SKNahin's picture
End of training
facf935 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": 0.18787174345625757,
"learning_rate": 5e-05,
"loss": 0.8483,
"step": 1
},
{
"epoch": 0.025974025974025976,
"grad_norm": 0.1881876180971173,
"learning_rate": 4.999472998758978e-05,
"loss": 0.8274,
"step": 2
},
{
"epoch": 0.03896103896103896,
"grad_norm": 0.2484116599817621,
"learning_rate": 4.99789221722016e-05,
"loss": 0.9658,
"step": 3
},
{
"epoch": 0.05194805194805195,
"grad_norm": 0.2687834599860072,
"learning_rate": 4.995258321842611e-05,
"loss": 0.9686,
"step": 4
},
{
"epoch": 0.06493506493506493,
"grad_norm": 0.14459778376590973,
"learning_rate": 4.991572423079236e-05,
"loss": 0.8246,
"step": 5
},
{
"epoch": 0.07792207792207792,
"grad_norm": 0.12789380689263963,
"learning_rate": 4.986836074908616e-05,
"loss": 0.8481,
"step": 6
},
{
"epoch": 0.09090909090909091,
"grad_norm": 0.1241999521840537,
"learning_rate": 4.98105127417984e-05,
"loss": 0.8287,
"step": 7
},
{
"epoch": 0.1038961038961039,
"grad_norm": 0.12124312827410104,
"learning_rate": 4.974220459770639e-05,
"loss": 0.7255,
"step": 8
},
{
"epoch": 0.11688311688311688,
"grad_norm": 0.10261829314704707,
"learning_rate": 4.966346511559149e-05,
"loss": 0.8029,
"step": 9
},
{
"epoch": 0.12987012987012986,
"grad_norm": 0.11018416242062518,
"learning_rate": 4.957432749209755e-05,
"loss": 0.7758,
"step": 10
},
{
"epoch": 0.14285714285714285,
"grad_norm": 0.15464498064215176,
"learning_rate": 4.9474829307735115e-05,
"loss": 0.738,
"step": 11
},
{
"epoch": 0.15584415584415584,
"grad_norm": 0.128517721396635,
"learning_rate": 4.9365012511037514e-05,
"loss": 0.7488,
"step": 12
},
{
"epoch": 0.16883116883116883,
"grad_norm": 0.16896802409788272,
"learning_rate": 4.9244923400875245e-05,
"loss": 0.7788,
"step": 13
},
{
"epoch": 0.18181818181818182,
"grad_norm": 0.11228565989870234,
"learning_rate": 4.911461260693638e-05,
"loss": 0.6975,
"step": 14
},
{
"epoch": 0.19480519480519481,
"grad_norm": 0.11221173687008401,
"learning_rate": 4.8974135068381036e-05,
"loss": 0.6526,
"step": 15
},
{
"epoch": 0.2077922077922078,
"grad_norm": 0.1282885413456516,
"learning_rate": 4.882355001067892e-05,
"loss": 0.7019,
"step": 16
},
{
"epoch": 0.22077922077922077,
"grad_norm": 0.13827934971027034,
"learning_rate": 4.8662920920639866e-05,
"loss": 0.6399,
"step": 17
},
{
"epoch": 0.23376623376623376,
"grad_norm": 0.14252803580500878,
"learning_rate": 4.849231551964771e-05,
"loss": 0.5874,
"step": 18
},
{
"epoch": 0.24675324675324675,
"grad_norm": 0.1567378099302403,
"learning_rate": 4.8311805735108894e-05,
"loss": 0.5871,
"step": 19
},
{
"epoch": 0.2597402597402597,
"grad_norm": 0.18892688129002116,
"learning_rate": 4.81214676701278e-05,
"loss": 0.5562,
"step": 20
},
{
"epoch": 0.2727272727272727,
"grad_norm": 0.3374448073807016,
"learning_rate": 4.792138157142158e-05,
"loss": 0.5319,
"step": 21
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.25712355804452103,
"learning_rate": 4.7711631795488096e-05,
"loss": 0.4744,
"step": 22
},
{
"epoch": 0.2987012987012987,
"grad_norm": 0.24700691510131254,
"learning_rate": 4.749230677304114e-05,
"loss": 0.444,
"step": 23
},
{
"epoch": 0.3116883116883117,
"grad_norm": 0.22489370668384237,
"learning_rate": 4.726349897172791e-05,
"loss": 0.3836,
"step": 24
},
{
"epoch": 0.3246753246753247,
"grad_norm": 0.19240095528864964,
"learning_rate": 4.702530485714461e-05,
"loss": 0.3523,
"step": 25
},
{
"epoch": 0.33766233766233766,
"grad_norm": 0.2888062734923711,
"learning_rate": 4.677782485216644e-05,
"loss": 0.3246,
"step": 26
},
{
"epoch": 0.35064935064935066,
"grad_norm": 0.1578459013655223,
"learning_rate": 4.6521163294609196e-05,
"loss": 0.2807,
"step": 27
},
{
"epoch": 0.36363636363636365,
"grad_norm": 0.17049112601293237,
"learning_rate": 4.625542839324036e-05,
"loss": 0.3049,
"step": 28
},
{
"epoch": 0.37662337662337664,
"grad_norm": 0.10623476540468543,
"learning_rate": 4.598073218215817e-05,
"loss": 0.2877,
"step": 29
},
{
"epoch": 0.38961038961038963,
"grad_norm": 0.08997970383090283,
"learning_rate": 4.5697190473557946e-05,
"loss": 0.2773,
"step": 30
},
{
"epoch": 0.4025974025974026,
"grad_norm": 0.11033930425860525,
"learning_rate": 4.540492280890555e-05,
"loss": 0.2758,
"step": 31
},
{
"epoch": 0.4155844155844156,
"grad_norm": 0.12378835216257449,
"learning_rate": 4.510405240853854e-05,
"loss": 0.2389,
"step": 32
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.0810759730541574,
"learning_rate": 4.4794706119716455e-05,
"loss": 0.2756,
"step": 33
},
{
"epoch": 0.44155844155844154,
"grad_norm": 0.09746550952897874,
"learning_rate": 4.447701436314176e-05,
"loss": 0.2836,
"step": 34
},
{
"epoch": 0.45454545454545453,
"grad_norm": 0.08835165902502037,
"learning_rate": 4.415111107797445e-05,
"loss": 0.2363,
"step": 35
},
{
"epoch": 0.4675324675324675,
"grad_norm": 0.09871638815546385,
"learning_rate": 4.381713366536311e-05,
"loss": 0.261,
"step": 36
},
{
"epoch": 0.4805194805194805,
"grad_norm": 0.09771703372866393,
"learning_rate": 4.347522293051648e-05,
"loss": 0.2328,
"step": 37
},
{
"epoch": 0.4935064935064935,
"grad_norm": 0.08303169266120812,
"learning_rate": 4.312552302333982e-05,
"loss": 0.2669,
"step": 38
},
{
"epoch": 0.5064935064935064,
"grad_norm": 0.09110609687207077,
"learning_rate": 4.276818137766118e-05,
"loss": 0.2493,
"step": 39
},
{
"epoch": 0.5194805194805194,
"grad_norm": 0.0857887848090492,
"learning_rate": 4.2403348649073174e-05,
"loss": 0.256,
"step": 40
},
{
"epoch": 0.5324675324675324,
"grad_norm": 0.07992881618393588,
"learning_rate": 4.203117865141635e-05,
"loss": 0.2504,
"step": 41
},
{
"epoch": 0.5454545454545454,
"grad_norm": 0.10190426019208573,
"learning_rate": 4.1651828291931264e-05,
"loss": 0.2561,
"step": 42
},
{
"epoch": 0.5584415584415584,
"grad_norm": 0.09480915169746995,
"learning_rate": 4.126545750510605e-05,
"loss": 0.2571,
"step": 43
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.09362782945360802,
"learning_rate": 4.0872229185248075e-05,
"loss": 0.2472,
"step": 44
},
{
"epoch": 0.5844155844155844,
"grad_norm": 0.07394172741628195,
"learning_rate": 4.047230911780737e-05,
"loss": 0.2208,
"step": 45
},
{
"epoch": 0.5974025974025974,
"grad_norm": 0.0728323124890986,
"learning_rate": 4.0065865909481417e-05,
"loss": 0.2572,
"step": 46
},
{
"epoch": 0.6103896103896104,
"grad_norm": 0.10380156711543853,
"learning_rate": 3.965307091713037e-05,
"loss": 0.218,
"step": 47
},
{
"epoch": 0.6233766233766234,
"grad_norm": 0.09455312570599705,
"learning_rate": 3.923409817553284e-05,
"loss": 0.234,
"step": 48
},
{
"epoch": 0.6363636363636364,
"grad_norm": 0.08887812243253841,
"learning_rate": 3.880912432401265e-05,
"loss": 0.2037,
"step": 49
},
{
"epoch": 0.6493506493506493,
"grad_norm": 0.07668088360221971,
"learning_rate": 3.837832853196751e-05,
"loss": 0.242,
"step": 50
},
{
"epoch": 0.6623376623376623,
"grad_norm": 0.07759668294077805,
"learning_rate": 3.794189242333106e-05,
"loss": 0.2439,
"step": 51
},
{
"epoch": 0.6753246753246753,
"grad_norm": 0.09233954207922085,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.2081,
"step": 52
},
{
"epoch": 0.6883116883116883,
"grad_norm": 0.08183875046921972,
"learning_rate": 3.705283756425872e-05,
"loss": 0.2424,
"step": 53
},
{
"epoch": 0.7012987012987013,
"grad_norm": 0.10315585570133078,
"learning_rate": 3.6600593640234086e-05,
"loss": 0.2468,
"step": 54
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.08508686423963427,
"learning_rate": 3.6143458894413465e-05,
"loss": 0.2218,
"step": 55
},
{
"epoch": 0.7272727272727273,
"grad_norm": 0.08486843572184524,
"learning_rate": 3.568162605525953e-05,
"loss": 0.2322,
"step": 56
},
{
"epoch": 0.7402597402597403,
"grad_norm": 0.08545739449487202,
"learning_rate": 3.5215289831955786e-05,
"loss": 0.241,
"step": 57
},
{
"epoch": 0.7532467532467533,
"grad_norm": 0.06488948479052951,
"learning_rate": 3.474464683231698e-05,
"loss": 0.2249,
"step": 58
},
{
"epoch": 0.7662337662337663,
"grad_norm": 0.0904558318938033,
"learning_rate": 3.426989547989902e-05,
"loss": 0.2337,
"step": 59
},
{
"epoch": 0.7792207792207793,
"grad_norm": 0.09019149052874986,
"learning_rate": 3.379123593034342e-05,
"loss": 0.2112,
"step": 60
},
{
"epoch": 0.7922077922077922,
"grad_norm": 0.08328318607208472,
"learning_rate": 3.330886998699149e-05,
"loss": 0.2007,
"step": 61
},
{
"epoch": 0.8051948051948052,
"grad_norm": 0.08263878807320083,
"learning_rate": 3.282300101580386e-05,
"loss": 0.2259,
"step": 62
},
{
"epoch": 0.8181818181818182,
"grad_norm": 0.07957332172491985,
"learning_rate": 3.2333833859621153e-05,
"loss": 0.2251,
"step": 63
},
{
"epoch": 0.8311688311688312,
"grad_norm": 0.10440656634971286,
"learning_rate": 3.1841574751802076e-05,
"loss": 0.2114,
"step": 64
},
{
"epoch": 0.8441558441558441,
"grad_norm": 0.07647118607084558,
"learning_rate": 3.13464312292752e-05,
"loss": 0.2123,
"step": 65
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.08658758520644272,
"learning_rate": 3.084861204504122e-05,
"loss": 0.1994,
"step": 66
},
{
"epoch": 0.8701298701298701,
"grad_norm": 0.08858346318492633,
"learning_rate": 3.0348327080162435e-05,
"loss": 0.2377,
"step": 67
},
{
"epoch": 0.8831168831168831,
"grad_norm": 0.09235241797460036,
"learning_rate": 2.9845787255276753e-05,
"loss": 0.215,
"step": 68
},
{
"epoch": 0.8961038961038961,
"grad_norm": 0.0788972148991508,
"learning_rate": 2.9341204441673266e-05,
"loss": 0.2112,
"step": 69
},
{
"epoch": 0.9090909090909091,
"grad_norm": 0.08960215541982136,
"learning_rate": 2.8834791371967142e-05,
"loss": 0.2647,
"step": 70
},
{
"epoch": 0.922077922077922,
"grad_norm": 0.08380836318512074,
"learning_rate": 2.8326761550411345e-05,
"loss": 0.2431,
"step": 71
},
{
"epoch": 0.935064935064935,
"grad_norm": 0.09187039951568829,
"learning_rate": 2.781732916288303e-05,
"loss": 0.2479,
"step": 72
},
{
"epoch": 0.948051948051948,
"grad_norm": 0.09291540687726117,
"learning_rate": 2.7306708986582553e-05,
"loss": 0.2357,
"step": 73
},
{
"epoch": 0.961038961038961,
"grad_norm": 0.0832454958287789,
"learning_rate": 2.679511629948319e-05,
"loss": 0.236,
"step": 74
},
{
"epoch": 0.974025974025974,
"grad_norm": 0.07504819631461856,
"learning_rate": 2.628276678956974e-05,
"loss": 0.2288,
"step": 75
},
{
"epoch": 0.987012987012987,
"grad_norm": 0.10741006282709406,
"learning_rate": 2.5769876463904265e-05,
"loss": 0.2404,
"step": 76
},
{
"epoch": 1.0,
"grad_norm": 0.0825957236169846,
"learning_rate": 2.5256661557557247e-05,
"loss": 0.2436,
"step": 77
},
{
"epoch": 1.0129870129870129,
"grad_norm": 0.07684874681832127,
"learning_rate": 2.4743338442442755e-05,
"loss": 0.2244,
"step": 78
},
{
"epoch": 1.025974025974026,
"grad_norm": 0.07704336923237068,
"learning_rate": 2.4230123536095748e-05,
"loss": 0.2626,
"step": 79
},
{
"epoch": 1.0389610389610389,
"grad_norm": 0.07500658424467158,
"learning_rate": 2.3717233210430256e-05,
"loss": 0.2192,
"step": 80
},
{
"epoch": 1.051948051948052,
"grad_norm": 0.08184169243002529,
"learning_rate": 2.3204883700516812e-05,
"loss": 0.2148,
"step": 81
},
{
"epoch": 1.0649350649350648,
"grad_norm": 0.08482067089986454,
"learning_rate": 2.2693291013417453e-05,
"loss": 0.2113,
"step": 82
},
{
"epoch": 1.077922077922078,
"grad_norm": 0.10550670423205909,
"learning_rate": 2.2182670837116975e-05,
"loss": 0.2463,
"step": 83
},
{
"epoch": 1.0909090909090908,
"grad_norm": 0.07848865475761758,
"learning_rate": 2.1673238449588668e-05,
"loss": 0.2544,
"step": 84
},
{
"epoch": 1.103896103896104,
"grad_norm": 0.08116964479727118,
"learning_rate": 2.116520862803286e-05,
"loss": 0.203,
"step": 85
},
{
"epoch": 1.1168831168831168,
"grad_norm": 0.0773019598198873,
"learning_rate": 2.0658795558326743e-05,
"loss": 0.1896,
"step": 86
},
{
"epoch": 1.12987012987013,
"grad_norm": 0.08577851670838929,
"learning_rate": 2.015421274472325e-05,
"loss": 0.2132,
"step": 87
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.08126404156555671,
"learning_rate": 1.965167291983757e-05,
"loss": 0.2156,
"step": 88
},
{
"epoch": 1.155844155844156,
"grad_norm": 0.08196682847954194,
"learning_rate": 1.9151387954958794e-05,
"loss": 0.178,
"step": 89
},
{
"epoch": 1.1688311688311688,
"grad_norm": 0.07898254614136963,
"learning_rate": 1.8653568770724806e-05,
"loss": 0.2158,
"step": 90
},
{
"epoch": 1.1818181818181819,
"grad_norm": 0.1007894448072893,
"learning_rate": 1.815842524819793e-05,
"loss": 0.176,
"step": 91
},
{
"epoch": 1.1948051948051948,
"grad_norm": 0.08182215036544653,
"learning_rate": 1.7666166140378852e-05,
"loss": 0.2048,
"step": 92
},
{
"epoch": 1.2077922077922079,
"grad_norm": 0.11560790878431627,
"learning_rate": 1.7176998984196146e-05,
"loss": 0.1904,
"step": 93
},
{
"epoch": 1.2207792207792207,
"grad_norm": 0.12113066083881273,
"learning_rate": 1.6691130013008514e-05,
"loss": 0.1974,
"step": 94
},
{
"epoch": 1.2337662337662338,
"grad_norm": 0.08515149977031479,
"learning_rate": 1.620876406965658e-05,
"loss": 0.2049,
"step": 95
},
{
"epoch": 1.2467532467532467,
"grad_norm": 0.09322796776822118,
"learning_rate": 1.5730104520100982e-05,
"loss": 0.2225,
"step": 96
},
{
"epoch": 1.2597402597402598,
"grad_norm": 0.0898952962414004,
"learning_rate": 1.5255353167683017e-05,
"loss": 0.2139,
"step": 97
},
{
"epoch": 1.2727272727272727,
"grad_norm": 0.08430600938698268,
"learning_rate": 1.4784710168044213e-05,
"loss": 0.2254,
"step": 98
},
{
"epoch": 1.2857142857142856,
"grad_norm": 0.08721397526200095,
"learning_rate": 1.4318373944740484e-05,
"loss": 0.1948,
"step": 99
},
{
"epoch": 1.2987012987012987,
"grad_norm": 0.09193805251870187,
"learning_rate": 1.3856541105586545e-05,
"loss": 0.189,
"step": 100
},
{
"epoch": 1.3116883116883118,
"grad_norm": 0.09260064723369027,
"learning_rate": 1.339940635976592e-05,
"loss": 0.1853,
"step": 101
},
{
"epoch": 1.3246753246753247,
"grad_norm": 0.09161658350392674,
"learning_rate": 1.2947162435741278e-05,
"loss": 0.2351,
"step": 102
},
{
"epoch": 1.3376623376623376,
"grad_norm": 0.07939421486765358,
"learning_rate": 1.2500000000000006e-05,
"loss": 0.2199,
"step": 103
},
{
"epoch": 1.3506493506493507,
"grad_norm": 0.08988123365679614,
"learning_rate": 1.205810757666894e-05,
"loss": 0.2203,
"step": 104
},
{
"epoch": 1.3636363636363638,
"grad_norm": 0.08790912980331905,
"learning_rate": 1.1621671468032493e-05,
"loss": 0.1891,
"step": 105
},
{
"epoch": 1.3766233766233766,
"grad_norm": 0.07960570450390624,
"learning_rate": 1.1190875675987356e-05,
"loss": 0.2464,
"step": 106
},
{
"epoch": 1.3896103896103895,
"grad_norm": 0.08768976314977797,
"learning_rate": 1.0765901824467167e-05,
"loss": 0.213,
"step": 107
},
{
"epoch": 1.4025974025974026,
"grad_norm": 0.0841723141024622,
"learning_rate": 1.0346929082869641e-05,
"loss": 0.2121,
"step": 108
},
{
"epoch": 1.4155844155844157,
"grad_norm": 0.08969311043319497,
"learning_rate": 9.934134090518593e-06,
"loss": 0.1684,
"step": 109
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.10925176253438569,
"learning_rate": 9.527690882192636e-06,
"loss": 0.2108,
"step": 110
},
{
"epoch": 1.4415584415584415,
"grad_norm": 0.10044980805756751,
"learning_rate": 9.127770814751933e-06,
"loss": 0.2142,
"step": 111
},
{
"epoch": 1.4545454545454546,
"grad_norm": 0.10075986222908401,
"learning_rate": 8.734542494893955e-06,
"loss": 0.2239,
"step": 112
},
{
"epoch": 1.4675324675324675,
"grad_norm": 0.14624227257627387,
"learning_rate": 8.348171708068747e-06,
"loss": 0.1907,
"step": 113
},
{
"epoch": 1.4805194805194806,
"grad_norm": 0.08167017231165358,
"learning_rate": 7.968821348583644e-06,
"loss": 0.2178,
"step": 114
},
{
"epoch": 1.4935064935064934,
"grad_norm": 0.1167316559372597,
"learning_rate": 7.5966513509268365e-06,
"loss": 0.1998,
"step": 115
},
{
"epoch": 1.5064935064935066,
"grad_norm": 0.08396562767447123,
"learning_rate": 7.231818622338823e-06,
"loss": 0.213,
"step": 116
},
{
"epoch": 1.5194805194805194,
"grad_norm": 0.08943222467451503,
"learning_rate": 6.8744769766601854e-06,
"loss": 0.2085,
"step": 117
},
{
"epoch": 1.5324675324675323,
"grad_norm": 0.08594290696448413,
"learning_rate": 6.524777069483526e-06,
"loss": 0.2005,
"step": 118
},
{
"epoch": 1.5454545454545454,
"grad_norm": 0.09141957886942967,
"learning_rate": 6.182866334636889e-06,
"loss": 0.185,
"step": 119
},
{
"epoch": 1.5584415584415585,
"grad_norm": 0.09996431130975963,
"learning_rate": 5.848888922025553e-06,
"loss": 0.2306,
"step": 120
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.09454859006099142,
"learning_rate": 5.522985636858239e-06,
"loss": 0.2195,
"step": 121
},
{
"epoch": 1.5844155844155843,
"grad_norm": 0.08951517611083147,
"learning_rate": 5.205293880283552e-06,
"loss": 0.1824,
"step": 122
},
{
"epoch": 1.5974025974025974,
"grad_norm": 0.08973290394393159,
"learning_rate": 4.8959475914614554e-06,
"loss": 0.2031,
"step": 123
},
{
"epoch": 1.6103896103896105,
"grad_norm": 0.0972420458274638,
"learning_rate": 4.5950771910944605e-06,
"loss": 0.218,
"step": 124
},
{
"epoch": 1.6233766233766234,
"grad_norm": 0.1028775215887483,
"learning_rate": 4.3028095264420535e-06,
"loss": 0.2295,
"step": 125
},
{
"epoch": 1.6363636363636362,
"grad_norm": 0.09422285979262787,
"learning_rate": 4.019267817841835e-06,
"loss": 0.231,
"step": 126
},
{
"epoch": 1.6493506493506493,
"grad_norm": 0.08245701472584765,
"learning_rate": 3.7445716067596503e-06,
"loss": 0.1968,
"step": 127
},
{
"epoch": 1.6623376623376624,
"grad_norm": 0.0900955932960198,
"learning_rate": 3.478836705390809e-06,
"loss": 0.2201,
"step": 128
},
{
"epoch": 1.6753246753246753,
"grad_norm": 0.08630235476963846,
"learning_rate": 3.222175147833556e-06,
"loss": 0.2172,
"step": 129
},
{
"epoch": 1.6883116883116882,
"grad_norm": 0.09086270485409138,
"learning_rate": 2.974695142855388e-06,
"loss": 0.2116,
"step": 130
},
{
"epoch": 1.7012987012987013,
"grad_norm": 0.09162946812983505,
"learning_rate": 2.7365010282720952e-06,
"loss": 0.198,
"step": 131
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.08702063300963413,
"learning_rate": 2.507693226958871e-06,
"loss": 0.2129,
"step": 132
},
{
"epoch": 1.7272727272727273,
"grad_norm": 0.0881788504739707,
"learning_rate": 2.2883682045119063e-06,
"loss": 0.167,
"step": 133
},
{
"epoch": 1.7402597402597402,
"grad_norm": 0.11644782656509362,
"learning_rate": 2.0786184285784297e-06,
"loss": 0.2054,
"step": 134
},
{
"epoch": 1.7532467532467533,
"grad_norm": 0.1766008455564786,
"learning_rate": 1.8785323298722097e-06,
"loss": 0.2186,
"step": 135
},
{
"epoch": 1.7662337662337664,
"grad_norm": 0.09795182977403628,
"learning_rate": 1.6881942648911076e-06,
"loss": 0.1994,
"step": 136
},
{
"epoch": 1.7792207792207793,
"grad_norm": 0.12180290940767717,
"learning_rate": 1.5076844803522922e-06,
"loss": 0.2012,
"step": 137
},
{
"epoch": 1.7922077922077921,
"grad_norm": 0.094696794518402,
"learning_rate": 1.3370790793601373e-06,
"loss": 0.2245,
"step": 138
},
{
"epoch": 1.8051948051948052,
"grad_norm": 0.0761787809631694,
"learning_rate": 1.1764499893210878e-06,
"loss": 0.1963,
"step": 139
},
{
"epoch": 1.8181818181818183,
"grad_norm": 0.09090562786095378,
"learning_rate": 1.0258649316189722e-06,
"loss": 0.1877,
"step": 140
},
{
"epoch": 1.8311688311688312,
"grad_norm": 0.08173059503885717,
"learning_rate": 8.85387393063622e-07,
"loss": 0.2222,
"step": 141
},
{
"epoch": 1.844155844155844,
"grad_norm": 0.08635060155818351,
"learning_rate": 7.550765991247654e-07,
"loss": 0.2235,
"step": 142
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.08607284916997383,
"learning_rate": 6.349874889624962e-07,
"loss": 0.2071,
"step": 143
},
{
"epoch": 1.87012987012987,
"grad_norm": 0.07825829604724413,
"learning_rate": 5.25170692264887e-07,
"loss": 0.192,
"step": 144
},
{
"epoch": 1.883116883116883,
"grad_norm": 0.08910203901931234,
"learning_rate": 4.256725079024554e-07,
"loss": 0.2164,
"step": 145
},
{
"epoch": 1.896103896103896,
"grad_norm": 0.08928208281125428,
"learning_rate": 3.3653488440851255e-07,
"loss": 0.2018,
"step": 146
},
{
"epoch": 1.9090909090909092,
"grad_norm": 0.08495149169392952,
"learning_rate": 2.5779540229361745e-07,
"loss": 0.1961,
"step": 147
},
{
"epoch": 1.922077922077922,
"grad_norm": 0.08626229151823323,
"learning_rate": 1.8948725820160662e-07,
"loss": 0.1768,
"step": 148
},
{
"epoch": 1.935064935064935,
"grad_norm": 0.08571927306677737,
"learning_rate": 1.3163925091384533e-07,
"loss": 0.2232,
"step": 149
},
{
"epoch": 1.948051948051948,
"grad_norm": 0.09343183243370598,
"learning_rate": 8.427576920763958e-08,
"loss": 0.1687,
"step": 150
},
{
"epoch": 1.9610389610389611,
"grad_norm": 0.0946463454270307,
"learning_rate": 4.741678157389739e-08,
"loss": 0.187,
"step": 151
},
{
"epoch": 1.974025974025974,
"grad_norm": 0.09513291585193097,
"learning_rate": 2.1077827798404726e-08,
"loss": 0.2231,
"step": 152
},
{
"epoch": 1.987012987012987,
"grad_norm": 0.085055457153114,
"learning_rate": 5.270012410216185e-09,
"loss": 0.1792,
"step": 153
},
{
"epoch": 2.0,
"grad_norm": 0.08464289636250304,
"learning_rate": 0.0,
"loss": 0.1753,
"step": 154
},
{
"epoch": 2.0,
"step": 154,
"total_flos": 145121340096512.0,
"train_loss": 0.2980368115104638,
"train_runtime": 2252.7177,
"train_samples_per_second": 0.272,
"train_steps_per_second": 0.068
}
],
"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": 145121340096512.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}