neurocti-small / training_graph.json
aaronkaplan's picture
initial release v3
0982c6d
[
{
"current_steps": 63,
"loss": 2.8305,
"learning_rate": 0.0005,
"epoch": 0.02549800796812749
},
{
"current_steps": 127,
"loss": 2.7784,
"learning_rate": 0.001,
"epoch": 0.05099601593625498
},
{
"current_steps": 191,
"loss": 2.6623,
"learning_rate": 0.0009974226804123712,
"epoch": 0.07649402390438247
},
{
"current_steps": 255,
"loss": 2.6442,
"learning_rate": 0.0009948453608247423,
"epoch": 0.10199203187250996
},
{
"current_steps": 319,
"loss": 2.822,
"learning_rate": 0.0009922680412371135,
"epoch": 0.12749003984063745
},
{
"current_steps": 383,
"loss": 2.6869,
"learning_rate": 0.0009896907216494846,
"epoch": 0.15298804780876493
},
{
"current_steps": 447,
"loss": 2.5865,
"learning_rate": 0.0009871134020618558,
"epoch": 0.17848605577689244
},
{
"current_steps": 511,
"loss": 2.6222,
"learning_rate": 0.000984536082474227,
"epoch": 0.20398406374501993
},
{
"current_steps": 575,
"loss": 2.5421,
"learning_rate": 0.0009819587628865979,
"epoch": 0.2294820717131474
},
{
"current_steps": 639,
"loss": 2.5766,
"learning_rate": 0.000979381443298969,
"epoch": 0.2549800796812749
},
{
"current_steps": 703,
"loss": 2.5266,
"learning_rate": 0.0009768041237113402,
"epoch": 0.2804780876494024
},
{
"current_steps": 767,
"loss": 2.5239,
"learning_rate": 0.0009742268041237113,
"epoch": 0.30597609561752986
},
{
"current_steps": 831,
"loss": 2.4799,
"learning_rate": 0.0009716494845360825,
"epoch": 0.3314741035856574
},
{
"current_steps": 895,
"loss": 2.5332,
"learning_rate": 0.0009690721649484536,
"epoch": 0.3569721115537849
},
{
"current_steps": 959,
"loss": 2.4283,
"learning_rate": 0.0009664948453608248,
"epoch": 0.38247011952191234
},
{
"current_steps": 1023,
"loss": 2.4595,
"learning_rate": 0.0009639175257731959,
"epoch": 0.40796812749003986
},
{
"current_steps": 1087,
"loss": 2.4821,
"learning_rate": 0.0009613402061855671,
"epoch": 0.4334661354581673
},
{
"current_steps": 1151,
"loss": 2.4473,
"learning_rate": 0.0009587628865979382,
"epoch": 0.4589641434262948
},
{
"current_steps": 1215,
"loss": 2.4614,
"learning_rate": 0.0009561855670103094,
"epoch": 0.48446215139442234
},
{
"current_steps": 1279,
"loss": 2.4037,
"learning_rate": 0.0009536082474226805,
"epoch": 0.5099601593625498
},
{
"current_steps": 1343,
"loss": 2.4243,
"learning_rate": 0.0009510309278350515,
"epoch": 0.5354581673306773
},
{
"current_steps": 1407,
"loss": 2.3534,
"learning_rate": 0.0009484536082474226,
"epoch": 0.5609561752988048
},
{
"current_steps": 1471,
"loss": 2.406,
"learning_rate": 0.0009458762886597938,
"epoch": 0.5864541832669322
},
{
"current_steps": 1535,
"loss": 2.483,
"learning_rate": 0.0009432989690721649,
"epoch": 0.6119521912350597
},
{
"current_steps": 1599,
"loss": 2.4313,
"learning_rate": 0.0009407216494845361,
"epoch": 0.6374501992031872
},
{
"current_steps": 1663,
"loss": 2.4101,
"learning_rate": 0.0009381443298969072,
"epoch": 0.6629482071713148
},
{
"current_steps": 1727,
"loss": 2.3847,
"learning_rate": 0.0009355670103092784,
"epoch": 0.6884462151394423
},
{
"current_steps": 1791,
"loss": 2.3194,
"learning_rate": 0.0009329896907216495,
"epoch": 0.7139442231075698
},
{
"current_steps": 1855,
"loss": 2.3921,
"learning_rate": 0.0009304123711340207,
"epoch": 0.7394422310756972
},
{
"current_steps": 1919,
"loss": 2.4158,
"learning_rate": 0.0009278350515463918,
"epoch": 0.7649402390438247
},
{
"current_steps": 1983,
"loss": 2.3134,
"learning_rate": 0.000925257731958763,
"epoch": 0.7904382470119522
},
{
"current_steps": 2047,
"loss": 2.3514,
"learning_rate": 0.0009226804123711341,
"epoch": 0.8159362549800797
},
{
"current_steps": 2111,
"loss": 2.3011,
"learning_rate": 0.0009201030927835051,
"epoch": 0.8414342629482072
},
{
"current_steps": 2175,
"loss": 2.4016,
"learning_rate": 0.0009175257731958762,
"epoch": 0.8669322709163346
},
{
"current_steps": 2239,
"loss": 2.3209,
"learning_rate": 0.0009149484536082474,
"epoch": 0.8924302788844621
},
{
"current_steps": 2303,
"loss": 2.3672,
"learning_rate": 0.0009123711340206185,
"epoch": 0.9179282868525896
},
{
"current_steps": 2367,
"loss": 2.3597,
"learning_rate": 0.0009097938144329897,
"epoch": 0.9434262948207172
},
{
"current_steps": 2431,
"loss": 2.3619,
"learning_rate": 0.0009072164948453608,
"epoch": 0.9689243027888447
},
{
"current_steps": 2495,
"loss": 2.3521,
"learning_rate": 0.000904639175257732,
"epoch": 0.9944223107569721
},
{
"current_steps": 2545,
"loss": 2.2467,
"learning_rate": 0.0009020618556701031,
"epoch": 1.0199203187250996
},
{
"current_steps": 2609,
"loss": 2.2082,
"learning_rate": 0.0008994845360824743,
"epoch": 1.045418326693227
},
{
"current_steps": 2673,
"loss": 2.2161,
"learning_rate": 0.0008969072164948454,
"epoch": 1.0709163346613546
},
{
"current_steps": 2737,
"loss": 2.1961,
"learning_rate": 0.0008943298969072166,
"epoch": 1.0964143426294821
},
{
"current_steps": 2801,
"loss": 2.215,
"learning_rate": 0.0008917525773195877,
"epoch": 1.1219123505976096
},
{
"current_steps": 2865,
"loss": 2.1951,
"learning_rate": 0.0008891752577319587,
"epoch": 1.1474103585657371
},
{
"current_steps": 2929,
"loss": 2.1599,
"learning_rate": 0.0008865979381443298,
"epoch": 1.1729083665338647
},
{
"current_steps": 2993,
"loss": 2.1511,
"learning_rate": 0.000884020618556701,
"epoch": 1.198406374501992
},
{
"current_steps": 3057,
"loss": 2.0713,
"learning_rate": 0.0008814432989690721,
"epoch": 1.2239043824701195
},
{
"current_steps": 3121,
"loss": 2.1312,
"learning_rate": 0.0008788659793814433,
"epoch": 1.249402390438247
},
{
"current_steps": 3185,
"loss": 2.1442,
"learning_rate": 0.0008762886597938144,
"epoch": 1.2749003984063745
},
{
"current_steps": 3249,
"loss": 2.141,
"learning_rate": 0.0008737113402061856,
"epoch": 1.300398406374502
},
{
"current_steps": 3313,
"loss": 2.1281,
"learning_rate": 0.0008711340206185567,
"epoch": 1.3258964143426295
},
{
"current_steps": 3377,
"loss": 2.1373,
"learning_rate": 0.0008685567010309279,
"epoch": 1.351394422310757
},
{
"current_steps": 3441,
"loss": 2.1111,
"learning_rate": 0.000865979381443299,
"epoch": 1.3768924302788845
},
{
"current_steps": 3505,
"loss": 2.0973,
"learning_rate": 0.0008634020618556702,
"epoch": 1.402390438247012
},
{
"current_steps": 3569,
"loss": 2.1299,
"learning_rate": 0.0008608247422680414,
"epoch": 1.4278884462151393
},
{
"current_steps": 3633,
"loss": 2.0971,
"learning_rate": 0.0008582474226804123,
"epoch": 1.453386454183267
},
{
"current_steps": 3697,
"loss": 2.0334,
"learning_rate": 0.0008556701030927834,
"epoch": 1.4788844621513944
},
{
"current_steps": 3761,
"loss": 2.0659,
"learning_rate": 0.0008530927835051546,
"epoch": 1.5043824701195219
},
{
"current_steps": 3825,
"loss": 2.0648,
"learning_rate": 0.0008505154639175257,
"epoch": 1.5298804780876494
},
{
"current_steps": 3889,
"loss": 2.0629,
"learning_rate": 0.0008479381443298969,
"epoch": 1.5553784860557769
},
{
"current_steps": 3953,
"loss": 2.0136,
"learning_rate": 0.000845360824742268,
"epoch": 1.5808764940239044
},
{
"current_steps": 4017,
"loss": 2.0692,
"learning_rate": 0.0008427835051546392,
"epoch": 1.606374501992032
},
{
"current_steps": 4081,
"loss": 2.1114,
"learning_rate": 0.0008402061855670104,
"epoch": 1.6318725099601594
},
{
"current_steps": 4145,
"loss": 2.048,
"learning_rate": 0.0008376288659793815,
"epoch": 1.6573705179282867
},
{
"current_steps": 4209,
"loss": 2.1087,
"learning_rate": 0.0008350515463917527,
"epoch": 1.6828685258964144
},
{
"current_steps": 4273,
"loss": 2.0474,
"learning_rate": 0.0008324742268041238,
"epoch": 1.7083665338645417
},
{
"current_steps": 4337,
"loss": 2.0699,
"learning_rate": 0.000829896907216495,
"epoch": 1.7338645418326695
},
{
"current_steps": 4401,
"loss": 2.0901,
"learning_rate": 0.0008273195876288659,
"epoch": 1.7593625498007968
},
{
"current_steps": 4465,
"loss": 2.018,
"learning_rate": 0.000824742268041237,
"epoch": 1.7848605577689243
},
{
"current_steps": 4529,
"loss": 2.039,
"learning_rate": 0.0008221649484536082,
"epoch": 1.8103585657370518
},
{
"current_steps": 4593,
"loss": 2.0168,
"learning_rate": 0.0008195876288659793,
"epoch": 1.8358565737051793
},
{
"current_steps": 4657,
"loss": 1.9646,
"learning_rate": 0.0008170103092783505,
"epoch": 1.8613545816733068
},
{
"current_steps": 4721,
"loss": 1.9875,
"learning_rate": 0.0008144329896907217,
"epoch": 1.886852589641434
},
{
"current_steps": 4785,
"loss": 2.0373,
"learning_rate": 0.0008118556701030928,
"epoch": 1.9123505976095618
},
{
"current_steps": 4849,
"loss": 1.9158,
"learning_rate": 0.000809278350515464,
"epoch": 1.9378486055776891
},
{
"current_steps": 4913,
"loss": 1.9173,
"learning_rate": 0.0008067010309278351,
"epoch": 1.9633466135458169
},
{
"current_steps": 4977,
"loss": 1.9941,
"learning_rate": 0.0008041237113402063,
"epoch": 1.9888446215139441
},
{
"current_steps": 5027,
"loss": 1.8231,
"learning_rate": 0.0008015463917525774,
"epoch": 2.014342629482072
},
{
"current_steps": 5091,
"loss": 1.8018,
"learning_rate": 0.0007989690721649486,
"epoch": 2.039840637450199
},
{
"current_steps": 5155,
"loss": 1.7098,
"learning_rate": 0.0007963917525773195,
"epoch": 2.065338645418327
},
{
"current_steps": 5219,
"loss": 1.7214,
"learning_rate": 0.0007938144329896907,
"epoch": 2.090836653386454
},
{
"current_steps": 5283,
"loss": 1.8029,
"learning_rate": 0.0007912371134020618,
"epoch": 2.1163346613545815
},
{
"current_steps": 5347,
"loss": 1.71,
"learning_rate": 0.000788659793814433,
"epoch": 2.141832669322709
},
{
"current_steps": 5411,
"loss": 1.725,
"learning_rate": 0.0007860824742268041,
"epoch": 2.1673306772908365
},
{
"current_steps": 5475,
"loss": 1.729,
"learning_rate": 0.0007835051546391753,
"epoch": 2.1928286852589642
},
{
"current_steps": 5539,
"loss": 1.7139,
"learning_rate": 0.0007809278350515464,
"epoch": 2.2183266932270915
},
{
"current_steps": 5603,
"loss": 1.6588,
"learning_rate": 0.0007783505154639176,
"epoch": 2.2438247011952193
},
{
"current_steps": 5667,
"loss": 1.7179,
"learning_rate": 0.0007757731958762887,
"epoch": 2.2693227091633466
},
{
"current_steps": 5731,
"loss": 1.7024,
"learning_rate": 0.0007731958762886599,
"epoch": 2.2948207171314743
},
{
"current_steps": 5795,
"loss": 1.7205,
"learning_rate": 0.000770618556701031,
"epoch": 2.3203187250996016
},
{
"current_steps": 5859,
"loss": 1.7094,
"learning_rate": 0.0007680412371134022,
"epoch": 2.3458167330677293
},
{
"current_steps": 5923,
"loss": 1.7152,
"learning_rate": 0.0007654639175257731,
"epoch": 2.3713147410358566
},
{
"current_steps": 5987,
"loss": 1.7285,
"learning_rate": 0.0007628865979381443,
"epoch": 2.396812749003984
},
{
"current_steps": 6051,
"loss": 1.6915,
"learning_rate": 0.0007603092783505154,
"epoch": 2.4223107569721116
},
{
"current_steps": 6115,
"loss": 1.6536,
"learning_rate": 0.0007577319587628866,
"epoch": 2.447808764940239
},
{
"current_steps": 6179,
"loss": 1.6924,
"learning_rate": 0.0007551546391752577,
"epoch": 2.4733067729083666
},
{
"current_steps": 6243,
"loss": 1.6518,
"learning_rate": 0.0007525773195876289,
"epoch": 2.498804780876494
},
{
"current_steps": 6307,
"loss": 1.6765,
"learning_rate": 0.00075,
"epoch": 2.5243027888446217
},
{
"current_steps": 6371,
"loss": 1.6662,
"learning_rate": 0.0007474226804123712,
"epoch": 2.549800796812749
},
{
"current_steps": 6435,
"loss": 1.6179,
"learning_rate": 0.0007448453608247423,
"epoch": 2.5752988047808767
},
{
"current_steps": 6499,
"loss": 1.6485,
"learning_rate": 0.0007422680412371135,
"epoch": 2.600796812749004
},
{
"current_steps": 6563,
"loss": 1.7025,
"learning_rate": 0.0007396907216494846,
"epoch": 2.6262948207171313
},
{
"current_steps": 6627,
"loss": 1.6723,
"learning_rate": 0.0007371134020618558,
"epoch": 2.651792828685259
},
{
"current_steps": 6691,
"loss": 1.7608,
"learning_rate": 0.0007345360824742269,
"epoch": 2.6772908366533863
},
{
"current_steps": 6755,
"loss": 1.6388,
"learning_rate": 0.0007319587628865979,
"epoch": 2.702788844621514
},
{
"current_steps": 6819,
"loss": 1.6381,
"learning_rate": 0.000729381443298969,
"epoch": 2.7282868525896413
},
{
"current_steps": 6883,
"loss": 1.6857,
"learning_rate": 0.0007268041237113402,
"epoch": 2.753784860557769
},
{
"current_steps": 6947,
"loss": 1.6556,
"learning_rate": 0.0007242268041237113,
"epoch": 2.7792828685258963
},
{
"current_steps": 7011,
"loss": 1.6446,
"learning_rate": 0.0007216494845360825,
"epoch": 2.804780876494024
},
{
"current_steps": 7075,
"loss": 1.593,
"learning_rate": 0.0007190721649484536,
"epoch": 2.8302788844621514
},
{
"current_steps": 7139,
"loss": 1.6836,
"learning_rate": 0.0007164948453608248,
"epoch": 2.8557768924302787
},
{
"current_steps": 7203,
"loss": 1.5774,
"learning_rate": 0.0007139175257731959,
"epoch": 2.8812749003984064
},
{
"current_steps": 7267,
"loss": 1.6251,
"learning_rate": 0.0007113402061855671,
"epoch": 2.906772908366534
},
{
"current_steps": 7331,
"loss": 1.6695,
"learning_rate": 0.0007087628865979382,
"epoch": 2.9322709163346614
},
{
"current_steps": 7395,
"loss": 1.6645,
"learning_rate": 0.0007061855670103094,
"epoch": 2.9577689243027887
},
{
"current_steps": 7459,
"loss": 1.6589,
"learning_rate": 0.0007036082474226805,
"epoch": 2.9832669322709164
},
{
"current_steps": 7509,
"loss": 1.4876,
"learning_rate": 0.0007010309278350515,
"epoch": 3.0087649402390437
},
{
"current_steps": 7573,
"loss": 1.3509,
"learning_rate": 0.0006984536082474226,
"epoch": 3.0342629482071715
},
{
"current_steps": 7637,
"loss": 1.3058,
"learning_rate": 0.0006958762886597938,
"epoch": 3.0597609561752988
},
{
"current_steps": 7701,
"loss": 1.4409,
"learning_rate": 0.0006932989690721649,
"epoch": 3.0852589641434265
},
{
"current_steps": 7765,
"loss": 1.3829,
"learning_rate": 0.0006907216494845361,
"epoch": 3.1107569721115538
},
{
"current_steps": 7829,
"loss": 1.3513,
"learning_rate": 0.0006881443298969072,
"epoch": 3.1362549800796815
},
{
"current_steps": 7893,
"loss": 1.3223,
"learning_rate": 0.0006855670103092784,
"epoch": 3.161752988047809
},
{
"current_steps": 7957,
"loss": 1.2705,
"learning_rate": 0.0006829896907216495,
"epoch": 3.187250996015936
},
{
"current_steps": 8021,
"loss": 1.3133,
"learning_rate": 0.0006804123711340207,
"epoch": 3.212749003984064
},
{
"current_steps": 8085,
"loss": 1.3229,
"learning_rate": 0.0006778350515463918,
"epoch": 3.238247011952191
},
{
"current_steps": 8149,
"loss": 1.3097,
"learning_rate": 0.000675257731958763,
"epoch": 3.263745019920319
},
{
"current_steps": 8213,
"loss": 1.2961,
"learning_rate": 0.0006726804123711341,
"epoch": 3.289243027888446
},
{
"current_steps": 8277,
"loss": 1.3048,
"learning_rate": 0.0006701030927835051,
"epoch": 3.314741035856574
},
{
"current_steps": 8341,
"loss": 1.2909,
"learning_rate": 0.0006675257731958762,
"epoch": 3.340239043824701
},
{
"current_steps": 8405,
"loss": 1.3333,
"learning_rate": 0.0006649484536082474,
"epoch": 3.365737051792829
},
{
"current_steps": 8469,
"loss": 1.2552,
"learning_rate": 0.0006623711340206185,
"epoch": 3.391235059760956
},
{
"current_steps": 8533,
"loss": 1.306,
"learning_rate": 0.0006597938144329897,
"epoch": 3.4167330677290835
},
{
"current_steps": 8597,
"loss": 1.2382,
"learning_rate": 0.0006572164948453608,
"epoch": 3.442231075697211
},
{
"current_steps": 8661,
"loss": 1.2718,
"learning_rate": 0.000654639175257732,
"epoch": 3.4677290836653385
},
{
"current_steps": 8725,
"loss": 1.2348,
"learning_rate": 0.0006520618556701031,
"epoch": 3.4932270916334662
},
{
"current_steps": 8789,
"loss": 1.2724,
"learning_rate": 0.0006494845360824743,
"epoch": 3.5187250996015935
},
{
"current_steps": 8853,
"loss": 1.244,
"learning_rate": 0.0006469072164948454,
"epoch": 3.5442231075697213
},
{
"current_steps": 8917,
"loss": 1.2948,
"learning_rate": 0.0006443298969072166,
"epoch": 3.5697211155378485
},
{
"current_steps": 8981,
"loss": 1.2063,
"learning_rate": 0.0006417525773195877,
"epoch": 3.5952191235059763
},
{
"current_steps": 9045,
"loss": 1.2656,
"learning_rate": 0.0006391752577319587,
"epoch": 3.6207171314741036
},
{
"current_steps": 9109,
"loss": 1.25,
"learning_rate": 0.0006365979381443298,
"epoch": 3.646215139442231
},
{
"current_steps": 9173,
"loss": 1.3042,
"learning_rate": 0.000634020618556701,
"epoch": 3.6717131474103586
},
{
"current_steps": 9237,
"loss": 1.2612,
"learning_rate": 0.0006314432989690721,
"epoch": 3.6972111553784863
},
{
"current_steps": 9301,
"loss": 1.2516,
"learning_rate": 0.0006288659793814433,
"epoch": 3.7227091633466136
},
{
"current_steps": 9365,
"loss": 1.2572,
"learning_rate": 0.0006262886597938144,
"epoch": 3.748207171314741
},
{
"current_steps": 9429,
"loss": 1.2525,
"learning_rate": 0.0006237113402061856,
"epoch": 3.7737051792828686
},
{
"current_steps": 9493,
"loss": 1.2509,
"learning_rate": 0.0006211340206185567,
"epoch": 3.799203187250996
},
{
"current_steps": 9557,
"loss": 1.2467,
"learning_rate": 0.0006185567010309279,
"epoch": 3.8247011952191237
},
{
"current_steps": 9621,
"loss": 1.2375,
"learning_rate": 0.000615979381443299,
"epoch": 3.850199203187251
},
{
"current_steps": 9685,
"loss": 1.2406,
"learning_rate": 0.0006134020618556702,
"epoch": 3.8756972111553782
},
{
"current_steps": 9749,
"loss": 1.2517,
"learning_rate": 0.0006108247422680413,
"epoch": 3.901195219123506
},
{
"current_steps": 9813,
"loss": 1.2533,
"learning_rate": 0.0006082474226804123,
"epoch": 3.9266932270916337
},
{
"current_steps": 9877,
"loss": 1.256,
"learning_rate": 0.0006056701030927834,
"epoch": 3.952191235059761
},
{
"current_steps": 9941,
"loss": 1.2826,
"learning_rate": 0.0006030927835051546,
"epoch": 3.9776892430278883
},
{
"current_steps": 9991,
"loss": 1.226,
"learning_rate": 0.0006005154639175257,
"epoch": 4.003187250996016
},
{
"current_steps": 10055,
"loss": 0.9512,
"learning_rate": 0.0005979381443298969,
"epoch": 4.028685258964144
},
{
"current_steps": 10055,
"loss": 0.9512,
"learning_rate": 0.0005979381443298969,
"epoch": 4.028685258964144
}
]