jeqcho's picture
Upload seed2/checkpoint-165
c8018dc verified
Raw
History Blame
29.3 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0857142857142856,
"eval_steps": 500,
"global_step": 165,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006593406593406593,
"grad_norm": 0.7566928863525391,
"learning_rate": 0.0,
"loss": 0.8968,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 0.8072069883346558,
"learning_rate": 4e-05,
"loss": 0.9227,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 0.8303298950195312,
"learning_rate": 8e-05,
"loss": 0.9508,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 0.9258667826652527,
"learning_rate": 0.00012,
"loss": 0.9527,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 0.9558561444282532,
"learning_rate": 0.00016,
"loss": 0.9178,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 0.47254669666290283,
"learning_rate": 0.0002,
"loss": 0.7227,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 0.5736677646636963,
"learning_rate": 0.00019955654101995565,
"loss": 0.7945,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 0.6585658192634583,
"learning_rate": 0.00019911308203991133,
"loss": 0.9034,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 0.6045550107955933,
"learning_rate": 0.00019866962305986697,
"loss": 0.8399,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.4790070056915283,
"learning_rate": 0.00019822616407982261,
"loss": 0.8234,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.3827012777328491,
"learning_rate": 0.00019778270509977829,
"loss": 0.8281,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.31580132246017456,
"learning_rate": 0.00019733924611973393,
"loss": 0.7572,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.2703302502632141,
"learning_rate": 0.0001968957871396896,
"loss": 0.7605,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.2565660774707794,
"learning_rate": 0.00019645232815964525,
"loss": 0.8042,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.19942161440849304,
"learning_rate": 0.00019600886917960092,
"loss": 0.7443,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.21022649109363556,
"learning_rate": 0.00019556541019955653,
"loss": 0.6641,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.2277892380952835,
"learning_rate": 0.0001951219512195122,
"loss": 0.7432,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.33732736110687256,
"learning_rate": 0.00019467849223946785,
"loss": 0.7787,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.27139249444007874,
"learning_rate": 0.00019423503325942352,
"loss": 0.7951,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.2788768410682678,
"learning_rate": 0.00019379157427937917,
"loss": 0.719,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.2770022451877594,
"learning_rate": 0.00019334811529933484,
"loss": 0.7604,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.2961127460002899,
"learning_rate": 0.00019290465631929045,
"loss": 0.7834,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.42819708585739136,
"learning_rate": 0.00019246119733924613,
"loss": 0.7302,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.2841340899467468,
"learning_rate": 0.00019201773835920177,
"loss": 0.7261,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.2913196384906769,
"learning_rate": 0.00019157427937915744,
"loss": 0.7212,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.3300360143184662,
"learning_rate": 0.00019113082039911309,
"loss": 0.6494,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.27701273560523987,
"learning_rate": 0.00019068736141906876,
"loss": 0.6838,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.2448320835828781,
"learning_rate": 0.0001902439024390244,
"loss": 0.6998,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.2562633454799652,
"learning_rate": 0.00018980044345898005,
"loss": 0.7449,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.2887221574783325,
"learning_rate": 0.00018935698447893572,
"loss": 0.6676,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.2212107628583908,
"learning_rate": 0.00018891352549889136,
"loss": 0.7629,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.26358944177627563,
"learning_rate": 0.00018847006651884703,
"loss": 0.7497,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.19833838939666748,
"learning_rate": 0.00018802660753880268,
"loss": 0.7787,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.21352550387382507,
"learning_rate": 0.00018758314855875832,
"loss": 0.7513,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.2602783739566803,
"learning_rate": 0.00018713968957871397,
"loss": 0.7423,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.25566816329956055,
"learning_rate": 0.00018669623059866964,
"loss": 0.7049,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.26156026124954224,
"learning_rate": 0.00018625277161862528,
"loss": 0.7342,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.2607591450214386,
"learning_rate": 0.00018580931263858095,
"loss": 0.6492,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.2538753151893616,
"learning_rate": 0.0001853658536585366,
"loss": 0.6907,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.25195640325546265,
"learning_rate": 0.00018492239467849224,
"loss": 0.7535,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.2823958098888397,
"learning_rate": 0.0001844789356984479,
"loss": 0.6653,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.2609056532382965,
"learning_rate": 0.00018403547671840356,
"loss": 0.6967,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.21727432310581207,
"learning_rate": 0.0001835920177383592,
"loss": 0.7071,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.28144368529319763,
"learning_rate": 0.00018314855875831487,
"loss": 0.7169,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.23335450887680054,
"learning_rate": 0.00018270509977827052,
"loss": 0.7365,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.2892163097858429,
"learning_rate": 0.00018226164079822616,
"loss": 0.6403,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.2446267455816269,
"learning_rate": 0.00018181818181818183,
"loss": 0.6869,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.24830380082130432,
"learning_rate": 0.00018137472283813748,
"loss": 0.6407,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.32878631353378296,
"learning_rate": 0.00018093126385809312,
"loss": 0.6962,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.23604710400104523,
"learning_rate": 0.0001804878048780488,
"loss": 0.7427,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.20495985448360443,
"learning_rate": 0.00018004434589800444,
"loss": 0.6272,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.21541891992092133,
"learning_rate": 0.00017960088691796008,
"loss": 0.7157,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.2712082266807556,
"learning_rate": 0.00017915742793791575,
"loss": 0.7132,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.2737255096435547,
"learning_rate": 0.0001787139689578714,
"loss": 0.7115,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.3590952455997467,
"learning_rate": 0.00017827050997782707,
"loss": 0.7041,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.22194194793701172,
"learning_rate": 0.00017782705099778271,
"loss": 0.6017,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.2181357890367508,
"learning_rate": 0.00017738359201773839,
"loss": 0.7292,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.2543794512748718,
"learning_rate": 0.000176940133037694,
"loss": 0.7028,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.33169296383857727,
"learning_rate": 0.00017649667405764967,
"loss": 0.6646,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.27475646138191223,
"learning_rate": 0.00017605321507760532,
"loss": 0.7889,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.2369152307510376,
"learning_rate": 0.000175609756097561,
"loss": 0.7018,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.21613454818725586,
"learning_rate": 0.00017516629711751663,
"loss": 0.6715,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.20882739126682281,
"learning_rate": 0.0001747228381374723,
"loss": 0.6892,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.2187095731496811,
"learning_rate": 0.00017427937915742792,
"loss": 0.6436,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.2040148377418518,
"learning_rate": 0.0001738359201773836,
"loss": 0.6512,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.2536020874977112,
"learning_rate": 0.00017339246119733924,
"loss": 0.7019,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.24403820931911469,
"learning_rate": 0.0001729490022172949,
"loss": 0.6723,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.2113356590270996,
"learning_rate": 0.00017250554323725056,
"loss": 0.7119,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.2046196013689041,
"learning_rate": 0.00017206208425720623,
"loss": 0.7191,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.22032175958156586,
"learning_rate": 0.00017161862527716187,
"loss": 0.7159,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.2522450387477875,
"learning_rate": 0.00017117516629711752,
"loss": 0.7039,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.2568543553352356,
"learning_rate": 0.0001707317073170732,
"loss": 0.6842,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.21719902753829956,
"learning_rate": 0.00017028824833702883,
"loss": 0.6942,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.22592927515506744,
"learning_rate": 0.0001698447893569845,
"loss": 0.7966,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.241453617811203,
"learning_rate": 0.00016940133037694015,
"loss": 0.7412,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.23723702132701874,
"learning_rate": 0.00016895787139689582,
"loss": 0.7148,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.20009562373161316,
"learning_rate": 0.00016851441241685144,
"loss": 0.7143,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.2050897777080536,
"learning_rate": 0.0001680709534368071,
"loss": 0.6766,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.22315199673175812,
"learning_rate": 0.00016762749445676275,
"loss": 0.7,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.20680196583271027,
"learning_rate": 0.00016718403547671842,
"loss": 0.6356,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.23944680392742157,
"learning_rate": 0.00016674057649667407,
"loss": 0.6559,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.22115568816661835,
"learning_rate": 0.00016629711751662974,
"loss": 0.6644,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.2396654337644577,
"learning_rate": 0.00016585365853658536,
"loss": 0.6972,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.2545161545276642,
"learning_rate": 0.00016541019955654103,
"loss": 0.7242,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.2548670172691345,
"learning_rate": 0.00016496674057649667,
"loss": 0.756,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.2570771872997284,
"learning_rate": 0.00016452328159645234,
"loss": 0.7392,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.25188854336738586,
"learning_rate": 0.000164079822616408,
"loss": 0.7504,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.24089300632476807,
"learning_rate": 0.00016363636363636366,
"loss": 0.6831,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.21377258002758026,
"learning_rate": 0.0001631929046563193,
"loss": 0.6904,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.22940956056118011,
"learning_rate": 0.00016274944567627495,
"loss": 0.7223,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.23013509809970856,
"learning_rate": 0.0001623059866962306,
"loss": 0.6743,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.2341698855161667,
"learning_rate": 0.00016186252771618626,
"loss": 0.6031,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.21239612996578217,
"learning_rate": 0.0001614190687361419,
"loss": 0.6043,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.21493980288505554,
"learning_rate": 0.00016097560975609758,
"loss": 0.6019,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.2181602418422699,
"learning_rate": 0.00016053215077605322,
"loss": 0.6601,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.2473670393228531,
"learning_rate": 0.00016008869179600887,
"loss": 0.7301,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.23289376497268677,
"learning_rate": 0.00015964523281596454,
"loss": 0.7493,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.22319060564041138,
"learning_rate": 0.00015920177383592018,
"loss": 0.7057,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.24551022052764893,
"learning_rate": 0.00015875831485587586,
"loss": 0.6467,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.21545983850955963,
"learning_rate": 0.0001583148558758315,
"loss": 0.7107,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.2510841190814972,
"learning_rate": 0.00015787139689578714,
"loss": 0.658,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.23200248181819916,
"learning_rate": 0.0001574279379157428,
"loss": 0.7351,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.2180459201335907,
"learning_rate": 0.00015698447893569846,
"loss": 0.6992,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.23387350142002106,
"learning_rate": 0.0001565410199556541,
"loss": 0.7398,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.22272081673145294,
"learning_rate": 0.00015609756097560978,
"loss": 0.6528,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.22667521238327026,
"learning_rate": 0.00015565410199556542,
"loss": 0.76,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.2085743099451065,
"learning_rate": 0.00015521064301552106,
"loss": 0.6842,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.24620012938976288,
"learning_rate": 0.0001547671840354767,
"loss": 0.738,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.23256433010101318,
"learning_rate": 0.00015432372505543238,
"loss": 0.6475,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.2518521249294281,
"learning_rate": 0.00015388026607538802,
"loss": 0.6764,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.22852903604507446,
"learning_rate": 0.0001534368070953437,
"loss": 0.6797,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.22933068871498108,
"learning_rate": 0.00015299334811529934,
"loss": 0.7095,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.22621572017669678,
"learning_rate": 0.00015254988913525498,
"loss": 0.6587,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 0.24995188415050507,
"learning_rate": 0.00015210643015521066,
"loss": 0.7068,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.25118041038513184,
"learning_rate": 0.0001516629711751663,
"loss": 0.6904,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.21053656935691833,
"learning_rate": 0.00015121951219512197,
"loss": 0.549,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.2095535695552826,
"learning_rate": 0.00015077605321507762,
"loss": 0.6875,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.21824686229228973,
"learning_rate": 0.0001503325942350333,
"loss": 0.6729,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.2307584136724472,
"learning_rate": 0.0001498891352549889,
"loss": 0.6493,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.22242283821105957,
"learning_rate": 0.00014944567627494458,
"loss": 0.668,
"step": 120
},
{
"epoch": 0.7978021978021979,
"grad_norm": 0.22179292142391205,
"learning_rate": 0.00014900221729490022,
"loss": 0.6386,
"step": 121
},
{
"epoch": 0.8043956043956044,
"grad_norm": 0.23222969472408295,
"learning_rate": 0.0001485587583148559,
"loss": 0.6712,
"step": 122
},
{
"epoch": 0.810989010989011,
"grad_norm": 0.2495681792497635,
"learning_rate": 0.00014811529933481154,
"loss": 0.6295,
"step": 123
},
{
"epoch": 0.8175824175824176,
"grad_norm": 0.2647445797920227,
"learning_rate": 0.0001476718403547672,
"loss": 0.7005,
"step": 124
},
{
"epoch": 0.8241758241758241,
"grad_norm": 0.24217277765274048,
"learning_rate": 0.00014722838137472282,
"loss": 0.6311,
"step": 125
},
{
"epoch": 0.8307692307692308,
"grad_norm": 0.2461085021495819,
"learning_rate": 0.0001467849223946785,
"loss": 0.6446,
"step": 126
},
{
"epoch": 0.8373626373626374,
"grad_norm": 0.2610090970993042,
"learning_rate": 0.00014634146341463414,
"loss": 0.7045,
"step": 127
},
{
"epoch": 0.843956043956044,
"grad_norm": 0.2201678454875946,
"learning_rate": 0.0001458980044345898,
"loss": 0.6436,
"step": 128
},
{
"epoch": 0.8505494505494505,
"grad_norm": 0.22592248022556305,
"learning_rate": 0.00014545454545454546,
"loss": 0.6608,
"step": 129
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.22529453039169312,
"learning_rate": 0.00014501108647450113,
"loss": 0.6401,
"step": 130
},
{
"epoch": 0.8637362637362638,
"grad_norm": 0.2538209855556488,
"learning_rate": 0.00014456762749445675,
"loss": 0.6788,
"step": 131
},
{
"epoch": 0.8703296703296703,
"grad_norm": 0.22796444594860077,
"learning_rate": 0.00014412416851441242,
"loss": 0.7022,
"step": 132
},
{
"epoch": 0.8769230769230769,
"grad_norm": 0.20975171029567719,
"learning_rate": 0.00014368070953436806,
"loss": 0.6779,
"step": 133
},
{
"epoch": 0.8835164835164835,
"grad_norm": 0.22414448857307434,
"learning_rate": 0.00014323725055432373,
"loss": 0.7459,
"step": 134
},
{
"epoch": 0.8901098901098901,
"grad_norm": 0.270942747592926,
"learning_rate": 0.00014279379157427938,
"loss": 0.6682,
"step": 135
},
{
"epoch": 0.8967032967032967,
"grad_norm": 0.25628402829170227,
"learning_rate": 0.00014235033259423505,
"loss": 0.6759,
"step": 136
},
{
"epoch": 0.9032967032967033,
"grad_norm": 0.2702762484550476,
"learning_rate": 0.0001419068736141907,
"loss": 0.7287,
"step": 137
},
{
"epoch": 0.9098901098901099,
"grad_norm": 0.23527158796787262,
"learning_rate": 0.00014146341463414634,
"loss": 0.6365,
"step": 138
},
{
"epoch": 0.9164835164835164,
"grad_norm": 0.2638787031173706,
"learning_rate": 0.000141019955654102,
"loss": 0.7456,
"step": 139
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.2431294023990631,
"learning_rate": 0.00014057649667405765,
"loss": 0.655,
"step": 140
},
{
"epoch": 0.9296703296703297,
"grad_norm": 0.26322004199028015,
"learning_rate": 0.00014013303769401332,
"loss": 0.6694,
"step": 141
},
{
"epoch": 0.9362637362637363,
"grad_norm": 0.22624383866786957,
"learning_rate": 0.00013968957871396897,
"loss": 0.6025,
"step": 142
},
{
"epoch": 0.9428571428571428,
"grad_norm": 0.20489341020584106,
"learning_rate": 0.00013924611973392464,
"loss": 0.6544,
"step": 143
},
{
"epoch": 0.9494505494505494,
"grad_norm": 0.23127716779708862,
"learning_rate": 0.00013880266075388026,
"loss": 0.748,
"step": 144
},
{
"epoch": 0.9560439560439561,
"grad_norm": 0.23263822495937347,
"learning_rate": 0.00013835920177383593,
"loss": 0.674,
"step": 145
},
{
"epoch": 0.9626373626373627,
"grad_norm": 0.23276172578334808,
"learning_rate": 0.00013791574279379157,
"loss": 0.7082,
"step": 146
},
{
"epoch": 0.9692307692307692,
"grad_norm": 0.2461167722940445,
"learning_rate": 0.00013747228381374724,
"loss": 0.7059,
"step": 147
},
{
"epoch": 0.9758241758241758,
"grad_norm": 0.24031785130500793,
"learning_rate": 0.0001370288248337029,
"loss": 0.6732,
"step": 148
},
{
"epoch": 0.9824175824175824,
"grad_norm": 0.21587732434272766,
"learning_rate": 0.00013658536585365856,
"loss": 0.6605,
"step": 149
},
{
"epoch": 0.989010989010989,
"grad_norm": 0.22994357347488403,
"learning_rate": 0.00013614190687361418,
"loss": 0.6609,
"step": 150
},
{
"epoch": 0.9956043956043956,
"grad_norm": 0.2200823873281479,
"learning_rate": 0.00013569844789356985,
"loss": 0.7032,
"step": 151
},
{
"epoch": 1.0,
"grad_norm": 0.26850587129592896,
"learning_rate": 0.0001352549889135255,
"loss": 0.7507,
"step": 152
},
{
"epoch": 1.0065934065934066,
"grad_norm": 0.23838046193122864,
"learning_rate": 0.00013481152993348116,
"loss": 0.6686,
"step": 153
},
{
"epoch": 1.0131868131868131,
"grad_norm": 0.21873874962329865,
"learning_rate": 0.0001343680709534368,
"loss": 0.759,
"step": 154
},
{
"epoch": 1.0197802197802197,
"grad_norm": 0.22888495028018951,
"learning_rate": 0.00013392461197339248,
"loss": 0.5565,
"step": 155
},
{
"epoch": 1.0263736263736263,
"grad_norm": 0.21489110589027405,
"learning_rate": 0.00013348115299334812,
"loss": 0.6417,
"step": 156
},
{
"epoch": 1.032967032967033,
"grad_norm": 0.23249667882919312,
"learning_rate": 0.00013303769401330377,
"loss": 0.6282,
"step": 157
},
{
"epoch": 1.0395604395604396,
"grad_norm": 0.2237980216741562,
"learning_rate": 0.00013259423503325944,
"loss": 0.68,
"step": 158
},
{
"epoch": 1.0461538461538462,
"grad_norm": 0.2389901876449585,
"learning_rate": 0.00013215077605321509,
"loss": 0.6522,
"step": 159
},
{
"epoch": 1.0527472527472528,
"grad_norm": 0.23192445933818817,
"learning_rate": 0.00013170731707317076,
"loss": 0.6478,
"step": 160
},
{
"epoch": 1.0593406593406594,
"grad_norm": 0.25663626194000244,
"learning_rate": 0.0001312638580931264,
"loss": 0.7291,
"step": 161
},
{
"epoch": 1.065934065934066,
"grad_norm": 0.22465288639068604,
"learning_rate": 0.00013082039911308205,
"loss": 0.6243,
"step": 162
},
{
"epoch": 1.0725274725274725,
"grad_norm": 0.22050045430660248,
"learning_rate": 0.0001303769401330377,
"loss": 0.6577,
"step": 163
},
{
"epoch": 1.079120879120879,
"grad_norm": 0.2221308797597885,
"learning_rate": 0.00012993348115299336,
"loss": 0.6401,
"step": 164
},
{
"epoch": 1.0857142857142856,
"grad_norm": 0.24798862636089325,
"learning_rate": 0.000129490022172949,
"loss": 0.6871,
"step": 165
}
],
"logging_steps": 1,
"max_steps": 456,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 15,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 7.594081144602624e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}