AgroAdapt / trainer_state.json
Charley890's picture
Upload 9 files
b12d73f verified
Raw
History Blame Contribute Delete
230 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 253,
"global_step": 1265,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003952569169960474,
"grad_norm": 1.1627222299575806,
"learning_rate": 0.0,
"loss": 1.587890625,
"step": 1
},
{
"epoch": 0.007905138339920948,
"grad_norm": 1.1683260202407837,
"learning_rate": 4.6875e-06,
"loss": 1.544921875,
"step": 2
},
{
"epoch": 0.011857707509881422,
"grad_norm": 1.1862308979034424,
"learning_rate": 9.375e-06,
"loss": 1.5966796875,
"step": 3
},
{
"epoch": 0.015810276679841896,
"grad_norm": 1.151333212852478,
"learning_rate": 1.40625e-05,
"loss": 1.59765625,
"step": 4
},
{
"epoch": 0.019762845849802372,
"grad_norm": 1.0971604585647583,
"learning_rate": 1.875e-05,
"loss": 1.537109375,
"step": 5
},
{
"epoch": 0.023715415019762844,
"grad_norm": 1.0160741806030273,
"learning_rate": 2.3437499999999997e-05,
"loss": 1.5908203125,
"step": 6
},
{
"epoch": 0.02766798418972332,
"grad_norm": 0.8460241556167603,
"learning_rate": 2.8125e-05,
"loss": 1.486328125,
"step": 7
},
{
"epoch": 0.03162055335968379,
"grad_norm": 0.8412477970123291,
"learning_rate": 3.28125e-05,
"loss": 1.462890625,
"step": 8
},
{
"epoch": 0.03557312252964427,
"grad_norm": 0.5087709426879883,
"learning_rate": 3.75e-05,
"loss": 1.345703125,
"step": 9
},
{
"epoch": 0.039525691699604744,
"grad_norm": 0.2874377965927124,
"learning_rate": 4.2187499999999995e-05,
"loss": 1.34765625,
"step": 10
},
{
"epoch": 0.043478260869565216,
"grad_norm": 0.2331884503364563,
"learning_rate": 4.6874999999999994e-05,
"loss": 1.328125,
"step": 11
},
{
"epoch": 0.04743083003952569,
"grad_norm": 0.14886870980262756,
"learning_rate": 5.156249999999999e-05,
"loss": 1.13031005859375,
"step": 12
},
{
"epoch": 0.05138339920948617,
"grad_norm": 0.18171799182891846,
"learning_rate": 5.625e-05,
"loss": 1.3154296875,
"step": 13
},
{
"epoch": 0.05533596837944664,
"grad_norm": 0.1508169174194336,
"learning_rate": 6.09375e-05,
"loss": 1.16778564453125,
"step": 14
},
{
"epoch": 0.05928853754940711,
"grad_norm": 0.16553623974323273,
"learning_rate": 6.5625e-05,
"loss": 1.30078125,
"step": 15
},
{
"epoch": 0.06324110671936758,
"grad_norm": 0.14081628620624542,
"learning_rate": 7.03125e-05,
"loss": 1.233642578125,
"step": 16
},
{
"epoch": 0.06719367588932806,
"grad_norm": 0.10984048992395401,
"learning_rate": 7.5e-05,
"loss": 1.1689453125,
"step": 17
},
{
"epoch": 0.07114624505928854,
"grad_norm": 0.08631673455238342,
"learning_rate": 7.968749999999999e-05,
"loss": 1.21875,
"step": 18
},
{
"epoch": 0.07509881422924901,
"grad_norm": 0.07686670124530792,
"learning_rate": 8.437499999999999e-05,
"loss": 1.2626953125,
"step": 19
},
{
"epoch": 0.07905138339920949,
"grad_norm": 0.08009079098701477,
"learning_rate": 8.906249999999999e-05,
"loss": 1.2177734375,
"step": 20
},
{
"epoch": 0.08300395256916997,
"grad_norm": 0.08306403458118439,
"learning_rate": 9.374999999999999e-05,
"loss": 1.2236328125,
"step": 21
},
{
"epoch": 0.08695652173913043,
"grad_norm": 0.09083710610866547,
"learning_rate": 9.843749999999999e-05,
"loss": 1.2236328125,
"step": 22
},
{
"epoch": 0.09090909090909091,
"grad_norm": 0.09399152547121048,
"learning_rate": 0.00010312499999999999,
"loss": 1.1141357421875,
"step": 23
},
{
"epoch": 0.09486166007905138,
"grad_norm": 0.07401788979768753,
"learning_rate": 0.00010781249999999998,
"loss": 1.208984375,
"step": 24
},
{
"epoch": 0.09881422924901186,
"grad_norm": 0.06614270061254501,
"learning_rate": 0.0001125,
"loss": 1.0986328125,
"step": 25
},
{
"epoch": 0.10276679841897234,
"grad_norm": 0.05751989036798477,
"learning_rate": 0.0001171875,
"loss": 1.15283203125,
"step": 26
},
{
"epoch": 0.1067193675889328,
"grad_norm": 0.05574972927570343,
"learning_rate": 0.000121875,
"loss": 1.11767578125,
"step": 27
},
{
"epoch": 0.11067193675889328,
"grad_norm": 0.05420740693807602,
"learning_rate": 0.0001265625,
"loss": 1.1435546875,
"step": 28
},
{
"epoch": 0.11462450592885376,
"grad_norm": 0.05071847513318062,
"learning_rate": 0.00013125,
"loss": 1.01220703125,
"step": 29
},
{
"epoch": 0.11857707509881422,
"grad_norm": 0.05072321742773056,
"learning_rate": 0.0001359375,
"loss": 1.11376953125,
"step": 30
},
{
"epoch": 0.1225296442687747,
"grad_norm": 0.055756594985723495,
"learning_rate": 0.000140625,
"loss": 1.16064453125,
"step": 31
},
{
"epoch": 0.12648221343873517,
"grad_norm": 0.06868632137775421,
"learning_rate": 0.0001453125,
"loss": 1.10107421875,
"step": 32
},
{
"epoch": 0.13043478260869565,
"grad_norm": 0.045417219400405884,
"learning_rate": 0.00015,
"loss": 1.0869140625,
"step": 33
},
{
"epoch": 0.13438735177865613,
"grad_norm": 0.04619515314698219,
"learning_rate": 0.00015468749999999999,
"loss": 1.1591796875,
"step": 34
},
{
"epoch": 0.1383399209486166,
"grad_norm": 0.04595471918582916,
"learning_rate": 0.00015937499999999998,
"loss": 1.1640625,
"step": 35
},
{
"epoch": 0.1422924901185771,
"grad_norm": 0.04469190537929535,
"learning_rate": 0.00016406249999999998,
"loss": 1.162109375,
"step": 36
},
{
"epoch": 0.14624505928853754,
"grad_norm": 0.04816310480237007,
"learning_rate": 0.00016874999999999998,
"loss": 1.142578125,
"step": 37
},
{
"epoch": 0.15019762845849802,
"grad_norm": 0.04557616636157036,
"learning_rate": 0.00017343749999999998,
"loss": 1.13671875,
"step": 38
},
{
"epoch": 0.1541501976284585,
"grad_norm": 0.04401496797800064,
"learning_rate": 0.00017812499999999998,
"loss": 1.12255859375,
"step": 39
},
{
"epoch": 0.15810276679841898,
"grad_norm": 0.04669838771224022,
"learning_rate": 0.00018281249999999998,
"loss": 1.14208984375,
"step": 40
},
{
"epoch": 0.16205533596837945,
"grad_norm": 0.040364984422922134,
"learning_rate": 0.00018749999999999998,
"loss": 1.03271484375,
"step": 41
},
{
"epoch": 0.16600790513833993,
"grad_norm": 0.03872290626168251,
"learning_rate": 0.00019218749999999998,
"loss": 1.1005859375,
"step": 42
},
{
"epoch": 0.16996047430830039,
"grad_norm": 0.03874187171459198,
"learning_rate": 0.00019687499999999997,
"loss": 1.080078125,
"step": 43
},
{
"epoch": 0.17391304347826086,
"grad_norm": 0.0381033681333065,
"learning_rate": 0.00020156249999999997,
"loss": 1.05419921875,
"step": 44
},
{
"epoch": 0.17786561264822134,
"grad_norm": 0.043727777898311615,
"learning_rate": 0.00020624999999999997,
"loss": 1.08642578125,
"step": 45
},
{
"epoch": 0.18181818181818182,
"grad_norm": 0.038846664130687714,
"learning_rate": 0.00021093749999999997,
"loss": 1.09375,
"step": 46
},
{
"epoch": 0.1857707509881423,
"grad_norm": 0.033395882695913315,
"learning_rate": 0.00021562499999999997,
"loss": 0.85516357421875,
"step": 47
},
{
"epoch": 0.18972332015810275,
"grad_norm": 0.04211333394050598,
"learning_rate": 0.00022031249999999997,
"loss": 1.1044921875,
"step": 48
},
{
"epoch": 0.19367588932806323,
"grad_norm": 0.03982433304190636,
"learning_rate": 0.000225,
"loss": 1.04345703125,
"step": 49
},
{
"epoch": 0.1976284584980237,
"grad_norm": 0.04038688540458679,
"learning_rate": 0.0002296875,
"loss": 1.08544921875,
"step": 50
},
{
"epoch": 0.2015810276679842,
"grad_norm": 0.035684842616319656,
"learning_rate": 0.000234375,
"loss": 1.091796875,
"step": 51
},
{
"epoch": 0.20553359683794467,
"grad_norm": 0.038577575236558914,
"learning_rate": 0.0002390625,
"loss": 0.95556640625,
"step": 52
},
{
"epoch": 0.20948616600790515,
"grad_norm": 0.0394609197974205,
"learning_rate": 0.00024375,
"loss": 1.0859375,
"step": 53
},
{
"epoch": 0.2134387351778656,
"grad_norm": 0.03605200722813606,
"learning_rate": 0.00024843749999999996,
"loss": 1.06005859375,
"step": 54
},
{
"epoch": 0.21739130434782608,
"grad_norm": 0.0389254167675972,
"learning_rate": 0.000253125,
"loss": 1.07763671875,
"step": 55
},
{
"epoch": 0.22134387351778656,
"grad_norm": 0.0410747230052948,
"learning_rate": 0.00025781249999999996,
"loss": 1.03369140625,
"step": 56
},
{
"epoch": 0.22529644268774704,
"grad_norm": 0.03684670105576515,
"learning_rate": 0.0002625,
"loss": 0.94970703125,
"step": 57
},
{
"epoch": 0.22924901185770752,
"grad_norm": 0.04475630819797516,
"learning_rate": 0.00026718749999999996,
"loss": 1.046875,
"step": 58
},
{
"epoch": 0.233201581027668,
"grad_norm": 0.03854816406965256,
"learning_rate": 0.000271875,
"loss": 1.09423828125,
"step": 59
},
{
"epoch": 0.23715415019762845,
"grad_norm": 0.04927290976047516,
"learning_rate": 0.00027656249999999995,
"loss": 1.0517578125,
"step": 60
},
{
"epoch": 0.24110671936758893,
"grad_norm": 0.04138105735182762,
"learning_rate": 0.00028125,
"loss": 0.982421875,
"step": 61
},
{
"epoch": 0.2450592885375494,
"grad_norm": 0.03985954076051712,
"learning_rate": 0.00028593749999999995,
"loss": 0.88995361328125,
"step": 62
},
{
"epoch": 0.2490118577075099,
"grad_norm": 0.04129613935947418,
"learning_rate": 0.000290625,
"loss": 0.98583984375,
"step": 63
},
{
"epoch": 0.25296442687747034,
"grad_norm": 0.040125906467437744,
"learning_rate": 0.00029531249999999995,
"loss": 1.0390625,
"step": 64
},
{
"epoch": 0.25691699604743085,
"grad_norm": 0.043358784168958664,
"learning_rate": 0.0003,
"loss": 1.033203125,
"step": 65
},
{
"epoch": 0.2608695652173913,
"grad_norm": 0.04132722690701485,
"learning_rate": 0.0002999995381326571,
"loss": 1.04150390625,
"step": 66
},
{
"epoch": 0.2648221343873518,
"grad_norm": 0.042613789439201355,
"learning_rate": 0.0002999981525337889,
"loss": 1.0712890625,
"step": 67
},
{
"epoch": 0.26877470355731226,
"grad_norm": 0.0416109599173069,
"learning_rate": 0.00029999584321287615,
"loss": 0.990234375,
"step": 68
},
{
"epoch": 0.2727272727272727,
"grad_norm": 0.04536754637956619,
"learning_rate": 0.0002999926101857205,
"loss": 1.01123046875,
"step": 69
},
{
"epoch": 0.2766798418972332,
"grad_norm": 0.03991825506091118,
"learning_rate": 0.0002999884534744437,
"loss": 1.0419921875,
"step": 70
},
{
"epoch": 0.28063241106719367,
"grad_norm": 0.05060945823788643,
"learning_rate": 0.0002999833731074881,
"loss": 1.0078125,
"step": 71
},
{
"epoch": 0.2845849802371542,
"grad_norm": 0.040758371353149414,
"learning_rate": 0.00029997736911961594,
"loss": 1.0458984375,
"step": 72
},
{
"epoch": 0.2885375494071146,
"grad_norm": 0.047824740409851074,
"learning_rate": 0.0002999704415519094,
"loss": 1.0048828125,
"step": 73
},
{
"epoch": 0.2924901185770751,
"grad_norm": 0.03890911117196083,
"learning_rate": 0.00029996259045177024,
"loss": 1.02392578125,
"step": 74
},
{
"epoch": 0.2964426877470356,
"grad_norm": 0.04222744703292847,
"learning_rate": 0.00029995381587291935,
"loss": 0.9697265625,
"step": 75
},
{
"epoch": 0.30039525691699603,
"grad_norm": 0.04298309609293938,
"learning_rate": 0.00029994411787539674,
"loss": 1.0263671875,
"step": 76
},
{
"epoch": 0.30434782608695654,
"grad_norm": 0.044538713991642,
"learning_rate": 0.0002999334965255607,
"loss": 1.0126953125,
"step": 77
},
{
"epoch": 0.308300395256917,
"grad_norm": 0.04344265162944794,
"learning_rate": 0.0002999219518960875,
"loss": 1.00537109375,
"step": 78
},
{
"epoch": 0.31225296442687744,
"grad_norm": 0.041526082903146744,
"learning_rate": 0.00029990948406597123,
"loss": 1.0029296875,
"step": 79
},
{
"epoch": 0.31620553359683795,
"grad_norm": 0.040406595915555954,
"learning_rate": 0.00029989609312052254,
"loss": 0.9951171875,
"step": 80
},
{
"epoch": 0.3201581027667984,
"grad_norm": 0.04501129314303398,
"learning_rate": 0.0002998817791513688,
"loss": 0.91748046875,
"step": 81
},
{
"epoch": 0.3241106719367589,
"grad_norm": 0.04174388572573662,
"learning_rate": 0.0002998665422564531,
"loss": 0.982421875,
"step": 82
},
{
"epoch": 0.32806324110671936,
"grad_norm": 0.0424112044274807,
"learning_rate": 0.0002998503825400335,
"loss": 1.05224609375,
"step": 83
},
{
"epoch": 0.33201581027667987,
"grad_norm": 0.04236952215433121,
"learning_rate": 0.00029983330011268254,
"loss": 0.9775390625,
"step": 84
},
{
"epoch": 0.3359683794466403,
"grad_norm": 0.04133501648902893,
"learning_rate": 0.00029981529509128636,
"loss": 0.994140625,
"step": 85
},
{
"epoch": 0.33992094861660077,
"grad_norm": 0.040734488517045975,
"learning_rate": 0.00029979636759904394,
"loss": 1.001953125,
"step": 86
},
{
"epoch": 0.3438735177865613,
"grad_norm": 0.042946454137563705,
"learning_rate": 0.00029977651776546627,
"loss": 0.98583984375,
"step": 87
},
{
"epoch": 0.34782608695652173,
"grad_norm": 0.04548358544707298,
"learning_rate": 0.00029975574572637547,
"loss": 0.97021484375,
"step": 88
},
{
"epoch": 0.35177865612648224,
"grad_norm": 0.042308006435632706,
"learning_rate": 0.0002997340516239037,
"loss": 1.02001953125,
"step": 89
},
{
"epoch": 0.3557312252964427,
"grad_norm": 0.04056175798177719,
"learning_rate": 0.00029971143560649237,
"loss": 0.9368896484375,
"step": 90
},
{
"epoch": 0.35968379446640314,
"grad_norm": 0.04562252387404442,
"learning_rate": 0.0002996878978288913,
"loss": 0.978515625,
"step": 91
},
{
"epoch": 0.36363636363636365,
"grad_norm": 0.04564323648810387,
"learning_rate": 0.00029966343845215705,
"loss": 0.9833984375,
"step": 92
},
{
"epoch": 0.3675889328063241,
"grad_norm": 0.03752854838967323,
"learning_rate": 0.0002996380576436524,
"loss": 0.9697265625,
"step": 93
},
{
"epoch": 0.3715415019762846,
"grad_norm": 0.04243145510554314,
"learning_rate": 0.0002996117555770452,
"loss": 0.9501953125,
"step": 94
},
{
"epoch": 0.37549407114624506,
"grad_norm": 0.04101577773690224,
"learning_rate": 0.0002995845324323066,
"loss": 1.00048828125,
"step": 95
},
{
"epoch": 0.3794466403162055,
"grad_norm": 0.045690495520830154,
"learning_rate": 0.0002995563883957104,
"loss": 1.02783203125,
"step": 96
},
{
"epoch": 0.383399209486166,
"grad_norm": 0.04030710831284523,
"learning_rate": 0.00029952732365983174,
"loss": 0.836669921875,
"step": 97
},
{
"epoch": 0.38735177865612647,
"grad_norm": 0.040962621569633484,
"learning_rate": 0.0002994973384235453,
"loss": 0.98779296875,
"step": 98
},
{
"epoch": 0.391304347826087,
"grad_norm": 0.040998805314302444,
"learning_rate": 0.00029946643289202455,
"loss": 0.97509765625,
"step": 99
},
{
"epoch": 0.3952569169960474,
"grad_norm": 0.04241682216525078,
"learning_rate": 0.0002994346072767399,
"loss": 0.990234375,
"step": 100
},
{
"epoch": 0.39920948616600793,
"grad_norm": 0.04064636677503586,
"learning_rate": 0.00029940186179545745,
"loss": 0.9541015625,
"step": 101
},
{
"epoch": 0.4031620553359684,
"grad_norm": 0.04384373873472214,
"learning_rate": 0.00029936819667223747,
"loss": 0.96337890625,
"step": 102
},
{
"epoch": 0.40711462450592883,
"grad_norm": 0.04403546452522278,
"learning_rate": 0.00029933361213743285,
"loss": 0.98779296875,
"step": 103
},
{
"epoch": 0.41106719367588934,
"grad_norm": 0.04663854464888573,
"learning_rate": 0.00029929810842768765,
"loss": 0.916015625,
"step": 104
},
{
"epoch": 0.4150197628458498,
"grad_norm": 0.04587282985448837,
"learning_rate": 0.00029926168578593514,
"loss": 0.91650390625,
"step": 105
},
{
"epoch": 0.4189723320158103,
"grad_norm": 0.04396233335137367,
"learning_rate": 0.00029922434446139653,
"loss": 0.9599609375,
"step": 106
},
{
"epoch": 0.42292490118577075,
"grad_norm": 0.04746716096997261,
"learning_rate": 0.00029918608470957915,
"loss": 0.962890625,
"step": 107
},
{
"epoch": 0.4268774703557312,
"grad_norm": 0.04683246091008186,
"learning_rate": 0.0002991469067922743,
"loss": 0.97607421875,
"step": 108
},
{
"epoch": 0.4308300395256917,
"grad_norm": 0.04502679780125618,
"learning_rate": 0.00029910681097755637,
"loss": 0.93408203125,
"step": 109
},
{
"epoch": 0.43478260869565216,
"grad_norm": 0.052390001714229584,
"learning_rate": 0.00029906579753978,
"loss": 0.94140625,
"step": 110
},
{
"epoch": 0.43873517786561267,
"grad_norm": 0.046164579689502716,
"learning_rate": 0.00029902386675957865,
"loss": 0.94482421875,
"step": 111
},
{
"epoch": 0.4426877470355731,
"grad_norm": 0.050589125603437424,
"learning_rate": 0.00029898101892386305,
"loss": 0.97705078125,
"step": 112
},
{
"epoch": 0.44664031620553357,
"grad_norm": 0.05410892516374588,
"learning_rate": 0.0002989372543258184,
"loss": 0.93359375,
"step": 113
},
{
"epoch": 0.4505928853754941,
"grad_norm": 0.046691250056028366,
"learning_rate": 0.0002988925732649033,
"loss": 0.9716796875,
"step": 114
},
{
"epoch": 0.45454545454545453,
"grad_norm": 0.058371126651763916,
"learning_rate": 0.0002988469760468467,
"loss": 1.02685546875,
"step": 115
},
{
"epoch": 0.45849802371541504,
"grad_norm": 0.05259089171886444,
"learning_rate": 0.00029880046298364686,
"loss": 0.9404296875,
"step": 116
},
{
"epoch": 0.4624505928853755,
"grad_norm": 0.05376051366329193,
"learning_rate": 0.0002987530343935683,
"loss": 0.99755859375,
"step": 117
},
{
"epoch": 0.466403162055336,
"grad_norm": 0.0611630342900753,
"learning_rate": 0.0002987046906011402,
"loss": 0.91064453125,
"step": 118
},
{
"epoch": 0.47035573122529645,
"grad_norm": 0.04968439042568207,
"learning_rate": 0.00029865543193715395,
"loss": 0.79779052734375,
"step": 119
},
{
"epoch": 0.4743083003952569,
"grad_norm": 0.04552493244409561,
"learning_rate": 0.0002986052587386609,
"loss": 0.97900390625,
"step": 120
},
{
"epoch": 0.4782608695652174,
"grad_norm": 0.04429067298769951,
"learning_rate": 0.00029855417134897014,
"loss": 0.9873046875,
"step": 121
},
{
"epoch": 0.48221343873517786,
"grad_norm": 0.04980103299021721,
"learning_rate": 0.0002985021701176461,
"loss": 0.978515625,
"step": 122
},
{
"epoch": 0.48616600790513836,
"grad_norm": 0.049386586993932724,
"learning_rate": 0.0002984492554005061,
"loss": 0.92529296875,
"step": 123
},
{
"epoch": 0.4901185770750988,
"grad_norm": 0.052703533321619034,
"learning_rate": 0.00029839542755961794,
"loss": 0.9423828125,
"step": 124
},
{
"epoch": 0.49407114624505927,
"grad_norm": 0.04399961978197098,
"learning_rate": 0.0002983406869632976,
"loss": 0.96630859375,
"step": 125
},
{
"epoch": 0.4980237154150198,
"grad_norm": 0.04781800135970116,
"learning_rate": 0.0002982850339861064,
"loss": 0.9765625,
"step": 126
},
{
"epoch": 0.5019762845849802,
"grad_norm": 0.047682613134384155,
"learning_rate": 0.0002982284690088486,
"loss": 0.96044921875,
"step": 127
},
{
"epoch": 0.5059288537549407,
"grad_norm": 0.05390389263629913,
"learning_rate": 0.0002981709924185691,
"loss": 0.94677734375,
"step": 128
},
{
"epoch": 0.5098814229249012,
"grad_norm": 0.041129425168037415,
"learning_rate": 0.00029811260460855003,
"loss": 0.9169921875,
"step": 129
},
{
"epoch": 0.5138339920948617,
"grad_norm": 0.05134471133351326,
"learning_rate": 0.0002980533059783089,
"loss": 0.9384765625,
"step": 130
},
{
"epoch": 0.5177865612648221,
"grad_norm": 0.04351402446627617,
"learning_rate": 0.00029799309693359535,
"loss": 0.87646484375,
"step": 131
},
{
"epoch": 0.5217391304347826,
"grad_norm": 0.05380969122052193,
"learning_rate": 0.00029793197788638843,
"loss": 0.984375,
"step": 132
},
{
"epoch": 0.525691699604743,
"grad_norm": 0.047631990164518356,
"learning_rate": 0.00029786994925489407,
"loss": 0.984375,
"step": 133
},
{
"epoch": 0.5296442687747036,
"grad_norm": 0.056191910058259964,
"learning_rate": 0.00029780701146354173,
"loss": 0.95458984375,
"step": 134
},
{
"epoch": 0.5335968379446641,
"grad_norm": 0.04604225605726242,
"learning_rate": 0.00029774316494298207,
"loss": 0.927001953125,
"step": 135
},
{
"epoch": 0.5375494071146245,
"grad_norm": 0.04962369054555893,
"learning_rate": 0.00029767841013008355,
"loss": 0.98046875,
"step": 136
},
{
"epoch": 0.541501976284585,
"grad_norm": 0.045723069459199905,
"learning_rate": 0.00029761274746792956,
"loss": 0.97119140625,
"step": 137
},
{
"epoch": 0.5454545454545454,
"grad_norm": 0.05229611694812775,
"learning_rate": 0.00029754617740581556,
"loss": 0.94384765625,
"step": 138
},
{
"epoch": 0.549407114624506,
"grad_norm": 0.04936910793185234,
"learning_rate": 0.00029747870039924576,
"loss": 0.955078125,
"step": 139
},
{
"epoch": 0.5533596837944664,
"grad_norm": 0.042374271899461746,
"learning_rate": 0.0002974103169099303,
"loss": 0.841064453125,
"step": 140
},
{
"epoch": 0.5573122529644269,
"grad_norm": 0.04642310366034508,
"learning_rate": 0.0002973410274057816,
"loss": 0.919921875,
"step": 141
},
{
"epoch": 0.5612648221343873,
"grad_norm": 0.060203034430742264,
"learning_rate": 0.0002972708323609118,
"loss": 0.9697265625,
"step": 142
},
{
"epoch": 0.5652173913043478,
"grad_norm": 0.054723016917705536,
"learning_rate": 0.0002971997322556289,
"loss": 0.91796875,
"step": 143
},
{
"epoch": 0.5691699604743083,
"grad_norm": 0.05615948513150215,
"learning_rate": 0.00029712772757643395,
"loss": 0.890625,
"step": 144
},
{
"epoch": 0.5731225296442688,
"grad_norm": 0.04686497151851654,
"learning_rate": 0.00029705481881601753,
"loss": 0.9296875,
"step": 145
},
{
"epoch": 0.5770750988142292,
"grad_norm": 0.05972789227962494,
"learning_rate": 0.00029698100647325627,
"loss": 0.94921875,
"step": 146
},
{
"epoch": 0.5810276679841897,
"grad_norm": 0.045615341514348984,
"learning_rate": 0.00029690629105320947,
"loss": 0.89599609375,
"step": 147
},
{
"epoch": 0.5849802371541502,
"grad_norm": 0.056290172040462494,
"learning_rate": 0.000296830673067116,
"loss": 0.96484375,
"step": 148
},
{
"epoch": 0.5889328063241107,
"grad_norm": 0.03920245170593262,
"learning_rate": 0.0002967541530323903,
"loss": 0.9521484375,
"step": 149
},
{
"epoch": 0.5928853754940712,
"grad_norm": 0.05123763158917427,
"learning_rate": 0.0002966767314726191,
"loss": 0.93896484375,
"step": 150
},
{
"epoch": 0.5968379446640316,
"grad_norm": 0.04955087602138519,
"learning_rate": 0.00029659840891755777,
"loss": 0.96728515625,
"step": 151
},
{
"epoch": 0.6007905138339921,
"grad_norm": 0.05180769041180611,
"learning_rate": 0.0002965191859031268,
"loss": 0.93701171875,
"step": 152
},
{
"epoch": 0.6047430830039525,
"grad_norm": 0.04893989488482475,
"learning_rate": 0.000296439062971408,
"loss": 0.96240234375,
"step": 153
},
{
"epoch": 0.6086956521739131,
"grad_norm": 0.04730680212378502,
"learning_rate": 0.0002963580406706409,
"loss": 0.9384765625,
"step": 154
},
{
"epoch": 0.6126482213438735,
"grad_norm": 0.044814035296440125,
"learning_rate": 0.00029627611955521885,
"loss": 0.9140625,
"step": 155
},
{
"epoch": 0.616600790513834,
"grad_norm": 0.045044906437397,
"learning_rate": 0.00029619330018568543,
"loss": 0.98974609375,
"step": 156
},
{
"epoch": 0.6205533596837944,
"grad_norm": 0.03976064175367355,
"learning_rate": 0.0002961095831287304,
"loss": 0.953125,
"step": 157
},
{
"epoch": 0.6245059288537549,
"grad_norm": 0.05014454200863838,
"learning_rate": 0.000296024968957186,
"loss": 0.90966796875,
"step": 158
},
{
"epoch": 0.6284584980237155,
"grad_norm": 0.05022059381008148,
"learning_rate": 0.000295939458250023,
"loss": 0.9423828125,
"step": 159
},
{
"epoch": 0.6324110671936759,
"grad_norm": 0.050143808126449585,
"learning_rate": 0.0002958530515923465,
"loss": 0.95947265625,
"step": 160
},
{
"epoch": 0.6363636363636364,
"grad_norm": 0.04551578313112259,
"learning_rate": 0.0002957657495753923,
"loss": 0.92333984375,
"step": 161
},
{
"epoch": 0.6403162055335968,
"grad_norm": 0.046222057193517685,
"learning_rate": 0.00029567755279652264,
"loss": 0.9638671875,
"step": 162
},
{
"epoch": 0.6442687747035574,
"grad_norm": 0.04669683426618576,
"learning_rate": 0.00029558846185922226,
"loss": 0.9169921875,
"step": 163
},
{
"epoch": 0.6482213438735178,
"grad_norm": 0.05498241260647774,
"learning_rate": 0.0002954984773730938,
"loss": 0.94921875,
"step": 164
},
{
"epoch": 0.6521739130434783,
"grad_norm": 0.04260798171162605,
"learning_rate": 0.0002954075999538544,
"loss": 0.8994140625,
"step": 165
},
{
"epoch": 0.6561264822134387,
"grad_norm": 0.0476594939827919,
"learning_rate": 0.00029531583022333093,
"loss": 0.8935546875,
"step": 166
},
{
"epoch": 0.6600790513833992,
"grad_norm": 0.04267974942922592,
"learning_rate": 0.00029522316880945573,
"loss": 0.93115234375,
"step": 167
},
{
"epoch": 0.6640316205533597,
"grad_norm": 0.046076323837041855,
"learning_rate": 0.0002951296163462627,
"loss": 0.9462890625,
"step": 168
},
{
"epoch": 0.6679841897233202,
"grad_norm": 0.043905530124902725,
"learning_rate": 0.0002950351734738825,
"loss": 0.87158203125,
"step": 169
},
{
"epoch": 0.6719367588932806,
"grad_norm": 0.03983068838715553,
"learning_rate": 0.0002949398408385387,
"loss": 0.9853515625,
"step": 170
},
{
"epoch": 0.6758893280632411,
"grad_norm": 0.040108658373355865,
"learning_rate": 0.00029484361909254273,
"loss": 0.9189453125,
"step": 171
},
{
"epoch": 0.6798418972332015,
"grad_norm": 0.04251674562692642,
"learning_rate": 0.00029474650889428985,
"loss": 0.88427734375,
"step": 172
},
{
"epoch": 0.6837944664031621,
"grad_norm": 0.045590125024318695,
"learning_rate": 0.0002946485109082547,
"loss": 0.95849609375,
"step": 173
},
{
"epoch": 0.6877470355731226,
"grad_norm": 0.04396858438849449,
"learning_rate": 0.00029454962580498635,
"loss": 0.94580078125,
"step": 174
},
{
"epoch": 0.691699604743083,
"grad_norm": 0.0419636070728302,
"learning_rate": 0.00029444985426110414,
"loss": 0.9111328125,
"step": 175
},
{
"epoch": 0.6956521739130435,
"grad_norm": 0.044178031384944916,
"learning_rate": 0.0002943491969592927,
"loss": 0.892578125,
"step": 176
},
{
"epoch": 0.6996047430830039,
"grad_norm": 0.04788000509142876,
"learning_rate": 0.00029424765458829755,
"loss": 0.90234375,
"step": 177
},
{
"epoch": 0.7035573122529645,
"grad_norm": 0.04179839417338371,
"learning_rate": 0.0002941452278429203,
"loss": 0.94580078125,
"step": 178
},
{
"epoch": 0.7075098814229249,
"grad_norm": 0.04924828186631203,
"learning_rate": 0.00029404191742401375,
"loss": 0.916015625,
"step": 179
},
{
"epoch": 0.7114624505928854,
"grad_norm": 0.03961114212870598,
"learning_rate": 0.0002939377240384773,
"loss": 0.8955078125,
"step": 180
},
{
"epoch": 0.7154150197628458,
"grad_norm": 0.04985342174768448,
"learning_rate": 0.000293832648399252,
"loss": 0.90234375,
"step": 181
},
{
"epoch": 0.7193675889328063,
"grad_norm": 0.04562315717339516,
"learning_rate": 0.00029372669122531577,
"loss": 0.93994140625,
"step": 182
},
{
"epoch": 0.7233201581027668,
"grad_norm": 0.044550821185112,
"learning_rate": 0.00029361985324167833,
"loss": 0.91162109375,
"step": 183
},
{
"epoch": 0.7272727272727273,
"grad_norm": 0.04301857203245163,
"learning_rate": 0.0002935121351793764,
"loss": 0.7841796875,
"step": 184
},
{
"epoch": 0.7312252964426877,
"grad_norm": 0.042543668299913406,
"learning_rate": 0.0002934035377754685,
"loss": 0.91943359375,
"step": 185
},
{
"epoch": 0.7351778656126482,
"grad_norm": 0.049981940537691116,
"learning_rate": 0.00029329406177303015,
"loss": 0.97021484375,
"step": 186
},
{
"epoch": 0.7391304347826086,
"grad_norm": 0.04402138292789459,
"learning_rate": 0.00029318370792114865,
"loss": 0.86962890625,
"step": 187
},
{
"epoch": 0.7430830039525692,
"grad_norm": 0.04544492065906525,
"learning_rate": 0.00029307247697491786,
"loss": 0.880859375,
"step": 188
},
{
"epoch": 0.7470355731225297,
"grad_norm": 0.046567656099796295,
"learning_rate": 0.00029296036969543327,
"loss": 0.939453125,
"step": 189
},
{
"epoch": 0.7509881422924901,
"grad_norm": 0.042909931391477585,
"learning_rate": 0.0002928473868497865,
"loss": 0.9482421875,
"step": 190
},
{
"epoch": 0.7549407114624506,
"grad_norm": 0.05513691529631615,
"learning_rate": 0.0002927335292110605,
"loss": 0.96826171875,
"step": 191
},
{
"epoch": 0.758893280632411,
"grad_norm": 0.03914443776011467,
"learning_rate": 0.0002926187975583236,
"loss": 0.7618408203125,
"step": 192
},
{
"epoch": 0.7628458498023716,
"grad_norm": 0.056443892419338226,
"learning_rate": 0.00029250319267662493,
"loss": 0.89501953125,
"step": 193
},
{
"epoch": 0.766798418972332,
"grad_norm": 0.04926628991961479,
"learning_rate": 0.0002923867153569882,
"loss": 0.93701171875,
"step": 194
},
{
"epoch": 0.7707509881422925,
"grad_norm": 0.04565820470452309,
"learning_rate": 0.00029226936639640736,
"loss": 0.83447265625,
"step": 195
},
{
"epoch": 0.7747035573122529,
"grad_norm": 0.047770265489816666,
"learning_rate": 0.00029215114659784003,
"loss": 0.9169921875,
"step": 196
},
{
"epoch": 0.7786561264822134,
"grad_norm": 0.05076134577393532,
"learning_rate": 0.00029203205677020275,
"loss": 0.923828125,
"step": 197
},
{
"epoch": 0.782608695652174,
"grad_norm": 0.0426226370036602,
"learning_rate": 0.0002919120977283653,
"loss": 0.8828125,
"step": 198
},
{
"epoch": 0.7865612648221344,
"grad_norm": 0.05760984495282173,
"learning_rate": 0.0002917912702931447,
"loss": 0.86669921875,
"step": 199
},
{
"epoch": 0.7905138339920948,
"grad_norm": 0.04304122552275658,
"learning_rate": 0.00029166957529130037,
"loss": 0.8818359375,
"step": 200
},
{
"epoch": 0.7944664031620553,
"grad_norm": 0.05602722242474556,
"learning_rate": 0.0002915470135555277,
"loss": 0.9150390625,
"step": 201
},
{
"epoch": 0.7984189723320159,
"grad_norm": 0.05378110706806183,
"learning_rate": 0.00029142358592445285,
"loss": 0.89404296875,
"step": 202
},
{
"epoch": 0.8023715415019763,
"grad_norm": 0.04891882464289665,
"learning_rate": 0.00029129929324262687,
"loss": 0.904296875,
"step": 203
},
{
"epoch": 0.8063241106719368,
"grad_norm": 0.04561693221330643,
"learning_rate": 0.00029117413636051966,
"loss": 0.98095703125,
"step": 204
},
{
"epoch": 0.8102766798418972,
"grad_norm": 0.04683287814259529,
"learning_rate": 0.00029104811613451484,
"loss": 0.93701171875,
"step": 205
},
{
"epoch": 0.8142292490118577,
"grad_norm": 0.04477319121360779,
"learning_rate": 0.000290921233426903,
"loss": 0.90869140625,
"step": 206
},
{
"epoch": 0.8181818181818182,
"grad_norm": 0.051787614822387695,
"learning_rate": 0.0002907934891058764,
"loss": 0.880859375,
"step": 207
},
{
"epoch": 0.8221343873517787,
"grad_norm": 0.042032573372125626,
"learning_rate": 0.000290664884045523,
"loss": 0.89990234375,
"step": 208
},
{
"epoch": 0.8260869565217391,
"grad_norm": 0.0502738319337368,
"learning_rate": 0.00029053541912582023,
"loss": 0.89892578125,
"step": 209
},
{
"epoch": 0.8300395256916996,
"grad_norm": 0.04846418276429176,
"learning_rate": 0.000290405095232629,
"loss": 0.9287109375,
"step": 210
},
{
"epoch": 0.83399209486166,
"grad_norm": 0.042253535240888596,
"learning_rate": 0.0002902739132576879,
"loss": 0.95361328125,
"step": 211
},
{
"epoch": 0.8379446640316206,
"grad_norm": 0.044552031904459,
"learning_rate": 0.00029014187409860697,
"loss": 0.88818359375,
"step": 212
},
{
"epoch": 0.841897233201581,
"grad_norm": 0.04693196713924408,
"learning_rate": 0.00029000897865886127,
"loss": 0.88134765625,
"step": 213
},
{
"epoch": 0.8458498023715415,
"grad_norm": 0.04980618506669998,
"learning_rate": 0.00028987522784778506,
"loss": 0.9248046875,
"step": 214
},
{
"epoch": 0.849802371541502,
"grad_norm": 0.04315394535660744,
"learning_rate": 0.0002897406225805656,
"loss": 0.86865234375,
"step": 215
},
{
"epoch": 0.8537549407114624,
"grad_norm": 0.04301592335104942,
"learning_rate": 0.0002896051637782365,
"loss": 0.91064453125,
"step": 216
},
{
"epoch": 0.857707509881423,
"grad_norm": 0.044881150126457214,
"learning_rate": 0.0002894688523676718,
"loss": 0.94384765625,
"step": 217
},
{
"epoch": 0.8616600790513834,
"grad_norm": 0.04752974957227707,
"learning_rate": 0.00028933168928157955,
"loss": 0.9453125,
"step": 218
},
{
"epoch": 0.8656126482213439,
"grad_norm": 0.042814064770936966,
"learning_rate": 0.00028919367545849527,
"loss": 0.93212890625,
"step": 219
},
{
"epoch": 0.8695652173913043,
"grad_norm": 0.04541821405291557,
"learning_rate": 0.0002890548118427757,
"loss": 0.9365234375,
"step": 220
},
{
"epoch": 0.8735177865612648,
"grad_norm": 0.04289292171597481,
"learning_rate": 0.00028891509938459224,
"loss": 0.9521484375,
"step": 221
},
{
"epoch": 0.8774703557312253,
"grad_norm": 0.040129248052835464,
"learning_rate": 0.0002887745390399244,
"loss": 0.955078125,
"step": 222
},
{
"epoch": 0.8814229249011858,
"grad_norm": 0.04864213243126869,
"learning_rate": 0.0002886331317705535,
"loss": 0.85546875,
"step": 223
},
{
"epoch": 0.8853754940711462,
"grad_norm": 0.04226663336157799,
"learning_rate": 0.0002884908785440557,
"loss": 0.8720703125,
"step": 224
},
{
"epoch": 0.8893280632411067,
"grad_norm": 0.04537901654839516,
"learning_rate": 0.0002883477803337959,
"loss": 0.912109375,
"step": 225
},
{
"epoch": 0.8932806324110671,
"grad_norm": 0.03907623887062073,
"learning_rate": 0.00028820383811892057,
"loss": 0.8544921875,
"step": 226
},
{
"epoch": 0.8972332015810277,
"grad_norm": 0.047970905900001526,
"learning_rate": 0.00028805905288435126,
"loss": 0.90087890625,
"step": 227
},
{
"epoch": 0.9011857707509882,
"grad_norm": 0.04218582808971405,
"learning_rate": 0.0002879134256207779,
"loss": 0.86962890625,
"step": 228
},
{
"epoch": 0.9051383399209486,
"grad_norm": 0.05012853816151619,
"learning_rate": 0.0002877669573246521,
"loss": 0.880859375,
"step": 229
},
{
"epoch": 0.9090909090909091,
"grad_norm": 0.041446082293987274,
"learning_rate": 0.00028761964899818015,
"loss": 0.93994140625,
"step": 230
},
{
"epoch": 0.9130434782608695,
"grad_norm": 0.04685799404978752,
"learning_rate": 0.00028747150164931597,
"loss": 0.8916015625,
"step": 231
},
{
"epoch": 0.9169960474308301,
"grad_norm": 0.044455114752054214,
"learning_rate": 0.00028732251629175497,
"loss": 0.93701171875,
"step": 232
},
{
"epoch": 0.9209486166007905,
"grad_norm": 0.04300787299871445,
"learning_rate": 0.00028717269394492624,
"loss": 0.91796875,
"step": 233
},
{
"epoch": 0.924901185770751,
"grad_norm": 0.04542584717273712,
"learning_rate": 0.00028702203563398605,
"loss": 0.8984375,
"step": 234
},
{
"epoch": 0.9288537549407114,
"grad_norm": 0.042647603899240494,
"learning_rate": 0.0002868705423898108,
"loss": 0.86328125,
"step": 235
},
{
"epoch": 0.932806324110672,
"grad_norm": 0.042481664568185806,
"learning_rate": 0.00028671821524898984,
"loss": 0.787261962890625,
"step": 236
},
{
"epoch": 0.9367588932806324,
"grad_norm": 0.04593292251229286,
"learning_rate": 0.00028656505525381836,
"loss": 0.91015625,
"step": 237
},
{
"epoch": 0.9407114624505929,
"grad_norm": 0.0421614944934845,
"learning_rate": 0.00028641106345229066,
"loss": 0.923828125,
"step": 238
},
{
"epoch": 0.9446640316205533,
"grad_norm": 0.0417473167181015,
"learning_rate": 0.0002862562408980922,
"loss": 0.880859375,
"step": 239
},
{
"epoch": 0.9486166007905138,
"grad_norm": 0.04324594512581825,
"learning_rate": 0.0002861005886505932,
"loss": 0.8974609375,
"step": 240
},
{
"epoch": 0.9525691699604744,
"grad_norm": 0.0489695779979229,
"learning_rate": 0.0002859441077748409,
"loss": 0.8818359375,
"step": 241
},
{
"epoch": 0.9565217391304348,
"grad_norm": 0.0438544861972332,
"learning_rate": 0.00028578679934155237,
"loss": 0.943359375,
"step": 242
},
{
"epoch": 0.9604743083003953,
"grad_norm": 0.047414906322956085,
"learning_rate": 0.0002856286644271074,
"loss": 0.9033203125,
"step": 243
},
{
"epoch": 0.9644268774703557,
"grad_norm": 0.049325939267873764,
"learning_rate": 0.0002854697041135408,
"loss": 0.91357421875,
"step": 244
},
{
"epoch": 0.9683794466403162,
"grad_norm": 0.04409405216574669,
"learning_rate": 0.0002853099194885351,
"loss": 0.80517578125,
"step": 245
},
{
"epoch": 0.9723320158102767,
"grad_norm": 0.047281622886657715,
"learning_rate": 0.00028514931164541336,
"loss": 0.912109375,
"step": 246
},
{
"epoch": 0.9762845849802372,
"grad_norm": 0.04580365866422653,
"learning_rate": 0.0002849878816831315,
"loss": 0.861328125,
"step": 247
},
{
"epoch": 0.9802371541501976,
"grad_norm": 0.04841425642371178,
"learning_rate": 0.0002848256307062704,
"loss": 0.89306640625,
"step": 248
},
{
"epoch": 0.9841897233201581,
"grad_norm": 0.04370254650712013,
"learning_rate": 0.0002846625598250293,
"loss": 0.91943359375,
"step": 249
},
{
"epoch": 0.9881422924901185,
"grad_norm": 0.03976978361606598,
"learning_rate": 0.00028449867015521707,
"loss": 0.7685546875,
"step": 250
},
{
"epoch": 0.9920948616600791,
"grad_norm": 0.04747812822461128,
"learning_rate": 0.00028433396281824544,
"loss": 0.9306640625,
"step": 251
},
{
"epoch": 0.9960474308300395,
"grad_norm": 0.03914341330528259,
"learning_rate": 0.0002841684389411209,
"loss": 0.84716796875,
"step": 252
},
{
"epoch": 1.0,
"grad_norm": 0.04547939449548721,
"learning_rate": 0.00028400209965643723,
"loss": 0.89306640625,
"step": 253
},
{
"epoch": 1.0,
"eval_loss": 0.86328125,
"eval_runtime": 2.213,
"eval_samples_per_second": 2.711,
"eval_steps_per_second": 0.452,
"step": 253
},
{
"epoch": 1.0039525691699605,
"grad_norm": 0.042374301701784134,
"learning_rate": 0.0002838349461023674,
"loss": 0.90478515625,
"step": 254
},
{
"epoch": 1.007905138339921,
"grad_norm": 0.043627265840768814,
"learning_rate": 0.00028366697942265617,
"loss": 0.89453125,
"step": 255
},
{
"epoch": 1.0118577075098814,
"grad_norm": 0.04519499093294144,
"learning_rate": 0.0002834982007666121,
"loss": 0.91748046875,
"step": 256
},
{
"epoch": 1.0158102766798418,
"grad_norm": 0.041247859597206116,
"learning_rate": 0.0002833286112890995,
"loss": 0.908203125,
"step": 257
},
{
"epoch": 1.0197628458498025,
"grad_norm": 0.042464207857847214,
"learning_rate": 0.0002831582121505309,
"loss": 0.90869140625,
"step": 258
},
{
"epoch": 1.023715415019763,
"grad_norm": 0.0450255461037159,
"learning_rate": 0.0002829870045168589,
"loss": 0.92626953125,
"step": 259
},
{
"epoch": 1.0276679841897234,
"grad_norm": 0.041911814361810684,
"learning_rate": 0.00028281498955956807,
"loss": 0.87353515625,
"step": 260
},
{
"epoch": 1.0316205533596838,
"grad_norm": 0.04590751603245735,
"learning_rate": 0.00028264216845566727,
"loss": 0.94287109375,
"step": 261
},
{
"epoch": 1.0355731225296443,
"grad_norm": 0.041068095713853836,
"learning_rate": 0.00028246854238768123,
"loss": 0.88330078125,
"step": 262
},
{
"epoch": 1.0395256916996047,
"grad_norm": 0.04542512446641922,
"learning_rate": 0.00028229411254364274,
"loss": 0.91943359375,
"step": 263
},
{
"epoch": 1.0434782608695652,
"grad_norm": 0.04547237604856491,
"learning_rate": 0.0002821188801170843,
"loss": 0.90625,
"step": 264
},
{
"epoch": 1.0474308300395256,
"grad_norm": 0.04166261851787567,
"learning_rate": 0.0002819428463070302,
"loss": 0.753753662109375,
"step": 265
},
{
"epoch": 1.051383399209486,
"grad_norm": 0.045231759548187256,
"learning_rate": 0.0002817660123179881,
"loss": 0.896484375,
"step": 266
},
{
"epoch": 1.0553359683794465,
"grad_norm": 0.03997467830777168,
"learning_rate": 0.0002815883793599409,
"loss": 0.844970703125,
"step": 267
},
{
"epoch": 1.0592885375494072,
"grad_norm": 0.04391000047326088,
"learning_rate": 0.0002814099486483384,
"loss": 0.912109375,
"step": 268
},
{
"epoch": 1.0632411067193677,
"grad_norm": 0.04376228153705597,
"learning_rate": 0.00028123072140408907,
"loss": 0.90576171875,
"step": 269
},
{
"epoch": 1.0671936758893281,
"grad_norm": 0.03993872553110123,
"learning_rate": 0.00028105069885355145,
"loss": 0.84814453125,
"step": 270
},
{
"epoch": 1.0711462450592886,
"grad_norm": 0.04249430447816849,
"learning_rate": 0.00028086988222852623,
"loss": 0.8671875,
"step": 271
},
{
"epoch": 1.075098814229249,
"grad_norm": 0.040229178965091705,
"learning_rate": 0.0002806882727662474,
"loss": 0.93896484375,
"step": 272
},
{
"epoch": 1.0790513833992095,
"grad_norm": 0.04056628420948982,
"learning_rate": 0.00028050587170937375,
"loss": 0.88427734375,
"step": 273
},
{
"epoch": 1.08300395256917,
"grad_norm": 0.039569560438394547,
"learning_rate": 0.00028032268030598093,
"loss": 0.90966796875,
"step": 274
},
{
"epoch": 1.0869565217391304,
"grad_norm": 0.04164031520485878,
"learning_rate": 0.00028013869980955225,
"loss": 0.9130859375,
"step": 275
},
{
"epoch": 1.0909090909090908,
"grad_norm": 0.038313645869493484,
"learning_rate": 0.00027995393147897023,
"loss": 0.830322265625,
"step": 276
},
{
"epoch": 1.0948616600790513,
"grad_norm": 0.040908657014369965,
"learning_rate": 0.0002797683765785085,
"loss": 0.90576171875,
"step": 277
},
{
"epoch": 1.098814229249012,
"grad_norm": 0.03984049707651138,
"learning_rate": 0.00027958203637782264,
"loss": 0.84521484375,
"step": 278
},
{
"epoch": 1.1027667984189724,
"grad_norm": 0.04440179839730263,
"learning_rate": 0.00027939491215194146,
"loss": 0.846435546875,
"step": 279
},
{
"epoch": 1.1067193675889329,
"grad_norm": 0.04004908725619316,
"learning_rate": 0.0002792070051812586,
"loss": 0.88232421875,
"step": 280
},
{
"epoch": 1.1106719367588933,
"grad_norm": 0.041686318814754486,
"learning_rate": 0.00027901831675152363,
"loss": 0.8740234375,
"step": 281
},
{
"epoch": 1.1146245059288538,
"grad_norm": 0.039405401796102524,
"learning_rate": 0.0002788288481538332,
"loss": 0.781097412109375,
"step": 282
},
{
"epoch": 1.1185770750988142,
"grad_norm": 0.040955573320388794,
"learning_rate": 0.0002786386006846222,
"loss": 0.8876953125,
"step": 283
},
{
"epoch": 1.1225296442687747,
"grad_norm": 0.04382171109318733,
"learning_rate": 0.000278447575645655,
"loss": 0.91259765625,
"step": 284
},
{
"epoch": 1.1264822134387351,
"grad_norm": 0.04224387928843498,
"learning_rate": 0.00027825577434401646,
"loss": 0.84130859375,
"step": 285
},
{
"epoch": 1.1304347826086956,
"grad_norm": 0.043710026890039444,
"learning_rate": 0.0002780631980921029,
"loss": 0.81787109375,
"step": 286
},
{
"epoch": 1.1343873517786562,
"grad_norm": 0.0418458990752697,
"learning_rate": 0.0002778698482076134,
"loss": 0.900390625,
"step": 287
},
{
"epoch": 1.1383399209486167,
"grad_norm": 0.04472304508090019,
"learning_rate": 0.0002776757260135405,
"loss": 0.8935546875,
"step": 288
},
{
"epoch": 1.1422924901185771,
"grad_norm": 0.04275103658437729,
"learning_rate": 0.00027748083283816126,
"loss": 0.90576171875,
"step": 289
},
{
"epoch": 1.1462450592885376,
"grad_norm": 0.046373337507247925,
"learning_rate": 0.00027728517001502815,
"loss": 0.87744140625,
"step": 290
},
{
"epoch": 1.150197628458498,
"grad_norm": 0.04072759300470352,
"learning_rate": 0.00027708873888296,
"loss": 0.90087890625,
"step": 291
},
{
"epoch": 1.1541501976284585,
"grad_norm": 0.04398782551288605,
"learning_rate": 0.0002768915407860327,
"loss": 0.8701171875,
"step": 292
},
{
"epoch": 1.158102766798419,
"grad_norm": 0.04115741327404976,
"learning_rate": 0.0002766935770735701,
"loss": 0.89306640625,
"step": 293
},
{
"epoch": 1.1620553359683794,
"grad_norm": 0.04533357545733452,
"learning_rate": 0.00027649484910013483,
"loss": 0.8232421875,
"step": 294
},
{
"epoch": 1.1660079051383399,
"grad_norm": 0.044129930436611176,
"learning_rate": 0.0002762953582255189,
"loss": 0.8515625,
"step": 295
},
{
"epoch": 1.1699604743083003,
"grad_norm": 0.046960361301898956,
"learning_rate": 0.00027609510581473443,
"loss": 0.85205078125,
"step": 296
},
{
"epoch": 1.1739130434782608,
"grad_norm": 0.042110152542591095,
"learning_rate": 0.0002758940932380043,
"loss": 0.8388671875,
"step": 297
},
{
"epoch": 1.1778656126482214,
"grad_norm": 0.0434475801885128,
"learning_rate": 0.000275692321870753,
"loss": 0.8818359375,
"step": 298
},
{
"epoch": 1.1818181818181819,
"grad_norm": 0.04657441005110741,
"learning_rate": 0.00027548979309359694,
"loss": 0.859375,
"step": 299
},
{
"epoch": 1.1857707509881423,
"grad_norm": 0.038384128361940384,
"learning_rate": 0.00027528650829233484,
"loss": 0.690155029296875,
"step": 300
},
{
"epoch": 1.1897233201581028,
"grad_norm": 0.05017929896712303,
"learning_rate": 0.0002750824688579389,
"loss": 0.89599609375,
"step": 301
},
{
"epoch": 1.1936758893280632,
"grad_norm": 0.04417145252227783,
"learning_rate": 0.00027487767618654467,
"loss": 0.84912109375,
"step": 302
},
{
"epoch": 1.1976284584980237,
"grad_norm": 0.05361942946910858,
"learning_rate": 0.0002746721316794417,
"loss": 0.876953125,
"step": 303
},
{
"epoch": 1.2015810276679841,
"grad_norm": 0.042196691036224365,
"learning_rate": 0.00027446583674306394,
"loss": 0.8984375,
"step": 304
},
{
"epoch": 1.2055335968379446,
"grad_norm": 0.04075762629508972,
"learning_rate": 0.00027425879278898034,
"loss": 0.77685546875,
"step": 305
},
{
"epoch": 1.2094861660079053,
"grad_norm": 0.050662342458963394,
"learning_rate": 0.0002740510012338847,
"loss": 0.89111328125,
"step": 306
},
{
"epoch": 1.2134387351778657,
"grad_norm": 0.041577134281396866,
"learning_rate": 0.00027384246349958653,
"loss": 0.8779296875,
"step": 307
},
{
"epoch": 1.2173913043478262,
"grad_norm": 0.04780205711722374,
"learning_rate": 0.00027363318101300077,
"loss": 0.89599609375,
"step": 308
},
{
"epoch": 1.2213438735177866,
"grad_norm": 0.04135953262448311,
"learning_rate": 0.0002734231552061386,
"loss": 0.83251953125,
"step": 309
},
{
"epoch": 1.225296442687747,
"grad_norm": 0.043677933514118195,
"learning_rate": 0.0002732123875160971,
"loss": 0.78271484375,
"step": 310
},
{
"epoch": 1.2292490118577075,
"grad_norm": 0.04680044949054718,
"learning_rate": 0.00027300087938505,
"loss": 0.87353515625,
"step": 311
},
{
"epoch": 1.233201581027668,
"grad_norm": 0.04444592073559761,
"learning_rate": 0.0002727886322602371,
"loss": 0.9150390625,
"step": 312
},
{
"epoch": 1.2371541501976284,
"grad_norm": 0.04775778949260712,
"learning_rate": 0.00027257564759395497,
"loss": 0.87353515625,
"step": 313
},
{
"epoch": 1.2411067193675889,
"grad_norm": 0.04651295766234398,
"learning_rate": 0.00027236192684354683,
"loss": 0.80810546875,
"step": 314
},
{
"epoch": 1.2450592885375493,
"grad_norm": 0.040339305996894836,
"learning_rate": 0.00027214747147139234,
"loss": 0.736236572265625,
"step": 315
},
{
"epoch": 1.2490118577075098,
"grad_norm": 0.04420219734311104,
"learning_rate": 0.00027193228294489794,
"loss": 0.82177734375,
"step": 316
},
{
"epoch": 1.2529644268774702,
"grad_norm": 0.07316038757562637,
"learning_rate": 0.0002717163627364867,
"loss": 0.86865234375,
"step": 317
},
{
"epoch": 1.256916996047431,
"grad_norm": 0.04813384637236595,
"learning_rate": 0.0002714997123235881,
"loss": 0.8505859375,
"step": 318
},
{
"epoch": 1.2608695652173914,
"grad_norm": 0.04286143556237221,
"learning_rate": 0.0002712823331886281,
"loss": 0.8642578125,
"step": 319
},
{
"epoch": 1.2648221343873518,
"grad_norm": 0.04291103035211563,
"learning_rate": 0.0002710642268190188,
"loss": 0.90478515625,
"step": 320
},
{
"epoch": 1.2687747035573123,
"grad_norm": 0.044597066938877106,
"learning_rate": 0.00027084539470714867,
"loss": 0.84033203125,
"step": 321
},
{
"epoch": 1.2727272727272727,
"grad_norm": 0.04486791417002678,
"learning_rate": 0.00027062583835037174,
"loss": 0.85693359375,
"step": 322
},
{
"epoch": 1.2766798418972332,
"grad_norm": 0.04800025373697281,
"learning_rate": 0.0002704055592509978,
"loss": 0.88232421875,
"step": 323
},
{
"epoch": 1.2806324110671936,
"grad_norm": 0.042168594896793365,
"learning_rate": 0.0002701845589162821,
"loss": 0.83642578125,
"step": 324
},
{
"epoch": 1.2845849802371543,
"grad_norm": 0.04465063661336899,
"learning_rate": 0.00026996283885841464,
"loss": 0.904296875,
"step": 325
},
{
"epoch": 1.2885375494071147,
"grad_norm": 0.044336192309856415,
"learning_rate": 0.0002697404005945105,
"loss": 0.85205078125,
"step": 326
},
{
"epoch": 1.2924901185770752,
"grad_norm": 0.04242439568042755,
"learning_rate": 0.0002695172456465987,
"loss": 0.89111328125,
"step": 327
},
{
"epoch": 1.2964426877470356,
"grad_norm": 0.04420636221766472,
"learning_rate": 0.0002692933755416125,
"loss": 0.83935546875,
"step": 328
},
{
"epoch": 1.300395256916996,
"grad_norm": 0.044761501252651215,
"learning_rate": 0.00026906879181137826,
"loss": 0.8779296875,
"step": 329
},
{
"epoch": 1.3043478260869565,
"grad_norm": 0.04770709574222565,
"learning_rate": 0.0002688434959926055,
"loss": 0.86474609375,
"step": 330
},
{
"epoch": 1.308300395256917,
"grad_norm": 0.04546400532126427,
"learning_rate": 0.0002686174896268762,
"loss": 0.86083984375,
"step": 331
},
{
"epoch": 1.3122529644268774,
"grad_norm": 0.0472126379609108,
"learning_rate": 0.0002683907742606342,
"loss": 0.86865234375,
"step": 332
},
{
"epoch": 1.316205533596838,
"grad_norm": 0.0454905666410923,
"learning_rate": 0.0002681633514451747,
"loss": 0.84912109375,
"step": 333
},
{
"epoch": 1.3201581027667983,
"grad_norm": 0.048112571239471436,
"learning_rate": 0.00026793522273663346,
"loss": 0.779296875,
"step": 334
},
{
"epoch": 1.3241106719367588,
"grad_norm": 0.044580429792404175,
"learning_rate": 0.0002677063896959766,
"loss": 0.85009765625,
"step": 335
},
{
"epoch": 1.3280632411067192,
"grad_norm": 0.045687440782785416,
"learning_rate": 0.0002674768538889893,
"loss": 0.912109375,
"step": 336
},
{
"epoch": 1.33201581027668,
"grad_norm": 0.04491416737437248,
"learning_rate": 0.00026724661688626544,
"loss": 0.83837890625,
"step": 337
},
{
"epoch": 1.3359683794466404,
"grad_norm": 0.04687702655792236,
"learning_rate": 0.0002670156802631972,
"loss": 0.85302734375,
"step": 338
},
{
"epoch": 1.3399209486166008,
"grad_norm": 0.042850445955991745,
"learning_rate": 0.0002667840455999633,
"loss": 0.8759765625,
"step": 339
},
{
"epoch": 1.3438735177865613,
"grad_norm": 0.05003659799695015,
"learning_rate": 0.00026655171448151927,
"loss": 0.84228515625,
"step": 340
},
{
"epoch": 1.3478260869565217,
"grad_norm": 0.042270537465810776,
"learning_rate": 0.0002663186884975859,
"loss": 0.8271484375,
"step": 341
},
{
"epoch": 1.3517786561264822,
"grad_norm": 0.04329278692603111,
"learning_rate": 0.0002660849692426387,
"loss": 0.8857421875,
"step": 342
},
{
"epoch": 1.3557312252964426,
"grad_norm": 0.04139779880642891,
"learning_rate": 0.00026585055831589665,
"loss": 0.811767578125,
"step": 343
},
{
"epoch": 1.359683794466403,
"grad_norm": 0.04415592923760414,
"learning_rate": 0.0002656154573213118,
"loss": 0.85009765625,
"step": 344
},
{
"epoch": 1.3636363636363638,
"grad_norm": 0.04318411275744438,
"learning_rate": 0.0002653796678675576,
"loss": 0.85009765625,
"step": 345
},
{
"epoch": 1.3675889328063242,
"grad_norm": 0.042097777128219604,
"learning_rate": 0.0002651431915680187,
"loss": 0.8427734375,
"step": 346
},
{
"epoch": 1.3715415019762847,
"grad_norm": 0.04307622089982033,
"learning_rate": 0.00026490603004077903,
"loss": 0.82275390625,
"step": 347
},
{
"epoch": 1.3754940711462451,
"grad_norm": 0.04380422830581665,
"learning_rate": 0.00026466818490861156,
"loss": 0.88720703125,
"step": 348
},
{
"epoch": 1.3794466403162056,
"grad_norm": 0.044478900730609894,
"learning_rate": 0.0002644296577989666,
"loss": 0.912109375,
"step": 349
},
{
"epoch": 1.383399209486166,
"grad_norm": 0.04454903304576874,
"learning_rate": 0.00026419045034396094,
"loss": 0.732666015625,
"step": 350
},
{
"epoch": 1.3873517786561265,
"grad_norm": 0.042623698711395264,
"learning_rate": 0.0002639505641803666,
"loss": 0.875,
"step": 351
},
{
"epoch": 1.391304347826087,
"grad_norm": 0.04541714861989021,
"learning_rate": 0.0002637100009495996,
"loss": 0.8505859375,
"step": 352
},
{
"epoch": 1.3952569169960474,
"grad_norm": 0.042143724858760834,
"learning_rate": 0.00026346876229770884,
"loss": 0.8740234375,
"step": 353
},
{
"epoch": 1.3992094861660078,
"grad_norm": 0.04524431750178337,
"learning_rate": 0.00026322684987536483,
"loss": 0.83740234375,
"step": 354
},
{
"epoch": 1.4031620553359683,
"grad_norm": 0.04276207089424133,
"learning_rate": 0.0002629842653378482,
"loss": 0.84619140625,
"step": 355
},
{
"epoch": 1.4071146245059287,
"grad_norm": 0.04153455048799515,
"learning_rate": 0.00026274101034503867,
"loss": 0.86572265625,
"step": 356
},
{
"epoch": 1.4110671936758894,
"grad_norm": 0.0465623177587986,
"learning_rate": 0.0002624970865614034,
"loss": 0.798828125,
"step": 357
},
{
"epoch": 1.4150197628458498,
"grad_norm": 0.04188476875424385,
"learning_rate": 0.00026225249565598586,
"loss": 0.7998046875,
"step": 358
},
{
"epoch": 1.4189723320158103,
"grad_norm": 0.04524742066860199,
"learning_rate": 0.00026200723930239417,
"loss": 0.84619140625,
"step": 359
},
{
"epoch": 1.4229249011857708,
"grad_norm": 0.045839957892894745,
"learning_rate": 0.0002617613191787898,
"loss": 0.84716796875,
"step": 360
},
{
"epoch": 1.4268774703557312,
"grad_norm": 0.04196564108133316,
"learning_rate": 0.00026151473696787607,
"loss": 0.85498046875,
"step": 361
},
{
"epoch": 1.4308300395256917,
"grad_norm": 0.043789785355329514,
"learning_rate": 0.0002612674943568867,
"loss": 0.83349609375,
"step": 362
},
{
"epoch": 1.434782608695652,
"grad_norm": 0.046692635864019394,
"learning_rate": 0.00026101959303757394,
"loss": 0.81591796875,
"step": 363
},
{
"epoch": 1.4387351778656128,
"grad_norm": 0.04454057663679123,
"learning_rate": 0.0002607710347061976,
"loss": 0.8388671875,
"step": 364
},
{
"epoch": 1.4426877470355732,
"grad_norm": 0.04469408094882965,
"learning_rate": 0.0002605218210635127,
"loss": 0.8662109375,
"step": 365
},
{
"epoch": 1.4466403162055337,
"grad_norm": 0.04723108559846878,
"learning_rate": 0.00026027195381475853,
"loss": 0.8193359375,
"step": 366
},
{
"epoch": 1.4505928853754941,
"grad_norm": 0.04649047181010246,
"learning_rate": 0.00026002143466964645,
"loss": 0.86865234375,
"step": 367
},
{
"epoch": 1.4545454545454546,
"grad_norm": 0.04534972086548805,
"learning_rate": 0.00025977026534234856,
"loss": 0.90625,
"step": 368
},
{
"epoch": 1.458498023715415,
"grad_norm": 0.046483900398015976,
"learning_rate": 0.00025951844755148565,
"loss": 0.82861328125,
"step": 369
},
{
"epoch": 1.4624505928853755,
"grad_norm": 0.04710755497217178,
"learning_rate": 0.0002592659830201158,
"loss": 0.8828125,
"step": 370
},
{
"epoch": 1.466403162055336,
"grad_norm": 0.046799853444099426,
"learning_rate": 0.0002590128734757222,
"loss": 0.7978515625,
"step": 371
},
{
"epoch": 1.4703557312252964,
"grad_norm": 0.04023011028766632,
"learning_rate": 0.0002587591206502017,
"loss": 0.702239990234375,
"step": 372
},
{
"epoch": 1.4743083003952568,
"grad_norm": 0.046316370368003845,
"learning_rate": 0.0002585047262798527,
"loss": 0.8740234375,
"step": 373
},
{
"epoch": 1.4782608695652173,
"grad_norm": 0.04171806946396828,
"learning_rate": 0.00025824969210536347,
"loss": 0.88623046875,
"step": 374
},
{
"epoch": 1.4822134387351777,
"grad_norm": 0.04423278570175171,
"learning_rate": 0.0002579940198717999,
"loss": 0.86767578125,
"step": 375
},
{
"epoch": 1.4861660079051384,
"grad_norm": 0.04458356648683548,
"learning_rate": 0.0002577377113285939,
"loss": 0.816162109375,
"step": 376
},
{
"epoch": 1.4901185770750989,
"grad_norm": 0.047173723578453064,
"learning_rate": 0.0002574807682295315,
"loss": 0.82373046875,
"step": 377
},
{
"epoch": 1.4940711462450593,
"grad_norm": 0.04137580841779709,
"learning_rate": 0.00025722319233274034,
"loss": 0.86181640625,
"step": 378
},
{
"epoch": 1.4980237154150198,
"grad_norm": 0.045425448566675186,
"learning_rate": 0.00025696498540067814,
"loss": 0.86572265625,
"step": 379
},
{
"epoch": 1.5019762845849802,
"grad_norm": 0.04810909181833267,
"learning_rate": 0.0002567061492001206,
"loss": 0.8486328125,
"step": 380
},
{
"epoch": 1.5059288537549407,
"grad_norm": 0.04513464868068695,
"learning_rate": 0.0002564466855021488,
"loss": 0.8408203125,
"step": 381
},
{
"epoch": 1.5098814229249014,
"grad_norm": 0.044425591826438904,
"learning_rate": 0.0002561865960821379,
"loss": 0.81884765625,
"step": 382
},
{
"epoch": 1.5138339920948618,
"grad_norm": 0.04571211710572243,
"learning_rate": 0.00025592588271974425,
"loss": 0.8349609375,
"step": 383
},
{
"epoch": 1.5177865612648223,
"grad_norm": 0.044951170682907104,
"learning_rate": 0.00025566454719889347,
"loss": 0.77978515625,
"step": 384
},
{
"epoch": 1.5217391304347827,
"grad_norm": 0.04639696329832077,
"learning_rate": 0.0002554025913077686,
"loss": 0.87060546875,
"step": 385
},
{
"epoch": 1.5256916996047432,
"grad_norm": 0.04575954005122185,
"learning_rate": 0.0002551400168387973,
"loss": 0.88037109375,
"step": 386
},
{
"epoch": 1.5296442687747036,
"grad_norm": 0.043124910444021225,
"learning_rate": 0.00025487682558863984,
"loss": 0.84912109375,
"step": 387
},
{
"epoch": 1.533596837944664,
"grad_norm": 0.050908640027046204,
"learning_rate": 0.00025461301935817695,
"loss": 0.828369140625,
"step": 388
},
{
"epoch": 1.5375494071146245,
"grad_norm": 0.04361329972743988,
"learning_rate": 0.0002543485999524972,
"loss": 0.8779296875,
"step": 389
},
{
"epoch": 1.541501976284585,
"grad_norm": 0.04733825474977493,
"learning_rate": 0.00025408356918088493,
"loss": 0.86865234375,
"step": 390
},
{
"epoch": 1.5454545454545454,
"grad_norm": 0.042182374745607376,
"learning_rate": 0.00025381792885680764,
"loss": 0.84716796875,
"step": 391
},
{
"epoch": 1.5494071146245059,
"grad_norm": 0.04864241182804108,
"learning_rate": 0.00025355168079790365,
"loss": 0.85888671875,
"step": 392
},
{
"epoch": 1.5533596837944663,
"grad_norm": 0.040568757802248,
"learning_rate": 0.0002532848268259698,
"loss": 0.7584228515625,
"step": 393
},
{
"epoch": 1.5573122529644268,
"grad_norm": 0.044907983392477036,
"learning_rate": 0.00025301736876694886,
"loss": 0.82958984375,
"step": 394
},
{
"epoch": 1.5612648221343872,
"grad_norm": 0.04343508556485176,
"learning_rate": 0.00025274930845091696,
"loss": 0.87109375,
"step": 395
},
{
"epoch": 1.5652173913043477,
"grad_norm": 0.04684678837656975,
"learning_rate": 0.0002524806477120713,
"loss": 0.8173828125,
"step": 396
},
{
"epoch": 1.5691699604743083,
"grad_norm": 0.044022269546985626,
"learning_rate": 0.0002522113883887173,
"loss": 0.796875,
"step": 397
},
{
"epoch": 1.5731225296442688,
"grad_norm": 0.045939527451992035,
"learning_rate": 0.0002519415323232563,
"loss": 0.83349609375,
"step": 398
},
{
"epoch": 1.5770750988142292,
"grad_norm": 0.04733288288116455,
"learning_rate": 0.00025167108136217283,
"loss": 0.85302734375,
"step": 399
},
{
"epoch": 1.5810276679841897,
"grad_norm": 0.046681083738803864,
"learning_rate": 0.00025140003735602196,
"loss": 0.79931640625,
"step": 400
},
{
"epoch": 1.5849802371541502,
"grad_norm": 0.050638966262340546,
"learning_rate": 0.0002511284021594166,
"loss": 0.865234375,
"step": 401
},
{
"epoch": 1.5889328063241108,
"grad_norm": 0.04428083077073097,
"learning_rate": 0.00025085617763101497,
"loss": 0.8623046875,
"step": 402
},
{
"epoch": 1.5928853754940713,
"grad_norm": 0.04469752311706543,
"learning_rate": 0.0002505833656335077,
"loss": 0.851806640625,
"step": 403
},
{
"epoch": 1.5968379446640317,
"grad_norm": 0.04667256399989128,
"learning_rate": 0.0002503099680336052,
"loss": 0.8662109375,
"step": 404
},
{
"epoch": 1.6007905138339922,
"grad_norm": 0.05383816733956337,
"learning_rate": 0.00025003598670202484,
"loss": 0.845703125,
"step": 405
},
{
"epoch": 1.6047430830039526,
"grad_norm": 0.049002401530742645,
"learning_rate": 0.00024976142351347823,
"loss": 0.86181640625,
"step": 406
},
{
"epoch": 1.608695652173913,
"grad_norm": 0.04890795797109604,
"learning_rate": 0.00024948628034665815,
"loss": 0.8447265625,
"step": 407
},
{
"epoch": 1.6126482213438735,
"grad_norm": 0.04785492643713951,
"learning_rate": 0.00024921055908422605,
"loss": 0.8271484375,
"step": 408
},
{
"epoch": 1.616600790513834,
"grad_norm": 0.04681883752346039,
"learning_rate": 0.00024893426161279894,
"loss": 0.89501953125,
"step": 409
},
{
"epoch": 1.6205533596837944,
"grad_norm": 0.050165873020887375,
"learning_rate": 0.00024865738982293646,
"loss": 0.87158203125,
"step": 410
},
{
"epoch": 1.6245059288537549,
"grad_norm": 0.05295834690332413,
"learning_rate": 0.0002483799456091282,
"loss": 0.8212890625,
"step": 411
},
{
"epoch": 1.6284584980237153,
"grad_norm": 0.045848701149225235,
"learning_rate": 0.0002481019308697801,
"loss": 0.849609375,
"step": 412
},
{
"epoch": 1.6324110671936758,
"grad_norm": 0.04794853553175926,
"learning_rate": 0.0002478233475072026,
"loss": 0.86474609375,
"step": 413
},
{
"epoch": 1.6363636363636362,
"grad_norm": 0.04572764411568642,
"learning_rate": 0.0002475441974275963,
"loss": 0.8369140625,
"step": 414
},
{
"epoch": 1.6403162055335967,
"grad_norm": 0.0464460663497448,
"learning_rate": 0.0002472644825410398,
"loss": 0.87255859375,
"step": 415
},
{
"epoch": 1.6442687747035574,
"grad_norm": 0.044800110161304474,
"learning_rate": 0.0002469842047614765,
"loss": 0.82666015625,
"step": 416
},
{
"epoch": 1.6482213438735178,
"grad_norm": 0.04495685175061226,
"learning_rate": 0.00024670336600670126,
"loss": 0.85498046875,
"step": 417
},
{
"epoch": 1.6521739130434783,
"grad_norm": 0.046193886548280716,
"learning_rate": 0.00024642196819834726,
"loss": 0.81298828125,
"step": 418
},
{
"epoch": 1.6561264822134387,
"grad_norm": 0.045579370111227036,
"learning_rate": 0.00024614001326187326,
"loss": 0.80615234375,
"step": 419
},
{
"epoch": 1.6600790513833992,
"grad_norm": 0.045904021710157394,
"learning_rate": 0.00024585750312655007,
"loss": 0.84521484375,
"step": 420
},
{
"epoch": 1.6640316205533598,
"grad_norm": 0.04338549077510834,
"learning_rate": 0.0002455744397254473,
"loss": 0.85888671875,
"step": 421
},
{
"epoch": 1.6679841897233203,
"grad_norm": 0.042087722569704056,
"learning_rate": 0.0002452908249954204,
"loss": 0.795166015625,
"step": 422
},
{
"epoch": 1.6719367588932808,
"grad_norm": 0.044984206557273865,
"learning_rate": 0.0002450066608770973,
"loss": 0.9013671875,
"step": 423
},
{
"epoch": 1.6758893280632412,
"grad_norm": 0.04374135285615921,
"learning_rate": 0.0002447219493148649,
"loss": 0.83984375,
"step": 424
},
{
"epoch": 1.6798418972332017,
"grad_norm": 0.04481242224574089,
"learning_rate": 0.00024443669225685633,
"loss": 0.79931640625,
"step": 425
},
{
"epoch": 1.683794466403162,
"grad_norm": 0.043329834938049316,
"learning_rate": 0.000244150891654937,
"loss": 0.875,
"step": 426
},
{
"epoch": 1.6877470355731226,
"grad_norm": 0.04465761408209801,
"learning_rate": 0.00024386454946469146,
"loss": 0.85986328125,
"step": 427
},
{
"epoch": 1.691699604743083,
"grad_norm": 0.0468703955411911,
"learning_rate": 0.00024357766764541034,
"loss": 0.82763671875,
"step": 428
},
{
"epoch": 1.6956521739130435,
"grad_norm": 0.04503852128982544,
"learning_rate": 0.00024329024816007637,
"loss": 0.8046875,
"step": 429
},
{
"epoch": 1.699604743083004,
"grad_norm": 0.048190027475357056,
"learning_rate": 0.00024300229297535147,
"loss": 0.82080078125,
"step": 430
},
{
"epoch": 1.7035573122529644,
"grad_norm": 0.04460554197430611,
"learning_rate": 0.00024271380406156305,
"loss": 0.86083984375,
"step": 431
},
{
"epoch": 1.7075098814229248,
"grad_norm": 0.04552039876580238,
"learning_rate": 0.0002424247833926903,
"loss": 0.82421875,
"step": 432
},
{
"epoch": 1.7114624505928853,
"grad_norm": 0.04481853172183037,
"learning_rate": 0.00024213523294635127,
"loss": 0.81640625,
"step": 433
},
{
"epoch": 1.7154150197628457,
"grad_norm": 0.04410327598452568,
"learning_rate": 0.00024184515470378881,
"loss": 0.81689453125,
"step": 434
},
{
"epoch": 1.7193675889328062,
"grad_norm": 0.04774461314082146,
"learning_rate": 0.00024155455064985725,
"loss": 0.85400390625,
"step": 435
},
{
"epoch": 1.7233201581027668,
"grad_norm": 0.04482584074139595,
"learning_rate": 0.00024126342277300874,
"loss": 0.82861328125,
"step": 436
},
{
"epoch": 1.7272727272727273,
"grad_norm": 0.0424453541636467,
"learning_rate": 0.00024097177306527974,
"loss": 0.714599609375,
"step": 437
},
{
"epoch": 1.7312252964426877,
"grad_norm": 0.04772420972585678,
"learning_rate": 0.00024067960352227736,
"loss": 0.83984375,
"step": 438
},
{
"epoch": 1.7351778656126482,
"grad_norm": 0.04523874446749687,
"learning_rate": 0.00024038691614316547,
"loss": 0.88720703125,
"step": 439
},
{
"epoch": 1.7391304347826086,
"grad_norm": 0.04779965803027153,
"learning_rate": 0.00024009371293065145,
"loss": 0.7890625,
"step": 440
},
{
"epoch": 1.7430830039525693,
"grad_norm": 0.045862387865781784,
"learning_rate": 0.00023979999589097216,
"loss": 0.80029296875,
"step": 441
},
{
"epoch": 1.7470355731225298,
"grad_norm": 0.047303758561611176,
"learning_rate": 0.0002395057670338803,
"loss": 0.85693359375,
"step": 442
},
{
"epoch": 1.7509881422924902,
"grad_norm": 0.04534810036420822,
"learning_rate": 0.00023921102837263069,
"loss": 0.8681640625,
"step": 443
},
{
"epoch": 1.7549407114624507,
"grad_norm": 0.048014990985393524,
"learning_rate": 0.0002389157819239665,
"loss": 0.8828125,
"step": 444
},
{
"epoch": 1.7588932806324111,
"grad_norm": 0.04202796891331673,
"learning_rate": 0.00023862002970810535,
"loss": 0.6929931640625,
"step": 445
},
{
"epoch": 1.7628458498023716,
"grad_norm": 0.05232452228665352,
"learning_rate": 0.0002383237737487257,
"loss": 0.81494140625,
"step": 446
},
{
"epoch": 1.766798418972332,
"grad_norm": 0.04318549484014511,
"learning_rate": 0.00023802701607295273,
"loss": 0.85302734375,
"step": 447
},
{
"epoch": 1.7707509881422925,
"grad_norm": 0.05377434939146042,
"learning_rate": 0.00023772975871134462,
"loss": 0.757568359375,
"step": 448
},
{
"epoch": 1.774703557312253,
"grad_norm": 0.04351175203919411,
"learning_rate": 0.00023743200369787869,
"loss": 0.83837890625,
"step": 449
},
{
"epoch": 1.7786561264822134,
"grad_norm": 0.05255289003252983,
"learning_rate": 0.00023713375306993743,
"loss": 0.8447265625,
"step": 450
},
{
"epoch": 1.7826086956521738,
"grad_norm": 0.045315928757190704,
"learning_rate": 0.00023683500886829452,
"loss": 0.80517578125,
"step": 451
},
{
"epoch": 1.7865612648221343,
"grad_norm": 0.047262173146009445,
"learning_rate": 0.00023653577313710096,
"loss": 0.7861328125,
"step": 452
},
{
"epoch": 1.7905138339920947,
"grad_norm": 0.0466645210981369,
"learning_rate": 0.00023623604792387092,
"loss": 0.80615234375,
"step": 453
},
{
"epoch": 1.7944664031620552,
"grad_norm": 0.04696672782301903,
"learning_rate": 0.00023593583527946807,
"loss": 0.833984375,
"step": 454
},
{
"epoch": 1.7984189723320159,
"grad_norm": 0.046677011996507645,
"learning_rate": 0.00023563513725809103,
"loss": 0.81298828125,
"step": 455
},
{
"epoch": 1.8023715415019763,
"grad_norm": 0.04685526713728905,
"learning_rate": 0.00023533395591725988,
"loss": 0.8291015625,
"step": 456
},
{
"epoch": 1.8063241106719368,
"grad_norm": 0.04871918261051178,
"learning_rate": 0.0002350322933178015,
"loss": 0.90087890625,
"step": 457
},
{
"epoch": 1.8102766798418972,
"grad_norm": 0.048640262335538864,
"learning_rate": 0.00023473015152383606,
"loss": 0.85791015625,
"step": 458
},
{
"epoch": 1.8142292490118577,
"grad_norm": 0.05096844956278801,
"learning_rate": 0.00023442753260276245,
"loss": 0.83154296875,
"step": 459
},
{
"epoch": 1.8181818181818183,
"grad_norm": 0.04710604250431061,
"learning_rate": 0.00023412443862524436,
"loss": 0.7939453125,
"step": 460
},
{
"epoch": 1.8221343873517788,
"grad_norm": 0.053786568343639374,
"learning_rate": 0.00023382087166519598,
"loss": 0.822265625,
"step": 461
},
{
"epoch": 1.8260869565217392,
"grad_norm": 0.04664744436740875,
"learning_rate": 0.00023351683379976788,
"loss": 0.818359375,
"step": 462
},
{
"epoch": 1.8300395256916997,
"grad_norm": 0.04617181420326233,
"learning_rate": 0.00023321232710933284,
"loss": 0.84765625,
"step": 463
},
{
"epoch": 1.8339920948616601,
"grad_norm": 0.04768504574894905,
"learning_rate": 0.00023290735367747158,
"loss": 0.873046875,
"step": 464
},
{
"epoch": 1.8379446640316206,
"grad_norm": 0.04921377822756767,
"learning_rate": 0.0002326019155909584,
"loss": 0.8125,
"step": 465
},
{
"epoch": 1.841897233201581,
"grad_norm": 0.04508016258478165,
"learning_rate": 0.00023229601493974708,
"loss": 0.80224609375,
"step": 466
},
{
"epoch": 1.8458498023715415,
"grad_norm": 0.05066506564617157,
"learning_rate": 0.0002319896538169564,
"loss": 0.84619140625,
"step": 467
},
{
"epoch": 1.849802371541502,
"grad_norm": 0.045238010585308075,
"learning_rate": 0.00023168283431885598,
"loss": 0.79736328125,
"step": 468
},
{
"epoch": 1.8537549407114624,
"grad_norm": 0.04527495428919792,
"learning_rate": 0.0002313755585448519,
"loss": 0.837890625,
"step": 469
},
{
"epoch": 1.8577075098814229,
"grad_norm": 0.048752311617136,
"learning_rate": 0.00023106782859747213,
"loss": 0.86328125,
"step": 470
},
{
"epoch": 1.8616600790513833,
"grad_norm": 0.04887886345386505,
"learning_rate": 0.0002307596465823525,
"loss": 0.86669921875,
"step": 471
},
{
"epoch": 1.8656126482213438,
"grad_norm": 0.052601270377635956,
"learning_rate": 0.00023045101460822195,
"loss": 0.852294921875,
"step": 472
},
{
"epoch": 1.8695652173913042,
"grad_norm": 0.05032513663172722,
"learning_rate": 0.0002301419347868884,
"loss": 0.857421875,
"step": 473
},
{
"epoch": 1.8735177865612647,
"grad_norm": 0.05006840080022812,
"learning_rate": 0.00022983240923322407,
"loss": 0.8740234375,
"step": 474
},
{
"epoch": 1.8774703557312253,
"grad_norm": 0.04741242900490761,
"learning_rate": 0.00022952244006515106,
"loss": 0.88427734375,
"step": 475
},
{
"epoch": 1.8814229249011858,
"grad_norm": 0.04881199449300766,
"learning_rate": 0.00022921202940362704,
"loss": 0.783203125,
"step": 476
},
{
"epoch": 1.8853754940711462,
"grad_norm": 0.0474226139485836,
"learning_rate": 0.00022890117937263035,
"loss": 0.798828125,
"step": 477
},
{
"epoch": 1.8893280632411067,
"grad_norm": 0.05127018690109253,
"learning_rate": 0.00022858989209914593,
"loss": 0.83935546875,
"step": 478
},
{
"epoch": 1.8932806324110671,
"grad_norm": 0.046419087797403336,
"learning_rate": 0.00022827816971315051,
"loss": 0.7861328125,
"step": 479
},
{
"epoch": 1.8972332015810278,
"grad_norm": 0.04532233998179436,
"learning_rate": 0.0002279660143475979,
"loss": 0.8310546875,
"step": 480
},
{
"epoch": 1.9011857707509883,
"grad_norm": 0.05073583871126175,
"learning_rate": 0.00022765342813840477,
"loss": 0.79296875,
"step": 481
},
{
"epoch": 1.9051383399209487,
"grad_norm": 0.04656722769141197,
"learning_rate": 0.00022734041322443574,
"loss": 0.80615234375,
"step": 482
},
{
"epoch": 1.9090909090909092,
"grad_norm": 0.04716819152235985,
"learning_rate": 0.00022702697174748878,
"loss": 0.86767578125,
"step": 483
},
{
"epoch": 1.9130434782608696,
"grad_norm": 0.054595693945884705,
"learning_rate": 0.00022671310585228069,
"loss": 0.8212890625,
"step": 484
},
{
"epoch": 1.91699604743083,
"grad_norm": 0.049015577882528305,
"learning_rate": 0.00022639881768643231,
"loss": 0.859375,
"step": 485
},
{
"epoch": 1.9209486166007905,
"grad_norm": 0.050880834460258484,
"learning_rate": 0.00022608410940045385,
"loss": 0.84765625,
"step": 486
},
{
"epoch": 1.924901185770751,
"grad_norm": 0.051552336663007736,
"learning_rate": 0.00022576898314773024,
"loss": 0.82373046875,
"step": 487
},
{
"epoch": 1.9288537549407114,
"grad_norm": 0.04669000953435898,
"learning_rate": 0.00022545344108450624,
"loss": 0.7939453125,
"step": 488
},
{
"epoch": 1.9328063241106719,
"grad_norm": 0.049080733209848404,
"learning_rate": 0.0002251374853698719,
"loss": 0.7199554443359375,
"step": 489
},
{
"epoch": 1.9367588932806323,
"grad_norm": 0.049850042909383774,
"learning_rate": 0.00022482111816574755,
"loss": 0.837890625,
"step": 490
},
{
"epoch": 1.9407114624505928,
"grad_norm": 0.04702037200331688,
"learning_rate": 0.00022450434163686923,
"loss": 0.85205078125,
"step": 491
},
{
"epoch": 1.9446640316205532,
"grad_norm": 0.04852689802646637,
"learning_rate": 0.0002241871579507737,
"loss": 0.8125,
"step": 492
},
{
"epoch": 1.9486166007905137,
"grad_norm": 0.04736710712313652,
"learning_rate": 0.0002238695692777838,
"loss": 0.82958984375,
"step": 493
},
{
"epoch": 1.9525691699604744,
"grad_norm": 0.04593873396515846,
"learning_rate": 0.0002235515777909933,
"loss": 0.80712890625,
"step": 494
},
{
"epoch": 1.9565217391304348,
"grad_norm": 0.051194928586483,
"learning_rate": 0.00022323318566625237,
"loss": 0.869140625,
"step": 495
},
{
"epoch": 1.9604743083003953,
"grad_norm": 0.04587307572364807,
"learning_rate": 0.00022291439508215246,
"loss": 0.82763671875,
"step": 496
},
{
"epoch": 1.9644268774703557,
"grad_norm": 0.04845285043120384,
"learning_rate": 0.00022259520822001154,
"loss": 0.8369140625,
"step": 497
},
{
"epoch": 1.9683794466403162,
"grad_norm": 0.045351188629865646,
"learning_rate": 0.00022227562726385907,
"loss": 0.7359619140625,
"step": 498
},
{
"epoch": 1.9723320158102768,
"grad_norm": 0.04514331743121147,
"learning_rate": 0.000221955654400421,
"loss": 0.8388671875,
"step": 499
},
{
"epoch": 1.9762845849802373,
"grad_norm": 0.04706789180636406,
"learning_rate": 0.00022163529181910504,
"loss": 0.791015625,
"step": 500
},
{
"epoch": 1.9802371541501977,
"grad_norm": 0.04613194614648819,
"learning_rate": 0.00022131454171198545,
"loss": 0.81982421875,
"step": 501
},
{
"epoch": 1.9841897233201582,
"grad_norm": 0.04641484469175339,
"learning_rate": 0.0002209934062737882,
"loss": 0.84521484375,
"step": 502
},
{
"epoch": 1.9881422924901186,
"grad_norm": 0.040886715054512024,
"learning_rate": 0.00022067188770187574,
"loss": 0.70989990234375,
"step": 503
},
{
"epoch": 1.992094861660079,
"grad_norm": 0.04634854570031166,
"learning_rate": 0.0002203499881962323,
"loss": 0.85595703125,
"step": 504
},
{
"epoch": 1.9960474308300395,
"grad_norm": 0.04712579771876335,
"learning_rate": 0.00022002770995944843,
"loss": 0.77978515625,
"step": 505
},
{
"epoch": 2.0,
"grad_norm": 0.05044356733560562,
"learning_rate": 0.00021970505519670633,
"loss": 0.806640625,
"step": 506
},
{
"epoch": 2.0,
"eval_loss": 0.83251953125,
"eval_runtime": 2.2169,
"eval_samples_per_second": 2.706,
"eval_steps_per_second": 0.451,
"step": 506
},
{
"epoch": 2.0039525691699605,
"grad_norm": 0.04614734649658203,
"learning_rate": 0.00021938202611576445,
"loss": 0.81298828125,
"step": 507
},
{
"epoch": 2.007905138339921,
"grad_norm": 0.05542993173003197,
"learning_rate": 0.00021905862492694258,
"loss": 0.82421875,
"step": 508
},
{
"epoch": 2.0118577075098814,
"grad_norm": 0.04725426435470581,
"learning_rate": 0.00021873485384310654,
"loss": 0.8466796875,
"step": 509
},
{
"epoch": 2.015810276679842,
"grad_norm": 0.049337390810251236,
"learning_rate": 0.00021841071507965333,
"loss": 0.8408203125,
"step": 510
},
{
"epoch": 2.0197628458498023,
"grad_norm": 0.049089428037405014,
"learning_rate": 0.00021808621085449558,
"loss": 0.84326171875,
"step": 511
},
{
"epoch": 2.0237154150197627,
"grad_norm": 0.04510679841041565,
"learning_rate": 0.00021776134338804672,
"loss": 0.853515625,
"step": 512
},
{
"epoch": 2.027667984189723,
"grad_norm": 0.04928339645266533,
"learning_rate": 0.0002174361149032056,
"loss": 0.802734375,
"step": 513
},
{
"epoch": 2.0316205533596836,
"grad_norm": 0.04705115407705307,
"learning_rate": 0.00021711052762534143,
"loss": 0.875,
"step": 514
},
{
"epoch": 2.035573122529644,
"grad_norm": 0.04963403940200806,
"learning_rate": 0.00021678458378227827,
"loss": 0.8125,
"step": 515
},
{
"epoch": 2.039525691699605,
"grad_norm": 0.04543919861316681,
"learning_rate": 0.0002164582856042801,
"loss": 0.85107421875,
"step": 516
},
{
"epoch": 2.0434782608695654,
"grad_norm": 0.048561736941337585,
"learning_rate": 0.0002161316353240354,
"loss": 0.83642578125,
"step": 517
},
{
"epoch": 2.047430830039526,
"grad_norm": 0.046552300453186035,
"learning_rate": 0.00021580463517664196,
"loss": 0.688995361328125,
"step": 518
},
{
"epoch": 2.0513833992094863,
"grad_norm": 0.045691922307014465,
"learning_rate": 0.0002154772873995914,
"loss": 0.82666015625,
"step": 519
},
{
"epoch": 2.0553359683794468,
"grad_norm": 0.04575952887535095,
"learning_rate": 0.00021514959423275413,
"loss": 0.78387451171875,
"step": 520
},
{
"epoch": 2.059288537549407,
"grad_norm": 0.05015664920210838,
"learning_rate": 0.0002148215579183637,
"loss": 0.84033203125,
"step": 521
},
{
"epoch": 2.0632411067193677,
"grad_norm": 0.04789474606513977,
"learning_rate": 0.0002144931807010019,
"loss": 0.831298828125,
"step": 522
},
{
"epoch": 2.067193675889328,
"grad_norm": 0.04774557426571846,
"learning_rate": 0.00021416446482758287,
"loss": 0.7841796875,
"step": 523
},
{
"epoch": 2.0711462450592886,
"grad_norm": 0.04742559790611267,
"learning_rate": 0.00021383541254733817,
"loss": 0.79833984375,
"step": 524
},
{
"epoch": 2.075098814229249,
"grad_norm": 0.044518161565065384,
"learning_rate": 0.00021350602611180117,
"loss": 0.86962890625,
"step": 525
},
{
"epoch": 2.0790513833992095,
"grad_norm": 0.04813148081302643,
"learning_rate": 0.00021317630777479163,
"loss": 0.81689453125,
"step": 526
},
{
"epoch": 2.08300395256917,
"grad_norm": 0.0458255298435688,
"learning_rate": 0.00021284625979240058,
"loss": 0.84033203125,
"step": 527
},
{
"epoch": 2.0869565217391304,
"grad_norm": 0.04855121672153473,
"learning_rate": 0.00021251588442297424,
"loss": 0.84423828125,
"step": 528
},
{
"epoch": 2.090909090909091,
"grad_norm": 0.04622291401028633,
"learning_rate": 0.0002121851839270993,
"loss": 0.7647705078125,
"step": 529
},
{
"epoch": 2.0948616600790513,
"grad_norm": 0.04799032583832741,
"learning_rate": 0.000211854160567587,
"loss": 0.83544921875,
"step": 530
},
{
"epoch": 2.0988142292490117,
"grad_norm": 0.045939851552248,
"learning_rate": 0.00021152281660945777,
"loss": 0.77880859375,
"step": 531
},
{
"epoch": 2.102766798418972,
"grad_norm": 0.04935876652598381,
"learning_rate": 0.00021119115431992568,
"loss": 0.778564453125,
"step": 532
},
{
"epoch": 2.1067193675889326,
"grad_norm": 0.04612088203430176,
"learning_rate": 0.00021085917596838313,
"loss": 0.81591796875,
"step": 533
},
{
"epoch": 2.110671936758893,
"grad_norm": 0.04778169468045235,
"learning_rate": 0.00021052688382638499,
"loss": 0.80810546875,
"step": 534
},
{
"epoch": 2.1146245059288535,
"grad_norm": 0.04639984667301178,
"learning_rate": 0.0002101942801676334,
"loss": 0.723175048828125,
"step": 535
},
{
"epoch": 2.1185770750988144,
"grad_norm": 0.046360574662685394,
"learning_rate": 0.00020986136726796183,
"loss": 0.82275390625,
"step": 536
},
{
"epoch": 2.122529644268775,
"grad_norm": 0.051891911774873734,
"learning_rate": 0.00020952814740532,
"loss": 0.8486328125,
"step": 537
},
{
"epoch": 2.1264822134387353,
"grad_norm": 0.04591868072748184,
"learning_rate": 0.00020919462285975778,
"loss": 0.77734375,
"step": 538
},
{
"epoch": 2.130434782608696,
"grad_norm": 0.048664532601833344,
"learning_rate": 0.00020886079591340994,
"loss": 0.75341796875,
"step": 539
},
{
"epoch": 2.1343873517786562,
"grad_norm": 0.04860478267073631,
"learning_rate": 0.00020852666885048048,
"loss": 0.8310546875,
"step": 540
},
{
"epoch": 2.1383399209486167,
"grad_norm": 0.0484267920255661,
"learning_rate": 0.0002081922439572267,
"loss": 0.826171875,
"step": 541
},
{
"epoch": 2.142292490118577,
"grad_norm": 0.051395684480667114,
"learning_rate": 0.00020785752352194407,
"loss": 0.8388671875,
"step": 542
},
{
"epoch": 2.1462450592885376,
"grad_norm": 0.045636989176273346,
"learning_rate": 0.00020752250983495024,
"loss": 0.80859375,
"step": 543
},
{
"epoch": 2.150197628458498,
"grad_norm": 0.05005775764584541,
"learning_rate": 0.00020718720518856927,
"loss": 0.83544921875,
"step": 544
},
{
"epoch": 2.1541501976284585,
"grad_norm": 0.04951068013906479,
"learning_rate": 0.00020685161187711625,
"loss": 0.80615234375,
"step": 545
},
{
"epoch": 2.158102766798419,
"grad_norm": 0.04543376713991165,
"learning_rate": 0.00020651573219688144,
"loss": 0.82373046875,
"step": 546
},
{
"epoch": 2.1620553359683794,
"grad_norm": 0.04580464959144592,
"learning_rate": 0.0002061795684461145,
"loss": 0.759765625,
"step": 547
},
{
"epoch": 2.16600790513834,
"grad_norm": 0.047638650983572006,
"learning_rate": 0.00020584312292500894,
"loss": 0.78662109375,
"step": 548
},
{
"epoch": 2.1699604743083003,
"grad_norm": 0.04593316465616226,
"learning_rate": 0.00020550639793568624,
"loss": 0.786865234375,
"step": 549
},
{
"epoch": 2.1739130434782608,
"grad_norm": 0.0512143075466156,
"learning_rate": 0.0002051693957821801,
"loss": 0.77734375,
"step": 550
},
{
"epoch": 2.177865612648221,
"grad_norm": 0.047573067247867584,
"learning_rate": 0.00020483211877042064,
"loss": 0.81689453125,
"step": 551
},
{
"epoch": 2.1818181818181817,
"grad_norm": 0.047719623893499374,
"learning_rate": 0.0002044945692082189,
"loss": 0.7919921875,
"step": 552
},
{
"epoch": 2.185770750988142,
"grad_norm": 0.04295816272497177,
"learning_rate": 0.00020415674940525065,
"loss": 0.637176513671875,
"step": 553
},
{
"epoch": 2.1897233201581026,
"grad_norm": 0.04974406957626343,
"learning_rate": 0.00020381866167304085,
"loss": 0.8349609375,
"step": 554
},
{
"epoch": 2.1936758893280635,
"grad_norm": 0.04715517535805702,
"learning_rate": 0.00020348030832494787,
"loss": 0.78515625,
"step": 555
},
{
"epoch": 2.197628458498024,
"grad_norm": 0.04895627871155739,
"learning_rate": 0.00020314169167614732,
"loss": 0.81103515625,
"step": 556
},
{
"epoch": 2.2015810276679844,
"grad_norm": 0.04950820282101631,
"learning_rate": 0.0002028028140436166,
"loss": 0.8349609375,
"step": 557
},
{
"epoch": 2.205533596837945,
"grad_norm": 0.044492971152067184,
"learning_rate": 0.0002024636777461189,
"loss": 0.71875,
"step": 558
},
{
"epoch": 2.2094861660079053,
"grad_norm": 0.04832074046134949,
"learning_rate": 0.00020212428510418712,
"loss": 0.8251953125,
"step": 559
},
{
"epoch": 2.2134387351778657,
"grad_norm": 0.048138100653886795,
"learning_rate": 0.00020178463844010847,
"loss": 0.81591796875,
"step": 560
},
{
"epoch": 2.217391304347826,
"grad_norm": 0.04953526705503464,
"learning_rate": 0.00020144474007790814,
"loss": 0.83447265625,
"step": 561
},
{
"epoch": 2.2213438735177866,
"grad_norm": 0.047930147498846054,
"learning_rate": 0.00020110459234333353,
"loss": 0.76904296875,
"step": 562
},
{
"epoch": 2.225296442687747,
"grad_norm": 0.048681121319532394,
"learning_rate": 0.0002007641975638385,
"loss": 0.72265625,
"step": 563
},
{
"epoch": 2.2292490118577075,
"grad_norm": 0.05481003224849701,
"learning_rate": 0.0002004235580685672,
"loss": 0.81298828125,
"step": 564
},
{
"epoch": 2.233201581027668,
"grad_norm": 0.048605479300022125,
"learning_rate": 0.00020008267618833829,
"loss": 0.8486328125,
"step": 565
},
{
"epoch": 2.2371541501976284,
"grad_norm": 0.05604838579893112,
"learning_rate": 0.00019974155425562894,
"loss": 0.81005859375,
"step": 566
},
{
"epoch": 2.241106719367589,
"grad_norm": 0.048590511083602905,
"learning_rate": 0.00019940019460455878,
"loss": 0.74658203125,
"step": 567
},
{
"epoch": 2.2450592885375493,
"grad_norm": 0.050683263689279556,
"learning_rate": 0.00019905859957087418,
"loss": 0.68475341796875,
"step": 568
},
{
"epoch": 2.2490118577075098,
"grad_norm": 0.05292607098817825,
"learning_rate": 0.00019871677149193204,
"loss": 0.7607421875,
"step": 569
},
{
"epoch": 2.2529644268774702,
"grad_norm": 0.05144540220499039,
"learning_rate": 0.00019837471270668379,
"loss": 0.80615234375,
"step": 570
},
{
"epoch": 2.2569169960474307,
"grad_norm": 0.05131471902132034,
"learning_rate": 0.00019803242555565964,
"loss": 0.78759765625,
"step": 571
},
{
"epoch": 2.260869565217391,
"grad_norm": 0.052379339933395386,
"learning_rate": 0.00019768991238095225,
"loss": 0.8037109375,
"step": 572
},
{
"epoch": 2.2648221343873516,
"grad_norm": 0.048578936606645584,
"learning_rate": 0.0001973471755262009,
"loss": 0.8427734375,
"step": 573
},
{
"epoch": 2.2687747035573125,
"grad_norm": 0.04910541698336601,
"learning_rate": 0.00019700421733657522,
"loss": 0.783203125,
"step": 574
},
{
"epoch": 2.2727272727272725,
"grad_norm": 0.046770643442869186,
"learning_rate": 0.00019666104015875967,
"loss": 0.7958984375,
"step": 575
},
{
"epoch": 2.2766798418972334,
"grad_norm": 0.04771951958537102,
"learning_rate": 0.00019631764634093685,
"loss": 0.8203125,
"step": 576
},
{
"epoch": 2.280632411067194,
"grad_norm": 0.0515475757420063,
"learning_rate": 0.0001959740382327718,
"loss": 0.77587890625,
"step": 577
},
{
"epoch": 2.2845849802371543,
"grad_norm": 0.04727964475750923,
"learning_rate": 0.0001956302181853959,
"loss": 0.84228515625,
"step": 578
},
{
"epoch": 2.2885375494071147,
"grad_norm": 0.047735366970300674,
"learning_rate": 0.00019528618855139057,
"loss": 0.79296875,
"step": 579
},
{
"epoch": 2.292490118577075,
"grad_norm": 0.048225726932287216,
"learning_rate": 0.00019494195168477137,
"loss": 0.8330078125,
"step": 580
},
{
"epoch": 2.2964426877470356,
"grad_norm": 0.04475891590118408,
"learning_rate": 0.00019459750994097204,
"loss": 0.77880859375,
"step": 581
},
{
"epoch": 2.300395256916996,
"grad_norm": 0.04793180525302887,
"learning_rate": 0.00019425286567682792,
"loss": 0.81494140625,
"step": 582
},
{
"epoch": 2.3043478260869565,
"grad_norm": 0.04663156345486641,
"learning_rate": 0.00019390802125056022,
"loss": 0.8056640625,
"step": 583
},
{
"epoch": 2.308300395256917,
"grad_norm": 0.047295719385147095,
"learning_rate": 0.00019356297902175973,
"loss": 0.80078125,
"step": 584
},
{
"epoch": 2.3122529644268774,
"grad_norm": 0.04829349368810654,
"learning_rate": 0.00019321774135137076,
"loss": 0.8076171875,
"step": 585
},
{
"epoch": 2.316205533596838,
"grad_norm": 0.048433221876621246,
"learning_rate": 0.00019287231060167482,
"loss": 0.7861328125,
"step": 586
},
{
"epoch": 2.3201581027667983,
"grad_norm": 0.04710831120610237,
"learning_rate": 0.00019252668913627462,
"loss": 0.7236328125,
"step": 587
},
{
"epoch": 2.324110671936759,
"grad_norm": 0.047688860446214676,
"learning_rate": 0.0001921808793200779,
"loss": 0.7900390625,
"step": 588
},
{
"epoch": 2.3280632411067192,
"grad_norm": 0.04863202944397926,
"learning_rate": 0.00019183488351928098,
"loss": 0.849609375,
"step": 589
},
{
"epoch": 2.3320158102766797,
"grad_norm": 0.04699735715985298,
"learning_rate": 0.000191488704101353,
"loss": 0.7763671875,
"step": 590
},
{
"epoch": 2.33596837944664,
"grad_norm": 0.045672137290239334,
"learning_rate": 0.00019114234343501948,
"loss": 0.7919921875,
"step": 591
},
{
"epoch": 2.3399209486166006,
"grad_norm": 0.04825318977236748,
"learning_rate": 0.00019079580389024593,
"loss": 0.8173828125,
"step": 592
},
{
"epoch": 2.3438735177865615,
"grad_norm": 0.05111541971564293,
"learning_rate": 0.00019044908783822203,
"loss": 0.78271484375,
"step": 593
},
{
"epoch": 2.3478260869565215,
"grad_norm": 0.048476655036211014,
"learning_rate": 0.0001901021976513451,
"loss": 0.767578125,
"step": 594
},
{
"epoch": 2.3517786561264824,
"grad_norm": 0.048755671828985214,
"learning_rate": 0.00018975513570320405,
"loss": 0.826171875,
"step": 595
},
{
"epoch": 2.355731225296443,
"grad_norm": 0.04929805546998978,
"learning_rate": 0.00018940790436856303,
"loss": 0.75439453125,
"step": 596
},
{
"epoch": 2.3596837944664033,
"grad_norm": 0.04922974482178688,
"learning_rate": 0.00018906050602334517,
"loss": 0.78955078125,
"step": 597
},
{
"epoch": 2.3636363636363638,
"grad_norm": 0.05141812562942505,
"learning_rate": 0.00018871294304461641,
"loss": 0.79345703125,
"step": 598
},
{
"epoch": 2.367588932806324,
"grad_norm": 0.050471507012844086,
"learning_rate": 0.00018836521781056924,
"loss": 0.7841796875,
"step": 599
},
{
"epoch": 2.3715415019762847,
"grad_norm": 0.05033344775438309,
"learning_rate": 0.00018801733270050626,
"loss": 0.765625,
"step": 600
},
{
"epoch": 2.375494071146245,
"grad_norm": 0.047611720860004425,
"learning_rate": 0.00018766929009482415,
"loss": 0.8271484375,
"step": 601
},
{
"epoch": 2.3794466403162056,
"grad_norm": 0.0506114736199379,
"learning_rate": 0.0001873210923749971,
"loss": 0.84814453125,
"step": 602
},
{
"epoch": 2.383399209486166,
"grad_norm": 0.04457153007388115,
"learning_rate": 0.00018697274192356077,
"loss": 0.682861328125,
"step": 603
},
{
"epoch": 2.3873517786561265,
"grad_norm": 0.04921259358525276,
"learning_rate": 0.00018662424112409593,
"loss": 0.8173828125,
"step": 604
},
{
"epoch": 2.391304347826087,
"grad_norm": 0.04977316036820412,
"learning_rate": 0.00018627559236121196,
"loss": 0.7939453125,
"step": 605
},
{
"epoch": 2.3952569169960474,
"grad_norm": 0.04721233621239662,
"learning_rate": 0.00018592679802053078,
"loss": 0.81494140625,
"step": 606
},
{
"epoch": 2.399209486166008,
"grad_norm": 0.0462174266576767,
"learning_rate": 0.00018557786048867042,
"loss": 0.77587890625,
"step": 607
},
{
"epoch": 2.4031620553359683,
"grad_norm": 0.04819757863879204,
"learning_rate": 0.00018522878215322864,
"loss": 0.7900390625,
"step": 608
},
{
"epoch": 2.4071146245059287,
"grad_norm": 0.048176128417253494,
"learning_rate": 0.00018487956540276667,
"loss": 0.80615234375,
"step": 609
},
{
"epoch": 2.411067193675889,
"grad_norm": 0.047973763197660446,
"learning_rate": 0.00018453021262679288,
"loss": 0.74365234375,
"step": 610
},
{
"epoch": 2.4150197628458496,
"grad_norm": 0.04828173667192459,
"learning_rate": 0.0001841807262157463,
"loss": 0.7451171875,
"step": 611
},
{
"epoch": 2.4189723320158105,
"grad_norm": 0.047229327261447906,
"learning_rate": 0.00018383110856098043,
"loss": 0.7890625,
"step": 612
},
{
"epoch": 2.4229249011857705,
"grad_norm": 0.04589885473251343,
"learning_rate": 0.00018348136205474685,
"loss": 0.78759765625,
"step": 613
},
{
"epoch": 2.4268774703557314,
"grad_norm": 0.046882059425115585,
"learning_rate": 0.00018313148909017865,
"loss": 0.79541015625,
"step": 614
},
{
"epoch": 2.430830039525692,
"grad_norm": 0.04611621052026749,
"learning_rate": 0.0001827814920612743,
"loss": 0.77734375,
"step": 615
},
{
"epoch": 2.4347826086956523,
"grad_norm": 0.048252951353788376,
"learning_rate": 0.00018243137336288124,
"loss": 0.75830078125,
"step": 616
},
{
"epoch": 2.438735177865613,
"grad_norm": 0.04710513353347778,
"learning_rate": 0.00018208113539067933,
"loss": 0.78369140625,
"step": 617
},
{
"epoch": 2.4426877470355732,
"grad_norm": 0.04928605258464813,
"learning_rate": 0.00018173078054116456,
"loss": 0.8095703125,
"step": 618
},
{
"epoch": 2.4466403162055337,
"grad_norm": 0.04609301686286926,
"learning_rate": 0.00018138031121163275,
"loss": 0.76123046875,
"step": 619
},
{
"epoch": 2.450592885375494,
"grad_norm": 0.05168458819389343,
"learning_rate": 0.00018102972980016296,
"loss": 0.807861328125,
"step": 620
},
{
"epoch": 2.4545454545454546,
"grad_norm": 0.05423901230096817,
"learning_rate": 0.0001806790387056011,
"loss": 0.84619140625,
"step": 621
},
{
"epoch": 2.458498023715415,
"grad_norm": 0.045651875436306,
"learning_rate": 0.00018032824032754383,
"loss": 0.7705078125,
"step": 622
},
{
"epoch": 2.4624505928853755,
"grad_norm": 0.04981774091720581,
"learning_rate": 0.00017997733706632166,
"loss": 0.82177734375,
"step": 623
},
{
"epoch": 2.466403162055336,
"grad_norm": 0.054035864770412445,
"learning_rate": 0.0001796263313229828,
"loss": 0.7373046875,
"step": 624
},
{
"epoch": 2.4703557312252964,
"grad_norm": 0.04274497181177139,
"learning_rate": 0.00017927522549927678,
"loss": 0.654510498046875,
"step": 625
},
{
"epoch": 2.474308300395257,
"grad_norm": 0.051630932837724686,
"learning_rate": 0.00017892402199763788,
"loss": 0.8173828125,
"step": 626
},
{
"epoch": 2.4782608695652173,
"grad_norm": 0.05124964937567711,
"learning_rate": 0.00017857272322116874,
"loss": 0.83203125,
"step": 627
},
{
"epoch": 2.4822134387351777,
"grad_norm": 0.05060219392180443,
"learning_rate": 0.00017822133157362386,
"loss": 0.80908203125,
"step": 628
},
{
"epoch": 2.486166007905138,
"grad_norm": 0.04931870102882385,
"learning_rate": 0.00017786984945939336,
"loss": 0.7587890625,
"step": 629
},
{
"epoch": 2.4901185770750986,
"grad_norm": 0.05254590883851051,
"learning_rate": 0.00017751827928348622,
"loss": 0.76611328125,
"step": 630
},
{
"epoch": 2.494071146245059,
"grad_norm": 0.05133964121341705,
"learning_rate": 0.00017716662345151402,
"loss": 0.80517578125,
"step": 631
},
{
"epoch": 2.4980237154150196,
"grad_norm": 0.04904676601290703,
"learning_rate": 0.0001768148843696745,
"loss": 0.80615234375,
"step": 632
},
{
"epoch": 2.5019762845849804,
"grad_norm": 0.05203196406364441,
"learning_rate": 0.00017646306444473497,
"loss": 0.7919921875,
"step": 633
},
{
"epoch": 2.5059288537549405,
"grad_norm": 0.05061133950948715,
"learning_rate": 0.00017611116608401596,
"loss": 0.7841796875,
"step": 634
},
{
"epoch": 2.5098814229249014,
"grad_norm": 0.04815781116485596,
"learning_rate": 0.0001757591916953746,
"loss": 0.759765625,
"step": 635
},
{
"epoch": 2.513833992094862,
"grad_norm": 0.051274754106998444,
"learning_rate": 0.0001754071436871884,
"loss": 0.77783203125,
"step": 636
},
{
"epoch": 2.5177865612648223,
"grad_norm": 0.05280039831995964,
"learning_rate": 0.0001750550244683385,
"loss": 0.7265625,
"step": 637
},
{
"epoch": 2.5217391304347827,
"grad_norm": 0.05001666396856308,
"learning_rate": 0.00017470283644819326,
"loss": 0.810546875,
"step": 638
},
{
"epoch": 2.525691699604743,
"grad_norm": 0.053191885352134705,
"learning_rate": 0.0001743505820365919,
"loss": 0.8232421875,
"step": 639
},
{
"epoch": 2.5296442687747036,
"grad_norm": 0.05170443281531334,
"learning_rate": 0.00017399826364382785,
"loss": 0.79248046875,
"step": 640
},
{
"epoch": 2.533596837944664,
"grad_norm": 0.05208049342036247,
"learning_rate": 0.0001736458836806324,
"loss": 0.767822265625,
"step": 641
},
{
"epoch": 2.5375494071146245,
"grad_norm": 0.05331271141767502,
"learning_rate": 0.0001732934445581582,
"loss": 0.81982421875,
"step": 642
},
{
"epoch": 2.541501976284585,
"grad_norm": 0.05136852711439133,
"learning_rate": 0.00017294094868796242,
"loss": 0.80908203125,
"step": 643
},
{
"epoch": 2.5454545454545454,
"grad_norm": 0.05010833591222763,
"learning_rate": 0.00017258839848199075,
"loss": 0.7919921875,
"step": 644
},
{
"epoch": 2.549407114624506,
"grad_norm": 0.04822184517979622,
"learning_rate": 0.00017223579635256074,
"loss": 0.80224609375,
"step": 645
},
{
"epoch": 2.5533596837944663,
"grad_norm": 0.04735623300075531,
"learning_rate": 0.00017188314471234493,
"loss": 0.7071533203125,
"step": 646
},
{
"epoch": 2.5573122529644268,
"grad_norm": 0.04892995208501816,
"learning_rate": 0.00017153044597435503,
"loss": 0.7763671875,
"step": 647
},
{
"epoch": 2.561264822134387,
"grad_norm": 0.04770994558930397,
"learning_rate": 0.00017117770255192463,
"loss": 0.8134765625,
"step": 648
},
{
"epoch": 2.5652173913043477,
"grad_norm": 0.0472155399620533,
"learning_rate": 0.00017082491685869333,
"loss": 0.76025390625,
"step": 649
},
{
"epoch": 2.5691699604743086,
"grad_norm": 0.04837966710329056,
"learning_rate": 0.0001704720913085898,
"loss": 0.74267578125,
"step": 650
},
{
"epoch": 2.5731225296442686,
"grad_norm": 0.05210874602198601,
"learning_rate": 0.00017011922831581562,
"loss": 0.77978515625,
"step": 651
},
{
"epoch": 2.5770750988142295,
"grad_norm": 0.047879863530397415,
"learning_rate": 0.00016976633029482837,
"loss": 0.79443359375,
"step": 652
},
{
"epoch": 2.5810276679841895,
"grad_norm": 0.05006123334169388,
"learning_rate": 0.00016941339966032544,
"loss": 0.744140625,
"step": 653
},
{
"epoch": 2.5849802371541504,
"grad_norm": 0.05046766623854637,
"learning_rate": 0.00016906043882722733,
"loss": 0.8076171875,
"step": 654
},
{
"epoch": 2.588932806324111,
"grad_norm": 0.04798324406147003,
"learning_rate": 0.00016870745021066121,
"loss": 0.80517578125,
"step": 655
},
{
"epoch": 2.5928853754940713,
"grad_norm": 0.0483081080019474,
"learning_rate": 0.00016835443622594432,
"loss": 0.79638671875,
"step": 656
},
{
"epoch": 2.5968379446640317,
"grad_norm": 0.055579736828804016,
"learning_rate": 0.0001680013992885675,
"loss": 0.81298828125,
"step": 657
},
{
"epoch": 2.600790513833992,
"grad_norm": 0.04978753253817558,
"learning_rate": 0.00016764834181417858,
"loss": 0.78857421875,
"step": 658
},
{
"epoch": 2.6047430830039526,
"grad_norm": 0.05404549837112427,
"learning_rate": 0.000167295266218566,
"loss": 0.8037109375,
"step": 659
},
{
"epoch": 2.608695652173913,
"grad_norm": 0.049912698566913605,
"learning_rate": 0.0001669421749176422,
"loss": 0.79296875,
"step": 660
},
{
"epoch": 2.6126482213438735,
"grad_norm": 0.04924013838171959,
"learning_rate": 0.000166589070327427,
"loss": 0.77197265625,
"step": 661
},
{
"epoch": 2.616600790513834,
"grad_norm": 0.051574837416410446,
"learning_rate": 0.00016623595486403125,
"loss": 0.837890625,
"step": 662
},
{
"epoch": 2.6205533596837944,
"grad_norm": 0.05079261586070061,
"learning_rate": 0.00016588283094364002,
"loss": 0.81494140625,
"step": 663
},
{
"epoch": 2.624505928853755,
"grad_norm": 0.0504782609641552,
"learning_rate": 0.0001655297009824965,
"loss": 0.76611328125,
"step": 664
},
{
"epoch": 2.6284584980237153,
"grad_norm": 0.05569262430071831,
"learning_rate": 0.0001651765673968851,
"loss": 0.7958984375,
"step": 665
},
{
"epoch": 2.632411067193676,
"grad_norm": 0.050162605941295624,
"learning_rate": 0.0001648234326031149,
"loss": 0.8095703125,
"step": 666
},
{
"epoch": 2.6363636363636362,
"grad_norm": 0.04872685670852661,
"learning_rate": 0.00016447029901750347,
"loss": 0.78271484375,
"step": 667
},
{
"epoch": 2.6403162055335967,
"grad_norm": 0.0540570393204689,
"learning_rate": 0.00016411716905635995,
"loss": 0.82080078125,
"step": 668
},
{
"epoch": 2.6442687747035576,
"grad_norm": 0.051567357033491135,
"learning_rate": 0.0001637640451359688,
"loss": 0.771484375,
"step": 669
},
{
"epoch": 2.6482213438735176,
"grad_norm": 0.05172124132514,
"learning_rate": 0.000163410929672573,
"loss": 0.80029296875,
"step": 670
},
{
"epoch": 2.6521739130434785,
"grad_norm": 0.05336343124508858,
"learning_rate": 0.0001630578250823578,
"loss": 0.76025390625,
"step": 671
},
{
"epoch": 2.6561264822134385,
"grad_norm": 0.05276660993695259,
"learning_rate": 0.00016270473378143395,
"loss": 0.75439453125,
"step": 672
},
{
"epoch": 2.6600790513833994,
"grad_norm": 0.051099881529808044,
"learning_rate": 0.00016235165818582141,
"loss": 0.7919921875,
"step": 673
},
{
"epoch": 2.66403162055336,
"grad_norm": 0.055066246539354324,
"learning_rate": 0.00016199860071143256,
"loss": 0.80419921875,
"step": 674
},
{
"epoch": 2.6679841897233203,
"grad_norm": 0.05164816230535507,
"learning_rate": 0.00016164556377405568,
"loss": 0.7412109375,
"step": 675
},
{
"epoch": 2.6719367588932808,
"grad_norm": 0.05231785029172897,
"learning_rate": 0.00016129254978933873,
"loss": 0.84521484375,
"step": 676
},
{
"epoch": 2.675889328063241,
"grad_norm": 0.053780488669872284,
"learning_rate": 0.00016093956117277266,
"loss": 0.7880859375,
"step": 677
},
{
"epoch": 2.6798418972332017,
"grad_norm": 0.048681799322366714,
"learning_rate": 0.00016058660033967454,
"loss": 0.7470703125,
"step": 678
},
{
"epoch": 2.683794466403162,
"grad_norm": 0.04854863882064819,
"learning_rate": 0.00016023366970517166,
"loss": 0.8251953125,
"step": 679
},
{
"epoch": 2.6877470355731226,
"grad_norm": 0.050627678632736206,
"learning_rate": 0.00015988077168418443,
"loss": 0.80615234375,
"step": 680
},
{
"epoch": 2.691699604743083,
"grad_norm": 0.05083775520324707,
"learning_rate": 0.0001595279086914102,
"loss": 0.7744140625,
"step": 681
},
{
"epoch": 2.6956521739130435,
"grad_norm": 0.049797188490629196,
"learning_rate": 0.00015917508314130667,
"loss": 0.75390625,
"step": 682
},
{
"epoch": 2.699604743083004,
"grad_norm": 0.05138544365763664,
"learning_rate": 0.00015882229744807537,
"loss": 0.7685546875,
"step": 683
},
{
"epoch": 2.7035573122529644,
"grad_norm": 0.04927722364664078,
"learning_rate": 0.000158469554025645,
"loss": 0.80615234375,
"step": 684
},
{
"epoch": 2.707509881422925,
"grad_norm": 0.051307618618011475,
"learning_rate": 0.00015811685528765502,
"loss": 0.7705078125,
"step": 685
},
{
"epoch": 2.7114624505928853,
"grad_norm": 0.05202597752213478,
"learning_rate": 0.00015776420364743926,
"loss": 0.7646484375,
"step": 686
},
{
"epoch": 2.7154150197628457,
"grad_norm": 0.051913194358348846,
"learning_rate": 0.00015741160151800925,
"loss": 0.76220703125,
"step": 687
},
{
"epoch": 2.719367588932806,
"grad_norm": 0.05061808228492737,
"learning_rate": 0.00015705905131203757,
"loss": 0.79931640625,
"step": 688
},
{
"epoch": 2.7233201581027666,
"grad_norm": 0.0506657175719738,
"learning_rate": 0.00015670655544184185,
"loss": 0.77685546875,
"step": 689
},
{
"epoch": 2.7272727272727275,
"grad_norm": 0.04603055119514465,
"learning_rate": 0.0001563541163193676,
"loss": 0.66796875,
"step": 690
},
{
"epoch": 2.7312252964426875,
"grad_norm": 0.05052204057574272,
"learning_rate": 0.00015600173635617212,
"loss": 0.78662109375,
"step": 691
},
{
"epoch": 2.7351778656126484,
"grad_norm": 0.0513266921043396,
"learning_rate": 0.00015564941796340808,
"loss": 0.83203125,
"step": 692
},
{
"epoch": 2.7391304347826084,
"grad_norm": 0.0499236024916172,
"learning_rate": 0.00015529716355180674,
"loss": 0.73583984375,
"step": 693
},
{
"epoch": 2.7430830039525693,
"grad_norm": 0.052487947046756744,
"learning_rate": 0.0001549449755316615,
"loss": 0.75,
"step": 694
},
{
"epoch": 2.7470355731225298,
"grad_norm": 0.05266030505299568,
"learning_rate": 0.0001545928563128116,
"loss": 0.8046875,
"step": 695
},
{
"epoch": 2.7509881422924902,
"grad_norm": 0.048343416303396225,
"learning_rate": 0.0001542408083046254,
"loss": 0.8173828125,
"step": 696
},
{
"epoch": 2.7549407114624507,
"grad_norm": 0.050842057913541794,
"learning_rate": 0.00015388883391598404,
"loss": 0.8271484375,
"step": 697
},
{
"epoch": 2.758893280632411,
"grad_norm": 0.04736270010471344,
"learning_rate": 0.000153536935555265,
"loss": 0.64453125,
"step": 698
},
{
"epoch": 2.7628458498023716,
"grad_norm": 0.05112220346927643,
"learning_rate": 0.0001531851156303255,
"loss": 0.76171875,
"step": 699
},
{
"epoch": 2.766798418972332,
"grad_norm": 0.05520337074995041,
"learning_rate": 0.00015283337654848597,
"loss": 0.80224609375,
"step": 700
},
{
"epoch": 2.7707509881422925,
"grad_norm": 0.04925573244690895,
"learning_rate": 0.00015248172071651378,
"loss": 0.706298828125,
"step": 701
},
{
"epoch": 2.774703557312253,
"grad_norm": 0.04990237206220627,
"learning_rate": 0.00015213015054060664,
"loss": 0.7890625,
"step": 702
},
{
"epoch": 2.7786561264822134,
"grad_norm": 0.04954756423830986,
"learning_rate": 0.00015177866842637608,
"loss": 0.7919921875,
"step": 703
},
{
"epoch": 2.782608695652174,
"grad_norm": 0.050141263753175735,
"learning_rate": 0.00015142727677883128,
"loss": 0.7548828125,
"step": 704
},
{
"epoch": 2.7865612648221343,
"grad_norm": 0.04988892376422882,
"learning_rate": 0.0001510759780023621,
"loss": 0.73876953125,
"step": 705
},
{
"epoch": 2.7905138339920947,
"grad_norm": 0.049026332795619965,
"learning_rate": 0.00015072477450072321,
"loss": 0.7578125,
"step": 706
},
{
"epoch": 2.794466403162055,
"grad_norm": 0.05193858593702316,
"learning_rate": 0.0001503736686770172,
"loss": 0.7841796875,
"step": 707
},
{
"epoch": 2.7984189723320156,
"grad_norm": 0.051796805113554,
"learning_rate": 0.0001500226629336783,
"loss": 0.763671875,
"step": 708
},
{
"epoch": 2.8023715415019765,
"grad_norm": 0.05025576427578926,
"learning_rate": 0.00014967175967245616,
"loss": 0.77685546875,
"step": 709
},
{
"epoch": 2.8063241106719365,
"grad_norm": 0.05267256498336792,
"learning_rate": 0.0001493209612943989,
"loss": 0.8466796875,
"step": 710
},
{
"epoch": 2.8102766798418974,
"grad_norm": 0.050027523189783096,
"learning_rate": 0.00014897027019983706,
"loss": 0.80615234375,
"step": 711
},
{
"epoch": 2.8142292490118574,
"grad_norm": 0.056734491139650345,
"learning_rate": 0.00014861968878836725,
"loss": 0.78125,
"step": 712
},
{
"epoch": 2.8181818181818183,
"grad_norm": 0.05816735327243805,
"learning_rate": 0.0001482692194588354,
"loss": 0.74755859375,
"step": 713
},
{
"epoch": 2.822134387351779,
"grad_norm": 0.051682472229003906,
"learning_rate": 0.00014791886460932072,
"loss": 0.76953125,
"step": 714
},
{
"epoch": 2.8260869565217392,
"grad_norm": 0.05062028393149376,
"learning_rate": 0.00014756862663711876,
"loss": 0.76708984375,
"step": 715
},
{
"epoch": 2.8300395256916997,
"grad_norm": 0.056935474276542664,
"learning_rate": 0.0001472185079387257,
"loss": 0.79541015625,
"step": 716
},
{
"epoch": 2.83399209486166,
"grad_norm": 0.05212491378188133,
"learning_rate": 0.00014686851090982134,
"loss": 0.82177734375,
"step": 717
},
{
"epoch": 2.8379446640316206,
"grad_norm": 0.05325692892074585,
"learning_rate": 0.00014651863794525315,
"loss": 0.76025390625,
"step": 718
},
{
"epoch": 2.841897233201581,
"grad_norm": 0.05286204814910889,
"learning_rate": 0.00014616889143901957,
"loss": 0.7548828125,
"step": 719
},
{
"epoch": 2.8458498023715415,
"grad_norm": 0.050668634474277496,
"learning_rate": 0.0001458192737842537,
"loss": 0.79248046875,
"step": 720
},
{
"epoch": 2.849802371541502,
"grad_norm": 0.050589222460985184,
"learning_rate": 0.00014546978737320712,
"loss": 0.74853515625,
"step": 721
},
{
"epoch": 2.8537549407114624,
"grad_norm": 0.05571528896689415,
"learning_rate": 0.0001451204345972333,
"loss": 0.78857421875,
"step": 722
},
{
"epoch": 2.857707509881423,
"grad_norm": 0.05910651758313179,
"learning_rate": 0.00014477121784677133,
"loss": 0.8115234375,
"step": 723
},
{
"epoch": 2.8616600790513833,
"grad_norm": 0.049208275973796844,
"learning_rate": 0.00014442213951132953,
"loss": 0.81787109375,
"step": 724
},
{
"epoch": 2.8656126482213438,
"grad_norm": 0.0521659329533577,
"learning_rate": 0.0001440732019794692,
"loss": 0.796142578125,
"step": 725
},
{
"epoch": 2.869565217391304,
"grad_norm": 0.052084822207689285,
"learning_rate": 0.00014372440763878804,
"loss": 0.80615234375,
"step": 726
},
{
"epoch": 2.8735177865612647,
"grad_norm": 0.05112325772643089,
"learning_rate": 0.00014337575887590407,
"loss": 0.8212890625,
"step": 727
},
{
"epoch": 2.8774703557312256,
"grad_norm": 0.052766695618629456,
"learning_rate": 0.00014302725807643923,
"loss": 0.8330078125,
"step": 728
},
{
"epoch": 2.8814229249011856,
"grad_norm": 0.05308271944522858,
"learning_rate": 0.0001426789076250029,
"loss": 0.73583984375,
"step": 729
},
{
"epoch": 2.8853754940711465,
"grad_norm": 0.04873475059866905,
"learning_rate": 0.00014233070990517588,
"loss": 0.75048828125,
"step": 730
},
{
"epoch": 2.8893280632411065,
"grad_norm": 0.051746852695941925,
"learning_rate": 0.0001419826672994937,
"loss": 0.7880859375,
"step": 731
},
{
"epoch": 2.8932806324110674,
"grad_norm": 0.04904266074299812,
"learning_rate": 0.00014163478218943076,
"loss": 0.73779296875,
"step": 732
},
{
"epoch": 2.897233201581028,
"grad_norm": 0.04873509705066681,
"learning_rate": 0.00014128705695538353,
"loss": 0.78369140625,
"step": 733
},
{
"epoch": 2.9011857707509883,
"grad_norm": 0.053178515285253525,
"learning_rate": 0.00014093949397665483,
"loss": 0.744140625,
"step": 734
},
{
"epoch": 2.9051383399209487,
"grad_norm": 0.05499696731567383,
"learning_rate": 0.000140592095631437,
"loss": 0.759765625,
"step": 735
},
{
"epoch": 2.909090909090909,
"grad_norm": 0.04868374392390251,
"learning_rate": 0.00014024486429679592,
"loss": 0.8173828125,
"step": 736
},
{
"epoch": 2.9130434782608696,
"grad_norm": 0.050794512033462524,
"learning_rate": 0.00013989780234865487,
"loss": 0.771484375,
"step": 737
},
{
"epoch": 2.91699604743083,
"grad_norm": 0.053152915090322495,
"learning_rate": 0.00013955091216177795,
"loss": 0.8095703125,
"step": 738
},
{
"epoch": 2.9209486166007905,
"grad_norm": 0.05093550682067871,
"learning_rate": 0.00013920419610975404,
"loss": 0.79736328125,
"step": 739
},
{
"epoch": 2.924901185770751,
"grad_norm": 0.051597364246845245,
"learning_rate": 0.00013885765656498054,
"loss": 0.77294921875,
"step": 740
},
{
"epoch": 2.9288537549407114,
"grad_norm": 0.05065556988120079,
"learning_rate": 0.000138511295898647,
"loss": 0.74560546875,
"step": 741
},
{
"epoch": 2.932806324110672,
"grad_norm": 0.04829628765583038,
"learning_rate": 0.000138165116480719,
"loss": 0.6778717041015625,
"step": 742
},
{
"epoch": 2.9367588932806323,
"grad_norm": 0.050820861011743546,
"learning_rate": 0.0001378191206799221,
"loss": 0.78857421875,
"step": 743
},
{
"epoch": 2.940711462450593,
"grad_norm": 0.05142400413751602,
"learning_rate": 0.00013747331086372535,
"loss": 0.802734375,
"step": 744
},
{
"epoch": 2.9446640316205532,
"grad_norm": 0.048891760408878326,
"learning_rate": 0.00013712768939832517,
"loss": 0.76220703125,
"step": 745
},
{
"epoch": 2.9486166007905137,
"grad_norm": 0.051397357136011124,
"learning_rate": 0.00013678225864862924,
"loss": 0.7783203125,
"step": 746
},
{
"epoch": 2.9525691699604746,
"grad_norm": 0.05603568255901337,
"learning_rate": 0.00013643702097824027,
"loss": 0.75390625,
"step": 747
},
{
"epoch": 2.9565217391304346,
"grad_norm": 0.05158814415335655,
"learning_rate": 0.00013609197874943975,
"loss": 0.818359375,
"step": 748
},
{
"epoch": 2.9604743083003955,
"grad_norm": 0.053329404443502426,
"learning_rate": 0.00013574713432317205,
"loss": 0.7783203125,
"step": 749
},
{
"epoch": 2.9644268774703555,
"grad_norm": 0.05176032707095146,
"learning_rate": 0.00013540249005902796,
"loss": 0.78662109375,
"step": 750
},
{
"epoch": 2.9683794466403164,
"grad_norm": 0.048907071352005005,
"learning_rate": 0.0001350580483152286,
"loss": 0.68994140625,
"step": 751
},
{
"epoch": 2.972332015810277,
"grad_norm": 0.05139489099383354,
"learning_rate": 0.00013471381144860946,
"loss": 0.791015625,
"step": 752
},
{
"epoch": 2.9762845849802373,
"grad_norm": 0.05032915994524956,
"learning_rate": 0.0001343697818146041,
"loss": 0.744140625,
"step": 753
},
{
"epoch": 2.9802371541501977,
"grad_norm": 0.052021317183971405,
"learning_rate": 0.00013402596176722813,
"loss": 0.77294921875,
"step": 754
},
{
"epoch": 2.984189723320158,
"grad_norm": 0.04918317124247551,
"learning_rate": 0.00013368235365906315,
"loss": 0.79345703125,
"step": 755
},
{
"epoch": 2.9881422924901186,
"grad_norm": 0.043905504047870636,
"learning_rate": 0.0001333389598412403,
"loss": 0.66925048828125,
"step": 756
},
{
"epoch": 2.992094861660079,
"grad_norm": 0.05138632282614708,
"learning_rate": 0.00013299578266342478,
"loss": 0.80859375,
"step": 757
},
{
"epoch": 2.9960474308300395,
"grad_norm": 0.05320889502763748,
"learning_rate": 0.0001326528244737991,
"loss": 0.73291015625,
"step": 758
},
{
"epoch": 3.0,
"grad_norm": 0.05528523400425911,
"learning_rate": 0.0001323100876190477,
"loss": 0.740234375,
"step": 759
},
{
"epoch": 3.0,
"eval_loss": 0.82666015625,
"eval_runtime": 2.2312,
"eval_samples_per_second": 2.689,
"eval_steps_per_second": 0.448,
"step": 759
},
{
"epoch": 3.0039525691699605,
"grad_norm": 0.051899995654821396,
"learning_rate": 0.00013196757444434033,
"loss": 0.74755859375,
"step": 760
},
{
"epoch": 3.007905138339921,
"grad_norm": 0.06162136793136597,
"learning_rate": 0.00013162528729331619,
"loss": 0.7763671875,
"step": 761
},
{
"epoch": 3.0118577075098814,
"grad_norm": 0.06101340427994728,
"learning_rate": 0.00013128322850806796,
"loss": 0.79833984375,
"step": 762
},
{
"epoch": 3.015810276679842,
"grad_norm": 0.05581176280975342,
"learning_rate": 0.00013094140042912582,
"loss": 0.7919921875,
"step": 763
},
{
"epoch": 3.0197628458498023,
"grad_norm": 0.051494572311639786,
"learning_rate": 0.0001305998053954412,
"loss": 0.7958984375,
"step": 764
},
{
"epoch": 3.0237154150197627,
"grad_norm": 0.05755125731229782,
"learning_rate": 0.00013025844574437109,
"loss": 0.8056640625,
"step": 765
},
{
"epoch": 3.027667984189723,
"grad_norm": 0.053429752588272095,
"learning_rate": 0.0001299173238116617,
"loss": 0.755859375,
"step": 766
},
{
"epoch": 3.0316205533596836,
"grad_norm": 0.054341088980436325,
"learning_rate": 0.0001295764419314328,
"loss": 0.8251953125,
"step": 767
},
{
"epoch": 3.035573122529644,
"grad_norm": 0.06252113729715347,
"learning_rate": 0.00012923580243616147,
"loss": 0.765625,
"step": 768
},
{
"epoch": 3.039525691699605,
"grad_norm": 0.06053081899881363,
"learning_rate": 0.00012889540765666644,
"loss": 0.8037109375,
"step": 769
},
{
"epoch": 3.0434782608695654,
"grad_norm": 0.05292205139994621,
"learning_rate": 0.0001285552599220919,
"loss": 0.7890625,
"step": 770
},
{
"epoch": 3.047430830039526,
"grad_norm": 0.05917607247829437,
"learning_rate": 0.00012821536155989153,
"loss": 0.646484375,
"step": 771
},
{
"epoch": 3.0513833992094863,
"grad_norm": 0.056112755089998245,
"learning_rate": 0.00012787571489581288,
"loss": 0.77880859375,
"step": 772
},
{
"epoch": 3.0553359683794468,
"grad_norm": 0.05101701244711876,
"learning_rate": 0.0001275363222538811,
"loss": 0.739990234375,
"step": 773
},
{
"epoch": 3.059288537549407,
"grad_norm": 0.06536255776882172,
"learning_rate": 0.00012719718595638333,
"loss": 0.79345703125,
"step": 774
},
{
"epoch": 3.0632411067193677,
"grad_norm": 0.06030237302184105,
"learning_rate": 0.00012685830832385268,
"loss": 0.780029296875,
"step": 775
},
{
"epoch": 3.067193675889328,
"grad_norm": 0.05529727414250374,
"learning_rate": 0.0001265196916750521,
"loss": 0.7392578125,
"step": 776
},
{
"epoch": 3.0711462450592886,
"grad_norm": 0.056271884590387344,
"learning_rate": 0.0001261813383269591,
"loss": 0.75244140625,
"step": 777
},
{
"epoch": 3.075098814229249,
"grad_norm": 0.0604536235332489,
"learning_rate": 0.00012584325059474932,
"loss": 0.822265625,
"step": 778
},
{
"epoch": 3.0790513833992095,
"grad_norm": 0.05639917030930519,
"learning_rate": 0.0001255054307917811,
"loss": 0.771484375,
"step": 779
},
{
"epoch": 3.08300395256917,
"grad_norm": 0.05530835688114166,
"learning_rate": 0.00012516788122957936,
"loss": 0.79150390625,
"step": 780
},
{
"epoch": 3.0869565217391304,
"grad_norm": 0.0566108264029026,
"learning_rate": 0.00012483060421781994,
"loss": 0.7958984375,
"step": 781
},
{
"epoch": 3.090909090909091,
"grad_norm": 0.05416880548000336,
"learning_rate": 0.00012449360206431373,
"loss": 0.7188720703125,
"step": 782
},
{
"epoch": 3.0948616600790513,
"grad_norm": 0.05598125979304314,
"learning_rate": 0.000124156877074991,
"loss": 0.78759765625,
"step": 783
},
{
"epoch": 3.0988142292490117,
"grad_norm": 0.05141172185540199,
"learning_rate": 0.00012382043155388545,
"loss": 0.732421875,
"step": 784
},
{
"epoch": 3.102766798418972,
"grad_norm": 0.05593885853886604,
"learning_rate": 0.00012348426780311856,
"loss": 0.73046875,
"step": 785
},
{
"epoch": 3.1067193675889326,
"grad_norm": 0.05612756684422493,
"learning_rate": 0.00012314838812288377,
"loss": 0.77099609375,
"step": 786
},
{
"epoch": 3.110671936758893,
"grad_norm": 0.051879674196243286,
"learning_rate": 0.00012281279481143073,
"loss": 0.763671875,
"step": 787
},
{
"epoch": 3.1146245059288535,
"grad_norm": 0.04744001477956772,
"learning_rate": 0.00012247749016504976,
"loss": 0.6829833984375,
"step": 788
},
{
"epoch": 3.1185770750988144,
"grad_norm": 0.055309098213911057,
"learning_rate": 0.00012214247647805587,
"loss": 0.7783203125,
"step": 789
},
{
"epoch": 3.122529644268775,
"grad_norm": 0.05403228476643562,
"learning_rate": 0.00012180775604277324,
"loss": 0.80126953125,
"step": 790
},
{
"epoch": 3.1264822134387353,
"grad_norm": 0.04919366165995598,
"learning_rate": 0.00012147333114951956,
"loss": 0.73046875,
"step": 791
},
{
"epoch": 3.130434782608696,
"grad_norm": 0.050172075629234314,
"learning_rate": 0.00012113920408659006,
"loss": 0.71044921875,
"step": 792
},
{
"epoch": 3.1343873517786562,
"grad_norm": 0.057564280927181244,
"learning_rate": 0.0001208053771402422,
"loss": 0.78759765625,
"step": 793
},
{
"epoch": 3.1383399209486167,
"grad_norm": 0.053241100162267685,
"learning_rate": 0.00012047185259467998,
"loss": 0.779296875,
"step": 794
},
{
"epoch": 3.142292490118577,
"grad_norm": 0.052953559905290604,
"learning_rate": 0.00012013863273203813,
"loss": 0.79150390625,
"step": 795
},
{
"epoch": 3.1462450592885376,
"grad_norm": 0.05897699296474457,
"learning_rate": 0.00011980571983236667,
"loss": 0.76318359375,
"step": 796
},
{
"epoch": 3.150197628458498,
"grad_norm": 0.05418133735656738,
"learning_rate": 0.000119473116173615,
"loss": 0.7900390625,
"step": 797
},
{
"epoch": 3.1541501976284585,
"grad_norm": 0.04996829479932785,
"learning_rate": 0.00011914082403161687,
"loss": 0.76123046875,
"step": 798
},
{
"epoch": 3.158102766798419,
"grad_norm": 0.05383431538939476,
"learning_rate": 0.00011880884568007431,
"loss": 0.77783203125,
"step": 799
},
{
"epoch": 3.1620553359683794,
"grad_norm": 0.05254179984331131,
"learning_rate": 0.00011847718339054222,
"loss": 0.71533203125,
"step": 800
},
{
"epoch": 3.16600790513834,
"grad_norm": 0.05000333487987518,
"learning_rate": 0.00011814583943241301,
"loss": 0.74267578125,
"step": 801
},
{
"epoch": 3.1699604743083003,
"grad_norm": 0.05227748304605484,
"learning_rate": 0.00011781481607290072,
"loss": 0.73974609375,
"step": 802
},
{
"epoch": 3.1739130434782608,
"grad_norm": 0.05048929154872894,
"learning_rate": 0.00011748411557702575,
"loss": 0.73095703125,
"step": 803
},
{
"epoch": 3.177865612648221,
"grad_norm": 0.05667538195848465,
"learning_rate": 0.0001171537402075994,
"loss": 0.7705078125,
"step": 804
},
{
"epoch": 3.1818181818181817,
"grad_norm": 0.05378851667046547,
"learning_rate": 0.00011682369222520828,
"loss": 0.74853515625,
"step": 805
},
{
"epoch": 3.185770750988142,
"grad_norm": 0.04754330962896347,
"learning_rate": 0.00011649397388819886,
"loss": 0.59869384765625,
"step": 806
},
{
"epoch": 3.1897233201581026,
"grad_norm": 0.05500974506139755,
"learning_rate": 0.00011616458745266183,
"loss": 0.7880859375,
"step": 807
},
{
"epoch": 3.1936758893280635,
"grad_norm": 0.0505843460559845,
"learning_rate": 0.00011583553517241714,
"loss": 0.74169921875,
"step": 808
},
{
"epoch": 3.197628458498024,
"grad_norm": 0.05279306322336197,
"learning_rate": 0.00011550681929899811,
"loss": 0.763671875,
"step": 809
},
{
"epoch": 3.2015810276679844,
"grad_norm": 0.052863262593746185,
"learning_rate": 0.00011517844208163622,
"loss": 0.78662109375,
"step": 810
},
{
"epoch": 3.205533596837945,
"grad_norm": 0.05115286260843277,
"learning_rate": 0.00011485040576724587,
"loss": 0.67724609375,
"step": 811
},
{
"epoch": 3.2094861660079053,
"grad_norm": 0.05531739071011543,
"learning_rate": 0.00011452271260040856,
"loss": 0.7783203125,
"step": 812
},
{
"epoch": 3.2134387351778657,
"grad_norm": 0.05174247547984123,
"learning_rate": 0.00011419536482335799,
"loss": 0.7685546875,
"step": 813
},
{
"epoch": 3.217391304347826,
"grad_norm": 0.05128086358308792,
"learning_rate": 0.00011386836467596456,
"loss": 0.78759765625,
"step": 814
},
{
"epoch": 3.2213438735177866,
"grad_norm": 0.05611417442560196,
"learning_rate": 0.00011354171439571986,
"loss": 0.7255859375,
"step": 815
},
{
"epoch": 3.225296442687747,
"grad_norm": 0.055481016635894775,
"learning_rate": 0.00011321541621772174,
"loss": 0.681640625,
"step": 816
},
{
"epoch": 3.2292490118577075,
"grad_norm": 0.05108511075377464,
"learning_rate": 0.00011288947237465856,
"loss": 0.7646484375,
"step": 817
},
{
"epoch": 3.233201581027668,
"grad_norm": 0.05600423738360405,
"learning_rate": 0.00011256388509679436,
"loss": 0.8017578125,
"step": 818
},
{
"epoch": 3.2371541501976284,
"grad_norm": 0.057243626564741135,
"learning_rate": 0.00011223865661195325,
"loss": 0.76318359375,
"step": 819
},
{
"epoch": 3.241106719367589,
"grad_norm": 0.053384605795145035,
"learning_rate": 0.00011191378914550442,
"loss": 0.705078125,
"step": 820
},
{
"epoch": 3.2450592885375493,
"grad_norm": 2.3215250968933105,
"learning_rate": 0.0001115892849203467,
"loss": 0.65301513671875,
"step": 821
},
{
"epoch": 3.2490118577075098,
"grad_norm": 0.0616152361035347,
"learning_rate": 0.00011126514615689345,
"loss": 0.716796875,
"step": 822
},
{
"epoch": 3.2529644268774702,
"grad_norm": 0.05792299658060074,
"learning_rate": 0.00011094137507305742,
"loss": 0.76220703125,
"step": 823
},
{
"epoch": 3.2569169960474307,
"grad_norm": 0.05174622684717178,
"learning_rate": 0.00011061797388423553,
"loss": 0.74560546875,
"step": 824
},
{
"epoch": 3.260869565217391,
"grad_norm": 0.05768445506691933,
"learning_rate": 0.00011029494480329362,
"loss": 0.759765625,
"step": 825
},
{
"epoch": 3.2648221343873516,
"grad_norm": 0.06220095977187157,
"learning_rate": 0.00010997229004055156,
"loss": 0.79638671875,
"step": 826
},
{
"epoch": 3.2687747035573125,
"grad_norm": 0.05393914505839348,
"learning_rate": 0.0001096500118037677,
"loss": 0.740234375,
"step": 827
},
{
"epoch": 3.2727272727272725,
"grad_norm": 0.05432239547371864,
"learning_rate": 0.00010932811229812426,
"loss": 0.7509765625,
"step": 828
},
{
"epoch": 3.2766798418972334,
"grad_norm": 0.059977006167173386,
"learning_rate": 0.00010900659372621178,
"loss": 0.77392578125,
"step": 829
},
{
"epoch": 3.280632411067194,
"grad_norm": 0.05477907136082649,
"learning_rate": 0.00010868545828801452,
"loss": 0.73193359375,
"step": 830
},
{
"epoch": 3.2845849802371543,
"grad_norm": 0.05100884288549423,
"learning_rate": 0.000108364708180895,
"loss": 0.79541015625,
"step": 831
},
{
"epoch": 3.2885375494071147,
"grad_norm": 0.05638902261853218,
"learning_rate": 0.000108044345599579,
"loss": 0.7490234375,
"step": 832
},
{
"epoch": 3.292490118577075,
"grad_norm": 0.0547369085252285,
"learning_rate": 0.00010772437273614093,
"loss": 0.78759765625,
"step": 833
},
{
"epoch": 3.2964426877470356,
"grad_norm": 0.052789900451898575,
"learning_rate": 0.00010740479177998842,
"loss": 0.73486328125,
"step": 834
},
{
"epoch": 3.300395256916996,
"grad_norm": 0.05357060208916664,
"learning_rate": 0.00010708560491784754,
"loss": 0.76806640625,
"step": 835
},
{
"epoch": 3.3043478260869565,
"grad_norm": 0.053670529276132584,
"learning_rate": 0.00010676681433374769,
"loss": 0.7607421875,
"step": 836
},
{
"epoch": 3.308300395256917,
"grad_norm": 0.053498417139053345,
"learning_rate": 0.00010644842220900674,
"loss": 0.75732421875,
"step": 837
},
{
"epoch": 3.3122529644268774,
"grad_norm": 0.05245465040206909,
"learning_rate": 0.00010613043072221622,
"loss": 0.7646484375,
"step": 838
},
{
"epoch": 3.316205533596838,
"grad_norm": 0.055819518864154816,
"learning_rate": 0.00010581284204922625,
"loss": 0.74169921875,
"step": 839
},
{
"epoch": 3.3201581027667983,
"grad_norm": 0.05201595649123192,
"learning_rate": 0.00010549565836313071,
"loss": 0.68408203125,
"step": 840
},
{
"epoch": 3.324110671936759,
"grad_norm": 0.051147766411304474,
"learning_rate": 0.00010517888183425243,
"loss": 0.74462890625,
"step": 841
},
{
"epoch": 3.3280632411067192,
"grad_norm": 0.05324004963040352,
"learning_rate": 0.00010486251463012813,
"loss": 0.8017578125,
"step": 842
},
{
"epoch": 3.3320158102766797,
"grad_norm": 0.051513224840164185,
"learning_rate": 0.00010454655891549375,
"loss": 0.734375,
"step": 843
},
{
"epoch": 3.33596837944664,
"grad_norm": 0.052302587777376175,
"learning_rate": 0.00010423101685226975,
"loss": 0.74951171875,
"step": 844
},
{
"epoch": 3.3399209486166006,
"grad_norm": 0.05285404622554779,
"learning_rate": 0.00010391589059954612,
"loss": 0.771484375,
"step": 845
},
{
"epoch": 3.3438735177865615,
"grad_norm": 0.05412985756993294,
"learning_rate": 0.00010360118231356766,
"loss": 0.73828125,
"step": 846
},
{
"epoch": 3.3478260869565215,
"grad_norm": 0.054956164211034775,
"learning_rate": 0.00010328689414771931,
"loss": 0.72705078125,
"step": 847
},
{
"epoch": 3.3517786561264824,
"grad_norm": 0.053771331906318665,
"learning_rate": 0.00010297302825251126,
"loss": 0.779296875,
"step": 848
},
{
"epoch": 3.355731225296443,
"grad_norm": 0.04873364046216011,
"learning_rate": 0.00010265958677556428,
"loss": 0.7108154296875,
"step": 849
},
{
"epoch": 3.3596837944664033,
"grad_norm": 0.05224348604679108,
"learning_rate": 0.0001023465718615952,
"loss": 0.74462890625,
"step": 850
},
{
"epoch": 3.3636363636363638,
"grad_norm": 0.053375955671072006,
"learning_rate": 0.00010203398565240204,
"loss": 0.74853515625,
"step": 851
},
{
"epoch": 3.367588932806324,
"grad_norm": 0.050562094897031784,
"learning_rate": 0.0001017218302868495,
"loss": 0.73876953125,
"step": 852
},
{
"epoch": 3.3715415019762847,
"grad_norm": 0.05314769595861435,
"learning_rate": 0.00010141010790085403,
"loss": 0.72314453125,
"step": 853
},
{
"epoch": 3.375494071146245,
"grad_norm": 0.05577458068728447,
"learning_rate": 0.00010109882062736967,
"loss": 0.78125,
"step": 854
},
{
"epoch": 3.3794466403162056,
"grad_norm": 0.05554281547665596,
"learning_rate": 0.000100787970596373,
"loss": 0.796875,
"step": 855
},
{
"epoch": 3.383399209486166,
"grad_norm": 0.0484260730445385,
"learning_rate": 0.00010047755993484891,
"loss": 0.6470947265625,
"step": 856
},
{
"epoch": 3.3873517786561265,
"grad_norm": 0.053015198558568954,
"learning_rate": 0.00010016759076677596,
"loss": 0.771484375,
"step": 857
},
{
"epoch": 3.391304347826087,
"grad_norm": 0.05134866014122963,
"learning_rate": 9.985806521311158e-05,
"loss": 0.75,
"step": 858
},
{
"epoch": 3.3952569169960474,
"grad_norm": 0.051030248403549194,
"learning_rate": 9.954898539177801e-05,
"loss": 0.77099609375,
"step": 859
},
{
"epoch": 3.399209486166008,
"grad_norm": 0.05247574672102928,
"learning_rate": 9.924035341764746e-05,
"loss": 0.7353515625,
"step": 860
},
{
"epoch": 3.4031620553359683,
"grad_norm": 0.05345858260989189,
"learning_rate": 9.893217140252784e-05,
"loss": 0.74755859375,
"step": 861
},
{
"epoch": 3.4071146245059287,
"grad_norm": 0.05108778551220894,
"learning_rate": 9.862444145514812e-05,
"loss": 0.7646484375,
"step": 862
},
{
"epoch": 3.411067193675889,
"grad_norm": 0.0508539117872715,
"learning_rate": 9.831716568114398e-05,
"loss": 0.7021484375,
"step": 863
},
{
"epoch": 3.4150197628458496,
"grad_norm": 0.05132082849740982,
"learning_rate": 9.801034618304355e-05,
"loss": 0.70361328125,
"step": 864
},
{
"epoch": 3.4189723320158105,
"grad_norm": 0.05184292420744896,
"learning_rate": 9.770398506025287e-05,
"loss": 0.74560546875,
"step": 865
},
{
"epoch": 3.4229249011857705,
"grad_norm": 0.051414720714092255,
"learning_rate": 9.739808440904152e-05,
"loss": 0.74462890625,
"step": 866
},
{
"epoch": 3.4268774703557314,
"grad_norm": 0.051381465047597885,
"learning_rate": 9.709264632252837e-05,
"loss": 0.7529296875,
"step": 867
},
{
"epoch": 3.430830039525692,
"grad_norm": 0.05242805927991867,
"learning_rate": 9.678767289066716e-05,
"loss": 0.73388671875,
"step": 868
},
{
"epoch": 3.4347826086956523,
"grad_norm": 0.05319010838866234,
"learning_rate": 9.648316620023212e-05,
"loss": 0.71630859375,
"step": 869
},
{
"epoch": 3.438735177865613,
"grad_norm": 0.05086330324411392,
"learning_rate": 9.6179128334804e-05,
"loss": 0.740234375,
"step": 870
},
{
"epoch": 3.4426877470355732,
"grad_norm": 0.05177238583564758,
"learning_rate": 9.58755613747556e-05,
"loss": 0.7646484375,
"step": 871
},
{
"epoch": 3.4466403162055337,
"grad_norm": 0.05241120979189873,
"learning_rate": 9.557246739723753e-05,
"loss": 0.720703125,
"step": 872
},
{
"epoch": 3.450592885375494,
"grad_norm": 0.05358758196234703,
"learning_rate": 9.52698484761639e-05,
"loss": 0.7587890625,
"step": 873
},
{
"epoch": 3.4545454545454546,
"grad_norm": 0.053646866232156754,
"learning_rate": 9.496770668219852e-05,
"loss": 0.79736328125,
"step": 874
},
{
"epoch": 3.458498023715415,
"grad_norm": 0.05216224491596222,
"learning_rate": 9.466604408274013e-05,
"loss": 0.72900390625,
"step": 875
},
{
"epoch": 3.4624505928853755,
"grad_norm": 0.053330615162849426,
"learning_rate": 9.436486274190893e-05,
"loss": 0.77685546875,
"step": 876
},
{
"epoch": 3.466403162055336,
"grad_norm": 0.057709477841854095,
"learning_rate": 9.406416472053196e-05,
"loss": 0.690673828125,
"step": 877
},
{
"epoch": 3.4703557312252964,
"grad_norm": 0.04858383163809776,
"learning_rate": 9.376395207612904e-05,
"loss": 0.620086669921875,
"step": 878
},
{
"epoch": 3.474308300395257,
"grad_norm": 0.0550827756524086,
"learning_rate": 9.346422686289904e-05,
"loss": 0.771484375,
"step": 879
},
{
"epoch": 3.4782608695652173,
"grad_norm": 0.05308609828352928,
"learning_rate": 9.31649911317055e-05,
"loss": 0.78515625,
"step": 880
},
{
"epoch": 3.4822134387351777,
"grad_norm": 0.053905121982097626,
"learning_rate": 9.286624693006258e-05,
"loss": 0.76416015625,
"step": 881
},
{
"epoch": 3.486166007905138,
"grad_norm": 0.05441486835479736,
"learning_rate": 9.256799630212134e-05,
"loss": 0.71923828125,
"step": 882
},
{
"epoch": 3.4901185770750986,
"grad_norm": 0.054014090448617935,
"learning_rate": 9.227024128865539e-05,
"loss": 0.72412109375,
"step": 883
},
{
"epoch": 3.494071146245059,
"grad_norm": 0.05252964794635773,
"learning_rate": 9.197298392704725e-05,
"loss": 0.76123046875,
"step": 884
},
{
"epoch": 3.4980237154150196,
"grad_norm": 0.054570894688367844,
"learning_rate": 9.167622625127425e-05,
"loss": 0.7607421875,
"step": 885
},
{
"epoch": 3.5019762845849804,
"grad_norm": 0.05284995585680008,
"learning_rate": 9.137997029189461e-05,
"loss": 0.74951171875,
"step": 886
},
{
"epoch": 3.5059288537549405,
"grad_norm": 0.053298115730285645,
"learning_rate": 9.108421807603353e-05,
"loss": 0.7421875,
"step": 887
},
{
"epoch": 3.5098814229249014,
"grad_norm": 0.05470963194966316,
"learning_rate": 9.078897162736931e-05,
"loss": 0.7158203125,
"step": 888
},
{
"epoch": 3.513833992094862,
"grad_norm": 0.05425053834915161,
"learning_rate": 9.049423296611971e-05,
"loss": 0.734375,
"step": 889
},
{
"epoch": 3.5177865612648223,
"grad_norm": 0.05183039605617523,
"learning_rate": 9.020000410902784e-05,
"loss": 0.6845703125,
"step": 890
},
{
"epoch": 3.5217391304347827,
"grad_norm": 0.05399145558476448,
"learning_rate": 8.990628706934852e-05,
"loss": 0.763671875,
"step": 891
},
{
"epoch": 3.525691699604743,
"grad_norm": 0.0534062385559082,
"learning_rate": 8.96130838568345e-05,
"loss": 0.77783203125,
"step": 892
},
{
"epoch": 3.5296442687747036,
"grad_norm": 0.053236447274684906,
"learning_rate": 8.932039647772266e-05,
"loss": 0.7470703125,
"step": 893
},
{
"epoch": 3.533596837944664,
"grad_norm": 0.05518777295947075,
"learning_rate": 8.902822693472024e-05,
"loss": 0.7236328125,
"step": 894
},
{
"epoch": 3.5375494071146245,
"grad_norm": 0.053785745054483414,
"learning_rate": 8.873657722699123e-05,
"loss": 0.7734375,
"step": 895
},
{
"epoch": 3.541501976284585,
"grad_norm": 0.05190523713827133,
"learning_rate": 8.844544935014272e-05,
"loss": 0.76513671875,
"step": 896
},
{
"epoch": 3.5454545454545454,
"grad_norm": 0.05303623154759407,
"learning_rate": 8.815484529621116e-05,
"loss": 0.74853515625,
"step": 897
},
{
"epoch": 3.549407114624506,
"grad_norm": 0.05198900029063225,
"learning_rate": 8.786476705364872e-05,
"loss": 0.7578125,
"step": 898
},
{
"epoch": 3.5533596837944663,
"grad_norm": 0.057638019323349,
"learning_rate": 8.75752166073097e-05,
"loss": 0.66552734375,
"step": 899
},
{
"epoch": 3.5573122529644268,
"grad_norm": 0.05313939228653908,
"learning_rate": 8.728619593843697e-05,
"loss": 0.732421875,
"step": 900
},
{
"epoch": 3.561264822134387,
"grad_norm": 0.0544971264898777,
"learning_rate": 8.699770702464848e-05,
"loss": 0.76904296875,
"step": 901
},
{
"epoch": 3.5652173913043477,
"grad_norm": 0.0540071502327919,
"learning_rate": 8.670975183992358e-05,
"loss": 0.72021484375,
"step": 902
},
{
"epoch": 3.5691699604743086,
"grad_norm": 0.05368657037615776,
"learning_rate": 8.642233235458966e-05,
"loss": 0.70166015625,
"step": 903
},
{
"epoch": 3.5731225296442686,
"grad_norm": 0.05290033668279648,
"learning_rate": 8.61354505353085e-05,
"loss": 0.73876953125,
"step": 904
},
{
"epoch": 3.5770750988142295,
"grad_norm": 0.05497506260871887,
"learning_rate": 8.584910834506305e-05,
"loss": 0.74853515625,
"step": 905
},
{
"epoch": 3.5810276679841895,
"grad_norm": 0.052698586136102676,
"learning_rate": 8.556330774314365e-05,
"loss": 0.70068359375,
"step": 906
},
{
"epoch": 3.5849802371541504,
"grad_norm": 0.05320180207490921,
"learning_rate": 8.527805068513506e-05,
"loss": 0.76220703125,
"step": 907
},
{
"epoch": 3.588932806324111,
"grad_norm": 0.05322538688778877,
"learning_rate": 8.499333912290276e-05,
"loss": 0.76220703125,
"step": 908
},
{
"epoch": 3.5928853754940713,
"grad_norm": 0.054569076746702194,
"learning_rate": 8.470917500457961e-05,
"loss": 0.75,
"step": 909
},
{
"epoch": 3.5968379446640317,
"grad_norm": 0.05753767862915993,
"learning_rate": 8.442556027455268e-05,
"loss": 0.76806640625,
"step": 910
},
{
"epoch": 3.600790513833992,
"grad_norm": 0.051646698266267776,
"learning_rate": 8.414249687344992e-05,
"loss": 0.74462890625,
"step": 911
},
{
"epoch": 3.6047430830039526,
"grad_norm": 0.0552995391190052,
"learning_rate": 8.38599867381267e-05,
"loss": 0.75927734375,
"step": 912
},
{
"epoch": 3.608695652173913,
"grad_norm": 0.058130476623773575,
"learning_rate": 8.357803180165275e-05,
"loss": 0.7509765625,
"step": 913
},
{
"epoch": 3.6126482213438735,
"grad_norm": 0.053999271243810654,
"learning_rate": 8.329663399329877e-05,
"loss": 0.7294921875,
"step": 914
},
{
"epoch": 3.616600790513834,
"grad_norm": 0.053738072514534,
"learning_rate": 8.301579523852347e-05,
"loss": 0.78857421875,
"step": 915
},
{
"epoch": 3.6205533596837944,
"grad_norm": 0.0562644898891449,
"learning_rate": 8.273551745896015e-05,
"loss": 0.76904296875,
"step": 916
},
{
"epoch": 3.624505928853755,
"grad_norm": 0.05426559969782829,
"learning_rate": 8.245580257240369e-05,
"loss": 0.720703125,
"step": 917
},
{
"epoch": 3.6284584980237153,
"grad_norm": 0.05383181944489479,
"learning_rate": 8.21766524927974e-05,
"loss": 0.75146484375,
"step": 918
},
{
"epoch": 3.632411067193676,
"grad_norm": 0.056170038878917694,
"learning_rate": 8.189806913021987e-05,
"loss": 0.76416015625,
"step": 919
},
{
"epoch": 3.6363636363636362,
"grad_norm": 0.05566052719950676,
"learning_rate": 8.162005439087185e-05,
"loss": 0.73828125,
"step": 920
},
{
"epoch": 3.6403162055335967,
"grad_norm": 0.05887375771999359,
"learning_rate": 8.134261017706348e-05,
"loss": 0.7783203125,
"step": 921
},
{
"epoch": 3.6442687747035576,
"grad_norm": 0.05650169029831886,
"learning_rate": 8.106573838720103e-05,
"loss": 0.728515625,
"step": 922
},
{
"epoch": 3.6482213438735176,
"grad_norm": 0.05518361181020737,
"learning_rate": 8.078944091577395e-05,
"loss": 0.75830078125,
"step": 923
},
{
"epoch": 3.6521739130434785,
"grad_norm": 0.0547516793012619,
"learning_rate": 8.051371965334184e-05,
"loss": 0.7158203125,
"step": 924
},
{
"epoch": 3.6561264822134385,
"grad_norm": 0.05537589639425278,
"learning_rate": 8.023857648652181e-05,
"loss": 0.7109375,
"step": 925
},
{
"epoch": 3.6600790513833994,
"grad_norm": 0.05405193194746971,
"learning_rate": 7.996401329797516e-05,
"loss": 0.7470703125,
"step": 926
},
{
"epoch": 3.66403162055336,
"grad_norm": 0.056710172444581985,
"learning_rate": 7.969003196639477e-05,
"loss": 0.75927734375,
"step": 927
},
{
"epoch": 3.6679841897233203,
"grad_norm": 0.055127404630184174,
"learning_rate": 7.941663436649229e-05,
"loss": 0.696044921875,
"step": 928
},
{
"epoch": 3.6719367588932808,
"grad_norm": 0.059965454041957855,
"learning_rate": 7.9143822368985e-05,
"loss": 0.798828125,
"step": 929
},
{
"epoch": 3.675889328063241,
"grad_norm": 0.05501282587647438,
"learning_rate": 7.887159784058335e-05,
"loss": 0.7431640625,
"step": 930
},
{
"epoch": 3.6798418972332017,
"grad_norm": 0.051082588732242584,
"learning_rate": 7.859996264397804e-05,
"loss": 0.70654296875,
"step": 931
},
{
"epoch": 3.683794466403162,
"grad_norm": 0.05296861380338669,
"learning_rate": 7.832891863782712e-05,
"loss": 0.7841796875,
"step": 932
},
{
"epoch": 3.6877470355731226,
"grad_norm": 0.05670865997672081,
"learning_rate": 7.80584676767437e-05,
"loss": 0.76318359375,
"step": 933
},
{
"epoch": 3.691699604743083,
"grad_norm": 0.054566651582717896,
"learning_rate": 7.77886116112827e-05,
"loss": 0.7314453125,
"step": 934
},
{
"epoch": 3.6956521739130435,
"grad_norm": 0.052188850939273834,
"learning_rate": 7.75193522879287e-05,
"loss": 0.71142578125,
"step": 935
},
{
"epoch": 3.699604743083004,
"grad_norm": 0.05537329986691475,
"learning_rate": 7.725069154908301e-05,
"loss": 0.72412109375,
"step": 936
},
{
"epoch": 3.7035573122529644,
"grad_norm": 0.05591835081577301,
"learning_rate": 7.698263123305116e-05,
"loss": 0.76318359375,
"step": 937
},
{
"epoch": 3.707509881422925,
"grad_norm": 0.055910952389240265,
"learning_rate": 7.671517317403022e-05,
"loss": 0.73095703125,
"step": 938
},
{
"epoch": 3.7114624505928853,
"grad_norm": 0.05722372606396675,
"learning_rate": 7.644831920209638e-05,
"loss": 0.72314453125,
"step": 939
},
{
"epoch": 3.7154150197628457,
"grad_norm": 0.05704692378640175,
"learning_rate": 7.618207114319238e-05,
"loss": 0.71826171875,
"step": 940
},
{
"epoch": 3.719367588932806,
"grad_norm": 0.057204436510801315,
"learning_rate": 7.591643081911505e-05,
"loss": 0.75634765625,
"step": 941
},
{
"epoch": 3.7233201581027666,
"grad_norm": 0.05155207961797714,
"learning_rate": 7.565140004750272e-05,
"loss": 0.73486328125,
"step": 942
},
{
"epoch": 3.7272727272727275,
"grad_norm": 0.04798625782132149,
"learning_rate": 7.538698064182303e-05,
"loss": 0.6318359375,
"step": 943
},
{
"epoch": 3.7312252964426875,
"grad_norm": 0.0545424185693264,
"learning_rate": 7.512317441136017e-05,
"loss": 0.7431640625,
"step": 944
},
{
"epoch": 3.7351778656126484,
"grad_norm": 0.05616064742207527,
"learning_rate": 7.485998316120273e-05,
"loss": 0.787109375,
"step": 945
},
{
"epoch": 3.7391304347826084,
"grad_norm": 0.05260308086872101,
"learning_rate": 7.459740869223139e-05,
"loss": 0.69580078125,
"step": 946
},
{
"epoch": 3.7430830039525693,
"grad_norm": 0.053783025592565536,
"learning_rate": 7.433545280110649e-05,
"loss": 0.70556640625,
"step": 947
},
{
"epoch": 3.7470355731225298,
"grad_norm": 0.05571635439991951,
"learning_rate": 7.40741172802558e-05,
"loss": 0.76025390625,
"step": 948
},
{
"epoch": 3.7509881422924902,
"grad_norm": 0.05421881005167961,
"learning_rate": 7.381340391786208e-05,
"loss": 0.771484375,
"step": 949
},
{
"epoch": 3.7549407114624507,
"grad_norm": 0.05487171560525894,
"learning_rate": 7.355331449785117e-05,
"loss": 0.783203125,
"step": 950
},
{
"epoch": 3.758893280632411,
"grad_norm": 0.0544293187558651,
"learning_rate": 7.329385079987942e-05,
"loss": 0.6055908203125,
"step": 951
},
{
"epoch": 3.7628458498023716,
"grad_norm": 0.05523071065545082,
"learning_rate": 7.303501459932179e-05,
"loss": 0.72216796875,
"step": 952
},
{
"epoch": 3.766798418972332,
"grad_norm": 0.05477157235145569,
"learning_rate": 7.277680766725963e-05,
"loss": 0.7587890625,
"step": 953
},
{
"epoch": 3.7707509881422925,
"grad_norm": 0.056483328342437744,
"learning_rate": 7.251923177046851e-05,
"loss": 0.664306640625,
"step": 954
},
{
"epoch": 3.774703557312253,
"grad_norm": 0.053752899169921875,
"learning_rate": 7.226228867140604e-05,
"loss": 0.74609375,
"step": 955
},
{
"epoch": 3.7786561264822134,
"grad_norm": 0.052997808903455734,
"learning_rate": 7.200598012820008e-05,
"loss": 0.74853515625,
"step": 956
},
{
"epoch": 3.782608695652174,
"grad_norm": 0.05428636074066162,
"learning_rate": 7.175030789463653e-05,
"loss": 0.71240234375,
"step": 957
},
{
"epoch": 3.7865612648221343,
"grad_norm": 0.05559973791241646,
"learning_rate": 7.149527372014723e-05,
"loss": 0.69873046875,
"step": 958
},
{
"epoch": 3.7905138339920947,
"grad_norm": 0.05483286455273628,
"learning_rate": 7.124087934979827e-05,
"loss": 0.71630859375,
"step": 959
},
{
"epoch": 3.794466403162055,
"grad_norm": 0.05329837277531624,
"learning_rate": 7.098712652427779e-05,
"loss": 0.7412109375,
"step": 960
},
{
"epoch": 3.7984189723320156,
"grad_norm": 0.05392313748598099,
"learning_rate": 7.07340169798842e-05,
"loss": 0.724609375,
"step": 961
},
{
"epoch": 3.8023715415019765,
"grad_norm": 0.054372984915971756,
"learning_rate": 7.048155244851431e-05,
"loss": 0.73486328125,
"step": 962
},
{
"epoch": 3.8063241106719365,
"grad_norm": 0.053075000643730164,
"learning_rate": 7.022973465765144e-05,
"loss": 0.802734375,
"step": 963
},
{
"epoch": 3.8102766798418974,
"grad_norm": 0.051393721252679825,
"learning_rate": 6.997856533035355e-05,
"loss": 0.76416015625,
"step": 964
},
{
"epoch": 3.8142292490118574,
"grad_norm": 0.05451299250125885,
"learning_rate": 6.972804618524148e-05,
"loss": 0.73828125,
"step": 965
},
{
"epoch": 3.8181818181818183,
"grad_norm": 0.05435147508978844,
"learning_rate": 6.947817893648728e-05,
"loss": 0.70703125,
"step": 966
},
{
"epoch": 3.822134387351779,
"grad_norm": 0.054048508405685425,
"learning_rate": 6.92289652938024e-05,
"loss": 0.72998046875,
"step": 967
},
{
"epoch": 3.8260869565217392,
"grad_norm": 0.053173504769802094,
"learning_rate": 6.8980406962426e-05,
"loss": 0.7275390625,
"step": 968
},
{
"epoch": 3.8300395256916997,
"grad_norm": 0.0538102425634861,
"learning_rate": 6.873250564311334e-05,
"loss": 0.75244140625,
"step": 969
},
{
"epoch": 3.83399209486166,
"grad_norm": 0.05333505943417549,
"learning_rate": 6.848526303212395e-05,
"loss": 0.7763671875,
"step": 970
},
{
"epoch": 3.8379446640316206,
"grad_norm": 0.05360402539372444,
"learning_rate": 6.823868082121022e-05,
"loss": 0.71533203125,
"step": 971
},
{
"epoch": 3.841897233201581,
"grad_norm": 0.053121209144592285,
"learning_rate": 6.799276069760584e-05,
"loss": 0.71240234375,
"step": 972
},
{
"epoch": 3.8458498023715415,
"grad_norm": 0.05314965918660164,
"learning_rate": 6.77475043440141e-05,
"loss": 0.74951171875,
"step": 973
},
{
"epoch": 3.849802371541502,
"grad_norm": 0.05307522788643837,
"learning_rate": 6.750291343859656e-05,
"loss": 0.7060546875,
"step": 974
},
{
"epoch": 3.8537549407114624,
"grad_norm": 0.05269191041588783,
"learning_rate": 6.725898965496129e-05,
"loss": 0.74169921875,
"step": 975
},
{
"epoch": 3.857707509881423,
"grad_norm": 0.05536837875843048,
"learning_rate": 6.701573466215177e-05,
"loss": 0.7666015625,
"step": 976
},
{
"epoch": 3.8616600790513833,
"grad_norm": 0.05472695827484131,
"learning_rate": 6.677315012463515e-05,
"loss": 0.77587890625,
"step": 977
},
{
"epoch": 3.8656126482213438,
"grad_norm": 0.056150708347558975,
"learning_rate": 6.653123770229114e-05,
"loss": 0.7509765625,
"step": 978
},
{
"epoch": 3.869565217391304,
"grad_norm": 0.054174479097127914,
"learning_rate": 6.628999905040043e-05,
"loss": 0.763671875,
"step": 979
},
{
"epoch": 3.8735177865612647,
"grad_norm": 0.05432188883423805,
"learning_rate": 6.604943581963341e-05,
"loss": 0.77685546875,
"step": 980
},
{
"epoch": 3.8774703557312256,
"grad_norm": 0.0533493347465992,
"learning_rate": 6.580954965603902e-05,
"loss": 0.7880859375,
"step": 981
},
{
"epoch": 3.8814229249011856,
"grad_norm": 0.05559117719531059,
"learning_rate": 6.557034220103336e-05,
"loss": 0.69580078125,
"step": 982
},
{
"epoch": 3.8853754940711465,
"grad_norm": 0.05539815127849579,
"learning_rate": 6.533181509138837e-05,
"loss": 0.708984375,
"step": 983
},
{
"epoch": 3.8893280632411065,
"grad_norm": 0.05573389679193497,
"learning_rate": 6.509396995922094e-05,
"loss": 0.748046875,
"step": 984
},
{
"epoch": 3.8932806324110674,
"grad_norm": 0.05240863934159279,
"learning_rate": 6.485680843198133e-05,
"loss": 0.697265625,
"step": 985
},
{
"epoch": 3.897233201581028,
"grad_norm": 0.05378623679280281,
"learning_rate": 6.462033213244237e-05,
"loss": 0.7412109375,
"step": 986
},
{
"epoch": 3.9011857707509883,
"grad_norm": 0.05812434107065201,
"learning_rate": 6.438454267868821e-05,
"loss": 0.703125,
"step": 987
},
{
"epoch": 3.9051383399209487,
"grad_norm": 0.05458831042051315,
"learning_rate": 6.414944168410334e-05,
"loss": 0.71875,
"step": 988
},
{
"epoch": 3.909090909090909,
"grad_norm": 0.05372072011232376,
"learning_rate": 6.391503075736134e-05,
"loss": 0.77294921875,
"step": 989
},
{
"epoch": 3.9130434782608696,
"grad_norm": 0.05204453691840172,
"learning_rate": 6.368131150241408e-05,
"loss": 0.7333984375,
"step": 990
},
{
"epoch": 3.91699604743083,
"grad_norm": 0.0560961477458477,
"learning_rate": 6.344828551848072e-05,
"loss": 0.76953125,
"step": 991
},
{
"epoch": 3.9209486166007905,
"grad_norm": 0.05361437052488327,
"learning_rate": 6.321595440003669e-05,
"loss": 0.755859375,
"step": 992
},
{
"epoch": 3.924901185770751,
"grad_norm": 0.05396462604403496,
"learning_rate": 6.298431973680281e-05,
"loss": 0.732421875,
"step": 993
},
{
"epoch": 3.9288537549407114,
"grad_norm": 0.053852856159210205,
"learning_rate": 6.275338311373452e-05,
"loss": 0.7041015625,
"step": 994
},
{
"epoch": 3.932806324110672,
"grad_norm": 0.05076231434941292,
"learning_rate": 6.252314611101077e-05,
"loss": 0.6410064697265625,
"step": 995
},
{
"epoch": 3.9367588932806323,
"grad_norm": 0.05324838310480118,
"learning_rate": 6.229361030402342e-05,
"loss": 0.7490234375,
"step": 996
},
{
"epoch": 3.940711462450593,
"grad_norm": 0.05387488380074501,
"learning_rate": 6.20647772633665e-05,
"loss": 0.76171875,
"step": 997
},
{
"epoch": 3.9446640316205532,
"grad_norm": 0.052048832178115845,
"learning_rate": 6.183664855482529e-05,
"loss": 0.72119140625,
"step": 998
},
{
"epoch": 3.9486166007905137,
"grad_norm": 0.05562395229935646,
"learning_rate": 6.16092257393658e-05,
"loss": 0.73583984375,
"step": 999
},
{
"epoch": 3.9525691699604746,
"grad_norm": 0.05489029362797737,
"learning_rate": 6.138251037312378e-05,
"loss": 0.71435546875,
"step": 1000
},
{
"epoch": 3.9565217391304346,
"grad_norm": 0.054414838552474976,
"learning_rate": 6.115650400739452e-05,
"loss": 0.77783203125,
"step": 1001
},
{
"epoch": 3.9604743083003955,
"grad_norm": 0.05501807853579521,
"learning_rate": 6.0931208188621775e-05,
"loss": 0.73486328125,
"step": 1002
},
{
"epoch": 3.9644268774703555,
"grad_norm": 0.05498626083135605,
"learning_rate": 6.070662445838751e-05,
"loss": 0.74560546875,
"step": 1003
},
{
"epoch": 3.9683794466403164,
"grad_norm": 0.1845346838235855,
"learning_rate": 6.048275435340127e-05,
"loss": 0.6566162109375,
"step": 1004
},
{
"epoch": 3.972332015810277,
"grad_norm": 0.05547404661774635,
"learning_rate": 6.025959940548949e-05,
"loss": 0.75048828125,
"step": 1005
},
{
"epoch": 3.9762845849802373,
"grad_norm": 0.05626276880502701,
"learning_rate": 6.003716114158531e-05,
"loss": 0.70654296875,
"step": 1006
},
{
"epoch": 3.9802371541501977,
"grad_norm": 0.053916070610284805,
"learning_rate": 5.98154410837179e-05,
"loss": 0.73388671875,
"step": 1007
},
{
"epoch": 3.984189723320158,
"grad_norm": 0.0541171133518219,
"learning_rate": 5.959444074900218e-05,
"loss": 0.75439453125,
"step": 1008
},
{
"epoch": 3.9881422924901186,
"grad_norm": 0.049360692501068115,
"learning_rate": 5.937416164962826e-05,
"loss": 0.6370849609375,
"step": 1009
},
{
"epoch": 3.992094861660079,
"grad_norm": 0.05568039417266846,
"learning_rate": 5.915460529285134e-05,
"loss": 0.7685546875,
"step": 1010
},
{
"epoch": 3.9960474308300395,
"grad_norm": 0.0535382516682148,
"learning_rate": 5.893577318098116e-05,
"loss": 0.691650390625,
"step": 1011
},
{
"epoch": 4.0,
"grad_norm": 0.07047536969184875,
"learning_rate": 5.8717666811371893e-05,
"loss": 0.6865234375,
"step": 1012
},
{
"epoch": 4.0,
"eval_loss": 0.82861328125,
"eval_runtime": 2.2041,
"eval_samples_per_second": 2.722,
"eval_steps_per_second": 0.454,
"step": 1012
},
{
"epoch": 4.003952569169961,
"grad_norm": 0.06031075865030289,
"learning_rate": 5.850028767641185e-05,
"loss": 0.69384765625,
"step": 1013
},
{
"epoch": 4.007905138339921,
"grad_norm": 0.06110788509249687,
"learning_rate": 5.8283637263513285e-05,
"loss": 0.7333984375,
"step": 1014
},
{
"epoch": 4.011857707509882,
"grad_norm": 0.06551854312419891,
"learning_rate": 5.8067717055102054e-05,
"loss": 0.75732421875,
"step": 1015
},
{
"epoch": 4.015810276679842,
"grad_norm": 0.06766308099031448,
"learning_rate": 5.785252852860766e-05,
"loss": 0.751953125,
"step": 1016
},
{
"epoch": 4.019762845849803,
"grad_norm": 0.06225856393575668,
"learning_rate": 5.763807315645317e-05,
"loss": 0.7568359375,
"step": 1017
},
{
"epoch": 4.023715415019763,
"grad_norm": 0.05833744257688522,
"learning_rate": 5.742435240604497e-05,
"loss": 0.76611328125,
"step": 1018
},
{
"epoch": 4.027667984189724,
"grad_norm": 0.06074969843029976,
"learning_rate": 5.7211367739762854e-05,
"loss": 0.71484375,
"step": 1019
},
{
"epoch": 4.031620553359684,
"grad_norm": 0.06087961420416832,
"learning_rate": 5.699912061494998e-05,
"loss": 0.783203125,
"step": 1020
},
{
"epoch": 4.0355731225296445,
"grad_norm": 0.05966727435588837,
"learning_rate": 5.678761248390286e-05,
"loss": 0.72216796875,
"step": 1021
},
{
"epoch": 4.0395256916996045,
"grad_norm": 0.059027113020420074,
"learning_rate": 5.657684479386141e-05,
"loss": 0.76123046875,
"step": 1022
},
{
"epoch": 4.043478260869565,
"grad_norm": 0.062165651470422745,
"learning_rate": 5.6366818986999205e-05,
"loss": 0.748046875,
"step": 1023
},
{
"epoch": 4.047430830039525,
"grad_norm": 7.732985019683838,
"learning_rate": 5.615753650041346e-05,
"loss": 0.96875,
"step": 1024
},
{
"epoch": 4.051383399209486,
"grad_norm": 0.06478087604045868,
"learning_rate": 5.594899876611526e-05,
"loss": 0.74072265625,
"step": 1025
},
{
"epoch": 4.055335968379446,
"grad_norm": 0.057147298008203506,
"learning_rate": 5.574120721101963e-05,
"loss": 0.703521728515625,
"step": 1026
},
{
"epoch": 4.059288537549407,
"grad_norm": 0.05950389802455902,
"learning_rate": 5.553416325693602e-05,
"loss": 0.7529296875,
"step": 1027
},
{
"epoch": 4.063241106719367,
"grad_norm": 0.06623628735542297,
"learning_rate": 5.5327868320558286e-05,
"loss": 0.73486328125,
"step": 1028
},
{
"epoch": 4.067193675889328,
"grad_norm": 0.05642949417233467,
"learning_rate": 5.5122323813455296e-05,
"loss": 0.700927734375,
"step": 1029
},
{
"epoch": 4.071146245059288,
"grad_norm": 0.05788682773709297,
"learning_rate": 5.491753114206106e-05,
"loss": 0.71630859375,
"step": 1030
},
{
"epoch": 4.075098814229249,
"grad_norm": 0.05707879737019539,
"learning_rate": 5.471349170766511e-05,
"loss": 0.78173828125,
"step": 1031
},
{
"epoch": 4.07905138339921,
"grad_norm": 0.05501970276236534,
"learning_rate": 5.451020690640307e-05,
"loss": 0.73486328125,
"step": 1032
},
{
"epoch": 4.08300395256917,
"grad_norm": 0.054872021079063416,
"learning_rate": 5.430767812924694e-05,
"loss": 0.75244140625,
"step": 1033
},
{
"epoch": 4.086956521739131,
"grad_norm": 0.05542471259832382,
"learning_rate": 5.4105906761995653e-05,
"loss": 0.755859375,
"step": 1034
},
{
"epoch": 4.090909090909091,
"grad_norm": 0.054993074387311935,
"learning_rate": 5.39048941852656e-05,
"loss": 0.681884765625,
"step": 1035
},
{
"epoch": 4.094861660079052,
"grad_norm": 0.05428818240761757,
"learning_rate": 5.370464177448109e-05,
"loss": 0.74853515625,
"step": 1036
},
{
"epoch": 4.098814229249012,
"grad_norm": 0.09079686552286148,
"learning_rate": 5.350515089986514e-05,
"loss": 0.69287109375,
"step": 1037
},
{
"epoch": 4.102766798418973,
"grad_norm": 0.05702628195285797,
"learning_rate": 5.3306422926429854e-05,
"loss": 0.69287109375,
"step": 1038
},
{
"epoch": 4.106719367588933,
"grad_norm": 0.0552668459713459,
"learning_rate": 5.3108459213967295e-05,
"loss": 0.73193359375,
"step": 1039
},
{
"epoch": 4.1106719367588935,
"grad_norm": 0.055145759135484695,
"learning_rate": 5.2911261117040014e-05,
"loss": 0.724609375,
"step": 1040
},
{
"epoch": 4.1146245059288535,
"grad_norm": 0.05150497332215309,
"learning_rate": 5.271482998497184e-05,
"loss": 0.65087890625,
"step": 1041
},
{
"epoch": 4.118577075098814,
"grad_norm": 0.053702473640441895,
"learning_rate": 5.251916716183872e-05,
"loss": 0.740234375,
"step": 1042
},
{
"epoch": 4.122529644268774,
"grad_norm": 0.05422266200184822,
"learning_rate": 5.232427398645947e-05,
"loss": 0.7646484375,
"step": 1043
},
{
"epoch": 4.126482213438735,
"grad_norm": 0.053399842232465744,
"learning_rate": 5.2130151792386566e-05,
"loss": 0.6953125,
"step": 1044
},
{
"epoch": 4.130434782608695,
"grad_norm": 0.05270052328705788,
"learning_rate": 5.1936801907897106e-05,
"loss": 0.67529296875,
"step": 1045
},
{
"epoch": 4.134387351778656,
"grad_norm": 0.05339214578270912,
"learning_rate": 5.17442256559836e-05,
"loss": 0.74853515625,
"step": 1046
},
{
"epoch": 4.138339920948616,
"grad_norm": 0.05379122123122215,
"learning_rate": 5.155242435434502e-05,
"loss": 0.7431640625,
"step": 1047
},
{
"epoch": 4.142292490118577,
"grad_norm": 0.054417215287685394,
"learning_rate": 5.1361399315377786e-05,
"loss": 0.75439453125,
"step": 1048
},
{
"epoch": 4.146245059288537,
"grad_norm": 0.05603625997900963,
"learning_rate": 5.1171151846166786e-05,
"loss": 0.7255859375,
"step": 1049
},
{
"epoch": 4.150197628458498,
"grad_norm": 0.05460800230503082,
"learning_rate": 5.0981683248476356e-05,
"loss": 0.7509765625,
"step": 1050
},
{
"epoch": 4.154150197628459,
"grad_norm": 0.05409042164683342,
"learning_rate": 5.079299481874138e-05,
"loss": 0.7265625,
"step": 1051
},
{
"epoch": 4.158102766798419,
"grad_norm": 0.05564555525779724,
"learning_rate": 5.060508784805851e-05,
"loss": 0.7421875,
"step": 1052
},
{
"epoch": 4.16205533596838,
"grad_norm": 0.05496601015329361,
"learning_rate": 5.041796362217736e-05,
"loss": 0.68115234375,
"step": 1053
},
{
"epoch": 4.16600790513834,
"grad_norm": 0.0534840002655983,
"learning_rate": 5.0231623421491426e-05,
"loss": 0.7099609375,
"step": 1054
},
{
"epoch": 4.169960474308301,
"grad_norm": 0.055106133222579956,
"learning_rate": 5.0046068521029753e-05,
"loss": 0.703369140625,
"step": 1055
},
{
"epoch": 4.173913043478261,
"grad_norm": 0.053178250789642334,
"learning_rate": 4.986130019044779e-05,
"loss": 0.6962890625,
"step": 1056
},
{
"epoch": 4.177865612648222,
"grad_norm": 0.05478484183549881,
"learning_rate": 4.9677319694019025e-05,
"loss": 0.73046875,
"step": 1057
},
{
"epoch": 4.181818181818182,
"grad_norm": 0.05557248741388321,
"learning_rate": 4.9494128290626173e-05,
"loss": 0.71435546875,
"step": 1058
},
{
"epoch": 4.1857707509881426,
"grad_norm": 0.05151933804154396,
"learning_rate": 4.931172723375262e-05,
"loss": 0.5699462890625,
"step": 1059
},
{
"epoch": 4.189723320158103,
"grad_norm": 0.05619212985038757,
"learning_rate": 4.913011777147375e-05,
"loss": 0.7509765625,
"step": 1060
},
{
"epoch": 4.1936758893280635,
"grad_norm": 0.05416307598352432,
"learning_rate": 4.894930114644853e-05,
"loss": 0.7080078125,
"step": 1061
},
{
"epoch": 4.1976284584980235,
"grad_norm": 0.054548755288124084,
"learning_rate": 4.8769278595910935e-05,
"loss": 0.72705078125,
"step": 1062
},
{
"epoch": 4.201581027667984,
"grad_norm": 0.055503588169813156,
"learning_rate": 4.859005135166156e-05,
"loss": 0.75,
"step": 1063
},
{
"epoch": 4.205533596837944,
"grad_norm": 0.05263538658618927,
"learning_rate": 4.841162064005903e-05,
"loss": 0.64453125,
"step": 1064
},
{
"epoch": 4.209486166007905,
"grad_norm": 0.05432296544313431,
"learning_rate": 4.823398768201185e-05,
"loss": 0.7412109375,
"step": 1065
},
{
"epoch": 4.213438735177865,
"grad_norm": 0.05512768030166626,
"learning_rate": 4.805715369296978e-05,
"loss": 0.73291015625,
"step": 1066
},
{
"epoch": 4.217391304347826,
"grad_norm": 0.05556974187493324,
"learning_rate": 4.7881119882915685e-05,
"loss": 0.75,
"step": 1067
},
{
"epoch": 4.221343873517786,
"grad_norm": 0.055198121815919876,
"learning_rate": 4.770588745635727e-05,
"loss": 0.69140625,
"step": 1068
},
{
"epoch": 4.225296442687747,
"grad_norm": 0.0551803782582283,
"learning_rate": 4.7531457612318735e-05,
"loss": 0.646484375,
"step": 1069
},
{
"epoch": 4.229249011857707,
"grad_norm": 0.05492149665951729,
"learning_rate": 4.735783154433267e-05,
"loss": 0.7275390625,
"step": 1070
},
{
"epoch": 4.233201581027668,
"grad_norm": 0.05539706349372864,
"learning_rate": 4.718501044043188e-05,
"loss": 0.76416015625,
"step": 1071
},
{
"epoch": 4.237154150197629,
"grad_norm": 0.05736236646771431,
"learning_rate": 4.7012995483141086e-05,
"loss": 0.72705078125,
"step": 1072
},
{
"epoch": 4.241106719367589,
"grad_norm": 0.05520552769303322,
"learning_rate": 4.6841787849469055e-05,
"loss": 0.67041015625,
"step": 1073
},
{
"epoch": 4.24505928853755,
"grad_norm": 1.1780487298965454,
"learning_rate": 4.667138871090048e-05,
"loss": 0.6583251953125,
"step": 1074
},
{
"epoch": 4.24901185770751,
"grad_norm": 0.055132906883955,
"learning_rate": 4.650179923338788e-05,
"loss": 0.68017578125,
"step": 1075
},
{
"epoch": 4.252964426877471,
"grad_norm": 0.054544541984796524,
"learning_rate": 4.633302057734379e-05,
"loss": 0.7255859375,
"step": 1076
},
{
"epoch": 4.256916996047431,
"grad_norm": 0.053575873374938965,
"learning_rate": 4.6165053897632576e-05,
"loss": 0.712890625,
"step": 1077
},
{
"epoch": 4.260869565217392,
"grad_norm": 0.05275188758969307,
"learning_rate": 4.599790034356278e-05,
"loss": 0.72509765625,
"step": 1078
},
{
"epoch": 4.264822134387352,
"grad_norm": 0.054403889924287796,
"learning_rate": 4.583156105887906e-05,
"loss": 0.75830078125,
"step": 1079
},
{
"epoch": 4.2687747035573125,
"grad_norm": 0.053071387112140656,
"learning_rate": 4.5666037181754555e-05,
"loss": 0.705078125,
"step": 1080
},
{
"epoch": 4.2727272727272725,
"grad_norm": 0.05347397178411484,
"learning_rate": 4.550132984478295e-05,
"loss": 0.71533203125,
"step": 1081
},
{
"epoch": 4.276679841897233,
"grad_norm": 0.054446324706077576,
"learning_rate": 4.5337440174970715e-05,
"loss": 0.73681640625,
"step": 1082
},
{
"epoch": 4.280632411067193,
"grad_norm": 0.05359195917844772,
"learning_rate": 4.517436929372954e-05,
"loss": 0.69580078125,
"step": 1083
},
{
"epoch": 4.284584980237154,
"grad_norm": 0.052981577813625336,
"learning_rate": 4.501211831686853e-05,
"loss": 0.75732421875,
"step": 1084
},
{
"epoch": 4.288537549407114,
"grad_norm": 0.0531194768846035,
"learning_rate": 4.485068835458658e-05,
"loss": 0.71337890625,
"step": 1085
},
{
"epoch": 4.292490118577075,
"grad_norm": 0.05377298966050148,
"learning_rate": 4.46900805114649e-05,
"loss": 0.75,
"step": 1086
},
{
"epoch": 4.296442687747035,
"grad_norm": 0.05639534816145897,
"learning_rate": 4.453029588645922e-05,
"loss": 0.697265625,
"step": 1087
},
{
"epoch": 4.300395256916996,
"grad_norm": 0.0568559356033802,
"learning_rate": 4.437133557289258e-05,
"loss": 0.73046875,
"step": 1088
},
{
"epoch": 4.304347826086957,
"grad_norm": 0.0537240132689476,
"learning_rate": 4.421320065844757e-05,
"loss": 0.72607421875,
"step": 1089
},
{
"epoch": 4.308300395256917,
"grad_norm": 0.054221879690885544,
"learning_rate": 4.4055892225159095e-05,
"loss": 0.7216796875,
"step": 1090
},
{
"epoch": 4.312252964426877,
"grad_norm": 0.05394740030169487,
"learning_rate": 4.38994113494068e-05,
"loss": 0.72998046875,
"step": 1091
},
{
"epoch": 4.316205533596838,
"grad_norm": 0.056213587522506714,
"learning_rate": 4.374375910190779e-05,
"loss": 0.70654296875,
"step": 1092
},
{
"epoch": 4.320158102766799,
"grad_norm": 0.05380198732018471,
"learning_rate": 4.358893654770935e-05,
"loss": 0.65185546875,
"step": 1093
},
{
"epoch": 4.324110671936759,
"grad_norm": 0.05435040965676308,
"learning_rate": 4.343494474618155e-05,
"loss": 0.7099609375,
"step": 1094
},
{
"epoch": 4.32806324110672,
"grad_norm": 0.05529727041721344,
"learning_rate": 4.3281784751010134e-05,
"loss": 0.76708984375,
"step": 1095
},
{
"epoch": 4.33201581027668,
"grad_norm": 0.05435086786746979,
"learning_rate": 4.3129457610189176e-05,
"loss": 0.701171875,
"step": 1096
},
{
"epoch": 4.335968379446641,
"grad_norm": 0.055761270225048065,
"learning_rate": 4.297796436601394e-05,
"loss": 0.71630859375,
"step": 1097
},
{
"epoch": 4.339920948616601,
"grad_norm": 0.056693367660045624,
"learning_rate": 4.282730605507374e-05,
"loss": 0.73779296875,
"step": 1098
},
{
"epoch": 4.3438735177865615,
"grad_norm": 0.05438676476478577,
"learning_rate": 4.2677483708245e-05,
"loss": 0.705078125,
"step": 1099
},
{
"epoch": 4.3478260869565215,
"grad_norm": 0.053797755390405655,
"learning_rate": 4.2528498350683965e-05,
"loss": 0.6953125,
"step": 1100
},
{
"epoch": 4.351778656126482,
"grad_norm": 0.05658596009016037,
"learning_rate": 4.2380351001819885e-05,
"loss": 0.74365234375,
"step": 1101
},
{
"epoch": 4.355731225296442,
"grad_norm": 0.060522112995386124,
"learning_rate": 4.223304267534785e-05,
"loss": 0.6790771484375,
"step": 1102
},
{
"epoch": 4.359683794466403,
"grad_norm": 0.05506613105535507,
"learning_rate": 4.208657437922204e-05,
"loss": 0.71142578125,
"step": 1103
},
{
"epoch": 4.363636363636363,
"grad_norm": 0.05358298122882843,
"learning_rate": 4.1940947115648734e-05,
"loss": 0.71630859375,
"step": 1104
},
{
"epoch": 4.367588932806324,
"grad_norm": 0.05336678400635719,
"learning_rate": 4.179616188107941e-05,
"loss": 0.70556640625,
"step": 1105
},
{
"epoch": 4.371541501976284,
"grad_norm": 0.05330111086368561,
"learning_rate": 4.165221966620406e-05,
"loss": 0.6904296875,
"step": 1106
},
{
"epoch": 4.375494071146245,
"grad_norm": 0.056206557899713516,
"learning_rate": 4.150912145594423e-05,
"loss": 0.74560546875,
"step": 1107
},
{
"epoch": 4.379446640316205,
"grad_norm": 0.058410242199897766,
"learning_rate": 4.136686822944649e-05,
"loss": 0.758056640625,
"step": 1108
},
{
"epoch": 4.383399209486166,
"grad_norm": 0.050166577100753784,
"learning_rate": 4.1225460960075556e-05,
"loss": 0.618072509765625,
"step": 1109
},
{
"epoch": 4.387351778656127,
"grad_norm": 0.0549464225769043,
"learning_rate": 4.1084900615407746e-05,
"loss": 0.73681640625,
"step": 1110
},
{
"epoch": 4.391304347826087,
"grad_norm": 0.054804883897304535,
"learning_rate": 4.094518815722427e-05,
"loss": 0.71630859375,
"step": 1111
},
{
"epoch": 4.395256916996048,
"grad_norm": 0.05403197556734085,
"learning_rate": 4.08063245415047e-05,
"loss": 0.7353515625,
"step": 1112
},
{
"epoch": 4.399209486166008,
"grad_norm": 0.052911508828401566,
"learning_rate": 4.0668310718420426e-05,
"loss": 0.7021484375,
"step": 1113
},
{
"epoch": 4.403162055335969,
"grad_norm": 0.0533103421330452,
"learning_rate": 4.053114763232818e-05,
"loss": 0.712890625,
"step": 1114
},
{
"epoch": 4.407114624505929,
"grad_norm": 0.05533958226442337,
"learning_rate": 4.039483622176351e-05,
"loss": 0.73095703125,
"step": 1115
},
{
"epoch": 4.41106719367589,
"grad_norm": 0.054855141788721085,
"learning_rate": 4.0259377419434425e-05,
"loss": 0.671875,
"step": 1116
},
{
"epoch": 4.41501976284585,
"grad_norm": 0.05641382187604904,
"learning_rate": 4.012477215221493e-05,
"loss": 0.6728515625,
"step": 1117
},
{
"epoch": 4.4189723320158105,
"grad_norm": 0.05477788299322128,
"learning_rate": 3.9991021341138726e-05,
"loss": 0.712890625,
"step": 1118
},
{
"epoch": 4.4229249011857705,
"grad_norm": 0.05365835875272751,
"learning_rate": 3.9858125901393e-05,
"loss": 0.7119140625,
"step": 1119
},
{
"epoch": 4.426877470355731,
"grad_norm": 0.05367009714245796,
"learning_rate": 3.972608674231201e-05,
"loss": 0.71923828125,
"step": 1120
},
{
"epoch": 4.430830039525691,
"grad_norm": 0.05536982789635658,
"learning_rate": 3.959490476737098e-05,
"loss": 0.701171875,
"step": 1121
},
{
"epoch": 4.434782608695652,
"grad_norm": 0.05440201237797737,
"learning_rate": 3.946458087417979e-05,
"loss": 0.6845703125,
"step": 1122
},
{
"epoch": 4.438735177865612,
"grad_norm": 0.05495268106460571,
"learning_rate": 3.9335115954477e-05,
"loss": 0.70703125,
"step": 1123
},
{
"epoch": 4.442687747035573,
"grad_norm": 0.054702214896678925,
"learning_rate": 3.9206510894123594e-05,
"loss": 0.73046875,
"step": 1124
},
{
"epoch": 4.446640316205533,
"grad_norm": 0.054403141140937805,
"learning_rate": 3.907876657309703e-05,
"loss": 0.68701171875,
"step": 1125
},
{
"epoch": 4.450592885375494,
"grad_norm": 0.05774274840950966,
"learning_rate": 3.8951883865485156e-05,
"loss": 0.723388671875,
"step": 1126
},
{
"epoch": 4.454545454545454,
"grad_norm": 0.056211017072200775,
"learning_rate": 3.882586363948027e-05,
"loss": 0.76171875,
"step": 1127
},
{
"epoch": 4.458498023715415,
"grad_norm": 0.05575614422559738,
"learning_rate": 3.870070675737313e-05,
"loss": 0.69580078125,
"step": 1128
},
{
"epoch": 4.462450592885375,
"grad_norm": 0.057191088795661926,
"learning_rate": 3.857641407554711e-05,
"loss": 0.744140625,
"step": 1129
},
{
"epoch": 4.466403162055336,
"grad_norm": 0.06048453971743584,
"learning_rate": 3.8452986444472266e-05,
"loss": 0.658203125,
"step": 1130
},
{
"epoch": 4.470355731225297,
"grad_norm": 0.04927687719464302,
"learning_rate": 3.8330424708699606e-05,
"loss": 0.5936279296875,
"step": 1131
},
{
"epoch": 4.474308300395257,
"grad_norm": 0.056541845202445984,
"learning_rate": 3.820872970685526e-05,
"loss": 0.736328125,
"step": 1132
},
{
"epoch": 4.478260869565218,
"grad_norm": 0.05535850673913956,
"learning_rate": 3.808790227163471e-05,
"loss": 0.75341796875,
"step": 1133
},
{
"epoch": 4.482213438735178,
"grad_norm": 0.05761480703949928,
"learning_rate": 3.796794322979717e-05,
"loss": 0.73095703125,
"step": 1134
},
{
"epoch": 4.486166007905139,
"grad_norm": 0.05654006078839302,
"learning_rate": 3.784885340215994e-05,
"loss": 0.6884765625,
"step": 1135
},
{
"epoch": 4.490118577075099,
"grad_norm": 0.05465972423553467,
"learning_rate": 3.7730633603592606e-05,
"loss": 0.6923828125,
"step": 1136
},
{
"epoch": 4.4940711462450595,
"grad_norm": 0.05400924012064934,
"learning_rate": 3.761328464301173e-05,
"loss": 0.72900390625,
"step": 1137
},
{
"epoch": 4.4980237154150196,
"grad_norm": 0.05557999014854431,
"learning_rate": 3.749680732337509e-05,
"loss": 0.7275390625,
"step": 1138
},
{
"epoch": 4.5019762845849804,
"grad_norm": 0.056743323802948,
"learning_rate": 3.7381202441676344e-05,
"loss": 0.71923828125,
"step": 1139
},
{
"epoch": 4.5059288537549405,
"grad_norm": 0.05441879481077194,
"learning_rate": 3.726647078893946e-05,
"loss": 0.7119140625,
"step": 1140
},
{
"epoch": 4.509881422924901,
"grad_norm": 0.05461134389042854,
"learning_rate": 3.715261315021343e-05,
"loss": 0.68310546875,
"step": 1141
},
{
"epoch": 4.513833992094861,
"grad_norm": 0.05546554550528526,
"learning_rate": 3.703963030456673e-05,
"loss": 0.70166015625,
"step": 1142
},
{
"epoch": 4.517786561264822,
"grad_norm": 0.05584446340799332,
"learning_rate": 3.692752302508211e-05,
"loss": 0.6552734375,
"step": 1143
},
{
"epoch": 4.521739130434782,
"grad_norm": 0.05811898037791252,
"learning_rate": 3.681629207885133e-05,
"loss": 0.7314453125,
"step": 1144
},
{
"epoch": 4.525691699604743,
"grad_norm": 0.05595145747065544,
"learning_rate": 3.67059382269698e-05,
"loss": 0.74462890625,
"step": 1145
},
{
"epoch": 4.529644268774703,
"grad_norm": 0.05631166696548462,
"learning_rate": 3.659646222453145e-05,
"loss": 0.71435546875,
"step": 1146
},
{
"epoch": 4.533596837944664,
"grad_norm": 0.057159360498189926,
"learning_rate": 3.64878648206236e-05,
"loss": 0.69189453125,
"step": 1147
},
{
"epoch": 4.537549407114625,
"grad_norm": 0.05762336775660515,
"learning_rate": 3.638014675832164e-05,
"loss": 0.7412109375,
"step": 1148
},
{
"epoch": 4.541501976284585,
"grad_norm": 0.056783583015203476,
"learning_rate": 3.627330877468422e-05,
"loss": 0.73388671875,
"step": 1149
},
{
"epoch": 4.545454545454545,
"grad_norm": 0.05468875914812088,
"learning_rate": 3.616735160074798e-05,
"loss": 0.71533203125,
"step": 1150
},
{
"epoch": 4.549407114624506,
"grad_norm": 0.05687073990702629,
"learning_rate": 3.606227596152269e-05,
"loss": 0.72705078125,
"step": 1151
},
{
"epoch": 4.553359683794467,
"grad_norm": 0.05497435852885246,
"learning_rate": 3.5958082575986254e-05,
"loss": 0.6357421875,
"step": 1152
},
{
"epoch": 4.557312252964427,
"grad_norm": 0.05538005381822586,
"learning_rate": 3.585477215707968e-05,
"loss": 0.7001953125,
"step": 1153
},
{
"epoch": 4.561264822134388,
"grad_norm": 0.0567510724067688,
"learning_rate": 3.57523454117024e-05,
"loss": 0.736328125,
"step": 1154
},
{
"epoch": 4.565217391304348,
"grad_norm": 0.05559039115905762,
"learning_rate": 3.565080304070727e-05,
"loss": 0.69091796875,
"step": 1155
},
{
"epoch": 4.569169960474309,
"grad_norm": 0.0571005754172802,
"learning_rate": 3.5550145738895836e-05,
"loss": 0.671875,
"step": 1156
},
{
"epoch": 4.573122529644269,
"grad_norm": 0.056164585053920746,
"learning_rate": 3.5450374195013606e-05,
"loss": 0.70703125,
"step": 1157
},
{
"epoch": 4.5770750988142295,
"grad_norm": 0.05715157091617584,
"learning_rate": 3.5351489091745274e-05,
"loss": 0.716796875,
"step": 1158
},
{
"epoch": 4.5810276679841895,
"grad_norm": 0.26093801856040955,
"learning_rate": 3.525349110571009e-05,
"loss": 0.67138671875,
"step": 1159
},
{
"epoch": 4.58498023715415,
"grad_norm": 0.060415253043174744,
"learning_rate": 3.515638090745726e-05,
"loss": 0.73193359375,
"step": 1160
},
{
"epoch": 4.58893280632411,
"grad_norm": 0.059150293469429016,
"learning_rate": 3.5060159161461286e-05,
"loss": 0.73095703125,
"step": 1161
},
{
"epoch": 4.592885375494071,
"grad_norm": 0.057372454553842545,
"learning_rate": 3.496482652611744e-05,
"loss": 0.71826171875,
"step": 1162
},
{
"epoch": 4.596837944664031,
"grad_norm": 0.05578102543950081,
"learning_rate": 3.48703836537373e-05,
"loss": 0.7373046875,
"step": 1163
},
{
"epoch": 4.600790513833992,
"grad_norm": 0.05556683987379074,
"learning_rate": 3.477683119054425e-05,
"loss": 0.71484375,
"step": 1164
},
{
"epoch": 4.604743083003952,
"grad_norm": 0.05595415458083153,
"learning_rate": 3.468416977666906e-05,
"loss": 0.728515625,
"step": 1165
},
{
"epoch": 4.608695652173913,
"grad_norm": 0.05514390021562576,
"learning_rate": 3.459240004614554e-05,
"loss": 0.72119140625,
"step": 1166
},
{
"epoch": 4.612648221343873,
"grad_norm": 0.055212028324604034,
"learning_rate": 3.450152262690616e-05,
"loss": 0.6982421875,
"step": 1167
},
{
"epoch": 4.616600790513834,
"grad_norm": 0.05663762241601944,
"learning_rate": 3.441153814077777e-05,
"loss": 0.75927734375,
"step": 1168
},
{
"epoch": 4.620553359683795,
"grad_norm": 0.055595897138118744,
"learning_rate": 3.432244720347731e-05,
"loss": 0.736328125,
"step": 1169
},
{
"epoch": 4.624505928853755,
"grad_norm": 0.05545177310705185,
"learning_rate": 3.423425042460768e-05,
"loss": 0.69287109375,
"step": 1170
},
{
"epoch": 4.628458498023716,
"grad_norm": 0.05727703496813774,
"learning_rate": 3.41469484076535e-05,
"loss": 0.7216796875,
"step": 1171
},
{
"epoch": 4.632411067193676,
"grad_norm": 0.05711454153060913,
"learning_rate": 3.4060541749977014e-05,
"loss": 0.73291015625,
"step": 1172
},
{
"epoch": 4.636363636363637,
"grad_norm": 0.055495601147413254,
"learning_rate": 3.397503104281395e-05,
"loss": 0.70849609375,
"step": 1173
},
{
"epoch": 4.640316205533597,
"grad_norm": 0.056339360773563385,
"learning_rate": 3.389041687126957e-05,
"loss": 0.7490234375,
"step": 1174
},
{
"epoch": 4.644268774703558,
"grad_norm": 0.05566352233290672,
"learning_rate": 3.380669981431455e-05,
"loss": 0.6982421875,
"step": 1175
},
{
"epoch": 4.648221343873518,
"grad_norm": 0.05475316569209099,
"learning_rate": 3.372388044478112e-05,
"loss": 0.7275390625,
"step": 1176
},
{
"epoch": 4.6521739130434785,
"grad_norm": 0.05501093342900276,
"learning_rate": 3.36419593293591e-05,
"loss": 0.68798828125,
"step": 1177
},
{
"epoch": 4.6561264822134385,
"grad_norm": 0.05590834096074104,
"learning_rate": 3.356093702859199e-05,
"loss": 0.681640625,
"step": 1178
},
{
"epoch": 4.660079051383399,
"grad_norm": 0.0547773577272892,
"learning_rate": 3.3480814096873205e-05,
"loss": 0.71826171875,
"step": 1179
},
{
"epoch": 4.664031620553359,
"grad_norm": 0.0576273575425148,
"learning_rate": 3.3401591082442256e-05,
"loss": 0.72900390625,
"step": 1180
},
{
"epoch": 4.66798418972332,
"grad_norm": 0.057993900030851364,
"learning_rate": 3.332326852738093e-05,
"loss": 0.665771484375,
"step": 1181
},
{
"epoch": 4.67193675889328,
"grad_norm": 0.05709964409470558,
"learning_rate": 3.32458469676097e-05,
"loss": 0.767578125,
"step": 1182
},
{
"epoch": 4.675889328063241,
"grad_norm": 0.055068306624889374,
"learning_rate": 3.316932693288398e-05,
"loss": 0.71337890625,
"step": 1183
},
{
"epoch": 4.679841897233201,
"grad_norm": 0.05504557862877846,
"learning_rate": 3.309370894679049e-05,
"loss": 0.679931640625,
"step": 1184
},
{
"epoch": 4.683794466403162,
"grad_norm": 0.05689159780740738,
"learning_rate": 3.301899352674373e-05,
"loss": 0.7578125,
"step": 1185
},
{
"epoch": 4.687747035573123,
"grad_norm": 0.05697442963719368,
"learning_rate": 3.294518118398244e-05,
"loss": 0.734375,
"step": 1186
},
{
"epoch": 4.691699604743083,
"grad_norm": 0.0566042996942997,
"learning_rate": 3.287227242356598e-05,
"loss": 0.7041015625,
"step": 1187
},
{
"epoch": 4.695652173913043,
"grad_norm": 0.054815925657749176,
"learning_rate": 3.280026774437107e-05,
"loss": 0.6845703125,
"step": 1188
},
{
"epoch": 4.699604743083004,
"grad_norm": 0.056150153279304504,
"learning_rate": 3.2729167639088196e-05,
"loss": 0.69580078125,
"step": 1189
},
{
"epoch": 4.703557312252965,
"grad_norm": 0.05479145422577858,
"learning_rate": 3.2658972594218356e-05,
"loss": 0.7333984375,
"step": 1190
},
{
"epoch": 4.707509881422925,
"grad_norm": 0.05574192851781845,
"learning_rate": 3.2589683090069686e-05,
"loss": 0.7021484375,
"step": 1191
},
{
"epoch": 4.711462450592886,
"grad_norm": 0.05705820396542549,
"learning_rate": 3.252129960075418e-05,
"loss": 0.6943359375,
"step": 1192
},
{
"epoch": 4.715415019762846,
"grad_norm": 0.05751410126686096,
"learning_rate": 3.2453822594184415e-05,
"loss": 0.688232421875,
"step": 1193
},
{
"epoch": 4.719367588932807,
"grad_norm": 0.055831827223300934,
"learning_rate": 3.238725253207042e-05,
"loss": 0.728515625,
"step": 1194
},
{
"epoch": 4.723320158102767,
"grad_norm": 0.05498051270842552,
"learning_rate": 3.232158986991645e-05,
"loss": 0.708984375,
"step": 1195
},
{
"epoch": 4.7272727272727275,
"grad_norm": 0.0530736930668354,
"learning_rate": 3.2256835057017896e-05,
"loss": 0.609130859375,
"step": 1196
},
{
"epoch": 4.7312252964426875,
"grad_norm": 0.055936723947525024,
"learning_rate": 3.219298853645823e-05,
"loss": 0.7177734375,
"step": 1197
},
{
"epoch": 4.735177865612648,
"grad_norm": 0.05768805369734764,
"learning_rate": 3.213005074510594e-05,
"loss": 0.7578125,
"step": 1198
},
{
"epoch": 4.739130434782608,
"grad_norm": 0.05408450588583946,
"learning_rate": 3.206802211361154e-05,
"loss": 0.67041015625,
"step": 1199
},
{
"epoch": 4.743083003952569,
"grad_norm": 0.055922579020261765,
"learning_rate": 3.200690306640465e-05,
"loss": 0.6787109375,
"step": 1200
},
{
"epoch": 4.747035573122529,
"grad_norm": 0.05565500259399414,
"learning_rate": 3.1946694021691064e-05,
"loss": 0.73291015625,
"step": 1201
},
{
"epoch": 4.75098814229249,
"grad_norm": 0.05630705878138542,
"learning_rate": 3.188739539144995e-05,
"loss": 0.74267578125,
"step": 1202
},
{
"epoch": 4.75494071146245,
"grad_norm": 0.05529142916202545,
"learning_rate": 3.182900758143091e-05,
"loss": 0.75390625,
"step": 1203
},
{
"epoch": 4.758893280632411,
"grad_norm": 0.05508255958557129,
"learning_rate": 3.1771530991151335e-05,
"loss": 0.579345703125,
"step": 1204
},
{
"epoch": 4.762845849802371,
"grad_norm": 0.05694893002510071,
"learning_rate": 3.1714966013893594e-05,
"loss": 0.69482421875,
"step": 1205
},
{
"epoch": 4.766798418972332,
"grad_norm": 0.05562539026141167,
"learning_rate": 3.1659313036702384e-05,
"loss": 0.73193359375,
"step": 1206
},
{
"epoch": 4.770750988142293,
"grad_norm": 0.05617164447903633,
"learning_rate": 3.160457244038201e-05,
"loss": 0.63671875,
"step": 1207
},
{
"epoch": 4.774703557312253,
"grad_norm": 0.054693274199962616,
"learning_rate": 3.155074459949388e-05,
"loss": 0.72021484375,
"step": 1208
},
{
"epoch": 4.778656126482213,
"grad_norm": 0.05582672357559204,
"learning_rate": 3.149782988235388e-05,
"loss": 0.724609375,
"step": 1209
},
{
"epoch": 4.782608695652174,
"grad_norm": 0.055862534791231155,
"learning_rate": 3.1445828651029814e-05,
"loss": 0.6865234375,
"step": 1210
},
{
"epoch": 4.786561264822135,
"grad_norm": 0.056729596108198166,
"learning_rate": 3.139474126133908e-05,
"loss": 0.67431640625,
"step": 1211
},
{
"epoch": 4.790513833992095,
"grad_norm": 0.055598948150873184,
"learning_rate": 3.134456806284605e-05,
"loss": 0.68994140625,
"step": 1212
},
{
"epoch": 4.794466403162056,
"grad_norm": 0.055375054478645325,
"learning_rate": 3.129530939885979e-05,
"loss": 0.71435546875,
"step": 1213
},
{
"epoch": 4.798418972332016,
"grad_norm": 0.055152665823698044,
"learning_rate": 3.124696560643167e-05,
"loss": 0.7001953125,
"step": 1214
},
{
"epoch": 4.8023715415019765,
"grad_norm": 0.056901007890701294,
"learning_rate": 3.1199537016353095e-05,
"loss": 0.71044921875,
"step": 1215
},
{
"epoch": 4.8063241106719365,
"grad_norm": 0.05612964555621147,
"learning_rate": 3.115302395315322e-05,
"loss": 0.775390625,
"step": 1216
},
{
"epoch": 4.810276679841897,
"grad_norm": 0.05552266910672188,
"learning_rate": 3.110742673509668e-05,
"loss": 0.73779296875,
"step": 1217
},
{
"epoch": 4.8142292490118574,
"grad_norm": 0.056585729122161865,
"learning_rate": 3.1062745674181515e-05,
"loss": 0.7099609375,
"step": 1218
},
{
"epoch": 4.818181818181818,
"grad_norm": 0.05520981550216675,
"learning_rate": 3.101898107613694e-05,
"loss": 0.68359375,
"step": 1219
},
{
"epoch": 4.822134387351778,
"grad_norm": 0.0560835637152195,
"learning_rate": 3.0976133240421296e-05,
"loss": 0.7041015625,
"step": 1220
},
{
"epoch": 4.826086956521739,
"grad_norm": 0.05474124476313591,
"learning_rate": 3.093420246022002e-05,
"loss": 0.70068359375,
"step": 1221
},
{
"epoch": 4.830039525691699,
"grad_norm": 0.05576196312904358,
"learning_rate": 3.0893189022443596e-05,
"loss": 0.724609375,
"step": 1222
},
{
"epoch": 4.83399209486166,
"grad_norm": 0.05694150924682617,
"learning_rate": 3.0853093207725634e-05,
"loss": 0.7490234375,
"step": 1223
},
{
"epoch": 4.837944664031621,
"grad_norm": 0.05832142382860184,
"learning_rate": 3.0813915290420866e-05,
"loss": 0.69140625,
"step": 1224
},
{
"epoch": 4.841897233201581,
"grad_norm": 0.05578732490539551,
"learning_rate": 3.0775655538603424e-05,
"loss": 0.689453125,
"step": 1225
},
{
"epoch": 4.845849802371541,
"grad_norm": 0.055678464472293854,
"learning_rate": 3.073831421406484e-05,
"loss": 0.72509765625,
"step": 1226
},
{
"epoch": 4.849802371541502,
"grad_norm": 0.05638342723250389,
"learning_rate": 3.070189157231234e-05,
"loss": 0.681640625,
"step": 1227
},
{
"epoch": 4.853754940711463,
"grad_norm": 0.05609418824315071,
"learning_rate": 3.0666387862567104e-05,
"loss": 0.7158203125,
"step": 1228
},
{
"epoch": 4.857707509881423,
"grad_norm": 0.05710776895284653,
"learning_rate": 3.0631803327762504e-05,
"loss": 0.74267578125,
"step": 1229
},
{
"epoch": 4.861660079051384,
"grad_norm": 0.056284066289663315,
"learning_rate": 3.059813820454254e-05,
"loss": 0.75146484375,
"step": 1230
},
{
"epoch": 4.865612648221344,
"grad_norm": 0.05773218721151352,
"learning_rate": 3.0565392723260084e-05,
"loss": 0.7236328125,
"step": 1231
},
{
"epoch": 4.869565217391305,
"grad_norm": 0.05682191252708435,
"learning_rate": 3.053356710797543e-05,
"loss": 0.73974609375,
"step": 1232
},
{
"epoch": 4.873517786561265,
"grad_norm": 0.057496849447488785,
"learning_rate": 3.0502661576454654e-05,
"loss": 0.75244140625,
"step": 1233
},
{
"epoch": 4.877470355731226,
"grad_norm": 0.055534396320581436,
"learning_rate": 3.047267634016824e-05,
"loss": 0.76220703125,
"step": 1234
},
{
"epoch": 4.881422924901186,
"grad_norm": 0.0553637370467186,
"learning_rate": 3.0443611604289538e-05,
"loss": 0.67236328125,
"step": 1235
},
{
"epoch": 4.8853754940711465,
"grad_norm": 0.05914520472288132,
"learning_rate": 3.04154675676934e-05,
"loss": 0.68701171875,
"step": 1236
},
{
"epoch": 4.8893280632411065,
"grad_norm": 0.056896913796663284,
"learning_rate": 3.0388244422954794e-05,
"loss": 0.72216796875,
"step": 1237
},
{
"epoch": 4.893280632411067,
"grad_norm": 0.05555310845375061,
"learning_rate": 3.0361942356347526e-05,
"loss": 0.6748046875,
"step": 1238
},
{
"epoch": 4.897233201581027,
"grad_norm": 0.05691086873412132,
"learning_rate": 3.0336561547842936e-05,
"loss": 0.71728515625,
"step": 1239
},
{
"epoch": 4.901185770750988,
"grad_norm": 0.058291394263505936,
"learning_rate": 3.0312102171108698e-05,
"loss": 0.67822265625,
"step": 1240
},
{
"epoch": 4.905138339920948,
"grad_norm": 0.05477149412035942,
"learning_rate": 3.028856439350756e-05,
"loss": 0.6962890625,
"step": 1241
},
{
"epoch": 4.909090909090909,
"grad_norm": 0.0555829256772995,
"learning_rate": 3.02659483760963e-05,
"loss": 0.74951171875,
"step": 1242
},
{
"epoch": 4.913043478260869,
"grad_norm": 0.054509956389665604,
"learning_rate": 3.0244254273624526e-05,
"loss": 0.71142578125,
"step": 1243
},
{
"epoch": 4.91699604743083,
"grad_norm": 0.0573466531932354,
"learning_rate": 3.0223482234533686e-05,
"loss": 0.744140625,
"step": 1244
},
{
"epoch": 4.920948616600791,
"grad_norm": 0.05668642744421959,
"learning_rate": 3.0203632400956037e-05,
"loss": 0.734375,
"step": 1245
},
{
"epoch": 4.924901185770751,
"grad_norm": 0.05693650245666504,
"learning_rate": 3.0184704908713622e-05,
"loss": 0.70751953125,
"step": 1246
},
{
"epoch": 4.928853754940711,
"grad_norm": 0.05662629008293152,
"learning_rate": 3.0166699887317446e-05,
"loss": 0.68212890625,
"step": 1247
},
{
"epoch": 4.932806324110672,
"grad_norm": 0.05085329711437225,
"learning_rate": 3.0149617459966466e-05,
"loss": 0.6214752197265625,
"step": 1248
},
{
"epoch": 4.936758893280633,
"grad_norm": 0.05406127870082855,
"learning_rate": 3.0133457743546867e-05,
"loss": 0.72705078125,
"step": 1249
},
{
"epoch": 4.940711462450593,
"grad_norm": 0.05496757850050926,
"learning_rate": 3.011822084863114e-05,
"loss": 0.7392578125,
"step": 1250
},
{
"epoch": 4.944664031620554,
"grad_norm": 0.05471997335553169,
"learning_rate": 3.0103906879477434e-05,
"loss": 0.69873046875,
"step": 1251
},
{
"epoch": 4.948616600790514,
"grad_norm": 0.05885379761457443,
"learning_rate": 3.0090515934028784e-05,
"loss": 0.71142578125,
"step": 1252
},
{
"epoch": 4.952569169960475,
"grad_norm": 0.05763247236609459,
"learning_rate": 3.0078048103912447e-05,
"loss": 0.69140625,
"step": 1253
},
{
"epoch": 4.956521739130435,
"grad_norm": 0.05539042875170708,
"learning_rate": 3.00665034744393e-05,
"loss": 0.75537109375,
"step": 1254
},
{
"epoch": 4.9604743083003955,
"grad_norm": 0.056817468255758286,
"learning_rate": 3.005588212460323e-05,
"loss": 0.7138671875,
"step": 1255
},
{
"epoch": 4.9644268774703555,
"grad_norm": 0.05679190158843994,
"learning_rate": 3.004618412708061e-05,
"loss": 0.72412109375,
"step": 1256
},
{
"epoch": 4.968379446640316,
"grad_norm": 0.05523546785116196,
"learning_rate": 3.0037409548229765e-05,
"loss": 0.631103515625,
"step": 1257
},
{
"epoch": 4.972332015810276,
"grad_norm": 0.05577237159013748,
"learning_rate": 3.002955844809058e-05,
"loss": 0.72802734375,
"step": 1258
},
{
"epoch": 4.976284584980237,
"grad_norm": 0.055667150765657425,
"learning_rate": 3.0022630880384044e-05,
"loss": 0.68408203125,
"step": 1259
},
{
"epoch": 4.980237154150197,
"grad_norm": 0.05597792938351631,
"learning_rate": 3.001662689251188e-05,
"loss": 0.71240234375,
"step": 1260
},
{
"epoch": 4.984189723320158,
"grad_norm": 0.05570489913225174,
"learning_rate": 3.0011546525556278e-05,
"loss": 0.73095703125,
"step": 1261
},
{
"epoch": 4.988142292490118,
"grad_norm": 0.05224841460585594,
"learning_rate": 3.0007389814279508e-05,
"loss": 0.617431640625,
"step": 1262
},
{
"epoch": 4.992094861660079,
"grad_norm": 0.05771161988377571,
"learning_rate": 3.0004156787123817e-05,
"loss": 0.7470703125,
"step": 1263
},
{
"epoch": 4.996047430830039,
"grad_norm": 0.05612274259328842,
"learning_rate": 3.0001847466211105e-05,
"loss": 0.66943359375,
"step": 1264
},
{
"epoch": 5.0,
"grad_norm": 0.0666361004114151,
"learning_rate": 3.000046186734286e-05,
"loss": 0.65478515625,
"step": 1265
},
{
"epoch": 5.0,
"eval_loss": 0.828125,
"eval_runtime": 2.22,
"eval_samples_per_second": 2.703,
"eval_steps_per_second": 0.45,
"step": 1265
}
],
"logging_steps": 1.0,
"max_steps": 1265,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 9.273463858175934e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}