learning_rate": 5.869648050007361e-05,
"loss": 0.5692176818847656,
"step": 503
},
{
"epoch": 3.2038216560509554,
"eval_loss": 0.5691375732421875,
"eval_runtime": 5.1761,
"eval_samples_per_second": 1.352,
"eval_steps_per_second": 0.193,
"step": 503
},
{
"epoch": 3.210191082802548,
"grad_norm": 0.12607790529727936,
"learning_rate": 5.8259327897366674e-05,
"loss": 0.5795440673828125,
"step": 504
},
{
"epoch": 3.21656050955414,
"grad_norm": 0.11750511825084686,
"learning_rate": 5.782514105568378e-05,
"loss": 0.6226959228515625,
"step": 505
},
{
"epoch": 3.2229299363057327,
"grad_norm": 0.1273873895406723,
"learning_rate": 5.7393932038790186e-05,
"loss": 0.607208251953125,
"step": 506
},
{
"epoch": 3.229299363057325,
"grad_norm": 0.11236650496721268,
"learning_rate": 5.6965712827713103e-05,
"loss": 0.5733528137207031,
"step": 507
},
{
"epoch": 3.2356687898089174,
"grad_norm": 0.11460690200328827,
"learning_rate": 5.654049532040875e-05,
"loss": 0.6213912963867188,
"step": 508
},
{
"epoch": 3.2420382165605095,
"grad_norm": 0.12059050798416138,
"learning_rate": 5.6118291331431886e-05,
"loss": 0.604522705078125,
"step": 509
},
{
"epoch": 3.248407643312102,
"grad_norm": 0.11258003860712051,
"learning_rate": 5.569911259160735e-05,
"loss": 0.5564193725585938,
"step": 510
},
{
"epoch": 3.254777070063694,
"grad_norm": 0.12630507349967957,
"learning_rate": 5.528297074770428e-05,
"loss": 0.6247711181640625,
"step": 511
},
{
"epoch": 3.261146496815287,
"grad_norm": 0.11103589087724686,
"learning_rate": 5.48698773621126e-05,
"loss": 0.5611529350280762,
"step": 512
},
{
"epoch": 3.267515923566879,
"grad_norm": 0.11982318758964539,
"learning_rate": 5.445984391252152e-05,
"loss": 0.600677490234375,
"step": 513
},
{
"epoch": 3.2738853503184715,
"grad_norm": 0.11556871980428696,
"learning_rate": 5.405288179160072e-05,
"loss": 0.5696296691894531,
"step": 514
},
{
"epoch": 3.2802547770700636,
"grad_norm": 0.11754198372364044,
"learning_rate": 5.364900230668387e-05,
"loss": 0.6072998046875,
"step": 515
},
{
"epoch": 3.286624203821656,
"grad_norm": 0.11896596848964691,
"learning_rate": 5.324821667945448e-05,
"loss": 0.5825119018554688,
"step": 516
},
{
"epoch": 3.2929936305732483,
"grad_norm": 0.11040665209293365,
"learning_rate": 5.285053604563396e-05,
"loss": 0.5658645629882812,
"step": 517
},
{
"epoch": 3.299363057324841,
"grad_norm": 0.1226251870393753,
"learning_rate": 5.2455971454672366e-05,
"loss": 0.59228515625,
"step": 518
},
{
"epoch": 3.305732484076433,
"grad_norm": 0.11311738193035126,
"learning_rate": 5.206453386944134e-05,
"loss": 0.5952987670898438,
"step": 519
},
{
"epoch": 3.3121019108280256,
"grad_norm": 0.11997239291667938,
"learning_rate": 5.167623416592947e-05,
"loss": 0.6220855712890625,
"step": 520
},
{
"epoch": 3.3184713375796178,
"grad_norm": 0.11941354721784592,
"learning_rate": 5.129108313294016e-05,
"loss": 0.598699688911438,
"step": 521
},
{
"epoch": 3.3248407643312103,
"grad_norm": 0.11876620352268219,
"learning_rate": 5.0909091471791896e-05,
"loss": 0.6198253631591797,
"step": 522
},
{
"epoch": 3.3312101910828025,
"grad_norm": 0.12098715454339981,
"learning_rate": 5.0530269796020715e-05,
"loss": 0.6304779052734375,
"step": 523
},
{
"epoch": 3.337579617834395,
"grad_norm": 0.115480437874794,
"learning_rate": 5.015462863108559e-05,
"loss": 0.6010208129882812,
"step": 524
},
{
"epoch": 3.343949044585987,
"grad_norm": 0.1109473928809166,
"learning_rate": 4.97821784140758e-05,
"loss": 0.5378494262695312,
"step": 525
},
{
"epoch": 3.3503184713375798,
"grad_norm": 0.12404850870370865,
"learning_rate": 4.9412929493421075e-05,
"loss": 0.6075439453125,
"step": 526
},
{
"epoch": 3.356687898089172,
"grad_norm": 0.11312513053417206,
"learning_rate": 4.904689212860388e-05,
"loss": 0.5474624633789062,
"step": 527
},
{
"epoch": 3.3630573248407645,
"grad_norm": 0.12030960619449615,
"learning_rate": 4.868407648987444e-05,
"loss": 0.613067626953125,
"step": 528
},
{
"epoch": 3.3694267515923566,
"grad_norm": 0.11236941069364548,
"learning_rate": 4.832449265796827e-05,
"loss": 0.569580078125,
"step": 529
},
{
"epoch": 3.375796178343949,
"grad_norm": 0.11299137026071548,
"learning_rate": 4.796815062382596e-05,
"loss": 0.5960693359375,
"step": 530
},
{
"epoch": 3.3821656050955413,
"grad_norm": 0.122473806142807,
"learning_rate": 4.7615060288315624e-05,
"loss": 0.589868426322937,
"step": 531
},
{
"epoch": 3.388535031847134,
"grad_norm": 0.1166764497756958,
"learning_rate": 4.726523146195777e-05,
"loss": 0.5731353759765625,
"step": 532
},
{
"epoch": 3.394904458598726,
"grad_norm": 0.11254797875881195,
"learning_rate": 4.691867386465278e-05,
"loss": 0.5731104612350464,
"step": 533
},
{
"epoch": 3.4012738853503186,
"grad_norm": 0.12588226795196533,
"learning_rate": 4.657539712541081e-05,
"loss": 0.6047592163085938,
"step": 534
},
{
"epoch": 3.4076433121019107,
"grad_norm": 0.11485734581947327,
"learning_rate": 4.6235410782084265e-05,
"loss": 0.5780868530273438,
"step": 535
},
{
"epoch": 3.4140127388535033,
"grad_norm": 0.11399234086275101,
"learning_rate": 4.5898724281102683e-05,
"loss": 0.5918350219726562,
"step": 536
},
{
"epoch": 3.4203821656050954,
"grad_norm": 0.11319176852703094,
"learning_rate": 4.55653469772105e-05,
"loss": 0.5530385971069336,
"step": 537
},
{
"epoch": 3.426751592356688,
"grad_norm": 0.11522573232650757,
"learning_rate": 4.523528813320687e-05,
"loss": 0.63470458984375,
"step": 538
},
{
"epoch": 3.43312101910828,
"grad_norm": 0.1146511435508728,
"learning_rate": 4.490855691968857e-05,
"loss": 0.6084060668945312,
"step": 539
},
{
"epoch": 3.4394904458598727,
"grad_norm": 0.11526243388652802,
"learning_rate": 4.4585162414794986e-05,
"loss": 0.586029052734375,
"step": 540
},
{
"epoch": 3.445859872611465,
"grad_norm": 0.11174765229225159,
"learning_rate": 4.426511360395585e-05,
"loss": 0.5800552368164062,
"step": 541
},
{
"epoch": 3.4522292993630574,
"grad_norm": 0.11285701394081116,
"learning_rate": 4.394841937964181e-05,
"loss": 0.5191566348075867,
"step": 542
},
{
"epoch": 3.4585987261146496,
"grad_norm": 0.11998529732227325,
"learning_rate": 4.36350885411172e-05,
"loss": 0.6203880310058594,
"step": 543
},
{
"epoch": 3.464968152866242,
"grad_norm": 0.11160973459482193,
"learning_rate": 4.332512979419553e-05,
"loss": 0.5934371948242188,
"step": 544
},
{
"epoch": 3.4713375796178343,
"grad_norm": 0.11388590931892395,
"learning_rate": 4.301855175099769e-05,
"loss": 0.591888427734375,
"step": 545
},
{
"epoch": 3.477707006369427,
"grad_norm": 0.11820085346698761,
"learning_rate": 4.27153629297126e-05,
"loss": 0.5998001098632812,
"step": 546
},
{
"epoch": 3.484076433121019,
"grad_norm": 0.11512783914804459,
"learning_rate": 4.241557175436059e-05,
"loss": 0.5966873168945312,
"step": 547
},
{
"epoch": 3.4904458598726116,
"grad_norm": 0.10947820544242859,
"learning_rate": 4.2119186554559284e-05,
"loss": 0.5952606201171875,
"step": 548
},
{
"epoch": 3.4968152866242037,
"grad_norm": 0.12195497006177902,
"learning_rate": 4.1826215565292134e-05,
"loss": 0.5769195556640625,
"step": 549
},
{
"epoch": 3.5031847133757963,
"grad_norm": 0.10718007385730743,
"learning_rate": 4.153666692667974e-05,
"loss": 0.5982446670532227,
"step": 550
},
{
"epoch": 3.5095541401273884,
"grad_norm": 0.1096276119351387,
"learning_rate": 4.125054868375358e-05,
"loss": 0.620819091796875,
"step": 551
},
{
"epoch": 3.515923566878981,
"grad_norm": 0.12272590398788452,
"learning_rate": 4.09678687862325e-05,
"loss": 0.5886993408203125,
"step": 552
},
{
"epoch": 3.522292993630573,
"grad_norm": 0.12129033356904984,
"learning_rate": 4.068863508830188e-05,
"loss": 0.5951309204101562,
"step": 553
},
{
"epoch": 3.5286624203821657,
"grad_norm": 0.12272969633340836,
"learning_rate": 4.0412855348395294e-05,
"loss": 0.6143798828125,
"step": 554
},
{
"epoch": 3.535031847133758,
"grad_norm": 0.10710962861776352,
"learning_rate": 4.014053722897904e-05,
"loss": 0.5522842407226562,
"step": 555
},
{
"epoch": 3.5414012738853504,
"grad_norm": 0.11110975593328476,
"learning_rate": 3.987168829633926e-05,
"loss": 0.5803451538085938,
"step": 556
},
{
"epoch": 3.5477707006369426,
"grad_norm": 0.11578673869371414,
"learning_rate": 3.9606316020371635e-05,
"loss": 0.5619888305664062,
"step": 557
},
{
"epoch": 3.554140127388535,
"grad_norm": 0.11307930201292038,
"learning_rate": 3.934442777437383e-05,
"loss": 0.6312026977539062,
"step": 558
},
{
"epoch": 3.5605095541401273,
"grad_norm": 0.11122153699398041,
"learning_rate": 3.908603083484074e-05,
"loss": 0.53570556640625,
"step": 559
},
{
"epoch": 3.56687898089172,
"grad_norm": 0.11363998800516129,
"learning_rate": 3.8831132381262244e-05,
"loss": 0.6043548583984375,
"step": 560
},
{
"epoch": 3.573248407643312,
"grad_norm": 0.1189269870519638,
"learning_rate": 3.857973949592365e-05,
"loss": 0.5921096801757812,
"step": 561
},
{
"epoch": 3.5796178343949046,
"grad_norm": 0.1117604523897171,
"learning_rate": 3.8331859163709086e-05,
"loss": 0.60650634765625,
"step": 562
},
{
"epoch": 3.5859872611464967,
"grad_norm": 0.1151510551571846,
"learning_rate": 3.808749827190723e-05,
"loss": 0.6067428588867188,
"step": 563
},
{
"epoch": 3.5923566878980893,
"grad_norm": 0.11094477027654648,
"learning_rate": 3.784666361002013e-05,
"loss": 0.5858001708984375,
"step": 564
},
{
"epoch": 3.5987261146496814,
"grad_norm": 0.11872120201587677,
"learning_rate": 3.7609361869574425e-05,
"loss": 0.568603515625,
"step": 565
},
{
"epoch": 3.605095541401274,
"grad_norm": 0.11176243424415588,
"learning_rate": 3.737559964393552e-05,
"loss": 0.6265898942947388,
"step": 566
},
{
"epoch": 3.611464968152866,
"grad_norm": 0.10548706352710724,
"learning_rate": 3.714538342812434e-05,
"loss": 0.5895538330078125,
"step": 567
},
{
"epoch": 3.6178343949044587,
"grad_norm": 0.10922879725694656,
"learning_rate": 3.691871961863683e-05,
"loss": 0.5919036865234375,
"step": 568
},
{
"epoch": 3.624203821656051,
"grad_norm": 0.1119789406657219,
"learning_rate": 3.669561451326634e-05,
"loss": 0.56719970703125,
"step": 569
},
{
"epoch": 3.6305732484076434,
"grad_norm": 0.11212991178035736,
"learning_rate": 3.6476074310928566e-05,
"loss": 0.5804367065429688,
"step": 570
},
{
"epoch": 3.6369426751592355,
"grad_norm": 0.11380063742399216,
"learning_rate": 3.626010511148926e-05,
"loss": 0.576891303062439,
"step": 571
},
{
"epoch": 3.643312101910828,
"grad_norm": 0.10741905122995377,
"learning_rate": 3.6047712915594853e-05,
"loss": 0.5605392456054688,
"step": 572
},
{
"epoch": 3.6496815286624202,
"grad_norm": 0.1313689798116684,
"learning_rate": 3.583890362450577e-05,
"loss": 0.5773947238922119,
"step": 573
},
{
"epoch": 3.656050955414013,
"grad_norm": 0.11181677132844925,
"learning_rate": 3.563368303993225e-05,
"loss": 0.61541748046875,
"step": 574
},
{
"epoch": 3.662420382165605,
"grad_norm": 0.12020916491746902,
"learning_rate": 3.54320568638734e-05,
"loss": 0.5890045166015625,
"step": 575
},
{
"epoch": 3.6687898089171975,
"grad_norm": 0.11567579954862595,
"learning_rate": 3.5234030698458534e-05,
"loss": 0.5779571533203125,
"step": 576
},
{
"epoch": 3.6751592356687897,
"grad_norm": 0.1177821010351181,
"learning_rate": 3.5039610045791716e-05,
"loss": 0.6016159057617188,
"step": 577
},
{
"epoch": 3.6815286624203822,
"grad_norm": 0.11920693516731262,
"learning_rate": 3.484880030779879e-05,
"loss": 0.6223907470703125,
"step": 578
},
{
"epoch": 3.6878980891719744,
"grad_norm": 0.10849031060934067,
"learning_rate": 3.466160678607726e-05,
"loss": 0.5529365539550781,
"step": 579
},
{
"epoch": 3.694267515923567,
"grad_norm": 0.11642079055309296,
"learning_rate": 3.447803468174908e-05,
"loss": 0.607879638671875,
"step": 580
},
{
"epoch": 3.700636942675159,
"grad_norm": 0.11872278898954391,
"learning_rate": 3.4298089095316075e-05,
"loss": 0.6125946044921875,
"step": 581
},
{
"epoch": 3.7070063694267517,
"grad_norm": 0.12201058864593506,
"learning_rate": 3.4121775026518204e-05,
"loss": 0.5991783142089844,
"step": 582
},
{
"epoch": 3.713375796178344,
"grad_norm": 0.11092175543308258,
"learning_rate": 3.394909737419475e-05,
"loss": 0.5940704345703125,
"step": 583
},
{
"epoch": 3.7197452229299364,
"grad_norm": 0.11027749627828598,
"learning_rate": 3.378006093614806e-05,
"loss": 0.5653915405273438,
"step": 584
},
{
"epoch": 3.7261146496815285,
"grad_norm": 0.11839186400175095,
"learning_rate": 3.361467040901035e-05,
"loss": 0.5750976204872131,
"step": 585
},
{
"epoch": 3.732484076433121,
"grad_norm": 0.11207658797502518,
"learning_rate": 3.34529303881132e-05,
"loss": 0.5675506591796875,
"step": 586
},
{
"epoch": 3.738853503184713,
"grad_norm": 0.10792435705661774,
"learning_rate": 3.329484536735984e-05,
"loss": 0.587005615234375,
"step": 587
},
{
"epoch": 3.745222929936306,
"grad_norm": 0.11606154590845108,
"learning_rate": 3.3140419739100266e-05,
"loss": 0.5737838745117188,
"step": 588
},
{
"epoch": 3.7515923566878984,
"grad_norm": 0.11868041753768921,
"learning_rate": 3.298965779400926e-05,
"loss": 0.6115951538085938,
"step": 589
},
{
"epoch": 3.7579617834394905,
"grad_norm": 0.11325030773878098,
"learning_rate": 3.284256372096713e-05,
"loss": 0.5740203857421875,
"step": 590
},
{
"epoch": 3.7643312101910826,
"grad_norm": 0.10752908885478973,
"learning_rate": 3.269914160694337e-05,
"loss": 0.5116958618164062,
"step": 591
},
{
"epoch": 3.770700636942675,
"grad_norm": 0.11671079695224762,
"learning_rate": 3.255939543688306e-05,
"loss": 0.6184310913085938,
"step": 592
},
{
"epoch": 3.777070063694268,
"grad_norm": 0.1126815527677536,
"learning_rate": 3.242332909359613e-05,
"loss": 0.5923385620117188,
"step": 593
},
{
"epoch": 3.78343949044586,
"grad_norm": 0.10861267894506454,
"learning_rate": 3.229094635764956e-05,
"loss": 0.5390701293945312,
"step": 594
},
{
"epoch": 3.789808917197452,
"grad_norm": 0.11774186789989471,
"learning_rate": 3.216225090726223e-05,
"loss": 0.6020126342773438,
"step": 595
},
{
"epoch": 3.7961783439490446,
"grad_norm": 0.10752571374177933,
"learning_rate": 3.2037246318202846e-05,
"loss": 0.5871200561523438,
"step": 596
},
{
"epoch": 3.802547770700637,
"grad_norm": 0.11397215723991394,
"learning_rate": 3.191593606369046e-05,
"loss": 0.608978271484375,
"step": 597
},
{
"epoch": 3.8089171974522293,
"grad_norm": 0.11120873689651489,
"learning_rate": 3.179832351429805e-05,
"loss": 0.5426864624023438,
"step": 598
},
{
"epoch": 3.8152866242038215,
"grad_norm": 0.11356130242347717,
"learning_rate": 3.1684411937858814e-05,
"loss": 0.6201629638671875,
"step": 599
},
{
"epoch": 3.821656050955414,
"grad_norm": 0.11339955031871796,
"learning_rate": 3.157420449937546e-05,
"loss": 0.60382080078125,
"step": 600
},
{
"epoch": 3.8280254777070066,
"grad_norm": 0.10754179954528809,
"learning_rate": 3.146770426093222e-05,
"loss": 0.554779052734375,
"step": 601
},
{
"epoch": 3.8343949044585988,
"grad_norm": 0.11259491741657257,
"learning_rate": 3.136491418160968e-05,
"loss": 0.5785980224609375,
"step": 602
},
{
"epoch": 3.840764331210191,
"grad_norm": 0.10771609842777252,
"learning_rate": 3.126583711740273e-05,
"loss": 0.5512466430664062,
"step": 603
},
{
"epoch": 3.8471337579617835,
"grad_norm": 0.11603587865829468,
"learning_rate": 3.117047582114108e-05,
"loss": 0.6403045654296875,
"step": 604
},
{
"epoch": 3.853503184713376,
"grad_norm": 0.1212775930762291,
"learning_rate": 3.1078832942412854e-05,
"loss": 0.5423660278320312,
"step": 605
},
{
"epoch": 3.859872611464968,
"grad_norm": 0.11277224123477936,
"learning_rate": 3.0990911027490914e-05,
"loss": 0.5763015747070312,
"step": 606
},
{
"epoch": 3.8662420382165603,
"grad_norm": 0.11192955076694489,
"learning_rate": 3.090671251926216e-05,
"loss": 0.5609245300292969,
"step": 607
},
{
"epoch": 3.872611464968153,
"grad_norm": 0.11367684602737427,
"learning_rate": 3.0826239757159634e-05,
"loss": 0.5995559692382812,
"step": 608
},
{
"epoch": 3.8789808917197455,
"grad_norm": 0.1102093756198883,
"learning_rate": 3.0749494977097477e-05,
"loss": 0.5271474123001099,
"step": 609
},
{
"epoch": 3.8853503184713376,
"grad_norm": 0.11243017017841339,
"learning_rate": 3.06764803114089e-05,
"loss": 0.6080722808837891,
"step": 610
},
{
"epoch": 3.8917197452229297,
"grad_norm": 0.11553356796503067,
"learning_rate": 3.060719778878684e-05,
"loss": 0.59722900390625,
"step": 611
},
{
"epoch": 3.8980891719745223,
"grad_norm": 0.18460510671138763,
"learning_rate": 3.054164933422767e-05,
"loss": 0.583221435546875,
"step": 612
},
{
"epoch": 3.904458598726115,
"grad_norm": 0.11210013180971146,
"learning_rate": 3.0479836768977663e-05,
"loss": 0.6054916381835938,
"step": 613
},
{
"epoch": 3.910828025477707,
"grad_norm": 0.11276479810476303,
"learning_rate": 3.042176181048241e-05,
"loss": 0.5625152587890625,
"step": 614
},
{
"epoch": 3.917197452229299,
"grad_norm": 0.11306929588317871,
"learning_rate": 3.0367426072339112e-05,
"loss": 0.634796142578125,
"step": 615
},
{
"epoch": 3.9235668789808917,
"grad_norm": 0.11257872730493546,
"learning_rate": 3.031683106425169e-05,
"loss": 0.6205291748046875,
"step": 616
},
{
"epoch": 3.9299363057324843,
"grad_norm": 0.10949276387691498,
"learning_rate": 3.0269978191988948e-05,
"loss": 0.5538330078125,
"step": 617
},
{
"epoch": 3.9363057324840764,
"grad_norm": 0.11157351732254028,
"learning_rate": 3.0226868757345395e-05,
"loss": 0.5657310485839844,
"step": 618
},
{
"epoch": 3.9426751592356686,
"grad_norm": 0.11258745938539505,
"learning_rate": 3.0187503958105123e-05,
"loss": 0.5833358764648438,
"step": 619
},
{
"epoch": 3.949044585987261,
"grad_norm": 0.11174048483371735,
"learning_rate": 3.0151884888008588e-05,
"loss": 0.5911941528320312,
"step": 620
},
{
"epoch": 3.9554140127388537,
"grad_norm": 0.107634037733078,
"learning_rate": 3.0120012536722087e-05,
"loss": 0.5614414215087891,
"step": 621
},
{
"epoch": 3.961783439490446,
"grad_norm": 0.11546964943408966,
"learning_rate": 3.0091887789810397e-05,
"loss": 0.5820770263671875,
"step": 622
},
{
"epoch": 3.968152866242038,
"grad_norm": 0.10852184891700745,
"learning_rate": 3.0067511428712072e-05,
"loss": 0.5699009895324707,
"step": 623
},
{
"epoch": 3.9745222929936306,
"grad_norm": 0.11604326963424683,
"learning_rate": 3.004688413071782e-05,
"loss": 0.58349609375,
"step": 624
},
{
"epoch": 3.980891719745223,
"grad_norm": 0.115114226937294,
"learning_rate": 3.0030006468951553e-05,
"loss": 0.5985107421875,
"step": 625
},
{
"epoch": 3.9872611464968153,
"grad_norm": 0.11075790971517563,
"learning_rate": 3.0016878912354617e-05,
"loss": 0.5899734497070312,
"step": 626
},
{
"epoch": 3.9936305732484074,
"grad_norm": 0.11452137678861618,
"learning_rate": 3.0007501825672667e-05,
"loss": 0.5993270874023438,
"step": 627
},
{
"epoch": 4.0,
"grad_norm": 0.10962215065956116,
"learning_rate": 3.0001875469445524e-05,
"loss": 0.577056884765625,
"step": 628
},
{
"epoch": 4.0,
"eval_loss": 0.5670642852783203,
"eval_runtime": 5.1926,
"eval_samples_per_second": 1.348,
"eval_steps_per_second": 0.193,
"step": 628
}
],
"logging_steps": 1.0,
"max_steps": 628,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 0,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.594651397478196e+20,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}