muhtasham's picture
Model save
b7734af verified
raw
history blame
65 kB
{
"best_metric": 0.17896194756031036,
"best_model_checkpoint": "output/output__lora/checkpoint-100",
"epoch": 2.821869488536155,
"eval_steps": 100,
"global_step": 400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007054673721340388,
"grad_norm": 1.7538496255874634,
"learning_rate": 0.0,
"loss": 0.4857,
"step": 1
},
{
"epoch": 0.014109347442680775,
"grad_norm": 1.2099508047103882,
"learning_rate": 8.859191006777897e-06,
"loss": 0.3211,
"step": 2
},
{
"epoch": 0.021164021164021163,
"grad_norm": 1.2099508047103882,
"learning_rate": 8.859191006777897e-06,
"loss": 0.4225,
"step": 3
},
{
"epoch": 0.02821869488536155,
"grad_norm": 1.1170622110366821,
"learning_rate": 1.4041485532469073e-05,
"loss": 0.3698,
"step": 4
},
{
"epoch": 0.03527336860670194,
"grad_norm": 1.1217817068099976,
"learning_rate": 1.7718382013555794e-05,
"loss": 0.347,
"step": 5
},
{
"epoch": 0.042328042328042326,
"grad_norm": 0.87273770570755,
"learning_rate": 2.0570404496611053e-05,
"loss": 0.3743,
"step": 6
},
{
"epoch": 0.04938271604938271,
"grad_norm": 0.7485833168029785,
"learning_rate": 2.2900676539246968e-05,
"loss": 0.2656,
"step": 7
},
{
"epoch": 0.0564373897707231,
"grad_norm": 1.150911808013916,
"learning_rate": 2.4870893478326387e-05,
"loss": 0.3674,
"step": 8
},
{
"epoch": 0.06349206349206349,
"grad_norm": 0.8416776061058044,
"learning_rate": 2.6577573020333684e-05,
"loss": 0.3613,
"step": 9
},
{
"epoch": 0.07054673721340388,
"grad_norm": 0.8826892971992493,
"learning_rate": 2.8082971064938146e-05,
"loss": 0.3495,
"step": 10
},
{
"epoch": 0.07760141093474426,
"grad_norm": 0.847586989402771,
"learning_rate": 2.9429595503388953e-05,
"loss": 0.2358,
"step": 11
},
{
"epoch": 0.08465608465608465,
"grad_norm": 0.7876963019371033,
"learning_rate": 3.064776548439465e-05,
"loss": 0.3538,
"step": 12
},
{
"epoch": 0.09171075837742504,
"grad_norm": 0.718278169631958,
"learning_rate": 3.1759867546024865e-05,
"loss": 0.3632,
"step": 13
},
{
"epoch": 0.09876543209876543,
"grad_norm": 1.0214649438858032,
"learning_rate": 3.2782902272079295e-05,
"loss": 0.26,
"step": 14
},
{
"epoch": 0.10582010582010581,
"grad_norm": 0.7344455122947693,
"learning_rate": 3.373008448510428e-05,
"loss": 0.3286,
"step": 15
},
{
"epoch": 0.1128747795414462,
"grad_norm": 0.9921013116836548,
"learning_rate": 3.4611890029080124e-05,
"loss": 0.3157,
"step": 16
},
{
"epoch": 0.11992945326278659,
"grad_norm": 2.3107821941375732,
"learning_rate": 3.543676402711159e-05,
"loss": 0.2328,
"step": 17
},
{
"epoch": 0.12698412698412698,
"grad_norm": 0.6335638761520386,
"learning_rate": 3.621161404374383e-05,
"loss": 0.2289,
"step": 18
},
{
"epoch": 0.13403880070546736,
"grad_norm": 0.848183810710907,
"learning_rate": 3.694216207171603e-05,
"loss": 0.3419,
"step": 19
},
{
"epoch": 0.14109347442680775,
"grad_norm": 0.8602741956710815,
"learning_rate": 3.76332012245438e-05,
"loss": 0.3045,
"step": 20
},
{
"epoch": 0.14814814814814814,
"grad_norm": 0.7947338819503784,
"learning_rate": 3.8288786510166846e-05,
"loss": 0.3092,
"step": 21
},
{
"epoch": 0.15520282186948853,
"grad_norm": 1.7006886005401611,
"learning_rate": 3.8912379010795455e-05,
"loss": 0.191,
"step": 22
},
{
"epoch": 0.16225749559082892,
"grad_norm": 0.7695497274398804,
"learning_rate": 3.9506956491172545e-05,
"loss": 0.2258,
"step": 23
},
{
"epoch": 0.1693121693121693,
"grad_norm": 0.675501823425293,
"learning_rate": 4.007509939970292e-05,
"loss": 0.2382,
"step": 24
},
{
"epoch": 0.1763668430335097,
"grad_norm": 0.9618274569511414,
"learning_rate": 4.061905855280276e-05,
"loss": 0.2598,
"step": 25
},
{
"epoch": 0.18342151675485008,
"grad_norm": 1.6994143724441528,
"learning_rate": 4.1140808993222106e-05,
"loss": 0.2156,
"step": 26
},
{
"epoch": 0.19047619047619047,
"grad_norm": 0.773503303527832,
"learning_rate": 4.164209327885719e-05,
"loss": 0.3194,
"step": 27
},
{
"epoch": 0.19753086419753085,
"grad_norm": 0.6324657201766968,
"learning_rate": 4.2124456597407214e-05,
"loss": 0.2947,
"step": 28
},
{
"epoch": 0.20458553791887124,
"grad_norm": 0.8014081120491028,
"learning_rate": 4.258927549188218e-05,
"loss": 0.256,
"step": 29
},
{
"epoch": 0.21164021164021163,
"grad_norm": 0.9835159182548523,
"learning_rate": 4.303778154313212e-05,
"loss": 0.1988,
"step": 30
},
{
"epoch": 0.21869488536155202,
"grad_norm": 1.0733263492584229,
"learning_rate": 4.347108103585803e-05,
"loss": 0.286,
"step": 31
},
{
"epoch": 0.2257495590828924,
"grad_norm": 0.8567582964897156,
"learning_rate": 4.389017139879164e-05,
"loss": 0.2152,
"step": 32
},
{
"epoch": 0.2328042328042328,
"grad_norm": 0.8153343796730042,
"learning_rate": 4.429595503388948e-05,
"loss": 0.301,
"step": 33
},
{
"epoch": 0.23985890652557318,
"grad_norm": 1.381162405014038,
"learning_rate": 4.468925101686371e-05,
"loss": 0.3343,
"step": 34
},
{
"epoch": 0.24691358024691357,
"grad_norm": 0.9026140570640564,
"learning_rate": 4.507080505052173e-05,
"loss": 0.2369,
"step": 35
},
{
"epoch": 0.25396825396825395,
"grad_norm": 1.1759003400802612,
"learning_rate": 4.544129797493744e-05,
"loss": 0.3082,
"step": 36
},
{
"epoch": 0.26102292768959434,
"grad_norm": 1.5342798233032227,
"learning_rate": 4.5801353078493936e-05,
"loss": 0.3168,
"step": 37
},
{
"epoch": 0.26807760141093473,
"grad_norm": 0.7265400886535645,
"learning_rate": 4.615154240700883e-05,
"loss": 0.2484,
"step": 38
},
{
"epoch": 0.2751322751322751,
"grad_norm": 0.7057551741600037,
"learning_rate": 4.6492392231321696e-05,
"loss": 0.2654,
"step": 39
},
{
"epoch": 0.2821869488536155,
"grad_norm": 0.7926758527755737,
"learning_rate": 4.682438780454837e-05,
"loss": 0.1032,
"step": 40
},
{
"epoch": 0.2892416225749559,
"grad_norm": 0.9488016963005066,
"learning_rate": 4.714797751694474e-05,
"loss": 0.2454,
"step": 41
},
{
"epoch": 0.2962962962962963,
"grad_norm": 1.9464285373687744,
"learning_rate": 4.7463576537657414e-05,
"loss": 0.2924,
"step": 42
},
{
"epoch": 0.30335097001763667,
"grad_norm": 1.1096171140670776,
"learning_rate": 4.777157001757336e-05,
"loss": 0.3058,
"step": 43
},
{
"epoch": 0.31040564373897706,
"grad_norm": 0.8923623561859131,
"learning_rate": 4.8072315915252694e-05,
"loss": 0.2073,
"step": 44
},
{
"epoch": 0.31746031746031744,
"grad_norm": 1.0031824111938477,
"learning_rate": 4.8366147497950435e-05,
"loss": 0.2059,
"step": 45
},
{
"epoch": 0.32451499118165783,
"grad_norm": 1.1026407480239868,
"learning_rate": 4.8653375561549195e-05,
"loss": 0.1936,
"step": 46
},
{
"epoch": 0.3315696649029982,
"grad_norm": 1.0787580013275146,
"learning_rate": 4.8934290406480814e-05,
"loss": 0.1917,
"step": 47
},
{
"epoch": 0.3386243386243386,
"grad_norm": 1.1401859521865845,
"learning_rate": 4.920916360113129e-05,
"loss": 0.1943,
"step": 48
},
{
"epoch": 0.345679012345679,
"grad_norm": 1.4272260665893555,
"learning_rate": 4.947824955958066e-05,
"loss": 0.2286,
"step": 49
},
{
"epoch": 0.3527336860670194,
"grad_norm": 0.9560362696647644,
"learning_rate": 4.9741786956652774e-05,
"loss": 0.1451,
"step": 50
},
{
"epoch": 0.35978835978835977,
"grad_norm": 0.8079693913459778,
"learning_rate": 5e-05,
"loss": 0.168,
"step": 51
},
{
"epoch": 0.36684303350970016,
"grad_norm": 1.3394136428833008,
"learning_rate": 5e-05,
"loss": 0.1198,
"step": 52
},
{
"epoch": 0.37389770723104054,
"grad_norm": 2.1363890171051025,
"learning_rate": 5e-05,
"loss": 0.2001,
"step": 53
},
{
"epoch": 0.38095238095238093,
"grad_norm": 0.903056263923645,
"learning_rate": 5e-05,
"loss": 0.2231,
"step": 54
},
{
"epoch": 0.3880070546737213,
"grad_norm": 0.9227181077003479,
"learning_rate": 5e-05,
"loss": 0.1655,
"step": 55
},
{
"epoch": 0.3950617283950617,
"grad_norm": 0.8971679210662842,
"learning_rate": 5e-05,
"loss": 0.2074,
"step": 56
},
{
"epoch": 0.4021164021164021,
"grad_norm": 0.8905817270278931,
"learning_rate": 5e-05,
"loss": 0.177,
"step": 57
},
{
"epoch": 0.4091710758377425,
"grad_norm": 1.6770292520523071,
"learning_rate": 5e-05,
"loss": 0.2223,
"step": 58
},
{
"epoch": 0.41622574955908287,
"grad_norm": 1.6770292520523071,
"learning_rate": 5e-05,
"loss": 0.104,
"step": 59
},
{
"epoch": 0.42328042328042326,
"grad_norm": 0.9908204674720764,
"learning_rate": 5e-05,
"loss": 0.28,
"step": 60
},
{
"epoch": 0.43033509700176364,
"grad_norm": 0.8167163133621216,
"learning_rate": 5e-05,
"loss": 0.2298,
"step": 61
},
{
"epoch": 0.43738977072310403,
"grad_norm": 1.0286040306091309,
"learning_rate": 5e-05,
"loss": 0.1949,
"step": 62
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.9994080066680908,
"learning_rate": 5e-05,
"loss": 0.1785,
"step": 63
},
{
"epoch": 0.4514991181657848,
"grad_norm": 1.0961331129074097,
"learning_rate": 5e-05,
"loss": 0.1841,
"step": 64
},
{
"epoch": 0.4585537918871252,
"grad_norm": 1.0142136812210083,
"learning_rate": 5e-05,
"loss": 0.1438,
"step": 65
},
{
"epoch": 0.4656084656084656,
"grad_norm": 0.9026923775672913,
"learning_rate": 5e-05,
"loss": 0.1882,
"step": 66
},
{
"epoch": 0.47266313932980597,
"grad_norm": 0.9396039843559265,
"learning_rate": 5e-05,
"loss": 0.1735,
"step": 67
},
{
"epoch": 0.47971781305114636,
"grad_norm": 0.9887558817863464,
"learning_rate": 5e-05,
"loss": 0.1382,
"step": 68
},
{
"epoch": 0.48677248677248675,
"grad_norm": 0.7315873503684998,
"learning_rate": 5e-05,
"loss": 0.1833,
"step": 69
},
{
"epoch": 0.49382716049382713,
"grad_norm": 0.7315873503684998,
"learning_rate": 5e-05,
"loss": 0.1534,
"step": 70
},
{
"epoch": 0.5008818342151675,
"grad_norm": 1.2682855129241943,
"learning_rate": 5e-05,
"loss": 0.1475,
"step": 71
},
{
"epoch": 0.5079365079365079,
"grad_norm": 2.3604001998901367,
"learning_rate": 5e-05,
"loss": 0.142,
"step": 72
},
{
"epoch": 0.5149911816578483,
"grad_norm": 1.310669183731079,
"learning_rate": 5e-05,
"loss": 0.144,
"step": 73
},
{
"epoch": 0.5220458553791887,
"grad_norm": 0.8857008218765259,
"learning_rate": 5e-05,
"loss": 0.1303,
"step": 74
},
{
"epoch": 0.5291005291005291,
"grad_norm": 0.8952376246452332,
"learning_rate": 5e-05,
"loss": 0.1491,
"step": 75
},
{
"epoch": 0.5361552028218695,
"grad_norm": 1.175799012184143,
"learning_rate": 5e-05,
"loss": 0.1242,
"step": 76
},
{
"epoch": 0.5432098765432098,
"grad_norm": 0.9906390905380249,
"learning_rate": 5e-05,
"loss": 0.1407,
"step": 77
},
{
"epoch": 0.5502645502645502,
"grad_norm": 1.0439103841781616,
"learning_rate": 5e-05,
"loss": 0.0782,
"step": 78
},
{
"epoch": 0.5573192239858906,
"grad_norm": 1.7823419570922852,
"learning_rate": 5e-05,
"loss": 0.1723,
"step": 79
},
{
"epoch": 0.564373897707231,
"grad_norm": 1.1472703218460083,
"learning_rate": 5e-05,
"loss": 0.2095,
"step": 80
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.9809481501579285,
"learning_rate": 5e-05,
"loss": 0.1764,
"step": 81
},
{
"epoch": 0.5784832451499118,
"grad_norm": 0.82795250415802,
"learning_rate": 5e-05,
"loss": 0.1617,
"step": 82
},
{
"epoch": 0.5855379188712522,
"grad_norm": 0.7833464741706848,
"learning_rate": 5e-05,
"loss": 0.1152,
"step": 83
},
{
"epoch": 0.5925925925925926,
"grad_norm": 0.691254198551178,
"learning_rate": 5e-05,
"loss": 0.0862,
"step": 84
},
{
"epoch": 0.599647266313933,
"grad_norm": 0.635303258895874,
"learning_rate": 5e-05,
"loss": 0.1132,
"step": 85
},
{
"epoch": 0.6067019400352733,
"grad_norm": 0.8403255939483643,
"learning_rate": 5e-05,
"loss": 0.1724,
"step": 86
},
{
"epoch": 0.6137566137566137,
"grad_norm": 1.0148879289627075,
"learning_rate": 5e-05,
"loss": 0.1044,
"step": 87
},
{
"epoch": 0.6208112874779541,
"grad_norm": 1.0047919750213623,
"learning_rate": 5e-05,
"loss": 0.1456,
"step": 88
},
{
"epoch": 0.6278659611992945,
"grad_norm": 0.6750177145004272,
"learning_rate": 5e-05,
"loss": 0.1013,
"step": 89
},
{
"epoch": 0.6349206349206349,
"grad_norm": 0.9232619404792786,
"learning_rate": 5e-05,
"loss": 0.1651,
"step": 90
},
{
"epoch": 0.6419753086419753,
"grad_norm": 0.9468359351158142,
"learning_rate": 5e-05,
"loss": 0.1783,
"step": 91
},
{
"epoch": 0.6490299823633157,
"grad_norm": 0.7553344964981079,
"learning_rate": 5e-05,
"loss": 0.1174,
"step": 92
},
{
"epoch": 0.656084656084656,
"grad_norm": 1.0219858884811401,
"learning_rate": 5e-05,
"loss": 0.0887,
"step": 93
},
{
"epoch": 0.6631393298059964,
"grad_norm": 0.6816285848617554,
"learning_rate": 5e-05,
"loss": 0.106,
"step": 94
},
{
"epoch": 0.6701940035273368,
"grad_norm": 0.928390622138977,
"learning_rate": 5e-05,
"loss": 0.1175,
"step": 95
},
{
"epoch": 0.6772486772486772,
"grad_norm": 1.2344391345977783,
"learning_rate": 5e-05,
"loss": 0.1767,
"step": 96
},
{
"epoch": 0.6843033509700176,
"grad_norm": 0.7818422913551331,
"learning_rate": 5e-05,
"loss": 0.1372,
"step": 97
},
{
"epoch": 0.691358024691358,
"grad_norm": 0.9105628132820129,
"learning_rate": 5e-05,
"loss": 0.0941,
"step": 98
},
{
"epoch": 0.6984126984126984,
"grad_norm": 0.8559777140617371,
"learning_rate": 5e-05,
"loss": 0.1225,
"step": 99
},
{
"epoch": 0.7054673721340388,
"grad_norm": 0.847297191619873,
"learning_rate": 5e-05,
"loss": 0.1465,
"step": 100
},
{
"epoch": 0.7054673721340388,
"eval_loss": 0.17896194756031036,
"eval_runtime": 360.2551,
"eval_samples_per_second": 6.296,
"eval_steps_per_second": 0.394,
"step": 100
},
{
"epoch": 0.7125220458553791,
"grad_norm": 0.8381081819534302,
"learning_rate": 5e-05,
"loss": 0.186,
"step": 101
},
{
"epoch": 0.7195767195767195,
"grad_norm": 1.418454885482788,
"learning_rate": 5e-05,
"loss": 0.0831,
"step": 102
},
{
"epoch": 0.7266313932980599,
"grad_norm": 1.4008698463439941,
"learning_rate": 5e-05,
"loss": 0.1661,
"step": 103
},
{
"epoch": 0.7336860670194003,
"grad_norm": 0.8513796329498291,
"learning_rate": 5e-05,
"loss": 0.1871,
"step": 104
},
{
"epoch": 0.7407407407407407,
"grad_norm": 1.5074268579483032,
"learning_rate": 5e-05,
"loss": 0.1343,
"step": 105
},
{
"epoch": 0.7477954144620811,
"grad_norm": 1.1504905223846436,
"learning_rate": 5e-05,
"loss": 0.1611,
"step": 106
},
{
"epoch": 0.7548500881834215,
"grad_norm": 0.7931183576583862,
"learning_rate": 5e-05,
"loss": 0.0819,
"step": 107
},
{
"epoch": 0.7619047619047619,
"grad_norm": 2.454035758972168,
"learning_rate": 5e-05,
"loss": 0.1533,
"step": 108
},
{
"epoch": 0.7689594356261023,
"grad_norm": 0.905976414680481,
"learning_rate": 5e-05,
"loss": 0.1099,
"step": 109
},
{
"epoch": 0.7760141093474426,
"grad_norm": 1.0910918712615967,
"learning_rate": 5e-05,
"loss": 0.0784,
"step": 110
},
{
"epoch": 0.783068783068783,
"grad_norm": 0.8586850166320801,
"learning_rate": 5e-05,
"loss": 0.1083,
"step": 111
},
{
"epoch": 0.7901234567901234,
"grad_norm": 0.8878437876701355,
"learning_rate": 5e-05,
"loss": 0.0986,
"step": 112
},
{
"epoch": 0.7971781305114638,
"grad_norm": 0.7834882736206055,
"learning_rate": 5e-05,
"loss": 0.135,
"step": 113
},
{
"epoch": 0.8042328042328042,
"grad_norm": 0.7140138745307922,
"learning_rate": 5e-05,
"loss": 0.105,
"step": 114
},
{
"epoch": 0.8112874779541446,
"grad_norm": 0.5810890197753906,
"learning_rate": 5e-05,
"loss": 0.0669,
"step": 115
},
{
"epoch": 0.818342151675485,
"grad_norm": 0.957624077796936,
"learning_rate": 5e-05,
"loss": 0.1112,
"step": 116
},
{
"epoch": 0.8253968253968254,
"grad_norm": 0.8660424947738647,
"learning_rate": 5e-05,
"loss": 0.1219,
"step": 117
},
{
"epoch": 0.8324514991181657,
"grad_norm": 0.7031818628311157,
"learning_rate": 5e-05,
"loss": 0.0599,
"step": 118
},
{
"epoch": 0.8395061728395061,
"grad_norm": 1.0137779712677002,
"learning_rate": 5e-05,
"loss": 0.1029,
"step": 119
},
{
"epoch": 0.8465608465608465,
"grad_norm": 0.696945309638977,
"learning_rate": 5e-05,
"loss": 0.0824,
"step": 120
},
{
"epoch": 0.8536155202821869,
"grad_norm": 1.1428477764129639,
"learning_rate": 5e-05,
"loss": 0.1621,
"step": 121
},
{
"epoch": 0.8606701940035273,
"grad_norm": 1.124836802482605,
"learning_rate": 5e-05,
"loss": 0.1221,
"step": 122
},
{
"epoch": 0.8677248677248677,
"grad_norm": 0.7269309163093567,
"learning_rate": 5e-05,
"loss": 0.0561,
"step": 123
},
{
"epoch": 0.8747795414462081,
"grad_norm": 0.5245713591575623,
"learning_rate": 5e-05,
"loss": 0.0474,
"step": 124
},
{
"epoch": 0.8818342151675485,
"grad_norm": 1.181915521621704,
"learning_rate": 5e-05,
"loss": 0.1044,
"step": 125
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.696465015411377,
"learning_rate": 5e-05,
"loss": 0.1542,
"step": 126
},
{
"epoch": 0.8959435626102292,
"grad_norm": 0.6903875470161438,
"learning_rate": 5e-05,
"loss": 0.0605,
"step": 127
},
{
"epoch": 0.9029982363315696,
"grad_norm": 0.8914228081703186,
"learning_rate": 5e-05,
"loss": 0.1034,
"step": 128
},
{
"epoch": 0.91005291005291,
"grad_norm": 0.8926368355751038,
"learning_rate": 5e-05,
"loss": 0.1088,
"step": 129
},
{
"epoch": 0.9171075837742504,
"grad_norm": 0.9177432656288147,
"learning_rate": 5e-05,
"loss": 0.1255,
"step": 130
},
{
"epoch": 0.9241622574955908,
"grad_norm": 0.7664863467216492,
"learning_rate": 5e-05,
"loss": 0.1019,
"step": 131
},
{
"epoch": 0.9312169312169312,
"grad_norm": 0.7729786038398743,
"learning_rate": 5e-05,
"loss": 0.0747,
"step": 132
},
{
"epoch": 0.9382716049382716,
"grad_norm": 0.5827771425247192,
"learning_rate": 5e-05,
"loss": 0.1354,
"step": 133
},
{
"epoch": 0.9453262786596119,
"grad_norm": 0.9261442422866821,
"learning_rate": 5e-05,
"loss": 0.0624,
"step": 134
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.7620460391044617,
"learning_rate": 5e-05,
"loss": 0.0884,
"step": 135
},
{
"epoch": 0.9594356261022927,
"grad_norm": 0.8573839068412781,
"learning_rate": 5e-05,
"loss": 0.0758,
"step": 136
},
{
"epoch": 0.9664902998236331,
"grad_norm": 0.8569554090499878,
"learning_rate": 5e-05,
"loss": 0.1048,
"step": 137
},
{
"epoch": 0.9735449735449735,
"grad_norm": 0.9836267232894897,
"learning_rate": 5e-05,
"loss": 0.1243,
"step": 138
},
{
"epoch": 0.9805996472663139,
"grad_norm": 0.6673980355262756,
"learning_rate": 5e-05,
"loss": 0.061,
"step": 139
},
{
"epoch": 0.9876543209876543,
"grad_norm": 0.8903977870941162,
"learning_rate": 5e-05,
"loss": 0.1116,
"step": 140
},
{
"epoch": 0.9947089947089947,
"grad_norm": 0.9424787163734436,
"learning_rate": 5e-05,
"loss": 0.0865,
"step": 141
},
{
"epoch": 1.001763668430335,
"grad_norm": 0.6135322451591492,
"learning_rate": 5e-05,
"loss": 0.0733,
"step": 142
},
{
"epoch": 1.0088183421516754,
"grad_norm": 0.7416030764579773,
"learning_rate": 5e-05,
"loss": 0.092,
"step": 143
},
{
"epoch": 1.0158730158730158,
"grad_norm": 0.7281748056411743,
"learning_rate": 5e-05,
"loss": 0.0896,
"step": 144
},
{
"epoch": 1.0229276895943562,
"grad_norm": 1.047066330909729,
"learning_rate": 5e-05,
"loss": 0.1042,
"step": 145
},
{
"epoch": 1.0299823633156966,
"grad_norm": 3.0005276203155518,
"learning_rate": 5e-05,
"loss": 0.0774,
"step": 146
},
{
"epoch": 1.037037037037037,
"grad_norm": 0.7662864923477173,
"learning_rate": 5e-05,
"loss": 0.119,
"step": 147
},
{
"epoch": 1.0440917107583774,
"grad_norm": 0.9837973117828369,
"learning_rate": 5e-05,
"loss": 0.0668,
"step": 148
},
{
"epoch": 1.0511463844797178,
"grad_norm": 0.8258010149002075,
"learning_rate": 5e-05,
"loss": 0.0473,
"step": 149
},
{
"epoch": 1.0582010582010581,
"grad_norm": 0.928363025188446,
"learning_rate": 5e-05,
"loss": 0.09,
"step": 150
},
{
"epoch": 1.0652557319223985,
"grad_norm": 1.009312391281128,
"learning_rate": 5e-05,
"loss": 0.1133,
"step": 151
},
{
"epoch": 1.072310405643739,
"grad_norm": 0.7772536873817444,
"learning_rate": 5e-05,
"loss": 0.069,
"step": 152
},
{
"epoch": 1.0793650793650793,
"grad_norm": 1.2250009775161743,
"learning_rate": 5e-05,
"loss": 0.0981,
"step": 153
},
{
"epoch": 1.0864197530864197,
"grad_norm": 0.5997045040130615,
"learning_rate": 5e-05,
"loss": 0.0598,
"step": 154
},
{
"epoch": 1.09347442680776,
"grad_norm": 0.9267628192901611,
"learning_rate": 5e-05,
"loss": 0.0384,
"step": 155
},
{
"epoch": 1.1005291005291005,
"grad_norm": 0.6563625335693359,
"learning_rate": 5e-05,
"loss": 0.0766,
"step": 156
},
{
"epoch": 1.1075837742504409,
"grad_norm": 0.8543305993080139,
"learning_rate": 5e-05,
"loss": 0.0896,
"step": 157
},
{
"epoch": 1.1146384479717812,
"grad_norm": 0.5792420506477356,
"learning_rate": 5e-05,
"loss": 0.1053,
"step": 158
},
{
"epoch": 1.1216931216931216,
"grad_norm": 0.7286255955696106,
"learning_rate": 5e-05,
"loss": 0.0998,
"step": 159
},
{
"epoch": 1.128747795414462,
"grad_norm": 0.4976038932800293,
"learning_rate": 5e-05,
"loss": 0.0782,
"step": 160
},
{
"epoch": 1.1358024691358024,
"grad_norm": 0.6580901741981506,
"learning_rate": 5e-05,
"loss": 0.0652,
"step": 161
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.6756439805030823,
"learning_rate": 5e-05,
"loss": 0.1008,
"step": 162
},
{
"epoch": 1.1499118165784832,
"grad_norm": 0.895070493221283,
"learning_rate": 5e-05,
"loss": 0.0771,
"step": 163
},
{
"epoch": 1.1569664902998236,
"grad_norm": 1.056799292564392,
"learning_rate": 5e-05,
"loss": 0.0516,
"step": 164
},
{
"epoch": 1.164021164021164,
"grad_norm": 0.8106465339660645,
"learning_rate": 5e-05,
"loss": 0.135,
"step": 165
},
{
"epoch": 1.1710758377425043,
"grad_norm": 0.5313682556152344,
"learning_rate": 5e-05,
"loss": 0.0929,
"step": 166
},
{
"epoch": 1.1781305114638447,
"grad_norm": 0.8005192279815674,
"learning_rate": 5e-05,
"loss": 0.064,
"step": 167
},
{
"epoch": 1.1851851851851851,
"grad_norm": 0.7275320291519165,
"learning_rate": 5e-05,
"loss": 0.1083,
"step": 168
},
{
"epoch": 1.1922398589065255,
"grad_norm": 1.9933772087097168,
"learning_rate": 5e-05,
"loss": 0.1345,
"step": 169
},
{
"epoch": 1.199294532627866,
"grad_norm": 0.7224838733673096,
"learning_rate": 5e-05,
"loss": 0.0492,
"step": 170
},
{
"epoch": 1.2063492063492063,
"grad_norm": 0.6393369436264038,
"learning_rate": 5e-05,
"loss": 0.0726,
"step": 171
},
{
"epoch": 1.2134038800705467,
"grad_norm": 0.5461933612823486,
"learning_rate": 5e-05,
"loss": 0.0283,
"step": 172
},
{
"epoch": 1.220458553791887,
"grad_norm": 1.0142794847488403,
"learning_rate": 5e-05,
"loss": 0.0768,
"step": 173
},
{
"epoch": 1.2275132275132274,
"grad_norm": 0.626775860786438,
"learning_rate": 5e-05,
"loss": 0.0971,
"step": 174
},
{
"epoch": 1.2345679012345678,
"grad_norm": 1.3706245422363281,
"learning_rate": 5e-05,
"loss": 0.0643,
"step": 175
},
{
"epoch": 1.2416225749559082,
"grad_norm": 0.6315011978149414,
"learning_rate": 5e-05,
"loss": 0.0431,
"step": 176
},
{
"epoch": 1.2486772486772486,
"grad_norm": 0.6979820132255554,
"learning_rate": 5e-05,
"loss": 0.0911,
"step": 177
},
{
"epoch": 1.255731922398589,
"grad_norm": 0.9407426118850708,
"learning_rate": 5e-05,
"loss": 0.0583,
"step": 178
},
{
"epoch": 1.2627865961199294,
"grad_norm": 1.1693543195724487,
"learning_rate": 5e-05,
"loss": 0.0636,
"step": 179
},
{
"epoch": 1.2698412698412698,
"grad_norm": 0.6498689651489258,
"learning_rate": 5e-05,
"loss": 0.023,
"step": 180
},
{
"epoch": 1.2768959435626102,
"grad_norm": 0.6040365695953369,
"learning_rate": 5e-05,
"loss": 0.06,
"step": 181
},
{
"epoch": 1.2839506172839505,
"grad_norm": 0.5838135480880737,
"learning_rate": 5e-05,
"loss": 0.0842,
"step": 182
},
{
"epoch": 1.291005291005291,
"grad_norm": 0.4301566779613495,
"learning_rate": 5e-05,
"loss": 0.0684,
"step": 183
},
{
"epoch": 1.2980599647266313,
"grad_norm": 0.6036396026611328,
"learning_rate": 5e-05,
"loss": 0.0938,
"step": 184
},
{
"epoch": 1.3051146384479717,
"grad_norm": 0.9883386492729187,
"learning_rate": 5e-05,
"loss": 0.0462,
"step": 185
},
{
"epoch": 1.312169312169312,
"grad_norm": 0.5813114643096924,
"learning_rate": 5e-05,
"loss": 0.0656,
"step": 186
},
{
"epoch": 1.3192239858906525,
"grad_norm": 0.8730061054229736,
"learning_rate": 5e-05,
"loss": 0.0433,
"step": 187
},
{
"epoch": 1.3262786596119929,
"grad_norm": 0.8635377287864685,
"learning_rate": 5e-05,
"loss": 0.082,
"step": 188
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.7513411045074463,
"learning_rate": 5e-05,
"loss": 0.0932,
"step": 189
},
{
"epoch": 1.3403880070546736,
"grad_norm": 0.7456687092781067,
"learning_rate": 5e-05,
"loss": 0.0723,
"step": 190
},
{
"epoch": 1.347442680776014,
"grad_norm": 0.572740912437439,
"learning_rate": 5e-05,
"loss": 0.0721,
"step": 191
},
{
"epoch": 1.3544973544973544,
"grad_norm": 1.2454944849014282,
"learning_rate": 5e-05,
"loss": 0.054,
"step": 192
},
{
"epoch": 1.3615520282186948,
"grad_norm": 0.5826276540756226,
"learning_rate": 5e-05,
"loss": 0.0367,
"step": 193
},
{
"epoch": 1.3686067019400352,
"grad_norm": 0.6496626138687134,
"learning_rate": 5e-05,
"loss": 0.0648,
"step": 194
},
{
"epoch": 1.3756613756613756,
"grad_norm": 0.8498976826667786,
"learning_rate": 5e-05,
"loss": 0.0942,
"step": 195
},
{
"epoch": 1.382716049382716,
"grad_norm": 1.1423848867416382,
"learning_rate": 5e-05,
"loss": 0.0545,
"step": 196
},
{
"epoch": 1.3897707231040564,
"grad_norm": 2.1429636478424072,
"learning_rate": 5e-05,
"loss": 0.0588,
"step": 197
},
{
"epoch": 1.3968253968253967,
"grad_norm": 0.6466217041015625,
"learning_rate": 5e-05,
"loss": 0.0313,
"step": 198
},
{
"epoch": 1.4038800705467371,
"grad_norm": 0.49399393796920776,
"learning_rate": 5e-05,
"loss": 0.0527,
"step": 199
},
{
"epoch": 1.4109347442680775,
"grad_norm": 0.5343263745307922,
"learning_rate": 5e-05,
"loss": 0.0339,
"step": 200
},
{
"epoch": 1.4109347442680775,
"eval_loss": 0.18905282020568848,
"eval_runtime": 358.5389,
"eval_samples_per_second": 6.326,
"eval_steps_per_second": 0.396,
"step": 200
},
{
"epoch": 1.417989417989418,
"grad_norm": 1.0444480180740356,
"learning_rate": 5e-05,
"loss": 0.0789,
"step": 201
},
{
"epoch": 1.4250440917107583,
"grad_norm": 1.5087664127349854,
"learning_rate": 5e-05,
"loss": 0.054,
"step": 202
},
{
"epoch": 1.4320987654320987,
"grad_norm": 0.8255050778388977,
"learning_rate": 5e-05,
"loss": 0.054,
"step": 203
},
{
"epoch": 1.439153439153439,
"grad_norm": 0.5734973549842834,
"learning_rate": 5e-05,
"loss": 0.0413,
"step": 204
},
{
"epoch": 1.4462081128747795,
"grad_norm": 0.5203781127929688,
"learning_rate": 5e-05,
"loss": 0.042,
"step": 205
},
{
"epoch": 1.4532627865961198,
"grad_norm": 0.6086573600769043,
"learning_rate": 5e-05,
"loss": 0.0415,
"step": 206
},
{
"epoch": 1.4603174603174602,
"grad_norm": 0.5426012873649597,
"learning_rate": 5e-05,
"loss": 0.036,
"step": 207
},
{
"epoch": 1.4673721340388006,
"grad_norm": 0.8343996405601501,
"learning_rate": 5e-05,
"loss": 0.0829,
"step": 208
},
{
"epoch": 1.474426807760141,
"grad_norm": 0.9328364133834839,
"learning_rate": 5e-05,
"loss": 0.0699,
"step": 209
},
{
"epoch": 1.4814814814814814,
"grad_norm": 0.64570152759552,
"learning_rate": 5e-05,
"loss": 0.067,
"step": 210
},
{
"epoch": 1.4885361552028218,
"grad_norm": 0.6451817750930786,
"learning_rate": 5e-05,
"loss": 0.0367,
"step": 211
},
{
"epoch": 1.4955908289241622,
"grad_norm": 0.6584360003471375,
"learning_rate": 5e-05,
"loss": 0.0932,
"step": 212
},
{
"epoch": 1.5026455026455028,
"grad_norm": 0.7680897116661072,
"learning_rate": 5e-05,
"loss": 0.0394,
"step": 213
},
{
"epoch": 1.509700176366843,
"grad_norm": 0.6519668698310852,
"learning_rate": 5e-05,
"loss": 0.0699,
"step": 214
},
{
"epoch": 1.5167548500881836,
"grad_norm": 0.7947211861610413,
"learning_rate": 5e-05,
"loss": 0.0323,
"step": 215
},
{
"epoch": 1.5238095238095237,
"grad_norm": 0.7202886343002319,
"learning_rate": 5e-05,
"loss": 0.0642,
"step": 216
},
{
"epoch": 1.5308641975308643,
"grad_norm": 0.507116973400116,
"learning_rate": 5e-05,
"loss": 0.0502,
"step": 217
},
{
"epoch": 1.5379188712522045,
"grad_norm": 0.5617340207099915,
"learning_rate": 5e-05,
"loss": 0.024,
"step": 218
},
{
"epoch": 1.544973544973545,
"grad_norm": 0.7389073371887207,
"learning_rate": 5e-05,
"loss": 0.0531,
"step": 219
},
{
"epoch": 1.5520282186948853,
"grad_norm": 0.6520772576332092,
"learning_rate": 5e-05,
"loss": 0.0652,
"step": 220
},
{
"epoch": 1.5590828924162259,
"grad_norm": 0.6626583933830261,
"learning_rate": 5e-05,
"loss": 0.0256,
"step": 221
},
{
"epoch": 1.566137566137566,
"grad_norm": 0.6184734106063843,
"learning_rate": 5e-05,
"loss": 0.0299,
"step": 222
},
{
"epoch": 1.5731922398589067,
"grad_norm": 0.5411644577980042,
"learning_rate": 5e-05,
"loss": 0.0466,
"step": 223
},
{
"epoch": 1.5802469135802468,
"grad_norm": 0.6262487769126892,
"learning_rate": 5e-05,
"loss": 0.0916,
"step": 224
},
{
"epoch": 1.5873015873015874,
"grad_norm": 0.6367466449737549,
"learning_rate": 5e-05,
"loss": 0.0462,
"step": 225
},
{
"epoch": 1.5943562610229276,
"grad_norm": 0.3993736505508423,
"learning_rate": 5e-05,
"loss": 0.053,
"step": 226
},
{
"epoch": 1.6014109347442682,
"grad_norm": 0.46192389726638794,
"learning_rate": 5e-05,
"loss": 0.0709,
"step": 227
},
{
"epoch": 1.6084656084656084,
"grad_norm": 1.1713682413101196,
"learning_rate": 5e-05,
"loss": 0.0442,
"step": 228
},
{
"epoch": 1.615520282186949,
"grad_norm": 0.6246752142906189,
"learning_rate": 5e-05,
"loss": 0.0588,
"step": 229
},
{
"epoch": 1.6225749559082892,
"grad_norm": 0.569995641708374,
"learning_rate": 5e-05,
"loss": 0.0625,
"step": 230
},
{
"epoch": 1.6296296296296298,
"grad_norm": 0.7993080019950867,
"learning_rate": 5e-05,
"loss": 0.0448,
"step": 231
},
{
"epoch": 1.63668430335097,
"grad_norm": 0.9412052631378174,
"learning_rate": 5e-05,
"loss": 0.106,
"step": 232
},
{
"epoch": 1.6437389770723105,
"grad_norm": 0.5617280006408691,
"learning_rate": 5e-05,
"loss": 0.048,
"step": 233
},
{
"epoch": 1.6507936507936507,
"grad_norm": 0.5206360220909119,
"learning_rate": 5e-05,
"loss": 0.0271,
"step": 234
},
{
"epoch": 1.6578483245149913,
"grad_norm": 0.5513091087341309,
"learning_rate": 5e-05,
"loss": 0.0352,
"step": 235
},
{
"epoch": 1.6649029982363315,
"grad_norm": 0.5904120206832886,
"learning_rate": 5e-05,
"loss": 0.069,
"step": 236
},
{
"epoch": 1.671957671957672,
"grad_norm": 0.8241035342216492,
"learning_rate": 5e-05,
"loss": 0.0654,
"step": 237
},
{
"epoch": 1.6790123456790123,
"grad_norm": 0.9514018297195435,
"learning_rate": 5e-05,
"loss": 0.0726,
"step": 238
},
{
"epoch": 1.6860670194003529,
"grad_norm": 0.5005506277084351,
"learning_rate": 5e-05,
"loss": 0.0655,
"step": 239
},
{
"epoch": 1.693121693121693,
"grad_norm": 0.44962841272354126,
"learning_rate": 5e-05,
"loss": 0.0403,
"step": 240
},
{
"epoch": 1.7001763668430336,
"grad_norm": 0.46677684783935547,
"learning_rate": 5e-05,
"loss": 0.0436,
"step": 241
},
{
"epoch": 1.7072310405643738,
"grad_norm": 0.7335297465324402,
"learning_rate": 5e-05,
"loss": 0.0496,
"step": 242
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.6942448019981384,
"learning_rate": 5e-05,
"loss": 0.1039,
"step": 243
},
{
"epoch": 1.7213403880070546,
"grad_norm": 0.4999411106109619,
"learning_rate": 5e-05,
"loss": 0.0543,
"step": 244
},
{
"epoch": 1.7283950617283952,
"grad_norm": 0.5241154432296753,
"learning_rate": 5e-05,
"loss": 0.0478,
"step": 245
},
{
"epoch": 1.7354497354497354,
"grad_norm": 0.6574307084083557,
"learning_rate": 5e-05,
"loss": 0.0579,
"step": 246
},
{
"epoch": 1.742504409171076,
"grad_norm": 0.8321516513824463,
"learning_rate": 5e-05,
"loss": 0.0663,
"step": 247
},
{
"epoch": 1.7495590828924161,
"grad_norm": 0.6835036873817444,
"learning_rate": 5e-05,
"loss": 0.0441,
"step": 248
},
{
"epoch": 1.7566137566137567,
"grad_norm": 0.6555665135383606,
"learning_rate": 5e-05,
"loss": 0.0311,
"step": 249
},
{
"epoch": 1.763668430335097,
"grad_norm": 0.4744579493999481,
"learning_rate": 5e-05,
"loss": 0.0302,
"step": 250
},
{
"epoch": 1.7707231040564375,
"grad_norm": 1.0260396003723145,
"learning_rate": 5e-05,
"loss": 0.0503,
"step": 251
},
{
"epoch": 1.7777777777777777,
"grad_norm": 0.6683841347694397,
"learning_rate": 5e-05,
"loss": 0.0355,
"step": 252
},
{
"epoch": 1.7848324514991183,
"grad_norm": 0.5520302057266235,
"learning_rate": 5e-05,
"loss": 0.0343,
"step": 253
},
{
"epoch": 1.7918871252204585,
"grad_norm": 0.7275727391242981,
"learning_rate": 5e-05,
"loss": 0.0379,
"step": 254
},
{
"epoch": 1.798941798941799,
"grad_norm": 0.7184352278709412,
"learning_rate": 5e-05,
"loss": 0.0541,
"step": 255
},
{
"epoch": 1.8059964726631392,
"grad_norm": 0.6140182614326477,
"learning_rate": 5e-05,
"loss": 0.0536,
"step": 256
},
{
"epoch": 1.8130511463844798,
"grad_norm": 0.48473063111305237,
"learning_rate": 5e-05,
"loss": 0.0401,
"step": 257
},
{
"epoch": 1.82010582010582,
"grad_norm": 0.5717530250549316,
"learning_rate": 5e-05,
"loss": 0.0376,
"step": 258
},
{
"epoch": 1.8271604938271606,
"grad_norm": 0.6555631756782532,
"learning_rate": 5e-05,
"loss": 0.0429,
"step": 259
},
{
"epoch": 1.8342151675485008,
"grad_norm": 0.539983868598938,
"learning_rate": 5e-05,
"loss": 0.0418,
"step": 260
},
{
"epoch": 1.8412698412698414,
"grad_norm": 0.7640647292137146,
"learning_rate": 5e-05,
"loss": 0.0648,
"step": 261
},
{
"epoch": 1.8483245149911816,
"grad_norm": 0.7768380641937256,
"learning_rate": 5e-05,
"loss": 0.0248,
"step": 262
},
{
"epoch": 1.8553791887125222,
"grad_norm": 0.42515769600868225,
"learning_rate": 5e-05,
"loss": 0.0652,
"step": 263
},
{
"epoch": 1.8624338624338623,
"grad_norm": 0.6031877994537354,
"learning_rate": 5e-05,
"loss": 0.0399,
"step": 264
},
{
"epoch": 1.869488536155203,
"grad_norm": 0.5836982131004333,
"learning_rate": 5e-05,
"loss": 0.0547,
"step": 265
},
{
"epoch": 1.876543209876543,
"grad_norm": 0.5359038710594177,
"learning_rate": 5e-05,
"loss": 0.0582,
"step": 266
},
{
"epoch": 1.8835978835978837,
"grad_norm": 0.5191663503646851,
"learning_rate": 5e-05,
"loss": 0.0347,
"step": 267
},
{
"epoch": 1.8906525573192239,
"grad_norm": 0.6412689089775085,
"learning_rate": 5e-05,
"loss": 0.0419,
"step": 268
},
{
"epoch": 1.8977072310405645,
"grad_norm": 0.76778244972229,
"learning_rate": 5e-05,
"loss": 0.0464,
"step": 269
},
{
"epoch": 1.9047619047619047,
"grad_norm": 0.4410521388053894,
"learning_rate": 5e-05,
"loss": 0.0342,
"step": 270
},
{
"epoch": 1.9118165784832453,
"grad_norm": 0.8977980017662048,
"learning_rate": 5e-05,
"loss": 0.0793,
"step": 271
},
{
"epoch": 1.9188712522045854,
"grad_norm": 0.9770653247833252,
"learning_rate": 5e-05,
"loss": 0.0519,
"step": 272
},
{
"epoch": 1.925925925925926,
"grad_norm": 0.9411201477050781,
"learning_rate": 5e-05,
"loss": 0.0443,
"step": 273
},
{
"epoch": 1.9329805996472662,
"grad_norm": 0.504085123538971,
"learning_rate": 5e-05,
"loss": 0.0112,
"step": 274
},
{
"epoch": 1.9400352733686068,
"grad_norm": 0.5680234432220459,
"learning_rate": 5e-05,
"loss": 0.0367,
"step": 275
},
{
"epoch": 1.947089947089947,
"grad_norm": 0.5446969270706177,
"learning_rate": 5e-05,
"loss": 0.046,
"step": 276
},
{
"epoch": 1.9541446208112876,
"grad_norm": 0.4226911664009094,
"learning_rate": 5e-05,
"loss": 0.0254,
"step": 277
},
{
"epoch": 1.9611992945326278,
"grad_norm": 0.4745901823043823,
"learning_rate": 5e-05,
"loss": 0.0296,
"step": 278
},
{
"epoch": 1.9682539682539684,
"grad_norm": 0.4772842526435852,
"learning_rate": 5e-05,
"loss": 0.0235,
"step": 279
},
{
"epoch": 1.9753086419753085,
"grad_norm": 0.561303436756134,
"learning_rate": 5e-05,
"loss": 0.0289,
"step": 280
},
{
"epoch": 1.9823633156966491,
"grad_norm": 3.243555784225464,
"learning_rate": 5e-05,
"loss": 0.0625,
"step": 281
},
{
"epoch": 1.9894179894179893,
"grad_norm": 0.5137839317321777,
"learning_rate": 5e-05,
"loss": 0.0852,
"step": 282
},
{
"epoch": 1.99647266313933,
"grad_norm": 0.4999793767929077,
"learning_rate": 5e-05,
"loss": 0.0398,
"step": 283
},
{
"epoch": 2.00352733686067,
"grad_norm": 0.4685242772102356,
"learning_rate": 5e-05,
"loss": 0.0404,
"step": 284
},
{
"epoch": 2.0105820105820107,
"grad_norm": 0.4656790494918823,
"learning_rate": 5e-05,
"loss": 0.0315,
"step": 285
},
{
"epoch": 2.017636684303351,
"grad_norm": 0.5658271312713623,
"learning_rate": 5e-05,
"loss": 0.0298,
"step": 286
},
{
"epoch": 2.0246913580246915,
"grad_norm": 0.731564998626709,
"learning_rate": 5e-05,
"loss": 0.0577,
"step": 287
},
{
"epoch": 2.0317460317460316,
"grad_norm": 0.45937952399253845,
"learning_rate": 5e-05,
"loss": 0.0393,
"step": 288
},
{
"epoch": 2.0388007054673722,
"grad_norm": 0.559946596622467,
"learning_rate": 5e-05,
"loss": 0.0602,
"step": 289
},
{
"epoch": 2.0458553791887124,
"grad_norm": 0.5641235709190369,
"learning_rate": 5e-05,
"loss": 0.0501,
"step": 290
},
{
"epoch": 2.052910052910053,
"grad_norm": 0.47334426641464233,
"learning_rate": 5e-05,
"loss": 0.0501,
"step": 291
},
{
"epoch": 2.059964726631393,
"grad_norm": 0.6770443320274353,
"learning_rate": 5e-05,
"loss": 0.0853,
"step": 292
},
{
"epoch": 2.067019400352734,
"grad_norm": 0.4847649037837982,
"learning_rate": 5e-05,
"loss": 0.0553,
"step": 293
},
{
"epoch": 2.074074074074074,
"grad_norm": 0.49225914478302,
"learning_rate": 5e-05,
"loss": 0.046,
"step": 294
},
{
"epoch": 2.0811287477954146,
"grad_norm": 0.7099577188491821,
"learning_rate": 5e-05,
"loss": 0.047,
"step": 295
},
{
"epoch": 2.0881834215167547,
"grad_norm": 0.5774824023246765,
"learning_rate": 5e-05,
"loss": 0.0329,
"step": 296
},
{
"epoch": 2.0952380952380953,
"grad_norm": 0.4122166931629181,
"learning_rate": 5e-05,
"loss": 0.032,
"step": 297
},
{
"epoch": 2.1022927689594355,
"grad_norm": 0.6180548071861267,
"learning_rate": 5e-05,
"loss": 0.0396,
"step": 298
},
{
"epoch": 2.109347442680776,
"grad_norm": 0.4783317446708679,
"learning_rate": 5e-05,
"loss": 0.028,
"step": 299
},
{
"epoch": 2.1164021164021163,
"grad_norm": 0.5351418256759644,
"learning_rate": 5e-05,
"loss": 0.033,
"step": 300
},
{
"epoch": 2.1164021164021163,
"eval_loss": 0.19941070675849915,
"eval_runtime": 362.8638,
"eval_samples_per_second": 6.25,
"eval_steps_per_second": 0.391,
"step": 300
},
{
"epoch": 2.123456790123457,
"grad_norm": 0.3710566759109497,
"learning_rate": 5e-05,
"loss": 0.0291,
"step": 301
},
{
"epoch": 2.130511463844797,
"grad_norm": 0.5422140955924988,
"learning_rate": 5e-05,
"loss": 0.0364,
"step": 302
},
{
"epoch": 2.1375661375661377,
"grad_norm": 0.6321272253990173,
"learning_rate": 5e-05,
"loss": 0.0462,
"step": 303
},
{
"epoch": 2.144620811287478,
"grad_norm": 0.5658572912216187,
"learning_rate": 5e-05,
"loss": 0.0265,
"step": 304
},
{
"epoch": 2.1516754850088184,
"grad_norm": 0.5490357279777527,
"learning_rate": 5e-05,
"loss": 0.028,
"step": 305
},
{
"epoch": 2.1587301587301586,
"grad_norm": 0.42299216985702515,
"learning_rate": 5e-05,
"loss": 0.0301,
"step": 306
},
{
"epoch": 2.165784832451499,
"grad_norm": 0.5153865814208984,
"learning_rate": 5e-05,
"loss": 0.0192,
"step": 307
},
{
"epoch": 2.1728395061728394,
"grad_norm": 0.5954696536064148,
"learning_rate": 5e-05,
"loss": 0.0362,
"step": 308
},
{
"epoch": 2.17989417989418,
"grad_norm": 0.7111172080039978,
"learning_rate": 5e-05,
"loss": 0.0496,
"step": 309
},
{
"epoch": 2.18694885361552,
"grad_norm": 0.7426902055740356,
"learning_rate": 5e-05,
"loss": 0.0625,
"step": 310
},
{
"epoch": 2.1940035273368608,
"grad_norm": 0.5204232335090637,
"learning_rate": 5e-05,
"loss": 0.0252,
"step": 311
},
{
"epoch": 2.201058201058201,
"grad_norm": 0.7376022338867188,
"learning_rate": 5e-05,
"loss": 0.0286,
"step": 312
},
{
"epoch": 2.2081128747795415,
"grad_norm": 0.46142226457595825,
"learning_rate": 5e-05,
"loss": 0.0484,
"step": 313
},
{
"epoch": 2.2151675485008817,
"grad_norm": 0.3670506477355957,
"learning_rate": 5e-05,
"loss": 0.0254,
"step": 314
},
{
"epoch": 2.2222222222222223,
"grad_norm": 0.7535457611083984,
"learning_rate": 5e-05,
"loss": 0.101,
"step": 315
},
{
"epoch": 2.2292768959435625,
"grad_norm": 0.5934197306632996,
"learning_rate": 5e-05,
"loss": 0.0496,
"step": 316
},
{
"epoch": 2.236331569664903,
"grad_norm": 0.30532220005989075,
"learning_rate": 5e-05,
"loss": 0.0212,
"step": 317
},
{
"epoch": 2.2433862433862433,
"grad_norm": 0.4631759822368622,
"learning_rate": 5e-05,
"loss": 0.0361,
"step": 318
},
{
"epoch": 2.250440917107584,
"grad_norm": 0.3577938675880432,
"learning_rate": 5e-05,
"loss": 0.0416,
"step": 319
},
{
"epoch": 2.257495590828924,
"grad_norm": 0.4464920461177826,
"learning_rate": 5e-05,
"loss": 0.0408,
"step": 320
},
{
"epoch": 2.2645502645502646,
"grad_norm": 0.3824048638343811,
"learning_rate": 5e-05,
"loss": 0.0248,
"step": 321
},
{
"epoch": 2.271604938271605,
"grad_norm": 0.6711484789848328,
"learning_rate": 5e-05,
"loss": 0.0487,
"step": 322
},
{
"epoch": 2.2786596119929454,
"grad_norm": 0.6138588786125183,
"learning_rate": 5e-05,
"loss": 0.043,
"step": 323
},
{
"epoch": 2.2857142857142856,
"grad_norm": 0.4771498739719391,
"learning_rate": 5e-05,
"loss": 0.0258,
"step": 324
},
{
"epoch": 2.292768959435626,
"grad_norm": 0.5928422808647156,
"learning_rate": 5e-05,
"loss": 0.0295,
"step": 325
},
{
"epoch": 2.2998236331569664,
"grad_norm": 0.579921305179596,
"learning_rate": 5e-05,
"loss": 0.068,
"step": 326
},
{
"epoch": 2.306878306878307,
"grad_norm": 0.6070377230644226,
"learning_rate": 5e-05,
"loss": 0.0542,
"step": 327
},
{
"epoch": 2.313932980599647,
"grad_norm": 0.6430080533027649,
"learning_rate": 5e-05,
"loss": 0.0492,
"step": 328
},
{
"epoch": 2.3209876543209877,
"grad_norm": 0.4864685535430908,
"learning_rate": 5e-05,
"loss": 0.0432,
"step": 329
},
{
"epoch": 2.328042328042328,
"grad_norm": 0.7958788275718689,
"learning_rate": 5e-05,
"loss": 0.0455,
"step": 330
},
{
"epoch": 2.3350970017636685,
"grad_norm": 0.49791809916496277,
"learning_rate": 5e-05,
"loss": 0.0132,
"step": 331
},
{
"epoch": 2.3421516754850087,
"grad_norm": 0.7294586896896362,
"learning_rate": 5e-05,
"loss": 0.0571,
"step": 332
},
{
"epoch": 2.3492063492063493,
"grad_norm": 0.42604896426200867,
"learning_rate": 5e-05,
"loss": 0.0288,
"step": 333
},
{
"epoch": 2.3562610229276895,
"grad_norm": 0.41210633516311646,
"learning_rate": 5e-05,
"loss": 0.0316,
"step": 334
},
{
"epoch": 2.36331569664903,
"grad_norm": 0.5827341675758362,
"learning_rate": 5e-05,
"loss": 0.0202,
"step": 335
},
{
"epoch": 2.3703703703703702,
"grad_norm": 0.4686066210269928,
"learning_rate": 5e-05,
"loss": 0.0431,
"step": 336
},
{
"epoch": 2.377425044091711,
"grad_norm": 0.4502599835395813,
"learning_rate": 5e-05,
"loss": 0.0234,
"step": 337
},
{
"epoch": 2.384479717813051,
"grad_norm": 0.6698682904243469,
"learning_rate": 5e-05,
"loss": 0.0523,
"step": 338
},
{
"epoch": 2.3915343915343916,
"grad_norm": 0.5106789469718933,
"learning_rate": 5e-05,
"loss": 0.0666,
"step": 339
},
{
"epoch": 2.398589065255732,
"grad_norm": 0.4766543507575989,
"learning_rate": 5e-05,
"loss": 0.0293,
"step": 340
},
{
"epoch": 2.4056437389770724,
"grad_norm": 0.9548158049583435,
"learning_rate": 5e-05,
"loss": 0.029,
"step": 341
},
{
"epoch": 2.4126984126984126,
"grad_norm": 0.4722541570663452,
"learning_rate": 5e-05,
"loss": 0.0585,
"step": 342
},
{
"epoch": 2.419753086419753,
"grad_norm": 0.42772984504699707,
"learning_rate": 5e-05,
"loss": 0.0684,
"step": 343
},
{
"epoch": 2.4268077601410933,
"grad_norm": 0.5742454528808594,
"learning_rate": 5e-05,
"loss": 0.0491,
"step": 344
},
{
"epoch": 2.433862433862434,
"grad_norm": 1.2364797592163086,
"learning_rate": 5e-05,
"loss": 0.0348,
"step": 345
},
{
"epoch": 2.440917107583774,
"grad_norm": 3.099977731704712,
"learning_rate": 5e-05,
"loss": 0.0264,
"step": 346
},
{
"epoch": 2.4479717813051147,
"grad_norm": 0.6101909279823303,
"learning_rate": 5e-05,
"loss": 0.0939,
"step": 347
},
{
"epoch": 2.455026455026455,
"grad_norm": 1.5888972282409668,
"learning_rate": 5e-05,
"loss": 0.0187,
"step": 348
},
{
"epoch": 2.4620811287477955,
"grad_norm": 0.5128622651100159,
"learning_rate": 5e-05,
"loss": 0.0267,
"step": 349
},
{
"epoch": 2.4691358024691357,
"grad_norm": 0.4196084141731262,
"learning_rate": 5e-05,
"loss": 0.0312,
"step": 350
},
{
"epoch": 2.4761904761904763,
"grad_norm": 0.5221646428108215,
"learning_rate": 5e-05,
"loss": 0.0234,
"step": 351
},
{
"epoch": 2.4832451499118164,
"grad_norm": 0.769625186920166,
"learning_rate": 5e-05,
"loss": 0.0181,
"step": 352
},
{
"epoch": 2.490299823633157,
"grad_norm": 0.5391407608985901,
"learning_rate": 5e-05,
"loss": 0.039,
"step": 353
},
{
"epoch": 2.497354497354497,
"grad_norm": 0.488760381937027,
"learning_rate": 5e-05,
"loss": 0.0292,
"step": 354
},
{
"epoch": 2.504409171075838,
"grad_norm": 0.40043187141418457,
"learning_rate": 5e-05,
"loss": 0.0197,
"step": 355
},
{
"epoch": 2.511463844797178,
"grad_norm": 0.4821717441082001,
"learning_rate": 5e-05,
"loss": 0.042,
"step": 356
},
{
"epoch": 2.5185185185185186,
"grad_norm": 0.3457970917224884,
"learning_rate": 5e-05,
"loss": 0.0276,
"step": 357
},
{
"epoch": 2.5255731922398588,
"grad_norm": 0.28284406661987305,
"learning_rate": 5e-05,
"loss": 0.022,
"step": 358
},
{
"epoch": 2.5326278659611994,
"grad_norm": 0.5945581793785095,
"learning_rate": 5e-05,
"loss": 0.0735,
"step": 359
},
{
"epoch": 2.5396825396825395,
"grad_norm": 0.4184766709804535,
"learning_rate": 5e-05,
"loss": 0.0257,
"step": 360
},
{
"epoch": 2.54673721340388,
"grad_norm": 0.620948851108551,
"learning_rate": 5e-05,
"loss": 0.0181,
"step": 361
},
{
"epoch": 2.5537918871252203,
"grad_norm": 0.4545421898365021,
"learning_rate": 5e-05,
"loss": 0.0146,
"step": 362
},
{
"epoch": 2.560846560846561,
"grad_norm": 0.7520444989204407,
"learning_rate": 5e-05,
"loss": 0.0262,
"step": 363
},
{
"epoch": 2.567901234567901,
"grad_norm": 0.46159473061561584,
"learning_rate": 5e-05,
"loss": 0.0254,
"step": 364
},
{
"epoch": 2.5749559082892417,
"grad_norm": 0.899054229259491,
"learning_rate": 5e-05,
"loss": 0.0166,
"step": 365
},
{
"epoch": 2.582010582010582,
"grad_norm": 0.501522958278656,
"learning_rate": 5e-05,
"loss": 0.0426,
"step": 366
},
{
"epoch": 2.5890652557319225,
"grad_norm": 0.5105156898498535,
"learning_rate": 5e-05,
"loss": 0.0275,
"step": 367
},
{
"epoch": 2.5961199294532626,
"grad_norm": 0.5256771445274353,
"learning_rate": 5e-05,
"loss": 0.054,
"step": 368
},
{
"epoch": 2.6031746031746033,
"grad_norm": 0.49999576807022095,
"learning_rate": 5e-05,
"loss": 0.0279,
"step": 369
},
{
"epoch": 2.6102292768959434,
"grad_norm": 0.5966548919677734,
"learning_rate": 5e-05,
"loss": 0.0425,
"step": 370
},
{
"epoch": 2.617283950617284,
"grad_norm": 0.45533132553100586,
"learning_rate": 5e-05,
"loss": 0.0218,
"step": 371
},
{
"epoch": 2.624338624338624,
"grad_norm": 0.6391978859901428,
"learning_rate": 5e-05,
"loss": 0.0365,
"step": 372
},
{
"epoch": 2.631393298059965,
"grad_norm": 0.8711655735969543,
"learning_rate": 5e-05,
"loss": 0.039,
"step": 373
},
{
"epoch": 2.638447971781305,
"grad_norm": 0.6811898350715637,
"learning_rate": 5e-05,
"loss": 0.0241,
"step": 374
},
{
"epoch": 2.6455026455026456,
"grad_norm": 0.7612636089324951,
"learning_rate": 5e-05,
"loss": 0.02,
"step": 375
},
{
"epoch": 2.6525573192239857,
"grad_norm": 0.8182013630867004,
"learning_rate": 5e-05,
"loss": 0.0703,
"step": 376
},
{
"epoch": 2.6596119929453264,
"grad_norm": 0.39782482385635376,
"learning_rate": 5e-05,
"loss": 0.0245,
"step": 377
},
{
"epoch": 2.6666666666666665,
"grad_norm": 0.4738399386405945,
"learning_rate": 5e-05,
"loss": 0.0302,
"step": 378
},
{
"epoch": 2.673721340388007,
"grad_norm": 0.3865676820278168,
"learning_rate": 5e-05,
"loss": 0.0369,
"step": 379
},
{
"epoch": 2.6807760141093473,
"grad_norm": 0.4017925262451172,
"learning_rate": 5e-05,
"loss": 0.0132,
"step": 380
},
{
"epoch": 2.687830687830688,
"grad_norm": 0.5341134667396545,
"learning_rate": 5e-05,
"loss": 0.0461,
"step": 381
},
{
"epoch": 2.694885361552028,
"grad_norm": 0.7711620330810547,
"learning_rate": 5e-05,
"loss": 0.0287,
"step": 382
},
{
"epoch": 2.7019400352733687,
"grad_norm": 0.4064803719520569,
"learning_rate": 5e-05,
"loss": 0.0202,
"step": 383
},
{
"epoch": 2.708994708994709,
"grad_norm": 0.24531042575836182,
"learning_rate": 5e-05,
"loss": 0.0211,
"step": 384
},
{
"epoch": 2.7160493827160495,
"grad_norm": 0.6126789450645447,
"learning_rate": 5e-05,
"loss": 0.0215,
"step": 385
},
{
"epoch": 2.7231040564373896,
"grad_norm": 0.4999621510505676,
"learning_rate": 5e-05,
"loss": 0.0218,
"step": 386
},
{
"epoch": 2.7301587301587302,
"grad_norm": 0.5171307921409607,
"learning_rate": 5e-05,
"loss": 0.0243,
"step": 387
},
{
"epoch": 2.7372134038800704,
"grad_norm": 0.95902419090271,
"learning_rate": 5e-05,
"loss": 0.0367,
"step": 388
},
{
"epoch": 2.744268077601411,
"grad_norm": 0.6669855117797852,
"learning_rate": 5e-05,
"loss": 0.0188,
"step": 389
},
{
"epoch": 2.751322751322751,
"grad_norm": 0.49141064286231995,
"learning_rate": 5e-05,
"loss": 0.0174,
"step": 390
},
{
"epoch": 2.758377425044092,
"grad_norm": 0.36193522810935974,
"learning_rate": 5e-05,
"loss": 0.0074,
"step": 391
},
{
"epoch": 2.765432098765432,
"grad_norm": 0.6513599753379822,
"learning_rate": 5e-05,
"loss": 0.0491,
"step": 392
},
{
"epoch": 2.7724867724867726,
"grad_norm": 0.5697189569473267,
"learning_rate": 5e-05,
"loss": 0.0225,
"step": 393
},
{
"epoch": 2.7795414462081127,
"grad_norm": 0.752934992313385,
"learning_rate": 5e-05,
"loss": 0.0561,
"step": 394
},
{
"epoch": 2.7865961199294533,
"grad_norm": 0.8643583655357361,
"learning_rate": 5e-05,
"loss": 0.0199,
"step": 395
},
{
"epoch": 2.7936507936507935,
"grad_norm": 0.5964650511741638,
"learning_rate": 5e-05,
"loss": 0.0356,
"step": 396
},
{
"epoch": 2.800705467372134,
"grad_norm": 0.3856894075870514,
"learning_rate": 5e-05,
"loss": 0.028,
"step": 397
},
{
"epoch": 2.8077601410934743,
"grad_norm": 0.6613327860832214,
"learning_rate": 5e-05,
"loss": 0.0278,
"step": 398
},
{
"epoch": 2.814814814814815,
"grad_norm": 0.40905261039733887,
"learning_rate": 5e-05,
"loss": 0.022,
"step": 399
},
{
"epoch": 2.821869488536155,
"grad_norm": 0.3591744005680084,
"learning_rate": 5e-05,
"loss": 0.0333,
"step": 400
},
{
"epoch": 2.821869488536155,
"eval_loss": 0.19655056297779083,
"eval_runtime": 358.8507,
"eval_samples_per_second": 6.32,
"eval_steps_per_second": 0.396,
"step": 400
},
{
"epoch": 2.821869488536155,
"step": 400,
"total_flos": 2.7548487274232545e+18,
"train_loss": 0.09715834772447124,
"train_runtime": 13184.0406,
"train_samples_per_second": 4.854,
"train_steps_per_second": 0.076
}
],
"logging_steps": 1.0,
"max_steps": 1000,
"num_input_tokens_seen": 0,
"num_train_epochs": 8,
"save_steps": 100,
"total_flos": 2.7548487274232545e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}