{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.24873322073073162,
"eval_steps": 500,
"global_step": 2798,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008889679082585119,
"grad_norm": 4.238861560821533,
"learning_rate": 1.1061797752808989e-06,
"loss": 1.7261,
"step": 10
},
{
"epoch": 0.0017779358165170237,
"grad_norm": 2.0652520656585693,
"learning_rate": 2.2241573033707866e-06,
"loss": 1.6328,
"step": 20
},
{
"epoch": 0.0026669037247755356,
"grad_norm": 1.8617759943008423,
"learning_rate": 3.342134831460675e-06,
"loss": 1.3995,
"step": 30
},
{
"epoch": 0.0035558716330340474,
"grad_norm": 1.4548546075820923,
"learning_rate": 4.4601123595505624e-06,
"loss": 1.3222,
"step": 40
},
{
"epoch": 0.004444839541292559,
"grad_norm": 0.696451723575592,
"learning_rate": 5.5780898876404495e-06,
"loss": 1.2108,
"step": 50
},
{
"epoch": 0.005333807449551071,
"grad_norm": 0.679622232913971,
"learning_rate": 6.6960674157303374e-06,
"loss": 1.1247,
"step": 60
},
{
"epoch": 0.006222775357809583,
"grad_norm": 0.6772049069404602,
"learning_rate": 7.814044943820226e-06,
"loss": 1.0773,
"step": 70
},
{
"epoch": 0.007111743266068095,
"grad_norm": 0.5850681662559509,
"learning_rate": 8.932022471910112e-06,
"loss": 1.0619,
"step": 80
},
{
"epoch": 0.008000711174326608,
"grad_norm": 0.595498263835907,
"learning_rate": 1.005e-05,
"loss": 1.0314,
"step": 90
},
{
"epoch": 0.008889679082585119,
"grad_norm": 0.533685028553009,
"learning_rate": 1.1167977528089888e-05,
"loss": 1.0384,
"step": 100
},
{
"epoch": 0.009778646990843631,
"grad_norm": 0.5636975765228271,
"learning_rate": 1.2285955056179776e-05,
"loss": 1.055,
"step": 110
},
{
"epoch": 0.010667614899102142,
"grad_norm": 0.523317277431488,
"learning_rate": 1.3403932584269664e-05,
"loss": 1.051,
"step": 120
},
{
"epoch": 0.011556582807360655,
"grad_norm": 0.548605740070343,
"learning_rate": 1.4521910112359552e-05,
"loss": 1.0005,
"step": 130
},
{
"epoch": 0.012445550715619166,
"grad_norm": 0.556210458278656,
"learning_rate": 1.563988764044944e-05,
"loss": 1.0724,
"step": 140
},
{
"epoch": 0.013334518623877679,
"grad_norm": 0.6226356029510498,
"learning_rate": 1.6757865168539328e-05,
"loss": 1.0316,
"step": 150
},
{
"epoch": 0.01422348653213619,
"grad_norm": 0.5927873849868774,
"learning_rate": 1.7875842696629214e-05,
"loss": 1.0391,
"step": 160
},
{
"epoch": 0.015112454440394702,
"grad_norm": 0.6042047739028931,
"learning_rate": 1.89938202247191e-05,
"loss": 1.02,
"step": 170
},
{
"epoch": 0.016001422348653215,
"grad_norm": 0.5578976273536682,
"learning_rate": 2e-05,
"loss": 1.0348,
"step": 180
},
{
"epoch": 0.016890390256911726,
"grad_norm": 0.6130852699279785,
"learning_rate": 2e-05,
"loss": 1.0207,
"step": 190
},
{
"epoch": 0.017779358165170237,
"grad_norm": 0.5213446617126465,
"learning_rate": 2e-05,
"loss": 1.06,
"step": 200
},
{
"epoch": 0.018668326073428748,
"grad_norm": 0.5071802139282227,
"learning_rate": 2e-05,
"loss": 1.0331,
"step": 210
},
{
"epoch": 0.019557293981687263,
"grad_norm": 0.49541351199150085,
"learning_rate": 2e-05,
"loss": 1.0726,
"step": 220
},
{
"epoch": 0.020446261889945774,
"grad_norm": 0.4953780472278595,
"learning_rate": 2e-05,
"loss": 1.0192,
"step": 230
},
{
"epoch": 0.021335229798204285,
"grad_norm": 0.5415428280830383,
"learning_rate": 2e-05,
"loss": 1.0232,
"step": 240
},
{
"epoch": 0.022224197706462796,
"grad_norm": 0.529830813407898,
"learning_rate": 2e-05,
"loss": 1.0408,
"step": 250
},
{
"epoch": 0.02311316561472131,
"grad_norm": 0.5176880955696106,
"learning_rate": 2e-05,
"loss": 1.0416,
"step": 260
},
{
"epoch": 0.02400213352297982,
"grad_norm": 0.5344821810722351,
"learning_rate": 2e-05,
"loss": 0.9997,
"step": 270
},
{
"epoch": 0.024891101431238332,
"grad_norm": 0.5449062585830688,
"learning_rate": 2e-05,
"loss": 1.0481,
"step": 280
},
{
"epoch": 0.025780069339496843,
"grad_norm": 0.5149458050727844,
"learning_rate": 2e-05,
"loss": 1.0454,
"step": 290
},
{
"epoch": 0.026669037247755358,
"grad_norm": 0.49063146114349365,
"learning_rate": 2e-05,
"loss": 1.0381,
"step": 300
},
{
"epoch": 0.02755800515601387,
"grad_norm": 0.48867329955101013,
"learning_rate": 2e-05,
"loss": 1.0128,
"step": 310
},
{
"epoch": 0.02844697306427238,
"grad_norm": 0.5222336649894714,
"learning_rate": 2e-05,
"loss": 1.0318,
"step": 320
},
{
"epoch": 0.02933594097253089,
"grad_norm": 0.589815080165863,
"learning_rate": 2e-05,
"loss": 0.9987,
"step": 330
},
{
"epoch": 0.030224908880789405,
"grad_norm": 0.522380530834198,
"learning_rate": 2e-05,
"loss": 1.0427,
"step": 340
},
{
"epoch": 0.031113876789047916,
"grad_norm": 0.5397540330886841,
"learning_rate": 2e-05,
"loss": 1.0103,
"step": 350
},
{
"epoch": 0.03200284469730643,
"grad_norm": 1.9739325046539307,
"learning_rate": 2e-05,
"loss": 1.0189,
"step": 360
},
{
"epoch": 0.03289181260556494,
"grad_norm": 0.5190985202789307,
"learning_rate": 2e-05,
"loss": 1.0137,
"step": 370
},
{
"epoch": 0.03378078051382345,
"grad_norm": 0.49212539196014404,
"learning_rate": 2e-05,
"loss": 1.0271,
"step": 380
},
{
"epoch": 0.03466974842208196,
"grad_norm": 0.48474904894828796,
"learning_rate": 2e-05,
"loss": 1.0107,
"step": 390
},
{
"epoch": 0.035558716330340474,
"grad_norm": 0.63145512342453,
"learning_rate": 2e-05,
"loss": 0.9979,
"step": 400
},
{
"epoch": 0.03644768423859899,
"grad_norm": 0.489841103553772,
"learning_rate": 2e-05,
"loss": 1.0007,
"step": 410
},
{
"epoch": 0.037336652146857496,
"grad_norm": 0.5093907117843628,
"learning_rate": 2e-05,
"loss": 0.9841,
"step": 420
},
{
"epoch": 0.03822562005511601,
"grad_norm": 0.5208895206451416,
"learning_rate": 2e-05,
"loss": 1.0045,
"step": 430
},
{
"epoch": 0.039114587963374525,
"grad_norm": 0.4912340044975281,
"learning_rate": 2e-05,
"loss": 1.0158,
"step": 440
},
{
"epoch": 0.04000355587163303,
"grad_norm": 0.5119054317474365,
"learning_rate": 2e-05,
"loss": 0.9946,
"step": 450
},
{
"epoch": 0.04089252377989155,
"grad_norm": 0.49770587682724,
"learning_rate": 2e-05,
"loss": 0.9851,
"step": 460
},
{
"epoch": 0.041781491688150055,
"grad_norm": 0.4990149140357971,
"learning_rate": 2e-05,
"loss": 1.0499,
"step": 470
},
{
"epoch": 0.04267045959640857,
"grad_norm": 0.4940296411514282,
"learning_rate": 2e-05,
"loss": 0.9977,
"step": 480
},
{
"epoch": 0.043559427504667084,
"grad_norm": 0.47203925251960754,
"learning_rate": 2e-05,
"loss": 0.9953,
"step": 490
},
{
"epoch": 0.04444839541292559,
"grad_norm": 0.5077679753303528,
"learning_rate": 2e-05,
"loss": 1.0069,
"step": 500
},
{
"epoch": 0.045337363321184106,
"grad_norm": 0.5261061191558838,
"learning_rate": 2e-05,
"loss": 1.0212,
"step": 510
},
{
"epoch": 0.04622633122944262,
"grad_norm": 0.49914729595184326,
"learning_rate": 2e-05,
"loss": 1.0094,
"step": 520
},
{
"epoch": 0.04711529913770113,
"grad_norm": 0.49721768498420715,
"learning_rate": 2e-05,
"loss": 0.9993,
"step": 530
},
{
"epoch": 0.04800426704595964,
"grad_norm": 0.46859484910964966,
"learning_rate": 2e-05,
"loss": 0.9901,
"step": 540
},
{
"epoch": 0.04889323495421815,
"grad_norm": 0.4489647150039673,
"learning_rate": 2e-05,
"loss": 0.99,
"step": 550
},
{
"epoch": 0.049782202862476664,
"grad_norm": 0.472504198551178,
"learning_rate": 2e-05,
"loss": 1.024,
"step": 560
},
{
"epoch": 0.05067117077073518,
"grad_norm": 0.5098609924316406,
"learning_rate": 2e-05,
"loss": 1.0048,
"step": 570
},
{
"epoch": 0.051560138678993686,
"grad_norm": 0.45842158794403076,
"learning_rate": 2e-05,
"loss": 1.0026,
"step": 580
},
{
"epoch": 0.0524491065872522,
"grad_norm": 0.4619347155094147,
"learning_rate": 2e-05,
"loss": 0.9719,
"step": 590
},
{
"epoch": 0.053338074495510715,
"grad_norm": 0.5127968788146973,
"learning_rate": 2e-05,
"loss": 1.0013,
"step": 600
},
{
"epoch": 0.05422704240376922,
"grad_norm": 0.47510862350463867,
"learning_rate": 2e-05,
"loss": 0.9684,
"step": 610
},
{
"epoch": 0.05511601031202774,
"grad_norm": 0.48674413561820984,
"learning_rate": 2e-05,
"loss": 0.9922,
"step": 620
},
{
"epoch": 0.056004978220286245,
"grad_norm": 0.4563288390636444,
"learning_rate": 2e-05,
"loss": 0.9954,
"step": 630
},
{
"epoch": 0.05689394612854476,
"grad_norm": 0.4836796820163727,
"learning_rate": 2e-05,
"loss": 0.9772,
"step": 640
},
{
"epoch": 0.05778291403680327,
"grad_norm": 0.5137700438499451,
"learning_rate": 2e-05,
"loss": 0.991,
"step": 650
},
{
"epoch": 0.05867188194506178,
"grad_norm": 0.48672813177108765,
"learning_rate": 2e-05,
"loss": 0.9755,
"step": 660
},
{
"epoch": 0.059560849853320295,
"grad_norm": 0.501348078250885,
"learning_rate": 2e-05,
"loss": 0.9903,
"step": 670
},
{
"epoch": 0.06044981776157881,
"grad_norm": 0.48052978515625,
"learning_rate": 2e-05,
"loss": 0.9822,
"step": 680
},
{
"epoch": 0.06133878566983732,
"grad_norm": 0.7372881770133972,
"learning_rate": 2e-05,
"loss": 0.9958,
"step": 690
},
{
"epoch": 0.06222775357809583,
"grad_norm": 0.5022790431976318,
"learning_rate": 2e-05,
"loss": 1.0131,
"step": 700
},
{
"epoch": 0.06311672148635435,
"grad_norm": 0.497873991727829,
"learning_rate": 2e-05,
"loss": 0.985,
"step": 710
},
{
"epoch": 0.06400568939461286,
"grad_norm": 1.2517738342285156,
"learning_rate": 2e-05,
"loss": 0.9648,
"step": 720
},
{
"epoch": 0.06489465730287136,
"grad_norm": 0.4873271882534027,
"learning_rate": 2e-05,
"loss": 0.9837,
"step": 730
},
{
"epoch": 0.06578362521112988,
"grad_norm": 0.5012655854225159,
"learning_rate": 2e-05,
"loss": 0.985,
"step": 740
},
{
"epoch": 0.06667259311938839,
"grad_norm": 0.482709676027298,
"learning_rate": 2e-05,
"loss": 0.9743,
"step": 750
},
{
"epoch": 0.0675615610276469,
"grad_norm": 0.4815094470977783,
"learning_rate": 2e-05,
"loss": 0.9818,
"step": 760
},
{
"epoch": 0.06845052893590542,
"grad_norm": 0.4626294672489166,
"learning_rate": 2e-05,
"loss": 0.9953,
"step": 770
},
{
"epoch": 0.06933949684416392,
"grad_norm": 0.4867992103099823,
"learning_rate": 2e-05,
"loss": 0.9743,
"step": 780
},
{
"epoch": 0.07022846475242243,
"grad_norm": 0.49126219749450684,
"learning_rate": 2e-05,
"loss": 0.972,
"step": 790
},
{
"epoch": 0.07111743266068095,
"grad_norm": 0.5143160223960876,
"learning_rate": 2e-05,
"loss": 0.9534,
"step": 800
},
{
"epoch": 0.07200640056893946,
"grad_norm": 0.5352365374565125,
"learning_rate": 2e-05,
"loss": 1.0183,
"step": 810
},
{
"epoch": 0.07289536847719798,
"grad_norm": 0.5039393901824951,
"learning_rate": 2e-05,
"loss": 0.9831,
"step": 820
},
{
"epoch": 0.07378433638545648,
"grad_norm": 0.461434006690979,
"learning_rate": 2e-05,
"loss": 0.9805,
"step": 830
},
{
"epoch": 0.07467330429371499,
"grad_norm": 0.48597556352615356,
"learning_rate": 2e-05,
"loss": 0.9592,
"step": 840
},
{
"epoch": 0.07556227220197351,
"grad_norm": 0.5177674889564514,
"learning_rate": 2e-05,
"loss": 0.9739,
"step": 850
},
{
"epoch": 0.07645124011023202,
"grad_norm": 0.48002588748931885,
"learning_rate": 2e-05,
"loss": 0.9878,
"step": 860
},
{
"epoch": 0.07734020801849054,
"grad_norm": 0.5129883885383606,
"learning_rate": 2e-05,
"loss": 0.9756,
"step": 870
},
{
"epoch": 0.07822917592674905,
"grad_norm": 0.5066726803779602,
"learning_rate": 2e-05,
"loss": 0.9699,
"step": 880
},
{
"epoch": 0.07911814383500755,
"grad_norm": 0.4818406403064728,
"learning_rate": 2e-05,
"loss": 0.9898,
"step": 890
},
{
"epoch": 0.08000711174326607,
"grad_norm": 0.48721879720687866,
"learning_rate": 2e-05,
"loss": 0.9503,
"step": 900
},
{
"epoch": 0.08089607965152458,
"grad_norm": 0.4314747452735901,
"learning_rate": 2e-05,
"loss": 0.9891,
"step": 910
},
{
"epoch": 0.0817850475597831,
"grad_norm": 0.4804377853870392,
"learning_rate": 2e-05,
"loss": 0.9727,
"step": 920
},
{
"epoch": 0.08267401546804161,
"grad_norm": 0.48248469829559326,
"learning_rate": 2e-05,
"loss": 0.967,
"step": 930
},
{
"epoch": 0.08356298337630011,
"grad_norm": 0.45454731583595276,
"learning_rate": 2e-05,
"loss": 0.9854,
"step": 940
},
{
"epoch": 0.08445195128455862,
"grad_norm": 0.47664403915405273,
"learning_rate": 2e-05,
"loss": 0.987,
"step": 950
},
{
"epoch": 0.08534091919281714,
"grad_norm": 0.47163963317871094,
"learning_rate": 2e-05,
"loss": 0.9979,
"step": 960
},
{
"epoch": 0.08622988710107565,
"grad_norm": 0.5137403011322021,
"learning_rate": 2e-05,
"loss": 0.9728,
"step": 970
},
{
"epoch": 0.08711885500933417,
"grad_norm": 0.449590802192688,
"learning_rate": 2e-05,
"loss": 0.9599,
"step": 980
},
{
"epoch": 0.08800782291759268,
"grad_norm": 0.4698745310306549,
"learning_rate": 2e-05,
"loss": 0.9475,
"step": 990
},
{
"epoch": 0.08889679082585118,
"grad_norm": 0.45183730125427246,
"learning_rate": 2e-05,
"loss": 0.9683,
"step": 1000
},
{
"epoch": 0.0897857587341097,
"grad_norm": 0.45844438672065735,
"learning_rate": 2e-05,
"loss": 0.9835,
"step": 1010
},
{
"epoch": 0.09067472664236821,
"grad_norm": 0.4777911305427551,
"learning_rate": 2e-05,
"loss": 0.9922,
"step": 1020
},
{
"epoch": 0.09156369455062673,
"grad_norm": 0.4591684937477112,
"learning_rate": 2e-05,
"loss": 0.9448,
"step": 1030
},
{
"epoch": 0.09245266245888524,
"grad_norm": 0.47120004892349243,
"learning_rate": 2e-05,
"loss": 0.9668,
"step": 1040
},
{
"epoch": 0.09334163036714374,
"grad_norm": 0.467716783285141,
"learning_rate": 2e-05,
"loss": 0.9661,
"step": 1050
},
{
"epoch": 0.09423059827540226,
"grad_norm": 0.479279488325119,
"learning_rate": 2e-05,
"loss": 0.9951,
"step": 1060
},
{
"epoch": 0.09511956618366077,
"grad_norm": 0.4522221088409424,
"learning_rate": 2e-05,
"loss": 0.9553,
"step": 1070
},
{
"epoch": 0.09600853409191928,
"grad_norm": 0.4667496979236603,
"learning_rate": 2e-05,
"loss": 0.9659,
"step": 1080
},
{
"epoch": 0.0968975020001778,
"grad_norm": 0.47797060012817383,
"learning_rate": 2e-05,
"loss": 0.9628,
"step": 1090
},
{
"epoch": 0.0977864699084363,
"grad_norm": 0.47188839316368103,
"learning_rate": 2e-05,
"loss": 0.9738,
"step": 1100
},
{
"epoch": 0.09867543781669481,
"grad_norm": 0.47207027673721313,
"learning_rate": 2e-05,
"loss": 0.9473,
"step": 1110
},
{
"epoch": 0.09956440572495333,
"grad_norm": 0.4718773066997528,
"learning_rate": 2e-05,
"loss": 0.9692,
"step": 1120
},
{
"epoch": 0.10045337363321184,
"grad_norm": 0.45084095001220703,
"learning_rate": 2e-05,
"loss": 0.9595,
"step": 1130
},
{
"epoch": 0.10134234154147036,
"grad_norm": 0.4841742217540741,
"learning_rate": 2e-05,
"loss": 0.9701,
"step": 1140
},
{
"epoch": 0.10223130944972887,
"grad_norm": 0.5060001015663147,
"learning_rate": 2e-05,
"loss": 0.966,
"step": 1150
},
{
"epoch": 0.10312027735798737,
"grad_norm": 0.4384157061576843,
"learning_rate": 2e-05,
"loss": 0.9809,
"step": 1160
},
{
"epoch": 0.10400924526624589,
"grad_norm": 0.4938412606716156,
"learning_rate": 2e-05,
"loss": 0.9664,
"step": 1170
},
{
"epoch": 0.1048982131745044,
"grad_norm": 0.5100815892219543,
"learning_rate": 2e-05,
"loss": 0.964,
"step": 1180
},
{
"epoch": 0.10578718108276292,
"grad_norm": 0.4635246992111206,
"learning_rate": 2e-05,
"loss": 0.9641,
"step": 1190
},
{
"epoch": 0.10667614899102143,
"grad_norm": 0.5389490127563477,
"learning_rate": 2e-05,
"loss": 0.9767,
"step": 1200
},
{
"epoch": 0.10756511689927993,
"grad_norm": 0.46785902976989746,
"learning_rate": 2e-05,
"loss": 0.9496,
"step": 1210
},
{
"epoch": 0.10845408480753845,
"grad_norm": 0.4610632359981537,
"learning_rate": 2e-05,
"loss": 0.9565,
"step": 1220
},
{
"epoch": 0.10934305271579696,
"grad_norm": 0.44586533308029175,
"learning_rate": 2e-05,
"loss": 0.9652,
"step": 1230
},
{
"epoch": 0.11023202062405547,
"grad_norm": 0.5270296931266785,
"learning_rate": 2e-05,
"loss": 0.9595,
"step": 1240
},
{
"epoch": 0.11112098853231399,
"grad_norm": 0.4567857086658478,
"learning_rate": 2e-05,
"loss": 0.9806,
"step": 1250
},
{
"epoch": 0.11200995644057249,
"grad_norm": 0.4863816201686859,
"learning_rate": 2e-05,
"loss": 0.9617,
"step": 1260
},
{
"epoch": 0.112898924348831,
"grad_norm": 0.4874187409877777,
"learning_rate": 2e-05,
"loss": 0.9785,
"step": 1270
},
{
"epoch": 0.11378789225708952,
"grad_norm": 0.4692484736442566,
"learning_rate": 2e-05,
"loss": 0.9593,
"step": 1280
},
{
"epoch": 0.11467686016534803,
"grad_norm": 0.6816130876541138,
"learning_rate": 2e-05,
"loss": 0.9237,
"step": 1290
},
{
"epoch": 0.11556582807360655,
"grad_norm": 0.49590855836868286,
"learning_rate": 2e-05,
"loss": 0.9628,
"step": 1300
},
{
"epoch": 0.11645479598186506,
"grad_norm": 0.45354118943214417,
"learning_rate": 2e-05,
"loss": 0.9396,
"step": 1310
},
{
"epoch": 0.11734376389012356,
"grad_norm": 0.4449705481529236,
"learning_rate": 2e-05,
"loss": 0.9473,
"step": 1320
},
{
"epoch": 0.11823273179838208,
"grad_norm": 0.44771867990493774,
"learning_rate": 2e-05,
"loss": 0.954,
"step": 1330
},
{
"epoch": 0.11912169970664059,
"grad_norm": 0.4958712160587311,
"learning_rate": 2e-05,
"loss": 0.9637,
"step": 1340
},
{
"epoch": 0.1200106676148991,
"grad_norm": 0.4684152603149414,
"learning_rate": 2e-05,
"loss": 0.9383,
"step": 1350
},
{
"epoch": 0.12089963552315762,
"grad_norm": 0.5252647399902344,
"learning_rate": 2e-05,
"loss": 0.9668,
"step": 1360
},
{
"epoch": 0.12178860343141612,
"grad_norm": 0.4878622591495514,
"learning_rate": 2e-05,
"loss": 0.9357,
"step": 1370
},
{
"epoch": 0.12267757133967463,
"grad_norm": 0.46592438220977783,
"learning_rate": 2e-05,
"loss": 0.9515,
"step": 1380
},
{
"epoch": 0.12356653924793315,
"grad_norm": 0.5377469062805176,
"learning_rate": 2e-05,
"loss": 0.9431,
"step": 1390
},
{
"epoch": 0.12445550715619166,
"grad_norm": 0.472373902797699,
"learning_rate": 2e-05,
"loss": 0.9305,
"step": 1400
},
{
"epoch": 0.12534447506445018,
"grad_norm": 0.4335474967956543,
"learning_rate": 2e-05,
"loss": 0.9501,
"step": 1410
},
{
"epoch": 0.1262334429727087,
"grad_norm": 0.43715789914131165,
"learning_rate": 2e-05,
"loss": 0.9565,
"step": 1420
},
{
"epoch": 0.1271224108809672,
"grad_norm": 0.473441481590271,
"learning_rate": 2e-05,
"loss": 0.9341,
"step": 1430
},
{
"epoch": 0.12801137878922572,
"grad_norm": 0.4540274143218994,
"learning_rate": 2e-05,
"loss": 0.9584,
"step": 1440
},
{
"epoch": 0.1289003466974842,
"grad_norm": 0.45082035660743713,
"learning_rate": 2e-05,
"loss": 0.9772,
"step": 1450
},
{
"epoch": 0.12978931460574272,
"grad_norm": 0.43487876653671265,
"learning_rate": 2e-05,
"loss": 0.9642,
"step": 1460
},
{
"epoch": 0.13067828251400124,
"grad_norm": 0.45913758873939514,
"learning_rate": 2e-05,
"loss": 0.9387,
"step": 1470
},
{
"epoch": 0.13156725042225975,
"grad_norm": 0.458950936794281,
"learning_rate": 2e-05,
"loss": 0.9597,
"step": 1480
},
{
"epoch": 0.13245621833051827,
"grad_norm": 0.462766170501709,
"learning_rate": 2e-05,
"loss": 0.9871,
"step": 1490
},
{
"epoch": 0.13334518623877678,
"grad_norm": 0.4476396441459656,
"learning_rate": 2e-05,
"loss": 0.9311,
"step": 1500
},
{
"epoch": 0.1342341541470353,
"grad_norm": 0.46129149198532104,
"learning_rate": 2e-05,
"loss": 0.9348,
"step": 1510
},
{
"epoch": 0.1351231220552938,
"grad_norm": 0.46218064427375793,
"learning_rate": 2e-05,
"loss": 0.9261,
"step": 1520
},
{
"epoch": 0.13601208996355232,
"grad_norm": 0.4620305895805359,
"learning_rate": 2e-05,
"loss": 0.9347,
"step": 1530
},
{
"epoch": 0.13690105787181084,
"grad_norm": 0.603297770023346,
"learning_rate": 2e-05,
"loss": 0.9829,
"step": 1540
},
{
"epoch": 0.13779002578006935,
"grad_norm": 0.5085828900337219,
"learning_rate": 2e-05,
"loss": 0.9259,
"step": 1550
},
{
"epoch": 0.13867899368832784,
"grad_norm": 0.4496013820171356,
"learning_rate": 2e-05,
"loss": 0.9561,
"step": 1560
},
{
"epoch": 0.13956796159658635,
"grad_norm": 0.468447208404541,
"learning_rate": 2e-05,
"loss": 0.9603,
"step": 1570
},
{
"epoch": 0.14045692950484487,
"grad_norm": 0.45801347494125366,
"learning_rate": 2e-05,
"loss": 0.9326,
"step": 1580
},
{
"epoch": 0.14134589741310338,
"grad_norm": 0.46467089653015137,
"learning_rate": 2e-05,
"loss": 0.9255,
"step": 1590
},
{
"epoch": 0.1422348653213619,
"grad_norm": 0.43190547823905945,
"learning_rate": 2e-05,
"loss": 0.9339,
"step": 1600
},
{
"epoch": 0.1431238332296204,
"grad_norm": 0.4498319923877716,
"learning_rate": 2e-05,
"loss": 0.9288,
"step": 1610
},
{
"epoch": 0.14401280113787893,
"grad_norm": 0.4732903838157654,
"learning_rate": 2e-05,
"loss": 0.9505,
"step": 1620
},
{
"epoch": 0.14490176904613744,
"grad_norm": 0.4331393539905548,
"learning_rate": 2e-05,
"loss": 0.9487,
"step": 1630
},
{
"epoch": 0.14579073695439596,
"grad_norm": 0.4622068405151367,
"learning_rate": 2e-05,
"loss": 0.9322,
"step": 1640
},
{
"epoch": 0.14667970486265447,
"grad_norm": 0.44649264216423035,
"learning_rate": 2e-05,
"loss": 0.944,
"step": 1650
},
{
"epoch": 0.14756867277091296,
"grad_norm": 0.44571954011917114,
"learning_rate": 2e-05,
"loss": 0.9305,
"step": 1660
},
{
"epoch": 0.14845764067917147,
"grad_norm": 0.47047024965286255,
"learning_rate": 2e-05,
"loss": 0.9837,
"step": 1670
},
{
"epoch": 0.14934660858742999,
"grad_norm": 0.4326838254928589,
"learning_rate": 2e-05,
"loss": 0.9455,
"step": 1680
},
{
"epoch": 0.1502355764956885,
"grad_norm": 0.4418770372867584,
"learning_rate": 2e-05,
"loss": 0.9395,
"step": 1690
},
{
"epoch": 0.15112454440394701,
"grad_norm": 0.4838589131832123,
"learning_rate": 2e-05,
"loss": 0.9467,
"step": 1700
},
{
"epoch": 0.15201351231220553,
"grad_norm": 0.46900397539138794,
"learning_rate": 2e-05,
"loss": 0.9553,
"step": 1710
},
{
"epoch": 0.15290248022046404,
"grad_norm": 0.4528874456882477,
"learning_rate": 2e-05,
"loss": 0.9536,
"step": 1720
},
{
"epoch": 0.15379144812872256,
"grad_norm": 0.43615949153900146,
"learning_rate": 2e-05,
"loss": 0.9439,
"step": 1730
},
{
"epoch": 0.15468041603698107,
"grad_norm": 0.4381987154483795,
"learning_rate": 2e-05,
"loss": 0.9625,
"step": 1740
},
{
"epoch": 0.1555693839452396,
"grad_norm": 0.4465603530406952,
"learning_rate": 2e-05,
"loss": 0.9219,
"step": 1750
},
{
"epoch": 0.1564583518534981,
"grad_norm": 0.4344707727432251,
"learning_rate": 2e-05,
"loss": 0.9348,
"step": 1760
},
{
"epoch": 0.1573473197617566,
"grad_norm": 0.47260528802871704,
"learning_rate": 2e-05,
"loss": 0.9142,
"step": 1770
},
{
"epoch": 0.1582362876700151,
"grad_norm": 0.4460822641849518,
"learning_rate": 2e-05,
"loss": 0.9283,
"step": 1780
},
{
"epoch": 0.15912525557827362,
"grad_norm": 0.46511539816856384,
"learning_rate": 2e-05,
"loss": 0.9484,
"step": 1790
},
{
"epoch": 0.16001422348653213,
"grad_norm": 0.4567843973636627,
"learning_rate": 2e-05,
"loss": 0.9499,
"step": 1800
},
{
"epoch": 0.16090319139479065,
"grad_norm": 0.4729498326778412,
"learning_rate": 2e-05,
"loss": 0.9633,
"step": 1810
},
{
"epoch": 0.16179215930304916,
"grad_norm": 0.44997239112854004,
"learning_rate": 2e-05,
"loss": 0.9255,
"step": 1820
},
{
"epoch": 0.16268112721130767,
"grad_norm": 0.4489092230796814,
"learning_rate": 2e-05,
"loss": 0.947,
"step": 1830
},
{
"epoch": 0.1635700951195662,
"grad_norm": 0.5339633226394653,
"learning_rate": 2e-05,
"loss": 0.9434,
"step": 1840
},
{
"epoch": 0.1644590630278247,
"grad_norm": 0.4252396523952484,
"learning_rate": 2e-05,
"loss": 0.9074,
"step": 1850
},
{
"epoch": 0.16534803093608322,
"grad_norm": 0.477722704410553,
"learning_rate": 2e-05,
"loss": 0.9234,
"step": 1860
},
{
"epoch": 0.16623699884434173,
"grad_norm": 0.46278834342956543,
"learning_rate": 2e-05,
"loss": 0.8918,
"step": 1870
},
{
"epoch": 0.16712596675260022,
"grad_norm": 0.4720710515975952,
"learning_rate": 2e-05,
"loss": 0.9356,
"step": 1880
},
{
"epoch": 0.16801493466085873,
"grad_norm": 0.4468317925930023,
"learning_rate": 2e-05,
"loss": 0.9237,
"step": 1890
},
{
"epoch": 0.16890390256911725,
"grad_norm": 0.4632788300514221,
"learning_rate": 2e-05,
"loss": 0.9552,
"step": 1900
},
{
"epoch": 0.16979287047737576,
"grad_norm": 0.42456817626953125,
"learning_rate": 2e-05,
"loss": 0.901,
"step": 1910
},
{
"epoch": 0.17068183838563428,
"grad_norm": 0.4745561182498932,
"learning_rate": 2e-05,
"loss": 0.9236,
"step": 1920
},
{
"epoch": 0.1715708062938928,
"grad_norm": 0.43758249282836914,
"learning_rate": 2e-05,
"loss": 0.9205,
"step": 1930
},
{
"epoch": 0.1724597742021513,
"grad_norm": 0.45937028527259827,
"learning_rate": 2e-05,
"loss": 0.8825,
"step": 1940
},
{
"epoch": 0.17334874211040982,
"grad_norm": 0.43388575315475464,
"learning_rate": 2e-05,
"loss": 0.9254,
"step": 1950
},
{
"epoch": 0.17423771001866833,
"grad_norm": 0.4711926281452179,
"learning_rate": 2e-05,
"loss": 0.9437,
"step": 1960
},
{
"epoch": 0.17512667792692685,
"grad_norm": 0.44924527406692505,
"learning_rate": 2e-05,
"loss": 0.9241,
"step": 1970
},
{
"epoch": 0.17601564583518536,
"grad_norm": 0.42580580711364746,
"learning_rate": 2e-05,
"loss": 0.9162,
"step": 1980
},
{
"epoch": 0.17690461374344385,
"grad_norm": 0.4601577818393707,
"learning_rate": 2e-05,
"loss": 0.9473,
"step": 1990
},
{
"epoch": 0.17779358165170236,
"grad_norm": 0.4731871485710144,
"learning_rate": 2e-05,
"loss": 0.9462,
"step": 2000
},
{
"epoch": 0.17868254955996088,
"grad_norm": 0.4369046688079834,
"learning_rate": 2e-05,
"loss": 0.9724,
"step": 2010
},
{
"epoch": 0.1795715174682194,
"grad_norm": 0.4617767333984375,
"learning_rate": 2e-05,
"loss": 0.9402,
"step": 2020
},
{
"epoch": 0.1804604853764779,
"grad_norm": 0.45765435695648193,
"learning_rate": 2e-05,
"loss": 0.9275,
"step": 2030
},
{
"epoch": 0.18134945328473642,
"grad_norm": 0.44978591799736023,
"learning_rate": 2e-05,
"loss": 0.9216,
"step": 2040
},
{
"epoch": 0.18223842119299494,
"grad_norm": 0.45181888341903687,
"learning_rate": 2e-05,
"loss": 0.9389,
"step": 2050
},
{
"epoch": 0.18312738910125345,
"grad_norm": 0.6255255341529846,
"learning_rate": 2e-05,
"loss": 0.9226,
"step": 2060
},
{
"epoch": 0.18401635700951197,
"grad_norm": 0.44182655215263367,
"learning_rate": 2e-05,
"loss": 0.9273,
"step": 2070
},
{
"epoch": 0.18490532491777048,
"grad_norm": 0.4544832408428192,
"learning_rate": 2e-05,
"loss": 0.9089,
"step": 2080
},
{
"epoch": 0.18579429282602897,
"grad_norm": 0.44694894552230835,
"learning_rate": 2e-05,
"loss": 0.9495,
"step": 2090
},
{
"epoch": 0.18668326073428748,
"grad_norm": 0.4754018485546112,
"learning_rate": 2e-05,
"loss": 0.9208,
"step": 2100
},
{
"epoch": 0.187572228642546,
"grad_norm": 0.43904373049736023,
"learning_rate": 2e-05,
"loss": 0.9171,
"step": 2110
},
{
"epoch": 0.1884611965508045,
"grad_norm": 0.43585121631622314,
"learning_rate": 2e-05,
"loss": 0.9224,
"step": 2120
},
{
"epoch": 0.18935016445906303,
"grad_norm": 0.4322623908519745,
"learning_rate": 2e-05,
"loss": 0.9096,
"step": 2130
},
{
"epoch": 0.19023913236732154,
"grad_norm": 0.45563212037086487,
"learning_rate": 2e-05,
"loss": 0.9504,
"step": 2140
},
{
"epoch": 0.19112810027558005,
"grad_norm": 0.46097010374069214,
"learning_rate": 2e-05,
"loss": 0.9338,
"step": 2150
},
{
"epoch": 0.19201706818383857,
"grad_norm": 0.43504899740219116,
"learning_rate": 2e-05,
"loss": 0.92,
"step": 2160
},
{
"epoch": 0.19290603609209708,
"grad_norm": 0.4069807827472687,
"learning_rate": 2e-05,
"loss": 0.9284,
"step": 2170
},
{
"epoch": 0.1937950040003556,
"grad_norm": 0.4753881096839905,
"learning_rate": 2e-05,
"loss": 0.9163,
"step": 2180
},
{
"epoch": 0.1946839719086141,
"grad_norm": 0.42152369022369385,
"learning_rate": 2e-05,
"loss": 0.898,
"step": 2190
},
{
"epoch": 0.1955729398168726,
"grad_norm": 0.451825350522995,
"learning_rate": 2e-05,
"loss": 0.9228,
"step": 2200
},
{
"epoch": 0.1964619077251311,
"grad_norm": 0.47456032037734985,
"learning_rate": 2e-05,
"loss": 0.9294,
"step": 2210
},
{
"epoch": 0.19735087563338963,
"grad_norm": 0.4597964286804199,
"learning_rate": 2e-05,
"loss": 0.942,
"step": 2220
},
{
"epoch": 0.19823984354164814,
"grad_norm": 0.46146100759506226,
"learning_rate": 2e-05,
"loss": 1.0043,
"step": 2230
},
{
"epoch": 0.19912881144990666,
"grad_norm": 0.43969210982322693,
"learning_rate": 2e-05,
"loss": 0.9286,
"step": 2240
},
{
"epoch": 0.20001777935816517,
"grad_norm": 0.4327503740787506,
"learning_rate": 2e-05,
"loss": 0.9348,
"step": 2250
},
{
"epoch": 0.20090674726642369,
"grad_norm": 0.4259391725063324,
"learning_rate": 2e-05,
"loss": 0.9348,
"step": 2260
},
{
"epoch": 0.2017957151746822,
"grad_norm": 0.4238135516643524,
"learning_rate": 2e-05,
"loss": 0.9743,
"step": 2270
},
{
"epoch": 0.20268468308294071,
"grad_norm": 0.43770846724510193,
"learning_rate": 2e-05,
"loss": 0.9308,
"step": 2280
},
{
"epoch": 0.20357365099119923,
"grad_norm": 0.45749926567077637,
"learning_rate": 2e-05,
"loss": 0.9328,
"step": 2290
},
{
"epoch": 0.20446261889945774,
"grad_norm": 0.4421558976173401,
"learning_rate": 2e-05,
"loss": 0.9015,
"step": 2300
},
{
"epoch": 0.20535158680771623,
"grad_norm": 0.44268208742141724,
"learning_rate": 2e-05,
"loss": 0.9204,
"step": 2310
},
{
"epoch": 0.20624055471597474,
"grad_norm": 0.4365476667881012,
"learning_rate": 2e-05,
"loss": 0.9408,
"step": 2320
},
{
"epoch": 0.20712952262423326,
"grad_norm": 0.4565020799636841,
"learning_rate": 2e-05,
"loss": 0.9241,
"step": 2330
},
{
"epoch": 0.20801849053249177,
"grad_norm": 0.43321648240089417,
"learning_rate": 2e-05,
"loss": 0.9455,
"step": 2340
},
{
"epoch": 0.2089074584407503,
"grad_norm": 0.44953176379203796,
"learning_rate": 2e-05,
"loss": 0.9006,
"step": 2350
},
{
"epoch": 0.2097964263490088,
"grad_norm": 0.43321532011032104,
"learning_rate": 2e-05,
"loss": 0.9259,
"step": 2360
},
{
"epoch": 0.21068539425726732,
"grad_norm": 0.43398517370224,
"learning_rate": 2e-05,
"loss": 0.9238,
"step": 2370
},
{
"epoch": 0.21157436216552583,
"grad_norm": 0.4406549334526062,
"learning_rate": 2e-05,
"loss": 0.9206,
"step": 2380
},
{
"epoch": 0.21246333007378435,
"grad_norm": 0.45563289523124695,
"learning_rate": 2e-05,
"loss": 0.9107,
"step": 2390
},
{
"epoch": 0.21335229798204286,
"grad_norm": 0.4393308758735657,
"learning_rate": 2e-05,
"loss": 0.9071,
"step": 2400
},
{
"epoch": 0.21424126589030135,
"grad_norm": 0.4431764781475067,
"learning_rate": 2e-05,
"loss": 0.9264,
"step": 2410
},
{
"epoch": 0.21513023379855986,
"grad_norm": 0.423136830329895,
"learning_rate": 2e-05,
"loss": 0.9301,
"step": 2420
},
{
"epoch": 0.21601920170681838,
"grad_norm": 0.42495959997177124,
"learning_rate": 2e-05,
"loss": 0.9082,
"step": 2430
},
{
"epoch": 0.2169081696150769,
"grad_norm": 0.4279535710811615,
"learning_rate": 2e-05,
"loss": 0.8823,
"step": 2440
},
{
"epoch": 0.2177971375233354,
"grad_norm": 0.4287704527378082,
"learning_rate": 2e-05,
"loss": 0.9135,
"step": 2450
},
{
"epoch": 0.21868610543159392,
"grad_norm": 0.43721771240234375,
"learning_rate": 2e-05,
"loss": 0.9327,
"step": 2460
},
{
"epoch": 0.21957507333985243,
"grad_norm": 0.4303989112377167,
"learning_rate": 2e-05,
"loss": 0.9058,
"step": 2470
},
{
"epoch": 0.22046404124811095,
"grad_norm": 0.43652382493019104,
"learning_rate": 2e-05,
"loss": 0.9157,
"step": 2480
},
{
"epoch": 0.22135300915636946,
"grad_norm": 0.4485083520412445,
"learning_rate": 2e-05,
"loss": 0.9024,
"step": 2490
},
{
"epoch": 0.22224197706462798,
"grad_norm": 0.4460156261920929,
"learning_rate": 2e-05,
"loss": 0.9064,
"step": 2500
},
{
"epoch": 0.2231309449728865,
"grad_norm": 0.4979501962661743,
"learning_rate": 2e-05,
"loss": 0.8991,
"step": 2510
},
{
"epoch": 0.22401991288114498,
"grad_norm": 0.4301646053791046,
"learning_rate": 2e-05,
"loss": 0.9366,
"step": 2520
},
{
"epoch": 0.2249088807894035,
"grad_norm": 0.45495837926864624,
"learning_rate": 2e-05,
"loss": 0.9183,
"step": 2530
},
{
"epoch": 0.225797848697662,
"grad_norm": 0.5348328351974487,
"learning_rate": 2e-05,
"loss": 0.8963,
"step": 2540
},
{
"epoch": 0.22668681660592052,
"grad_norm": 0.3985919952392578,
"learning_rate": 1.9980979278401095e-05,
"loss": 0.9202,
"step": 2550
},
{
"epoch": 0.22757578451417904,
"grad_norm": 0.41780054569244385,
"learning_rate": 1.982924955463327e-05,
"loss": 0.9042,
"step": 2560
},
{
"epoch": 0.22846475242243755,
"grad_norm": 0.4487382471561432,
"learning_rate": 1.9528108298328235e-05,
"loss": 0.9029,
"step": 2570
},
{
"epoch": 0.22935372033069606,
"grad_norm": 0.43859750032424927,
"learning_rate": 1.9082156473635994e-05,
"loss": 0.9447,
"step": 2580
},
{
"epoch": 0.23024268823895458,
"grad_norm": 0.4244905114173889,
"learning_rate": 1.8498207522139434e-05,
"loss": 0.8991,
"step": 2590
},
{
"epoch": 0.2311316561472131,
"grad_norm": 0.4426525831222534,
"learning_rate": 1.7785183264196977e-05,
"loss": 0.9378,
"step": 2600
},
{
"epoch": 0.2320206240554716,
"grad_norm": 0.4329013526439667,
"learning_rate": 1.6953977587577846e-05,
"loss": 0.8998,
"step": 2610
},
{
"epoch": 0.23290959196373012,
"grad_norm": 0.39430952072143555,
"learning_rate": 1.601729000601297e-05,
"loss": 0.9149,
"step": 2620
},
{
"epoch": 0.2337985598719886,
"grad_norm": 0.43645504117012024,
"learning_rate": 1.4989431630624763e-05,
"loss": 0.9035,
"step": 2630
},
{
"epoch": 0.23468752778024712,
"grad_norm": 0.5260468125343323,
"learning_rate": 1.3886106518686746e-05,
"loss": 0.9378,
"step": 2640
},
{
"epoch": 0.23557649568850564,
"grad_norm": 0.4265429973602295,
"learning_rate": 1.2724171740359612e-05,
"loss": 0.9296,
"step": 2650
},
{
"epoch": 0.23646546359676415,
"grad_norm": 0.4294310212135315,
"learning_rate": 1.1521379829206218e-05,
"loss": 0.9089,
"step": 2660
},
{
"epoch": 0.23735443150502267,
"grad_norm": 0.3869112730026245,
"learning_rate": 1.029610755143595e-05,
"loss": 0.8842,
"step": 2670
},
{
"epoch": 0.23824339941328118,
"grad_norm": 0.42560723423957825,
"learning_rate": 9.067075137857348e-06,
"loss": 0.919,
"step": 2680
},
{
"epoch": 0.2391323673215397,
"grad_norm": 0.5010161399841309,
"learning_rate": 7.853060268232525e-06,
"loss": 0.8967,
"step": 2690
},
{
"epoch": 0.2400213352297982,
"grad_norm": 0.41254520416259766,
"learning_rate": 6.672611177902054e-06,
"loss": 0.8722,
"step": 2700
},
{
"epoch": 0.24091030313805673,
"grad_norm": 0.41050252318382263,
"learning_rate": 5.543763269959312e-06,
"loss": 0.8919,
"step": 2710
},
{
"epoch": 0.24179927104631524,
"grad_norm": 0.43112391233444214,
"learning_rate": 4.483763562693867e-06,
"loss": 0.8909,
"step": 2720
},
{
"epoch": 0.24268823895457373,
"grad_norm": 0.43985289335250854,
"learning_rate": 3.508807182313187e-06,
"loss": 0.8812,
"step": 2730
},
{
"epoch": 0.24357720686283224,
"grad_norm": 0.42094886302948,
"learning_rate": 2.6337899269187294e-06,
"loss": 0.9153,
"step": 2740
},
{
"epoch": 0.24446617477109076,
"grad_norm": 0.4215700924396515,
"learning_rate": 1.8720806821693126e-06,
"loss": 0.8994,
"step": 2750
},
{
"epoch": 0.24535514267934927,
"grad_norm": 0.4199082851409912,
"learning_rate": 1.2353171657619887e-06,
"loss": 0.9055,
"step": 2760
},
{
"epoch": 0.24624411058760778,
"grad_norm": 0.4178229570388794,
"learning_rate": 7.332281214330356e-07,
"loss": 0.8871,
"step": 2770
},
{
"epoch": 0.2471330784958663,
"grad_norm": 0.4354834258556366,
"learning_rate": 3.73484679074808e-07,
"loss": 0.9173,
"step": 2780
},
{
"epoch": 0.2480220464041248,
"grad_norm": 0.4030560255050659,
"learning_rate": 1.61583151951702e-07,
"loss": 0.9178,
"step": 2790
},
{
"epoch": 0.24873322073073162,
"step": 2798,
"total_flos": 1.1366756130249245e+19,
"train_loss": 0.08288464024716229,
"train_runtime": 2316.3386,
"train_samples_per_second": 14.495,
"train_steps_per_second": 1.208
}
],
"logging_steps": 10,
"max_steps": 2798,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 159,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.1366756130249245e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.24873322073073162,
"eval_steps": 500,
"global_step": 2798,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008889679082585119,
"grad_norm": 4.238861560821533,
"learning_rate": 1.1061797752808989e-06,
"loss": 1.7261,
"step": 10
},
{
"epoch": 0.0017779358165170237,
"grad_norm": 2.0652520656585693,
"learning_rate": 2.2241573033707866e-06,
"loss": 1.6328,
"step": 20
},
{
"epoch": 0.0026669037247755356,
"grad_norm": 1.8617759943008423,
"learning_rate": 3.342134831460675e-06,
"loss": 1.3995,
"step": 30
},
{
"epoch": 0.0035558716330340474,
"grad_norm": 1.4548546075820923,
"learning_rate": 4.4601123595505624e-06,
"loss": 1.3222,
"step": 40
},
{
"epoch": 0.004444839541292559,
"grad_norm": 0.696451723575592,
"learning_rate": 5.5780898876404495e-06,
"loss": 1.2108,
"step": 50
},
{
"epoch": 0.005333807449551071,
"grad_norm": 0.679622232913971,
"learning_rate": 6.6960674157303374e-06,
"loss": 1.1247,
"step": 60
},
{
"epoch": 0.006222775357809583,
"grad_norm": 0.6772049069404602,
"learning_rate": 7.814044943820226e-06,
"loss": 1.0773,
"step": 70
},
{
"epoch": 0.007111743266068095,
"grad_norm": 0.5850681662559509,
"learning_rate": 8.932022471910112e-06,
"loss": 1.0619,
"step": 80
},
{
"epoch": 0.008000711174326608,
"grad_norm": 0.595498263835907,
"learning_rate": 1.005e-05,
"loss": 1.0314,
"step": 90
},
{
"epoch": 0.008889679082585119,
"grad_norm": 0.533685028553009,
"learning_rate": 1.1167977528089888e-05,
"loss": 1.0384,
"step": 100
},
{
"epoch": 0.009778646990843631,
"grad_norm": 0.5636975765228271,
"learning_rate": 1.2285955056179776e-05,
"loss": 1.055,
"step": 110
},
{
"epoch": 0.010667614899102142,
"grad_norm": 0.523317277431488,
"learning_rate": 1.3403932584269664e-05,
"loss": 1.051,
"step": 120
},
{
"epoch": 0.011556582807360655,
"grad_norm": 0.548605740070343,
"learning_rate": 1.4521910112359552e-05,
"loss": 1.0005,