SKNahin's picture
End of training
d409899 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 154,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012987012987012988,
"grad_norm": 0.18144113461390085,
"learning_rate": 5e-05,
"loss": 1.0999,
"step": 1
},
{
"epoch": 0.025974025974025976,
"grad_norm": 0.23032732922747598,
"learning_rate": 4.999472998758978e-05,
"loss": 1.1136,
"step": 2
},
{
"epoch": 0.03896103896103896,
"grad_norm": 0.4242438104270526,
"learning_rate": 4.99789221722016e-05,
"loss": 1.117,
"step": 3
},
{
"epoch": 0.05194805194805195,
"grad_norm": 0.13949563534262774,
"learning_rate": 4.995258321842611e-05,
"loss": 1.1443,
"step": 4
},
{
"epoch": 0.06493506493506493,
"grad_norm": 0.13514225593950582,
"learning_rate": 4.991572423079236e-05,
"loss": 1.0891,
"step": 5
},
{
"epoch": 0.07792207792207792,
"grad_norm": 0.14984418288923035,
"learning_rate": 4.986836074908616e-05,
"loss": 1.0726,
"step": 6
},
{
"epoch": 0.09090909090909091,
"grad_norm": 0.12653097266120492,
"learning_rate": 4.98105127417984e-05,
"loss": 1.0409,
"step": 7
},
{
"epoch": 0.1038961038961039,
"grad_norm": 0.11446226508433231,
"learning_rate": 4.974220459770639e-05,
"loss": 1.0037,
"step": 8
},
{
"epoch": 0.11688311688311688,
"grad_norm": 0.12538536445416737,
"learning_rate": 4.966346511559149e-05,
"loss": 1.0099,
"step": 9
},
{
"epoch": 0.12987012987012986,
"grad_norm": 0.13956358176650924,
"learning_rate": 4.957432749209755e-05,
"loss": 0.9622,
"step": 10
},
{
"epoch": 0.14285714285714285,
"grad_norm": 0.13023502553169922,
"learning_rate": 4.9474829307735115e-05,
"loss": 0.9268,
"step": 11
},
{
"epoch": 0.15584415584415584,
"grad_norm": 0.14573960009230288,
"learning_rate": 4.9365012511037514e-05,
"loss": 0.9193,
"step": 12
},
{
"epoch": 0.16883116883116883,
"grad_norm": 0.15714825644311314,
"learning_rate": 4.9244923400875245e-05,
"loss": 0.9041,
"step": 13
},
{
"epoch": 0.18181818181818182,
"grad_norm": 0.23471225872389656,
"learning_rate": 4.911461260693638e-05,
"loss": 0.8208,
"step": 14
},
{
"epoch": 0.19480519480519481,
"grad_norm": 0.17775946949108917,
"learning_rate": 4.8974135068381036e-05,
"loss": 0.7785,
"step": 15
},
{
"epoch": 0.2077922077922078,
"grad_norm": 0.19437928872049462,
"learning_rate": 4.882355001067892e-05,
"loss": 0.7853,
"step": 16
},
{
"epoch": 0.22077922077922077,
"grad_norm": 0.19322817025233702,
"learning_rate": 4.8662920920639866e-05,
"loss": 0.7249,
"step": 17
},
{
"epoch": 0.23376623376623376,
"grad_norm": 0.20058294537861102,
"learning_rate": 4.849231551964771e-05,
"loss": 0.6819,
"step": 18
},
{
"epoch": 0.24675324675324675,
"grad_norm": 0.21732448821139638,
"learning_rate": 4.8311805735108894e-05,
"loss": 0.6567,
"step": 19
},
{
"epoch": 0.2597402597402597,
"grad_norm": 0.23709930298897716,
"learning_rate": 4.81214676701278e-05,
"loss": 0.5673,
"step": 20
},
{
"epoch": 0.2727272727272727,
"grad_norm": 0.2728207241894303,
"learning_rate": 4.792138157142158e-05,
"loss": 0.5222,
"step": 21
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.2553339334935731,
"learning_rate": 4.7711631795488096e-05,
"loss": 0.4701,
"step": 22
},
{
"epoch": 0.2987012987012987,
"grad_norm": 0.23197839119716365,
"learning_rate": 4.749230677304114e-05,
"loss": 0.4274,
"step": 23
},
{
"epoch": 0.3116883116883117,
"grad_norm": 0.21872873731232853,
"learning_rate": 4.726349897172791e-05,
"loss": 0.3741,
"step": 24
},
{
"epoch": 0.3246753246753247,
"grad_norm": 0.17857783786023249,
"learning_rate": 4.702530485714461e-05,
"loss": 0.3407,
"step": 25
},
{
"epoch": 0.33766233766233766,
"grad_norm": 0.17903424786616526,
"learning_rate": 4.677782485216644e-05,
"loss": 0.3233,
"step": 26
},
{
"epoch": 0.35064935064935066,
"grad_norm": 0.15061122938108154,
"learning_rate": 4.6521163294609196e-05,
"loss": 0.2983,
"step": 27
},
{
"epoch": 0.36363636363636365,
"grad_norm": 0.14543691061657488,
"learning_rate": 4.625542839324036e-05,
"loss": 0.3219,
"step": 28
},
{
"epoch": 0.37662337662337664,
"grad_norm": 0.1295659588775802,
"learning_rate": 4.598073218215817e-05,
"loss": 0.3157,
"step": 29
},
{
"epoch": 0.38961038961038963,
"grad_norm": 0.12301948743109298,
"learning_rate": 4.5697190473557946e-05,
"loss": 0.275,
"step": 30
},
{
"epoch": 0.4025974025974026,
"grad_norm": 0.1257222959274228,
"learning_rate": 4.540492280890555e-05,
"loss": 0.2861,
"step": 31
},
{
"epoch": 0.4155844155844156,
"grad_norm": 0.13782951808887584,
"learning_rate": 4.510405240853854e-05,
"loss": 0.2741,
"step": 32
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.1111597988935005,
"learning_rate": 4.4794706119716455e-05,
"loss": 0.2997,
"step": 33
},
{
"epoch": 0.44155844155844154,
"grad_norm": 0.12816107050100844,
"learning_rate": 4.447701436314176e-05,
"loss": 0.2867,
"step": 34
},
{
"epoch": 0.45454545454545453,
"grad_norm": 0.11428514810989718,
"learning_rate": 4.415111107797445e-05,
"loss": 0.2559,
"step": 35
},
{
"epoch": 0.4675324675324675,
"grad_norm": 0.13727102269725863,
"learning_rate": 4.381713366536311e-05,
"loss": 0.2683,
"step": 36
},
{
"epoch": 0.4805194805194805,
"grad_norm": 0.13944308581694792,
"learning_rate": 4.347522293051648e-05,
"loss": 0.2473,
"step": 37
},
{
"epoch": 0.4935064935064935,
"grad_norm": 0.11515884356963244,
"learning_rate": 4.312552302333982e-05,
"loss": 0.2596,
"step": 38
},
{
"epoch": 0.5064935064935064,
"grad_norm": 0.16402738244448228,
"learning_rate": 4.276818137766118e-05,
"loss": 0.2733,
"step": 39
},
{
"epoch": 0.5194805194805194,
"grad_norm": 0.11249447066822464,
"learning_rate": 4.2403348649073174e-05,
"loss": 0.2644,
"step": 40
},
{
"epoch": 0.5324675324675324,
"grad_norm": 0.09977226412522378,
"learning_rate": 4.203117865141635e-05,
"loss": 0.245,
"step": 41
},
{
"epoch": 0.5454545454545454,
"grad_norm": 0.10594808589466843,
"learning_rate": 4.1651828291931264e-05,
"loss": 0.2665,
"step": 42
},
{
"epoch": 0.5584415584415584,
"grad_norm": 0.10830822496604134,
"learning_rate": 4.126545750510605e-05,
"loss": 0.2561,
"step": 43
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.1559908437327689,
"learning_rate": 4.0872229185248075e-05,
"loss": 0.2737,
"step": 44
},
{
"epoch": 0.5844155844155844,
"grad_norm": 0.09988303145068146,
"learning_rate": 4.047230911780737e-05,
"loss": 0.2244,
"step": 45
},
{
"epoch": 0.5974025974025974,
"grad_norm": 0.1288226897900868,
"learning_rate": 4.0065865909481417e-05,
"loss": 0.2475,
"step": 46
},
{
"epoch": 0.6103896103896104,
"grad_norm": 0.12903928820913718,
"learning_rate": 3.965307091713037e-05,
"loss": 0.2512,
"step": 47
},
{
"epoch": 0.6233766233766234,
"grad_norm": 0.11575890096611409,
"learning_rate": 3.923409817553284e-05,
"loss": 0.2317,
"step": 48
},
{
"epoch": 0.6363636363636364,
"grad_norm": 0.12776553215236372,
"learning_rate": 3.880912432401265e-05,
"loss": 0.2354,
"step": 49
},
{
"epoch": 0.6493506493506493,
"grad_norm": 0.09574018706970228,
"learning_rate": 3.837832853196751e-05,
"loss": 0.2453,
"step": 50
},
{
"epoch": 0.6623376623376623,
"grad_norm": 0.14189226736209729,
"learning_rate": 3.794189242333106e-05,
"loss": 0.2585,
"step": 51
},
{
"epoch": 0.6753246753246753,
"grad_norm": 0.10649210075361353,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.2322,
"step": 52
},
{
"epoch": 0.6883116883116883,
"grad_norm": 0.10920114430754739,
"learning_rate": 3.705283756425872e-05,
"loss": 0.2551,
"step": 53
},
{
"epoch": 0.7012987012987013,
"grad_norm": 0.11682678153514109,
"learning_rate": 3.6600593640234086e-05,
"loss": 0.2463,
"step": 54
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.12836916469010362,
"learning_rate": 3.6143458894413465e-05,
"loss": 0.2484,
"step": 55
},
{
"epoch": 0.7272727272727273,
"grad_norm": 0.11178024025521166,
"learning_rate": 3.568162605525953e-05,
"loss": 0.2468,
"step": 56
},
{
"epoch": 0.7402597402597403,
"grad_norm": 0.1010380015595644,
"learning_rate": 3.5215289831955786e-05,
"loss": 0.2516,
"step": 57
},
{
"epoch": 0.7532467532467533,
"grad_norm": 0.085784899994474,
"learning_rate": 3.474464683231698e-05,
"loss": 0.2236,
"step": 58
},
{
"epoch": 0.7662337662337663,
"grad_norm": 0.13947209045153394,
"learning_rate": 3.426989547989902e-05,
"loss": 0.2525,
"step": 59
},
{
"epoch": 0.7792207792207793,
"grad_norm": 0.13889886189167572,
"learning_rate": 3.379123593034342e-05,
"loss": 0.2246,
"step": 60
},
{
"epoch": 0.7922077922077922,
"grad_norm": 0.13859464920490144,
"learning_rate": 3.330886998699149e-05,
"loss": 0.2282,
"step": 61
},
{
"epoch": 0.8051948051948052,
"grad_norm": 0.12266245312170791,
"learning_rate": 3.282300101580386e-05,
"loss": 0.24,
"step": 62
},
{
"epoch": 0.8181818181818182,
"grad_norm": 0.10874801908049964,
"learning_rate": 3.2333833859621153e-05,
"loss": 0.2167,
"step": 63
},
{
"epoch": 0.8311688311688312,
"grad_norm": 0.14138294201534896,
"learning_rate": 3.1841574751802076e-05,
"loss": 0.237,
"step": 64
},
{
"epoch": 0.8441558441558441,
"grad_norm": 0.09884384035255168,
"learning_rate": 3.13464312292752e-05,
"loss": 0.2245,
"step": 65
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.10988380829000544,
"learning_rate": 3.084861204504122e-05,
"loss": 0.223,
"step": 66
},
{
"epoch": 0.8701298701298701,
"grad_norm": 0.11209266526012397,
"learning_rate": 3.0348327080162435e-05,
"loss": 0.2461,
"step": 67
},
{
"epoch": 0.8831168831168831,
"grad_norm": 0.10525055273584627,
"learning_rate": 2.9845787255276753e-05,
"loss": 0.2315,
"step": 68
},
{
"epoch": 0.8961038961038961,
"grad_norm": 0.10152599128895917,
"learning_rate": 2.9341204441673266e-05,
"loss": 0.2191,
"step": 69
},
{
"epoch": 0.9090909090909091,
"grad_norm": 0.10226640825737425,
"learning_rate": 2.8834791371967142e-05,
"loss": 0.2466,
"step": 70
},
{
"epoch": 0.922077922077922,
"grad_norm": 0.10423067422254412,
"learning_rate": 2.8326761550411345e-05,
"loss": 0.2376,
"step": 71
},
{
"epoch": 0.935064935064935,
"grad_norm": 0.10976215204067583,
"learning_rate": 2.781732916288303e-05,
"loss": 0.2404,
"step": 72
},
{
"epoch": 0.948051948051948,
"grad_norm": 0.1035692636894243,
"learning_rate": 2.7306708986582553e-05,
"loss": 0.259,
"step": 73
},
{
"epoch": 0.961038961038961,
"grad_norm": 0.14063555362021704,
"learning_rate": 2.679511629948319e-05,
"loss": 0.2438,
"step": 74
},
{
"epoch": 0.974025974025974,
"grad_norm": 0.9597181120586398,
"learning_rate": 2.628276678956974e-05,
"loss": 0.2442,
"step": 75
},
{
"epoch": 0.987012987012987,
"grad_norm": 0.1203799439431295,
"learning_rate": 2.5769876463904265e-05,
"loss": 0.2366,
"step": 76
},
{
"epoch": 1.0,
"grad_norm": 0.09597247653833042,
"learning_rate": 2.5256661557557247e-05,
"loss": 0.238,
"step": 77
},
{
"epoch": 1.0129870129870129,
"grad_norm": 0.09579838644516969,
"learning_rate": 2.4743338442442755e-05,
"loss": 0.2335,
"step": 78
},
{
"epoch": 1.025974025974026,
"grad_norm": 0.13620749307450852,
"learning_rate": 2.4230123536095748e-05,
"loss": 0.245,
"step": 79
},
{
"epoch": 1.0389610389610389,
"grad_norm": 0.08863848063701799,
"learning_rate": 2.3717233210430256e-05,
"loss": 0.2213,
"step": 80
},
{
"epoch": 1.051948051948052,
"grad_norm": 0.1046252531819379,
"learning_rate": 2.3204883700516812e-05,
"loss": 0.2353,
"step": 81
},
{
"epoch": 1.0649350649350648,
"grad_norm": 0.09712895373564606,
"learning_rate": 2.2693291013417453e-05,
"loss": 0.2266,
"step": 82
},
{
"epoch": 1.077922077922078,
"grad_norm": 0.1049298738716712,
"learning_rate": 2.2182670837116975e-05,
"loss": 0.2503,
"step": 83
},
{
"epoch": 1.0909090909090908,
"grad_norm": 0.10947482026387487,
"learning_rate": 2.1673238449588668e-05,
"loss": 0.2464,
"step": 84
},
{
"epoch": 1.103896103896104,
"grad_norm": 0.09384377240838161,
"learning_rate": 2.116520862803286e-05,
"loss": 0.2075,
"step": 85
},
{
"epoch": 1.1168831168831168,
"grad_norm": 0.10452746319843585,
"learning_rate": 2.0658795558326743e-05,
"loss": 0.2021,
"step": 86
},
{
"epoch": 1.12987012987013,
"grad_norm": 0.09899057248726559,
"learning_rate": 2.015421274472325e-05,
"loss": 0.2033,
"step": 87
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.09826518503965749,
"learning_rate": 1.965167291983757e-05,
"loss": 0.2109,
"step": 88
},
{
"epoch": 1.155844155844156,
"grad_norm": 0.0985826451923068,
"learning_rate": 1.9151387954958794e-05,
"loss": 0.2073,
"step": 89
},
{
"epoch": 1.1688311688311688,
"grad_norm": 0.09710768909185251,
"learning_rate": 1.8653568770724806e-05,
"loss": 0.2126,
"step": 90
},
{
"epoch": 1.1818181818181819,
"grad_norm": 0.10690715430327113,
"learning_rate": 1.815842524819793e-05,
"loss": 0.199,
"step": 91
},
{
"epoch": 1.1948051948051948,
"grad_norm": 0.09404290387080795,
"learning_rate": 1.7666166140378852e-05,
"loss": 0.209,
"step": 92
},
{
"epoch": 1.2077922077922079,
"grad_norm": 0.09685266845623604,
"learning_rate": 1.7176998984196146e-05,
"loss": 0.2111,
"step": 93
},
{
"epoch": 1.2207792207792207,
"grad_norm": 0.12797307846931577,
"learning_rate": 1.6691130013008514e-05,
"loss": 0.2169,
"step": 94
},
{
"epoch": 1.2337662337662338,
"grad_norm": 0.09459374702406319,
"learning_rate": 1.620876406965658e-05,
"loss": 0.2156,
"step": 95
},
{
"epoch": 1.2467532467532467,
"grad_norm": 0.11356481706534574,
"learning_rate": 1.5730104520100982e-05,
"loss": 0.2373,
"step": 96
},
{
"epoch": 1.2597402597402598,
"grad_norm": 0.0979596040625175,
"learning_rate": 1.5255353167683017e-05,
"loss": 0.2301,
"step": 97
},
{
"epoch": 1.2727272727272727,
"grad_norm": 0.11027200176584859,
"learning_rate": 1.4784710168044213e-05,
"loss": 0.2418,
"step": 98
},
{
"epoch": 1.2857142857142856,
"grad_norm": 0.10844293714708106,
"learning_rate": 1.4318373944740484e-05,
"loss": 0.2008,
"step": 99
},
{
"epoch": 1.2987012987012987,
"grad_norm": 0.10604532957507184,
"learning_rate": 1.3856541105586545e-05,
"loss": 0.2071,
"step": 100
},
{
"epoch": 1.3116883116883118,
"grad_norm": 0.11015549612393535,
"learning_rate": 1.339940635976592e-05,
"loss": 0.2028,
"step": 101
},
{
"epoch": 1.3246753246753247,
"grad_norm": 0.1034248530061317,
"learning_rate": 1.2947162435741278e-05,
"loss": 0.2465,
"step": 102
},
{
"epoch": 1.3376623376623376,
"grad_norm": 0.09802522224283734,
"learning_rate": 1.2500000000000006e-05,
"loss": 0.2241,
"step": 103
},
{
"epoch": 1.3506493506493507,
"grad_norm": 0.14178769263776372,
"learning_rate": 1.205810757666894e-05,
"loss": 0.2248,
"step": 104
},
{
"epoch": 1.3636363636363638,
"grad_norm": 0.11033086188055496,
"learning_rate": 1.1621671468032493e-05,
"loss": 0.2031,
"step": 105
},
{
"epoch": 1.3766233766233766,
"grad_norm": 0.10556352756700285,
"learning_rate": 1.1190875675987356e-05,
"loss": 0.2423,
"step": 106
},
{
"epoch": 1.3896103896103895,
"grad_norm": 0.10622962825704242,
"learning_rate": 1.0765901824467167e-05,
"loss": 0.2267,
"step": 107
},
{
"epoch": 1.4025974025974026,
"grad_norm": 0.1421477896111532,
"learning_rate": 1.0346929082869641e-05,
"loss": 0.2263,
"step": 108
},
{
"epoch": 1.4155844155844157,
"grad_norm": 0.10648219200325142,
"learning_rate": 9.934134090518593e-06,
"loss": 0.1941,
"step": 109
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.1057487742668598,
"learning_rate": 9.527690882192636e-06,
"loss": 0.2211,
"step": 110
},
{
"epoch": 1.4415584415584415,
"grad_norm": 0.10788661622220058,
"learning_rate": 9.127770814751933e-06,
"loss": 0.2175,
"step": 111
},
{
"epoch": 1.4545454545454546,
"grad_norm": 0.1363593925410807,
"learning_rate": 8.734542494893955e-06,
"loss": 0.258,
"step": 112
},
{
"epoch": 1.4675324675324675,
"grad_norm": 0.10238450016241465,
"learning_rate": 8.348171708068747e-06,
"loss": 0.2061,
"step": 113
},
{
"epoch": 1.4805194805194806,
"grad_norm": 0.10248345724192277,
"learning_rate": 7.968821348583644e-06,
"loss": 0.2367,
"step": 114
},
{
"epoch": 1.4935064935064934,
"grad_norm": 0.1008163725183197,
"learning_rate": 7.5966513509268365e-06,
"loss": 0.1913,
"step": 115
},
{
"epoch": 1.5064935064935066,
"grad_norm": 0.11368875761071572,
"learning_rate": 7.231818622338823e-06,
"loss": 0.2311,
"step": 116
},
{
"epoch": 1.5194805194805194,
"grad_norm": 0.10611786603146683,
"learning_rate": 6.8744769766601854e-06,
"loss": 0.2195,
"step": 117
},
{
"epoch": 1.5324675324675323,
"grad_norm": 0.16883578702676916,
"learning_rate": 6.524777069483526e-06,
"loss": 0.21,
"step": 118
},
{
"epoch": 1.5454545454545454,
"grad_norm": 0.3916790615317874,
"learning_rate": 6.182866334636889e-06,
"loss": 0.1902,
"step": 119
},
{
"epoch": 1.5584415584415585,
"grad_norm": 0.10344358329557357,
"learning_rate": 5.848888922025553e-06,
"loss": 0.2293,
"step": 120
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.10663200516115459,
"learning_rate": 5.522985636858239e-06,
"loss": 0.227,
"step": 121
},
{
"epoch": 1.5844155844155843,
"grad_norm": 0.09225160387433178,
"learning_rate": 5.205293880283552e-06,
"loss": 0.1884,
"step": 122
},
{
"epoch": 1.5974025974025974,
"grad_norm": 0.10313365280428856,
"learning_rate": 4.8959475914614554e-06,
"loss": 0.2241,
"step": 123
},
{
"epoch": 1.6103896103896105,
"grad_norm": 0.0999145020748516,
"learning_rate": 4.5950771910944605e-06,
"loss": 0.215,
"step": 124
},
{
"epoch": 1.6233766233766234,
"grad_norm": 0.1117717811624237,
"learning_rate": 4.3028095264420535e-06,
"loss": 0.2213,
"step": 125
},
{
"epoch": 1.6363636363636362,
"grad_norm": 0.11041126744122085,
"learning_rate": 4.019267817841835e-06,
"loss": 0.2278,
"step": 126
},
{
"epoch": 1.6493506493506493,
"grad_norm": 0.10135009905974361,
"learning_rate": 3.7445716067596503e-06,
"loss": 0.1999,
"step": 127
},
{
"epoch": 1.6623376623376624,
"grad_norm": 0.11867580501114842,
"learning_rate": 3.478836705390809e-06,
"loss": 0.2341,
"step": 128
},
{
"epoch": 1.6753246753246753,
"grad_norm": 0.10320476535311193,
"learning_rate": 3.222175147833556e-06,
"loss": 0.2206,
"step": 129
},
{
"epoch": 1.6883116883116882,
"grad_norm": 0.11168179403192097,
"learning_rate": 2.974695142855388e-06,
"loss": 0.2408,
"step": 130
},
{
"epoch": 1.7012987012987013,
"grad_norm": 0.1125984540823009,
"learning_rate": 2.7365010282720952e-06,
"loss": 0.2164,
"step": 131
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.09569488160276661,
"learning_rate": 2.507693226958871e-06,
"loss": 0.2044,
"step": 132
},
{
"epoch": 1.7272727272727273,
"grad_norm": 0.15157539119477123,
"learning_rate": 2.2883682045119063e-06,
"loss": 0.1979,
"step": 133
},
{
"epoch": 1.7402597402597402,
"grad_norm": 0.11616095837214428,
"learning_rate": 2.0786184285784297e-06,
"loss": 0.2124,
"step": 134
},
{
"epoch": 1.7532467532467533,
"grad_norm": 0.1146841773253501,
"learning_rate": 1.8785323298722097e-06,
"loss": 0.2435,
"step": 135
},
{
"epoch": 1.7662337662337664,
"grad_norm": 0.11483142271925956,
"learning_rate": 1.6881942648911076e-06,
"loss": 0.2092,
"step": 136
},
{
"epoch": 1.7792207792207793,
"grad_norm": 0.09833676885705019,
"learning_rate": 1.5076844803522922e-06,
"loss": 0.2117,
"step": 137
},
{
"epoch": 1.7922077922077921,
"grad_norm": 0.0995771697098598,
"learning_rate": 1.3370790793601373e-06,
"loss": 0.2325,
"step": 138
},
{
"epoch": 1.8051948051948052,
"grad_norm": 0.09445215715425767,
"learning_rate": 1.1764499893210878e-06,
"loss": 0.186,
"step": 139
},
{
"epoch": 1.8181818181818183,
"grad_norm": 0.11698733467556797,
"learning_rate": 1.0258649316189722e-06,
"loss": 0.1942,
"step": 140
},
{
"epoch": 1.8311688311688312,
"grad_norm": 0.10350738235418655,
"learning_rate": 8.85387393063622e-07,
"loss": 0.2093,
"step": 141
},
{
"epoch": 1.844155844155844,
"grad_norm": 0.1320557339644457,
"learning_rate": 7.550765991247654e-07,
"loss": 0.2134,
"step": 142
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.11723658145778595,
"learning_rate": 6.349874889624962e-07,
"loss": 0.2068,
"step": 143
},
{
"epoch": 1.87012987012987,
"grad_norm": 0.0943770110295723,
"learning_rate": 5.25170692264887e-07,
"loss": 0.2025,
"step": 144
},
{
"epoch": 1.883116883116883,
"grad_norm": 0.10423983848555778,
"learning_rate": 4.256725079024554e-07,
"loss": 0.2288,
"step": 145
},
{
"epoch": 1.896103896103896,
"grad_norm": 0.11847062226348895,
"learning_rate": 3.3653488440851255e-07,
"loss": 0.2264,
"step": 146
},
{
"epoch": 1.9090909090909092,
"grad_norm": 0.14252192764477026,
"learning_rate": 2.5779540229361745e-07,
"loss": 0.211,
"step": 147
},
{
"epoch": 1.922077922077922,
"grad_norm": 0.10277127195084139,
"learning_rate": 1.8948725820160662e-07,
"loss": 0.2003,
"step": 148
},
{
"epoch": 1.935064935064935,
"grad_norm": 0.11579327333733375,
"learning_rate": 1.3163925091384533e-07,
"loss": 0.2245,
"step": 149
},
{
"epoch": 1.948051948051948,
"grad_norm": 0.10964012331355301,
"learning_rate": 8.427576920763958e-08,
"loss": 0.1908,
"step": 150
},
{
"epoch": 1.9610389610389611,
"grad_norm": 0.10331672937700692,
"learning_rate": 4.741678157389739e-08,
"loss": 0.1992,
"step": 151
},
{
"epoch": 1.974025974025974,
"grad_norm": 0.10867464652832311,
"learning_rate": 2.1077827798404726e-08,
"loss": 0.2069,
"step": 152
},
{
"epoch": 1.987012987012987,
"grad_norm": 0.09129517660776866,
"learning_rate": 5.270012410216185e-09,
"loss": 0.1865,
"step": 153
},
{
"epoch": 2.0,
"grad_norm": 0.101463897247349,
"learning_rate": 0.0,
"loss": 0.1957,
"step": 154
},
{
"epoch": 2.0,
"step": 154,
"total_flos": 98079354388480.0,
"train_loss": 0.32735763886919267,
"train_runtime": 1594.7329,
"train_samples_per_second": 0.384,
"train_steps_per_second": 0.097
}
],
"logging_steps": 1,
"max_steps": 154,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 98079354388480.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}