Files
Malaysian-Llama-3.2-3B-Inst…/lora-embedding-128-llama3.2-3b-malaysian-8k/checkpoint-800/trainer_state.json
ModelHub XC a833baf8fa 初始化项目,由ModelHub XC社区提供模型
Model: mesolitica/Malaysian-Llama-3.2-3B-Instruct
Source: Original Platform
2026-08-22 12:53:17 +08:00

5635 lines
124 KiB
JSON

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2761477390403866,
"eval_steps": 500,
"global_step": 800,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034518467380048324,
"grad_norm": 25.833335876464844,
"learning_rate": 0.0,
"loss": 2.2926,
"step": 1
},
{
"epoch": 0.0006903693476009665,
"grad_norm": 23.58083724975586,
"learning_rate": 2e-05,
"loss": 2.1943,
"step": 2
},
{
"epoch": 0.0010355540214014498,
"grad_norm": 24.2187442779541,
"learning_rate": 2e-05,
"loss": 2.3772,
"step": 3
},
{
"epoch": 0.001380738695201933,
"grad_norm": 14.579557418823242,
"learning_rate": 2e-05,
"loss": 2.0945,
"step": 4
},
{
"epoch": 0.0017259233690024164,
"grad_norm": 15.069305419921875,
"learning_rate": 2e-05,
"loss": 2.1537,
"step": 5
},
{
"epoch": 0.0020711080428028996,
"grad_norm": 14.385339736938477,
"learning_rate": 2e-05,
"loss": 2.1585,
"step": 6
},
{
"epoch": 0.002416292716603383,
"grad_norm": 9.95476245880127,
"learning_rate": 2e-05,
"loss": 1.8333,
"step": 7
},
{
"epoch": 0.002761477390403866,
"grad_norm": 9.15005111694336,
"learning_rate": 2e-05,
"loss": 1.937,
"step": 8
},
{
"epoch": 0.0031066620642043494,
"grad_norm": 7.361661911010742,
"learning_rate": 2e-05,
"loss": 1.9484,
"step": 9
},
{
"epoch": 0.0034518467380048328,
"grad_norm": 5.931179046630859,
"learning_rate": 2e-05,
"loss": 1.7668,
"step": 10
},
{
"epoch": 0.0037970314118053157,
"grad_norm": 8.192151069641113,
"learning_rate": 2e-05,
"loss": 1.8234,
"step": 11
},
{
"epoch": 0.004142216085605799,
"grad_norm": 6.827078342437744,
"learning_rate": 2e-05,
"loss": 1.9133,
"step": 12
},
{
"epoch": 0.0044874007594062825,
"grad_norm": 7.808759689331055,
"learning_rate": 2e-05,
"loss": 1.8314,
"step": 13
},
{
"epoch": 0.004832585433206766,
"grad_norm": 7.531504154205322,
"learning_rate": 2e-05,
"loss": 1.7961,
"step": 14
},
{
"epoch": 0.0051777701070072485,
"grad_norm": 6.617609977722168,
"learning_rate": 2e-05,
"loss": 1.7624,
"step": 15
},
{
"epoch": 0.005522954780807732,
"grad_norm": 4.966954708099365,
"learning_rate": 2e-05,
"loss": 1.7034,
"step": 16
},
{
"epoch": 0.005868139454608215,
"grad_norm": 5.566157817840576,
"learning_rate": 2e-05,
"loss": 1.7722,
"step": 17
},
{
"epoch": 0.006213324128408699,
"grad_norm": 4.915079593658447,
"learning_rate": 2e-05,
"loss": 1.6602,
"step": 18
},
{
"epoch": 0.006558508802209182,
"grad_norm": 4.77263069152832,
"learning_rate": 2e-05,
"loss": 1.6854,
"step": 19
},
{
"epoch": 0.0069036934760096655,
"grad_norm": 4.299682140350342,
"learning_rate": 2e-05,
"loss": 1.6217,
"step": 20
},
{
"epoch": 0.007248878149810148,
"grad_norm": 4.1203694343566895,
"learning_rate": 2e-05,
"loss": 1.6546,
"step": 21
},
{
"epoch": 0.0075940628236106315,
"grad_norm": 4.058311939239502,
"learning_rate": 2e-05,
"loss": 1.6795,
"step": 22
},
{
"epoch": 0.007939247497411116,
"grad_norm": 3.668001651763916,
"learning_rate": 2e-05,
"loss": 1.7228,
"step": 23
},
{
"epoch": 0.008284432171211598,
"grad_norm": 3.397109270095825,
"learning_rate": 2e-05,
"loss": 1.555,
"step": 24
},
{
"epoch": 0.00862961684501208,
"grad_norm": 4.351656436920166,
"learning_rate": 2e-05,
"loss": 1.6977,
"step": 25
},
{
"epoch": 0.008974801518812565,
"grad_norm": 3.7789554595947266,
"learning_rate": 2e-05,
"loss": 1.6534,
"step": 26
},
{
"epoch": 0.009319986192613048,
"grad_norm": 3.4693193435668945,
"learning_rate": 2e-05,
"loss": 1.6248,
"step": 27
},
{
"epoch": 0.009665170866413532,
"grad_norm": 2.6027116775512695,
"learning_rate": 2e-05,
"loss": 1.4901,
"step": 28
},
{
"epoch": 0.010010355540214014,
"grad_norm": 2.6816513538360596,
"learning_rate": 2e-05,
"loss": 1.4964,
"step": 29
},
{
"epoch": 0.010355540214014497,
"grad_norm": 5.244405746459961,
"learning_rate": 2e-05,
"loss": 1.5238,
"step": 30
},
{
"epoch": 0.010700724887814981,
"grad_norm": 4.071628570556641,
"learning_rate": 2e-05,
"loss": 1.5401,
"step": 31
},
{
"epoch": 0.011045909561615464,
"grad_norm": 3.897395372390747,
"learning_rate": 2e-05,
"loss": 1.4759,
"step": 32
},
{
"epoch": 0.011391094235415948,
"grad_norm": 2.9609882831573486,
"learning_rate": 2e-05,
"loss": 1.4919,
"step": 33
},
{
"epoch": 0.01173627890921643,
"grad_norm": 3.1106183528900146,
"learning_rate": 2e-05,
"loss": 1.5436,
"step": 34
},
{
"epoch": 0.012081463583016915,
"grad_norm": 3.7441351413726807,
"learning_rate": 2e-05,
"loss": 1.5496,
"step": 35
},
{
"epoch": 0.012426648256817397,
"grad_norm": 3.6406350135803223,
"learning_rate": 2e-05,
"loss": 1.4531,
"step": 36
},
{
"epoch": 0.01277183293061788,
"grad_norm": 2.915447950363159,
"learning_rate": 2e-05,
"loss": 1.48,
"step": 37
},
{
"epoch": 0.013117017604418364,
"grad_norm": 2.8513331413269043,
"learning_rate": 2e-05,
"loss": 1.5192,
"step": 38
},
{
"epoch": 0.013462202278218847,
"grad_norm": 3.2347466945648193,
"learning_rate": 2e-05,
"loss": 1.5727,
"step": 39
},
{
"epoch": 0.013807386952019331,
"grad_norm": 2.82135272026062,
"learning_rate": 2e-05,
"loss": 1.5098,
"step": 40
},
{
"epoch": 0.014152571625819814,
"grad_norm": 2.694873809814453,
"learning_rate": 2e-05,
"loss": 1.4223,
"step": 41
},
{
"epoch": 0.014497756299620296,
"grad_norm": 2.7129478454589844,
"learning_rate": 2e-05,
"loss": 1.4062,
"step": 42
},
{
"epoch": 0.01484294097342078,
"grad_norm": 2.6555328369140625,
"learning_rate": 2e-05,
"loss": 1.4993,
"step": 43
},
{
"epoch": 0.015188125647221263,
"grad_norm": 2.3439159393310547,
"learning_rate": 2e-05,
"loss": 1.4281,
"step": 44
},
{
"epoch": 0.015533310321021747,
"grad_norm": 2.40368914604187,
"learning_rate": 2e-05,
"loss": 1.4261,
"step": 45
},
{
"epoch": 0.01587849499482223,
"grad_norm": 2.3288614749908447,
"learning_rate": 2e-05,
"loss": 1.3958,
"step": 46
},
{
"epoch": 0.016223679668622714,
"grad_norm": 2.474519968032837,
"learning_rate": 2e-05,
"loss": 1.4246,
"step": 47
},
{
"epoch": 0.016568864342423197,
"grad_norm": 2.680997371673584,
"learning_rate": 2e-05,
"loss": 1.4318,
"step": 48
},
{
"epoch": 0.01691404901622368,
"grad_norm": 2.6899235248565674,
"learning_rate": 2e-05,
"loss": 1.3581,
"step": 49
},
{
"epoch": 0.01725923369002416,
"grad_norm": 2.5045225620269775,
"learning_rate": 2e-05,
"loss": 1.3983,
"step": 50
},
{
"epoch": 0.017604418363824648,
"grad_norm": 2.650184154510498,
"learning_rate": 2e-05,
"loss": 1.4005,
"step": 51
},
{
"epoch": 0.01794960303762513,
"grad_norm": 2.560302495956421,
"learning_rate": 2e-05,
"loss": 1.3706,
"step": 52
},
{
"epoch": 0.018294787711425613,
"grad_norm": 2.116626739501953,
"learning_rate": 2e-05,
"loss": 1.2987,
"step": 53
},
{
"epoch": 0.018639972385226095,
"grad_norm": 3.0732431411743164,
"learning_rate": 2e-05,
"loss": 1.4394,
"step": 54
},
{
"epoch": 0.018985157059026578,
"grad_norm": 2.880014657974243,
"learning_rate": 2e-05,
"loss": 1.3772,
"step": 55
},
{
"epoch": 0.019330341732827064,
"grad_norm": 2.65002179145813,
"learning_rate": 2e-05,
"loss": 1.344,
"step": 56
},
{
"epoch": 0.019675526406627546,
"grad_norm": 2.4109294414520264,
"learning_rate": 2e-05,
"loss": 1.3818,
"step": 57
},
{
"epoch": 0.02002071108042803,
"grad_norm": 3.318305730819702,
"learning_rate": 2e-05,
"loss": 1.4488,
"step": 58
},
{
"epoch": 0.02036589575422851,
"grad_norm": 2.9551541805267334,
"learning_rate": 2e-05,
"loss": 1.3245,
"step": 59
},
{
"epoch": 0.020711080428028994,
"grad_norm": 2.512965679168701,
"learning_rate": 2e-05,
"loss": 1.3476,
"step": 60
},
{
"epoch": 0.02105626510182948,
"grad_norm": 2.608680248260498,
"learning_rate": 2e-05,
"loss": 1.335,
"step": 61
},
{
"epoch": 0.021401449775629963,
"grad_norm": 2.2880616188049316,
"learning_rate": 2e-05,
"loss": 1.2781,
"step": 62
},
{
"epoch": 0.021746634449430445,
"grad_norm": 2.7310123443603516,
"learning_rate": 2e-05,
"loss": 1.3449,
"step": 63
},
{
"epoch": 0.022091819123230928,
"grad_norm": 2.5008130073547363,
"learning_rate": 2e-05,
"loss": 1.4042,
"step": 64
},
{
"epoch": 0.02243700379703141,
"grad_norm": 3.5907320976257324,
"learning_rate": 2e-05,
"loss": 1.344,
"step": 65
},
{
"epoch": 0.022782188470831896,
"grad_norm": 2.4797489643096924,
"learning_rate": 2e-05,
"loss": 1.3342,
"step": 66
},
{
"epoch": 0.02312737314463238,
"grad_norm": 2.556204319000244,
"learning_rate": 2e-05,
"loss": 1.3244,
"step": 67
},
{
"epoch": 0.02347255781843286,
"grad_norm": 5.068964004516602,
"learning_rate": 2e-05,
"loss": 1.3041,
"step": 68
},
{
"epoch": 0.023817742492233344,
"grad_norm": 2.165076494216919,
"learning_rate": 2e-05,
"loss": 1.2727,
"step": 69
},
{
"epoch": 0.02416292716603383,
"grad_norm": 2.202164649963379,
"learning_rate": 2e-05,
"loss": 1.2887,
"step": 70
},
{
"epoch": 0.024508111839834312,
"grad_norm": 2.3834869861602783,
"learning_rate": 2e-05,
"loss": 1.2694,
"step": 71
},
{
"epoch": 0.024853296513634795,
"grad_norm": 2.5316550731658936,
"learning_rate": 2e-05,
"loss": 1.2514,
"step": 72
},
{
"epoch": 0.025198481187435277,
"grad_norm": 1.9449459314346313,
"learning_rate": 2e-05,
"loss": 1.26,
"step": 73
},
{
"epoch": 0.02554366586123576,
"grad_norm": 2.2826900482177734,
"learning_rate": 2e-05,
"loss": 1.2931,
"step": 74
},
{
"epoch": 0.025888850535036246,
"grad_norm": 2.260650396347046,
"learning_rate": 2e-05,
"loss": 1.2732,
"step": 75
},
{
"epoch": 0.02623403520883673,
"grad_norm": 2.356182336807251,
"learning_rate": 2e-05,
"loss": 1.2449,
"step": 76
},
{
"epoch": 0.02657921988263721,
"grad_norm": 2.199906826019287,
"learning_rate": 2e-05,
"loss": 1.2733,
"step": 77
},
{
"epoch": 0.026924404556437694,
"grad_norm": 2.3083510398864746,
"learning_rate": 2e-05,
"loss": 1.2257,
"step": 78
},
{
"epoch": 0.027269589230238176,
"grad_norm": 2.2658169269561768,
"learning_rate": 2e-05,
"loss": 1.2525,
"step": 79
},
{
"epoch": 0.027614773904038662,
"grad_norm": 2.352308988571167,
"learning_rate": 2e-05,
"loss": 1.2202,
"step": 80
},
{
"epoch": 0.027959958577839145,
"grad_norm": 2.523381471633911,
"learning_rate": 2e-05,
"loss": 1.2996,
"step": 81
},
{
"epoch": 0.028305143251639627,
"grad_norm": 2.4327428340911865,
"learning_rate": 2e-05,
"loss": 1.2135,
"step": 82
},
{
"epoch": 0.02865032792544011,
"grad_norm": 2.4549570083618164,
"learning_rate": 2e-05,
"loss": 1.2813,
"step": 83
},
{
"epoch": 0.028995512599240592,
"grad_norm": 2.4394640922546387,
"learning_rate": 2e-05,
"loss": 1.2828,
"step": 84
},
{
"epoch": 0.029340697273041078,
"grad_norm": 2.4780633449554443,
"learning_rate": 2e-05,
"loss": 1.2517,
"step": 85
},
{
"epoch": 0.02968588194684156,
"grad_norm": 2.326880931854248,
"learning_rate": 2e-05,
"loss": 1.2288,
"step": 86
},
{
"epoch": 0.030031066620642043,
"grad_norm": 3.1833627223968506,
"learning_rate": 2e-05,
"loss": 1.1978,
"step": 87
},
{
"epoch": 0.030376251294442526,
"grad_norm": 2.624091625213623,
"learning_rate": 2e-05,
"loss": 1.2534,
"step": 88
},
{
"epoch": 0.03072143596824301,
"grad_norm": 2.531895160675049,
"learning_rate": 2e-05,
"loss": 1.2263,
"step": 89
},
{
"epoch": 0.031066620642043494,
"grad_norm": 2.2346715927124023,
"learning_rate": 2e-05,
"loss": 1.2301,
"step": 90
},
{
"epoch": 0.03141180531584398,
"grad_norm": 2.237839698791504,
"learning_rate": 2e-05,
"loss": 1.1897,
"step": 91
},
{
"epoch": 0.03175698998964446,
"grad_norm": 2.4267807006835938,
"learning_rate": 2e-05,
"loss": 1.2508,
"step": 92
},
{
"epoch": 0.03210217466344494,
"grad_norm": 2.2506682872772217,
"learning_rate": 2e-05,
"loss": 1.2262,
"step": 93
},
{
"epoch": 0.03244735933724543,
"grad_norm": 2.5266077518463135,
"learning_rate": 2e-05,
"loss": 1.3139,
"step": 94
},
{
"epoch": 0.03279254401104591,
"grad_norm": 2.2002406120300293,
"learning_rate": 2e-05,
"loss": 1.2755,
"step": 95
},
{
"epoch": 0.03313772868484639,
"grad_norm": 2.20263409614563,
"learning_rate": 2e-05,
"loss": 1.2388,
"step": 96
},
{
"epoch": 0.03348291335864688,
"grad_norm": 2.297576665878296,
"learning_rate": 2e-05,
"loss": 1.2406,
"step": 97
},
{
"epoch": 0.03382809803244736,
"grad_norm": 2.3951361179351807,
"learning_rate": 2e-05,
"loss": 1.2244,
"step": 98
},
{
"epoch": 0.034173282706247844,
"grad_norm": 2.2707271575927734,
"learning_rate": 2e-05,
"loss": 1.2719,
"step": 99
},
{
"epoch": 0.03451846738004832,
"grad_norm": 2.2766411304473877,
"learning_rate": 2e-05,
"loss": 1.23,
"step": 100
},
{
"epoch": 0.03486365205384881,
"grad_norm": 2.253887414932251,
"learning_rate": 2e-05,
"loss": 1.1369,
"step": 101
},
{
"epoch": 0.035208836727649295,
"grad_norm": 2.0003821849823,
"learning_rate": 2e-05,
"loss": 1.2547,
"step": 102
},
{
"epoch": 0.035554021401449774,
"grad_norm": 2.277153253555298,
"learning_rate": 2e-05,
"loss": 1.2244,
"step": 103
},
{
"epoch": 0.03589920607525026,
"grad_norm": 2.1561081409454346,
"learning_rate": 2e-05,
"loss": 1.2222,
"step": 104
},
{
"epoch": 0.03624439074905074,
"grad_norm": 2.0002012252807617,
"learning_rate": 2e-05,
"loss": 1.1599,
"step": 105
},
{
"epoch": 0.036589575422851225,
"grad_norm": 2.3313021659851074,
"learning_rate": 2e-05,
"loss": 1.1658,
"step": 106
},
{
"epoch": 0.03693476009665171,
"grad_norm": 2.58686900138855,
"learning_rate": 2e-05,
"loss": 1.2282,
"step": 107
},
{
"epoch": 0.03727994477045219,
"grad_norm": 2.485671043395996,
"learning_rate": 2e-05,
"loss": 1.1537,
"step": 108
},
{
"epoch": 0.037625129444252677,
"grad_norm": 2.3962278366088867,
"learning_rate": 2e-05,
"loss": 1.133,
"step": 109
},
{
"epoch": 0.037970314118053156,
"grad_norm": 2.118319034576416,
"learning_rate": 2e-05,
"loss": 1.1769,
"step": 110
},
{
"epoch": 0.03831549879185364,
"grad_norm": 2.095940113067627,
"learning_rate": 2e-05,
"loss": 1.1763,
"step": 111
},
{
"epoch": 0.03866068346565413,
"grad_norm": 2.0862512588500977,
"learning_rate": 2e-05,
"loss": 1.1356,
"step": 112
},
{
"epoch": 0.03900586813945461,
"grad_norm": 1.9276546239852905,
"learning_rate": 2e-05,
"loss": 1.2068,
"step": 113
},
{
"epoch": 0.03935105281325509,
"grad_norm": 2.5604825019836426,
"learning_rate": 2e-05,
"loss": 1.16,
"step": 114
},
{
"epoch": 0.03969623748705557,
"grad_norm": 2.200289726257324,
"learning_rate": 2e-05,
"loss": 1.1811,
"step": 115
},
{
"epoch": 0.04004142216085606,
"grad_norm": 2.2654318809509277,
"learning_rate": 2e-05,
"loss": 1.2745,
"step": 116
},
{
"epoch": 0.040386606834656544,
"grad_norm": 2.194129228591919,
"learning_rate": 2e-05,
"loss": 1.1633,
"step": 117
},
{
"epoch": 0.04073179150845702,
"grad_norm": 2.267609119415283,
"learning_rate": 2e-05,
"loss": 1.1025,
"step": 118
},
{
"epoch": 0.04107697618225751,
"grad_norm": 2.3966379165649414,
"learning_rate": 2e-05,
"loss": 1.1624,
"step": 119
},
{
"epoch": 0.04142216085605799,
"grad_norm": 2.3428127765655518,
"learning_rate": 2e-05,
"loss": 1.2521,
"step": 120
},
{
"epoch": 0.041767345529858474,
"grad_norm": 2.257154941558838,
"learning_rate": 2e-05,
"loss": 1.1427,
"step": 121
},
{
"epoch": 0.04211253020365896,
"grad_norm": 2.4615261554718018,
"learning_rate": 2e-05,
"loss": 1.209,
"step": 122
},
{
"epoch": 0.04245771487745944,
"grad_norm": 2.215366840362549,
"learning_rate": 2e-05,
"loss": 1.1213,
"step": 123
},
{
"epoch": 0.042802899551259925,
"grad_norm": 2.293936014175415,
"learning_rate": 2e-05,
"loss": 1.1118,
"step": 124
},
{
"epoch": 0.043148084225060404,
"grad_norm": 2.351991653442383,
"learning_rate": 2e-05,
"loss": 1.1849,
"step": 125
},
{
"epoch": 0.04349326889886089,
"grad_norm": 2.118906259536743,
"learning_rate": 2e-05,
"loss": 1.1905,
"step": 126
},
{
"epoch": 0.043838453572661376,
"grad_norm": 2.1108460426330566,
"learning_rate": 2e-05,
"loss": 1.1787,
"step": 127
},
{
"epoch": 0.044183638246461855,
"grad_norm": 2.560715436935425,
"learning_rate": 2e-05,
"loss": 1.0727,
"step": 128
},
{
"epoch": 0.04452882292026234,
"grad_norm": 1.9983900785446167,
"learning_rate": 2e-05,
"loss": 1.1665,
"step": 129
},
{
"epoch": 0.04487400759406282,
"grad_norm": 2.3714847564697266,
"learning_rate": 2e-05,
"loss": 1.1488,
"step": 130
},
{
"epoch": 0.045219192267863306,
"grad_norm": 2.243546724319458,
"learning_rate": 2e-05,
"loss": 1.0965,
"step": 131
},
{
"epoch": 0.04556437694166379,
"grad_norm": 1.989858627319336,
"learning_rate": 2e-05,
"loss": 1.0833,
"step": 132
},
{
"epoch": 0.04590956161546427,
"grad_norm": 2.298943519592285,
"learning_rate": 2e-05,
"loss": 1.1548,
"step": 133
},
{
"epoch": 0.04625474628926476,
"grad_norm": 2.256289005279541,
"learning_rate": 2e-05,
"loss": 1.1139,
"step": 134
},
{
"epoch": 0.04659993096306524,
"grad_norm": 2.386530876159668,
"learning_rate": 2e-05,
"loss": 1.1245,
"step": 135
},
{
"epoch": 0.04694511563686572,
"grad_norm": 2.073687791824341,
"learning_rate": 2e-05,
"loss": 1.1337,
"step": 136
},
{
"epoch": 0.04729030031066621,
"grad_norm": 2.307697057723999,
"learning_rate": 2e-05,
"loss": 1.1325,
"step": 137
},
{
"epoch": 0.04763548498446669,
"grad_norm": 2.1158194541931152,
"learning_rate": 2e-05,
"loss": 1.1637,
"step": 138
},
{
"epoch": 0.047980669658267174,
"grad_norm": 2.21449613571167,
"learning_rate": 2e-05,
"loss": 1.1802,
"step": 139
},
{
"epoch": 0.04832585433206766,
"grad_norm": 2.041476249694824,
"learning_rate": 2e-05,
"loss": 1.1007,
"step": 140
},
{
"epoch": 0.04867103900586814,
"grad_norm": 2.262849807739258,
"learning_rate": 2e-05,
"loss": 1.1006,
"step": 141
},
{
"epoch": 0.049016223679668625,
"grad_norm": 2.207761287689209,
"learning_rate": 2e-05,
"loss": 1.133,
"step": 142
},
{
"epoch": 0.049361408353469104,
"grad_norm": 2.083613872528076,
"learning_rate": 2e-05,
"loss": 1.1319,
"step": 143
},
{
"epoch": 0.04970659302726959,
"grad_norm": 2.1225838661193848,
"learning_rate": 2e-05,
"loss": 1.0786,
"step": 144
},
{
"epoch": 0.050051777701070076,
"grad_norm": 2.17154598236084,
"learning_rate": 2e-05,
"loss": 1.2138,
"step": 145
},
{
"epoch": 0.050396962374870555,
"grad_norm": 2.655251979827881,
"learning_rate": 2e-05,
"loss": 1.1639,
"step": 146
},
{
"epoch": 0.05074214704867104,
"grad_norm": 2.241605758666992,
"learning_rate": 2e-05,
"loss": 1.1345,
"step": 147
},
{
"epoch": 0.05108733172247152,
"grad_norm": 2.397520065307617,
"learning_rate": 2e-05,
"loss": 1.1592,
"step": 148
},
{
"epoch": 0.051432516396272006,
"grad_norm": 2.2444629669189453,
"learning_rate": 2e-05,
"loss": 1.134,
"step": 149
},
{
"epoch": 0.05177770107007249,
"grad_norm": 2.179332971572876,
"learning_rate": 2e-05,
"loss": 1.1726,
"step": 150
},
{
"epoch": 0.05212288574387297,
"grad_norm": 2.1803085803985596,
"learning_rate": 2e-05,
"loss": 1.1458,
"step": 151
},
{
"epoch": 0.05246807041767346,
"grad_norm": 2.06752872467041,
"learning_rate": 2e-05,
"loss": 1.1741,
"step": 152
},
{
"epoch": 0.052813255091473936,
"grad_norm": 1.9567921161651611,
"learning_rate": 2e-05,
"loss": 1.1783,
"step": 153
},
{
"epoch": 0.05315843976527442,
"grad_norm": 1.8780710697174072,
"learning_rate": 2e-05,
"loss": 1.0461,
"step": 154
},
{
"epoch": 0.05350362443907491,
"grad_norm": 2.142355442047119,
"learning_rate": 2e-05,
"loss": 1.1683,
"step": 155
},
{
"epoch": 0.05384880911287539,
"grad_norm": 2.404834270477295,
"learning_rate": 2e-05,
"loss": 1.1367,
"step": 156
},
{
"epoch": 0.05419399378667587,
"grad_norm": 2.467586040496826,
"learning_rate": 2e-05,
"loss": 1.0616,
"step": 157
},
{
"epoch": 0.05453917846047635,
"grad_norm": 2.428678035736084,
"learning_rate": 2e-05,
"loss": 1.1587,
"step": 158
},
{
"epoch": 0.05488436313427684,
"grad_norm": 1.9721519947052002,
"learning_rate": 2e-05,
"loss": 1.0864,
"step": 159
},
{
"epoch": 0.055229547808077324,
"grad_norm": 2.282735586166382,
"learning_rate": 2e-05,
"loss": 1.1805,
"step": 160
},
{
"epoch": 0.0555747324818778,
"grad_norm": 2.136899471282959,
"learning_rate": 2e-05,
"loss": 1.0941,
"step": 161
},
{
"epoch": 0.05591991715567829,
"grad_norm": 2.0251846313476562,
"learning_rate": 2e-05,
"loss": 1.0796,
"step": 162
},
{
"epoch": 0.05626510182947877,
"grad_norm": 2.1328299045562744,
"learning_rate": 2e-05,
"loss": 1.0917,
"step": 163
},
{
"epoch": 0.056610286503279254,
"grad_norm": 2.205331802368164,
"learning_rate": 2e-05,
"loss": 1.1792,
"step": 164
},
{
"epoch": 0.05695547117707974,
"grad_norm": 2.0339744091033936,
"learning_rate": 2e-05,
"loss": 1.1874,
"step": 165
},
{
"epoch": 0.05730065585088022,
"grad_norm": 1.8030365705490112,
"learning_rate": 2e-05,
"loss": 1.0929,
"step": 166
},
{
"epoch": 0.057645840524680705,
"grad_norm": 2.1905670166015625,
"learning_rate": 2e-05,
"loss": 1.1831,
"step": 167
},
{
"epoch": 0.057991025198481184,
"grad_norm": 2.142336845397949,
"learning_rate": 2e-05,
"loss": 1.1237,
"step": 168
},
{
"epoch": 0.05833620987228167,
"grad_norm": 2.3521053791046143,
"learning_rate": 2e-05,
"loss": 1.1077,
"step": 169
},
{
"epoch": 0.058681394546082156,
"grad_norm": 2.105743408203125,
"learning_rate": 2e-05,
"loss": 1.1048,
"step": 170
},
{
"epoch": 0.059026579219882636,
"grad_norm": 1.9414738416671753,
"learning_rate": 2e-05,
"loss": 1.112,
"step": 171
},
{
"epoch": 0.05937176389368312,
"grad_norm": 1.9606658220291138,
"learning_rate": 2e-05,
"loss": 1.1109,
"step": 172
},
{
"epoch": 0.0597169485674836,
"grad_norm": 2.3274831771850586,
"learning_rate": 2e-05,
"loss": 1.1803,
"step": 173
},
{
"epoch": 0.06006213324128409,
"grad_norm": 2.1384570598602295,
"learning_rate": 2e-05,
"loss": 1.0515,
"step": 174
},
{
"epoch": 0.06040731791508457,
"grad_norm": 2.0795719623565674,
"learning_rate": 2e-05,
"loss": 1.0581,
"step": 175
},
{
"epoch": 0.06075250258888505,
"grad_norm": 2.0180423259735107,
"learning_rate": 2e-05,
"loss": 1.0686,
"step": 176
},
{
"epoch": 0.06109768726268554,
"grad_norm": 2.0913267135620117,
"learning_rate": 2e-05,
"loss": 1.117,
"step": 177
},
{
"epoch": 0.06144287193648602,
"grad_norm": 2.0325934886932373,
"learning_rate": 2e-05,
"loss": 1.1526,
"step": 178
},
{
"epoch": 0.0617880566102865,
"grad_norm": 2.222254991531372,
"learning_rate": 2e-05,
"loss": 1.113,
"step": 179
},
{
"epoch": 0.06213324128408699,
"grad_norm": 2.2039270401000977,
"learning_rate": 2e-05,
"loss": 1.1886,
"step": 180
},
{
"epoch": 0.06247842595788747,
"grad_norm": 2.0291781425476074,
"learning_rate": 2e-05,
"loss": 1.0884,
"step": 181
},
{
"epoch": 0.06282361063168795,
"grad_norm": 2.2183430194854736,
"learning_rate": 2e-05,
"loss": 1.0223,
"step": 182
},
{
"epoch": 0.06316879530548844,
"grad_norm": 2.37440824508667,
"learning_rate": 2e-05,
"loss": 1.0775,
"step": 183
},
{
"epoch": 0.06351397997928893,
"grad_norm": 1.8214384317398071,
"learning_rate": 2e-05,
"loss": 1.1279,
"step": 184
},
{
"epoch": 0.0638591646530894,
"grad_norm": 2.205291271209717,
"learning_rate": 2e-05,
"loss": 1.0396,
"step": 185
},
{
"epoch": 0.06420434932688988,
"grad_norm": 2.137577533721924,
"learning_rate": 2e-05,
"loss": 1.0861,
"step": 186
},
{
"epoch": 0.06454953400069037,
"grad_norm": 1.982663869857788,
"learning_rate": 2e-05,
"loss": 1.1612,
"step": 187
},
{
"epoch": 0.06489471867449086,
"grad_norm": 21.140506744384766,
"learning_rate": 2e-05,
"loss": 1.0824,
"step": 188
},
{
"epoch": 0.06523990334829134,
"grad_norm": 2.2611193656921387,
"learning_rate": 2e-05,
"loss": 1.0795,
"step": 189
},
{
"epoch": 0.06558508802209181,
"grad_norm": 2.0905325412750244,
"learning_rate": 2e-05,
"loss": 1.1989,
"step": 190
},
{
"epoch": 0.0659302726958923,
"grad_norm": 1.9430997371673584,
"learning_rate": 2e-05,
"loss": 1.0885,
"step": 191
},
{
"epoch": 0.06627545736969279,
"grad_norm": 1.8876497745513916,
"learning_rate": 2e-05,
"loss": 1.0708,
"step": 192
},
{
"epoch": 0.06662064204349327,
"grad_norm": 2.0716099739074707,
"learning_rate": 2e-05,
"loss": 1.124,
"step": 193
},
{
"epoch": 0.06696582671729376,
"grad_norm": 2.413959503173828,
"learning_rate": 2e-05,
"loss": 1.1856,
"step": 194
},
{
"epoch": 0.06731101139109423,
"grad_norm": 1.8021107912063599,
"learning_rate": 2e-05,
"loss": 1.1284,
"step": 195
},
{
"epoch": 0.06765619606489472,
"grad_norm": 2.2795395851135254,
"learning_rate": 2e-05,
"loss": 1.1101,
"step": 196
},
{
"epoch": 0.0680013807386952,
"grad_norm": 1.936448097229004,
"learning_rate": 2e-05,
"loss": 1.0921,
"step": 197
},
{
"epoch": 0.06834656541249569,
"grad_norm": 1.940928339958191,
"learning_rate": 2e-05,
"loss": 1.1236,
"step": 198
},
{
"epoch": 0.06869175008629617,
"grad_norm": 2.1147520542144775,
"learning_rate": 2e-05,
"loss": 1.0332,
"step": 199
},
{
"epoch": 0.06903693476009665,
"grad_norm": 1.9784513711929321,
"learning_rate": 2e-05,
"loss": 1.0644,
"step": 200
},
{
"epoch": 0.06938211943389713,
"grad_norm": 2.135711431503296,
"learning_rate": 2e-05,
"loss": 1.0189,
"step": 201
},
{
"epoch": 0.06972730410769762,
"grad_norm": 2.3416550159454346,
"learning_rate": 2e-05,
"loss": 1.0788,
"step": 202
},
{
"epoch": 0.0700724887814981,
"grad_norm": 2.143134593963623,
"learning_rate": 2e-05,
"loss": 1.0657,
"step": 203
},
{
"epoch": 0.07041767345529859,
"grad_norm": 9.058279991149902,
"learning_rate": 2e-05,
"loss": 1.0657,
"step": 204
},
{
"epoch": 0.07076285812909906,
"grad_norm": 2.2367799282073975,
"learning_rate": 2e-05,
"loss": 1.0822,
"step": 205
},
{
"epoch": 0.07110804280289955,
"grad_norm": 1.9047443866729736,
"learning_rate": 2e-05,
"loss": 1.0999,
"step": 206
},
{
"epoch": 0.07145322747670003,
"grad_norm": 2.307863473892212,
"learning_rate": 2e-05,
"loss": 1.1275,
"step": 207
},
{
"epoch": 0.07179841215050052,
"grad_norm": 2.0635058879852295,
"learning_rate": 2e-05,
"loss": 1.0477,
"step": 208
},
{
"epoch": 0.072143596824301,
"grad_norm": 2.144148111343384,
"learning_rate": 2e-05,
"loss": 1.0351,
"step": 209
},
{
"epoch": 0.07248878149810148,
"grad_norm": 1.9361531734466553,
"learning_rate": 2e-05,
"loss": 1.0704,
"step": 210
},
{
"epoch": 0.07283396617190196,
"grad_norm": 1.8395414352416992,
"learning_rate": 2e-05,
"loss": 1.1099,
"step": 211
},
{
"epoch": 0.07317915084570245,
"grad_norm": 2.1172099113464355,
"learning_rate": 2e-05,
"loss": 1.1169,
"step": 212
},
{
"epoch": 0.07352433551950294,
"grad_norm": 2.084325075149536,
"learning_rate": 2e-05,
"loss": 1.0347,
"step": 213
},
{
"epoch": 0.07386952019330342,
"grad_norm": 2.1838455200195312,
"learning_rate": 2e-05,
"loss": 1.0926,
"step": 214
},
{
"epoch": 0.0742147048671039,
"grad_norm": 2.1516849994659424,
"learning_rate": 2e-05,
"loss": 1.082,
"step": 215
},
{
"epoch": 0.07455988954090438,
"grad_norm": 2.011460781097412,
"learning_rate": 2e-05,
"loss": 1.073,
"step": 216
},
{
"epoch": 0.07490507421470487,
"grad_norm": 2.2096571922302246,
"learning_rate": 2e-05,
"loss": 1.1239,
"step": 217
},
{
"epoch": 0.07525025888850535,
"grad_norm": 2.088879346847534,
"learning_rate": 2e-05,
"loss": 1.1313,
"step": 218
},
{
"epoch": 0.07559544356230584,
"grad_norm": 2.0846405029296875,
"learning_rate": 2e-05,
"loss": 0.9951,
"step": 219
},
{
"epoch": 0.07594062823610631,
"grad_norm": 1.9645204544067383,
"learning_rate": 2e-05,
"loss": 1.0431,
"step": 220
},
{
"epoch": 0.0762858129099068,
"grad_norm": 2.1063179969787598,
"learning_rate": 2e-05,
"loss": 1.0659,
"step": 221
},
{
"epoch": 0.07663099758370728,
"grad_norm": 2.0268285274505615,
"learning_rate": 2e-05,
"loss": 1.0909,
"step": 222
},
{
"epoch": 0.07697618225750777,
"grad_norm": 1.9405102729797363,
"learning_rate": 2e-05,
"loss": 1.0,
"step": 223
},
{
"epoch": 0.07732136693130826,
"grad_norm": 2.1061298847198486,
"learning_rate": 2e-05,
"loss": 1.083,
"step": 224
},
{
"epoch": 0.07766655160510873,
"grad_norm": 2.07513165473938,
"learning_rate": 2e-05,
"loss": 1.0872,
"step": 225
},
{
"epoch": 0.07801173627890921,
"grad_norm": 2.2630527019500732,
"learning_rate": 2e-05,
"loss": 1.0296,
"step": 226
},
{
"epoch": 0.0783569209527097,
"grad_norm": 2.0668439865112305,
"learning_rate": 2e-05,
"loss": 1.1433,
"step": 227
},
{
"epoch": 0.07870210562651019,
"grad_norm": 2.3092525005340576,
"learning_rate": 2e-05,
"loss": 1.0347,
"step": 228
},
{
"epoch": 0.07904729030031067,
"grad_norm": 2.0190646648406982,
"learning_rate": 2e-05,
"loss": 1.0423,
"step": 229
},
{
"epoch": 0.07939247497411114,
"grad_norm": 2.0675878524780273,
"learning_rate": 2e-05,
"loss": 1.1551,
"step": 230
},
{
"epoch": 0.07973765964791163,
"grad_norm": 2.282857894897461,
"learning_rate": 2e-05,
"loss": 1.043,
"step": 231
},
{
"epoch": 0.08008284432171212,
"grad_norm": 1.886343240737915,
"learning_rate": 2e-05,
"loss": 1.0244,
"step": 232
},
{
"epoch": 0.0804280289955126,
"grad_norm": 2.2882308959960938,
"learning_rate": 2e-05,
"loss": 1.0228,
"step": 233
},
{
"epoch": 0.08077321366931309,
"grad_norm": 2.05058217048645,
"learning_rate": 2e-05,
"loss": 1.0567,
"step": 234
},
{
"epoch": 0.08111839834311356,
"grad_norm": 2.2782809734344482,
"learning_rate": 2e-05,
"loss": 1.0744,
"step": 235
},
{
"epoch": 0.08146358301691405,
"grad_norm": 1.9740854501724243,
"learning_rate": 2e-05,
"loss": 1.0601,
"step": 236
},
{
"epoch": 0.08180876769071453,
"grad_norm": 2.08333158493042,
"learning_rate": 2e-05,
"loss": 1.0873,
"step": 237
},
{
"epoch": 0.08215395236451502,
"grad_norm": 2.0546019077301025,
"learning_rate": 2e-05,
"loss": 1.088,
"step": 238
},
{
"epoch": 0.0824991370383155,
"grad_norm": 1.9426814317703247,
"learning_rate": 2e-05,
"loss": 1.0512,
"step": 239
},
{
"epoch": 0.08284432171211598,
"grad_norm": 2.0802295207977295,
"learning_rate": 2e-05,
"loss": 1.1123,
"step": 240
},
{
"epoch": 0.08318950638591646,
"grad_norm": 2.010526657104492,
"learning_rate": 2e-05,
"loss": 1.0883,
"step": 241
},
{
"epoch": 0.08353469105971695,
"grad_norm": 2.083188056945801,
"learning_rate": 2e-05,
"loss": 1.0987,
"step": 242
},
{
"epoch": 0.08387987573351743,
"grad_norm": 2.137660264968872,
"learning_rate": 2e-05,
"loss": 0.9924,
"step": 243
},
{
"epoch": 0.08422506040731792,
"grad_norm": 2.041710376739502,
"learning_rate": 2e-05,
"loss": 1.1403,
"step": 244
},
{
"epoch": 0.08457024508111839,
"grad_norm": 2.0598714351654053,
"learning_rate": 2e-05,
"loss": 1.02,
"step": 245
},
{
"epoch": 0.08491542975491888,
"grad_norm": 2.168576955795288,
"learning_rate": 2e-05,
"loss": 1.0771,
"step": 246
},
{
"epoch": 0.08526061442871936,
"grad_norm": 2.145132303237915,
"learning_rate": 2e-05,
"loss": 1.0746,
"step": 247
},
{
"epoch": 0.08560579910251985,
"grad_norm": 2.24804425239563,
"learning_rate": 2e-05,
"loss": 1.0898,
"step": 248
},
{
"epoch": 0.08595098377632034,
"grad_norm": 1.8360575437545776,
"learning_rate": 2e-05,
"loss": 1.0741,
"step": 249
},
{
"epoch": 0.08629616845012081,
"grad_norm": 2.1169514656066895,
"learning_rate": 2e-05,
"loss": 1.1025,
"step": 250
},
{
"epoch": 0.0866413531239213,
"grad_norm": 1.929721474647522,
"learning_rate": 2e-05,
"loss": 1.0455,
"step": 251
},
{
"epoch": 0.08698653779772178,
"grad_norm": 5.5121026039123535,
"learning_rate": 2e-05,
"loss": 1.07,
"step": 252
},
{
"epoch": 0.08733172247152227,
"grad_norm": 2.2410662174224854,
"learning_rate": 2e-05,
"loss": 1.1145,
"step": 253
},
{
"epoch": 0.08767690714532275,
"grad_norm": 2.027545213699341,
"learning_rate": 2e-05,
"loss": 0.9882,
"step": 254
},
{
"epoch": 0.08802209181912322,
"grad_norm": 2.0337374210357666,
"learning_rate": 2e-05,
"loss": 0.999,
"step": 255
},
{
"epoch": 0.08836727649292371,
"grad_norm": 2.1120731830596924,
"learning_rate": 2e-05,
"loss": 1.0424,
"step": 256
},
{
"epoch": 0.0887124611667242,
"grad_norm": 2.039837121963501,
"learning_rate": 2e-05,
"loss": 1.0316,
"step": 257
},
{
"epoch": 0.08905764584052468,
"grad_norm": 2.008521318435669,
"learning_rate": 2e-05,
"loss": 1.019,
"step": 258
},
{
"epoch": 0.08940283051432517,
"grad_norm": 2.081023693084717,
"learning_rate": 2e-05,
"loss": 1.003,
"step": 259
},
{
"epoch": 0.08974801518812564,
"grad_norm": 4.9017229080200195,
"learning_rate": 2e-05,
"loss": 1.1215,
"step": 260
},
{
"epoch": 0.09009319986192613,
"grad_norm": 2.0149810314178467,
"learning_rate": 2e-05,
"loss": 1.0643,
"step": 261
},
{
"epoch": 0.09043838453572661,
"grad_norm": 2.0311553478240967,
"learning_rate": 2e-05,
"loss": 1.0287,
"step": 262
},
{
"epoch": 0.0907835692095271,
"grad_norm": 2.089172124862671,
"learning_rate": 2e-05,
"loss": 1.0435,
"step": 263
},
{
"epoch": 0.09112875388332758,
"grad_norm": 2.233536720275879,
"learning_rate": 2e-05,
"loss": 1.0787,
"step": 264
},
{
"epoch": 0.09147393855712806,
"grad_norm": 2.050518035888672,
"learning_rate": 2e-05,
"loss": 1.0818,
"step": 265
},
{
"epoch": 0.09181912323092854,
"grad_norm": 2.117332935333252,
"learning_rate": 2e-05,
"loss": 1.0334,
"step": 266
},
{
"epoch": 0.09216430790472903,
"grad_norm": 2.1400556564331055,
"learning_rate": 2e-05,
"loss": 1.0997,
"step": 267
},
{
"epoch": 0.09250949257852951,
"grad_norm": 6.34127950668335,
"learning_rate": 2e-05,
"loss": 1.0854,
"step": 268
},
{
"epoch": 0.09285467725233,
"grad_norm": 2.346954584121704,
"learning_rate": 2e-05,
"loss": 1.041,
"step": 269
},
{
"epoch": 0.09319986192613049,
"grad_norm": 2.049189329147339,
"learning_rate": 2e-05,
"loss": 1.1082,
"step": 270
},
{
"epoch": 0.09354504659993096,
"grad_norm": 2.0327305793762207,
"learning_rate": 2e-05,
"loss": 1.0755,
"step": 271
},
{
"epoch": 0.09389023127373144,
"grad_norm": 2.1110620498657227,
"learning_rate": 2e-05,
"loss": 1.0721,
"step": 272
},
{
"epoch": 0.09423541594753193,
"grad_norm": 1.8782284259796143,
"learning_rate": 2e-05,
"loss": 0.9842,
"step": 273
},
{
"epoch": 0.09458060062133242,
"grad_norm": 1.8504958152770996,
"learning_rate": 2e-05,
"loss": 1.0183,
"step": 274
},
{
"epoch": 0.0949257852951329,
"grad_norm": 2.0672526359558105,
"learning_rate": 2e-05,
"loss": 1.0126,
"step": 275
},
{
"epoch": 0.09527096996893337,
"grad_norm": 2.104374885559082,
"learning_rate": 2e-05,
"loss": 1.0911,
"step": 276
},
{
"epoch": 0.09561615464273386,
"grad_norm": 1.9912065267562866,
"learning_rate": 2e-05,
"loss": 1.0659,
"step": 277
},
{
"epoch": 0.09596133931653435,
"grad_norm": 2.093083143234253,
"learning_rate": 2e-05,
"loss": 1.0771,
"step": 278
},
{
"epoch": 0.09630652399033483,
"grad_norm": 1.92844820022583,
"learning_rate": 2e-05,
"loss": 1.006,
"step": 279
},
{
"epoch": 0.09665170866413532,
"grad_norm": 1.7608734369277954,
"learning_rate": 2e-05,
"loss": 1.0353,
"step": 280
},
{
"epoch": 0.09699689333793579,
"grad_norm": 2.1199417114257812,
"learning_rate": 2e-05,
"loss": 1.0065,
"step": 281
},
{
"epoch": 0.09734207801173628,
"grad_norm": 1.7883626222610474,
"learning_rate": 2e-05,
"loss": 1.0815,
"step": 282
},
{
"epoch": 0.09768726268553676,
"grad_norm": 1.9652053117752075,
"learning_rate": 2e-05,
"loss": 1.0158,
"step": 283
},
{
"epoch": 0.09803244735933725,
"grad_norm": 2.1138057708740234,
"learning_rate": 2e-05,
"loss": 1.029,
"step": 284
},
{
"epoch": 0.09837763203313774,
"grad_norm": 2.0844762325286865,
"learning_rate": 2e-05,
"loss": 1.0783,
"step": 285
},
{
"epoch": 0.09872281670693821,
"grad_norm": 1.954588532447815,
"learning_rate": 2e-05,
"loss": 1.0256,
"step": 286
},
{
"epoch": 0.0990680013807387,
"grad_norm": 2.3191030025482178,
"learning_rate": 2e-05,
"loss": 1.1083,
"step": 287
},
{
"epoch": 0.09941318605453918,
"grad_norm": 2.0656120777130127,
"learning_rate": 2e-05,
"loss": 1.0798,
"step": 288
},
{
"epoch": 0.09975837072833967,
"grad_norm": 1.8802495002746582,
"learning_rate": 2e-05,
"loss": 1.0258,
"step": 289
},
{
"epoch": 0.10010355540214015,
"grad_norm": 2.062614917755127,
"learning_rate": 2e-05,
"loss": 1.0565,
"step": 290
},
{
"epoch": 0.10044874007594062,
"grad_norm": 2.0783498287200928,
"learning_rate": 2e-05,
"loss": 1.1027,
"step": 291
},
{
"epoch": 0.10079392474974111,
"grad_norm": 2.0610833168029785,
"learning_rate": 2e-05,
"loss": 1.0019,
"step": 292
},
{
"epoch": 0.1011391094235416,
"grad_norm": 2.029587745666504,
"learning_rate": 2e-05,
"loss": 1.0369,
"step": 293
},
{
"epoch": 0.10148429409734208,
"grad_norm": 1.8925073146820068,
"learning_rate": 2e-05,
"loss": 1.0196,
"step": 294
},
{
"epoch": 0.10182947877114257,
"grad_norm": 1.9382961988449097,
"learning_rate": 2e-05,
"loss": 1.0812,
"step": 295
},
{
"epoch": 0.10217466344494304,
"grad_norm": 1.8473429679870605,
"learning_rate": 2e-05,
"loss": 1.0407,
"step": 296
},
{
"epoch": 0.10251984811874353,
"grad_norm": 2.0330350399017334,
"learning_rate": 2e-05,
"loss": 1.0093,
"step": 297
},
{
"epoch": 0.10286503279254401,
"grad_norm": 2.0864484310150146,
"learning_rate": 2e-05,
"loss": 1.0155,
"step": 298
},
{
"epoch": 0.1032102174663445,
"grad_norm": 1.8072278499603271,
"learning_rate": 2e-05,
"loss": 1.0674,
"step": 299
},
{
"epoch": 0.10355540214014498,
"grad_norm": 2.2771360874176025,
"learning_rate": 2e-05,
"loss": 1.0345,
"step": 300
},
{
"epoch": 0.10390058681394546,
"grad_norm": 1.8649107217788696,
"learning_rate": 2e-05,
"loss": 0.9528,
"step": 301
},
{
"epoch": 0.10424577148774594,
"grad_norm": 1.751585841178894,
"learning_rate": 2e-05,
"loss": 0.9587,
"step": 302
},
{
"epoch": 0.10459095616154643,
"grad_norm": 2.0218489170074463,
"learning_rate": 2e-05,
"loss": 0.9844,
"step": 303
},
{
"epoch": 0.10493614083534691,
"grad_norm": 2.0804543495178223,
"learning_rate": 2e-05,
"loss": 1.0221,
"step": 304
},
{
"epoch": 0.1052813255091474,
"grad_norm": 2.1906816959381104,
"learning_rate": 2e-05,
"loss": 1.0347,
"step": 305
},
{
"epoch": 0.10562651018294787,
"grad_norm": 1.852725863456726,
"learning_rate": 2e-05,
"loss": 1.0482,
"step": 306
},
{
"epoch": 0.10597169485674836,
"grad_norm": 1.9083342552185059,
"learning_rate": 2e-05,
"loss": 1.0901,
"step": 307
},
{
"epoch": 0.10631687953054884,
"grad_norm": 2.0140769481658936,
"learning_rate": 2e-05,
"loss": 1.087,
"step": 308
},
{
"epoch": 0.10666206420434933,
"grad_norm": 1.8648165464401245,
"learning_rate": 2e-05,
"loss": 1.0129,
"step": 309
},
{
"epoch": 0.10700724887814982,
"grad_norm": 2.034452438354492,
"learning_rate": 2e-05,
"loss": 1.0424,
"step": 310
},
{
"epoch": 0.10735243355195029,
"grad_norm": 1.7214909791946411,
"learning_rate": 2e-05,
"loss": 1.0461,
"step": 311
},
{
"epoch": 0.10769761822575077,
"grad_norm": 2.31937575340271,
"learning_rate": 2e-05,
"loss": 1.0606,
"step": 312
},
{
"epoch": 0.10804280289955126,
"grad_norm": 1.9707671403884888,
"learning_rate": 2e-05,
"loss": 0.9882,
"step": 313
},
{
"epoch": 0.10838798757335175,
"grad_norm": 1.837477207183838,
"learning_rate": 2e-05,
"loss": 0.9285,
"step": 314
},
{
"epoch": 0.10873317224715223,
"grad_norm": 1.8579028844833374,
"learning_rate": 2e-05,
"loss": 1.0121,
"step": 315
},
{
"epoch": 0.1090783569209527,
"grad_norm": 1.8835140466690063,
"learning_rate": 2e-05,
"loss": 1.0724,
"step": 316
},
{
"epoch": 0.10942354159475319,
"grad_norm": 1.7847641706466675,
"learning_rate": 2e-05,
"loss": 1.0265,
"step": 317
},
{
"epoch": 0.10976872626855368,
"grad_norm": 2.0330307483673096,
"learning_rate": 2e-05,
"loss": 1.0218,
"step": 318
},
{
"epoch": 0.11011391094235416,
"grad_norm": 1.8466086387634277,
"learning_rate": 2e-05,
"loss": 1.0594,
"step": 319
},
{
"epoch": 0.11045909561615465,
"grad_norm": 1.884079933166504,
"learning_rate": 2e-05,
"loss": 1.0734,
"step": 320
},
{
"epoch": 0.11080428028995512,
"grad_norm": 1.8187580108642578,
"learning_rate": 2e-05,
"loss": 0.9995,
"step": 321
},
{
"epoch": 0.1111494649637556,
"grad_norm": 2.196646213531494,
"learning_rate": 2e-05,
"loss": 1.0265,
"step": 322
},
{
"epoch": 0.11149464963755609,
"grad_norm": 1.9797489643096924,
"learning_rate": 2e-05,
"loss": 1.0325,
"step": 323
},
{
"epoch": 0.11183983431135658,
"grad_norm": 2.0785601139068604,
"learning_rate": 2e-05,
"loss": 1.1051,
"step": 324
},
{
"epoch": 0.11218501898515706,
"grad_norm": 2.0432729721069336,
"learning_rate": 2e-05,
"loss": 1.0815,
"step": 325
},
{
"epoch": 0.11253020365895754,
"grad_norm": 2.0694308280944824,
"learning_rate": 2e-05,
"loss": 1.0851,
"step": 326
},
{
"epoch": 0.11287538833275802,
"grad_norm": 1.8386410474777222,
"learning_rate": 2e-05,
"loss": 1.0106,
"step": 327
},
{
"epoch": 0.11322057300655851,
"grad_norm": 2.018885850906372,
"learning_rate": 2e-05,
"loss": 1.0318,
"step": 328
},
{
"epoch": 0.113565757680359,
"grad_norm": 2.105708360671997,
"learning_rate": 2e-05,
"loss": 1.0567,
"step": 329
},
{
"epoch": 0.11391094235415948,
"grad_norm": 1.9204944372177124,
"learning_rate": 2e-05,
"loss": 1.0262,
"step": 330
},
{
"epoch": 0.11425612702795995,
"grad_norm": 1.9768996238708496,
"learning_rate": 2e-05,
"loss": 1.0085,
"step": 331
},
{
"epoch": 0.11460131170176044,
"grad_norm": 1.785104751586914,
"learning_rate": 2e-05,
"loss": 1.102,
"step": 332
},
{
"epoch": 0.11494649637556092,
"grad_norm": 2.0644032955169678,
"learning_rate": 2e-05,
"loss": 1.0617,
"step": 333
},
{
"epoch": 0.11529168104936141,
"grad_norm": 2.0390021800994873,
"learning_rate": 2e-05,
"loss": 0.9609,
"step": 334
},
{
"epoch": 0.1156368657231619,
"grad_norm": 1.919952392578125,
"learning_rate": 2e-05,
"loss": 1.0701,
"step": 335
},
{
"epoch": 0.11598205039696237,
"grad_norm": 1.8437055349349976,
"learning_rate": 2e-05,
"loss": 1.0486,
"step": 336
},
{
"epoch": 0.11632723507076285,
"grad_norm": 1.864856243133545,
"learning_rate": 2e-05,
"loss": 1.0564,
"step": 337
},
{
"epoch": 0.11667241974456334,
"grad_norm": 2.0349135398864746,
"learning_rate": 2e-05,
"loss": 0.9971,
"step": 338
},
{
"epoch": 0.11701760441836383,
"grad_norm": 2.007643461227417,
"learning_rate": 2e-05,
"loss": 0.986,
"step": 339
},
{
"epoch": 0.11736278909216431,
"grad_norm": 2.1241238117218018,
"learning_rate": 2e-05,
"loss": 1.0278,
"step": 340
},
{
"epoch": 0.11770797376596479,
"grad_norm": 1.960552453994751,
"learning_rate": 2e-05,
"loss": 1.057,
"step": 341
},
{
"epoch": 0.11805315843976527,
"grad_norm": 2.3228769302368164,
"learning_rate": 2e-05,
"loss": 1.029,
"step": 342
},
{
"epoch": 0.11839834311356576,
"grad_norm": 1.9010450839996338,
"learning_rate": 2e-05,
"loss": 0.9918,
"step": 343
},
{
"epoch": 0.11874352778736624,
"grad_norm": 1.9832115173339844,
"learning_rate": 2e-05,
"loss": 0.9904,
"step": 344
},
{
"epoch": 0.11908871246116673,
"grad_norm": 2.176405668258667,
"learning_rate": 2e-05,
"loss": 1.0155,
"step": 345
},
{
"epoch": 0.1194338971349672,
"grad_norm": 2.0718116760253906,
"learning_rate": 2e-05,
"loss": 1.0706,
"step": 346
},
{
"epoch": 0.11977908180876769,
"grad_norm": 2.000976085662842,
"learning_rate": 2e-05,
"loss": 0.9916,
"step": 347
},
{
"epoch": 0.12012426648256817,
"grad_norm": 1.9181327819824219,
"learning_rate": 2e-05,
"loss": 1.0556,
"step": 348
},
{
"epoch": 0.12046945115636866,
"grad_norm": 1.7830644845962524,
"learning_rate": 2e-05,
"loss": 0.9755,
"step": 349
},
{
"epoch": 0.12081463583016915,
"grad_norm": 2.0355966091156006,
"learning_rate": 2e-05,
"loss": 1.0421,
"step": 350
},
{
"epoch": 0.12115982050396962,
"grad_norm": 1.8209973573684692,
"learning_rate": 2e-05,
"loss": 1.0213,
"step": 351
},
{
"epoch": 0.1215050051777701,
"grad_norm": 1.9484202861785889,
"learning_rate": 2e-05,
"loss": 1.11,
"step": 352
},
{
"epoch": 0.12185018985157059,
"grad_norm": 1.959164023399353,
"learning_rate": 2e-05,
"loss": 1.0318,
"step": 353
},
{
"epoch": 0.12219537452537108,
"grad_norm": 1.893936276435852,
"learning_rate": 2e-05,
"loss": 1.0534,
"step": 354
},
{
"epoch": 0.12254055919917156,
"grad_norm": 1.9669185876846313,
"learning_rate": 2e-05,
"loss": 0.9959,
"step": 355
},
{
"epoch": 0.12288574387297203,
"grad_norm": 2.152151584625244,
"learning_rate": 2e-05,
"loss": 1.0081,
"step": 356
},
{
"epoch": 0.12323092854677252,
"grad_norm": 2.203021764755249,
"learning_rate": 2e-05,
"loss": 1.0443,
"step": 357
},
{
"epoch": 0.123576113220573,
"grad_norm": 2.069221258163452,
"learning_rate": 2e-05,
"loss": 1.0519,
"step": 358
},
{
"epoch": 0.12392129789437349,
"grad_norm": 2.054393768310547,
"learning_rate": 2e-05,
"loss": 1.0314,
"step": 359
},
{
"epoch": 0.12426648256817398,
"grad_norm": 2.0708425045013428,
"learning_rate": 2e-05,
"loss": 0.9856,
"step": 360
},
{
"epoch": 0.12461166724197445,
"grad_norm": 2.4350380897521973,
"learning_rate": 2e-05,
"loss": 0.9796,
"step": 361
},
{
"epoch": 0.12495685191577494,
"grad_norm": 1.8085037469863892,
"learning_rate": 2e-05,
"loss": 0.9932,
"step": 362
},
{
"epoch": 0.12530203658957542,
"grad_norm": 1.824069619178772,
"learning_rate": 2e-05,
"loss": 1.024,
"step": 363
},
{
"epoch": 0.1256472212633759,
"grad_norm": 2.675426959991455,
"learning_rate": 2e-05,
"loss": 1.0231,
"step": 364
},
{
"epoch": 0.1259924059371764,
"grad_norm": 2.127661943435669,
"learning_rate": 2e-05,
"loss": 1.043,
"step": 365
},
{
"epoch": 0.12633759061097688,
"grad_norm": 1.9300974607467651,
"learning_rate": 2e-05,
"loss": 1.0163,
"step": 366
},
{
"epoch": 0.12668277528477737,
"grad_norm": 1.984744668006897,
"learning_rate": 2e-05,
"loss": 1.0101,
"step": 367
},
{
"epoch": 0.12702795995857785,
"grad_norm": 1.9173483848571777,
"learning_rate": 2e-05,
"loss": 1.0672,
"step": 368
},
{
"epoch": 0.1273731446323783,
"grad_norm": 2.148045778274536,
"learning_rate": 2e-05,
"loss": 1.0037,
"step": 369
},
{
"epoch": 0.1277183293061788,
"grad_norm": 2.0799989700317383,
"learning_rate": 2e-05,
"loss": 1.0067,
"step": 370
},
{
"epoch": 0.12806351397997928,
"grad_norm": 1.5450844764709473,
"learning_rate": 2e-05,
"loss": 0.9314,
"step": 371
},
{
"epoch": 0.12840869865377977,
"grad_norm": 2.0938477516174316,
"learning_rate": 2e-05,
"loss": 1.0326,
"step": 372
},
{
"epoch": 0.12875388332758025,
"grad_norm": 2.148625612258911,
"learning_rate": 2e-05,
"loss": 1.006,
"step": 373
},
{
"epoch": 0.12909906800138074,
"grad_norm": 1.964438796043396,
"learning_rate": 2e-05,
"loss": 0.9921,
"step": 374
},
{
"epoch": 0.12944425267518123,
"grad_norm": 1.7084150314331055,
"learning_rate": 2e-05,
"loss": 1.0276,
"step": 375
},
{
"epoch": 0.1297894373489817,
"grad_norm": 1.8643776178359985,
"learning_rate": 2e-05,
"loss": 1.071,
"step": 376
},
{
"epoch": 0.1301346220227822,
"grad_norm": 1.9768637418746948,
"learning_rate": 2e-05,
"loss": 1.0634,
"step": 377
},
{
"epoch": 0.13047980669658268,
"grad_norm": 1.8979171514511108,
"learning_rate": 2e-05,
"loss": 1.0746,
"step": 378
},
{
"epoch": 0.13082499137038314,
"grad_norm": 2.2266244888305664,
"learning_rate": 2e-05,
"loss": 1.0139,
"step": 379
},
{
"epoch": 0.13117017604418363,
"grad_norm": 2.767505645751953,
"learning_rate": 2e-05,
"loss": 1.0483,
"step": 380
},
{
"epoch": 0.13151536071798411,
"grad_norm": 1.9986623525619507,
"learning_rate": 2e-05,
"loss": 1.0527,
"step": 381
},
{
"epoch": 0.1318605453917846,
"grad_norm": 2.7748537063598633,
"learning_rate": 2e-05,
"loss": 1.0117,
"step": 382
},
{
"epoch": 0.1322057300655851,
"grad_norm": 2.404034376144409,
"learning_rate": 2e-05,
"loss": 1.0509,
"step": 383
},
{
"epoch": 0.13255091473938557,
"grad_norm": 1.8266741037368774,
"learning_rate": 2e-05,
"loss": 0.9569,
"step": 384
},
{
"epoch": 0.13289609941318606,
"grad_norm": 1.6617871522903442,
"learning_rate": 2e-05,
"loss": 1.0284,
"step": 385
},
{
"epoch": 0.13324128408698654,
"grad_norm": 2.1641674041748047,
"learning_rate": 2e-05,
"loss": 1.0185,
"step": 386
},
{
"epoch": 0.13358646876078703,
"grad_norm": 2.230027675628662,
"learning_rate": 2e-05,
"loss": 1.0059,
"step": 387
},
{
"epoch": 0.13393165343458752,
"grad_norm": 2.0304672718048096,
"learning_rate": 2e-05,
"loss": 0.9458,
"step": 388
},
{
"epoch": 0.13427683810838797,
"grad_norm": 1.9289956092834473,
"learning_rate": 2e-05,
"loss": 0.9867,
"step": 389
},
{
"epoch": 0.13462202278218846,
"grad_norm": 2.290512800216675,
"learning_rate": 2e-05,
"loss": 1.0438,
"step": 390
},
{
"epoch": 0.13496720745598895,
"grad_norm": 1.9645930528640747,
"learning_rate": 2e-05,
"loss": 1.0647,
"step": 391
},
{
"epoch": 0.13531239212978943,
"grad_norm": 1.9078412055969238,
"learning_rate": 2e-05,
"loss": 1.0219,
"step": 392
},
{
"epoch": 0.13565757680358992,
"grad_norm": 1.8987268209457397,
"learning_rate": 2e-05,
"loss": 0.9697,
"step": 393
},
{
"epoch": 0.1360027614773904,
"grad_norm": 1.8962979316711426,
"learning_rate": 2e-05,
"loss": 1.0337,
"step": 394
},
{
"epoch": 0.1363479461511909,
"grad_norm": 1.955389380455017,
"learning_rate": 2e-05,
"loss": 0.9921,
"step": 395
},
{
"epoch": 0.13669313082499138,
"grad_norm": 1.89638352394104,
"learning_rate": 2e-05,
"loss": 0.9957,
"step": 396
},
{
"epoch": 0.13703831549879186,
"grad_norm": 1.949547290802002,
"learning_rate": 2e-05,
"loss": 1.0009,
"step": 397
},
{
"epoch": 0.13738350017259235,
"grad_norm": 1.9283349514007568,
"learning_rate": 2e-05,
"loss": 0.9941,
"step": 398
},
{
"epoch": 0.1377286848463928,
"grad_norm": 1.9636731147766113,
"learning_rate": 2e-05,
"loss": 0.9358,
"step": 399
},
{
"epoch": 0.1380738695201933,
"grad_norm": 1.988175630569458,
"learning_rate": 2e-05,
"loss": 1.0143,
"step": 400
},
{
"epoch": 0.13841905419399378,
"grad_norm": 3.700079917907715,
"learning_rate": 2e-05,
"loss": 1.0032,
"step": 401
},
{
"epoch": 0.13876423886779427,
"grad_norm": 1.7401189804077148,
"learning_rate": 2e-05,
"loss": 0.9809,
"step": 402
},
{
"epoch": 0.13910942354159475,
"grad_norm": 2.0770182609558105,
"learning_rate": 2e-05,
"loss": 0.9912,
"step": 403
},
{
"epoch": 0.13945460821539524,
"grad_norm": 1.9828225374221802,
"learning_rate": 2e-05,
"loss": 0.9539,
"step": 404
},
{
"epoch": 0.13979979288919572,
"grad_norm": 2.1846377849578857,
"learning_rate": 2e-05,
"loss": 1.0277,
"step": 405
},
{
"epoch": 0.1401449775629962,
"grad_norm": 2.0720324516296387,
"learning_rate": 2e-05,
"loss": 0.9867,
"step": 406
},
{
"epoch": 0.1404901622367967,
"grad_norm": 2.008073329925537,
"learning_rate": 2e-05,
"loss": 1.0534,
"step": 407
},
{
"epoch": 0.14083534691059718,
"grad_norm": 1.7485285997390747,
"learning_rate": 2e-05,
"loss": 0.9596,
"step": 408
},
{
"epoch": 0.14118053158439764,
"grad_norm": 1.7809031009674072,
"learning_rate": 2e-05,
"loss": 0.901,
"step": 409
},
{
"epoch": 0.14152571625819813,
"grad_norm": 1.941487431526184,
"learning_rate": 2e-05,
"loss": 1.015,
"step": 410
},
{
"epoch": 0.1418709009319986,
"grad_norm": 2.04276180267334,
"learning_rate": 2e-05,
"loss": 0.9139,
"step": 411
},
{
"epoch": 0.1422160856057991,
"grad_norm": 1.9277434349060059,
"learning_rate": 2e-05,
"loss": 1.0199,
"step": 412
},
{
"epoch": 0.14256127027959958,
"grad_norm": 1.8862082958221436,
"learning_rate": 2e-05,
"loss": 1.0346,
"step": 413
},
{
"epoch": 0.14290645495340007,
"grad_norm": 2.0231850147247314,
"learning_rate": 2e-05,
"loss": 0.9775,
"step": 414
},
{
"epoch": 0.14325163962720056,
"grad_norm": 1.9419363737106323,
"learning_rate": 2e-05,
"loss": 1.0278,
"step": 415
},
{
"epoch": 0.14359682430100104,
"grad_norm": 2.052281618118286,
"learning_rate": 2e-05,
"loss": 0.989,
"step": 416
},
{
"epoch": 0.14394200897480153,
"grad_norm": 2.1041719913482666,
"learning_rate": 2e-05,
"loss": 1.0169,
"step": 417
},
{
"epoch": 0.144287193648602,
"grad_norm": 1.7935234308242798,
"learning_rate": 2e-05,
"loss": 0.9689,
"step": 418
},
{
"epoch": 0.14463237832240247,
"grad_norm": 1.9612940549850464,
"learning_rate": 2e-05,
"loss": 1.0247,
"step": 419
},
{
"epoch": 0.14497756299620296,
"grad_norm": 2.0655298233032227,
"learning_rate": 2e-05,
"loss": 0.9698,
"step": 420
},
{
"epoch": 0.14532274767000344,
"grad_norm": 1.9818885326385498,
"learning_rate": 2e-05,
"loss": 0.993,
"step": 421
},
{
"epoch": 0.14566793234380393,
"grad_norm": 1.8600380420684814,
"learning_rate": 2e-05,
"loss": 0.9699,
"step": 422
},
{
"epoch": 0.14601311701760442,
"grad_norm": 1.8439067602157593,
"learning_rate": 2e-05,
"loss": 1.0416,
"step": 423
},
{
"epoch": 0.1463583016914049,
"grad_norm": 1.8851103782653809,
"learning_rate": 2e-05,
"loss": 1.0046,
"step": 424
},
{
"epoch": 0.1467034863652054,
"grad_norm": 1.8863391876220703,
"learning_rate": 2e-05,
"loss": 1.0108,
"step": 425
},
{
"epoch": 0.14704867103900587,
"grad_norm": 1.9725341796875,
"learning_rate": 2e-05,
"loss": 0.973,
"step": 426
},
{
"epoch": 0.14739385571280636,
"grad_norm": 1.8963711261749268,
"learning_rate": 2e-05,
"loss": 1.0043,
"step": 427
},
{
"epoch": 0.14773904038660685,
"grad_norm": 1.9554258584976196,
"learning_rate": 2e-05,
"loss": 0.9763,
"step": 428
},
{
"epoch": 0.1480842250604073,
"grad_norm": 1.8015611171722412,
"learning_rate": 2e-05,
"loss": 0.9258,
"step": 429
},
{
"epoch": 0.1484294097342078,
"grad_norm": 1.798030138015747,
"learning_rate": 2e-05,
"loss": 1.0276,
"step": 430
},
{
"epoch": 0.14877459440800828,
"grad_norm": 1.989066481590271,
"learning_rate": 2e-05,
"loss": 1.0152,
"step": 431
},
{
"epoch": 0.14911977908180876,
"grad_norm": 1.7505500316619873,
"learning_rate": 2e-05,
"loss": 0.9626,
"step": 432
},
{
"epoch": 0.14946496375560925,
"grad_norm": 1.805210828781128,
"learning_rate": 2e-05,
"loss": 1.0081,
"step": 433
},
{
"epoch": 0.14981014842940973,
"grad_norm": 1.7437788248062134,
"learning_rate": 2e-05,
"loss": 0.9594,
"step": 434
},
{
"epoch": 0.15015533310321022,
"grad_norm": 1.9620840549468994,
"learning_rate": 2e-05,
"loss": 0.9735,
"step": 435
},
{
"epoch": 0.1505005177770107,
"grad_norm": 1.7169198989868164,
"learning_rate": 2e-05,
"loss": 1.0218,
"step": 436
},
{
"epoch": 0.1508457024508112,
"grad_norm": 1.7955130338668823,
"learning_rate": 2e-05,
"loss": 1.0152,
"step": 437
},
{
"epoch": 0.15119088712461168,
"grad_norm": 1.7508571147918701,
"learning_rate": 2e-05,
"loss": 1.0157,
"step": 438
},
{
"epoch": 0.15153607179841216,
"grad_norm": 1.7915910482406616,
"learning_rate": 2e-05,
"loss": 0.9635,
"step": 439
},
{
"epoch": 0.15188125647221262,
"grad_norm": 1.9122554063796997,
"learning_rate": 2e-05,
"loss": 0.9794,
"step": 440
},
{
"epoch": 0.1522264411460131,
"grad_norm": 1.9118950366973877,
"learning_rate": 2e-05,
"loss": 1.0267,
"step": 441
},
{
"epoch": 0.1525716258198136,
"grad_norm": 2.0399434566497803,
"learning_rate": 2e-05,
"loss": 0.9489,
"step": 442
},
{
"epoch": 0.15291681049361408,
"grad_norm": 1.8079497814178467,
"learning_rate": 2e-05,
"loss": 0.918,
"step": 443
},
{
"epoch": 0.15326199516741457,
"grad_norm": 2.0133776664733887,
"learning_rate": 2e-05,
"loss": 1.0247,
"step": 444
},
{
"epoch": 0.15360717984121505,
"grad_norm": 1.708000659942627,
"learning_rate": 2e-05,
"loss": 0.9877,
"step": 445
},
{
"epoch": 0.15395236451501554,
"grad_norm": 2.8612570762634277,
"learning_rate": 2e-05,
"loss": 0.9431,
"step": 446
},
{
"epoch": 0.15429754918881602,
"grad_norm": 1.9113045930862427,
"learning_rate": 2e-05,
"loss": 1.0209,
"step": 447
},
{
"epoch": 0.1546427338626165,
"grad_norm": 1.9729554653167725,
"learning_rate": 2e-05,
"loss": 1.0083,
"step": 448
},
{
"epoch": 0.154987918536417,
"grad_norm": 1.7863906621932983,
"learning_rate": 2e-05,
"loss": 0.9785,
"step": 449
},
{
"epoch": 0.15533310321021745,
"grad_norm": 1.834122896194458,
"learning_rate": 2e-05,
"loss": 1.0116,
"step": 450
},
{
"epoch": 0.15567828788401794,
"grad_norm": 1.78994882106781,
"learning_rate": 2e-05,
"loss": 0.9919,
"step": 451
},
{
"epoch": 0.15602347255781843,
"grad_norm": 1.75197434425354,
"learning_rate": 2e-05,
"loss": 0.9562,
"step": 452
},
{
"epoch": 0.1563686572316189,
"grad_norm": 1.8412542343139648,
"learning_rate": 2e-05,
"loss": 0.958,
"step": 453
},
{
"epoch": 0.1567138419054194,
"grad_norm": 1.835324764251709,
"learning_rate": 2e-05,
"loss": 1.0405,
"step": 454
},
{
"epoch": 0.15705902657921988,
"grad_norm": 1.9802517890930176,
"learning_rate": 2e-05,
"loss": 1.0106,
"step": 455
},
{
"epoch": 0.15740421125302037,
"grad_norm": 1.9370285272598267,
"learning_rate": 2e-05,
"loss": 0.9831,
"step": 456
},
{
"epoch": 0.15774939592682086,
"grad_norm": 1.7783889770507812,
"learning_rate": 2e-05,
"loss": 0.9671,
"step": 457
},
{
"epoch": 0.15809458060062134,
"grad_norm": 2.029588460922241,
"learning_rate": 2e-05,
"loss": 0.9721,
"step": 458
},
{
"epoch": 0.15843976527442183,
"grad_norm": 2.1747827529907227,
"learning_rate": 2e-05,
"loss": 1.0175,
"step": 459
},
{
"epoch": 0.1587849499482223,
"grad_norm": 1.686989188194275,
"learning_rate": 2e-05,
"loss": 0.8473,
"step": 460
},
{
"epoch": 0.15913013462202277,
"grad_norm": 2.0917375087738037,
"learning_rate": 2e-05,
"loss": 0.9891,
"step": 461
},
{
"epoch": 0.15947531929582326,
"grad_norm": 2.1684677600860596,
"learning_rate": 2e-05,
"loss": 1.0662,
"step": 462
},
{
"epoch": 0.15982050396962375,
"grad_norm": 1.7718673944473267,
"learning_rate": 2e-05,
"loss": 0.9163,
"step": 463
},
{
"epoch": 0.16016568864342423,
"grad_norm": 2.3066091537475586,
"learning_rate": 2e-05,
"loss": 0.8755,
"step": 464
},
{
"epoch": 0.16051087331722472,
"grad_norm": 1.7189663648605347,
"learning_rate": 2e-05,
"loss": 0.988,
"step": 465
},
{
"epoch": 0.1608560579910252,
"grad_norm": 1.8097484111785889,
"learning_rate": 2e-05,
"loss": 1.0246,
"step": 466
},
{
"epoch": 0.1612012426648257,
"grad_norm": 1.7880991697311401,
"learning_rate": 2e-05,
"loss": 0.9776,
"step": 467
},
{
"epoch": 0.16154642733862618,
"grad_norm": 1.6561658382415771,
"learning_rate": 2e-05,
"loss": 0.9556,
"step": 468
},
{
"epoch": 0.16189161201242666,
"grad_norm": 1.8971339464187622,
"learning_rate": 2e-05,
"loss": 1.0484,
"step": 469
},
{
"epoch": 0.16223679668622712,
"grad_norm": 2.243511915206909,
"learning_rate": 2e-05,
"loss": 1.0367,
"step": 470
},
{
"epoch": 0.1625819813600276,
"grad_norm": 1.692306399345398,
"learning_rate": 2e-05,
"loss": 0.9451,
"step": 471
},
{
"epoch": 0.1629271660338281,
"grad_norm": 1.8681774139404297,
"learning_rate": 2e-05,
"loss": 1.0005,
"step": 472
},
{
"epoch": 0.16327235070762858,
"grad_norm": 1.9061826467514038,
"learning_rate": 2e-05,
"loss": 0.977,
"step": 473
},
{
"epoch": 0.16361753538142906,
"grad_norm": 1.8971025943756104,
"learning_rate": 2e-05,
"loss": 0.9634,
"step": 474
},
{
"epoch": 0.16396272005522955,
"grad_norm": 1.9363058805465698,
"learning_rate": 2e-05,
"loss": 0.9951,
"step": 475
},
{
"epoch": 0.16430790472903004,
"grad_norm": 1.7034854888916016,
"learning_rate": 2e-05,
"loss": 1.0549,
"step": 476
},
{
"epoch": 0.16465308940283052,
"grad_norm": 1.768808364868164,
"learning_rate": 2e-05,
"loss": 0.9632,
"step": 477
},
{
"epoch": 0.164998274076631,
"grad_norm": 2.002805471420288,
"learning_rate": 2e-05,
"loss": 0.9811,
"step": 478
},
{
"epoch": 0.1653434587504315,
"grad_norm": 2.1307835578918457,
"learning_rate": 2e-05,
"loss": 0.9379,
"step": 479
},
{
"epoch": 0.16568864342423195,
"grad_norm": 1.944579005241394,
"learning_rate": 2e-05,
"loss": 1.0082,
"step": 480
},
{
"epoch": 0.16603382809803244,
"grad_norm": 1.9522337913513184,
"learning_rate": 2e-05,
"loss": 0.9292,
"step": 481
},
{
"epoch": 0.16637901277183292,
"grad_norm": 1.8480734825134277,
"learning_rate": 2e-05,
"loss": 1.0149,
"step": 482
},
{
"epoch": 0.1667241974456334,
"grad_norm": 1.8783234357833862,
"learning_rate": 2e-05,
"loss": 1.0015,
"step": 483
},
{
"epoch": 0.1670693821194339,
"grad_norm": 1.8167026042938232,
"learning_rate": 2e-05,
"loss": 1.0144,
"step": 484
},
{
"epoch": 0.16741456679323438,
"grad_norm": 1.9404585361480713,
"learning_rate": 2e-05,
"loss": 1.0473,
"step": 485
},
{
"epoch": 0.16775975146703487,
"grad_norm": 1.7782187461853027,
"learning_rate": 2e-05,
"loss": 0.9862,
"step": 486
},
{
"epoch": 0.16810493614083535,
"grad_norm": 1.8282090425491333,
"learning_rate": 2e-05,
"loss": 0.9692,
"step": 487
},
{
"epoch": 0.16845012081463584,
"grad_norm": 2.0017974376678467,
"learning_rate": 2e-05,
"loss": 0.9859,
"step": 488
},
{
"epoch": 0.16879530548843633,
"grad_norm": 1.8540397882461548,
"learning_rate": 2e-05,
"loss": 0.9618,
"step": 489
},
{
"epoch": 0.16914049016223678,
"grad_norm": 1.848656415939331,
"learning_rate": 2e-05,
"loss": 0.9297,
"step": 490
},
{
"epoch": 0.16948567483603727,
"grad_norm": 1.8251721858978271,
"learning_rate": 2e-05,
"loss": 1.0148,
"step": 491
},
{
"epoch": 0.16983085950983776,
"grad_norm": 1.84182608127594,
"learning_rate": 2e-05,
"loss": 0.9766,
"step": 492
},
{
"epoch": 0.17017604418363824,
"grad_norm": 1.9774746894836426,
"learning_rate": 2e-05,
"loss": 1.0387,
"step": 493
},
{
"epoch": 0.17052122885743873,
"grad_norm": 1.8130301237106323,
"learning_rate": 2e-05,
"loss": 0.8676,
"step": 494
},
{
"epoch": 0.17086641353123921,
"grad_norm": 1.987480878829956,
"learning_rate": 2e-05,
"loss": 1.0048,
"step": 495
},
{
"epoch": 0.1712115982050397,
"grad_norm": 1.9262433052062988,
"learning_rate": 2e-05,
"loss": 1.0175,
"step": 496
},
{
"epoch": 0.17155678287884019,
"grad_norm": 1.8977035284042358,
"learning_rate": 2e-05,
"loss": 0.9327,
"step": 497
},
{
"epoch": 0.17190196755264067,
"grad_norm": 1.955051302909851,
"learning_rate": 2e-05,
"loss": 1.0237,
"step": 498
},
{
"epoch": 0.17224715222644116,
"grad_norm": 1.9467777013778687,
"learning_rate": 2e-05,
"loss": 0.9421,
"step": 499
},
{
"epoch": 0.17259233690024162,
"grad_norm": 1.7480354309082031,
"learning_rate": 2e-05,
"loss": 0.9468,
"step": 500
},
{
"epoch": 0.1729375215740421,
"grad_norm": 1.8241736888885498,
"learning_rate": 2e-05,
"loss": 1.0302,
"step": 501
},
{
"epoch": 0.1732827062478426,
"grad_norm": 1.9474701881408691,
"learning_rate": 2e-05,
"loss": 0.9348,
"step": 502
},
{
"epoch": 0.17362789092164307,
"grad_norm": 3.8794655799865723,
"learning_rate": 2e-05,
"loss": 0.9469,
"step": 503
},
{
"epoch": 0.17397307559544356,
"grad_norm": 1.8369200229644775,
"learning_rate": 2e-05,
"loss": 1.0089,
"step": 504
},
{
"epoch": 0.17431826026924405,
"grad_norm": 1.978410243988037,
"learning_rate": 2e-05,
"loss": 0.9513,
"step": 505
},
{
"epoch": 0.17466344494304453,
"grad_norm": 1.8215962648391724,
"learning_rate": 2e-05,
"loss": 1.0027,
"step": 506
},
{
"epoch": 0.17500862961684502,
"grad_norm": 2.0822768211364746,
"learning_rate": 2e-05,
"loss": 0.9163,
"step": 507
},
{
"epoch": 0.1753538142906455,
"grad_norm": 1.9336357116699219,
"learning_rate": 2e-05,
"loss": 0.9545,
"step": 508
},
{
"epoch": 0.175698998964446,
"grad_norm": 1.7150814533233643,
"learning_rate": 2e-05,
"loss": 1.0166,
"step": 509
},
{
"epoch": 0.17604418363824645,
"grad_norm": 2.2125966548919678,
"learning_rate": 2e-05,
"loss": 1.0112,
"step": 510
},
{
"epoch": 0.17638936831204693,
"grad_norm": 1.9416768550872803,
"learning_rate": 2e-05,
"loss": 1.0636,
"step": 511
},
{
"epoch": 0.17673455298584742,
"grad_norm": 2.351174831390381,
"learning_rate": 2e-05,
"loss": 1.1013,
"step": 512
},
{
"epoch": 0.1770797376596479,
"grad_norm": 1.7502448558807373,
"learning_rate": 2e-05,
"loss": 1.0309,
"step": 513
},
{
"epoch": 0.1774249223334484,
"grad_norm": 1.9532209634780884,
"learning_rate": 2e-05,
"loss": 1.011,
"step": 514
},
{
"epoch": 0.17777010700724888,
"grad_norm": 1.607026219367981,
"learning_rate": 2e-05,
"loss": 0.9655,
"step": 515
},
{
"epoch": 0.17811529168104936,
"grad_norm": 1.8020447492599487,
"learning_rate": 2e-05,
"loss": 1.1234,
"step": 516
},
{
"epoch": 0.17846047635484985,
"grad_norm": 1.7421331405639648,
"learning_rate": 2e-05,
"loss": 0.9701,
"step": 517
},
{
"epoch": 0.17880566102865034,
"grad_norm": 1.955671787261963,
"learning_rate": 2e-05,
"loss": 0.9801,
"step": 518
},
{
"epoch": 0.17915084570245082,
"grad_norm": 1.9366713762283325,
"learning_rate": 2e-05,
"loss": 1.068,
"step": 519
},
{
"epoch": 0.17949603037625128,
"grad_norm": 1.8221323490142822,
"learning_rate": 2e-05,
"loss": 0.9617,
"step": 520
},
{
"epoch": 0.17984121505005177,
"grad_norm": 1.9764049053192139,
"learning_rate": 2e-05,
"loss": 0.9905,
"step": 521
},
{
"epoch": 0.18018639972385225,
"grad_norm": 1.9731082916259766,
"learning_rate": 2e-05,
"loss": 0.8959,
"step": 522
},
{
"epoch": 0.18053158439765274,
"grad_norm": 1.8409956693649292,
"learning_rate": 2e-05,
"loss": 1.0071,
"step": 523
},
{
"epoch": 0.18087676907145323,
"grad_norm": 2.0879194736480713,
"learning_rate": 2e-05,
"loss": 1.0887,
"step": 524
},
{
"epoch": 0.1812219537452537,
"grad_norm": 1.9950392246246338,
"learning_rate": 2e-05,
"loss": 1.0518,
"step": 525
},
{
"epoch": 0.1815671384190542,
"grad_norm": 1.9359629154205322,
"learning_rate": 2e-05,
"loss": 0.9284,
"step": 526
},
{
"epoch": 0.18191232309285468,
"grad_norm": 1.8083279132843018,
"learning_rate": 2e-05,
"loss": 0.9626,
"step": 527
},
{
"epoch": 0.18225750776665517,
"grad_norm": 1.8995139598846436,
"learning_rate": 2e-05,
"loss": 1.0653,
"step": 528
},
{
"epoch": 0.18260269244045566,
"grad_norm": 1.8402221202850342,
"learning_rate": 2e-05,
"loss": 1.0167,
"step": 529
},
{
"epoch": 0.1829478771142561,
"grad_norm": 1.8456122875213623,
"learning_rate": 2e-05,
"loss": 1.0094,
"step": 530
},
{
"epoch": 0.1832930617880566,
"grad_norm": 1.8030531406402588,
"learning_rate": 2e-05,
"loss": 0.9756,
"step": 531
},
{
"epoch": 0.18363824646185709,
"grad_norm": 1.9745162725448608,
"learning_rate": 2e-05,
"loss": 0.9858,
"step": 532
},
{
"epoch": 0.18398343113565757,
"grad_norm": 1.7643399238586426,
"learning_rate": 2e-05,
"loss": 1.0337,
"step": 533
},
{
"epoch": 0.18432861580945806,
"grad_norm": 1.9381707906723022,
"learning_rate": 2e-05,
"loss": 1.0522,
"step": 534
},
{
"epoch": 0.18467380048325854,
"grad_norm": 1.9115724563598633,
"learning_rate": 2e-05,
"loss": 0.9142,
"step": 535
},
{
"epoch": 0.18501898515705903,
"grad_norm": 1.718685507774353,
"learning_rate": 2e-05,
"loss": 0.9398,
"step": 536
},
{
"epoch": 0.18536416983085952,
"grad_norm": 1.9832113981246948,
"learning_rate": 2e-05,
"loss": 0.9009,
"step": 537
},
{
"epoch": 0.18570935450466,
"grad_norm": 1.7210725545883179,
"learning_rate": 2e-05,
"loss": 0.9163,
"step": 538
},
{
"epoch": 0.1860545391784605,
"grad_norm": 1.7867950201034546,
"learning_rate": 2e-05,
"loss": 0.9385,
"step": 539
},
{
"epoch": 0.18639972385226097,
"grad_norm": 1.7639451026916504,
"learning_rate": 2e-05,
"loss": 0.9628,
"step": 540
},
{
"epoch": 0.18674490852606143,
"grad_norm": 1.7130681276321411,
"learning_rate": 2e-05,
"loss": 1.0034,
"step": 541
},
{
"epoch": 0.18709009319986192,
"grad_norm": 1.872327208518982,
"learning_rate": 2e-05,
"loss": 1.0531,
"step": 542
},
{
"epoch": 0.1874352778736624,
"grad_norm": 1.8734036684036255,
"learning_rate": 2e-05,
"loss": 1.0669,
"step": 543
},
{
"epoch": 0.1877804625474629,
"grad_norm": 1.8868738412857056,
"learning_rate": 2e-05,
"loss": 1.0207,
"step": 544
},
{
"epoch": 0.18812564722126338,
"grad_norm": 2.1517584323883057,
"learning_rate": 2e-05,
"loss": 0.9915,
"step": 545
},
{
"epoch": 0.18847083189506386,
"grad_norm": 1.9018532037734985,
"learning_rate": 2e-05,
"loss": 0.9622,
"step": 546
},
{
"epoch": 0.18881601656886435,
"grad_norm": 1.9562731981277466,
"learning_rate": 2e-05,
"loss": 0.9878,
"step": 547
},
{
"epoch": 0.18916120124266483,
"grad_norm": 2.049401044845581,
"learning_rate": 2e-05,
"loss": 0.9626,
"step": 548
},
{
"epoch": 0.18950638591646532,
"grad_norm": 2.0909905433654785,
"learning_rate": 2e-05,
"loss": 1.0714,
"step": 549
},
{
"epoch": 0.1898515705902658,
"grad_norm": 2.006314754486084,
"learning_rate": 2e-05,
"loss": 1.0382,
"step": 550
},
{
"epoch": 0.19019675526406626,
"grad_norm": 3.2776713371276855,
"learning_rate": 2e-05,
"loss": 1.0598,
"step": 551
},
{
"epoch": 0.19054193993786675,
"grad_norm": 1.798421859741211,
"learning_rate": 2e-05,
"loss": 0.8935,
"step": 552
},
{
"epoch": 0.19088712461166724,
"grad_norm": 1.7902554273605347,
"learning_rate": 2e-05,
"loss": 0.9895,
"step": 553
},
{
"epoch": 0.19123230928546772,
"grad_norm": 2.0086610317230225,
"learning_rate": 2e-05,
"loss": 0.9428,
"step": 554
},
{
"epoch": 0.1915774939592682,
"grad_norm": 1.7480082511901855,
"learning_rate": 2e-05,
"loss": 0.9595,
"step": 555
},
{
"epoch": 0.1919226786330687,
"grad_norm": 3.485732078552246,
"learning_rate": 2e-05,
"loss": 0.9498,
"step": 556
},
{
"epoch": 0.19226786330686918,
"grad_norm": 1.9598274230957031,
"learning_rate": 2e-05,
"loss": 0.9638,
"step": 557
},
{
"epoch": 0.19261304798066967,
"grad_norm": 1.8408749103546143,
"learning_rate": 2e-05,
"loss": 0.932,
"step": 558
},
{
"epoch": 0.19295823265447015,
"grad_norm": 1.9857864379882812,
"learning_rate": 2e-05,
"loss": 1.0111,
"step": 559
},
{
"epoch": 0.19330341732827064,
"grad_norm": 1.9467519521713257,
"learning_rate": 2e-05,
"loss": 1.012,
"step": 560
},
{
"epoch": 0.1936486020020711,
"grad_norm": 1.8841748237609863,
"learning_rate": 2e-05,
"loss": 0.9868,
"step": 561
},
{
"epoch": 0.19399378667587158,
"grad_norm": 1.8785362243652344,
"learning_rate": 2e-05,
"loss": 0.9281,
"step": 562
},
{
"epoch": 0.19433897134967207,
"grad_norm": 1.8642878532409668,
"learning_rate": 2e-05,
"loss": 1.0245,
"step": 563
},
{
"epoch": 0.19468415602347255,
"grad_norm": 1.7851183414459229,
"learning_rate": 2e-05,
"loss": 0.8646,
"step": 564
},
{
"epoch": 0.19502934069727304,
"grad_norm": 1.768984079360962,
"learning_rate": 2e-05,
"loss": 0.9925,
"step": 565
},
{
"epoch": 0.19537452537107353,
"grad_norm": 2.008229970932007,
"learning_rate": 2e-05,
"loss": 1.0027,
"step": 566
},
{
"epoch": 0.195719710044874,
"grad_norm": 1.7181416749954224,
"learning_rate": 2e-05,
"loss": 0.9368,
"step": 567
},
{
"epoch": 0.1960648947186745,
"grad_norm": 3.3756608963012695,
"learning_rate": 2e-05,
"loss": 0.9934,
"step": 568
},
{
"epoch": 0.19641007939247498,
"grad_norm": 1.853429913520813,
"learning_rate": 2e-05,
"loss": 0.9384,
"step": 569
},
{
"epoch": 0.19675526406627547,
"grad_norm": 1.8626399040222168,
"learning_rate": 2e-05,
"loss": 0.979,
"step": 570
},
{
"epoch": 0.19710044874007593,
"grad_norm": 1.994254231452942,
"learning_rate": 2e-05,
"loss": 0.9143,
"step": 571
},
{
"epoch": 0.19744563341387641,
"grad_norm": 4.6400861740112305,
"learning_rate": 2e-05,
"loss": 0.9844,
"step": 572
},
{
"epoch": 0.1977908180876769,
"grad_norm": 1.7284791469573975,
"learning_rate": 2e-05,
"loss": 0.9309,
"step": 573
},
{
"epoch": 0.1981360027614774,
"grad_norm": 1.7410945892333984,
"learning_rate": 2e-05,
"loss": 0.9495,
"step": 574
},
{
"epoch": 0.19848118743527787,
"grad_norm": 1.8936198949813843,
"learning_rate": 2e-05,
"loss": 0.9256,
"step": 575
},
{
"epoch": 0.19882637210907836,
"grad_norm": 1.8987468481063843,
"learning_rate": 2e-05,
"loss": 0.9167,
"step": 576
},
{
"epoch": 0.19917155678287884,
"grad_norm": 1.562294602394104,
"learning_rate": 2e-05,
"loss": 0.9001,
"step": 577
},
{
"epoch": 0.19951674145667933,
"grad_norm": 1.8768669366836548,
"learning_rate": 2e-05,
"loss": 0.9402,
"step": 578
},
{
"epoch": 0.19986192613047982,
"grad_norm": 5.918983459472656,
"learning_rate": 2e-05,
"loss": 0.9048,
"step": 579
},
{
"epoch": 0.2002071108042803,
"grad_norm": 2.3079235553741455,
"learning_rate": 2e-05,
"loss": 0.9528,
"step": 580
},
{
"epoch": 0.20055229547808076,
"grad_norm": 2.0658676624298096,
"learning_rate": 2e-05,
"loss": 0.9182,
"step": 581
},
{
"epoch": 0.20089748015188125,
"grad_norm": 1.7358447313308716,
"learning_rate": 2e-05,
"loss": 1.021,
"step": 582
},
{
"epoch": 0.20124266482568173,
"grad_norm": 1.9200198650360107,
"learning_rate": 2e-05,
"loss": 0.9035,
"step": 583
},
{
"epoch": 0.20158784949948222,
"grad_norm": 1.811689019203186,
"learning_rate": 2e-05,
"loss": 0.8721,
"step": 584
},
{
"epoch": 0.2019330341732827,
"grad_norm": 1.8374279737472534,
"learning_rate": 2e-05,
"loss": 1.0171,
"step": 585
},
{
"epoch": 0.2022782188470832,
"grad_norm": 1.793975591659546,
"learning_rate": 2e-05,
"loss": 0.9927,
"step": 586
},
{
"epoch": 0.20262340352088368,
"grad_norm": 1.6837302446365356,
"learning_rate": 2e-05,
"loss": 0.949,
"step": 587
},
{
"epoch": 0.20296858819468416,
"grad_norm": 3.0887913703918457,
"learning_rate": 2e-05,
"loss": 1.0262,
"step": 588
},
{
"epoch": 0.20331377286848465,
"grad_norm": 1.7894266843795776,
"learning_rate": 2e-05,
"loss": 0.9647,
"step": 589
},
{
"epoch": 0.20365895754228514,
"grad_norm": 1.7858067750930786,
"learning_rate": 2e-05,
"loss": 0.9771,
"step": 590
},
{
"epoch": 0.2040041422160856,
"grad_norm": 1.6570981740951538,
"learning_rate": 2e-05,
"loss": 0.9162,
"step": 591
},
{
"epoch": 0.20434932688988608,
"grad_norm": 1.6933810710906982,
"learning_rate": 2e-05,
"loss": 0.944,
"step": 592
},
{
"epoch": 0.20469451156368657,
"grad_norm": 1.7173789739608765,
"learning_rate": 2e-05,
"loss": 1.0037,
"step": 593
},
{
"epoch": 0.20503969623748705,
"grad_norm": 2.1869938373565674,
"learning_rate": 2e-05,
"loss": 0.9036,
"step": 594
},
{
"epoch": 0.20538488091128754,
"grad_norm": 1.7724378108978271,
"learning_rate": 2e-05,
"loss": 0.967,
"step": 595
},
{
"epoch": 0.20573006558508802,
"grad_norm": 1.7970529794692993,
"learning_rate": 2e-05,
"loss": 0.9555,
"step": 596
},
{
"epoch": 0.2060752502588885,
"grad_norm": 1.699947476387024,
"learning_rate": 2e-05,
"loss": 0.8565,
"step": 597
},
{
"epoch": 0.206420434932689,
"grad_norm": 1.7085161209106445,
"learning_rate": 2e-05,
"loss": 0.9417,
"step": 598
},
{
"epoch": 0.20676561960648948,
"grad_norm": 1.78633451461792,
"learning_rate": 2e-05,
"loss": 1.0238,
"step": 599
},
{
"epoch": 0.20711080428028997,
"grad_norm": 1.875192403793335,
"learning_rate": 2e-05,
"loss": 0.9575,
"step": 600
},
{
"epoch": 0.20745598895409043,
"grad_norm": 1.7347480058670044,
"learning_rate": 2e-05,
"loss": 0.9826,
"step": 601
},
{
"epoch": 0.2078011736278909,
"grad_norm": 1.7980979681015015,
"learning_rate": 2e-05,
"loss": 0.9445,
"step": 602
},
{
"epoch": 0.2081463583016914,
"grad_norm": 1.879648208618164,
"learning_rate": 2e-05,
"loss": 0.9538,
"step": 603
},
{
"epoch": 0.20849154297549188,
"grad_norm": 1.876985788345337,
"learning_rate": 2e-05,
"loss": 0.9867,
"step": 604
},
{
"epoch": 0.20883672764929237,
"grad_norm": 1.6838924884796143,
"learning_rate": 2e-05,
"loss": 0.9112,
"step": 605
},
{
"epoch": 0.20918191232309286,
"grad_norm": 1.7551112174987793,
"learning_rate": 2e-05,
"loss": 0.9535,
"step": 606
},
{
"epoch": 0.20952709699689334,
"grad_norm": 1.9521592855453491,
"learning_rate": 2e-05,
"loss": 0.8873,
"step": 607
},
{
"epoch": 0.20987228167069383,
"grad_norm": 1.963653802871704,
"learning_rate": 2e-05,
"loss": 1.0226,
"step": 608
},
{
"epoch": 0.2102174663444943,
"grad_norm": 1.8531434535980225,
"learning_rate": 2e-05,
"loss": 0.9903,
"step": 609
},
{
"epoch": 0.2105626510182948,
"grad_norm": 1.847257137298584,
"learning_rate": 2e-05,
"loss": 0.9529,
"step": 610
},
{
"epoch": 0.21090783569209526,
"grad_norm": 1.6460868120193481,
"learning_rate": 2e-05,
"loss": 0.9071,
"step": 611
},
{
"epoch": 0.21125302036589574,
"grad_norm": 1.652666449546814,
"learning_rate": 2e-05,
"loss": 0.9661,
"step": 612
},
{
"epoch": 0.21159820503969623,
"grad_norm": 1.817264199256897,
"learning_rate": 2e-05,
"loss": 0.9367,
"step": 613
},
{
"epoch": 0.21194338971349672,
"grad_norm": 1.8240456581115723,
"learning_rate": 2e-05,
"loss": 0.9783,
"step": 614
},
{
"epoch": 0.2122885743872972,
"grad_norm": 1.7032090425491333,
"learning_rate": 2e-05,
"loss": 0.923,
"step": 615
},
{
"epoch": 0.2126337590610977,
"grad_norm": 1.5968724489212036,
"learning_rate": 2e-05,
"loss": 0.8963,
"step": 616
},
{
"epoch": 0.21297894373489817,
"grad_norm": 1.8011481761932373,
"learning_rate": 2e-05,
"loss": 0.9966,
"step": 617
},
{
"epoch": 0.21332412840869866,
"grad_norm": 1.6756153106689453,
"learning_rate": 2e-05,
"loss": 0.9442,
"step": 618
},
{
"epoch": 0.21366931308249915,
"grad_norm": 1.9339874982833862,
"learning_rate": 2e-05,
"loss": 1.0488,
"step": 619
},
{
"epoch": 0.21401449775629963,
"grad_norm": 1.896833896636963,
"learning_rate": 2e-05,
"loss": 0.9623,
"step": 620
},
{
"epoch": 0.2143596824301001,
"grad_norm": 1.8234562873840332,
"learning_rate": 2e-05,
"loss": 0.9437,
"step": 621
},
{
"epoch": 0.21470486710390058,
"grad_norm": 1.7837271690368652,
"learning_rate": 2e-05,
"loss": 0.9726,
"step": 622
},
{
"epoch": 0.21505005177770106,
"grad_norm": 1.661525845527649,
"learning_rate": 2e-05,
"loss": 1.0058,
"step": 623
},
{
"epoch": 0.21539523645150155,
"grad_norm": 1.8720719814300537,
"learning_rate": 2e-05,
"loss": 0.9022,
"step": 624
},
{
"epoch": 0.21574042112530203,
"grad_norm": 1.767267107963562,
"learning_rate": 2e-05,
"loss": 1.0418,
"step": 625
},
{
"epoch": 0.21608560579910252,
"grad_norm": 1.9188283681869507,
"learning_rate": 2e-05,
"loss": 0.9585,
"step": 626
},
{
"epoch": 0.216430790472903,
"grad_norm": 1.827047348022461,
"learning_rate": 2e-05,
"loss": 0.9868,
"step": 627
},
{
"epoch": 0.2167759751467035,
"grad_norm": 1.7124732732772827,
"learning_rate": 2e-05,
"loss": 1.0239,
"step": 628
},
{
"epoch": 0.21712115982050398,
"grad_norm": 1.7362115383148193,
"learning_rate": 2e-05,
"loss": 0.9693,
"step": 629
},
{
"epoch": 0.21746634449430446,
"grad_norm": 1.7512201070785522,
"learning_rate": 2e-05,
"loss": 0.9334,
"step": 630
},
{
"epoch": 0.21781152916810492,
"grad_norm": 1.6031123399734497,
"learning_rate": 2e-05,
"loss": 0.9221,
"step": 631
},
{
"epoch": 0.2181567138419054,
"grad_norm": 1.7011840343475342,
"learning_rate": 2e-05,
"loss": 0.9383,
"step": 632
},
{
"epoch": 0.2185018985157059,
"grad_norm": 1.9012757539749146,
"learning_rate": 2e-05,
"loss": 0.9804,
"step": 633
},
{
"epoch": 0.21884708318950638,
"grad_norm": 1.7027804851531982,
"learning_rate": 2e-05,
"loss": 0.9185,
"step": 634
},
{
"epoch": 0.21919226786330687,
"grad_norm": 1.6549376249313354,
"learning_rate": 2e-05,
"loss": 0.9549,
"step": 635
},
{
"epoch": 0.21953745253710735,
"grad_norm": 1.726919412612915,
"learning_rate": 2e-05,
"loss": 0.9505,
"step": 636
},
{
"epoch": 0.21988263721090784,
"grad_norm": 1.9867405891418457,
"learning_rate": 2e-05,
"loss": 0.9442,
"step": 637
},
{
"epoch": 0.22022782188470832,
"grad_norm": 1.711452841758728,
"learning_rate": 2e-05,
"loss": 0.9889,
"step": 638
},
{
"epoch": 0.2205730065585088,
"grad_norm": 1.7813612222671509,
"learning_rate": 2e-05,
"loss": 0.9664,
"step": 639
},
{
"epoch": 0.2209181912323093,
"grad_norm": 1.8781616687774658,
"learning_rate": 2e-05,
"loss": 0.9372,
"step": 640
},
{
"epoch": 0.22126337590610975,
"grad_norm": 1.828626275062561,
"learning_rate": 2e-05,
"loss": 0.9614,
"step": 641
},
{
"epoch": 0.22160856057991024,
"grad_norm": 1.8183270692825317,
"learning_rate": 2e-05,
"loss": 0.9404,
"step": 642
},
{
"epoch": 0.22195374525371073,
"grad_norm": 1.769091010093689,
"learning_rate": 2e-05,
"loss": 1.0213,
"step": 643
},
{
"epoch": 0.2222989299275112,
"grad_norm": 1.8975324630737305,
"learning_rate": 2e-05,
"loss": 0.9083,
"step": 644
},
{
"epoch": 0.2226441146013117,
"grad_norm": 1.765549898147583,
"learning_rate": 2e-05,
"loss": 0.949,
"step": 645
},
{
"epoch": 0.22298929927511218,
"grad_norm": 1.8278275728225708,
"learning_rate": 2e-05,
"loss": 1.0029,
"step": 646
},
{
"epoch": 0.22333448394891267,
"grad_norm": 1.9216228723526,
"learning_rate": 2e-05,
"loss": 0.9992,
"step": 647
},
{
"epoch": 0.22367966862271316,
"grad_norm": 1.8710668087005615,
"learning_rate": 2e-05,
"loss": 0.8935,
"step": 648
},
{
"epoch": 0.22402485329651364,
"grad_norm": 1.7842600345611572,
"learning_rate": 2e-05,
"loss": 0.924,
"step": 649
},
{
"epoch": 0.22437003797031413,
"grad_norm": 1.785706639289856,
"learning_rate": 2e-05,
"loss": 0.9034,
"step": 650
},
{
"epoch": 0.22471522264411462,
"grad_norm": 1.6121408939361572,
"learning_rate": 2e-05,
"loss": 0.9245,
"step": 651
},
{
"epoch": 0.22506040731791507,
"grad_norm": 1.7515367269515991,
"learning_rate": 2e-05,
"loss": 0.9113,
"step": 652
},
{
"epoch": 0.22540559199171556,
"grad_norm": 2.607435941696167,
"learning_rate": 2e-05,
"loss": 0.9552,
"step": 653
},
{
"epoch": 0.22575077666551605,
"grad_norm": 1.733254313468933,
"learning_rate": 2e-05,
"loss": 0.9455,
"step": 654
},
{
"epoch": 0.22609596133931653,
"grad_norm": 1.6248252391815186,
"learning_rate": 2e-05,
"loss": 0.912,
"step": 655
},
{
"epoch": 0.22644114601311702,
"grad_norm": 1.753952980041504,
"learning_rate": 2e-05,
"loss": 1.0012,
"step": 656
},
{
"epoch": 0.2267863306869175,
"grad_norm": 1.61372709274292,
"learning_rate": 2e-05,
"loss": 0.9647,
"step": 657
},
{
"epoch": 0.227131515360718,
"grad_norm": 1.6623982191085815,
"learning_rate": 2e-05,
"loss": 0.8908,
"step": 658
},
{
"epoch": 0.22747670003451848,
"grad_norm": 1.7860376834869385,
"learning_rate": 2e-05,
"loss": 0.9372,
"step": 659
},
{
"epoch": 0.22782188470831896,
"grad_norm": 1.815545678138733,
"learning_rate": 2e-05,
"loss": 1.0017,
"step": 660
},
{
"epoch": 0.22816706938211945,
"grad_norm": 1.7496399879455566,
"learning_rate": 2e-05,
"loss": 0.9127,
"step": 661
},
{
"epoch": 0.2285122540559199,
"grad_norm": 1.7833198308944702,
"learning_rate": 2e-05,
"loss": 0.9015,
"step": 662
},
{
"epoch": 0.2288574387297204,
"grad_norm": 1.7757753133773804,
"learning_rate": 2e-05,
"loss": 0.9892,
"step": 663
},
{
"epoch": 0.22920262340352088,
"grad_norm": 1.666808843612671,
"learning_rate": 2e-05,
"loss": 0.9612,
"step": 664
},
{
"epoch": 0.22954780807732136,
"grad_norm": 1.7391040325164795,
"learning_rate": 2e-05,
"loss": 0.9297,
"step": 665
},
{
"epoch": 0.22989299275112185,
"grad_norm": 1.8499102592468262,
"learning_rate": 2e-05,
"loss": 0.9248,
"step": 666
},
{
"epoch": 0.23023817742492234,
"grad_norm": 1.6855679750442505,
"learning_rate": 2e-05,
"loss": 0.9588,
"step": 667
},
{
"epoch": 0.23058336209872282,
"grad_norm": 1.9015147686004639,
"learning_rate": 2e-05,
"loss": 0.9679,
"step": 668
},
{
"epoch": 0.2309285467725233,
"grad_norm": 1.734497308731079,
"learning_rate": 2e-05,
"loss": 0.9969,
"step": 669
},
{
"epoch": 0.2312737314463238,
"grad_norm": 1.7719879150390625,
"learning_rate": 2e-05,
"loss": 0.9055,
"step": 670
},
{
"epoch": 0.23161891612012428,
"grad_norm": 1.710024118423462,
"learning_rate": 2e-05,
"loss": 0.9228,
"step": 671
},
{
"epoch": 0.23196410079392474,
"grad_norm": 1.8393081426620483,
"learning_rate": 2e-05,
"loss": 0.9664,
"step": 672
},
{
"epoch": 0.23230928546772522,
"grad_norm": 1.7636027336120605,
"learning_rate": 2e-05,
"loss": 0.8789,
"step": 673
},
{
"epoch": 0.2326544701415257,
"grad_norm": 1.9402978420257568,
"learning_rate": 2e-05,
"loss": 0.9477,
"step": 674
},
{
"epoch": 0.2329996548153262,
"grad_norm": 1.7338268756866455,
"learning_rate": 2e-05,
"loss": 1.0104,
"step": 675
},
{
"epoch": 0.23334483948912668,
"grad_norm": 1.8638617992401123,
"learning_rate": 2e-05,
"loss": 0.9193,
"step": 676
},
{
"epoch": 0.23369002416292717,
"grad_norm": 1.8146984577178955,
"learning_rate": 2e-05,
"loss": 0.9209,
"step": 677
},
{
"epoch": 0.23403520883672765,
"grad_norm": 1.733011245727539,
"learning_rate": 2e-05,
"loss": 0.9181,
"step": 678
},
{
"epoch": 0.23438039351052814,
"grad_norm": 2.038259267807007,
"learning_rate": 2e-05,
"loss": 0.9892,
"step": 679
},
{
"epoch": 0.23472557818432863,
"grad_norm": 1.7838467359542847,
"learning_rate": 2e-05,
"loss": 1.0078,
"step": 680
},
{
"epoch": 0.2350707628581291,
"grad_norm": 1.8283867835998535,
"learning_rate": 2e-05,
"loss": 0.9701,
"step": 681
},
{
"epoch": 0.23541594753192957,
"grad_norm": 1.8064738512039185,
"learning_rate": 2e-05,
"loss": 0.9827,
"step": 682
},
{
"epoch": 0.23576113220573006,
"grad_norm": 2.4323370456695557,
"learning_rate": 2e-05,
"loss": 0.9854,
"step": 683
},
{
"epoch": 0.23610631687953054,
"grad_norm": 1.8830887079238892,
"learning_rate": 2e-05,
"loss": 0.9793,
"step": 684
},
{
"epoch": 0.23645150155333103,
"grad_norm": 1.6631356477737427,
"learning_rate": 2e-05,
"loss": 0.9141,
"step": 685
},
{
"epoch": 0.23679668622713151,
"grad_norm": 1.8258715867996216,
"learning_rate": 2e-05,
"loss": 0.9989,
"step": 686
},
{
"epoch": 0.237141870900932,
"grad_norm": 1.7349517345428467,
"learning_rate": 2e-05,
"loss": 0.953,
"step": 687
},
{
"epoch": 0.2374870555747325,
"grad_norm": 1.7592962980270386,
"learning_rate": 2e-05,
"loss": 1.0145,
"step": 688
},
{
"epoch": 0.23783224024853297,
"grad_norm": 1.762784719467163,
"learning_rate": 2e-05,
"loss": 0.9735,
"step": 689
},
{
"epoch": 0.23817742492233346,
"grad_norm": 1.789164662361145,
"learning_rate": 2e-05,
"loss": 0.9689,
"step": 690
},
{
"epoch": 0.23852260959613394,
"grad_norm": 1.7294576168060303,
"learning_rate": 2e-05,
"loss": 0.9342,
"step": 691
},
{
"epoch": 0.2388677942699344,
"grad_norm": 1.6930007934570312,
"learning_rate": 2e-05,
"loss": 0.9667,
"step": 692
},
{
"epoch": 0.2392129789437349,
"grad_norm": 1.6673132181167603,
"learning_rate": 2e-05,
"loss": 0.944,
"step": 693
},
{
"epoch": 0.23955816361753537,
"grad_norm": 1.746750831604004,
"learning_rate": 2e-05,
"loss": 0.9419,
"step": 694
},
{
"epoch": 0.23990334829133586,
"grad_norm": 1.7649177312850952,
"learning_rate": 2e-05,
"loss": 0.9247,
"step": 695
},
{
"epoch": 0.24024853296513635,
"grad_norm": 2.140566349029541,
"learning_rate": 2e-05,
"loss": 0.9695,
"step": 696
},
{
"epoch": 0.24059371763893683,
"grad_norm": 1.7225303649902344,
"learning_rate": 2e-05,
"loss": 0.9818,
"step": 697
},
{
"epoch": 0.24093890231273732,
"grad_norm": 1.6975003480911255,
"learning_rate": 2e-05,
"loss": 0.9326,
"step": 698
},
{
"epoch": 0.2412840869865378,
"grad_norm": 1.9510295391082764,
"learning_rate": 2e-05,
"loss": 0.9339,
"step": 699
},
{
"epoch": 0.2416292716603383,
"grad_norm": 1.8641351461410522,
"learning_rate": 2e-05,
"loss": 1.0054,
"step": 700
},
{
"epoch": 0.24197445633413878,
"grad_norm": 1.6479326486587524,
"learning_rate": 2e-05,
"loss": 1.0389,
"step": 701
},
{
"epoch": 0.24231964100793923,
"grad_norm": 1.8591350317001343,
"learning_rate": 2e-05,
"loss": 0.9602,
"step": 702
},
{
"epoch": 0.24266482568173972,
"grad_norm": 1.6348824501037598,
"learning_rate": 2e-05,
"loss": 0.9516,
"step": 703
},
{
"epoch": 0.2430100103555402,
"grad_norm": 1.6092488765716553,
"learning_rate": 2e-05,
"loss": 0.9398,
"step": 704
},
{
"epoch": 0.2433551950293407,
"grad_norm": 1.698967456817627,
"learning_rate": 2e-05,
"loss": 0.9346,
"step": 705
},
{
"epoch": 0.24370037970314118,
"grad_norm": 1.6550766229629517,
"learning_rate": 2e-05,
"loss": 0.8931,
"step": 706
},
{
"epoch": 0.24404556437694166,
"grad_norm": 1.7332935333251953,
"learning_rate": 2e-05,
"loss": 0.9521,
"step": 707
},
{
"epoch": 0.24439074905074215,
"grad_norm": 1.828611135482788,
"learning_rate": 2e-05,
"loss": 0.9345,
"step": 708
},
{
"epoch": 0.24473593372454264,
"grad_norm": 1.8282678127288818,
"learning_rate": 2e-05,
"loss": 0.9783,
"step": 709
},
{
"epoch": 0.24508111839834312,
"grad_norm": 1.7431113719940186,
"learning_rate": 2e-05,
"loss": 0.9836,
"step": 710
},
{
"epoch": 0.2454263030721436,
"grad_norm": 1.741969347000122,
"learning_rate": 2e-05,
"loss": 0.9099,
"step": 711
},
{
"epoch": 0.24577148774594407,
"grad_norm": 1.7447651624679565,
"learning_rate": 2e-05,
"loss": 0.8919,
"step": 712
},
{
"epoch": 0.24611667241974455,
"grad_norm": 1.7293975353240967,
"learning_rate": 2e-05,
"loss": 0.8974,
"step": 713
},
{
"epoch": 0.24646185709354504,
"grad_norm": 1.651405692100525,
"learning_rate": 2e-05,
"loss": 0.9471,
"step": 714
},
{
"epoch": 0.24680704176734553,
"grad_norm": 1.8038339614868164,
"learning_rate": 2e-05,
"loss": 0.9247,
"step": 715
},
{
"epoch": 0.247152226441146,
"grad_norm": 1.744349479675293,
"learning_rate": 2e-05,
"loss": 0.9745,
"step": 716
},
{
"epoch": 0.2474974111149465,
"grad_norm": 1.694891095161438,
"learning_rate": 2e-05,
"loss": 0.9512,
"step": 717
},
{
"epoch": 0.24784259578874698,
"grad_norm": 1.5880845785140991,
"learning_rate": 2e-05,
"loss": 0.9427,
"step": 718
},
{
"epoch": 0.24818778046254747,
"grad_norm": 1.5526502132415771,
"learning_rate": 2e-05,
"loss": 0.9582,
"step": 719
},
{
"epoch": 0.24853296513634796,
"grad_norm": 2.023087978363037,
"learning_rate": 2e-05,
"loss": 0.9629,
"step": 720
},
{
"epoch": 0.24887814981014844,
"grad_norm": 1.6062517166137695,
"learning_rate": 2e-05,
"loss": 0.9112,
"step": 721
},
{
"epoch": 0.2492233344839489,
"grad_norm": 1.9484480619430542,
"learning_rate": 2e-05,
"loss": 0.9474,
"step": 722
},
{
"epoch": 0.24956851915774939,
"grad_norm": 1.9322245121002197,
"learning_rate": 2e-05,
"loss": 0.9844,
"step": 723
},
{
"epoch": 0.24991370383154987,
"grad_norm": 2.028559923171997,
"learning_rate": 2e-05,
"loss": 0.9776,
"step": 724
},
{
"epoch": 0.2502588885053504,
"grad_norm": 1.8569518327713013,
"learning_rate": 2e-05,
"loss": 0.9211,
"step": 725
},
{
"epoch": 0.25060407317915084,
"grad_norm": 1.677549958229065,
"learning_rate": 2e-05,
"loss": 0.9246,
"step": 726
},
{
"epoch": 0.2509492578529513,
"grad_norm": 1.685090184211731,
"learning_rate": 2e-05,
"loss": 1.0399,
"step": 727
},
{
"epoch": 0.2512944425267518,
"grad_norm": 1.7994401454925537,
"learning_rate": 2e-05,
"loss": 0.96,
"step": 728
},
{
"epoch": 0.2516396272005523,
"grad_norm": 1.883177638053894,
"learning_rate": 2e-05,
"loss": 0.9082,
"step": 729
},
{
"epoch": 0.2519848118743528,
"grad_norm": 1.5140488147735596,
"learning_rate": 2e-05,
"loss": 0.8972,
"step": 730
},
{
"epoch": 0.25232999654815325,
"grad_norm": 1.6996492147445679,
"learning_rate": 2e-05,
"loss": 0.8545,
"step": 731
},
{
"epoch": 0.25267518122195376,
"grad_norm": 1.8028596639633179,
"learning_rate": 2e-05,
"loss": 0.9156,
"step": 732
},
{
"epoch": 0.2530203658957542,
"grad_norm": 1.6255139112472534,
"learning_rate": 2e-05,
"loss": 0.9471,
"step": 733
},
{
"epoch": 0.25336555056955473,
"grad_norm": 1.9539834260940552,
"learning_rate": 2e-05,
"loss": 0.9597,
"step": 734
},
{
"epoch": 0.2537107352433552,
"grad_norm": 1.6089783906936646,
"learning_rate": 2e-05,
"loss": 0.9853,
"step": 735
},
{
"epoch": 0.2540559199171557,
"grad_norm": 1.6394222974777222,
"learning_rate": 2e-05,
"loss": 0.9084,
"step": 736
},
{
"epoch": 0.25440110459095616,
"grad_norm": 1.7713274955749512,
"learning_rate": 2e-05,
"loss": 0.9766,
"step": 737
},
{
"epoch": 0.2547462892647566,
"grad_norm": 1.7471550703048706,
"learning_rate": 2e-05,
"loss": 0.9579,
"step": 738
},
{
"epoch": 0.25509147393855713,
"grad_norm": 1.7203348875045776,
"learning_rate": 2e-05,
"loss": 0.91,
"step": 739
},
{
"epoch": 0.2554366586123576,
"grad_norm": 1.7159513235092163,
"learning_rate": 2e-05,
"loss": 0.9477,
"step": 740
},
{
"epoch": 0.2557818432861581,
"grad_norm": 1.7029972076416016,
"learning_rate": 2e-05,
"loss": 0.9791,
"step": 741
},
{
"epoch": 0.25612702795995856,
"grad_norm": 1.848547101020813,
"learning_rate": 2e-05,
"loss": 0.9907,
"step": 742
},
{
"epoch": 0.2564722126337591,
"grad_norm": 1.7434319257736206,
"learning_rate": 2e-05,
"loss": 0.9491,
"step": 743
},
{
"epoch": 0.25681739730755954,
"grad_norm": 1.6110520362854004,
"learning_rate": 2e-05,
"loss": 0.8835,
"step": 744
},
{
"epoch": 0.25716258198136005,
"grad_norm": 1.8141536712646484,
"learning_rate": 2e-05,
"loss": 0.953,
"step": 745
},
{
"epoch": 0.2575077666551605,
"grad_norm": 1.6879647970199585,
"learning_rate": 2e-05,
"loss": 0.9404,
"step": 746
},
{
"epoch": 0.25785295132896097,
"grad_norm": 1.7503207921981812,
"learning_rate": 2e-05,
"loss": 0.9159,
"step": 747
},
{
"epoch": 0.2581981360027615,
"grad_norm": 1.6459016799926758,
"learning_rate": 2e-05,
"loss": 0.9823,
"step": 748
},
{
"epoch": 0.25854332067656194,
"grad_norm": 1.7275407314300537,
"learning_rate": 2e-05,
"loss": 1.0185,
"step": 749
},
{
"epoch": 0.25888850535036245,
"grad_norm": 1.8986669778823853,
"learning_rate": 2e-05,
"loss": 0.9283,
"step": 750
},
{
"epoch": 0.2592336900241629,
"grad_norm": 1.7517776489257812,
"learning_rate": 2e-05,
"loss": 0.9502,
"step": 751
},
{
"epoch": 0.2595788746979634,
"grad_norm": 1.912253975868225,
"learning_rate": 2e-05,
"loss": 0.9399,
"step": 752
},
{
"epoch": 0.2599240593717639,
"grad_norm": 1.729828953742981,
"learning_rate": 2e-05,
"loss": 0.9014,
"step": 753
},
{
"epoch": 0.2602692440455644,
"grad_norm": 1.780542254447937,
"learning_rate": 2e-05,
"loss": 0.9285,
"step": 754
},
{
"epoch": 0.26061442871936485,
"grad_norm": 1.8199851512908936,
"learning_rate": 2e-05,
"loss": 1.0126,
"step": 755
},
{
"epoch": 0.26095961339316537,
"grad_norm": 1.7953726053237915,
"learning_rate": 2e-05,
"loss": 0.9783,
"step": 756
},
{
"epoch": 0.2613047980669658,
"grad_norm": 1.6949175596237183,
"learning_rate": 2e-05,
"loss": 0.9116,
"step": 757
},
{
"epoch": 0.2616499827407663,
"grad_norm": 1.7206783294677734,
"learning_rate": 2e-05,
"loss": 0.8995,
"step": 758
},
{
"epoch": 0.2619951674145668,
"grad_norm": 1.9204108715057373,
"learning_rate": 2e-05,
"loss": 0.891,
"step": 759
},
{
"epoch": 0.26234035208836726,
"grad_norm": 1.8647918701171875,
"learning_rate": 2e-05,
"loss": 0.9909,
"step": 760
},
{
"epoch": 0.26268553676216777,
"grad_norm": 1.8312782049179077,
"learning_rate": 2e-05,
"loss": 0.9955,
"step": 761
},
{
"epoch": 0.26303072143596823,
"grad_norm": 1.5803852081298828,
"learning_rate": 2e-05,
"loss": 0.9231,
"step": 762
},
{
"epoch": 0.26337590610976874,
"grad_norm": 2.0904886722564697,
"learning_rate": 2e-05,
"loss": 0.975,
"step": 763
},
{
"epoch": 0.2637210907835692,
"grad_norm": 1.7414122819900513,
"learning_rate": 2e-05,
"loss": 0.8893,
"step": 764
},
{
"epoch": 0.2640662754573697,
"grad_norm": 1.5421781539916992,
"learning_rate": 2e-05,
"loss": 0.879,
"step": 765
},
{
"epoch": 0.2644114601311702,
"grad_norm": 1.515834927558899,
"learning_rate": 2e-05,
"loss": 0.9232,
"step": 766
},
{
"epoch": 0.2647566448049707,
"grad_norm": 1.6821200847625732,
"learning_rate": 2e-05,
"loss": 0.8878,
"step": 767
},
{
"epoch": 0.26510182947877114,
"grad_norm": 1.6648080348968506,
"learning_rate": 2e-05,
"loss": 0.9165,
"step": 768
},
{
"epoch": 0.2654470141525716,
"grad_norm": 1.9394623041152954,
"learning_rate": 2e-05,
"loss": 0.9148,
"step": 769
},
{
"epoch": 0.2657921988263721,
"grad_norm": 2.4916532039642334,
"learning_rate": 2e-05,
"loss": 0.9865,
"step": 770
},
{
"epoch": 0.2661373835001726,
"grad_norm": 1.6897066831588745,
"learning_rate": 2e-05,
"loss": 0.9648,
"step": 771
},
{
"epoch": 0.2664825681739731,
"grad_norm": 1.78070068359375,
"learning_rate": 2e-05,
"loss": 0.9886,
"step": 772
},
{
"epoch": 0.26682775284777355,
"grad_norm": 1.6246932744979858,
"learning_rate": 2e-05,
"loss": 0.9563,
"step": 773
},
{
"epoch": 0.26717293752157406,
"grad_norm": 1.588151454925537,
"learning_rate": 2e-05,
"loss": 0.9383,
"step": 774
},
{
"epoch": 0.2675181221953745,
"grad_norm": 2.021819591522217,
"learning_rate": 2e-05,
"loss": 0.9145,
"step": 775
},
{
"epoch": 0.26786330686917503,
"grad_norm": 1.529710292816162,
"learning_rate": 2e-05,
"loss": 0.9574,
"step": 776
},
{
"epoch": 0.2682084915429755,
"grad_norm": 1.8142794370651245,
"learning_rate": 2e-05,
"loss": 0.9996,
"step": 777
},
{
"epoch": 0.26855367621677595,
"grad_norm": 1.7581377029418945,
"learning_rate": 2e-05,
"loss": 0.9296,
"step": 778
},
{
"epoch": 0.26889886089057646,
"grad_norm": 1.7572534084320068,
"learning_rate": 2e-05,
"loss": 0.9383,
"step": 779
},
{
"epoch": 0.2692440455643769,
"grad_norm": 1.6054904460906982,
"learning_rate": 2e-05,
"loss": 0.9062,
"step": 780
},
{
"epoch": 0.26958923023817744,
"grad_norm": 1.7486181259155273,
"learning_rate": 2e-05,
"loss": 0.9292,
"step": 781
},
{
"epoch": 0.2699344149119779,
"grad_norm": 1.6551092863082886,
"learning_rate": 2e-05,
"loss": 0.8319,
"step": 782
},
{
"epoch": 0.2702795995857784,
"grad_norm": 2.0110371112823486,
"learning_rate": 2e-05,
"loss": 0.9898,
"step": 783
},
{
"epoch": 0.27062478425957887,
"grad_norm": 1.6469950675964355,
"learning_rate": 2e-05,
"loss": 0.8295,
"step": 784
},
{
"epoch": 0.2709699689333794,
"grad_norm": 1.765363335609436,
"learning_rate": 2e-05,
"loss": 0.961,
"step": 785
},
{
"epoch": 0.27131515360717984,
"grad_norm": 1.6705784797668457,
"learning_rate": 2e-05,
"loss": 0.9283,
"step": 786
},
{
"epoch": 0.27166033828098035,
"grad_norm": 1.784940481185913,
"learning_rate": 2e-05,
"loss": 0.946,
"step": 787
},
{
"epoch": 0.2720055229547808,
"grad_norm": 1.7462352514266968,
"learning_rate": 2e-05,
"loss": 0.916,
"step": 788
},
{
"epoch": 0.27235070762858127,
"grad_norm": 1.7009105682373047,
"learning_rate": 2e-05,
"loss": 0.8394,
"step": 789
},
{
"epoch": 0.2726958923023818,
"grad_norm": 2.4563820362091064,
"learning_rate": 2e-05,
"loss": 0.9461,
"step": 790
},
{
"epoch": 0.27304107697618224,
"grad_norm": 1.7224385738372803,
"learning_rate": 2e-05,
"loss": 0.9249,
"step": 791
},
{
"epoch": 0.27338626164998275,
"grad_norm": 1.8439266681671143,
"learning_rate": 2e-05,
"loss": 0.925,
"step": 792
},
{
"epoch": 0.2737314463237832,
"grad_norm": 1.7695287466049194,
"learning_rate": 2e-05,
"loss": 0.9225,
"step": 793
},
{
"epoch": 0.2740766309975837,
"grad_norm": 1.8887242078781128,
"learning_rate": 2e-05,
"loss": 0.9009,
"step": 794
},
{
"epoch": 0.2744218156713842,
"grad_norm": 1.554460883140564,
"learning_rate": 2e-05,
"loss": 0.8906,
"step": 795
},
{
"epoch": 0.2747670003451847,
"grad_norm": 1.7165745496749878,
"learning_rate": 2e-05,
"loss": 0.9627,
"step": 796
},
{
"epoch": 0.27511218501898516,
"grad_norm": 1.60774564743042,
"learning_rate": 2e-05,
"loss": 0.9952,
"step": 797
},
{
"epoch": 0.2754573696927856,
"grad_norm": 1.6151418685913086,
"learning_rate": 2e-05,
"loss": 0.9684,
"step": 798
},
{
"epoch": 0.27580255436658613,
"grad_norm": 1.7905076742172241,
"learning_rate": 2e-05,
"loss": 0.922,
"step": 799
},
{
"epoch": 0.2761477390403866,
"grad_norm": 1.731622338294983,
"learning_rate": 2e-05,
"loss": 0.9088,
"step": 800
}
],
"logging_steps": 1.0,
"max_steps": 14485,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 330497733427200.0,
"train_batch_size": 12,
"trial_name": null,
"trial_params": null
}