c1_science_nod_1s_0.3k / trainer_state.json
ryanmarten's picture
Upload model
f3a654e verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 13.0,
"eval_steps": 500,
"global_step": 130,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1,
"grad_norm": 6.261992492095545,
"learning_rate": 7.692307692307694e-07,
"loss": 1.0416,
"step": 1
},
{
"epoch": 0.2,
"grad_norm": 6.757128287380425,
"learning_rate": 1.5384615384615387e-06,
"loss": 1.0857,
"step": 2
},
{
"epoch": 0.3,
"grad_norm": 6.218315850314032,
"learning_rate": 2.307692307692308e-06,
"loss": 1.0292,
"step": 3
},
{
"epoch": 0.4,
"grad_norm": 6.144117812031815,
"learning_rate": 3.0769230769230774e-06,
"loss": 1.0209,
"step": 4
},
{
"epoch": 0.5,
"grad_norm": 4.958220725029353,
"learning_rate": 3.846153846153847e-06,
"loss": 0.9878,
"step": 5
},
{
"epoch": 0.6,
"grad_norm": 3.289052932916341,
"learning_rate": 4.615384615384616e-06,
"loss": 0.934,
"step": 6
},
{
"epoch": 0.7,
"grad_norm": 2.1492953443919744,
"learning_rate": 5.384615384615385e-06,
"loss": 0.9264,
"step": 7
},
{
"epoch": 0.8,
"grad_norm": 3.5251489841659644,
"learning_rate": 6.153846153846155e-06,
"loss": 0.9201,
"step": 8
},
{
"epoch": 0.9,
"grad_norm": 4.8414581671040935,
"learning_rate": 6.923076923076923e-06,
"loss": 0.98,
"step": 9
},
{
"epoch": 1.0,
"grad_norm": 5.16359119853228,
"learning_rate": 7.692307692307694e-06,
"loss": 0.9998,
"step": 10
},
{
"epoch": 1.1,
"grad_norm": 3.9675380379279193,
"learning_rate": 8.461538461538462e-06,
"loss": 0.8545,
"step": 11
},
{
"epoch": 1.2,
"grad_norm": 3.925504578809822,
"learning_rate": 9.230769230769232e-06,
"loss": 0.8453,
"step": 12
},
{
"epoch": 1.3,
"grad_norm": 3.2437937510710175,
"learning_rate": 1e-05,
"loss": 0.8299,
"step": 13
},
{
"epoch": 1.4,
"grad_norm": 2.8873899733237374,
"learning_rate": 9.998197638354428e-06,
"loss": 0.8255,
"step": 14
},
{
"epoch": 1.5,
"grad_norm": 2.5806235449580557,
"learning_rate": 9.992791852820709e-06,
"loss": 0.8424,
"step": 15
},
{
"epoch": 1.6,
"grad_norm": 2.1708263840665496,
"learning_rate": 9.983786540671052e-06,
"loss": 0.7638,
"step": 16
},
{
"epoch": 1.7,
"grad_norm": 2.016409440376707,
"learning_rate": 9.971188194237141e-06,
"loss": 0.7712,
"step": 17
},
{
"epoch": 1.8,
"grad_norm": 1.863726147422399,
"learning_rate": 9.955005896229543e-06,
"loss": 0.7931,
"step": 18
},
{
"epoch": 1.9,
"grad_norm": 1.6909887326457729,
"learning_rate": 9.935251313189564e-06,
"loss": 0.8593,
"step": 19
},
{
"epoch": 2.0,
"grad_norm": 1.4452535576675236,
"learning_rate": 9.911938687078324e-06,
"loss": 0.7589,
"step": 20
},
{
"epoch": 2.1,
"grad_norm": 1.5429348453007168,
"learning_rate": 9.885084825009085e-06,
"loss": 0.7058,
"step": 21
},
{
"epoch": 2.2,
"grad_norm": 1.8735420436178696,
"learning_rate": 9.854709087130261e-06,
"loss": 0.7155,
"step": 22
},
{
"epoch": 2.3,
"grad_norm": 1.4473127574705544,
"learning_rate": 9.820833372667813e-06,
"loss": 0.6617,
"step": 23
},
{
"epoch": 2.4,
"grad_norm": 1.1629121378457525,
"learning_rate": 9.783482104137127e-06,
"loss": 0.6961,
"step": 24
},
{
"epoch": 2.5,
"grad_norm": 0.9235934527154791,
"learning_rate": 9.742682209735727e-06,
"loss": 0.5911,
"step": 25
},
{
"epoch": 2.6,
"grad_norm": 1.4997874901274457,
"learning_rate": 9.698463103929542e-06,
"loss": 0.6389,
"step": 26
},
{
"epoch": 2.7,
"grad_norm": 1.2260627887557662,
"learning_rate": 9.650856666246693e-06,
"loss": 0.6318,
"step": 27
},
{
"epoch": 2.8,
"grad_norm": 1.0166146171416393,
"learning_rate": 9.599897218294122e-06,
"loss": 0.6037,
"step": 28
},
{
"epoch": 2.9,
"grad_norm": 1.0196126823025176,
"learning_rate": 9.54562149901362e-06,
"loss": 0.6719,
"step": 29
},
{
"epoch": 3.0,
"grad_norm": 1.0816774204687938,
"learning_rate": 9.488068638195072e-06,
"loss": 0.6298,
"step": 30
},
{
"epoch": 3.1,
"grad_norm": 1.037351206454359,
"learning_rate": 9.427280128266049e-06,
"loss": 0.5452,
"step": 31
},
{
"epoch": 3.2,
"grad_norm": 1.0969362066069972,
"learning_rate": 9.363299794378072e-06,
"loss": 0.481,
"step": 32
},
{
"epoch": 3.3,
"grad_norm": 0.9790416378583843,
"learning_rate": 9.296173762811084e-06,
"loss": 0.5335,
"step": 33
},
{
"epoch": 3.4,
"grad_norm": 1.6959655965023333,
"learning_rate": 9.225950427718974e-06,
"loss": 0.513,
"step": 34
},
{
"epoch": 3.5,
"grad_norm": 1.1314959176267063,
"learning_rate": 9.152680416240059e-06,
"loss": 0.4448,
"step": 35
},
{
"epoch": 3.6,
"grad_norm": 0.9612956636893629,
"learning_rate": 9.076416551997721e-06,
"loss": 0.4697,
"step": 36
},
{
"epoch": 3.7,
"grad_norm": 1.0735754296687787,
"learning_rate": 8.997213817017508e-06,
"loss": 0.4798,
"step": 37
},
{
"epoch": 3.8,
"grad_norm": 1.0261860545039265,
"learning_rate": 8.915129312088112e-06,
"loss": 0.4716,
"step": 38
},
{
"epoch": 3.9,
"grad_norm": 0.9985061750968255,
"learning_rate": 8.83022221559489e-06,
"loss": 0.4623,
"step": 39
},
{
"epoch": 4.0,
"grad_norm": 0.911516530542988,
"learning_rate": 8.742553740855507e-06,
"loss": 0.4422,
"step": 40
},
{
"epoch": 4.1,
"grad_norm": 0.9870183016864826,
"learning_rate": 8.652187091988516e-06,
"loss": 0.3902,
"step": 41
},
{
"epoch": 4.2,
"grad_norm": 0.9817082509946518,
"learning_rate": 8.559187418346703e-06,
"loss": 0.3621,
"step": 42
},
{
"epoch": 4.3,
"grad_norm": 0.8952256862416887,
"learning_rate": 8.463621767547998e-06,
"loss": 0.3463,
"step": 43
},
{
"epoch": 4.4,
"grad_norm": 1.3927494433485679,
"learning_rate": 8.36555903713785e-06,
"loss": 0.3098,
"step": 44
},
{
"epoch": 4.5,
"grad_norm": 1.173886510842353,
"learning_rate": 8.265069924917925e-06,
"loss": 0.3471,
"step": 45
},
{
"epoch": 4.6,
"grad_norm": 0.9657884754337799,
"learning_rate": 8.162226877976886e-06,
"loss": 0.4013,
"step": 46
},
{
"epoch": 4.7,
"grad_norm": 0.9767071030666424,
"learning_rate": 8.057104040460062e-06,
"loss": 0.3122,
"step": 47
},
{
"epoch": 4.8,
"grad_norm": 0.8691811357935035,
"learning_rate": 7.949777200115617e-06,
"loss": 0.3231,
"step": 48
},
{
"epoch": 4.9,
"grad_norm": 0.9290514482697234,
"learning_rate": 7.84032373365578e-06,
"loss": 0.3175,
"step": 49
},
{
"epoch": 5.0,
"grad_norm": 0.9201535177937232,
"learning_rate": 7.728822550972523e-06,
"loss": 0.3356,
"step": 50
},
{
"epoch": 5.1,
"grad_norm": 0.8355745446224265,
"learning_rate": 7.615354038247889e-06,
"loss": 0.2762,
"step": 51
},
{
"epoch": 5.2,
"grad_norm": 0.8132503757872306,
"learning_rate": 7.500000000000001e-06,
"loss": 0.2111,
"step": 52
},
{
"epoch": 5.3,
"grad_norm": 0.8785443030734309,
"learning_rate": 7.382843600106539e-06,
"loss": 0.2391,
"step": 53
},
{
"epoch": 5.4,
"grad_norm": 0.8137093496706936,
"learning_rate": 7.263969301848188e-06,
"loss": 0.2429,
"step": 54
},
{
"epoch": 5.5,
"grad_norm": 1.0320656582276806,
"learning_rate": 7.143462807015271e-06,
"loss": 0.2146,
"step": 55
},
{
"epoch": 5.6,
"grad_norm": 0.7903514159885137,
"learning_rate": 7.021410994121525e-06,
"loss": 0.23,
"step": 56
},
{
"epoch": 5.7,
"grad_norm": 0.8907415847463244,
"learning_rate": 6.897901855769483e-06,
"loss": 0.2682,
"step": 57
},
{
"epoch": 5.8,
"grad_norm": 0.8524844118482418,
"learning_rate": 6.773024435212678e-06,
"loss": 0.2163,
"step": 58
},
{
"epoch": 5.9,
"grad_norm": 0.8757136261617099,
"learning_rate": 6.646868762160399e-06,
"loss": 0.213,
"step": 59
},
{
"epoch": 6.0,
"grad_norm": 0.8758502179638537,
"learning_rate": 6.519525787871235e-06,
"loss": 0.2465,
"step": 60
},
{
"epoch": 6.1,
"grad_norm": 0.7539179182235125,
"learning_rate": 6.391087319582264e-06,
"loss": 0.1475,
"step": 61
},
{
"epoch": 6.2,
"grad_norm": 0.7331644780159402,
"learning_rate": 6.261645954321109e-06,
"loss": 0.1736,
"step": 62
},
{
"epoch": 6.3,
"grad_norm": 0.8672832823204837,
"learning_rate": 6.131295012148613e-06,
"loss": 0.1595,
"step": 63
},
{
"epoch": 6.4,
"grad_norm": 0.907785828709626,
"learning_rate": 6.000128468880223e-06,
"loss": 0.1459,
"step": 64
},
{
"epoch": 6.5,
"grad_norm": 0.9570338080602984,
"learning_rate": 5.8682408883346535e-06,
"loss": 0.1712,
"step": 65
},
{
"epoch": 6.6,
"grad_norm": 0.7196333655812464,
"learning_rate": 5.735727354158581e-06,
"loss": 0.1681,
"step": 66
},
{
"epoch": 6.7,
"grad_norm": 0.8038729491960346,
"learning_rate": 5.6026834012766155e-06,
"loss": 0.1537,
"step": 67
},
{
"epoch": 6.8,
"grad_norm": 0.8009489947163452,
"learning_rate": 5.469204947015897e-06,
"loss": 0.1448,
"step": 68
},
{
"epoch": 6.9,
"grad_norm": 0.7446611066366815,
"learning_rate": 5.335388221955012e-06,
"loss": 0.1399,
"step": 69
},
{
"epoch": 7.0,
"grad_norm": 0.7784919314378965,
"learning_rate": 5.201329700547077e-06,
"loss": 0.1303,
"step": 70
},
{
"epoch": 7.1,
"grad_norm": 0.7629509387357639,
"learning_rate": 5.067126031566988e-06,
"loss": 0.1127,
"step": 71
},
{
"epoch": 7.2,
"grad_norm": 0.68694962782659,
"learning_rate": 4.932873968433014e-06,
"loss": 0.1212,
"step": 72
},
{
"epoch": 7.3,
"grad_norm": 0.5527020407336934,
"learning_rate": 4.798670299452926e-06,
"loss": 0.0886,
"step": 73
},
{
"epoch": 7.4,
"grad_norm": 0.7206360070058249,
"learning_rate": 4.664611778044988e-06,
"loss": 0.0967,
"step": 74
},
{
"epoch": 7.5,
"grad_norm": 0.8123658599323496,
"learning_rate": 4.530795052984104e-06,
"loss": 0.1155,
"step": 75
},
{
"epoch": 7.6,
"grad_norm": 0.6010018172494729,
"learning_rate": 4.397316598723385e-06,
"loss": 0.0933,
"step": 76
},
{
"epoch": 7.7,
"grad_norm": 0.6288721135182109,
"learning_rate": 4.264272645841419e-06,
"loss": 0.0757,
"step": 77
},
{
"epoch": 7.8,
"grad_norm": 0.8244605450802386,
"learning_rate": 4.131759111665349e-06,
"loss": 0.1136,
"step": 78
},
{
"epoch": 7.9,
"grad_norm": 0.7063323301160357,
"learning_rate": 3.999871531119779e-06,
"loss": 0.0695,
"step": 79
},
{
"epoch": 8.0,
"grad_norm": 0.6064405150970131,
"learning_rate": 3.86870498785139e-06,
"loss": 0.0708,
"step": 80
},
{
"epoch": 8.1,
"grad_norm": 0.6439819098334986,
"learning_rate": 3.7383540456788915e-06,
"loss": 0.0595,
"step": 81
},
{
"epoch": 8.2,
"grad_norm": 0.50622452441808,
"learning_rate": 3.6089126804177373e-06,
"loss": 0.0607,
"step": 82
},
{
"epoch": 8.3,
"grad_norm": 0.5486790385729916,
"learning_rate": 3.480474212128766e-06,
"loss": 0.0831,
"step": 83
},
{
"epoch": 8.4,
"grad_norm": 0.548545151827244,
"learning_rate": 3.3531312378396026e-06,
"loss": 0.0698,
"step": 84
},
{
"epoch": 8.5,
"grad_norm": 0.6787444490577134,
"learning_rate": 3.226975564787322e-06,
"loss": 0.0714,
"step": 85
},
{
"epoch": 8.6,
"grad_norm": 0.5990604401225172,
"learning_rate": 3.1020981442305187e-06,
"loss": 0.0714,
"step": 86
},
{
"epoch": 8.7,
"grad_norm": 0.5726875229691178,
"learning_rate": 2.978589005878476e-06,
"loss": 0.0713,
"step": 87
},
{
"epoch": 8.8,
"grad_norm": 0.6786669611580614,
"learning_rate": 2.8565371929847286e-06,
"loss": 0.0405,
"step": 88
},
{
"epoch": 8.9,
"grad_norm": 0.5149293555014661,
"learning_rate": 2.736030698151815e-06,
"loss": 0.0659,
"step": 89
},
{
"epoch": 9.0,
"grad_norm": 0.5885561764043062,
"learning_rate": 2.6171563998934605e-06,
"loss": 0.0678,
"step": 90
},
{
"epoch": 9.1,
"grad_norm": 0.6563105482116436,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.0688,
"step": 91
},
{
"epoch": 9.2,
"grad_norm": 0.449237722580197,
"learning_rate": 2.384645961752113e-06,
"loss": 0.0428,
"step": 92
},
{
"epoch": 9.3,
"grad_norm": 0.4646158928426489,
"learning_rate": 2.2711774490274767e-06,
"loss": 0.0555,
"step": 93
},
{
"epoch": 9.4,
"grad_norm": 0.4684893371292831,
"learning_rate": 2.159676266344222e-06,
"loss": 0.0564,
"step": 94
},
{
"epoch": 9.5,
"grad_norm": 0.4034580016856263,
"learning_rate": 2.050222799884387e-06,
"loss": 0.0354,
"step": 95
},
{
"epoch": 9.6,
"grad_norm": 0.5500842249709914,
"learning_rate": 1.942895959539939e-06,
"loss": 0.0554,
"step": 96
},
{
"epoch": 9.7,
"grad_norm": 0.5623133765815935,
"learning_rate": 1.8377731220231144e-06,
"loss": 0.0474,
"step": 97
},
{
"epoch": 9.8,
"grad_norm": 0.424264822350842,
"learning_rate": 1.7349300750820758e-06,
"loss": 0.0283,
"step": 98
},
{
"epoch": 9.9,
"grad_norm": 0.5976358690027289,
"learning_rate": 1.6344409628621482e-06,
"loss": 0.049,
"step": 99
},
{
"epoch": 10.0,
"grad_norm": 0.45353232830921913,
"learning_rate": 1.5363782324520033e-06,
"loss": 0.042,
"step": 100
},
{
"epoch": 10.1,
"grad_norm": 0.349198657083718,
"learning_rate": 1.4408125816532981e-06,
"loss": 0.0422,
"step": 101
},
{
"epoch": 10.2,
"grad_norm": 0.35448805560228613,
"learning_rate": 1.347812908011485e-06,
"loss": 0.0388,
"step": 102
},
{
"epoch": 10.3,
"grad_norm": 0.32631277707661516,
"learning_rate": 1.257446259144494e-06,
"loss": 0.0387,
"step": 103
},
{
"epoch": 10.4,
"grad_norm": 0.35301449862172507,
"learning_rate": 1.1697777844051105e-06,
"loss": 0.0311,
"step": 104
},
{
"epoch": 10.5,
"grad_norm": 0.3240516942726898,
"learning_rate": 1.0848706879118893e-06,
"loss": 0.0248,
"step": 105
},
{
"epoch": 10.6,
"grad_norm": 0.33973718166980815,
"learning_rate": 1.0027861829824953e-06,
"loss": 0.0386,
"step": 106
},
{
"epoch": 10.7,
"grad_norm": 0.2868406661095396,
"learning_rate": 9.235834480022788e-07,
"loss": 0.0255,
"step": 107
},
{
"epoch": 10.8,
"grad_norm": 0.3211679065492814,
"learning_rate": 8.473195837599419e-07,
"loss": 0.033,
"step": 108
},
{
"epoch": 10.9,
"grad_norm": 0.33495759526983737,
"learning_rate": 7.740495722810271e-07,
"loss": 0.0391,
"step": 109
},
{
"epoch": 11.0,
"grad_norm": 0.4008588181719736,
"learning_rate": 7.03826237188916e-07,
"loss": 0.0397,
"step": 110
},
{
"epoch": 11.1,
"grad_norm": 0.3111647369519002,
"learning_rate": 6.367002056219285e-07,
"loss": 0.0388,
"step": 111
},
{
"epoch": 11.2,
"grad_norm": 0.271491728379142,
"learning_rate": 5.727198717339511e-07,
"loss": 0.0243,
"step": 112
},
{
"epoch": 11.3,
"grad_norm": 0.2686985574786467,
"learning_rate": 5.119313618049309e-07,
"loss": 0.028,
"step": 113
},
{
"epoch": 11.4,
"grad_norm": 0.22737131467374813,
"learning_rate": 4.54378500986381e-07,
"loss": 0.0171,
"step": 114
},
{
"epoch": 11.5,
"grad_norm": 0.2639800951995699,
"learning_rate": 4.001027817058789e-07,
"loss": 0.0254,
"step": 115
},
{
"epoch": 11.6,
"grad_norm": 0.30444222862800524,
"learning_rate": 3.49143333753309e-07,
"loss": 0.026,
"step": 116
},
{
"epoch": 11.7,
"grad_norm": 0.2878808572147184,
"learning_rate": 3.015368960704584e-07,
"loss": 0.0318,
"step": 117
},
{
"epoch": 11.8,
"grad_norm": 0.32649526275654867,
"learning_rate": 2.573177902642726e-07,
"loss": 0.0408,
"step": 118
},
{
"epoch": 11.9,
"grad_norm": 0.2950295402871519,
"learning_rate": 2.1651789586287442e-07,
"loss": 0.0328,
"step": 119
},
{
"epoch": 12.0,
"grad_norm": 0.33114385101591637,
"learning_rate": 1.7916662733218848e-07,
"loss": 0.0332,
"step": 120
},
{
"epoch": 12.1,
"grad_norm": 0.25771679525162605,
"learning_rate": 1.4529091286973994e-07,
"loss": 0.0214,
"step": 121
},
{
"epoch": 12.2,
"grad_norm": 0.2370890325426454,
"learning_rate": 1.1491517499091498e-07,
"loss": 0.0221,
"step": 122
},
{
"epoch": 12.3,
"grad_norm": 0.291038994793003,
"learning_rate": 8.80613129216762e-08,
"loss": 0.0412,
"step": 123
},
{
"epoch": 12.4,
"grad_norm": 0.23588084084748412,
"learning_rate": 6.474868681043578e-08,
"loss": 0.0209,
"step": 124
},
{
"epoch": 12.5,
"grad_norm": 0.26151697168589666,
"learning_rate": 4.499410377045765e-08,
"loss": 0.0286,
"step": 125
},
{
"epoch": 12.6,
"grad_norm": 0.2984386009069585,
"learning_rate": 2.8811805762860578e-08,
"loss": 0.0372,
"step": 126
},
{
"epoch": 12.7,
"grad_norm": 0.3087679043979653,
"learning_rate": 1.6213459328950355e-08,
"loss": 0.0365,
"step": 127
},
{
"epoch": 12.8,
"grad_norm": 0.2869494275539929,
"learning_rate": 7.2081471792911914e-09,
"loss": 0.0392,
"step": 128
},
{
"epoch": 12.9,
"grad_norm": 0.23149536322103795,
"learning_rate": 1.8023616455731253e-09,
"loss": 0.0231,
"step": 129
},
{
"epoch": 13.0,
"grad_norm": 0.7477746490679082,
"learning_rate": 0.0,
"loss": 0.0144,
"step": 130
},
{
"epoch": 13.0,
"step": 130,
"total_flos": 3.6012573467869184e+16,
"train_loss": 0.3063949236073173,
"train_runtime": 1388.6914,
"train_samples_per_second": 2.958,
"train_steps_per_second": 0.094
}
],
"logging_steps": 1,
"max_steps": 130,
"num_input_tokens_seen": 0,
"num_train_epochs": 13,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.6012573467869184e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}