fats-fme's picture
Training in progress, step 141, checkpoint
ce32ecb verified
raw
history blame
25.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2503884572697003,
"eval_steps": 141,
"global_step": 141,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0017758046614872365,
"grad_norm": 0.40501952171325684,
"learning_rate": 4.000000000000001e-06,
"loss": 1.1387,
"step": 1
},
{
"epoch": 0.0017758046614872365,
"eval_loss": 1.4082584381103516,
"eval_runtime": 167.7664,
"eval_samples_per_second": 5.657,
"eval_steps_per_second": 1.419,
"step": 1
},
{
"epoch": 0.003551609322974473,
"grad_norm": 0.491682767868042,
"learning_rate": 8.000000000000001e-06,
"loss": 1.2151,
"step": 2
},
{
"epoch": 0.005327413984461709,
"grad_norm": 0.49752455949783325,
"learning_rate": 1.2e-05,
"loss": 1.1941,
"step": 3
},
{
"epoch": 0.007103218645948946,
"grad_norm": 0.5617953538894653,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.2472,
"step": 4
},
{
"epoch": 0.008879023307436182,
"grad_norm": 0.646000862121582,
"learning_rate": 2e-05,
"loss": 1.2767,
"step": 5
},
{
"epoch": 0.010654827968923418,
"grad_norm": 0.6190630197525024,
"learning_rate": 2.4e-05,
"loss": 1.2839,
"step": 6
},
{
"epoch": 0.012430632630410655,
"grad_norm": 0.6891798973083496,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.2914,
"step": 7
},
{
"epoch": 0.014206437291897892,
"grad_norm": 0.6742885708808899,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.3001,
"step": 8
},
{
"epoch": 0.01598224195338513,
"grad_norm": 0.693493664264679,
"learning_rate": 3.6e-05,
"loss": 1.2673,
"step": 9
},
{
"epoch": 0.017758046614872364,
"grad_norm": 0.7951493859291077,
"learning_rate": 4e-05,
"loss": 1.3314,
"step": 10
},
{
"epoch": 0.0195338512763596,
"grad_norm": 0.7866435050964355,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.2703,
"step": 11
},
{
"epoch": 0.021309655937846835,
"grad_norm": 0.7218112349510193,
"learning_rate": 4.8e-05,
"loss": 1.2542,
"step": 12
},
{
"epoch": 0.023085460599334074,
"grad_norm": 0.6838662028312683,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.2432,
"step": 13
},
{
"epoch": 0.02486126526082131,
"grad_norm": 0.6592800617218018,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.2374,
"step": 14
},
{
"epoch": 0.026637069922308545,
"grad_norm": 0.513134241104126,
"learning_rate": 6e-05,
"loss": 1.246,
"step": 15
},
{
"epoch": 0.028412874583795784,
"grad_norm": 0.5785119533538818,
"learning_rate": 6.400000000000001e-05,
"loss": 1.169,
"step": 16
},
{
"epoch": 0.03018867924528302,
"grad_norm": 0.6144536733627319,
"learning_rate": 6.800000000000001e-05,
"loss": 1.1532,
"step": 17
},
{
"epoch": 0.03196448390677026,
"grad_norm": 0.674633800983429,
"learning_rate": 7.2e-05,
"loss": 1.1175,
"step": 18
},
{
"epoch": 0.03374028856825749,
"grad_norm": 0.5997682809829712,
"learning_rate": 7.6e-05,
"loss": 1.092,
"step": 19
},
{
"epoch": 0.03551609322974473,
"grad_norm": 0.5651845335960388,
"learning_rate": 8e-05,
"loss": 1.0543,
"step": 20
},
{
"epoch": 0.03729189789123197,
"grad_norm": 0.562713623046875,
"learning_rate": 8.4e-05,
"loss": 1.0377,
"step": 21
},
{
"epoch": 0.0390677025527192,
"grad_norm": 0.5826591849327087,
"learning_rate": 8.800000000000001e-05,
"loss": 1.0178,
"step": 22
},
{
"epoch": 0.04084350721420644,
"grad_norm": 0.5972415208816528,
"learning_rate": 9.200000000000001e-05,
"loss": 0.9916,
"step": 23
},
{
"epoch": 0.04261931187569367,
"grad_norm": 0.6266159415245056,
"learning_rate": 9.6e-05,
"loss": 1.0026,
"step": 24
},
{
"epoch": 0.04439511653718091,
"grad_norm": 0.7757481932640076,
"learning_rate": 0.0001,
"loss": 1.0245,
"step": 25
},
{
"epoch": 0.04617092119866815,
"grad_norm": 0.6832363605499268,
"learning_rate": 0.00010400000000000001,
"loss": 0.9408,
"step": 26
},
{
"epoch": 0.04794672586015538,
"grad_norm": 1.2983894348144531,
"learning_rate": 0.00010800000000000001,
"loss": 0.9228,
"step": 27
},
{
"epoch": 0.04972253052164262,
"grad_norm": 0.9382829666137695,
"learning_rate": 0.00011200000000000001,
"loss": 0.9605,
"step": 28
},
{
"epoch": 0.05149833518312986,
"grad_norm": 0.5051376819610596,
"learning_rate": 0.000116,
"loss": 0.9769,
"step": 29
},
{
"epoch": 0.05327413984461709,
"grad_norm": 0.40853050351142883,
"learning_rate": 0.00012,
"loss": 0.8912,
"step": 30
},
{
"epoch": 0.05504994450610433,
"grad_norm": 0.4261438846588135,
"learning_rate": 0.000124,
"loss": 0.9438,
"step": 31
},
{
"epoch": 0.05682574916759157,
"grad_norm": 0.44900333881378174,
"learning_rate": 0.00012800000000000002,
"loss": 0.9589,
"step": 32
},
{
"epoch": 0.0586015538290788,
"grad_norm": 0.4262010157108307,
"learning_rate": 0.000132,
"loss": 0.8775,
"step": 33
},
{
"epoch": 0.06037735849056604,
"grad_norm": 0.40672022104263306,
"learning_rate": 0.00013600000000000003,
"loss": 0.8956,
"step": 34
},
{
"epoch": 0.06215316315205328,
"grad_norm": 0.39336153864860535,
"learning_rate": 0.00014,
"loss": 0.866,
"step": 35
},
{
"epoch": 0.06392896781354052,
"grad_norm": 0.40699368715286255,
"learning_rate": 0.000144,
"loss": 0.8612,
"step": 36
},
{
"epoch": 0.06570477247502775,
"grad_norm": 0.438643217086792,
"learning_rate": 0.000148,
"loss": 0.922,
"step": 37
},
{
"epoch": 0.06748057713651498,
"grad_norm": 0.45053544640541077,
"learning_rate": 0.000152,
"loss": 0.8681,
"step": 38
},
{
"epoch": 0.06925638179800223,
"grad_norm": 0.4289852976799011,
"learning_rate": 0.00015600000000000002,
"loss": 0.9071,
"step": 39
},
{
"epoch": 0.07103218645948946,
"grad_norm": 0.4101032316684723,
"learning_rate": 0.00016,
"loss": 0.8692,
"step": 40
},
{
"epoch": 0.07280799112097669,
"grad_norm": 0.418319433927536,
"learning_rate": 0.000164,
"loss": 0.8654,
"step": 41
},
{
"epoch": 0.07458379578246394,
"grad_norm": 0.41637811064720154,
"learning_rate": 0.000168,
"loss": 0.8348,
"step": 42
},
{
"epoch": 0.07635960044395117,
"grad_norm": 0.40830302238464355,
"learning_rate": 0.000172,
"loss": 0.8928,
"step": 43
},
{
"epoch": 0.0781354051054384,
"grad_norm": 0.4163912236690521,
"learning_rate": 0.00017600000000000002,
"loss": 0.8793,
"step": 44
},
{
"epoch": 0.07991120976692564,
"grad_norm": 0.4240954518318176,
"learning_rate": 0.00018,
"loss": 0.9029,
"step": 45
},
{
"epoch": 0.08168701442841288,
"grad_norm": 0.48420408368110657,
"learning_rate": 0.00018400000000000003,
"loss": 0.8632,
"step": 46
},
{
"epoch": 0.08346281908990011,
"grad_norm": 0.5267483592033386,
"learning_rate": 0.000188,
"loss": 0.8575,
"step": 47
},
{
"epoch": 0.08523862375138734,
"grad_norm": 0.4947332441806793,
"learning_rate": 0.000192,
"loss": 0.9051,
"step": 48
},
{
"epoch": 0.08701442841287459,
"grad_norm": 0.5025691986083984,
"learning_rate": 0.000196,
"loss": 0.9145,
"step": 49
},
{
"epoch": 0.08879023307436182,
"grad_norm": 0.5430313944816589,
"learning_rate": 0.0002,
"loss": 0.8954,
"step": 50
},
{
"epoch": 0.09056603773584905,
"grad_norm": 0.45721662044525146,
"learning_rate": 0.00019999812486015523,
"loss": 0.9655,
"step": 51
},
{
"epoch": 0.0923418423973363,
"grad_norm": 0.4364672899246216,
"learning_rate": 0.00019999249951094388,
"loss": 0.9318,
"step": 52
},
{
"epoch": 0.09411764705882353,
"grad_norm": 0.38933759927749634,
"learning_rate": 0.00019998312416333227,
"loss": 0.8963,
"step": 53
},
{
"epoch": 0.09589345172031076,
"grad_norm": 0.35572728514671326,
"learning_rate": 0.0001999699991689222,
"loss": 0.9073,
"step": 54
},
{
"epoch": 0.097669256381798,
"grad_norm": 0.3042948544025421,
"learning_rate": 0.00019995312501993765,
"loss": 0.8751,
"step": 55
},
{
"epoch": 0.09944506104328524,
"grad_norm": 0.32266151905059814,
"learning_rate": 0.00019993250234920636,
"loss": 0.8493,
"step": 56
},
{
"epoch": 0.10122086570477247,
"grad_norm": 0.31894031167030334,
"learning_rate": 0.00019990813193013625,
"loss": 0.8512,
"step": 57
},
{
"epoch": 0.10299667036625972,
"grad_norm": 0.33073991537094116,
"learning_rate": 0.0001998800146766861,
"loss": 0.8424,
"step": 58
},
{
"epoch": 0.10477247502774695,
"grad_norm": 0.32064828276634216,
"learning_rate": 0.00019984815164333163,
"loss": 0.8698,
"step": 59
},
{
"epoch": 0.10654827968923418,
"grad_norm": 0.3364376425743103,
"learning_rate": 0.00019981254402502566,
"loss": 0.8525,
"step": 60
},
{
"epoch": 0.10832408435072143,
"grad_norm": 0.31403639912605286,
"learning_rate": 0.0001997731931571535,
"loss": 0.8309,
"step": 61
},
{
"epoch": 0.11009988901220866,
"grad_norm": 0.3375100791454315,
"learning_rate": 0.00019973010051548275,
"loss": 0.8573,
"step": 62
},
{
"epoch": 0.11187569367369589,
"grad_norm": 0.3584939241409302,
"learning_rate": 0.00019968326771610797,
"loss": 0.8479,
"step": 63
},
{
"epoch": 0.11365149833518313,
"grad_norm": 0.35480472445487976,
"learning_rate": 0.00019963269651539017,
"loss": 0.845,
"step": 64
},
{
"epoch": 0.11542730299667037,
"grad_norm": 0.33250972628593445,
"learning_rate": 0.00019957838880989078,
"loss": 0.8438,
"step": 65
},
{
"epoch": 0.1172031076581576,
"grad_norm": 0.39302438497543335,
"learning_rate": 0.00019952034663630062,
"loss": 0.8391,
"step": 66
},
{
"epoch": 0.11897891231964484,
"grad_norm": 0.3517158031463623,
"learning_rate": 0.00019945857217136363,
"loss": 0.7966,
"step": 67
},
{
"epoch": 0.12075471698113208,
"grad_norm": 0.38860467076301575,
"learning_rate": 0.00019939306773179497,
"loss": 0.8279,
"step": 68
},
{
"epoch": 0.12253052164261931,
"grad_norm": 0.3762984573841095,
"learning_rate": 0.00019932383577419432,
"loss": 0.7848,
"step": 69
},
{
"epoch": 0.12430632630410655,
"grad_norm": 0.4535103440284729,
"learning_rate": 0.00019925087889495374,
"loss": 0.8,
"step": 70
},
{
"epoch": 0.12608213096559379,
"grad_norm": 0.4869844317436218,
"learning_rate": 0.00019917419983016025,
"loss": 0.8442,
"step": 71
},
{
"epoch": 0.12785793562708103,
"grad_norm": 0.4379689395427704,
"learning_rate": 0.00019909380145549324,
"loss": 0.8353,
"step": 72
},
{
"epoch": 0.12963374028856825,
"grad_norm": 0.39510270953178406,
"learning_rate": 0.00019900968678611666,
"loss": 0.8538,
"step": 73
},
{
"epoch": 0.1314095449500555,
"grad_norm": 0.4764181971549988,
"learning_rate": 0.00019892185897656578,
"loss": 0.8509,
"step": 74
},
{
"epoch": 0.13318534961154274,
"grad_norm": 0.5591267347335815,
"learning_rate": 0.00019883032132062925,
"loss": 0.8661,
"step": 75
},
{
"epoch": 0.13496115427302996,
"grad_norm": 0.41077056527137756,
"learning_rate": 0.00019873507725122504,
"loss": 0.9418,
"step": 76
},
{
"epoch": 0.1367369589345172,
"grad_norm": 0.393622487783432,
"learning_rate": 0.00019863613034027224,
"loss": 0.926,
"step": 77
},
{
"epoch": 0.13851276359600445,
"grad_norm": 0.36414071917533875,
"learning_rate": 0.00019853348429855672,
"loss": 0.8649,
"step": 78
},
{
"epoch": 0.14028856825749167,
"grad_norm": 0.3100601136684418,
"learning_rate": 0.00019842714297559213,
"loss": 0.9114,
"step": 79
},
{
"epoch": 0.14206437291897892,
"grad_norm": 0.29151105880737305,
"learning_rate": 0.0001983171103594755,
"loss": 0.8681,
"step": 80
},
{
"epoch": 0.14384017758046616,
"grad_norm": 0.28398221731185913,
"learning_rate": 0.0001982033905767377,
"loss": 0.8515,
"step": 81
},
{
"epoch": 0.14561598224195338,
"grad_norm": 0.2883840799331665,
"learning_rate": 0.00019808598789218865,
"loss": 0.8569,
"step": 82
},
{
"epoch": 0.14739178690344062,
"grad_norm": 0.29812031984329224,
"learning_rate": 0.0001979649067087574,
"loss": 0.8529,
"step": 83
},
{
"epoch": 0.14916759156492787,
"grad_norm": 0.3074108958244324,
"learning_rate": 0.00019784015156732693,
"loss": 0.8771,
"step": 84
},
{
"epoch": 0.1509433962264151,
"grad_norm": 0.3601110279560089,
"learning_rate": 0.000197711727146564,
"loss": 0.8609,
"step": 85
},
{
"epoch": 0.15271920088790233,
"grad_norm": 0.3126521110534668,
"learning_rate": 0.00019757963826274357,
"loss": 0.8162,
"step": 86
},
{
"epoch": 0.15449500554938958,
"grad_norm": 0.3152073323726654,
"learning_rate": 0.00019744388986956822,
"loss": 0.7661,
"step": 87
},
{
"epoch": 0.1562708102108768,
"grad_norm": 0.33570149540901184,
"learning_rate": 0.00019730448705798239,
"loss": 0.8179,
"step": 88
},
{
"epoch": 0.15804661487236404,
"grad_norm": 0.33989331126213074,
"learning_rate": 0.0001971614350559814,
"loss": 0.8288,
"step": 89
},
{
"epoch": 0.1598224195338513,
"grad_norm": 0.3292713761329651,
"learning_rate": 0.0001970147392284154,
"loss": 0.8415,
"step": 90
},
{
"epoch": 0.1615982241953385,
"grad_norm": 0.3394547700881958,
"learning_rate": 0.00019686440507678824,
"loss": 0.8232,
"step": 91
},
{
"epoch": 0.16337402885682575,
"grad_norm": 0.3370296061038971,
"learning_rate": 0.0001967104382390511,
"loss": 0.7771,
"step": 92
},
{
"epoch": 0.16514983351831297,
"grad_norm": 0.3798193633556366,
"learning_rate": 0.00019655284448939094,
"loss": 0.789,
"step": 93
},
{
"epoch": 0.16692563817980022,
"grad_norm": 0.3790013790130615,
"learning_rate": 0.00019639162973801426,
"loss": 0.8153,
"step": 94
},
{
"epoch": 0.16870144284128746,
"grad_norm": 0.42274704575538635,
"learning_rate": 0.00019622680003092503,
"loss": 0.8012,
"step": 95
},
{
"epoch": 0.17047724750277468,
"grad_norm": 0.4776620864868164,
"learning_rate": 0.0001960583615496984,
"loss": 0.8132,
"step": 96
},
{
"epoch": 0.17225305216426193,
"grad_norm": 0.4170360565185547,
"learning_rate": 0.00019588632061124837,
"loss": 0.8139,
"step": 97
},
{
"epoch": 0.17402885682574917,
"grad_norm": 0.47097012400627136,
"learning_rate": 0.00019571068366759143,
"loss": 0.7711,
"step": 98
},
{
"epoch": 0.1758046614872364,
"grad_norm": 0.8176291584968567,
"learning_rate": 0.00019553145730560415,
"loss": 0.7906,
"step": 99
},
{
"epoch": 0.17758046614872364,
"grad_norm": 0.7204902172088623,
"learning_rate": 0.0001953486482467764,
"loss": 0.9088,
"step": 100
},
{
"epoch": 0.17935627081021088,
"grad_norm": 0.3952767252922058,
"learning_rate": 0.0001951622633469592,
"loss": 0.9362,
"step": 101
},
{
"epoch": 0.1811320754716981,
"grad_norm": 0.3742019534111023,
"learning_rate": 0.00019497230959610756,
"loss": 0.933,
"step": 102
},
{
"epoch": 0.18290788013318535,
"grad_norm": 0.3385975658893585,
"learning_rate": 0.00019477879411801844,
"loss": 0.9028,
"step": 103
},
{
"epoch": 0.1846836847946726,
"grad_norm": 0.2950561046600342,
"learning_rate": 0.00019458172417006347,
"loss": 0.8245,
"step": 104
},
{
"epoch": 0.1864594894561598,
"grad_norm": 0.30859696865081787,
"learning_rate": 0.00019438110714291694,
"loss": 0.8771,
"step": 105
},
{
"epoch": 0.18823529411764706,
"grad_norm": 0.3490929901599884,
"learning_rate": 0.00019417695056027844,
"loss": 0.8565,
"step": 106
},
{
"epoch": 0.1900110987791343,
"grad_norm": 0.31133994460105896,
"learning_rate": 0.00019396926207859084,
"loss": 0.8734,
"step": 107
},
{
"epoch": 0.19178690344062152,
"grad_norm": 0.2884789705276489,
"learning_rate": 0.00019375804948675306,
"loss": 0.8645,
"step": 108
},
{
"epoch": 0.19356270810210877,
"grad_norm": 0.2969193160533905,
"learning_rate": 0.0001935433207058281,
"loss": 0.8751,
"step": 109
},
{
"epoch": 0.195338512763596,
"grad_norm": 0.41810932755470276,
"learning_rate": 0.0001933250837887457,
"loss": 0.8037,
"step": 110
},
{
"epoch": 0.19711431742508323,
"grad_norm": 0.3271716833114624,
"learning_rate": 0.00019310334692000075,
"loss": 0.7814,
"step": 111
},
{
"epoch": 0.19889012208657048,
"grad_norm": 0.4146140515804291,
"learning_rate": 0.00019287811841534595,
"loss": 0.8425,
"step": 112
},
{
"epoch": 0.20066592674805772,
"grad_norm": 0.3369704484939575,
"learning_rate": 0.00019264940672148018,
"loss": 0.8301,
"step": 113
},
{
"epoch": 0.20244173140954494,
"grad_norm": 0.32731175422668457,
"learning_rate": 0.00019241722041573166,
"loss": 0.7964,
"step": 114
},
{
"epoch": 0.20421753607103219,
"grad_norm": 0.3840983510017395,
"learning_rate": 0.0001921815682057362,
"loss": 0.7864,
"step": 115
},
{
"epoch": 0.20599334073251943,
"grad_norm": 0.37049344182014465,
"learning_rate": 0.0001919424589291108,
"loss": 0.8086,
"step": 116
},
{
"epoch": 0.20776914539400665,
"grad_norm": 0.380991131067276,
"learning_rate": 0.0001916999015531221,
"loss": 0.8039,
"step": 117
},
{
"epoch": 0.2095449500554939,
"grad_norm": 0.3884637653827667,
"learning_rate": 0.00019145390517435012,
"loss": 0.7693,
"step": 118
},
{
"epoch": 0.21132075471698114,
"grad_norm": 0.39195218682289124,
"learning_rate": 0.00019120447901834706,
"loss": 0.8139,
"step": 119
},
{
"epoch": 0.21309655937846836,
"grad_norm": 0.41479626297950745,
"learning_rate": 0.00019095163243929142,
"loss": 0.7714,
"step": 120
},
{
"epoch": 0.2148723640399556,
"grad_norm": 0.3856278657913208,
"learning_rate": 0.0001906953749196371,
"loss": 0.8198,
"step": 121
},
{
"epoch": 0.21664816870144285,
"grad_norm": 0.3706349730491638,
"learning_rate": 0.00019043571606975777,
"loss": 0.7106,
"step": 122
},
{
"epoch": 0.21842397336293007,
"grad_norm": 0.5981292724609375,
"learning_rate": 0.00019017266562758659,
"loss": 0.8005,
"step": 123
},
{
"epoch": 0.22019977802441731,
"grad_norm": 0.4480712115764618,
"learning_rate": 0.00018990623345825083,
"loss": 0.8167,
"step": 124
},
{
"epoch": 0.22197558268590456,
"grad_norm": 0.9817702770233154,
"learning_rate": 0.00018963642955370201,
"loss": 0.8555,
"step": 125
},
{
"epoch": 0.22375138734739178,
"grad_norm": 0.4110267460346222,
"learning_rate": 0.00018936326403234125,
"loss": 0.9069,
"step": 126
},
{
"epoch": 0.22552719200887902,
"grad_norm": 0.36051687598228455,
"learning_rate": 0.00018908674713863952,
"loss": 0.8783,
"step": 127
},
{
"epoch": 0.22730299667036627,
"grad_norm": 0.34053486585617065,
"learning_rate": 0.00018880688924275378,
"loss": 0.8563,
"step": 128
},
{
"epoch": 0.2290788013318535,
"grad_norm": 0.30984926223754883,
"learning_rate": 0.0001885237008401378,
"loss": 0.8434,
"step": 129
},
{
"epoch": 0.23085460599334073,
"grad_norm": 0.3125753700733185,
"learning_rate": 0.0001882371925511488,
"loss": 0.831,
"step": 130
},
{
"epoch": 0.23263041065482798,
"grad_norm": 0.3113706409931183,
"learning_rate": 0.0001879473751206489,
"loss": 0.8659,
"step": 131
},
{
"epoch": 0.2344062153163152,
"grad_norm": 0.2837103605270386,
"learning_rate": 0.00018765425941760238,
"loss": 0.812,
"step": 132
},
{
"epoch": 0.23618201997780244,
"grad_norm": 0.2814521789550781,
"learning_rate": 0.00018735785643466784,
"loss": 0.8116,
"step": 133
},
{
"epoch": 0.2379578246392897,
"grad_norm": 0.2922544777393341,
"learning_rate": 0.00018705817728778624,
"loss": 0.8305,
"step": 134
},
{
"epoch": 0.2397336293007769,
"grad_norm": 0.3140820860862732,
"learning_rate": 0.00018675523321576371,
"loss": 0.7882,
"step": 135
},
{
"epoch": 0.24150943396226415,
"grad_norm": 0.29498058557510376,
"learning_rate": 0.00018644903557985025,
"loss": 0.8226,
"step": 136
},
{
"epoch": 0.2432852386237514,
"grad_norm": 0.3298538625240326,
"learning_rate": 0.00018613959586331362,
"loss": 0.7867,
"step": 137
},
{
"epoch": 0.24506104328523862,
"grad_norm": 0.3474237024784088,
"learning_rate": 0.00018582692567100867,
"loss": 0.7876,
"step": 138
},
{
"epoch": 0.24683684794672586,
"grad_norm": 0.3735051155090332,
"learning_rate": 0.00018551103672894206,
"loss": 0.818,
"step": 139
},
{
"epoch": 0.2486126526082131,
"grad_norm": 0.3931002914905548,
"learning_rate": 0.00018519194088383273,
"loss": 0.7896,
"step": 140
},
{
"epoch": 0.2503884572697003,
"grad_norm": 0.36460694670677185,
"learning_rate": 0.00018486965010266725,
"loss": 0.8105,
"step": 141
},
{
"epoch": 0.2503884572697003,
"eval_loss": 0.8086357712745667,
"eval_runtime": 159.8215,
"eval_samples_per_second": 5.938,
"eval_steps_per_second": 1.489,
"step": 141
}
],
"logging_steps": 1,
"max_steps": 563,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 141,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.8570783162472858e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}