Files
llama3-8b-full-sft-c4-1m-en-v2/trainer_state.json

6617 lines
160 KiB
JSON
Raw Normal View History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 939,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0032,
"grad_norm": 30.96875150445469,
"learning_rate": 0.0,
"loss": 1.8349742889404297,
"step": 1
},
{
"epoch": 0.0064,
"grad_norm": 34.95019581450876,
"learning_rate": 1.0638297872340426e-07,
"loss": 2.0016040802001953,
"step": 2
},
{
"epoch": 0.0096,
"grad_norm": 32.45279398076596,
"learning_rate": 2.1276595744680852e-07,
"loss": 1.4195575714111328,
"step": 3
},
{
"epoch": 0.0128,
"grad_norm": 32.80607912486261,
"learning_rate": 3.1914893617021275e-07,
"loss": 1.83726167678833,
"step": 4
},
{
"epoch": 0.016,
"grad_norm": 36.86296058029906,
"learning_rate": 4.2553191489361704e-07,
"loss": 1.8575166463851929,
"step": 5
},
{
"epoch": 0.0192,
"grad_norm": 32.61625329865889,
"learning_rate": 5.319148936170213e-07,
"loss": 2.033665895462036,
"step": 6
},
{
"epoch": 0.0224,
"grad_norm": 34.426697968740584,
"learning_rate": 6.382978723404255e-07,
"loss": 1.5992650985717773,
"step": 7
},
{
"epoch": 0.0256,
"grad_norm": 36.23664039546045,
"learning_rate": 7.446808510638298e-07,
"loss": 1.830265998840332,
"step": 8
},
{
"epoch": 0.0288,
"grad_norm": 33.21757257282207,
"learning_rate": 8.510638297872341e-07,
"loss": 1.7864813804626465,
"step": 9
},
{
"epoch": 0.032,
"grad_norm": 34.5991653097688,
"learning_rate": 9.574468085106384e-07,
"loss": 1.9527478218078613,
"step": 10
},
{
"epoch": 0.0352,
"grad_norm": 29.008360920775424,
"learning_rate": 1.0638297872340427e-06,
"loss": 1.68494713306427,
"step": 11
},
{
"epoch": 0.0384,
"grad_norm": 34.538707651820694,
"learning_rate": 1.170212765957447e-06,
"loss": 1.7542328834533691,
"step": 12
},
{
"epoch": 0.0416,
"grad_norm": 21.7487137271236,
"learning_rate": 1.276595744680851e-06,
"loss": 1.6859506368637085,
"step": 13
},
{
"epoch": 0.0448,
"grad_norm": 21.078691821583366,
"learning_rate": 1.3829787234042555e-06,
"loss": 1.4219917058944702,
"step": 14
},
{
"epoch": 0.048,
"grad_norm": 26.93301061418375,
"learning_rate": 1.4893617021276596e-06,
"loss": 1.9395288228988647,
"step": 15
},
{
"epoch": 0.0512,
"grad_norm": 22.121624461328494,
"learning_rate": 1.595744680851064e-06,
"loss": 1.6113699674606323,
"step": 16
},
{
"epoch": 0.0544,
"grad_norm": 18.897886549324493,
"learning_rate": 1.7021276595744682e-06,
"loss": 1.7385358810424805,
"step": 17
},
{
"epoch": 0.0576,
"grad_norm": 22.03871877789075,
"learning_rate": 1.8085106382978727e-06,
"loss": 1.8294150829315186,
"step": 18
},
{
"epoch": 0.0608,
"grad_norm": 15.406834573321145,
"learning_rate": 1.9148936170212767e-06,
"loss": 1.7034738063812256,
"step": 19
},
{
"epoch": 0.064,
"grad_norm": 18.373204800193015,
"learning_rate": 2.021276595744681e-06,
"loss": 1.6598455905914307,
"step": 20
},
{
"epoch": 0.0672,
"grad_norm": 19.592535448012214,
"learning_rate": 2.1276595744680853e-06,
"loss": 1.3032071590423584,
"step": 21
},
{
"epoch": 0.0704,
"grad_norm": 13.495246124339976,
"learning_rate": 2.2340425531914894e-06,
"loss": 1.6954210996627808,
"step": 22
},
{
"epoch": 0.0736,
"grad_norm": 12.970591363414057,
"learning_rate": 2.340425531914894e-06,
"loss": 1.5859076976776123,
"step": 23
},
{
"epoch": 0.0768,
"grad_norm": 11.06105741263378,
"learning_rate": 2.446808510638298e-06,
"loss": 1.2175744771957397,
"step": 24
},
{
"epoch": 0.08,
"grad_norm": 11.844253708019131,
"learning_rate": 2.553191489361702e-06,
"loss": 1.4733150005340576,
"step": 25
},
{
"epoch": 0.0832,
"grad_norm": 10.35129504094599,
"learning_rate": 2.6595744680851065e-06,
"loss": 1.3996121883392334,
"step": 26
},
{
"epoch": 0.0864,
"grad_norm": 6.985786531088317,
"learning_rate": 2.765957446808511e-06,
"loss": 0.7041330337524414,
"step": 27
},
{
"epoch": 0.0896,
"grad_norm": 10.843669233693165,
"learning_rate": 2.8723404255319155e-06,
"loss": 1.3123451471328735,
"step": 28
},
{
"epoch": 0.0928,
"grad_norm": 14.51074241907493,
"learning_rate": 2.978723404255319e-06,
"loss": 1.4157214164733887,
"step": 29
},
{
"epoch": 0.096,
"grad_norm": 9.069063206364158,
"learning_rate": 3.0851063829787237e-06,
"loss": 1.3999661207199097,
"step": 30
},
{
"epoch": 0.0992,
"grad_norm": 10.79465351317264,
"learning_rate": 3.191489361702128e-06,
"loss": 1.1525228023529053,
"step": 31
},
{
"epoch": 0.1024,
"grad_norm": 7.77759608671091,
"learning_rate": 3.297872340425532e-06,
"loss": 1.0802254676818848,
"step": 32
},
{
"epoch": 0.1056,
"grad_norm": 7.236947074794681,
"learning_rate": 3.4042553191489363e-06,
"loss": 1.2458343505859375,
"step": 33
},
{
"epoch": 0.1088,
"grad_norm": 8.556093385252257,
"learning_rate": 3.510638297872341e-06,
"loss": 1.1014039516448975,
"step": 34
},
{
"epoch": 0.112,
"grad_norm": 8.88523637866704,
"learning_rate": 3.6170212765957453e-06,
"loss": 1.4348636865615845,
"step": 35
},
{
"epoch": 0.1152,
"grad_norm": 12.187559987922132,
"learning_rate": 3.723404255319149e-06,
"loss": 1.279908537864685,
"step": 36
},
{
"epoch": 0.1184,
"grad_norm": 9.386079656794308,
"learning_rate": 3.8297872340425535e-06,
"loss": 1.2550249099731445,
"step": 37
},
{
"epoch": 0.1216,
"grad_norm": 10.237297417039766,
"learning_rate": 3.936170212765958e-06,
"loss": 1.3033971786499023,
"step": 38
},
{
"epoch": 0.1248,
"grad_norm": 10.180050386372764,
"learning_rate": 4.042553191489362e-06,
"loss": 1.2937856912612915,
"step": 39
},
{
"epoch": 0.128,
"grad_norm": 8.993124480573385,
"learning_rate": 4.148936170212766e-06,
"loss": 1.2794173955917358,
"step": 40
},
{
"epoch": 0.1312,
"grad_norm": 8.197974292027313,
"learning_rate": 4.255319148936171e-06,
"loss": 1.3401811122894287,
"step": 41
},
{
"epoch": 0.1344,
"grad_norm": 9.581134774245738,
"learning_rate": 4.361702127659575e-06,
"loss": 1.4371700286865234,
"step": 42
},
{
"epoch": 0.1376,
"grad_norm": 9.638042206927206,
"learning_rate": 4.468085106382979e-06,
"loss": 1.2635990381240845,
"step": 43
},
{
"epoch": 0.1408,
"grad_norm": 7.796666702565968,
"learning_rate": 4.574468085106383e-06,
"loss": 1.2196773290634155,
"step": 44
},
{
"epoch": 0.144,
"grad_norm": 10.426027552051274,
"learning_rate": 4.680851063829788e-06,
"loss": 1.162177562713623,
"step": 45
},
{
"epoch": 0.1472,
"grad_norm": 7.247222462163813,
"learning_rate": 4.787234042553192e-06,
"loss": 1.0528342723846436,
"step": 46
},
{
"epoch": 0.1504,
"grad_norm": 9.465099894062243,
"learning_rate": 4.893617021276596e-06,
"loss": 1.5967459678649902,
"step": 47
},
{
"epoch": 0.1536,
"grad_norm": 7.550984062777398,
"learning_rate": 5e-06,
"loss": 1.2654751539230347,
"step": 48
},
{
"epoch": 0.1568,
"grad_norm": 10.76023862618631,
"learning_rate": 5.106382978723404e-06,
"loss": 1.2069895267486572,
"step": 49
},
{
"epoch": 0.16,
"grad_norm": 9.136516250945109,
"learning_rate": 5.212765957446809e-06,
"loss": 1.2848241329193115,
"step": 50
},
{
"epoch": 0.1632,
"grad_norm": 10.301776121316426,
"learning_rate": 5.319148936170213e-06,
"loss": 1.2709619998931885,
"step": 51
},
{
"epoch": 0.1664,
"grad_norm": 7.542443832554114,
"learning_rate": 5.425531914893617e-06,
"loss": 1.535873532295227,
"step": 52
},
{
"epoch": 0.1696,
"grad_norm": 7.590712819179057,
"learning_rate": 5.531914893617022e-06,
"loss": 1.1793067455291748,
"step": 53
},
{
"epoch": 0.1728,
"grad_norm": 8.189202743606653,
"learning_rate": 5.638297872340426e-06,
"loss": 1.390581727027893,
"step": 54
},
{
"epoch": 0.176,
"grad_norm": 8.758692219332021,
"learning_rate": 5.744680851063831e-06,
"loss": 1.604058027267456,
"step": 55
},
{
"epoch": 0.1792,
"grad_norm": 7.34525972239494,
"learning_rate": 5.851063829787235e-06,
"loss": 1.3224234580993652,
"step": 56
},
{
"epoch": 0.1824,
"grad_norm": 9.347814779490452,
"learning_rate": 5.957446808510638e-06,
"loss": 1.272003173828125,
"step": 57
},
{
"epoch": 0.1856,
"grad_norm": 8.367564401249584,
"learning_rate": 6.063829787234044e-06,
"loss": 1.2350473403930664,
"step": 58
},
{
"epoch": 0.1888,
"grad_norm": 8.010485046273208,
"learning_rate": 6.170212765957447e-06,
"loss": 1.37330162525177,
"step": 59
},
{
"epoch": 0.192,
"grad_norm": 9.937514811635035,
"learning_rate": 6.276595744680851e-06,
"loss": 1.0028364658355713,
"step": 60
},
{
"epoch": 0.1952,
"grad_norm": 7.960093556304971,
"learning_rate": 6.382978723404256e-06,
"loss": 1.1944432258605957,
"step": 61
},
{
"epoch": 0.1984,
"grad_norm": 6.776583763386315,
"learning_rate": 6.48936170212766e-06,
"loss": 1.267136573791504,
"step": 62
},
{
"epoch": 0.2016,
"grad_norm": 11.136111311029287,
"learning_rate": 6.595744680851064e-06,
"loss": 1.4628270864486694,
"step": 63
},
{
"epoch": 0.2048,
"grad_norm": 9.435199406382802,
"learning_rate": 6.702127659574469e-06,
"loss": 1.1075782775878906,
"step": 64
},
{
"epoch": 0.208,
"grad_norm": 10.286519037221874,
"learning_rate": 6.808510638297873e-06,
"loss": 1.2595106363296509,
"step": 65
},
{
"epoch": 0.2112,
"grad_norm": 9.620595259881748,
"learning_rate": 6.914893617021278e-06,
"loss": 1.3000699281692505,
"step": 66
},
{
"epoch": 0.2144,
"grad_norm": 7.536926343903873,
"learning_rate": 7.021276595744682e-06,
"loss": 1.3746538162231445,
"step": 67
},
{
"epoch": 0.2176,
"grad_norm": 8.731908589039898,
"learning_rate": 7.127659574468085e-06,
"loss": 1.3396170139312744,
"step": 68
},
{
"epoch": 0.2208,
"grad_norm": 7.854135252040015,
"learning_rate": 7.234042553191491e-06,
"loss": 1.073827862739563,
"step": 69
},
{
"epoch": 0.224,
"grad_norm": 7.733710817679651,
"learning_rate": 7.340425531914894e-06,
"loss": 0.9759301543235779,
"step": 70
},
{
"epoch": 0.2272,
"grad_norm": 7.909330011436939,
"learning_rate": 7.446808510638298e-06,
"loss": 1.3497977256774902,
"step": 71
},
{
"epoch": 0.2304,
"grad_norm": 11.78949760266287,
"learning_rate": 7.553191489361703e-06,
"loss": 1.1876658201217651,
"step": 72
},
{
"epoch": 0.2336,
"grad_norm": 8.298838056537683,
"learning_rate": 7.659574468085107e-06,
"loss": 1.2548987865447998,
"step": 73
},
{
"epoch": 0.2368,
"grad_norm": 9.125944026168344,
"learning_rate": 7.765957446808511e-06,
"loss": 1.4559820890426636,
"step": 74
},
{
"epoch": 0.24,
"grad_norm": 11.624278478953103,
"learning_rate": 7.872340425531916e-06,
"loss": 1.6806881427764893,
"step": 75
},
{
"epoch": 0.2432,
"grad_norm": 6.9038083151156515,
"learning_rate": 7.97872340425532e-06,
"loss": 1.1877515316009521,
"step": 76
},
{
"epoch": 0.2464,
"grad_norm": 7.823547542303503,
"learning_rate": 8.085106382978723e-06,
"loss": 1.4321260452270508,
"step": 77
},
{
"epoch": 0.2496,
"grad_norm": 9.02972627426372,
"learning_rate": 8.191489361702128e-06,
"loss": 1.2051981687545776,
"step": 78
},
{
"epoch": 0.2528,
"grad_norm": 9.327692687220065,
"learning_rate": 8.297872340425532e-06,
"loss": 1.159995198249817,
"step": 79
},
{
"epoch": 0.256,
"grad_norm": 8.372816951097537,
"learning_rate": 8.404255319148937e-06,
"loss": 1.3725446462631226,
"step": 80
},
{
"epoch": 0.2592,
"grad_norm": 8.08166498508954,
"learning_rate": 8.510638297872341e-06,
"loss": 1.5179659128189087,
"step": 81
},
{
"epoch": 0.2624,
"grad_norm": 7.799489940965433,
"learning_rate": 8.617021276595746e-06,
"loss": 1.437788963317871,
"step": 82
},
{
"epoch": 0.2656,
"grad_norm": 11.248863381595092,
"learning_rate": 8.72340425531915e-06,
"loss": 1.1491832733154297,
"step": 83
},
{
"epoch": 0.2688,
"grad_norm": 7.10583697775692,
"learning_rate": 8.829787234042555e-06,
"loss": 1.0702165365219116,
"step": 84
},
{
"epoch": 0.272,
"grad_norm": 9.473667376587484,
"learning_rate": 8.936170212765958e-06,
"loss": 1.389183521270752,
"step": 85
},
{
"epoch": 0.2752,
"grad_norm": 7.012139508655576,
"learning_rate": 9.042553191489362e-06,
"loss": 1.2944904565811157,
"step": 86
},
{
"epoch": 0.2784,
"grad_norm": 8.347943103318496,
"learning_rate": 9.148936170212767e-06,
"loss": 1.2050387859344482,
"step": 87
},
{
"epoch": 0.2816,
"grad_norm": 8.551639933185136,
"learning_rate": 9.255319148936171e-06,
"loss": 1.1384426355361938,
"step": 88
},
{
"epoch": 0.2848,
"grad_norm": 8.912024381596014,
"learning_rate": 9.361702127659576e-06,
"loss": 1.436863660812378,
"step": 89
},
{
"epoch": 0.288,
"grad_norm": 8.31416368360688,
"learning_rate": 9.46808510638298e-06,
"loss": 1.2077499628067017,
"step": 90
},
{
"epoch": 0.2912,
"grad_norm": 9.91164603240442,
"learning_rate": 9.574468085106385e-06,
"loss": 1.1718724966049194,
"step": 91
},
{
"epoch": 0.2944,
"grad_norm": 11.956056504029057,
"learning_rate": 9.680851063829787e-06,
"loss": 1.2550005912780762,
"step": 92
},
{
"epoch": 0.2976,
"grad_norm": 9.357707936070234,
"learning_rate": 9.787234042553192e-06,
"loss": 1.6930280923843384,
"step": 93
},
{
"epoch": 0.3008,
"grad_norm": 7.901106221576849,
"learning_rate": 9.893617021276596e-06,
"loss": 1.2924106121063232,
"step": 94
},
{
"epoch": 0.304,
"grad_norm": 9.334720179751995,
"learning_rate": 1e-05,
"loss": 1.4082775115966797,
"step": 95
},
{
"epoch": 0.3072,
"grad_norm": 7.535092364165803,
"learning_rate": 9.999965443811378e-06,
"loss": 1.2915349006652832,
"step": 96
},
{
"epoch": 0.3104,
"grad_norm": 8.263475834935997,
"learning_rate": 9.999861775723162e-06,
"loss": 1.3475099802017212,
"step": 97
},
{
"epoch": 0.3136,
"grad_norm": 7.648559636952261,
"learning_rate": 9.999688997168301e-06,
"loss": 1.049058437347412,
"step": 98
},
{
"epoch": 0.3168,
"grad_norm": 7.5409703446829095,
"learning_rate": 9.999447110535026e-06,
"loss": 1.1638190746307373,
"step": 99
},
{
"epoch": 0.32,
"grad_norm": 7.31326945050447,
"learning_rate": 9.999136119166803e-06,
"loss": 1.2690186500549316,
"step": 100
},
{
"epoch": 0.3232,
"grad_norm": 7.371374382103116,
"learning_rate": 9.998756027362308e-06,
"loss": 1.271148681640625,
"step": 101
},
{
"epoch": 0.3264,
"grad_norm": 8.432395320064106,
"learning_rate": 9.99830684037535e-06,
"loss": 1.1501715183258057,
"step": 102
},
{
"epoch": 0.3296,
"grad_norm": 8.617624539965131,
"learning_rate": 9.9977885644148e-06,
"loss": 1.3156936168670654,
"step": 103
},
{
"epoch": 0.3328,
"grad_norm": 8.600550715469133,
"learning_rate": 9.997201206644522e-06,
"loss": 1.4087587594985962,
"step": 104
},
{
"epoch": 0.336,
"grad_norm": 8.010539885033761,
"learning_rate": 9.99654477518325e-06,
"loss": 1.3723515272140503,
"step": 105
},
{
"epoch": 0.3392,
"grad_norm": 10.015355986402822,
"learning_rate": 9.995819279104494e-06,
"loss": 1.437239408493042,
"step": 106
},
{
"epoch": 0.3424,
"grad_norm": 7.7487706895929485,
"learning_rate": 9.995024728436402e-06,
"loss": 1.434226155281067,
"step": 107
},
{
"epoch": 0.3456,
"grad_norm": 9.117544182516218,
"learning_rate": 9.994161134161635e-06,
"loss": 1.3603150844573975,
"step": 108
},
{
"epoch": 0.3488,
"grad_norm": 6.788867107690524,
"learning_rate": 9.993228508217201e-06,
"loss": 1.267934799194336,
"step": 109
},
{
"epoch": 0.352,
"grad_norm": 9.669438898873976,
"learning_rate": 9.9922268634943e-06,
"loss": 1.168867826461792,
"step": 110
},
{
"epoch": 0.3552,
"grad_norm": 13.689594861211107,
"learning_rate": 9.991156213838143e-06,
"loss": 1.2784748077392578,
"step": 111
},
{
"epoch": 0.3584,
"grad_norm": 7.943483018618271,
"learning_rate": 9.990016574047757e-06,
"loss": 1.2634623050689697,
"step": 112
},
{
"epoch": 0.3616,
"grad_norm": 8.468543469548031,
"learning_rate": 9.988807959875785e-06,
"loss": 1.6450899839401245,
"step": 113
},
{
"epoch": 0.3648,
"grad_norm": 6.588375130584607,
"learning_rate": 9.987530388028269e-06,
"loss": 0.9087746739387512,
"step": 114
},
{
"epoch": 0.368,
"grad_norm": 9.836251002577367,
"learning_rate": 9.986183876164412e-06,
"loss": 1.0217828750610352,
"step": 115
},
{
"epoch": 0.3712,
"grad_norm": 9.643715235954506,
"learning_rate": 9.984768442896342e-06,
"loss": 1.262690544128418,
"step": 116
},
{
"epoch": 0.3744,
"grad_norm": 10.040279374863353,
"learning_rate": 9.983284107788852e-06,
"loss": 1.2868056297302246,
"step": 117
},
{
"epoch": 0.3776,
"grad_norm": 8.035896469127108,
"learning_rate": 9.981730891359123e-06,
"loss": 1.4883698225021362,
"step": 118
},
{
"epoch": 0.3808,
"grad_norm": 8.292927585211592,
"learning_rate": 9.980108815076456e-06,
"loss": 1.6060783863067627,
"step": 119
},
{
"epoch": 0.384,
"grad_norm": 8.360485993283595,
"learning_rate": 9.978417901361958e-06,
"loss": 1.423858880996704,
"step": 120
},
{
"epoch": 0.3872,
"grad_norm": 7.251543226190821,
"learning_rate": 9.976658173588244e-06,
"loss": 1.3574882745742798,
"step": 121
},
{
"epoch": 0.3904,
"grad_norm": 8.39919425687285,
"learning_rate": 9.974829656079106e-06,
"loss": 1.1160762310028076,
"step": 122
},
{
"epoch": 0.3936,
"grad_norm": 6.86268366822002,
"learning_rate": 9.972932374109184e-06,
"loss": 1.3323800563812256,
"step": 123
},
{
"epoch": 0.3968,
"grad_norm": 9.079755548651608,
"learning_rate": 9.97096635390361e-06,
"loss": 1.388983130455017,
"step": 124
},
{
"epoch": 0.4,
"grad_norm": 8.320616663121625,
"learning_rate": 9.968931622637652e-06,
"loss": 1.467790126800537,
"step": 125
},
{
"epoch": 0.4032,
"grad_norm": 11.534992416476264,
"learning_rate": 9.966828208436332e-06,
"loss": 1.3372962474822998,
"step": 126
},
{
"epoch": 0.4064,
"grad_norm": 9.611003780885763,
"learning_rate": 9.96465614037404e-06,
"loss": 1.5618739128112793,
"step": 127
},
{
"epoch": 0.4096,
"grad_norm": 8.217835669877172,
"learning_rate": 9.962415448474134e-06,
"loss": 1.574603796005249,
"step": 128
},
{
"epoch": 0.4128,
"grad_norm": 10.226792927619416,
"learning_rate": 9.960106163708522e-06,
"loss": 1.2998956441879272,
"step": 129
},
{
"epoch": 0.416,
"grad_norm": 9.007862705746613,
"learning_rate": 9.95772831799724e-06,
"loss": 1.226587176322937,
"step": 130
},
{
"epoch": 0.4192,
"grad_norm": 9.323562095808699,
"learning_rate": 9.955281944207998e-06,
"loss": 1.5016090869903564,
"step": 131
},
{
"epoch": 0.4224,
"grad_norm": 9.032461366830766,
"learning_rate": 9.95276707615574e-06,
"loss": 1.3798859119415283,
"step": 132
},
{
"epoch": 0.4256,
"grad_norm": 9.535209655464094,
"learning_rate": 9.950183748602164e-06,
"loss": 1.4370064735412598,
"step": 133
},
{
"epoch": 0.4288,
"grad_norm": 7.37580804624013,
"learning_rate": 9.947531997255256e-06,
"loss": 1.5972474813461304,
"step": 134
},
{
"epoch": 0.432,
"grad_norm": 8.601914118029566,
"learning_rate": 9.944811858768782e-06,
"loss": 1.2247103452682495,
"step": 135
},
{
"epoch": 0.4352,
"grad_norm": 8.00148882827197,
"learning_rate": 9.94202337074179e-06,
"loss": 1.3642845153808594,
"step": 136
},
{
"epoch": 0.4384,
"grad_norm": 10.331198505072173,
"learning_rate": 9.939166571718086e-06,
"loss": 1.3845267295837402,
"step": 137
},
{
"epoch": 0.4416,
"grad_norm": 6.955091267740038,
"learning_rate": 9.936241501185706e-06,
"loss": 1.3615238666534424,
"step": 138
},
{
"epoch": 0.4448,
"grad_norm": 8.57723687785519,
"learning_rate": 9.933248199576366e-06,
"loss": 1.6141746044158936,
"step": 139
},
{
"epoch": 0.448,
"grad_norm": 10.089526067211054,
"learning_rate": 9.930186708264902e-06,
"loss": 1.359433650970459,
"step": 140
},
{
"epoch": 0.4512,
"grad_norm": 6.783706799602165,
"learning_rate": 9.927057069568704e-06,
"loss": 1.4856258630752563,
"step": 141
},
{
"epoch": 0.4544,
"grad_norm": 7.799697591642719,
"learning_rate": 9.923859326747125e-06,
"loss": 1.1757385730743408,
"step": 142
},
{
"epoch": 0.4576,
"grad_norm": 9.03252291305227,
"learning_rate": 9.920593524000887e-06,
"loss": 1.4313726425170898,
"step": 143
},
{
"epoch": 0.4608,
"grad_norm": 9.065244876878161,
"learning_rate": 9.917259706471469e-06,
"loss": 1.1987106800079346,
"step": 144
},
{
"epoch": 0.464,
"grad_norm": 8.170331975982476,
"learning_rate": 9.913857920240481e-06,
"loss": 1.3925058841705322,
"step": 145
},
{
"epoch": 0.4672,
"grad_norm": 8.674441658597983,
"learning_rate": 9.91038821232903e-06,
"loss": 1.154026746749878,
"step": 146
},
{
"epoch": 0.4704,
"grad_norm": 8.017930051145642,
"learning_rate": 9.906850630697068e-06,
"loss": 1.4966177940368652,
"step": 147
},
{
"epoch": 0.4736,
"grad_norm": 7.116286207941994,
"learning_rate": 9.903245224242732e-06,
"loss": 1.4258092641830444,
"step": 148
},
{
"epoch": 0.4768,
"grad_norm": 8.897001777117357,
"learning_rate": 9.899572042801662e-06,
"loss": 1.0794379711151123,
"step": 149
},
{
"epoch": 0.48,
"grad_norm": 8.094499313219195,
"learning_rate": 9.895831137146319e-06,
"loss": 1.6029235124588013,
"step": 150
},
{
"epoch": 0.4832,
"grad_norm": 7.894503427411005,
"learning_rate": 9.89202255898528e-06,
"loss": 1.298710823059082,
"step": 151
},
{
"epoch": 0.4864,
"grad_norm": 6.9424091786582425,
"learning_rate": 9.888146360962523e-06,
"loss": 1.2579549551010132,
"step": 152
},
{
"epoch": 0.4896,
"grad_norm": 7.789551735514812,
"learning_rate": 9.8842025966567e-06,
"loss": 1.2674002647399902,
"step": 153
},
{
"epoch": 0.4928,
"grad_norm": 7.449801727346905,
"learning_rate": 9.880191320580396e-06,
"loss": 1.0756787061691284,
"step": 154
},
{
"epoch": 0.496,
"grad_norm": 8.976478984694314,
"learning_rate": 9.876112588179378e-06,
"loss": 1.3505208492279053,
"step": 155
},
{
"epoch": 0.4992,
"grad_norm": 7.628207774924687,
"learning_rate": 9.87196645583182e-06,
"loss": 1.548148512840271,
"step": 156
},
{
"epoch": 0.5024,
"grad_norm": 8.159214519700773,
"learning_rate": 9.86775298084754e-06,
"loss": 1.2795175313949585,
"step": 157
},
{
"epoch": 0.5056,
"grad_norm": 10.401589042976578,
"learning_rate": 9.863472221467189e-06,
"loss": 1.32072114944458,
"step": 158
},
{
"epoch": 0.5088,
"grad_norm": 7.342627377858892,
"learning_rate": 9.85912423686146e-06,
"loss": 1.2856944799423218,
"step": 159
},
{
"epoch": 0.512,
"grad_norm": 9.802720039801498,
"learning_rate": 9.854709087130261e-06,
"loss": 1.2735116481781006,
"step": 160
},
{
"epoch": 0.5152,
"grad_norm": 9.012158159809712,
"learning_rate": 9.850226833301893e-06,
"loss": 1.3676214218139648,
"step": 161
},
{
"epoch": 0.5184,
"grad_norm": 9.504718702805361,
"learning_rate": 9.8456775373322e-06,
"loss": 1.3856254816055298,
"step": 162
},
{
"epoch": 0.5216,
"grad_norm": 9.520254954936085,
"learning_rate": 9.841061262103713e-06,
"loss": 1.3689014911651611,
"step": 163
},
{
"epoch": 0.5248,
"grad_norm": 8.992355401926835,
"learning_rate": 9.836378071424782e-06,
"loss": 1.1833181381225586,
"step": 164
},
{
"epoch": 0.528,
"grad_norm": 11.527699125349812,
"learning_rate": 9.831628030028698e-06,
"loss": 1.4919489622116089,
"step": 165
},
{
"epoch": 0.5312,
"grad_norm": 10.0230724132307,
"learning_rate": 9.826811203572785e-06,
"loss": 1.4446158409118652,
"step": 166
},
{
"epoch": 0.5344,
"grad_norm": 9.791234363205684,
"learning_rate": 9.821927658637518e-06,
"loss": 1.2425103187561035,
"step": 167
},
{
"epoch": 0.5376,
"grad_norm": 9.5128469859557,
"learning_rate": 9.81697746272557e-06,
"loss": 1.3857293128967285,
"step": 168
},
{
"epoch": 0.5408,
"grad_norm": 8.752661437595991,
"learning_rate": 9.811960684260907e-06,
"loss": 1.6042490005493164,
"step": 169
},
{
"epoch": 0.544,
"grad_norm": 8.09952625313001,
"learning_rate": 9.80687739258782e-06,
"loss": 1.2307994365692139,
"step": 170
},
{
"epoch": 0.5472,
"grad_norm": 7.536038343565144,
"learning_rate": 9.801727657969988e-06,
"loss": 1.6148277521133423,
"step": 171
},
{
"epoch": 0.5504,
"grad_norm": 9.419412970594843,
"learning_rate": 9.796511551589492e-06,
"loss": 1.626853585243225,
"step": 172
},
{
"epoch": 0.5536,
"grad_norm": 8.279075558536261,
"learning_rate": 9.791229145545832e-06,
"loss": 1.462764024734497,
"step": 173
},
{
"epoch": 0.5568,
"grad_norm": 8.195905208534509,
"learning_rate": 9.785880512854937e-06,
"loss": 1.3920596837997437,
"step": 174
},
{
"epoch": 0.56,
"grad_norm": 8.065511167834286,
"learning_rate": 9.78046572744815e-06,
"loss": 1.4325257539749146,
"step": 175
},
{
"epoch": 0.5632,
"grad_norm": 11.280239877491145,
"learning_rate": 9.77498486417121e-06,
"loss": 1.3757168054580688,
"step": 176
},
{
"epoch": 0.5664,
"grad_norm": 8.55752203763051,
"learning_rate": 9.769437998783216e-06,
"loss": 1.272997260093689,
"step": 177
},
{
"epoch": 0.5696,
"grad_norm": 6.664372135897697,
"learning_rate": 9.763825207955577e-06,
"loss": 1.4110825061798096,
"step": 178
},
{
"epoch": 0.5728,
"grad_norm": 6.528368357810476,
"learning_rate": 9.758146569270957e-06,
"loss": 1.3816301822662354,
"step": 179
},
{
"epoch": 0.576,
"grad_norm": 9.428555967314438,
"learning_rate": 9.7524021612222e-06,
"loss": 1.3761601448059082,
"step": 180
},
{
"epoch": 0.5792,
"grad_norm": 7.99527003460233,
"learning_rate": 9.746592063211247e-06,
"loss": 1.4292595386505127,
"step": 181
},
{
"epoch": 0.5824,
"grad_norm": 8.041390813612201,
"learning_rate": 9.74071635554803e-06,
"loss": 1.4273180961608887,
"step": 182
},
{
"epoch": 0.5856,
"grad_norm": 8.124552819493383,
"learning_rate": 9.73477511944938e-06,
"loss": 1.6726312637329102,
"step": 183
},
{
"epoch": 0.5888,
"grad_norm": 9.23429333066722,
"learning_rate": 9.728768437037882e-06,
"loss": 1.2996139526367188,
"step": 184
},
{
"epoch": 0.592,
"grad_norm": 7.5626447521114635,
"learning_rate": 9.722696391340762e-06,
"loss": 1.4366767406463623,
"step": 185
},
{
"epoch": 0.5952,
"grad_norm": 7.737574074357637,
"learning_rate": 9.716559066288716e-06,
"loss": 1.6778459548950195,
"step": 186
},
{
"epoch": 0.5984,
"grad_norm": 7.580211458049055,
"learning_rate": 9.710356546714774e-06,
"loss": 1.492369532585144,
"step": 187
},
{
"epoch": 0.6016,
"grad_norm": 8.470192657114852,
"learning_rate": 9.704088918353108e-06,
"loss": 1.5446763038635254,
"step": 188
},
{
"epoch": 0.6048,
"grad_norm": 6.495467996912486,
"learning_rate": 9.697756267837856e-06,
"loss": 1.6100184917449951,
"step": 189
},
{
"epoch": 0.608,
"grad_norm": 9.085731634540966,
"learning_rate": 9.691358682701927e-06,
"loss": 1.0907909870147705,
"step": 190
},
{
"epoch": 0.6112,
"grad_norm": 8.090818860840935,
"learning_rate": 9.684896251375784e-06,
"loss": 1.3831478357315063,
"step": 191
},
{
"epoch": 0.6144,
"grad_norm": 8.19502440424346,
"learning_rate": 9.678369063186224e-06,
"loss": 1.242227554321289,
"step": 192
},
{
"epoch": 0.6176,
"grad_norm": 8.509433204924015,
"learning_rate": 9.671777208355146e-06,
"loss": 1.3014357089996338,
"step": 193
},
{
"epoch": 0.6208,
"grad_norm": 9.694482283129544,
"learning_rate": 9.665120777998303e-06,
"loss": 1.1530601978302002,
"step": 194
},
{
"epoch": 0.624,
"grad_norm": 8.527024235466444,
"learning_rate": 9.658399864124037e-06,
"loss": 1.1213865280151367,
"step": 195
},
{
"epoch": 0.6272,
"grad_norm": 10.196856651685144,
"learning_rate": 9.65161455963202e-06,
"loss": 1.7852551937103271,
"step": 196
},
{
"epoch": 0.6304,
"grad_norm": 6.421841392452185,
"learning_rate": 9.64476495831195e-06,
"loss": 1.198685884475708,
"step": 197
},
{
"epoch": 0.6336,
"grad_norm": 9.93540746554796,
"learning_rate": 9.637851154842279e-06,
"loss": 1.8969557285308838,
"step": 198
},
{
"epoch": 0.6368,
"grad_norm": 9.221671552208548,
"learning_rate": 9.630873244788884e-06,
"loss": 1.3296985626220703,
"step": 199
},
{
"epoch": 0.64,
"grad_norm": 8.157249387218771,
"learning_rate": 9.623831324603755e-06,
"loss": 1.1994402408599854,
"step": 200
},
{
"epoch": 0.6432,
"grad_norm": 7.906826454561754,
"learning_rate": 9.61672549162366e-06,
"loss": 1.218889832496643,
"step": 201
},
{
"epoch": 0.6464,
"grad_norm": 9.26538506398652,
"learning_rate": 9.6095558440688e-06,
"loss": 1.787184238433838,
"step": 202
},
{
"epoch": 0.6496,
"grad_norm": 8.462485694883314,
"learning_rate": 9.602322481041457e-06,
"loss": 1.2930833101272583,
"step": 203
},
{
"epoch": 0.6528,
"grad_norm": 9.157214864566567,
"learning_rate": 9.595025502524609e-06,
"loss": 1.4967553615570068,
"step": 204
},
{
"epoch": 0.656,
"grad_norm": 9.612059848941996,
"learning_rate": 9.587665009380565e-06,
"loss": 1.4448820352554321,
"step": 205
},
{
"epoch": 0.6592,
"grad_norm": 6.635947315543452,
"learning_rate": 9.580241103349562e-06,
"loss": 1.4597171545028687,
"step": 206
},
{
"epoch": 0.6624,
"grad_norm": 7.425792888730578,
"learning_rate": 9.572753887048353e-06,
"loss": 1.3284748792648315,
"step": 207
},
{
"epoch": 0.6656,
"grad_norm": 8.007002722154544,
"learning_rate": 9.565203463968808e-06,
"loss": 1.3783037662506104,
"step": 208
},
{
"epoch": 0.6688,
"grad_norm": 8.405535227892571,
"learning_rate": 9.557589938476462e-06,
"loss": 1.05716872215271,
"step": 209
},
{
"epoch": 0.672,
"grad_norm": 8.991120037960716,
"learning_rate": 9.549913415809084e-06,
"loss": 1.2013208866119385,
"step": 210
},
{
"epoch": 0.6752,
"grad_norm": 8.612535125939647,
"learning_rate": 9.542174002075221e-06,
"loss": 1.3602917194366455,
"step": 211
},
{
"epoch": 0.6784,
"grad_norm": 7.278176190506091,
"learning_rate": 9.534371804252727e-06,
"loss": 1.1710789203643799,
"step": 212
},
{
"epoch": 0.6816,
"grad_norm": 8.28564418534231,
"learning_rate": 9.526506930187294e-06,
"loss": 1.2485671043395996,
"step": 213
},
{
"epoch": 0.6848,
"grad_norm": 7.508757976969094,
"learning_rate": 9.518579488590947e-06,
"loss": 1.4293999671936035,
"step": 214
},
{
"epoch": 0.688,
"grad_norm": 8.041715280031156,
"learning_rate": 9.510589589040554e-06,
"loss": 1.2213821411132812,
"step": 215
},
{
"epoch": 0.6912,
"grad_norm": 8.523016055109165,
"learning_rate": 9.502537341976305e-06,
"loss": 1.2829132080078125,
"step": 216
},
{
"epoch": 0.6944,
"grad_norm": 9.891884102081251,
"learning_rate": 9.494422858700188e-06,
"loss": 1.2510731220245361,
"step": 217
},
{
"epoch": 0.6976,
"grad_norm": 8.236145684986843,
"learning_rate": 9.48624625137445e-06,
"loss": 1.195442795753479,
"step": 218
},
{
"epoch": 0.7008,
"grad_norm": 7.609097444534671,
"learning_rate": 9.478007633020043e-06,
"loss": 1.1375254392623901,
"step": 219
},
{
"epoch": 0.704,
"grad_norm": 7.771415536538384,
"learning_rate": 9.469707117515068e-06,
"loss": 1.433631420135498,
"step": 220
},
{
"epoch": 0.7072,
"grad_norm": 8.103054466969105,
"learning_rate": 9.461344819593194e-06,
"loss": 1.3020174503326416,
"step": 221
},
{
"epoch": 0.7104,
"grad_norm": 10.272390792987453,
"learning_rate": 9.452920854842085e-06,
"loss": 1.0885748863220215,
"step": 222
},
{
"epoch": 0.7136,
"grad_norm": 8.000204602572728,
"learning_rate": 9.44443533970178e-06,
"loss": 1.1722259521484375,
"step": 223
},
{
"epoch": 0.7168,
"grad_norm": 8.9234066585956,
"learning_rate": 9.435888391463108e-06,
"loss": 1.3848644495010376,
"step": 224
},
{
"epoch": 0.72,
"grad_norm": 7.986954099491675,
"learning_rate": 9.427280128266049e-06,
"loss": 1.416928768157959,
"step": 225
},
{
"epoch": 0.7232,
"grad_norm": 6.819172404168966,
"learning_rate": 9.418610669098114e-06,
"loss": 1.2840094566345215,
"step": 226
},
{
"epoch": 0.7264,
"grad_norm": 8.223256552695606,
"learning_rate": 9.409880133792684e-06,
"loss": 1.3752789497375488,
"step": 227
},
{
"epoch": 0.7296,
"grad_norm": 6.713643405627083,
"learning_rate": 9.40108864302737e-06,
"loss": 1.213709831237793,
"step": 228
},
{
"epoch": 0.7328,
"grad_norm": 7.515111293431923,
"learning_rate": 9.392236318322339e-06,
"loss": 1.5599004030227661,
"step": 229
},
{
"epoch": 0.736,
"grad_norm": 8.22857594761183,
"learning_rate": 9.383323282038632e-06,
"loss": 1.186930775642395,
"step": 230
},
{
"epoch": 0.7392,
"grad_norm": 7.965812457724141,
"learning_rate": 9.374349657376473e-06,
"loss": 1.4170236587524414,
"step": 231
},
{
"epoch": 0.7424,
"grad_norm": 9.304018211768758,
"learning_rate": 9.365315568373569e-06,
"loss": 1.3196254968643188,
"step": 232
},
{
"epoch": 0.7456,
"grad_norm": 7.619946855866199,
"learning_rate": 9.356221139903395e-06,
"loss": 1.1788700819015503,
"step": 233
},
{
"epoch": 0.7488,
"grad_norm": 7.279866102884263,
"learning_rate": 9.347066497673462e-06,
"loss": 1.1612021923065186,
"step": 234
},
{
"epoch": 0.752,
"grad_norm": 9.394732588124834,
"learning_rate": 9.337851768223589e-06,
"loss": 1.3253111839294434,
"step": 235
},
{
"epoch": 0.7552,
"grad_norm": 8.391708650144727,
"learning_rate": 9.328577078924151e-06,
"loss": 1.502340316772461,
"step": 236
},
{
"epoch": 0.7584,
"grad_norm": 7.251057106955394,
"learning_rate": 9.319242557974306e-06,
"loss": 1.4578585624694824,
"step": 237
},
{
"epoch": 0.7616,
"grad_norm": 9.310148530597965,
"learning_rate": 9.309848334400247e-06,
"loss": 1.0988597869873047,
"step": 238
},
{
"epoch": 0.7648,
"grad_norm": 8.689254989106397,
"learning_rate": 9.300394538053395e-06,
"loss": 1.3972364664077759,
"step": 239
},
{
"epoch": 0.768,
"grad_norm": 7.578102222508737,
"learning_rate": 9.29088129960862e-06,
"loss": 1.475066900253296,
"step": 240
},
{
"epoch": 0.7712,
"grad_norm": 7.121033215982822,
"learning_rate": 9.281308750562426e-06,
"loss": 1.2461925745010376,
"step": 241
},
{
"epoch": 0.7744,
"grad_norm": 6.317352065605404,
"learning_rate": 9.271677023231137e-06,
"loss": 1.616062879562378,
"step": 242
},
{
"epoch": 0.7776,
"grad_norm": 7.599911843968734,
"learning_rate": 9.261986250749068e-06,
"loss": 1.2415354251861572,
"step": 243
},
{
"epoch": 0.7808,
"grad_norm": 8.389800355264274,
"learning_rate": 9.252236567066686e-06,
"loss": 1.4176453351974487,
"step": 244
},
{
"epoch": 0.784,
"grad_norm": 8.871502172267567,
"learning_rate": 9.242428106948748e-06,
"loss": 1.1231502294540405,
"step": 245
},
{
"epoch": 0.7872,
"grad_norm": 8.997027840467029,
"learning_rate": 9.23256100597246e-06,
"loss": 1.2574081420898438,
"step": 246
},
{
"epoch": 0.7904,
"grad_norm": 7.683471944383215,
"learning_rate": 9.22263540052558e-06,
"loss": 1.2583084106445312,
"step": 247
},
{
"epoch": 0.7936,
"grad_norm": 7.301467116616291,
"learning_rate": 9.212651427804544e-06,
"loss": 1.3025351762771606,
"step": 248
},
{
"epoch": 0.7968,
"grad_norm": 7.826673647372452,
"learning_rate": 9.202609225812572e-06,
"loss": 1.353793978691101,
"step": 249
},
{
"epoch": 0.8,
"grad_norm": 7.075690985725697,
"learning_rate": 9.192508933357753e-06,
"loss": 1.1186013221740723,
"step": 250
},
{
"epoch": 0.8032,
"grad_norm": 7.455533940626682,
"learning_rate": 9.182350690051134e-06,
"loss": 1.293712854385376,
"step": 251
},
{
"epoch": 0.8064,
"grad_norm": 7.87250246460631,
"learning_rate": 9.172134636304783e-06,
"loss": 1.3515195846557617,
"step": 252
},
{
"epoch": 0.8096,
"grad_norm": 7.974102971676109,
"learning_rate": 9.16186091332985e-06,
"loss": 1.1324989795684814,
"step": 253
},
{
"epoch": 0.8128,
"grad_norm": 8.636803619619252,
"learning_rate": 9.15152966313462e-06,
"loss": 1.5039851665496826,
"step": 254
},
{
"epoch": 0.816,
"grad_norm": 8.074812370703706,
"learning_rate": 9.141141028522544e-06,
"loss": 0.949569821357727,
"step": 255
},
{
"epoch": 0.8192,
"grad_norm": 9.002512871458807,
"learning_rate": 9.130695153090272e-06,
"loss": 1.5842180252075195,
"step": 256
},
{
"epoch": 0.8224,
"grad_norm": 7.5470006196531285,
"learning_rate": 9.120192181225658e-06,
"loss": 1.455406904220581,
"step": 257
},
{
"epoch": 0.8256,
"grad_norm": 8.219270226798965,
"learning_rate": 9.109632258105771e-06,
"loss": 1.2991818189620972,
"step": 258
},
{
"epoch": 0.8288,
"grad_norm": 8.536723985075131,
"learning_rate": 9.099015529694894e-06,
"loss": 1.2435449361801147,
"step": 259
},
{
"epoch": 0.832,
"grad_norm": 8.572669888654463,
"learning_rate": 9.088342142742493e-06,
"loss": 1.158048152923584,
"step": 260
},
{
"epoch": 0.8352,
"grad_norm": 9.83600721254279,
"learning_rate": 9.077612244781196e-06,
"loss": 1.3466534614562988,
"step": 261
},
{
"epoch": 0.8384,
"grad_norm": 8.874902862728637,
"learning_rate": 9.066825984124751e-06,
"loss": 1.3222754001617432,
"step": 262
},
{
"epoch": 0.8416,
"grad_norm": 7.74285846301192,
"learning_rate": 9.055983509865988e-06,
"loss": 1.453827142715454,
"step": 263
},
{
"epoch": 0.8448,
"grad_norm": 8.139368063669426,
"learning_rate": 9.045084971874738e-06,
"loss": 1.4674158096313477,
"step": 264
},
{
"epoch": 0.848,
"grad_norm": 9.895719601908977,
"learning_rate": 9.034130520795774e-06,
"loss": 1.2776812314987183,
"step": 265
},
{
"epoch": 0.8512,
"grad_norm": 7.578896523638344,
"learning_rate": 9.023120308046726e-06,
"loss": 1.464031457901001,
"step": 266
},
{
"epoch": 0.8544,
"grad_norm": 6.64445558656183,
"learning_rate": 9.012054485815995e-06,
"loss": 1.441255807876587,
"step": 267
},
{
"epoch": 0.8576,
"grad_norm": 7.766399837035784,
"learning_rate": 9.00093320706063e-06,
"loss": 1.3127418756484985,
"step": 268
},
{
"epoch": 0.8608,
"grad_norm": 7.00310553484858,
"learning_rate": 8.989756625504237e-06,
"loss": 1.4914216995239258,
"step": 269
},
{
"epoch": 0.864,
"grad_norm": 6.903194839157025,
"learning_rate": 8.978524895634842e-06,
"loss": 1.2364141941070557,
"step": 270
},
{
"epoch": 0.8672,
"grad_norm": 10.35338800595393,
"learning_rate": 8.967238172702754e-06,
"loss": 1.3861830234527588,
"step": 271
},
{
"epoch": 0.8704,
"grad_norm": 8.475429519971145,
"learning_rate": 8.95589661271842e-06,
"loss": 1.2866461277008057,
"step": 272
},
{
"epoch": 0.8736,
"grad_norm": 8.511194806287389,
"learning_rate": 8.94450037245028e-06,
"loss": 1.5202913284301758,
"step": 273
},
{
"epoch": 0.8768,
"grad_norm": 7.8786457580535725,
"learning_rate": 8.933049609422582e-06,
"loss": 1.0238956212997437,
"step": 274
},
{
"epoch": 0.88,
"grad_norm": 8.974873612698929,
"learning_rate": 8.921544481913218e-06,
"loss": 1.3878096342086792,
"step": 275
},
{
"epoch": 0.8832,
"grad_norm": 7.970969321239065,
"learning_rate": 8.909985148951528e-06,
"loss": 1.495922565460205,
"step": 276
},
{
"epoch": 0.8864,
"grad_norm": 8.701106326378357,
"learning_rate": 8.898371770316113e-06,
"loss": 1.4205118417739868,
"step": 277
},
{
"epoch": 0.8896,
"grad_norm": 7.467794482233481,
"learning_rate": 8.886704506532611e-06,
"loss": 1.6192761659622192,
"step": 278
},
{
"epoch": 0.8928,
"grad_norm": 7.840175358415983,
"learning_rate": 8.874983518871488e-06,
"loss": 1.0924839973449707,
"step": 279
},
{
"epoch": 0.896,
"grad_norm": 7.975854546267657,
"learning_rate": 8.86320896934581e-06,
"loss": 1.0391392707824707,
"step": 280
},
{
"epoch": 0.8992,
"grad_norm": 6.692040020121022,
"learning_rate": 8.851381020709e-06,
"loss": 1.4041378498077393,
"step": 281
},
{
"epoch": 0.9024,
"grad_norm": 8.189664692313427,
"learning_rate": 8.839499836452584e-06,
"loss": 1.150742530822754,
"step": 282
},
{
"epoch": 0.9056,
"grad_norm": 9.212202115772826,
"learning_rate": 8.827565580803944e-06,
"loss": 1.3862483501434326,
"step": 283
},
{
"epoch": 0.9088,
"grad_norm": 6.676029519519889,
"learning_rate": 8.815578418724031e-06,
"loss": 1.3897206783294678,
"step": 284
},
{
"epoch": 0.912,
"grad_norm": 7.9151360196877585,
"learning_rate": 8.803538515905102e-06,
"loss": 1.3710534572601318,
"step": 285
},
{
"epoch": 0.9152,
"grad_norm": 9.529654414821383,
"learning_rate": 8.791446038768416e-06,
"loss": 1.4369233846664429,
"step": 286
},
{
"epoch": 0.9184,
"grad_norm": 7.024727905527602,
"learning_rate": 8.779301154461945e-06,
"loss": 1.614762783050537,
"step": 287
},
{
"epoch": 0.9216,
"grad_norm": 7.70744502431242,
"learning_rate": 8.76710403085805e-06,
"loss": 1.3067625761032104,
"step": 288
},
{
"epoch": 0.9248,
"grad_norm": 8.065346985410748,
"learning_rate": 8.754854836551174e-06,
"loss": 1.4161975383758545,
"step": 289
},
{
"epoch": 0.928,
"grad_norm": 8.613006134359955,
"learning_rate": 8.742553740855507e-06,
"loss": 1.730478286743164,
"step": 290
},
{
"epoch": 0.9312,
"grad_norm": 7.359498471835029,
"learning_rate": 8.730200913802638e-06,
"loss": 1.3258979320526123,
"step": 291
},
{
"epoch": 0.9344,
"grad_norm": 8.229055111716256,
"learning_rate": 8.717796526139218e-06,
"loss": 1.4235806465148926,
"step": 292
},
{
"epoch": 0.9376,
"grad_norm": 9.339372817341873,
"learning_rate": 8.70534074932459e-06,
"loss": 1.3135337829589844,
"step": 293
},
{
"epoch": 0.9408,
"grad_norm": 7.743189681566963,
"learning_rate": 8.692833755528426e-06,
"loss": 1.5984234809875488,
"step": 294
},
{
"epoch": 0.944,
"grad_norm": 7.465357382837326,
"learning_rate": 8.680275717628336e-06,
"loss": 0.9200436472892761,
"step": 295
},
{
"epoch": 0.9472,
"grad_norm": 6.113621472338499,
"learning_rate": 8.667666809207495e-06,
"loss": 1.1590797901153564,
"step": 296
},
{
"epoch": 0.9504,
"grad_norm": 8.83222913220266,
"learning_rate": 8.655007204552228e-06,
"loss": 1.3525431156158447,
"step": 297
},
{
"epoch": 0.9536,
"grad_norm": 8.089684426773257,
"learning_rate": 8.64229707864961e-06,
"loss": 1.541809320449829,
"step": 298
},
{
"epoch": 0.9568,
"grad_norm": 6.266691544034235,
"learning_rate": 8.629536607185042e-06,
"loss": 1.49853515625,
"step": 299
},
{
"epoch": 0.96,
"grad_norm": 7.832985166720924,
"learning_rate": 8.616725966539831e-06,
"loss": 1.2963213920593262,
"step": 300
},
{
"epoch": 0.9632,
"grad_norm": 8.244275439016056,
"learning_rate": 8.60386533378874e-06,
"loss": 1.2718666791915894,
"step": 301
},
{
"epoch": 0.9664,
"grad_norm": 6.803745886564737,
"learning_rate": 8.590954886697554e-06,
"loss": 1.3287005424499512,
"step": 302
},
{
"epoch": 0.9696,
"grad_norm": 8.14230735516803,
"learning_rate": 8.577994803720605e-06,
"loss": 1.3496315479278564,
"step": 303
},
{
"epoch": 0.9728,
"grad_norm": 7.160395887752691,
"learning_rate": 8.564985263998327e-06,
"loss": 1.1852588653564453,
"step": 304
},
{
"epoch": 0.976,
"grad_norm": 7.505073223770977,
"learning_rate": 8.551926447354759e-06,
"loss": 1.407005786895752,
"step": 305
},
{
"epoch": 0.9792,
"grad_norm": 6.952348949565176,
"learning_rate": 8.538818534295076e-06,
"loss": 1.309870958328247,
"step": 306
},
{
"epoch": 0.9824,
"grad_norm": 11.204121598042944,
"learning_rate": 8.525661706003083e-06,
"loss": 1.1610193252563477,
"step": 307
},
{
"epoch": 0.9856,
"grad_norm": 7.81690298212684,
"learning_rate": 8.512456144338717e-06,
"loss": 1.0622930526733398,
"step": 308
},
{
"epoch": 0.9888,
"grad_norm": 7.827397581008609,
"learning_rate": 8.499202031835532e-06,
"loss": 1.6788573265075684,
"step": 309
},
{
"epoch": 0.992,
"grad_norm": 6.992836734099746,
"learning_rate": 8.485899551698166e-06,
"loss": 1.377954363822937,
"step": 310
},
{
"epoch": 0.9952,
"grad_norm": 8.177275233313308,
"learning_rate": 8.472548887799833e-06,
"loss": 1.4246879816055298,
"step": 311
},
{
"epoch": 0.9984,
"grad_norm": 8.970522617796236,
"learning_rate": 8.45915022467975e-06,
"loss": 1.2063406705856323,
"step": 312
},
{
"epoch": 1.0,
"grad_norm": 10.634518893202033,
"learning_rate": 8.445703747540614e-06,
"loss": 1.7203607559204102,
"step": 313
},
{
"epoch": 1.0032,
"grad_norm": 6.0129608154730185,
"learning_rate": 8.43220964224602e-06,
"loss": 0.6026131510734558,
"step": 314
},
{
"epoch": 1.0064,
"grad_norm": 6.2087941253109875,
"learning_rate": 8.418668095317912e-06,
"loss": 0.693263053894043,
"step": 315
},
{
"epoch": 1.0096,
"grad_norm": 6.802241704778323,
"learning_rate": 8.405079293933986e-06,
"loss": 0.8391908407211304,
"step": 316
},
{
"epoch": 1.0128,
"grad_norm": 7.168009400795295,
"learning_rate": 8.391443425925118e-06,
"loss": 0.7134256958961487,
"step": 317
},
{
"epoch": 1.016,
"grad_norm": 5.159689332695886,
"learning_rate": 8.37776067977276e-06,
"loss": 0.412528932094574,
"step": 318
},
{
"epoch": 1.0192,
"grad_norm": 6.7851942428234375,
"learning_rate": 8.36403124460633e-06,
"loss": 0.4317566752433777,
"step": 319
},
{
"epoch": 1.0224,
"grad_norm": 7.033580669276503,
"learning_rate": 8.350255310200611e-06,
"loss": 0.5773562788963318,
"step": 320
},
{
"epoch": 1.0256,
"grad_norm": 8.572327933327205,
"learning_rate": 8.336433066973122e-06,
"loss": 0.45880258083343506,
"step": 321
},
{
"epoch": 1.0288,
"grad_norm": 4.26177700162146,
"learning_rate": 8.322564705981476e-06,
"loss": 0.31130874156951904,
"step": 322
},
{
"epoch": 1.032,
"grad_norm": 8.950237570860338,
"learning_rate": 8.308650418920751e-06,
"loss": 0.4881691038608551,
"step": 323
},
{
"epoch": 1.0352,
"grad_norm": 8.100508120823337,
"learning_rate": 8.294690398120843e-06,
"loss": 0.47666963934898376,
"step": 324
},
{
"epoch": 1.0384,
"grad_norm": 8.492513070032976,
"learning_rate": 8.280684836543794e-06,
"loss": 0.523851752281189,
"step": 325
},
{
"epoch": 1.0416,
"grad_norm": 7.834401969644655,
"learning_rate": 8.266633927781135e-06,
"loss": 0.40193814039230347,
"step": 326
},
{
"epoch": 1.0448,
"grad_norm": 8.41916508828993,
"learning_rate": 8.25253786605121e-06,
"loss": 0.5010974407196045,
"step": 327
},
{
"epoch": 1.048,
"grad_norm": 11.516524168240021,
"learning_rate": 8.238396846196483e-06,
"loss": 0.9146987199783325,
"step": 328
},
{
"epoch": 1.0512,
"grad_norm": 9.0198714380633,
"learning_rate": 8.224211063680854e-06,
"loss": 0.6981992125511169,
"step": 329
},
{
"epoch": 1.0544,
"grad_norm": 6.998783223211796,
"learning_rate": 8.209980714586955e-06,
"loss": 0.4859839379787445,
"step": 330
},
{
"epoch": 1.0576,
"grad_norm": 8.349880314032555,
"learning_rate": 8.195705995613436e-06,
"loss": 0.484186589717865,
"step": 331
},
{
"epoch": 1.0608,
"grad_norm": 8.652727667709966,
"learning_rate": 8.181387104072252e-06,
"loss": 0.5918219089508057,
"step": 332
},
{
"epoch": 1.064,
"grad_norm": 8.108894193376182,
"learning_rate": 8.167024237885927e-06,
"loss": 0.4831613302230835,
"step": 333
},
{
"epoch": 1.0672,
"grad_norm": 9.568383097450416,
"learning_rate": 8.152617595584827e-06,
"loss": 0.5082488059997559,
"step": 334
},
{
"epoch": 1.0704,
"grad_norm": 9.116586472732667,
"learning_rate": 8.138167376304411e-06,
"loss": 0.4299033284187317,
"step": 335
},
{
"epoch": 1.0735999999999999,
"grad_norm": 9.938944550395636,
"learning_rate": 8.123673779782481e-06,
"loss": 0.5700979232788086,
"step": 336
},
{
"epoch": 1.0768,
"grad_norm": 6.553593657836474,
"learning_rate": 8.10913700635642e-06,
"loss": 0.43401452898979187,
"step": 337
},
{
"epoch": 1.08,
"grad_norm": 7.805918697967689,
"learning_rate": 8.094557256960419e-06,
"loss": 0.3755732476711273,
"step": 338
},
{
"epoch": 1.0832,
"grad_norm": 9.931474303877597,
"learning_rate": 8.079934733122708e-06,
"loss": 0.647379457950592,
"step": 339
},
{
"epoch": 1.0864,
"grad_norm": 7.425089205956735,
"learning_rate": 8.065269636962765e-06,
"loss": 0.46480637788772583,
"step": 340
},
{
"epoch": 1.0896,
"grad_norm": 8.782176288911128,
"learning_rate": 8.05056217118852e-06,
"loss": 0.3868180513381958,
"step": 341
},
{
"epoch": 1.0928,
"grad_norm": 6.140913907691472,
"learning_rate": 8.035812539093557e-06,
"loss": 0.493317574262619,
"step": 342
},
{
"epoch": 1.096,
"grad_norm": 7.770229864260365,
"learning_rate": 8.021020944554305e-06,
"loss": 0.5228533744812012,
"step": 343
},
{
"epoch": 1.0992,
"grad_norm": 6.758718918464084,
"learning_rate": 8.006187592027215e-06,
"loss": 0.49244755506515503,
"step": 344
},
{
"epoch": 1.1024,
"grad_norm": 6.007524624868723,
"learning_rate": 7.991312686545939e-06,
"loss": 0.31924042105674744,
"step": 345
},
{
"epoch": 1.1056,
"grad_norm": 6.092485118851268,
"learning_rate": 7.976396433718492e-06,
"loss": 0.43302348256111145,
"step": 346
},
{
"epoch": 1.1088,
"grad_norm": 7.2962861862283255,
"learning_rate": 7.961439039724413e-06,
"loss": 0.38337451219558716,
"step": 347
},
{
"epoch": 1.112,
"grad_norm": 7.687897005630008,
"learning_rate": 7.946440711311913e-06,
"loss": 0.5438653230667114,
"step": 348
},
{
"epoch": 1.1152,
"grad_norm": 7.315122628911977,
"learning_rate": 7.931401655795021e-06,
"loss": 0.4932315945625305,
"step": 349
},
{
"epoch": 1.1184,
"grad_norm": 6.301004200496302,
"learning_rate": 7.916322081050708e-06,
"loss": 0.500643253326416,
"step": 350
},
{
"epoch": 1.1216,
"grad_norm": 8.282590265531661,
"learning_rate": 7.90120219551603e-06,
"loss": 0.4490651488304138,
"step": 351
},
{
"epoch": 1.1248,
"grad_norm": 6.969886396647708,
"learning_rate": 7.88604220818523e-06,
"loss": 0.36395400762557983,
"step": 352
},
{
"epoch": 1.1280000000000001,
"grad_norm": 9.159662699133262,
"learning_rate": 7.870842328606863e-06,
"loss": 0.5426280498504639,
"step": 353
},
{
"epoch": 1.1312,
"grad_norm": 6.8896079550726315,
"learning_rate": 7.85560276688089e-06,
"loss": 0.4683595895767212,
"step": 354
},
{
"epoch": 1.1344,
"grad_norm": 8.817357244607884,
"learning_rate": 7.84032373365578e-06,
"loss": 0.5551140308380127,
"step": 355
},
{
"epoch": 1.1376,
"grad_norm": 10.300203625445725,
"learning_rate": 7.825005440125595e-06,
"loss": 0.5555459260940552,
"step": 356
},
{
"epoch": 1.1408,
"grad_norm": 7.13157050243688,
"learning_rate": 7.809648098027067e-06,
"loss": 0.4033656120300293,
"step": 357
},
{
"epoch": 1.144,
"grad_norm": 6.7508224634417715,
"learning_rate": 7.794251919636687e-06,
"loss": 0.3559337854385376,
"step": 358
},
{
"epoch": 1.1472,
"grad_norm": 7.575793726503865,
"learning_rate": 7.778817117767748e-06,
"loss": 0.47292202711105347,
"step": 359
},
{
"epoch": 1.1504,
"grad_norm": 6.635195311082491,
"learning_rate": 7.76334390576742e-06,
"loss": 0.5196764469146729,
"step": 360
},
{
"epoch": 1.1536,
"grad_norm": 7.095792499545719,
"learning_rate": 7.747832497513797e-06,
"loss": 0.3894740343093872,
"step": 361
},
{
"epoch": 1.1568,
"grad_norm": 6.958926707839154,
"learning_rate": 7.732283107412938e-06,
"loss": 0.573284387588501,
"step": 362
},
{
"epoch": 1.16,
"grad_norm": 7.150705987411844,
"learning_rate": 7.71669595039591e-06,
"loss": 0.5691808462142944,
"step": 363
},
{
"epoch": 1.1632,
"grad_norm": 8.302242175722544,
"learning_rate": 7.701071241915804e-06,
"loss": 0.49648988246917725,
"step": 364
},
{
"epoch": 1.1663999999999999,
"grad_norm": 8.783982677246252,
"learning_rate": 7.685409197944768e-06,
"loss": 0.5622018575668335,
"step": 365
},
{
"epoch": 1.1696,
"grad_norm": 6.546897724253767,
"learning_rate": 7.669710034971025e-06,
"loss": 0.31806284189224243,
"step": 366
},
{
"epoch": 1.1728,
"grad_norm": 9.312765890650233,
"learning_rate": 7.653973969995866e-06,
"loss": 0.5242887735366821,
"step": 367
},
{
"epoch": 1.176,
"grad_norm": 8.015908661421868,
"learning_rate": 7.638201220530664e-06,
"loss": 0.4817794859409332,
"step": 368
},
{
"epoch": 1.1792,
"grad_norm": 10.116008707526621,
"learning_rate": 7.622392004593862e-06,
"loss": 0.7446014881134033,
"step": 369
},
{
"epoch": 1.1824,
"grad_norm": 7.34054674575216,
"learning_rate": 7.60654654070796e-06,
"loss": 0.5413037538528442,
"step": 370
},
{
"epoch": 1.1856,
"grad_norm": 6.88515217243263,
"learning_rate": 7.59066504789649e-06,
"loss": 0.3386208713054657,
"step": 371
},
{
"epoch": 1.1888,
"grad_norm": 7.830595129737216,
"learning_rate": 7.574747745681e-06,
"loss": 0.4951593279838562,
"step": 372
},
{
"epoch": 1.192,
"grad_norm": 7.755917362853179,
"learning_rate": 7.558794854078006e-06,
"loss": 0.48083654046058655,
"step": 373
},
{
"epoch": 1.1952,
"grad_norm": 5.940952881837767,
"learning_rate": 7.542806593595963e-06,
"loss": 0.6030147075653076,
"step": 374
},
{
"epoch": 1.1984,
"grad_norm": 8.614416571200671,
"learning_rate": 7.526783185232208e-06,
"loss": 0.46970248222351074,
"step": 375
},
{
"epoch": 1.2016,
"grad_norm": 7.181942071466236,
"learning_rate": 7.51072485046991e-06,
"loss": 0.6210339069366455,
"step": 376
},
{
"epoch": 1.2048,
"grad_norm": 8.038745633912365,
"learning_rate": 7.494631811275008e-06,
"loss": 0.7287887334823608,
"step": 377
},
{
"epoch": 1.208,
"grad_norm": 6.965686386159484,
"learning_rate": 7.478504290093138e-06,
"loss": 0.46270203590393066,
"step": 378
},
{
"epoch": 1.2112,
"grad_norm": 8.05373490928641,
"learning_rate": 7.462342509846571e-06,
"loss": 0.5416064262390137,
"step": 379
},
{
"epoch": 1.2144,
"grad_norm": 7.468977417797918,
"learning_rate": 7.446146693931111e-06,
"loss": 0.5158865451812744,
"step": 380
},
{
"epoch": 1.2176,
"grad_norm": 6.316859771702962,
"learning_rate": 7.42991706621303e-06,
"loss": 0.3206472396850586,
"step": 381
},
{
"epoch": 1.2208,
"grad_norm": 7.246141431179871,
"learning_rate": 7.413653851025959e-06,
"loss": 0.4935796856880188,
"step": 382
},
{
"epoch": 1.224,
"grad_norm": 8.161886936054467,
"learning_rate": 7.397357273167789e-06,
"loss": 0.4832332134246826,
"step": 383
},
{
"epoch": 1.2272,
"grad_norm": 8.414019577213743,
"learning_rate": 7.381027557897568e-06,
"loss": 0.7333202362060547,
"step": 384
},
{
"epoch": 1.2304,
"grad_norm": 7.295310354820947,
"learning_rate": 7.364664930932385e-06,
"loss": 0.45894700288772583,
"step": 385
},
{
"epoch": 1.2336,
"grad_norm": 8.224958365402728,
"learning_rate": 7.348269618444248e-06,
"loss": 0.4369300305843353,
"step": 386
},
{
"epoch": 1.2368000000000001,
"grad_norm": 7.373140609992038,
"learning_rate": 7.331841847056962e-06,
"loss": 0.5660817623138428,
"step": 387
},
{
"epoch": 1.24,
"grad_norm": 6.567851177459024,
"learning_rate": 7.315381843842995e-06,
"loss": 0.40187352895736694,
"step": 388
},
{
"epoch": 1.2432,
"grad_norm": 5.463671305472818,
"learning_rate": 7.298889836320334e-06,
"loss": 0.6158207654953003,
"step": 389
},
{
"epoch": 1.2464,
"grad_norm": 7.869861547320635,
"learning_rate": 7.282366052449351e-06,
"loss": 0.5330398678779602,
"step": 390
},
{
"epoch": 1.2496,
"grad_norm": 5.984248245975827,
"learning_rate": 7.265810720629643e-06,
"loss": 0.4520382285118103,
"step": 391
},
{
"epoch": 1.2528000000000001,
"grad_norm": 7.259128013267779,
"learning_rate": 7.249224069696876e-06,
"loss": 0.5072014927864075,
"step": 392
},
{
"epoch": 1.256,
"grad_norm": 7.591866132136374,
"learning_rate": 7.232606328919627e-06,
"loss": 0.5436946153640747,
"step": 393
},
{
"epoch": 1.2591999999999999,
"grad_norm": 8.044729588702769,
"learning_rate": 7.215957727996208e-06,
"loss": 0.509716272354126,
"step": 394
},
{
"epoch": 1.2624,
"grad_norm": 8.687414465189462,
"learning_rate": 7.199278497051498e-06,
"loss": 0.4460294246673584,
"step": 395
},
{
"epoch": 1.2656,
"grad_norm": 9.237015560620783,
"learning_rate": 7.182568866633757e-06,
"loss": 0.34009209275245667,
"step": 396
},
{
"epoch": 1.2688,
"grad_norm": 9.211572739369355,
"learning_rate": 7.16582906771144e-06,
"loss": 0.5390087366104126,
"step": 397
},
{
"epoch": 1.272,
"grad_norm": 6.912086833640618,
"learning_rate": 7.149059331670009e-06,
"loss": 0.39291244745254517,
"step": 398
},
{
"epoch": 1.2752,
"grad_norm": 7.343908598206628,
"learning_rate": 7.132259890308726e-06,
"loss": 0.48069047927856445,
"step": 399
},
{
"epoch": 1.2784,
"grad_norm": 8.12225916606559,
"learning_rate": 7.115430975837457e-06,
"loss": 0.48029690980911255,
"step": 400
},
{
"epoch": 1.2816,
"grad_norm": 11.18404693145568,
"learning_rate": 7.098572820873461e-06,
"loss": 0.5022896528244019,
"step": 401
},
{
"epoch": 1.2848,
"grad_norm": 6.833398911953582,
"learning_rate": 7.081685658438173e-06,
"loss": 0.35290712118148804,
"step": 402
},
{
"epoch": 1.288,
"grad_norm": 8.464531487482974,
"learning_rate": 7.064769721953975e-06,
"loss": 0.4891313910484314,
"step": 403
},
{
"epoch": 1.2912,
"grad_norm": 8.146629099778286,
"learning_rate": 7.047825245240989e-06,
"loss": 0.39079463481903076,
"step": 404
},
{
"epoch": 1.2944,
"grad_norm": 9.074826017902641,
"learning_rate": 7.030852462513827e-06,
"loss": 0.32526761293411255,
"step": 405
},
{
"epoch": 1.2976,
"grad_norm": 7.223505288805913,
"learning_rate": 7.013851608378359e-06,
"loss": 0.45433783531188965,
"step": 406
},
{
"epoch": 1.3008,
"grad_norm": 6.689620059648597,
"learning_rate": 6.9968229178284775e-06,
"loss": 0.3736943006515503,
"step": 407
},
{
"epoch": 1.304,
"grad_norm": 9.924447085380843,
"learning_rate": 6.979766626242839e-06,
"loss": 0.6519632935523987,
"step": 408
},
{
"epoch": 1.3072,
"grad_norm": 10.13170705723922,
"learning_rate": 6.9626829693816135e-06,
"loss": 0.5979541540145874,
"step": 409
},
{
"epoch": 1.3104,
"grad_norm": 8.955913652595548,
"learning_rate": 6.945572183383229e-06,
"loss": 0.6324474811553955,
"step": 410
},
{
"epoch": 1.3136,
"grad_norm": 10.655745338759424,
"learning_rate": 6.928434504761106e-06,
"loss": 0.6388872861862183,
"step": 411
},
{
"epoch": 1.3168,
"grad_norm": 7.7027810167004365,
"learning_rate": 6.911270170400385e-06,
"loss": 0.4256141781806946,
"step": 412
},
{
"epoch": 1.32,
"grad_norm": 7.010917206820395,
"learning_rate": 6.894079417554657e-06,
"loss": 0.44266918301582336,
"step": 413
},
{
"epoch": 1.3232,
"grad_norm": 6.151652971274576,
"learning_rate": 6.8768624838426815e-06,
"loss": 0.39850685000419617,
"step": 414
},
{
"epoch": 1.3264,
"grad_norm": 11.231975079494845,
"learning_rate": 6.859619607245102e-06,
"loss": 0.7118866443634033,
"step": 415
},
{
"epoch": 1.3296000000000001,
"grad_norm": 9.552955747361931,
"learning_rate": 6.842351026101155e-06,
"loss": 0.7048600912094116,
"step": 416
},
{
"epoch": 1.3328,
"grad_norm": 7.780839236027681,
"learning_rate": 6.825056979105382e-06,
"loss": 0.45705699920654297,
"step": 417
},
{
"epoch": 1.336,
"grad_norm": 7.629955459559422,
"learning_rate": 6.807737705304324e-06,
"loss": 0.5459251999855042,
"step": 418
},
{
"epoch": 1.3392,
"grad_norm": 6.447757931872972,
"learning_rate": 6.790393444093214e-06,
"loss": 0.5751878023147583,
"step": 419
},
{
"epoch": 1.3424,
"grad_norm": 6.906397089104152,
"learning_rate": 6.773024435212678e-06,
"loss": 0.44277092814445496,
"step": 420
},
{
"epoch": 1.3456000000000001,
"grad_norm": 6.8167918661739835,
"learning_rate": 6.7556309187454185e-06,
"loss": 0.3328106105327606,
"step": 421
},
{
"epoch": 1.3488,
"grad_norm": 8.261291571398948,
"learning_rate": 6.738213135112884e-06,
"loss": 0.5300989151000977,
"step": 422
},
{
"epoch": 1.3519999999999999,
"grad_norm": 6.740733782224303,
"learning_rate": 6.720771325071965e-06,
"loss": 0.5413635969161987,
"step": 423
},
{
"epoch": 1.3552,
"grad_norm": 6.908354071133098,
"learning_rate": 6.703305729711653e-06,
"loss": 0.44419699907302856,
"step": 424
},
{
"epoch": 1.3584,
"grad_norm": 7.5209877219924985,
"learning_rate": 6.685816590449708e-06,
"loss": 0.42481735348701477,
"step": 425
},
{
"epoch": 1.3616,
"grad_norm": 9.778704978756092,
"learning_rate": 6.668304149029331e-06,
"loss": 0.6383399963378906,
"step": 426
},
{
"epoch": 1.3648,
"grad_norm": 7.465110530688073,
"learning_rate": 6.650768647515813e-06,
"loss": 0.5352426171302795,
"step": 427
},
{
"epoch": 1.3679999999999999,
"grad_norm": 6.926848707875294,
"learning_rate": 6.63321032829319e-06,
"loss": 0.5800532102584839,
"step": 428
},
{
"epoch": 1.3712,
"grad_norm": 7.37843561048704,
"learning_rate": 6.615629434060903e-06,
"loss": 0.5298522710800171,
"step": 429
},
{
"epoch": 1.3744,
"grad_norm": 6.054930765959329,
"learning_rate": 6.598026207830428e-06,
"loss": 0.4980102777481079,
"step": 430
},
{
"epoch": 1.3776,
"grad_norm": 7.647492558315197,
"learning_rate": 6.5804008929219284e-06,
"loss": 0.5644188523292542,
"step": 431
},
{
"epoch": 1.3808,
"grad_norm": 5.774822663716222,
"learning_rate": 6.562753732960887e-06,
"loss": 0.36280328035354614,
"step": 432
},
{
"epoch": 1.384,
"grad_norm": 7.708619443193026,
"learning_rate": 6.545084971874738e-06,
"loss": 0.5643590688705444,
"step": 433
},
{
"epoch": 1.3872,
"grad_norm": 8.102789292896407,
"learning_rate": 6.527394853889499e-06,
"loss": 0.5093599557876587,
"step": 434
},
{
"epoch": 1.3904,
"grad_norm": 8.80110018229554,
"learning_rate": 6.5096836235263904e-06,
"loss": 0.5586891770362854,
"step": 435
},
{
"epoch": 1.3936,
"grad_norm": 7.893909469953318,
"learning_rate": 6.491951525598461e-06,
"loss": 0.5126465559005737,
"step": 436
},
{
"epoch": 1.3968,
"grad_norm": 8.778594057654601,
"learning_rate": 6.4741988052071965e-06,
"loss": 0.5542795658111572,
"step": 437
},
{
"epoch": 1.4,
"grad_norm": 5.979119305761236,
"learning_rate": 6.45642570773914e-06,
"loss": 0.4091089069843292,
"step": 438
},
{
"epoch": 1.4032,
"grad_norm": 7.1502048687779824,
"learning_rate": 6.438632478862495e-06,
"loss": 0.5460984706878662,
"step": 439
},
{
"epoch": 1.4064,
"grad_norm": 6.171441380062532,
"learning_rate": 6.4208193645237314e-06,
"loss": 0.6471701860427856,
"step": 440
},
{
"epoch": 1.4096,
"grad_norm": 11.31605764321686,
"learning_rate": 6.402986610944183e-06,
"loss": 0.752935528755188,
"step": 441
},
{
"epoch": 1.4128,
"grad_norm": 9.653333842160079,
"learning_rate": 6.385134464616649e-06,
"loss": 0.34474432468414307,
"step": 442
},
{
"epoch": 1.416,
"grad_norm": 8.8307627053379,
"learning_rate": 6.367263172301985e-06,
"loss": 0.4292425513267517,
"step": 443
},
{
"epoch": 1.4192,
"grad_norm": 6.9560500362599464,
"learning_rate": 6.3493729810256895e-06,
"loss": 0.5380972623825073,
"step": 444
},
{
"epoch": 1.4224,
"grad_norm": 6.887582072387786,
"learning_rate": 6.331464138074493e-06,
"loss": 0.3827627897262573,
"step": 445
},
{
"epoch": 1.4256,
"grad_norm": 6.922249194420599,
"learning_rate": 6.313536890992935e-06,
"loss": 0.48258543014526367,
"step": 446
},
{
"epoch": 1.4288,
"grad_norm": 6.118436604098598,
"learning_rate": 6.29559148757995e-06,
"loss": 0.4225442409515381,
"step": 447
},
{
"epoch": 1.432,
"grad_norm": 6.738392697574742,
"learning_rate": 6.277628175885437e-06,
"loss": 0.5184521675109863,
"step": 448
},
{
"epoch": 1.4352,
"grad_norm": 9.188538442906372,
"learning_rate": 6.2596472042068275e-06,
"loss": 0.46589305996894836,
"step": 449
},
{
"epoch": 1.4384000000000001,
"grad_norm": 6.670234799774067,
"learning_rate": 6.241648821085666e-06,
"loss": 0.5558629631996155,
"step": 450
},
{
"epoch": 1.4416,
"grad_norm": 6.152456279053409,
"learning_rate": 6.223633275304157e-06,
"loss": 0.5446882843971252,
"step": 451
},
{
"epoch": 1.4447999999999999,
"grad_norm": 7.143249704595933,
"learning_rate": 6.205600815881741e-06,
"loss": 0.4068102538585663,
"step": 452
},
{
"epoch": 1.448,
"grad_norm": 5.667007815341408,
"learning_rate": 6.187551692071648e-06,
"loss": 0.38176125288009644,
"step": 453
},
{
"epoch": 1.4512,
"grad_norm": 7.046710075234125,
"learning_rate": 6.1694861533574445e-06,
"loss": 0.5277380347251892,
"step": 454
},
{
"epoch": 1.4544000000000001,
"grad_norm": 8.199121579949253,
"learning_rate": 6.1514044494496e-06,
"loss": 0.7369883060455322,
"step": 455
},
{
"epoch": 1.4576,
"grad_norm": 10.497590603898514,
"learning_rate": 6.133306830282021e-06,
"loss": 0.417258620262146,
"step": 456
},
{
"epoch": 1.4607999999999999,
"grad_norm": 6.637346853321983,
"learning_rate": 6.115193546008602e-06,
"loss": 0.43404704332351685,
"step": 457
},
{
"epoch": 1.464,
"grad_norm": 6.46089602405522,
"learning_rate": 6.097064846999774e-06,
"loss": 0.5073419809341431,
"step": 458
},
{
"epoch": 1.4672,
"grad_norm": 6.6829209811525025,
"learning_rate": 6.078920983839032e-06,
"loss": 0.4765991270542145,
"step": 459
},
{
"epoch": 1.4704,
"grad_norm": 6.323446652450166,
"learning_rate": 6.060762207319479e-06,
"loss": 0.388445109128952,
"step": 460
},
{
"epoch": 1.4736,
"grad_norm": 7.399234218436147,
"learning_rate": 6.042588768440358e-06,
"loss": 0.4553852081298828,
"step": 461
},
{
"epoch": 1.4768,
"grad_norm": 7.223724090087657,
"learning_rate": 6.024400918403581e-06,
"loss": 0.5650292038917542,
"step": 462
},
{
"epoch": 1.48,
"grad_norm": 10.409085903251606,
"learning_rate": 6.006198908610261e-06,
"loss": 0.70589280128479,
"step": 463
},
{
"epoch": 1.4832,
"grad_norm": 6.796037874973836,
"learning_rate": 5.987982990657229e-06,
"loss": 0.41508570313453674,
"step": 464
},
{
"epoch": 1.4864,
"grad_norm": 7.48922458372165,
"learning_rate": 5.9697534163335645e-06,
"loss": 0.48055723309516907,
"step": 465
},
{
"epoch": 1.4896,
"grad_norm": 6.282702772135452,
"learning_rate": 5.95151043761711e-06,
"loss": 0.4922732412815094,
"step": 466
},
{
"epoch": 1.4928,
"grad_norm": 5.8126680668553306,
"learning_rate": 5.933254306670995e-06,
"loss": 0.5029237270355225,
"step": 467
},
{
"epoch": 1.496,
"grad_norm": 5.43503003531343,
"learning_rate": 5.914985275840135e-06,
"loss": 0.4639953374862671,
"step": 468
},
{
"epoch": 1.4992,
"grad_norm": 8.193347236188009,
"learning_rate": 5.896703597647765e-06,
"loss": 0.6097243428230286,
"step": 469
},
{
"epoch": 1.5024,
"grad_norm": 7.222009935197594,
"learning_rate": 5.878409524791931e-06,
"loss": 0.5702711343765259,
"step": 470
},
{
"epoch": 1.5056,
"grad_norm": 6.994674481698864,
"learning_rate": 5.8601033101420055e-06,
"loss": 0.5210344791412354,
"step": 471
},
{
"epoch": 1.5088,
"grad_norm": 7.377898406161829,
"learning_rate": 5.841785206735192e-06,
"loss": 0.38308286666870117,
"step": 472
},
{
"epoch": 1.512,
"grad_norm": 8.822095933217978,
"learning_rate": 5.823455467773027e-06,
"loss": 0.554124653339386,
"step": 473
},
{
"epoch": 1.5152,
"grad_norm": 8.500313445555642,
"learning_rate": 5.805114346617874e-06,
"loss": 0.5035825967788696,
"step": 474
},
{
"epoch": 1.5184,
"grad_norm": 7.053399430408619,
"learning_rate": 5.786762096789431e-06,
"loss": 0.5587537288665771,
"step": 475
},
{
"epoch": 1.5215999999999998,
"grad_norm": 7.727022367120782,
"learning_rate": 5.768398971961221e-06,
"loss": 0.4846581816673279,
"step": 476
},
{
"epoch": 1.5248,
"grad_norm": 7.823615919680324,
"learning_rate": 5.750025225957086e-06,
"loss": 0.5808063745498657,
"step": 477
},
{
"epoch": 1.528,
"grad_norm": 9.90393372134271,
"learning_rate": 5.731641112747679e-06,
"loss": 0.4148855209350586,
"step": 478
},
{
"epoch": 1.5312000000000001,
"grad_norm": 7.407774790675967,
"learning_rate": 5.713246886446954e-06,
"loss": 0.41522204875946045,
"step": 479
},
{
"epoch": 1.5344,
"grad_norm": 9.758860537059899,
"learning_rate": 5.694842801308651e-06,
"loss": 0.7127000093460083,
"step": 480
},
{
"epoch": 1.5375999999999999,
"grad_norm": 6.98509907484725,
"learning_rate": 5.676429111722786e-06,
"loss": 0.36238986253738403,
"step": 481
},
{
"epoch": 1.5408,
"grad_norm": 6.70899989029257,
"learning_rate": 5.6580060722121325e-06,
"loss": 0.5036066770553589,
"step": 482
},
{
"epoch": 1.544,
"grad_norm": 8.14198060469778,
"learning_rate": 5.639573937428699e-06,
"loss": 0.5849555730819702,
"step": 483
},
{
"epoch": 1.5472000000000001,
"grad_norm": 8.607240665165682,
"learning_rate": 5.621132962150216e-06,
"loss": 0.6441385746002197,
"step": 484
},
{
"epoch": 1.5504,
"grad_norm": 8.184158790115639,
"learning_rate": 5.6026834012766155e-06,
"loss": 0.6535292267799377,
"step": 485
},
{
"epoch": 1.5535999999999999,
"grad_norm": 7.817571273097133,
"learning_rate": 5.584225509826497e-06,
"loss": 0.7754327654838562,
"step": 486
},
{
"epoch": 1.5568,
"grad_norm": 8.11932753823281,
"learning_rate": 5.565759542933612e-06,
"loss": 0.4354695677757263,
"step": 487
},
{
"epoch": 1.56,
"grad_norm": 5.913463112988504,
"learning_rate": 5.547285755843334e-06,
"loss": 0.44843506813049316,
"step": 488
},
{
"epoch": 1.5632000000000001,
"grad_norm": 8.735793750574354,
"learning_rate": 5.5288044039091335e-06,
"loss": 0.6580309867858887,
"step": 489
},
{
"epoch": 1.5664,
"grad_norm": 5.292671032163985,
"learning_rate": 5.510315742589042e-06,
"loss": 0.4061349928379059,
"step": 490
},
{
"epoch": 1.5695999999999999,
"grad_norm": 8.464438261126881,
"learning_rate": 5.491820027442126e-06,
"loss": 0.7057147026062012,
"step": 491
},
{
"epoch": 1.5728,
"grad_norm": 6.686670150549535,
"learning_rate": 5.473317514124958e-06,
"loss": 0.4275538921356201,
"step": 492
},
{
"epoch": 1.576,
"grad_norm": 8.76197272595298,
"learning_rate": 5.454808458388069e-06,
"loss": 0.6766518354415894,
"step": 493
},
{
"epoch": 1.5792000000000002,
"grad_norm": 7.394368773931638,
"learning_rate": 5.436293116072431e-06,
"loss": 0.46650800108909607,
"step": 494
},
{
"epoch": 1.5824,
"grad_norm": 8.923346069899644,
"learning_rate": 5.417771743105908e-06,
"loss": 0.5577391386032104,
"step": 495
},
{
"epoch": 1.5856,
"grad_norm": 8.440092963996491,
"learning_rate": 5.399244595499721e-06,
"loss": 0.533458411693573,
"step": 496
},
{
"epoch": 1.5888,
"grad_norm": 6.541181913843434,
"learning_rate": 5.380711929344915e-06,
"loss": 0.5325558185577393,
"step": 497
},
{
"epoch": 1.592,
"grad_norm": 5.187061044099187,
"learning_rate": 5.362174000808813e-06,
"loss": 0.3211737275123596,
"step": 498
},
{
"epoch": 1.5952,
"grad_norm": 6.505410388942965,
"learning_rate": 5.343631066131476e-06,
"loss": 0.38888561725616455,
"step": 499
},
{
"epoch": 1.5984,
"grad_norm": 7.364431646376633,
"learning_rate": 5.325083381622165e-06,
"loss": 0.5453630685806274,
"step": 500
},
{
"epoch": 1.6016,
"grad_norm": 6.322688350699228,
"learning_rate": 5.30653120365579e-06,
"loss": 0.5652034878730774,
"step": 501
},
{
"epoch": 1.6048,
"grad_norm": 8.853318124726744,
"learning_rate": 5.28797478866938e-06,
"loss": 0.582036554813385,
"step": 502
},
{
"epoch": 1.608,
"grad_norm": 8.912225583736802,
"learning_rate": 5.269414393158523e-06,
"loss": 0.5842963457107544,
"step": 503
},
{
"epoch": 1.6112,
"grad_norm": 5.732818552753856,
"learning_rate": 5.250850273673831e-06,
"loss": 0.3532952666282654,
"step": 504
},
{
"epoch": 1.6143999999999998,
"grad_norm": 7.011543560393292,
"learning_rate": 5.232282686817392e-06,
"loss": 0.777542233467102,
"step": 505
},
{
"epoch": 1.6176,
"grad_norm": 7.230283153374082,
"learning_rate": 5.213711889239214e-06,
"loss": 0.504940927028656,
"step": 506
},
{
"epoch": 1.6208,
"grad_norm": 6.739984960746159,
"learning_rate": 5.195138137633695e-06,
"loss": 0.477466344833374,
"step": 507
},
{
"epoch": 1.624,
"grad_norm": 8.172205188673544,
"learning_rate": 5.17656168873606e-06,
"loss": 0.702189028263092,
"step": 508
},
{
"epoch": 1.6272,
"grad_norm": 6.462077357844308,
"learning_rate": 5.157982799318817e-06,
"loss": 0.57176673412323,
"step": 509
},
{
"epoch": 1.6303999999999998,
"grad_norm": 6.680404492750995,
"learning_rate": 5.139401726188208e-06,
"loss": 0.5739114284515381,
"step": 510
},
{
"epoch": 1.6336,
"grad_norm": 6.366100074105676,
"learning_rate": 5.120818726180662e-06,
"loss": 0.5177488923072815,
"step": 511
},
{
"epoch": 1.6368,
"grad_norm": 7.4161655655077405,
"learning_rate": 5.1022340561592396e-06,
"loss": 0.3786865174770355,
"step": 512
},
{
"epoch": 1.6400000000000001,
"grad_norm": 6.483208789049453,
"learning_rate": 5.083647973010085e-06,
"loss": 0.41597098112106323,
"step": 513
},
{
"epoch": 1.6432,
"grad_norm": 8.47709181800357,
"learning_rate": 5.065060733638878e-06,
"loss": 0.686662495136261,
"step": 514
},
{
"epoch": 1.6463999999999999,
"grad_norm": 6.44253851538182,
"learning_rate": 5.046472594967279e-06,
"loss": 0.4751847982406616,
"step": 515
},
{
"epoch": 1.6496,
"grad_norm": 6.5783238890436095,
"learning_rate": 5.027883813929374e-06,
"loss": 0.445523202419281,
"step": 516
},
{
"epoch": 1.6528,
"grad_norm": 9.01720827881954,
"learning_rate": 5.009294647468137e-06,
"loss": 0.6079023480415344,
"step": 517
},
{
"epoch": 1.6560000000000001,
"grad_norm": 5.577531039837312,
"learning_rate": 4.990705352531864e-06,
"loss": 0.4216201901435852,
"step": 518
},
{
"epoch": 1.6592,
"grad_norm": 6.823433754728423,
"learning_rate": 4.972116186070626e-06,
"loss": 0.38610994815826416,
"step": 519
},
{
"epoch": 1.6623999999999999,
"grad_norm": 8.553838186951001,
"learning_rate": 4.953527405032723e-06,
"loss": 0.47645601630210876,
"step": 520
},
{
"epoch": 1.6656,
"grad_norm": 7.331220534335315,
"learning_rate": 4.934939266361123e-06,
"loss": 0.47244787216186523,
"step": 521
},
{
"epoch": 1.6688,
"grad_norm": 8.41185348646009,
"learning_rate": 4.916352026989914e-06,
"loss": 0.557049036026001,
"step": 522
},
{
"epoch": 1.6720000000000002,
"grad_norm": 7.611589059224408,
"learning_rate": 4.897765943840761e-06,
"loss": 0.4868379831314087,
"step": 523
},
{
"epoch": 1.6752,
"grad_norm": 7.726083343924204,
"learning_rate": 4.87918127381934e-06,
"loss": 0.4325038194656372,
"step": 524
},
{
"epoch": 1.6784,
"grad_norm": 8.23049428608718,
"learning_rate": 4.860598273811793e-06,
"loss": 0.46239835023880005,
"step": 525
},
{
"epoch": 1.6816,
"grad_norm": 7.465086897123833,
"learning_rate": 4.842017200681185e-06,
"loss": 0.33587491512298584,
"step": 526
},
{
"epoch": 1.6848,
"grad_norm": 8.984941447389932,
"learning_rate": 4.823438311263943e-06,
"loss": 0.6378401517868042,
"step": 527
},
{
"epoch": 1.688,
"grad_norm": 6.899400246362851,
"learning_rate": 4.804861862366306e-06,
"loss": 0.5093947649002075,
"step": 528
},
{
"epoch": 1.6912,
"grad_norm": 6.150565378799528,
"learning_rate": 4.786288110760787e-06,
"loss": 0.35318124294281006,
"step": 529
},
{
"epoch": 1.6944,
"grad_norm": 7.2762947803634095,
"learning_rate": 4.767717313182611e-06,
"loss": 0.5937176942825317,
"step": 530
},
{
"epoch": 1.6976,
"grad_norm": 7.670919348457662,
"learning_rate": 4.74914972632617e-06,
"loss": 0.5973190069198608,
"step": 531
},
{
"epoch": 1.7008,
"grad_norm": 6.489029658397704,
"learning_rate": 4.730585606841479e-06,
"loss": 0.4227399528026581,
"step": 532
},
{
"epoch": 1.704,
"grad_norm": 7.865431935205323,
"learning_rate": 4.7120252113306216e-06,
"loss": 0.556594729423523,
"step": 533
},
{
"epoch": 1.7072,
"grad_norm": 7.79683851505494,
"learning_rate": 4.693468796344211e-06,
"loss": 0.43302100896835327,
"step": 534
},
{
"epoch": 1.7104,
"grad_norm": 7.517950496389598,
"learning_rate": 4.6749166183778375e-06,
"loss": 0.5427360534667969,
"step": 535
},
{
"epoch": 1.7136,
"grad_norm": 7.0916163633635545,
"learning_rate": 4.656368933868525e-06,
"loss": 0.4578840434551239,
"step": 536
},
{
"epoch": 1.7168,
"grad_norm": 7.432425888767991,
"learning_rate": 4.637825999191189e-06,
"loss": 0.571090579032898,
"step": 537
},
{
"epoch": 1.72,
"grad_norm": 7.084193443955135,
"learning_rate": 4.619288070655086e-06,
"loss": 0.3775066137313843,
"step": 538
},
{
"epoch": 1.7231999999999998,
"grad_norm": 7.204834903940395,
"learning_rate": 4.600755404500281e-06,
"loss": 0.5986708402633667,
"step": 539
},
{
"epoch": 1.7264,
"grad_norm": 8.97101592974044,
"learning_rate": 4.582228256894093e-06,
"loss": 0.567808210849762,
"step": 540
},
{
"epoch": 1.7296,
"grad_norm": 6.250038530392417,
"learning_rate": 4.56370688392757e-06,
"loss": 0.24780938029289246,
"step": 541
},
{
"epoch": 1.7328000000000001,
"grad_norm": 6.666933108484488,
"learning_rate": 4.545191541611933e-06,
"loss": 0.6238658428192139,
"step": 542
},
{
"epoch": 1.736,
"grad_norm": 5.58981336637436,
"learning_rate": 4.526682485875044e-06,
"loss": 0.37057310342788696,
"step": 543
},
{
"epoch": 1.7391999999999999,
"grad_norm": 7.219161759707987,
"learning_rate": 4.508179972557875e-06,
"loss": 0.6386445760726929,
"step": 544
},
{
"epoch": 1.7424,
"grad_norm": 7.36801782800253,
"learning_rate": 4.489684257410959e-06,
"loss": 0.5321599245071411,
"step": 545
},
{
"epoch": 1.7456,
"grad_norm": 7.7993334107505055,
"learning_rate": 4.471195596090867e-06,
"loss": 0.5753816962242126,
"step": 546
},
{
"epoch": 1.7488000000000001,
"grad_norm": 6.259209128757145,
"learning_rate": 4.452714244156667e-06,
"loss": 0.35375815629959106,
"step": 547
},
{
"epoch": 1.752,
"grad_norm": 8.143367308425173,
"learning_rate": 4.434240457066388e-06,
"loss": 0.42853569984436035,
"step": 548
},
{
"epoch": 1.7551999999999999,
"grad_norm": 6.353295386251523,
"learning_rate": 4.415774490173504e-06,
"loss": 0.37098920345306396,
"step": 549
},
{
"epoch": 1.7584,
"grad_norm": 7.774937292617225,
"learning_rate": 4.397316598723385e-06,
"loss": 0.43329817056655884,
"step": 550
},
{
"epoch": 1.7616,
"grad_norm": 6.930052749769366,
"learning_rate": 4.3788670378497836e-06,
"loss": 0.29799777269363403,
"step": 551
},
{
"epoch": 1.7648000000000001,
"grad_norm": 7.2904450023589575,
"learning_rate": 4.360426062571303e-06,
"loss": 0.4680325388908386,
"step": 552
},
{
"epoch": 1.768,
"grad_norm": 11.176699661756395,
"learning_rate": 4.341993927787871e-06,
"loss": 0.8519117832183838,
"step": 553
},
{
"epoch": 1.7711999999999999,
"grad_norm": 5.941186616599786,
"learning_rate": 4.323570888277215e-06,
"loss": 0.5166082382202148,
"step": 554
},
{
"epoch": 1.7744,
"grad_norm": 8.456979163035736,
"learning_rate": 4.305157198691351e-06,
"loss": 0.4467886686325073,
"step": 555
},
{
"epoch": 1.7776,
"grad_norm": 10.97290536605935,
"learning_rate": 4.286753113553049e-06,
"loss": 0.4852108955383301,
"step": 556
},
{
"epoch": 1.7808000000000002,
"grad_norm": 7.94306194994752,
"learning_rate": 4.268358887252322e-06,
"loss": 0.422019362449646,
"step": 557
},
{
"epoch": 1.784,
"grad_norm": 8.517824147784971,
"learning_rate": 4.249974774042915e-06,
"loss": 0.4542234539985657,
"step": 558
},
{
"epoch": 1.7872,
"grad_norm": 7.423070170573783,
"learning_rate": 4.231601028038781e-06,
"loss": 0.517538845539093,
"step": 559
},
{
"epoch": 1.7904,
"grad_norm": 7.404211000180959,
"learning_rate": 4.2132379032105695e-06,
"loss": 0.48762762546539307,
"step": 560
},
{
"epoch": 1.7936,
"grad_norm": 6.7976579593011754,
"learning_rate": 4.194885653382128e-06,
"loss": 0.48664554953575134,
"step": 561
},
{
"epoch": 1.7968,
"grad_norm": 9.282800221274133,
"learning_rate": 4.176544532226974e-06,
"loss": 0.35848039388656616,
"step": 562
},
{
"epoch": 1.8,
"grad_norm": 11.487760877045696,
"learning_rate": 4.158214793264808e-06,
"loss": 0.5448033809661865,
"step": 563
},
{
"epoch": 1.8032,
"grad_norm": 6.3902322523678645,
"learning_rate": 4.139896689857995e-06,
"loss": 0.4202970266342163,
"step": 564
},
{
"epoch": 1.8064,
"grad_norm": 5.972529567288068,
"learning_rate": 4.121590475208071e-06,
"loss": 0.4400099813938141,
"step": 565
},
{
"epoch": 1.8096,
"grad_norm": 9.058390840184762,
"learning_rate": 4.1032964023522366e-06,
"loss": 0.615606963634491,
"step": 566
},
{
"epoch": 1.8128,
"grad_norm": 9.314811430467595,
"learning_rate": 4.085014724159866e-06,
"loss": 0.5888881683349609,
"step": 567
},
{
"epoch": 1.8159999999999998,
"grad_norm": 7.2310016254714915,
"learning_rate": 4.066745693329008e-06,
"loss": 0.37168291211128235,
"step": 568
},
{
"epoch": 1.8192,
"grad_norm": 6.967935778623861,
"learning_rate": 4.0484895623828906e-06,
"loss": 0.4908190071582794,
"step": 569
},
{
"epoch": 1.8224,
"grad_norm": 10.510681464005504,
"learning_rate": 4.030246583666437e-06,
"loss": 0.6651096940040588,
"step": 570
},
{
"epoch": 1.8256000000000001,
"grad_norm": 8.592400516306187,
"learning_rate": 4.012017009342773e-06,
"loss": 0.5469528436660767,
"step": 571
},
{
"epoch": 1.8288,
"grad_norm": 6.091750448693852,
"learning_rate": 3.99380109138974e-06,
"loss": 0.38212019205093384,
"step": 572
},
{
"epoch": 1.8319999999999999,
"grad_norm": 7.664831821554298,
"learning_rate": 3.97559908159642e-06,
"loss": 0.5373251438140869,
"step": 573
},
{
"epoch": 1.8352,
"grad_norm": 6.725331155192924,
"learning_rate": 3.9574112315596425e-06,
"loss": 0.46206820011138916,
"step": 574
},
{
"epoch": 1.8384,
"grad_norm": 6.781301091046379,
"learning_rate": 3.9392377926805226e-06,
"loss": 0.33050593733787537,
"step": 575
},
{
"epoch": 1.8416000000000001,
"grad_norm": 6.725281017376952,
"learning_rate": 3.92107901616097e-06,
"loss": 0.5594092011451721,
"step": 576
},
{
"epoch": 1.8448,
"grad_norm": 7.609708053400679,
"learning_rate": 3.9029351530002264e-06,
"loss": 0.4402165412902832,
"step": 577
},
{
"epoch": 1.8479999999999999,
"grad_norm": 10.276120185424958,
"learning_rate": 3.884806453991399e-06,
"loss": 0.5187775492668152,
"step": 578
},
{
"epoch": 1.8512,
"grad_norm": 8.90459562092144,
"learning_rate": 3.866693169717982e-06,
"loss": 0.5199622511863708,
"step": 579
},
{
"epoch": 1.8544,
"grad_norm": 6.48308735520407,
"learning_rate": 3.848595550550401e-06,
"loss": 0.3771589994430542,
"step": 580
},
{
"epoch": 1.8576000000000001,
"grad_norm": 5.492460437578398,
"learning_rate": 3.830513846642556e-06,
"loss": 0.34523096680641174,
"step": 581
},
{
"epoch": 1.8608,
"grad_norm": 16.614436807458986,
"learning_rate": 3.8124483079283546e-06,
"loss": 1.2838107347488403,
"step": 582
},
{
"epoch": 1.8639999999999999,
"grad_norm": 8.692333467484982,
"learning_rate": 3.7943991841182586e-06,
"loss": 0.7714948654174805,
"step": 583
},
{
"epoch": 1.8672,
"grad_norm": 7.127734804172419,
"learning_rate": 3.7763667246958447e-06,
"loss": 0.44820207357406616,
"step": 584
},
{
"epoch": 1.8704,
"grad_norm": 7.718481922141558,
"learning_rate": 3.758351178914336e-06,
"loss": 0.4199792444705963,
"step": 585
},
{
"epoch": 1.8736000000000002,
"grad_norm": 6.296045082104664,
"learning_rate": 3.7403527957931716e-06,
"loss": 0.4381064772605896,
"step": 586
},
{
"epoch": 1.8768,
"grad_norm": 6.932702469092418,
"learning_rate": 3.7223718241145646e-06,
"loss": 0.47167322039604187,
"step": 587
},
{
"epoch": 1.88,
"grad_norm": 9.031300597462264,
"learning_rate": 3.7044085124200517e-06,
"loss": 0.6867875456809998,
"step": 588
},
{
"epoch": 1.8832,
"grad_norm": 7.062223052036681,
"learning_rate": 3.6864631090070656e-06,
"loss": 0.47436535358428955,
"step": 589
},
{
"epoch": 1.8864,
"grad_norm": 8.906615196089755,
"learning_rate": 3.668535861925509e-06,
"loss": 0.3686508536338806,
"step": 590
},
{
"epoch": 1.8896,
"grad_norm": 8.405480848487068,
"learning_rate": 3.650627018974312e-06,
"loss": 0.3820822238922119,
"step": 591
},
{
"epoch": 1.8928,
"grad_norm": 8.275566721307396,
"learning_rate": 3.632736827698015e-06,
"loss": 0.5092222690582275,
"step": 592
},
{
"epoch": 1.896,
"grad_norm": 7.774299328200095,
"learning_rate": 3.6148655353833518e-06,
"loss": 0.41467800736427307,
"step": 593
},
{
"epoch": 1.8992,
"grad_norm": 8.62945356420848,
"learning_rate": 3.5970133890558184e-06,
"loss": 0.6799741983413696,
"step": 594
},
{
"epoch": 1.9024,
"grad_norm": 9.422198590276302,
"learning_rate": 3.5791806354762702e-06,
"loss": 0.4172382950782776,
"step": 595
},
{
"epoch": 1.9056,
"grad_norm": 7.284452022605865,
"learning_rate": 3.5613675211375066e-06,
"loss": 0.3244074583053589,
"step": 596
},
{
"epoch": 1.9088,
"grad_norm": 6.7685097548176465,
"learning_rate": 3.5435742922608618e-06,
"loss": 0.42148303985595703,
"step": 597
},
{
"epoch": 1.912,
"grad_norm": 7.726690102911872,
"learning_rate": 3.525801194792805e-06,
"loss": 0.44875943660736084,
"step": 598
},
{
"epoch": 1.9152,
"grad_norm": 7.24076957052674,
"learning_rate": 3.508048474401541e-06,
"loss": 0.3699103593826294,
"step": 599
},
{
"epoch": 1.9184,
"grad_norm": 6.27663328476831,
"learning_rate": 3.4903163764736104e-06,
"loss": 0.6262998580932617,
"step": 600
},
{
"epoch": 1.9216,
"grad_norm": 8.210577151531504,
"learning_rate": 3.4726051461105016e-06,
"loss": 0.3968774080276489,
"step": 601
},
{
"epoch": 1.9247999999999998,
"grad_norm": 5.743222930021626,
"learning_rate": 3.4549150281252635e-06,
"loss": 0.28913938999176025,
"step": 602
},
{
"epoch": 1.928,
"grad_norm": 7.807416096779423,
"learning_rate": 3.437246267039115e-06,
"loss": 0.5585134029388428,
"step": 603
},
{
"epoch": 1.9312,
"grad_norm": 9.268118509360665,
"learning_rate": 3.419599107078073e-06,
"loss": 0.5054421424865723,
"step": 604
},
{
"epoch": 1.9344000000000001,
"grad_norm": 7.046488281002558,
"learning_rate": 3.401973792169574e-06,
"loss": 0.3996657729148865,
"step": 605
},
{
"epoch": 1.9376,
"grad_norm": 7.979268431428972,
"learning_rate": 3.384370565939098e-06,
"loss": 0.4870864152908325,
"step": 606
},
{
"epoch": 1.9407999999999999,
"grad_norm": 7.484047793433678,
"learning_rate": 3.3667896717068105e-06,
"loss": 0.30252915620803833,
"step": 607
},
{
"epoch": 1.944,
"grad_norm": 7.134772084164971,
"learning_rate": 3.34923135248419e-06,
"loss": 0.4390268623828888,
"step": 608
},
{
"epoch": 1.9472,
"grad_norm": 7.183693296155156,
"learning_rate": 3.33169585097067e-06,
"loss": 0.49310848116874695,
"step": 609
},
{
"epoch": 1.9504000000000001,
"grad_norm": 8.48958718056308,
"learning_rate": 3.314183409550293e-06,
"loss": 0.5456429719924927,
"step": 610
},
{
"epoch": 1.9536,
"grad_norm": 12.647335256604812,
"learning_rate": 3.2966942702883494e-06,
"loss": 0.9464772939682007,
"step": 611
},
{
"epoch": 1.9567999999999999,
"grad_norm": 8.063285257091946,
"learning_rate": 3.279228674928035e-06,
"loss": 0.5313974618911743,
"step": 612
},
{
"epoch": 1.96,
"grad_norm": 9.345108674794647,
"learning_rate": 3.261786864887117e-06,
"loss": 0.3752167820930481,
"step": 613
},
{
"epoch": 1.9632,
"grad_norm": 6.079689599944422,
"learning_rate": 3.244369081254585e-06,
"loss": 0.4303323030471802,
"step": 614
},
{
"epoch": 1.9664000000000001,
"grad_norm": 8.575990908650828,
"learning_rate": 3.226975564787322e-06,
"loss": 0.462505966424942,
"step": 615
},
{
"epoch": 1.9696,
"grad_norm": 8.593263079809223,
"learning_rate": 3.209606555906788e-06,
"loss": 0.8094262480735779,
"step": 616
},
{
"epoch": 1.9727999999999999,
"grad_norm": 13.480603141588325,
"learning_rate": 3.192262294695679e-06,
"loss": 0.455192506313324,
"step": 617
},
{
"epoch": 1.976,
"grad_norm": 10.531989446620917,
"learning_rate": 3.174943020894618e-06,
"loss": 0.5750752687454224,
"step": 618
},
{
"epoch": 1.9792,
"grad_norm": 7.553631123493846,
"learning_rate": 3.1576489738988457e-06,
"loss": 0.35894471406936646,
"step": 619
},
{
"epoch": 1.9824000000000002,
"grad_norm": 8.540503144458707,
"learning_rate": 3.140380392754901e-06,
"loss": 0.6796849966049194,
"step": 620
},
{
"epoch": 1.9856,
"grad_norm": 8.35280964116722,
"learning_rate": 3.12313751615732e-06,
"loss": 0.46999385952949524,
"step": 621
},
{
"epoch": 1.9888,
"grad_norm": 8.568794999872507,
"learning_rate": 3.1059205824453446e-06,
"loss": 0.3941504657268524,
"step": 622
},
{
"epoch": 1.992,
"grad_norm": 6.684851255750161,
"learning_rate": 3.0887298295996183e-06,
"loss": 0.4799797236919403,
"step": 623
},
{
"epoch": 1.9952,
"grad_norm": 7.213098462732672,
"learning_rate": 3.0715654952388957e-06,
"loss": 0.27094176411628723,
"step": 624
},
{
"epoch": 1.9984,
"grad_norm": 7.927331670269777,
"learning_rate": 3.054427816616773e-06,
"loss": 0.4041209816932678,
"step": 625
},
{
"epoch": 2.0,
"grad_norm": 8.925389406817386,
"learning_rate": 3.0373170306183885e-06,
"loss": 0.3835887908935547,
"step": 626
},
{
"epoch": 2.0032,
"grad_norm": 3.6696787846966155,
"learning_rate": 3.020233373757162e-06,
"loss": 0.11996147036552429,
"step": 627
},
{
"epoch": 2.0064,
"grad_norm": 4.525868686813128,
"learning_rate": 3.0031770821715233e-06,
"loss": 0.10392191261053085,
"step": 628
},
{
"epoch": 2.0096,
"grad_norm": 3.033656690349916,
"learning_rate": 2.9861483916216404e-06,
"loss": 0.07572668790817261,
"step": 629
},
{
"epoch": 2.0128,
"grad_norm": 3.736375869488147,
"learning_rate": 2.969147537486175e-06,
"loss": 0.1307162344455719,
"step": 630
},
{
"epoch": 2.016,
"grad_norm": 4.5812754930574915,
"learning_rate": 2.952174754759012e-06,
"loss": 0.09220964461565018,
"step": 631
},
{
"epoch": 2.0192,
"grad_norm": 3.0443178212260658,
"learning_rate": 2.935230278046025e-06,
"loss": 0.06570678949356079,
"step": 632
},
{
"epoch": 2.0224,
"grad_norm": 4.088653886656501,
"learning_rate": 2.9183143415618297e-06,
"loss": 0.11156592518091202,
"step": 633
},
{
"epoch": 2.0256,
"grad_norm": 3.03243057493807,
"learning_rate": 2.9014271791265403e-06,
"loss": 0.07169395685195923,
"step": 634
},
{
"epoch": 2.0288,
"grad_norm": 5.475026508777983,
"learning_rate": 2.8845690241625437e-06,
"loss": 0.10455334186553955,
"step": 635
},
{
"epoch": 2.032,
"grad_norm": 4.683590552622473,
"learning_rate": 2.867740109691277e-06,
"loss": 0.08296695351600647,
"step": 636
},
{
"epoch": 2.0352,
"grad_norm": 5.020663964838416,
"learning_rate": 2.850940668329996e-06,
"loss": 0.07749265432357788,
"step": 637
},
{
"epoch": 2.0384,
"grad_norm": 6.536993423404543,
"learning_rate": 2.8341709322885624e-06,
"loss": 0.14159438014030457,
"step": 638
},
{
"epoch": 2.0416,
"grad_norm": 5.63144732673268,
"learning_rate": 2.817431133366246e-06,
"loss": 0.11202438175678253,
"step": 639
},
{
"epoch": 2.0448,
"grad_norm": 5.547154034396612,
"learning_rate": 2.800721502948506e-06,
"loss": 0.08011537790298462,
"step": 640
},
{
"epoch": 2.048,
"grad_norm": 4.710396977778961,
"learning_rate": 2.7840422720037943e-06,
"loss": 0.07997912913560867,
"step": 641
},
{
"epoch": 2.0512,
"grad_norm": 5.156424983682207,
"learning_rate": 2.767393671080376e-06,
"loss": 0.10096947103738785,
"step": 642
},
{
"epoch": 2.0544,
"grad_norm": 6.684726084640156,
"learning_rate": 2.7507759303031257e-06,
"loss": 0.14593079686164856,
"step": 643
},
{
"epoch": 2.0576,
"grad_norm": 5.275881838131332,
"learning_rate": 2.7341892793703594e-06,
"loss": 0.058174774050712585,
"step": 644
},
{
"epoch": 2.0608,
"grad_norm": 6.401885652816549,
"learning_rate": 2.7176339475506515e-06,
"loss": 0.13831673562526703,
"step": 645
},
{
"epoch": 2.064,
"grad_norm": 15.366451196142448,
"learning_rate": 2.7011101636796677e-06,
"loss": 0.33416709303855896,
"step": 646
},
{
"epoch": 2.0672,
"grad_norm": 4.993321072035578,
"learning_rate": 2.6846181561570085e-06,
"loss": 0.08862864971160889,
"step": 647
},
{
"epoch": 2.0704,
"grad_norm": 6.473580137498222,
"learning_rate": 2.668158152943039e-06,
"loss": 0.07409396767616272,
"step": 648
},
{
"epoch": 2.0736,
"grad_norm": 5.124105945490085,
"learning_rate": 2.651730381555754e-06,
"loss": 0.08712749928236008,
"step": 649
},
{
"epoch": 2.0768,
"grad_norm": 5.935077190092968,
"learning_rate": 2.635335069067617e-06,
"loss": 0.22049905359745026,
"step": 650
},
{
"epoch": 2.08,
"grad_norm": 5.319857253160783,
"learning_rate": 2.618972442102432e-06,
"loss": 0.12233918160200119,
"step": 651
},
{
"epoch": 2.0832,
"grad_norm": 5.153804835442563,
"learning_rate": 2.602642726832212e-06,
"loss": 0.12913931906223297,
"step": 652
},
{
"epoch": 2.0864,
"grad_norm": 4.66351603235089,
"learning_rate": 2.5863461489740403e-06,
"loss": 0.05634521692991257,
"step": 653
},
{
"epoch": 2.0896,
"grad_norm": 6.761786245650492,
"learning_rate": 2.57008293378697e-06,
"loss": 0.1739203929901123,
"step": 654
},
{
"epoch": 2.0928,
"grad_norm": 4.699874854528912,
"learning_rate": 2.553853306068888e-06,
"loss": 0.0878625139594078,
"step": 655
},
{
"epoch": 2.096,
"grad_norm": 4.698505864731701,
"learning_rate": 2.5376574901534303e-06,
"loss": 0.05961507558822632,
"step": 656
},
{
"epoch": 2.0992,
"grad_norm": 8.26543488991142,
"learning_rate": 2.5214957099068613e-06,
"loss": 0.14727714657783508,
"step": 657
},
{
"epoch": 2.1024,
"grad_norm": 4.391239804263717,
"learning_rate": 2.5053681887249916e-06,
"loss": 0.08559496700763702,
"step": 658
},
{
"epoch": 2.1056,
"grad_norm": 4.956071012404755,
"learning_rate": 2.4892751495300893e-06,
"loss": 0.07294371724128723,
"step": 659
},
{
"epoch": 2.1088,
"grad_norm": 4.9091867826378595,
"learning_rate": 2.4732168147677927e-06,
"loss": 0.10186387598514557,
"step": 660
},
{
"epoch": 2.112,
"grad_norm": 4.150563528247117,
"learning_rate": 2.4571934064040364e-06,
"loss": 0.06323671340942383,
"step": 661
},
{
"epoch": 2.1152,
"grad_norm": 4.463255280307685,
"learning_rate": 2.4412051459219945e-06,
"loss": 0.11771675944328308,
"step": 662
},
{
"epoch": 2.1184,
"grad_norm": 5.589014744071712,
"learning_rate": 2.425252254319002e-06,
"loss": 0.12130504846572876,
"step": 663
},
{
"epoch": 2.1216,
"grad_norm": 3.9085615319173317,
"learning_rate": 2.4093349521035105e-06,
"loss": 0.06084325164556503,
"step": 664
},
{
"epoch": 2.1248,
"grad_norm": 3.171680726644144,
"learning_rate": 2.3934534592920416e-06,
"loss": 0.03246958926320076,
"step": 665
},
{
"epoch": 2.128,
"grad_norm": 6.753945331539417,
"learning_rate": 2.3776079954061385e-06,
"loss": 0.09609811753034592,
"step": 666
},
{
"epoch": 2.1312,
"grad_norm": 6.030756481398649,
"learning_rate": 2.3617987794693358e-06,
"loss": 0.1699962317943573,
"step": 667
},
{
"epoch": 2.1344,
"grad_norm": 6.044337546289677,
"learning_rate": 2.3460260300041355e-06,
"loss": 0.14179761707782745,
"step": 668
},
{
"epoch": 2.1376,
"grad_norm": 3.8392076063382103,
"learning_rate": 2.3302899650289773e-06,
"loss": 0.061842452734708786,
"step": 669
},
{
"epoch": 2.1408,
"grad_norm": 4.531411032541098,
"learning_rate": 2.314590802055232e-06,
"loss": 0.1088966429233551,
"step": 670
},
{
"epoch": 2.144,
"grad_norm": 3.594842955826742,
"learning_rate": 2.2989287580841985e-06,
"loss": 0.03651595860719681,
"step": 671
},
{
"epoch": 2.1471999999999998,
"grad_norm": 4.817508345143068,
"learning_rate": 2.2833040496040925e-06,
"loss": 0.11619774997234344,
"step": 672
},
{
"epoch": 2.1504,
"grad_norm": 7.650573703632381,
"learning_rate": 2.267716892587062e-06,
"loss": 0.1421288400888443,
"step": 673
},
{
"epoch": 2.1536,
"grad_norm": 6.300220492075128,
"learning_rate": 2.252167502486205e-06,
"loss": 0.1366984248161316,
"step": 674
},
{
"epoch": 2.1568,
"grad_norm": 6.02686513882292,
"learning_rate": 2.2366560942325833e-06,
"loss": 0.06580697000026703,
"step": 675
},
{
"epoch": 2.16,
"grad_norm": 6.107958640385895,
"learning_rate": 2.2211828822322547e-06,
"loss": 0.12179602682590485,
"step": 676
},
{
"epoch": 2.1632,
"grad_norm": 6.448953912294206,
"learning_rate": 2.205748080363316e-06,
"loss": 0.10135053098201752,
"step": 677
},
{
"epoch": 2.1664,
"grad_norm": 7.221656212408016,
"learning_rate": 2.190351901972935e-06,
"loss": 0.17090697586536407,
"step": 678
},
{
"epoch": 2.1696,
"grad_norm": 5.71225349201858,
"learning_rate": 2.1749945598744076e-06,
"loss": 0.1405285894870758,
"step": 679
},
{
"epoch": 2.1728,
"grad_norm": 6.444356691669942,
"learning_rate": 2.159676266344222e-06,
"loss": 0.11138138175010681,
"step": 680
},
{
"epoch": 2.176,
"grad_norm": 4.767368668732903,
"learning_rate": 2.144397233119112e-06,
"loss": 0.07948726415634155,
"step": 681
},
{
"epoch": 2.1792,
"grad_norm": 5.253750918459062,
"learning_rate": 2.1291576713931382e-06,
"loss": 0.09645087271928787,
"step": 682
},
{
"epoch": 2.1824,
"grad_norm": 5.870766029186202,
"learning_rate": 2.1139577918147715e-06,
"loss": 0.11395483464002609,
"step": 683
},
{
"epoch": 2.1856,
"grad_norm": 4.096758645068137,
"learning_rate": 2.0987978044839707e-06,
"loss": 0.08182550966739655,
"step": 684
},
{
"epoch": 2.1888,
"grad_norm": 5.9347235653337105,
"learning_rate": 2.0836779189492925e-06,
"loss": 0.1497229039669037,
"step": 685
},
{
"epoch": 2.192,
"grad_norm": 3.906020759911345,
"learning_rate": 2.068598344204981e-06,
"loss": 0.09528996050357819,
"step": 686
},
{
"epoch": 2.1952,
"grad_norm": 5.749677047442575,
"learning_rate": 2.053559288688086e-06,
"loss": 0.1537422239780426,
"step": 687
},
{
"epoch": 2.1984,
"grad_norm": 4.435560536875201,
"learning_rate": 2.0385609602755878e-06,
"loss": 0.08181922137737274,
"step": 688
},
{
"epoch": 2.2016,
"grad_norm": 5.342641944412979,
"learning_rate": 2.02360356628151e-06,
"loss": 0.11698771268129349,
"step": 689
},
{
"epoch": 2.2048,
"grad_norm": 3.846845894711269,
"learning_rate": 2.0086873134540626e-06,
"loss": 0.14168213307857513,
"step": 690
},
{
"epoch": 2.208,
"grad_norm": 5.624553439494294,
"learning_rate": 1.9938124079727874e-06,
"loss": 0.09469903260469437,
"step": 691
},
{
"epoch": 2.2112,
"grad_norm": 4.973173648515756,
"learning_rate": 1.9789790554456977e-06,
"loss": 0.10835753381252289,
"step": 692
},
{
"epoch": 2.2144,
"grad_norm": 5.1930553937123936,
"learning_rate": 1.9641874609064443e-06,
"loss": 0.11629842221736908,
"step": 693
},
{
"epoch": 2.2176,
"grad_norm": 6.205457238508838,
"learning_rate": 1.9494378288114816e-06,
"loss": 0.11438259482383728,
"step": 694
},
{
"epoch": 2.2208,
"grad_norm": 5.369211423853327,
"learning_rate": 1.9347303630372373e-06,
"loss": 0.1212492436170578,
"step": 695
},
{
"epoch": 2.224,
"grad_norm": 3.3304223352399185,
"learning_rate": 1.9200652668772924e-06,
"loss": 0.04342126473784447,
"step": 696
},
{
"epoch": 2.2272,
"grad_norm": 3.545011123467542,
"learning_rate": 1.9054427430395828e-06,
"loss": 0.09564132988452911,
"step": 697
},
{
"epoch": 2.2304,
"grad_norm": 4.809787829193569,
"learning_rate": 1.890862993643583e-06,
"loss": 0.13682125508785248,
"step": 698
},
{
"epoch": 2.2336,
"grad_norm": 6.123550310826348,
"learning_rate": 1.8763262202175204e-06,
"loss": 0.1395423710346222,
"step": 699
},
{
"epoch": 2.2368,
"grad_norm": 7.055949453049508,
"learning_rate": 1.8618326236955908e-06,
"loss": 0.15431663393974304,
"step": 700
},
{
"epoch": 2.24,
"grad_norm": 4.791237282938236,
"learning_rate": 1.8473824044151762e-06,
"loss": 0.1401059627532959,
"step": 701
},
{
"epoch": 2.2432,
"grad_norm": 5.4420427947229895,
"learning_rate": 1.8329757621140748e-06,
"loss": 0.09011302143335342,
"step": 702
},
{
"epoch": 2.2464,
"grad_norm": 6.550722463045357,
"learning_rate": 1.81861289592775e-06,
"loss": 0.10779771208763123,
"step": 703
},
{
"epoch": 2.2496,
"grad_norm": 6.106268968400953,
"learning_rate": 1.8042940043865658e-06,
"loss": 0.13367201387882233,
"step": 704
},
{
"epoch": 2.2528,
"grad_norm": 5.494609125221687,
"learning_rate": 1.7900192854130465e-06,
"loss": 0.12417173385620117,
"step": 705
},
{
"epoch": 2.2560000000000002,
"grad_norm": 4.068204210271371,
"learning_rate": 1.7757889363191484e-06,
"loss": 0.08244695514440536,
"step": 706
},
{
"epoch": 2.2592,
"grad_norm": 2.7453827328709957,
"learning_rate": 1.7616031538035189e-06,
"loss": 0.05444292724132538,
"step": 707
},
{
"epoch": 2.2624,
"grad_norm": 6.2577921697828724,
"learning_rate": 1.7474621339487925e-06,
"loss": 0.11946985125541687,
"step": 708
},
{
"epoch": 2.2656,
"grad_norm": 4.994947590574668,
"learning_rate": 1.7333660722188667e-06,
"loss": 0.15361633896827698,
"step": 709
},
{
"epoch": 2.2688,
"grad_norm": 6.062884608603293,
"learning_rate": 1.7193151634562071e-06,
"loss": 0.17315593361854553,
"step": 710
},
{
"epoch": 2.2720000000000002,
"grad_norm": 4.8609104632230835,
"learning_rate": 1.7053096018791588e-06,
"loss": 0.09136267006397247,
"step": 711
},
{
"epoch": 2.2752,
"grad_norm": 5.867454619937701,
"learning_rate": 1.691349581079249e-06,
"loss": 0.12086353451013565,
"step": 712
},
{
"epoch": 2.2784,
"grad_norm": 5.892173551588763,
"learning_rate": 1.6774352940185269e-06,
"loss": 0.10306617617607117,
"step": 713
},
{
"epoch": 2.2816,
"grad_norm": 4.150966492737294,
"learning_rate": 1.663566933026879e-06,
"loss": 0.07620586454868317,
"step": 714
},
{
"epoch": 2.2848,
"grad_norm": 5.432625327839043,
"learning_rate": 1.6497446897993885e-06,
"loss": 0.12006257474422455,
"step": 715
},
{
"epoch": 2.288,
"grad_norm": 6.1988544472798015,
"learning_rate": 1.6359687553936714e-06,
"loss": 0.06950559467077255,
"step": 716
},
{
"epoch": 2.2912,
"grad_norm": 3.6222193166168757,
"learning_rate": 1.6222393202272414e-06,
"loss": 0.07582759112119675,
"step": 717
},
{
"epoch": 2.2944,
"grad_norm": 4.460271899357273,
"learning_rate": 1.6085565740748825e-06,
"loss": 0.07245473563671112,
"step": 718
},
{
"epoch": 2.2976,
"grad_norm": 5.026948482587842,
"learning_rate": 1.5949207060660138e-06,
"loss": 0.09753254055976868,
"step": 719
},
{
"epoch": 2.3008,
"grad_norm": 4.870544354743463,
"learning_rate": 1.581331904682089e-06,
"loss": 0.06839516013860703,
"step": 720
},
{
"epoch": 2.304,
"grad_norm": 3.534009364026584,
"learning_rate": 1.5677903577539806e-06,
"loss": 0.06540823727846146,
"step": 721
},
{
"epoch": 2.3072,
"grad_norm": 5.0733570772826955,
"learning_rate": 1.5542962524593869e-06,
"loss": 0.10535422712564468,
"step": 722
},
{
"epoch": 2.3104,
"grad_norm": 3.6068016602853503,
"learning_rate": 1.54084977532025e-06,
"loss": 0.0575660765171051,
"step": 723
},
{
"epoch": 2.3136,
"grad_norm": 5.042780505809956,
"learning_rate": 1.5274511122001684e-06,
"loss": 0.11762597411870956,
"step": 724
},
{
"epoch": 2.3168,
"grad_norm": 5.134362812746946,
"learning_rate": 1.5141004483018323e-06,
"loss": 0.06998032331466675,
"step": 725
},
{
"epoch": 2.32,
"grad_norm": 5.5498922740758445,
"learning_rate": 1.5007979681644696e-06,
"loss": 0.05732321739196777,
"step": 726
},
{
"epoch": 2.3232,
"grad_norm": 5.99070604809497,
"learning_rate": 1.4875438556612836e-06,
"loss": 0.17882873117923737,
"step": 727
},
{
"epoch": 2.3264,
"grad_norm": 4.830442342633692,
"learning_rate": 1.474338293996917e-06,
"loss": 0.13739310204982758,
"step": 728
},
{
"epoch": 2.3296,
"grad_norm": 4.180068798814137,
"learning_rate": 1.4611814657049257e-06,
"loss": 0.05291110277175903,
"step": 729
},
{
"epoch": 2.3327999999999998,
"grad_norm": 5.138435902318426,
"learning_rate": 1.4480735526452427e-06,
"loss": 0.06695031374692917,
"step": 730
},
{
"epoch": 2.336,
"grad_norm": 3.91474389316094,
"learning_rate": 1.4350147360016743e-06,
"loss": 0.05291609838604927,
"step": 731
},
{
"epoch": 2.3392,
"grad_norm": 5.542625247698976,
"learning_rate": 1.4220051962793952e-06,
"loss": 0.07234814018011093,
"step": 732
},
{
"epoch": 2.3424,
"grad_norm": 6.566917111647726,
"learning_rate": 1.4090451133024473e-06,
"loss": 0.1104026734828949,
"step": 733
},
{
"epoch": 2.3456,
"grad_norm": 2.9910147365026503,
"learning_rate": 1.3961346662112585e-06,
"loss": 0.045543380081653595,
"step": 734
},
{
"epoch": 2.3487999999999998,
"grad_norm": 4.8443437357951895,
"learning_rate": 1.3832740334601692e-06,
"loss": 0.11693132668733597,
"step": 735
},
{
"epoch": 2.352,
"grad_norm": 4.238193407388062,
"learning_rate": 1.3704633928149575e-06,
"loss": 0.10108187794685364,
"step": 736
},
{
"epoch": 2.3552,
"grad_norm": 2.8297398748345053,
"learning_rate": 1.3577029213503911e-06,
"loss": 0.04281865805387497,
"step": 737
},
{
"epoch": 2.3584,
"grad_norm": 5.035788948623994,
"learning_rate": 1.3449927954477732e-06,
"loss": 0.11006296426057816,
"step": 738
},
{
"epoch": 2.3616,
"grad_norm": 3.855141269509382,
"learning_rate": 1.3323331907925046e-06,
"loss": 0.06673809140920639,
"step": 739
},
{
"epoch": 2.3648,
"grad_norm": 4.868399649302668,
"learning_rate": 1.319724282371664e-06,
"loss": 0.09489268809556961,
"step": 740
},
{
"epoch": 2.368,
"grad_norm": 7.517296359964302,
"learning_rate": 1.307166244471576e-06,
"loss": 0.18027102947235107,
"step": 741
},
{
"epoch": 2.3712,
"grad_norm": 4.443750597623774,
"learning_rate": 1.2946592506754097e-06,
"loss": 0.09601432085037231,
"step": 742
},
{
"epoch": 2.3744,
"grad_norm": 3.7507062386771826,
"learning_rate": 1.282203473860783e-06,
"loss": 0.07339777052402496,
"step": 743
},
{
"epoch": 2.3776,
"grad_norm": 5.379526848435967,
"learning_rate": 1.2697990861973635e-06,
"loss": 0.10539920628070831,
"step": 744
},
{
"epoch": 2.3808,
"grad_norm": 5.168657979668781,
"learning_rate": 1.257446259144494e-06,
"loss": 0.10802607238292694,
"step": 745
},
{
"epoch": 2.384,
"grad_norm": 10.88801203756203,
"learning_rate": 1.2451451634488264e-06,
"loss": 0.17059877514839172,
"step": 746
},
{
"epoch": 2.3872,
"grad_norm": 6.506653697708005,
"learning_rate": 1.2328959691419517e-06,
"loss": 0.10177908837795258,
"step": 747
},
{
"epoch": 2.3904,
"grad_norm": 7.06876194771458,
"learning_rate": 1.2206988455380558e-06,
"loss": 0.14067994058132172,
"step": 748
},
{
"epoch": 2.3936,
"grad_norm": 5.459049161009346,
"learning_rate": 1.2085539612315844e-06,
"loss": 0.09186317026615143,
"step": 749
},
{
"epoch": 2.3968,
"grad_norm": 4.853909602574328,
"learning_rate": 1.1964614840949002e-06,
"loss": 0.09414474666118622,
"step": 750
},
{
"epoch": 2.4,
"grad_norm": 5.701034512876923,
"learning_rate": 1.1844215812759708e-06,
"loss": 0.07064532488584518,
"step": 751
},
{
"epoch": 2.4032,
"grad_norm": 4.225475376304274,
"learning_rate": 1.1724344191960591e-06,
"loss": 0.09624212980270386,
"step": 752
},
{
"epoch": 2.4064,
"grad_norm": 6.831160922735881,
"learning_rate": 1.1605001635474183e-06,
"loss": 0.13697776198387146,
"step": 753
},
{
"epoch": 2.4096,
"grad_norm": 5.410920242544437,
"learning_rate": 1.1486189792910024e-06,
"loss": 0.09551814943552017,
"step": 754
},
{
"epoch": 2.4128,
"grad_norm": 6.943374658941839,
"learning_rate": 1.1367910306541918e-06,
"loss": 0.11858892440795898,
"step": 755
},
{
"epoch": 2.416,
"grad_norm": 4.011544255361457,
"learning_rate": 1.1250164811285148e-06,
"loss": 0.1095619648694992,
"step": 756
},
{
"epoch": 2.4192,
"grad_norm": 8.17865472562301,
"learning_rate": 1.1132954934673911e-06,
"loss": 0.1675768792629242,
"step": 757
},
{
"epoch": 2.4224,
"grad_norm": 3.6499383545129014,
"learning_rate": 1.1016282296838887e-06,
"loss": 0.04391354322433472,
"step": 758
},
{
"epoch": 2.4256,
"grad_norm": 4.52344799617554,
"learning_rate": 1.090014851048473e-06,
"loss": 0.06339210271835327,
"step": 759
},
{
"epoch": 2.4288,
"grad_norm": 5.662883659435518,
"learning_rate": 1.078455518086784e-06,
"loss": 0.14258350431919098,
"step": 760
},
{
"epoch": 2.432,
"grad_norm": 6.097256574924503,
"learning_rate": 1.0669503905774198e-06,
"loss": 0.06327582895755768,
"step": 761
},
{
"epoch": 2.4352,
"grad_norm": 6.492617704409979,
"learning_rate": 1.055499627549722e-06,
"loss": 0.10183501988649368,
"step": 762
},
{
"epoch": 2.4384,
"grad_norm": 6.02086878331262,
"learning_rate": 1.0441033872815804e-06,
"loss": 0.07817564904689789,
"step": 763
},
{
"epoch": 2.4416,
"grad_norm": 8.346456202456045,
"learning_rate": 1.0327618272972484e-06,
"loss": 0.09021017700433731,
"step": 764
},
{
"epoch": 2.4448,
"grad_norm": 5.293217633696834,
"learning_rate": 1.0214751043651582e-06,
"loss": 0.13087089359760284,
"step": 765
},
{
"epoch": 2.448,
"grad_norm": 5.87700949157379,
"learning_rate": 1.010243374495763e-06,
"loss": 0.12380192428827286,
"step": 766
},
{
"epoch": 2.4512,
"grad_norm": 5.808186222788822,
"learning_rate": 9.990667929393715e-07,
"loss": 0.12605151534080505,
"step": 767
},
{
"epoch": 2.4544,
"grad_norm": 5.151183159264049,
"learning_rate": 9.879455141840067e-07,
"loss": 0.0865304172039032,
"step": 768
},
{
"epoch": 2.4576000000000002,
"grad_norm": 5.4129462450659505,
"learning_rate": 9.768796919532742e-07,
"loss": 0.08209861814975739,
"step": 769
},
{
"epoch": 2.4608,
"grad_norm": 5.068584123988632,
"learning_rate": 9.658694792042284e-07,
"loss": 0.11468471586704254,
"step": 770
},
{
"epoch": 2.464,
"grad_norm": 4.844978102081947,
"learning_rate": 9.549150281252633e-07,
"loss": 0.08285008370876312,
"step": 771
},
{
"epoch": 2.4672,
"grad_norm": 5.068349498921108,
"learning_rate": 9.440164901340127e-07,
"loss": 0.10419681668281555,
"step": 772
},
{
"epoch": 2.4704,
"grad_norm": 3.1625623661687032,
"learning_rate": 9.331740158752495e-07,
"loss": 0.04847210645675659,
"step": 773
},
{
"epoch": 2.4736000000000002,
"grad_norm": 4.874535469808533,
"learning_rate": 9.223877552188065e-07,
"loss": 0.03893538564443588,
"step": 774
},
{
"epoch": 2.4768,
"grad_norm": 4.619975687019092,
"learning_rate": 9.116578572575091e-07,
"loss": 0.07748477160930634,
"step": 775
},
{
"epoch": 2.48,
"grad_norm": 2.92604082395473,
"learning_rate": 9.009844703051063e-07,
"loss": 0.041283268481492996,
"step": 776
},
{
"epoch": 2.4832,
"grad_norm": 5.393054740107025,
"learning_rate": 8.903677418942292e-07,
"loss": 0.136105015873909,
"step": 777
},
{
"epoch": 2.4864,
"grad_norm": 5.693089364156197,
"learning_rate": 8.79807818774343e-07,
"loss": 0.09653803706169128,
"step": 778
},
{
"epoch": 2.4896,
"grad_norm": 5.2367755231685535,
"learning_rate": 8.693048469097293e-07,
"loss": 0.1141771450638771,
"step": 779
},
{
"epoch": 2.4928,
"grad_norm": 6.220753165757646,
"learning_rate": 8.58858971477457e-07,
"loss": 0.10124068707227707,
"step": 780
},
{
"epoch": 2.496,
"grad_norm": 6.699744425384384,
"learning_rate": 8.484703368653812e-07,
"loss": 0.18161731958389282,
"step": 781
},
{
"epoch": 2.4992,
"grad_norm": 3.2719510580915094,
"learning_rate": 8.381390866701517e-07,
"loss": 0.07561002671718597,
"step": 782
},
{
"epoch": 2.5023999999999997,
"grad_norm": 4.0750793358019175,
"learning_rate": 8.278653636952177e-07,
"loss": 0.07349054515361786,
"step": 783
},
{
"epoch": 2.5056000000000003,
"grad_norm": 3.853945091772515,
"learning_rate": 8.176493099488664e-07,
"loss": 0.07924634218215942,
"step": 784
},
{
"epoch": 2.5088,
"grad_norm": 3.9708605790822973,
"learning_rate": 8.074910666422475e-07,
"loss": 0.06928728520870209,
"step": 785
},
{
"epoch": 2.512,
"grad_norm": 3.640343605257409,
"learning_rate": 7.973907741874287e-07,
"loss": 0.07105650752782822,
"step": 786
},
{
"epoch": 2.5152,
"grad_norm": 4.302121204890136,
"learning_rate": 7.873485721954572e-07,
"loss": 0.10211469233036041,
"step": 787
},
{
"epoch": 2.5183999999999997,
"grad_norm": 4.308262119474157,
"learning_rate": 7.773645994744222e-07,
"loss": 0.08780980855226517,
"step": 788
},
{
"epoch": 2.5216,
"grad_norm": 4.547313783660713,
"learning_rate": 7.674389940275406e-07,
"loss": 0.08024639636278152,
"step": 789
},
{
"epoch": 2.5248,
"grad_norm": 5.334742625561698,
"learning_rate": 7.575718930512516e-07,
"loss": 0.11789308488368988,
"step": 790
},
{
"epoch": 2.528,
"grad_norm": 3.9018912781819983,
"learning_rate": 7.47763432933315e-07,
"loss": 0.06020133197307587,
"step": 791
},
{
"epoch": 2.5312,
"grad_norm": 5.221747350625461,
"learning_rate": 7.380137492509309e-07,
"loss": 0.12893611192703247,
"step": 792
},
{
"epoch": 2.5343999999999998,
"grad_norm": 4.252973698980377,
"learning_rate": 7.283229767688627e-07,
"loss": 0.07680028676986694,
"step": 793
},
{
"epoch": 2.5376,
"grad_norm": 3.179449105684439,
"learning_rate": 7.186912494375736e-07,
"loss": 0.04430155083537102,
"step": 794
},
{
"epoch": 2.5408,
"grad_norm": 4.187638577055214,
"learning_rate": 7.091187003913802e-07,
"loss": 0.0837840884923935,
"step": 795
},
{
"epoch": 2.544,
"grad_norm": 4.67528134834416,
"learning_rate": 6.996054619466053e-07,
"loss": 0.10668416321277618,
"step": 796
},
{
"epoch": 2.5472,
"grad_norm": 5.167138261403643,
"learning_rate": 6.901516655997536e-07,
"loss": 0.08135296404361725,
"step": 797
},
{
"epoch": 2.5504,
"grad_norm": 3.531241276260812,
"learning_rate": 6.80757442025694e-07,
"loss": 0.05354129523038864,
"step": 798
},
{
"epoch": 2.5536,
"grad_norm": 3.2277596569432947,
"learning_rate": 6.714229210758516e-07,
"loss": 0.058047980070114136,
"step": 799
},
{
"epoch": 2.5568,
"grad_norm": 5.901204699020555,
"learning_rate": 6.621482317764105e-07,
"loss": 0.16003961861133575,
"step": 800
},
{
"epoch": 2.56,
"grad_norm": 3.8324224758212724,
"learning_rate": 6.529335023265387e-07,
"loss": 0.05353522300720215,
"step": 801
},
{
"epoch": 2.5632,
"grad_norm": 7.073082353236605,
"learning_rate": 6.437788600966066e-07,
"loss": 0.12031964212656021,
"step": 802
},
{
"epoch": 2.5664,
"grad_norm": 4.558795574006864,
"learning_rate": 6.346844316264312e-07,
"loss": 0.08245455473661423,
"step": 803
},
{
"epoch": 2.5696,
"grad_norm": 5.696560344883344,
"learning_rate": 6.256503426235277e-07,
"loss": 0.10456888377666473,
"step": 804
},
{
"epoch": 2.5728,
"grad_norm": 4.587213807091814,
"learning_rate": 6.166767179613691e-07,
"loss": 0.06099589914083481,
"step": 805
},
{
"epoch": 2.576,
"grad_norm": 3.6312702846358236,
"learning_rate": 6.077636816776611e-07,
"loss": 0.060435544699430466,
"step": 806
},
{
"epoch": 2.5792,
"grad_norm": 5.159232812533308,
"learning_rate": 5.989113569726312e-07,
"loss": 0.10681406408548355,
"step": 807
},
{
"epoch": 2.5824,
"grad_norm": 6.647332164624498,
"learning_rate": 5.901198662073188e-07,
"loss": 0.18219977617263794,
"step": 808
},
{
"epoch": 2.5856,
"grad_norm": 5.048494011845977,
"learning_rate": 5.813893309018881e-07,
"loss": 0.13821908831596375,
"step": 809
},
{
"epoch": 2.5888,
"grad_norm": 4.846199848264473,
"learning_rate": 5.727198717339511e-07,
"loss": 0.09387294948101044,
"step": 810
},
{
"epoch": 2.592,
"grad_norm": 6.330368563148582,
"learning_rate": 5.641116085368931e-07,
"loss": 0.12654753029346466,
"step": 811
},
{
"epoch": 2.5952,
"grad_norm": 4.983682635451174,
"learning_rate": 5.555646602982207e-07,
"loss": 0.054955482482910156,
"step": 812
},
{
"epoch": 2.5984,
"grad_norm": 5.337337985366779,
"learning_rate": 5.470791451579172e-07,
"loss": 0.11604686081409454,
"step": 813
},
{
"epoch": 2.6016,
"grad_norm": 4.774234054999309,
"learning_rate": 5.386551804068063e-07,
"loss": 0.07480829954147339,
"step": 814
},
{
"epoch": 2.6048,
"grad_norm": 5.67616606913421,
"learning_rate": 5.302928824849335e-07,
"loss": 0.08432568609714508,
"step": 815
},
{
"epoch": 2.608,
"grad_norm": 6.669876648378904,
"learning_rate": 5.219923669799587e-07,
"loss": 0.10097655653953552,
"step": 816
},
{
"epoch": 2.6112,
"grad_norm": 4.785192140569578,
"learning_rate": 5.137537486255517e-07,
"loss": 0.09213853627443314,
"step": 817
},
{
"epoch": 2.6144,
"grad_norm": 12.887457114172935,
"learning_rate": 5.055771412998122e-07,
"loss": 0.09667956829071045,
"step": 818
},
{
"epoch": 2.6176,
"grad_norm": 5.686077115139262,
"learning_rate": 4.974626580236957e-07,
"loss": 0.08253185451030731,
"step": 819
},
{
"epoch": 2.6208,
"grad_norm": 5.213664957325537,
"learning_rate": 4.894104109594466e-07,
"loss": 0.10998277366161346,
"step": 820
},
{
"epoch": 2.624,
"grad_norm": 4.1341620316686924,
"learning_rate": 4.814205114090543e-07,
"loss": 0.08224129676818848,
"step": 821
},
{
"epoch": 2.6272,
"grad_norm": 4.531631823362974,
"learning_rate": 4.734930698127077e-07,
"loss": 0.09060163795948029,
"step": 822
},
{
"epoch": 2.6304,
"grad_norm": 3.918488960881494,
"learning_rate": 4.6562819574727304e-07,
"loss": 0.06134440377354622,
"step": 823
},
{
"epoch": 2.6336,
"grad_norm": 4.088829148724274,
"learning_rate": 4.578259979247801e-07,
"loss": 0.08996803313493729,
"step": 824
},
{
"epoch": 2.6368,
"grad_norm": 3.8607902988831206,
"learning_rate": 4.500865841909169e-07,
"loss": 0.04868876188993454,
"step": 825
},
{
"epoch": 2.64,
"grad_norm": 6.376083407800039,
"learning_rate": 4.4241006152353885e-07,
"loss": 0.5533008575439453,
"step": 826
},
{
"epoch": 2.6432,
"grad_norm": 6.219934828074983,
"learning_rate": 4.3479653603119287e-07,
"loss": 0.12393755465745926,
"step": 827
},
{
"epoch": 2.6464,
"grad_norm": 5.88163203033371,
"learning_rate": 4.2724611295164755e-07,
"loss": 0.12869954109191895,
"step": 828
},
{
"epoch": 2.6496,
"grad_norm": 2.8670150880763425,
"learning_rate": 4.197588966504401e-07,
"loss": 0.06858257204294205,
"step": 829
},
{
"epoch": 2.6528,
"grad_norm": 5.8230781250099355,
"learning_rate": 4.123349906194357e-07,
"loss": 0.08777829259634018,
"step": 830
},
{
"epoch": 2.656,
"grad_norm": 3.9293889102506667,
"learning_rate": 4.0497449747539217e-07,
"loss": 0.06030702218413353,
"step": 831
},
{
"epoch": 2.6592000000000002,
"grad_norm": 6.72925262950812,
"learning_rate": 3.9767751895854467e-07,
"loss": 0.11489322781562805,
"step": 832
},
{
"epoch": 2.6624,
"grad_norm": 4.884107661803806,
"learning_rate": 3.904441559312006e-07,
"loss": 0.10746165364980698,
"step": 833
},
{
"epoch": 2.6656,
"grad_norm": 5.602826417452112,
"learning_rate": 3.8327450837634284e-07,
"loss": 0.08274800330400467,
"step": 834
},
{
"epoch": 2.6688,
"grad_norm": 6.784555867087458,
"learning_rate": 3.7616867539624733e-07,
"loss": 0.0792284607887268,
"step": 835
},
{
"epoch": 2.672,
"grad_norm": 4.382084970128556,
"learning_rate": 3.691267552111183e-07,
"loss": 0.07785268872976303,
"step": 836
},
{
"epoch": 2.6752000000000002,
"grad_norm": 5.3642679105191045,
"learning_rate": 3.621488451577221e-07,
"loss": 0.08154767751693726,
"step": 837
},
{
"epoch": 2.6784,
"grad_norm": 4.455268403353234,
"learning_rate": 3.552350416880507e-07,
"loss": 0.08759278804063797,
"step": 838
},
{
"epoch": 2.6816,
"grad_norm": 4.890874276873109,
"learning_rate": 3.483854403679832e-07,
"loss": 0.08747395873069763,
"step": 839
},
{
"epoch": 2.6848,
"grad_norm": 3.414803190746504,
"learning_rate": 3.416001358759635e-07,
"loss": 0.05378187075257301,
"step": 840
},
{
"epoch": 2.6879999999999997,
"grad_norm": 4.214372107625873,
"learning_rate": 3.3487922200169944e-07,
"loss": 0.05643921345472336,
"step": 841
},
{
"epoch": 2.6912000000000003,
"grad_norm": 4.678631918928488,
"learning_rate": 3.2822279164485494e-07,
"loss": 0.08409986644983292,
"step": 842
},
{
"epoch": 2.6944,
"grad_norm": 4.4898335138859204,
"learning_rate": 3.2163093681377765e-07,
"loss": 0.09269889444112778,
"step": 843
},
{
"epoch": 2.6976,
"grad_norm": 5.792458748078186,
"learning_rate": 3.151037486242181e-07,
"loss": 0.11759718507528305,
"step": 844
},
{
"epoch": 2.7008,
"grad_norm": 5.161229138155429,
"learning_rate": 3.08641317298074e-07,
"loss": 0.14189603924751282,
"step": 845
},
{
"epoch": 2.7039999999999997,
"grad_norm": 3.8712622879349654,
"learning_rate": 3.022437321621452e-07,
"loss": 0.08138757944107056,
"step": 846
},
{
"epoch": 2.7072000000000003,
"grad_norm": 5.041797515047301,
"learning_rate": 2.959110816468935e-07,
"loss": 0.09337767958641052,
"step": 847
},
{
"epoch": 2.7104,
"grad_norm": 5.201198943760548,
"learning_rate": 2.896434532852277e-07,
"loss": 0.1141236275434494,
"step": 848
},
{
"epoch": 2.7136,
"grad_norm": 6.691835246317423,
"learning_rate": 2.834409337112842e-07,
"loss": 0.11867150664329529,
"step": 849
},
{
"epoch": 2.7168,
"grad_norm": 3.792971355121214,
"learning_rate": 2.7730360865923954e-07,
"loss": 0.06238650158047676,
"step": 850
},
{
"epoch": 2.7199999999999998,
"grad_norm": 4.9855904224915255,
"learning_rate": 2.712315629621176e-07,
"loss": 0.09140697866678238,
"step": 851
},
{
"epoch": 2.7232,
"grad_norm": 5.099509790835439,
"learning_rate": 2.6522488055062076e-07,
"loss": 0.17426876723766327,
"step": 852
},
{
"epoch": 2.7264,
"grad_norm": 7.019145608185476,
"learning_rate": 2.5928364445196975e-07,
"loss": 0.1029796227812767,
"step": 853
},
{
"epoch": 2.7296,
"grad_norm": 4.55381734355966,
"learning_rate": 2.534079367887549e-07,
"loss": 0.05041209235787392,
"step": 854
},
{
"epoch": 2.7328,
"grad_norm": 5.058506134416135,
"learning_rate": 2.475978387778e-07,
"loss": 0.10950443148612976,
"step": 855
},
{
"epoch": 2.7359999999999998,
"grad_norm": 4.927007604916832,
"learning_rate": 2.4185343072904376e-07,
"loss": 0.11046621948480606,
"step": 856
},
{
"epoch": 2.7392,
"grad_norm": 4.645862831777831,
"learning_rate": 2.3617479204442462e-07,
"loss": 0.09512713551521301,
"step": 857
},
{
"epoch": 2.7424,
"grad_norm": 4.715134017738007,
"learning_rate": 2.305620012167853e-07,
"loss": 0.1317645162343979,
"step": 858
},
{
"epoch": 2.7456,
"grad_norm": 4.172825091167619,
"learning_rate": 2.2501513582879108e-07,
"loss": 0.09508270770311356,
"step": 859
},
{
"epoch": 2.7488,
"grad_norm": 6.365380885327864,
"learning_rate": 2.1953427255185122e-07,
"loss": 0.15742623805999756,
"step": 860
},
{
"epoch": 2.752,
"grad_norm": 4.7911655395733606,
"learning_rate": 2.1411948714506414e-07,
"loss": 0.09890823066234589,
"step": 861
},
{
"epoch": 2.7552,
"grad_norm": 4.706980448081932,
"learning_rate": 2.0877085445416889e-07,
"loss": 0.07184596359729767,
"step": 862
},
{
"epoch": 2.7584,
"grad_norm": 5.914603913016412,
"learning_rate": 2.034884484105093e-07,
"loss": 0.14604350924491882,
"step": 863
},
{
"epoch": 2.7616,
"grad_norm": 8.410573869539732,
"learning_rate": 1.98272342030012e-07,
"loss": 0.24116627871990204,
"step": 864
},
{
"epoch": 2.7648,
"grad_norm": 6.398832671810751,
"learning_rate": 1.9312260741218114e-07,
"loss": 0.0800832137465477,
"step": 865
},
{
"epoch": 2.768,
"grad_norm": 4.579455858957462,
"learning_rate": 1.8803931573909584e-07,
"loss": 0.1112121194601059,
"step": 866
},
{
"epoch": 2.7712,
"grad_norm": 3.494963830618945,
"learning_rate": 1.8302253727443041e-07,
"loss": 0.056444257497787476,
"step": 867
},
{
"epoch": 2.7744,
"grad_norm": 3.573538905236335,
"learning_rate": 1.7807234136248296e-07,
"loss": 0.05214056372642517,
"step": 868
},
{
"epoch": 2.7776,
"grad_norm": 5.010204343123873,
"learning_rate": 1.731887964272144e-07,
"loss": 0.09860917180776596,
"step": 869
},
{
"epoch": 2.7808,
"grad_norm": 4.816662522386438,
"learning_rate": 1.6837196997130434e-07,
"loss": 0.07981070131063461,
"step": 870
},
{
"epoch": 2.784,
"grad_norm": 4.576350976116394,
"learning_rate": 1.6362192857521942e-07,
"loss": 0.09621265530586243,
"step": 871
},
{
"epoch": 2.7872,
"grad_norm": 5.670009488363537,
"learning_rate": 1.5893873789628812e-07,
"loss": 0.19886067509651184,
"step": 872
},
{
"epoch": 2.7904,
"grad_norm": 3.6510168385477657,
"learning_rate": 1.5432246266780083e-07,
"loss": 0.06333699822425842,
"step": 873
},
{
"epoch": 2.7936,
"grad_norm": 4.505577754745766,
"learning_rate": 1.4977316669810782e-07,
"loss": 0.0873306542634964,
"step": 874
},
{
"epoch": 2.7968,
"grad_norm": 5.092498083811537,
"learning_rate": 1.4529091286973994e-07,
"loss": 0.09957022964954376,
"step": 875
},
{
"epoch": 2.8,
"grad_norm": 3.8356935709166895,
"learning_rate": 1.4087576313854212e-07,
"loss": 0.045311711728572845,
"step": 876
},
{
"epoch": 2.8032,
"grad_norm": 3.688765051401209,
"learning_rate": 1.365277785328123e-07,
"loss": 0.06849552690982819,
"step": 877
},
{
"epoch": 2.8064,
"grad_norm": 5.2503433933764425,
"learning_rate": 1.3224701915246053e-07,
"loss": 0.09803561866283417,
"step": 878
},
{
"epoch": 2.8096,
"grad_norm": 4.361830484953425,
"learning_rate": 1.280335441681796e-07,
"loss": 0.0886538177728653,
"step": 879
},
{
"epoch": 2.8128,
"grad_norm": 5.031427873320053,
"learning_rate": 1.2388741182062348e-07,
"loss": 0.10888531059026718,
"step": 880
},
{
"epoch": 2.816,
"grad_norm": 5.302368605213448,
"learning_rate": 1.198086794196035e-07,
"loss": 0.09809792041778564,
"step": 881
},
{
"epoch": 2.8192,
"grad_norm": 4.374814290647814,
"learning_rate": 1.1579740334330014e-07,
"loss": 0.09694273769855499,
"step": 882
},
{
"epoch": 2.8224,
"grad_norm": 6.119239783240622,
"learning_rate": 1.1185363903747748e-07,
"loss": 0.08512193709611893,
"step": 883
},
{
"epoch": 2.8256,
"grad_norm": 3.945935449802739,
"learning_rate": 1.0797744101472052e-07,
"loss": 0.05518460273742676,
"step": 884
},
{
"epoch": 2.8288,
"grad_norm": 4.26544181969666,
"learning_rate": 1.0416886285368188e-07,
"loss": 0.08117370307445526,
"step": 885
},
{
"epoch": 2.832,
"grad_norm": 8.417107803278832,
"learning_rate": 1.0042795719833964e-07,
"loss": 0.18891701102256775,
"step": 886
},
{
"epoch": 2.8352,
"grad_norm": 6.157564227583656,
"learning_rate": 9.675477575726954e-08,
"loss": 0.07360401749610901,
"step": 887
},
{
"epoch": 2.8384,
"grad_norm": 4.168193829425873,
"learning_rate": 9.314936930293283e-08,
"loss": 0.06772521138191223,
"step": 888
},
{
"epoch": 2.8416,
"grad_norm": 4.489063568415961,
"learning_rate": 8.961178767097178e-08,
"loss": 0.09246842563152313,
"step": 889
},
{
"epoch": 2.8448,
"grad_norm": 4.039066368305648,
"learning_rate": 8.614207975952083e-08,
"loss": 0.10015315562486649,
"step": 890
},
{
"epoch": 2.848,
"grad_norm": 5.612972639879038,
"learning_rate": 8.274029352853264e-08,
"loss": 0.16348965466022491,
"step": 891
},
{
"epoch": 2.8512,
"grad_norm": 3.329092188649537,
"learning_rate": 7.940647599911477e-08,
"loss": 0.043626099824905396,
"step": 892
},
{
"epoch": 2.8544,
"grad_norm": 7.0831125545836695,
"learning_rate": 7.614067325287632e-08,
"loss": 0.10901731252670288,
"step": 893
},
{
"epoch": 2.8576,
"grad_norm": 2.982607780144671,
"learning_rate": 7.294293043129785e-08,
"loss": 0.03991899639368057,
"step": 894
},
{
"epoch": 2.8608000000000002,
"grad_norm": 4.998673932267322,
"learning_rate": 6.981329173509909e-08,
"loss": 0.08470803499221802,
"step": 895
},
{
"epoch": 2.864,
"grad_norm": 4.870997890379601,
"learning_rate": 6.675180042363505e-08,
"loss": 0.07652558386325836,
"step": 896
},
{
"epoch": 2.8672,
"grad_norm": 4.817406641864773,
"learning_rate": 6.375849881429418e-08,
"loss": 0.11191246658563614,
"step": 897
},
{
"epoch": 2.8704,
"grad_norm": 5.581451527558614,
"learning_rate": 6.083342828191453e-08,
"loss": 0.10482735931873322,
"step": 898
},
{
"epoch": 2.8736,
"grad_norm": 5.708471007091137,
"learning_rate": 5.797662925821068e-08,
"loss": 0.08502088487148285,
"step": 899
},
{
"epoch": 2.8768000000000002,
"grad_norm": 4.901671890903101,
"learning_rate": 5.518814123121885e-08,
"loss": 0.10883375257253647,
"step": 900
},
{
"epoch": 2.88,
"grad_norm": 4.154419493969357,
"learning_rate": 5.246800274474439e-08,
"loss": 0.09115639328956604,
"step": 901
},
{
"epoch": 2.8832,
"grad_norm": 4.348128911352974,
"learning_rate": 4.981625139783619e-08,
"loss": 0.06913866847753525,
"step": 902
},
{
"epoch": 2.8864,
"grad_norm": 5.289331472487325,
"learning_rate": 4.723292384426203e-08,
"loss": 0.11700673401355743,
"step": 903
},
{
"epoch": 2.8895999999999997,
"grad_norm": 3.791109353781895,
"learning_rate": 4.471805579200239e-08,
"loss": 0.04840843379497528,
"step": 904
},
{
"epoch": 2.8928000000000003,
"grad_norm": 5.036440006786255,
"learning_rate": 4.227168200276077e-08,
"loss": 0.0787072479724884,
"step": 905
},
{
"epoch": 2.896,
"grad_norm": 4.735914230933199,
"learning_rate": 3.989383629147747e-08,
"loss": 0.14012834429740906,
"step": 906
},
{
"epoch": 2.8992,
"grad_norm": 4.291348277092904,
"learning_rate": 3.758455152586715e-08,
"loss": 0.07618975639343262,
"step": 907
},
{
"epoch": 2.9024,
"grad_norm": 4.2881539813162695,
"learning_rate": 3.534385962596143e-08,
"loss": 0.06973709911108017,
"step": 908
},
{
"epoch": 2.9055999999999997,
"grad_norm": 7.05419033769194,
"learning_rate": 3.3171791563669785e-08,
"loss": 0.13123367726802826,
"step": 909
},
{
"epoch": 2.9088000000000003,
"grad_norm": 4.423070168190909,
"learning_rate": 3.10683773623488e-08,
"loss": 0.05719318240880966,
"step": 910
},
{
"epoch": 2.912,
"grad_norm": 6.187388732751734,
"learning_rate": 2.9033646096390255e-08,
"loss": 0.11336243897676468,
"step": 911
},
{
"epoch": 2.9152,
"grad_norm": 2.831466025307935,
"learning_rate": 2.706762589081646e-08,
"loss": 0.0554865300655365,
"step": 912
},
{
"epoch": 2.9184,
"grad_norm": 4.209287469214515,
"learning_rate": 2.517034392089446e-08,
"loss": 0.09645409882068634,
"step": 913
},
{
"epoch": 2.9215999999999998,
"grad_norm": 3.7148368498294406,
"learning_rate": 2.3341826411756863e-08,
"loss": 0.0811377689242363,
"step": 914
},
{
"epoch": 2.9248,
"grad_norm": 5.727089346896338,
"learning_rate": 2.158209863804217e-08,
"loss": 0.11350905150175095,
"step": 915
},
{
"epoch": 2.928,
"grad_norm": 5.766713213274287,
"learning_rate": 1.9891184923544472e-08,
"loss": 0.09957945346832275,
"step": 916
},
{
"epoch": 2.9312,
"grad_norm": 6.228807909433766,
"learning_rate": 1.826910864087761e-08,
"loss": 0.15663447976112366,
"step": 917
},
{
"epoch": 2.9344,
"grad_norm": 3.0808615653614693,
"learning_rate": 1.6715892211150442e-08,
"loss": 0.06668084114789963,
"step": 918
},
{
"epoch": 2.9375999999999998,
"grad_norm": 4.467484447991994,
"learning_rate": 1.5231557103658755e-08,
"loss": 0.08607907593250275,
"step": 919
},
{
"epoch": 2.9408,
"grad_norm": 4.706051133262561,
"learning_rate": 1.3816123835588835e-08,
"loss": 0.14103570580482483,
"step": 920
},
{
"epoch": 2.944,
"grad_norm": 8.374006967885531,
"learning_rate": 1.2469611971731576e-08,
"loss": 0.14255325496196747,
"step": 921
},
{
"epoch": 2.9472,
"grad_norm": 3.3943861642239246,
"learning_rate": 1.1192040124214931e-08,
"loss": 0.06863875687122345,
"step": 922
},
{
"epoch": 2.9504,
"grad_norm": 4.618502897797104,
"learning_rate": 9.983425952243552e-09,
"loss": 0.06344830244779587,
"step": 923
},
{
"epoch": 2.9536,
"grad_norm": 3.606277777210792,
"learning_rate": 8.84378616185788e-09,
"loss": 0.0726478099822998,
"step": 924
},
{
"epoch": 2.9568,
"grad_norm": 4.413595141431842,
"learning_rate": 7.773136505700995e-09,
"loss": 0.0803748369216919,
"step": 925
},
{
"epoch": 2.96,
"grad_norm": 4.1373546517714725,
"learning_rate": 6.7714917828004545e-09,
"loss": 0.056443389505147934,
"step": 926
},
{
"epoch": 2.9632,
"grad_norm": 4.7751319628895255,
"learning_rate": 5.838865838366792e-09,
"loss": 0.12406027317047119,
"step": 927
},
{
"epoch": 2.9664,
"grad_norm": 5.464434492318426,
"learning_rate": 4.975271563599227e-09,
"loss": 0.1432250440120697,
"step": 928
},
{
"epoch": 2.9696,
"grad_norm": 5.079654771644715,
"learning_rate": 4.180720895508028e-09,
"loss": 0.09522116184234619,
"step": 929
},
{
"epoch": 2.9728,
"grad_norm": 4.173639506166777,
"learning_rate": 3.4552248167507576e-09,
"loss": 0.052742742002010345,
"step": 930
},
{
"epoch": 2.976,
"grad_norm": 4.965049219914937,
"learning_rate": 2.798793355478502e-09,
"loss": 0.10027141869068146,
"step": 931
},
{
"epoch": 2.9792,
"grad_norm": 4.807277989835046,
"learning_rate": 2.2114355851993175e-09,
"loss": 0.0803011953830719,
"step": 932
},
{
"epoch": 2.9824,
"grad_norm": 4.7972776442936835,
"learning_rate": 1.6931596246516636e-09,
"loss": 0.09913653135299683,
"step": 933
},
{
"epoch": 2.9856,
"grad_norm": 4.063194276355487,
"learning_rate": 1.24397263769227e-09,
"loss": 0.07257185131311417,
"step": 934
},
{
"epoch": 2.9888,
"grad_norm": 5.424426759123465,
"learning_rate": 8.638808331973281e-10,
"loss": 0.12553086876869202,
"step": 935
},
{
"epoch": 2.992,
"grad_norm": 4.240720507916698,
"learning_rate": 5.528894649758921e-10,
"loss": 0.12835493683815002,
"step": 936
},
{
"epoch": 2.9952,
"grad_norm": 5.2388649859814596,
"learning_rate": 3.1100283169938074e-10,
"loss": 0.14904943108558655,
"step": 937
},
{
"epoch": 2.9984,
"grad_norm": 3.75793392949412,
"learning_rate": 1.3822427683884975e-10,
"loss": 0.10862727463245392,
"step": 938
},
{
"epoch": 3.0,
"grad_norm": 6.681865773550804,
"learning_rate": 3.4556188622802964e-11,
"loss": 0.11463062465190887,
"step": 939
},
{
"epoch": 3.0,
"step": 939,
"total_flos": 2233489489920.0,
"train_loss": 0.6554125065739733,
"train_runtime": 3840.4405,
"train_samples_per_second": 3.906,
"train_steps_per_second": 0.245
}
],
"logging_steps": 1,
"max_steps": 939,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 2233489489920.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}