Hugging Face's logo

open-sci
/
open-sci-1.7b-nemotron-cc-1T-oh-dcft

Feature Extraction
Transformers
Safetensors
opensci
llama-factory
full
Generated from Trainer
custom_code
Model card Files
xet
 Community
open-sci-1.7b-nemotron-cc-1T-oh-dcft / trainer_state.json
marianna13's picture
marianna13
Upload folder using huggingface_hub
b2f4a9f verified
raw
history blame contribute delete
93.9 kB
{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 3.0,
 "eval_steps": 500,
 "global_step": 5871,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.005109862033725089,
 "grad_norm": 0.33659857760959316,
 "learning_rate": 5e-06,
 "loss": 1.2266,
 "step": 10
 },
 {
 "epoch": 0.010219724067450179,
 "grad_norm": 0.27906848020280245,
 "learning_rate": 5e-06,
 "loss": 1.1927,
 "step": 20
 },
 {
 "epoch": 0.015329586101175269,
 "grad_norm": 0.17780612512031585,
 "learning_rate": 5e-06,
 "loss": 1.1325,
 "step": 30
 },
 {
 "epoch": 0.020439448134900357,
 "grad_norm": 0.1258477993946921,
 "learning_rate": 5e-06,
 "loss": 1.0755,
 "step": 40
 },
 {
 "epoch": 0.025549310168625446,
 "grad_norm": 0.10850896052962487,
 "learning_rate": 5e-06,
 "loss": 1.0559,
 "step": 50
 },
 {
 "epoch": 0.030659172202350538,
 "grad_norm": 0.1008214475411604,
 "learning_rate": 5e-06,
 "loss": 1.0381,
 "step": 60
 },
 {
 "epoch": 0.03576903423607562,
 "grad_norm": 0.09230130516181131,
 "learning_rate": 5e-06,
 "loss": 1.0359,
 "step": 70
 },
 {
 "epoch": 0.040878896269800714,
 "grad_norm": 0.12761405349230925,
 "learning_rate": 5e-06,
 "loss": 1.02,
 "step": 80
 },
 {
 "epoch": 0.045988758303525806,
 "grad_norm": 0.09657363359659779,
 "learning_rate": 5e-06,
 "loss": 1.0108,
 "step": 90
 },
 {
 "epoch": 0.05109862033725089,
 "grad_norm": 0.07985711883606804,
 "learning_rate": 5e-06,
 "loss": 1.0112,
 "step": 100
 },
 {
 "epoch": 0.05620848237097598,
 "grad_norm": 0.3841577988890222,
 "learning_rate": 5e-06,
 "loss": 1.004,
 "step": 110
 },
 {
 "epoch": 0.061318344404701075,
 "grad_norm": 0.07880791404523275,
 "learning_rate": 5e-06,
 "loss": 1.0005,
 "step": 120
 },
 {
 "epoch": 0.06642820643842616,
 "grad_norm": 0.07684646209763941,
 "learning_rate": 5e-06,
 "loss": 0.9969,
 "step": 130
 },
 {
 "epoch": 0.07153806847215124,
 "grad_norm": 0.07364942700770905,
 "learning_rate": 5e-06,
 "loss": 0.9817,
 "step": 140
 },
 {
 "epoch": 0.07664793050587634,
 "grad_norm": 0.07307840824030326,
 "learning_rate": 5e-06,
 "loss": 1.0017,
 "step": 150
 },
 {
 "epoch": 0.08175779253960143,
 "grad_norm": 0.07899180708739008,
 "learning_rate": 5e-06,
 "loss": 1.0064,
 "step": 160
 },
 {
 "epoch": 0.08686765457332651,
 "grad_norm": 0.13990750744492506,
 "learning_rate": 5e-06,
 "loss": 0.9664,
 "step": 170
 },
 {
 "epoch": 0.09197751660705161,
 "grad_norm": 0.07623610966974216,
 "learning_rate": 5e-06,
 "loss": 0.993,
 "step": 180
 },
 {
 "epoch": 0.0970873786407767,
 "grad_norm": 0.07177184337925457,
 "learning_rate": 5e-06,
 "loss": 0.9802,
 "step": 190
 },
 {
 "epoch": 0.10219724067450178,
 "grad_norm": 0.07599595168859198,
 "learning_rate": 5e-06,
 "loss": 0.9821,
 "step": 200
 },
 {
 "epoch": 0.10730710270822688,
 "grad_norm": 0.08156619926999734,
 "learning_rate": 5e-06,
 "loss": 0.9848,
 "step": 210
 },
 {
 "epoch": 0.11241696474195197,
 "grad_norm": 0.08647559353210667,
 "learning_rate": 5e-06,
 "loss": 0.9669,
 "step": 220
 },
 {
 "epoch": 0.11752682677567705,
 "grad_norm": 0.09175368496172068,
 "learning_rate": 5e-06,
 "loss": 0.9768,
 "step": 230
 },
 {
 "epoch": 0.12263668880940215,
 "grad_norm": 0.07679212882863759,
 "learning_rate": 5e-06,
 "loss": 0.9785,
 "step": 240
 },
 {
 "epoch": 0.12774655084312725,
 "grad_norm": 0.0876157967492165,
 "learning_rate": 5e-06,
 "loss": 0.97,
 "step": 250
 },
 {
 "epoch": 0.13285641287685232,
 "grad_norm": 0.07438658820336003,
 "learning_rate": 5e-06,
 "loss": 0.9642,
 "step": 260
 },
 {
 "epoch": 0.13796627491057742,
 "grad_norm": 0.11327800060102156,
 "learning_rate": 5e-06,
 "loss": 0.9566,
 "step": 270
 },
 {
 "epoch": 0.1430761369443025,
 "grad_norm": 0.07300739672589697,
 "learning_rate": 5e-06,
 "loss": 0.9641,
 "step": 280
 },
 {
 "epoch": 0.1481859989780276,
 "grad_norm": 0.0706224800129807,
 "learning_rate": 5e-06,
 "loss": 0.9608,
 "step": 290
 },
 {
 "epoch": 0.1532958610117527,
 "grad_norm": 0.10268101288716767,
 "learning_rate": 5e-06,
 "loss": 0.9594,
 "step": 300
 },
 {
 "epoch": 0.15840572304547776,
 "grad_norm": 0.10115126588406155,
 "learning_rate": 5e-06,
 "loss": 0.9497,
 "step": 310
 },
 {
 "epoch": 0.16351558507920286,
 "grad_norm": 0.07906545142322015,
 "learning_rate": 5e-06,
 "loss": 0.9708,
 "step": 320
 },
 {
 "epoch": 0.16862544711292796,
 "grad_norm": 0.08205445152944524,
 "learning_rate": 5e-06,
 "loss": 0.9578,
 "step": 330
 },
 {
 "epoch": 0.17373530914665303,
 "grad_norm": 0.08422630569633463,
 "learning_rate": 5e-06,
 "loss": 0.9596,
 "step": 340
 },
 {
 "epoch": 0.17884517118037813,
 "grad_norm": 0.08374924134366432,
 "learning_rate": 5e-06,
 "loss": 0.9538,
 "step": 350
 },
 {
 "epoch": 0.18395503321410323,
 "grad_norm": 0.07381594898486545,
 "learning_rate": 5e-06,
 "loss": 0.9632,
 "step": 360
 },
 {
 "epoch": 0.1890648952478283,
 "grad_norm": 0.0742024858441321,
 "learning_rate": 5e-06,
 "loss": 0.9574,
 "step": 370
 },
 {
 "epoch": 0.1941747572815534,
 "grad_norm": 0.07635133337670513,
 "learning_rate": 5e-06,
 "loss": 0.9642,
 "step": 380
 },
 {
 "epoch": 0.1992846193152785,
 "grad_norm": 0.07547026097910627,
 "learning_rate": 5e-06,
 "loss": 0.9559,
 "step": 390
 },
 {
 "epoch": 0.20439448134900357,
 "grad_norm": 0.08098346259777026,
 "learning_rate": 5e-06,
 "loss": 0.9608,
 "step": 400
 },
 {
 "epoch": 0.20950434338272866,
 "grad_norm": 0.0740110860457063,
 "learning_rate": 5e-06,
 "loss": 0.9626,
 "step": 410
 },
 {
 "epoch": 0.21461420541645376,
 "grad_norm": 0.06838098261628725,
 "learning_rate": 5e-06,
 "loss": 0.956,
 "step": 420
 },
 {
 "epoch": 0.21972406745017883,
 "grad_norm": 0.07627481328859255,
 "learning_rate": 5e-06,
 "loss": 0.947,
 "step": 430
 },
 {
 "epoch": 0.22483392948390393,
 "grad_norm": 0.07121602448305268,
 "learning_rate": 5e-06,
 "loss": 0.936,
 "step": 440
 },
 {
 "epoch": 0.22994379151762903,
 "grad_norm": 0.07130096221687535,
 "learning_rate": 5e-06,
 "loss": 0.9489,
 "step": 450
 },
 {
 "epoch": 0.2350536535513541,
 "grad_norm": 0.0705427638202678,
 "learning_rate": 5e-06,
 "loss": 0.9488,
 "step": 460
 },
 {
 "epoch": 0.2401635155850792,
 "grad_norm": 0.07263405103965026,
 "learning_rate": 5e-06,
 "loss": 0.9577,
 "step": 470
 },
 {
 "epoch": 0.2452733776188043,
 "grad_norm": 0.11012974887960399,
 "learning_rate": 5e-06,
 "loss": 0.943,
 "step": 480
 },
 {
 "epoch": 0.2503832396525294,
 "grad_norm": 0.10355809585077033,
 "learning_rate": 5e-06,
 "loss": 0.939,
 "step": 490
 },
 {
 "epoch": 0.2554931016862545,
 "grad_norm": 0.0793194619120587,
 "learning_rate": 5e-06,
 "loss": 0.9461,
 "step": 500
 },
 {
 "epoch": 0.26060296371997954,
 "grad_norm": 0.07305857929904291,
 "learning_rate": 5e-06,
 "loss": 0.94,
 "step": 510
 },
 {
 "epoch": 0.26571282575370464,
 "grad_norm": 0.07524998598879123,
 "learning_rate": 5e-06,
 "loss": 0.9346,
 "step": 520
 },
 {
 "epoch": 0.27082268778742974,
 "grad_norm": 0.07947372908760092,
 "learning_rate": 5e-06,
 "loss": 0.9469,
 "step": 530
 },
 {
 "epoch": 0.27593254982115484,
 "grad_norm": 0.1241601221912902,
 "learning_rate": 5e-06,
 "loss": 0.9439,
 "step": 540
 },
 {
 "epoch": 0.28104241185487994,
 "grad_norm": 0.09428433932371161,
 "learning_rate": 5e-06,
 "loss": 0.9364,
 "step": 550
 },
 {
 "epoch": 0.286152273888605,
 "grad_norm": 0.07643085121646655,
 "learning_rate": 5e-06,
 "loss": 0.9362,
 "step": 560
 },
 {
 "epoch": 0.2912621359223301,
 "grad_norm": 0.07053914919464828,
 "learning_rate": 5e-06,
 "loss": 0.9434,
 "step": 570
 },
 {
 "epoch": 0.2963719979560552,
 "grad_norm": 0.07770599024749027,
 "learning_rate": 5e-06,
 "loss": 0.9339,
 "step": 580
 },
 {
 "epoch": 0.3014818599897803,
 "grad_norm": 0.07178293782557839,
 "learning_rate": 5e-06,
 "loss": 0.9375,
 "step": 590
 },
 {
 "epoch": 0.3065917220235054,
 "grad_norm": 0.08584366089279562,
 "learning_rate": 5e-06,
 "loss": 0.9371,
 "step": 600
 },
 {
 "epoch": 0.3117015840572305,
 "grad_norm": 0.07944827441074408,
 "learning_rate": 5e-06,
 "loss": 0.9455,
 "step": 610
 },
 {
 "epoch": 0.3168114460909555,
 "grad_norm": 0.07201506395499371,
 "learning_rate": 5e-06,
 "loss": 0.9468,
 "step": 620
 },
 {
 "epoch": 0.3219213081246806,
 "grad_norm": 0.06802889338099032,
 "learning_rate": 5e-06,
 "loss": 0.9216,
 "step": 630
 },
 {
 "epoch": 0.3270311701584057,
 "grad_norm": 0.07330902217526364,
 "learning_rate": 5e-06,
 "loss": 0.9236,
 "step": 640
 },
 {
 "epoch": 0.3321410321921308,
 "grad_norm": 0.07252233851918731,
 "learning_rate": 5e-06,
 "loss": 0.9389,
 "step": 650
 },
 {
 "epoch": 0.3372508942258559,
 "grad_norm": 0.07496139269293961,
 "learning_rate": 5e-06,
 "loss": 0.9237,
 "step": 660
 },
 {
 "epoch": 0.342360756259581,
 "grad_norm": 0.07750656954616246,
 "learning_rate": 5e-06,
 "loss": 0.9369,
 "step": 670
 },
 {
 "epoch": 0.34747061829330605,
 "grad_norm": 0.07099579035430438,
 "learning_rate": 5e-06,
 "loss": 0.9305,
 "step": 680
 },
 {
 "epoch": 0.35258048032703115,
 "grad_norm": 0.07147696465885814,
 "learning_rate": 5e-06,
 "loss": 0.9278,
 "step": 690
 },
 {
 "epoch": 0.35769034236075625,
 "grad_norm": 0.06679094313753112,
 "learning_rate": 5e-06,
 "loss": 0.9209,
 "step": 700
 },
 {
 "epoch": 0.36280020439448135,
 "grad_norm": 0.0741205857711921,
 "learning_rate": 5e-06,
 "loss": 0.9239,
 "step": 710
 },
 {
 "epoch": 0.36791006642820645,
 "grad_norm": 0.07314565717664778,
 "learning_rate": 5e-06,
 "loss": 0.9228,
 "step": 720
 },
 {
 "epoch": 0.37301992846193155,
 "grad_norm": 0.06970796428185207,
 "learning_rate": 5e-06,
 "loss": 0.9261,
 "step": 730
 },
 {
 "epoch": 0.3781297904956566,
 "grad_norm": 0.08781289255732734,
 "learning_rate": 5e-06,
 "loss": 0.9184,
 "step": 740
 },
 {
 "epoch": 0.3832396525293817,
 "grad_norm": 0.0733298775244439,
 "learning_rate": 5e-06,
 "loss": 0.9239,
 "step": 750
 },
 {
 "epoch": 0.3883495145631068,
 "grad_norm": 0.07059494784250205,
 "learning_rate": 5e-06,
 "loss": 0.9256,
 "step": 760
 },
 {
 "epoch": 0.3934593765968319,
 "grad_norm": 0.07435764722394751,
 "learning_rate": 5e-06,
 "loss": 0.9317,
 "step": 770
 },
 {
 "epoch": 0.398569238630557,
 "grad_norm": 0.08580109544056579,
 "learning_rate": 5e-06,
 "loss": 0.915,
 "step": 780
 },
 {
 "epoch": 0.4036791006642821,
 "grad_norm": 0.13857712945248865,
 "learning_rate": 5e-06,
 "loss": 0.9266,
 "step": 790
 },
 {
 "epoch": 0.40878896269800713,
 "grad_norm": 0.09252960975773743,
 "learning_rate": 5e-06,
 "loss": 0.9292,
 "step": 800
 },
 {
 "epoch": 0.41389882473173223,
 "grad_norm": 0.0786939477268516,
 "learning_rate": 5e-06,
 "loss": 0.9229,
 "step": 810
 },
 {
 "epoch": 0.4190086867654573,
 "grad_norm": 0.07870146545651402,
 "learning_rate": 5e-06,
 "loss": 0.9222,
 "step": 820
 },
 {
 "epoch": 0.4241185487991824,
 "grad_norm": 0.22636518086425345,
 "learning_rate": 5e-06,
 "loss": 0.9198,
 "step": 830
 },
 {
 "epoch": 0.4292284108329075,
 "grad_norm": 0.07019267445206644,
 "learning_rate": 5e-06,
 "loss": 0.9175,
 "step": 840
 },
 {
 "epoch": 0.4343382728666326,
 "grad_norm": 0.1807350892295952,
 "learning_rate": 5e-06,
 "loss": 0.9196,
 "step": 850
 },
 {
 "epoch": 0.43944813490035767,
 "grad_norm": 0.0725849350335069,
 "learning_rate": 5e-06,
 "loss": 0.9125,
 "step": 860
 },
 {
 "epoch": 0.44455799693408277,
 "grad_norm": 0.07593721579585741,
 "learning_rate": 5e-06,
 "loss": 0.9281,
 "step": 870
 },
 {
 "epoch": 0.44966785896780787,
 "grad_norm": 0.07560334097743046,
 "learning_rate": 5e-06,
 "loss": 0.9135,
 "step": 880
 },
 {
 "epoch": 0.45477772100153296,
 "grad_norm": 0.06971504265848284,
 "learning_rate": 5e-06,
 "loss": 0.9237,
 "step": 890
 },
 {
 "epoch": 0.45988758303525806,
 "grad_norm": 0.07156759501755959,
 "learning_rate": 5e-06,
 "loss": 0.9138,
 "step": 900
 },
 {
 "epoch": 0.46499744506898316,
 "grad_norm": 0.07895160546618792,
 "learning_rate": 5e-06,
 "loss": 0.921,
 "step": 910
 },
 {
 "epoch": 0.4701073071027082,
 "grad_norm": 0.07451564044792575,
 "learning_rate": 5e-06,
 "loss": 0.9199,
 "step": 920
 },
 {
 "epoch": 0.4752171691364333,
 "grad_norm": 0.10378845787672986,
 "learning_rate": 5e-06,
 "loss": 0.9265,
 "step": 930
 },
 {
 "epoch": 0.4803270311701584,
 "grad_norm": 0.0667143142951708,
 "learning_rate": 5e-06,
 "loss": 0.9177,
 "step": 940
 },
 {
 "epoch": 0.4854368932038835,
 "grad_norm": 0.1158465430965177,
 "learning_rate": 5e-06,
 "loss": 0.9226,
 "step": 950
 },
 {
 "epoch": 0.4905467552376086,
 "grad_norm": 0.07122640133664004,
 "learning_rate": 5e-06,
 "loss": 0.9264,
 "step": 960
 },
 {
 "epoch": 0.4956566172713337,
 "grad_norm": 0.07221992051194193,
 "learning_rate": 5e-06,
 "loss": 0.9131,
 "step": 970
 },
 {
 "epoch": 0.5007664793050588,
 "grad_norm": 0.07924509176000209,
 "learning_rate": 5e-06,
 "loss": 0.9125,
 "step": 980
 },
 {
 "epoch": 0.5058763413387839,
 "grad_norm": 0.07672190213186483,
 "learning_rate": 5e-06,
 "loss": 0.9122,
 "step": 990
 },
 {
 "epoch": 0.510986203372509,
 "grad_norm": 0.07692062751941903,
 "learning_rate": 5e-06,
 "loss": 0.929,
 "step": 1000
 },
 {
 "epoch": 0.516096065406234,
 "grad_norm": 0.11741801773911116,
 "learning_rate": 5e-06,
 "loss": 0.9159,
 "step": 1010
 },
 {
 "epoch": 0.5212059274399591,
 "grad_norm": 0.07370462072026876,
 "learning_rate": 5e-06,
 "loss": 0.9297,
 "step": 1020
 },
 {
 "epoch": 0.5263157894736842,
 "grad_norm": 0.07324740223664235,
 "learning_rate": 5e-06,
 "loss": 0.9102,
 "step": 1030
 },
 {
 "epoch": 0.5314256515074093,
 "grad_norm": 0.06719441090965804,
 "learning_rate": 5e-06,
 "loss": 0.9095,
 "step": 1040
 },
 {
 "epoch": 0.5365355135411344,
 "grad_norm": 0.0752101579557485,
 "learning_rate": 5e-06,
 "loss": 0.9118,
 "step": 1050
 },
 {
 "epoch": 0.5416453755748595,
 "grad_norm": 0.07316438131338852,
 "learning_rate": 5e-06,
 "loss": 0.909,
 "step": 1060
 },
 {
 "epoch": 0.5467552376085846,
 "grad_norm": 0.07217762056098373,
 "learning_rate": 5e-06,
 "loss": 0.9045,
 "step": 1070
 },
 {
 "epoch": 0.5518650996423097,
 "grad_norm": 0.06882269438361814,
 "learning_rate": 5e-06,
 "loss": 0.9241,
 "step": 1080
 },
 {
 "epoch": 0.5569749616760348,
 "grad_norm": 0.18147585225890778,
 "learning_rate": 5e-06,
 "loss": 0.9167,
 "step": 1090
 },
 {
 "epoch": 0.5620848237097599,
 "grad_norm": 0.07945137709096421,
 "learning_rate": 5e-06,
 "loss": 0.9058,
 "step": 1100
 },
 {
 "epoch": 0.567194685743485,
 "grad_norm": 0.06985941949554184,
 "learning_rate": 5e-06,
 "loss": 0.9159,
 "step": 1110
 },
 {
 "epoch": 0.57230454777721,
 "grad_norm": 0.07626155133966736,
 "learning_rate": 5e-06,
 "loss": 0.9152,
 "step": 1120
 },
 {
 "epoch": 0.5774144098109351,
 "grad_norm": 0.07367359682427968,
 "learning_rate": 5e-06,
 "loss": 0.9033,
 "step": 1130
 },
 {
 "epoch": 0.5825242718446602,
 "grad_norm": 0.07246294215791606,
 "learning_rate": 5e-06,
 "loss": 0.9056,
 "step": 1140
 },
 {
 "epoch": 0.5876341338783853,
 "grad_norm": 0.06636935667746374,
 "learning_rate": 5e-06,
 "loss": 0.9096,
 "step": 1150
 },
 {
 "epoch": 0.5927439959121104,
 "grad_norm": 0.06914204310614962,
 "learning_rate": 5e-06,
 "loss": 0.9124,
 "step": 1160
 },
 {
 "epoch": 0.5978538579458355,
 "grad_norm": 0.06622472549827609,
 "learning_rate": 5e-06,
 "loss": 0.9042,
 "step": 1170
 },
 {
 "epoch": 0.6029637199795606,
 "grad_norm": 0.07526422643221314,
 "learning_rate": 5e-06,
 "loss": 0.9099,
 "step": 1180
 },
 {
 "epoch": 0.6080735820132857,
 "grad_norm": 0.07865312982736179,
 "learning_rate": 5e-06,
 "loss": 0.9121,
 "step": 1190
 },
 {
 "epoch": 0.6131834440470108,
 "grad_norm": 0.08100630197435015,
 "learning_rate": 5e-06,
 "loss": 0.9108,
 "step": 1200
 },
 {
 "epoch": 0.6182933060807358,
 "grad_norm": 0.14439251719042823,
 "learning_rate": 5e-06,
 "loss": 0.9085,
 "step": 1210
 },
 {
 "epoch": 0.623403168114461,
 "grad_norm": 0.07351842090072493,
 "learning_rate": 5e-06,
 "loss": 0.9102,
 "step": 1220
 },
 {
 "epoch": 0.628513030148186,
 "grad_norm": 0.0710785086017881,
 "learning_rate": 5e-06,
 "loss": 0.9137,
 "step": 1230
 },
 {
 "epoch": 0.633622892181911,
 "grad_norm": 0.07184247120200028,
 "learning_rate": 5e-06,
 "loss": 0.8997,
 "step": 1240
 },
 {
 "epoch": 0.6387327542156361,
 "grad_norm": 0.07131702245604768,
 "learning_rate": 5e-06,
 "loss": 0.9087,
 "step": 1250
 },
 {
 "epoch": 0.6438426162493612,
 "grad_norm": 0.0730402054534026,
 "learning_rate": 5e-06,
 "loss": 0.894,
 "step": 1260
 },
 {
 "epoch": 0.6489524782830863,
 "grad_norm": 0.07322424351281255,
 "learning_rate": 5e-06,
 "loss": 0.9127,
 "step": 1270
 },
 {
 "epoch": 0.6540623403168114,
 "grad_norm": 0.09436026180688377,
 "learning_rate": 5e-06,
 "loss": 0.919,
 "step": 1280
 },
 {
 "epoch": 0.6591722023505365,
 "grad_norm": 0.07076855510548616,
 "learning_rate": 5e-06,
 "loss": 0.9044,
 "step": 1290
 },
 {
 "epoch": 0.6642820643842616,
 "grad_norm": 0.07409183519590924,
 "learning_rate": 5e-06,
 "loss": 0.8925,
 "step": 1300
 },
 {
 "epoch": 0.6693919264179867,
 "grad_norm": 0.3253569122085339,
 "learning_rate": 5e-06,
 "loss": 0.897,
 "step": 1310
 },
 {
 "epoch": 0.6745017884517118,
 "grad_norm": 0.07002482080488048,
 "learning_rate": 5e-06,
 "loss": 0.8905,
 "step": 1320
 },
 {
 "epoch": 0.6796116504854369,
 "grad_norm": 0.8542494508434101,
 "learning_rate": 5e-06,
 "loss": 0.9052,
 "step": 1330
 },
 {
 "epoch": 0.684721512519162,
 "grad_norm": 0.09406257309495393,
 "learning_rate": 5e-06,
 "loss": 0.91,
 "step": 1340
 },
 {
 "epoch": 0.6898313745528871,
 "grad_norm": 0.08661096377263379,
 "learning_rate": 5e-06,
 "loss": 0.9096,
 "step": 1350
 },
 {
 "epoch": 0.6949412365866121,
 "grad_norm": 0.07544412418690473,
 "learning_rate": 5e-06,
 "loss": 0.9039,
 "step": 1360
 },
 {
 "epoch": 0.7000510986203372,
 "grad_norm": 0.07803646465670126,
 "learning_rate": 5e-06,
 "loss": 0.8892,
 "step": 1370
 },
 {
 "epoch": 0.7051609606540623,
 "grad_norm": 0.07088553834184458,
 "learning_rate": 5e-06,
 "loss": 0.8975,
 "step": 1380
 },
 {
 "epoch": 0.7102708226877874,
 "grad_norm": 0.08931444692520309,
 "learning_rate": 5e-06,
 "loss": 0.882,
 "step": 1390
 },
 {
 "epoch": 0.7153806847215125,
 "grad_norm": 0.07261368946056458,
 "learning_rate": 5e-06,
 "loss": 0.903,
 "step": 1400
 },
 {
 "epoch": 0.7204905467552376,
 "grad_norm": 0.07364955770557434,
 "learning_rate": 5e-06,
 "loss": 0.9019,
 "step": 1410
 },
 {
 "epoch": 0.7256004087889627,
 "grad_norm": 0.07232725672310655,
 "learning_rate": 5e-06,
 "loss": 0.9047,
 "step": 1420
 },
 {
 "epoch": 0.7307102708226878,
 "grad_norm": 0.07284538520098455,
 "learning_rate": 5e-06,
 "loss": 0.8969,
 "step": 1430
 },
 {
 "epoch": 0.7358201328564129,
 "grad_norm": 0.06804520794145767,
 "learning_rate": 5e-06,
 "loss": 0.8983,
 "step": 1440
 },
 {
 "epoch": 0.740929994890138,
 "grad_norm": 0.07080981200832792,
 "learning_rate": 5e-06,
 "loss": 0.9034,
 "step": 1450
 },
 {
 "epoch": 0.7460398569238631,
 "grad_norm": 0.07015236628919412,
 "learning_rate": 5e-06,
 "loss": 0.9033,
 "step": 1460
 },
 {
 "epoch": 0.7511497189575882,
 "grad_norm": 0.10418032275009997,
 "learning_rate": 5e-06,
 "loss": 0.9008,
 "step": 1470
 },
 {
 "epoch": 0.7562595809913132,
 "grad_norm": 0.07009703060030868,
 "learning_rate": 5e-06,
 "loss": 0.9006,
 "step": 1480
 },
 {
 "epoch": 0.7613694430250383,
 "grad_norm": 0.07561374961635098,
 "learning_rate": 5e-06,
 "loss": 0.8992,
 "step": 1490
 },
 {
 "epoch": 0.7664793050587634,
 "grad_norm": 0.07543087417873817,
 "learning_rate": 5e-06,
 "loss": 0.9022,
 "step": 1500
 },
 {
 "epoch": 0.7715891670924885,
 "grad_norm": 0.07303222610905763,
 "learning_rate": 5e-06,
 "loss": 0.8876,
 "step": 1510
 },
 {
 "epoch": 0.7766990291262136,
 "grad_norm": 0.12947977214304454,
 "learning_rate": 5e-06,
 "loss": 0.9017,
 "step": 1520
 },
 {
 "epoch": 0.7818088911599387,
 "grad_norm": 0.07389484625510247,
 "learning_rate": 5e-06,
 "loss": 0.8972,
 "step": 1530
 },
 {
 "epoch": 0.7869187531936638,
 "grad_norm": 0.07577895984597245,
 "learning_rate": 5e-06,
 "loss": 0.9029,
 "step": 1540
 },
 {
 "epoch": 0.7920286152273889,
 "grad_norm": 0.07179725920965228,
 "learning_rate": 5e-06,
 "loss": 0.8973,
 "step": 1550
 },
 {
 "epoch": 0.797138477261114,
 "grad_norm": 0.09446753813662215,
 "learning_rate": 5e-06,
 "loss": 0.8884,
 "step": 1560
 },
 {
 "epoch": 0.8022483392948391,
 "grad_norm": 0.0694040937128912,
 "learning_rate": 5e-06,
 "loss": 0.8858,
 "step": 1570
 },
 {
 "epoch": 0.8073582013285642,
 "grad_norm": 0.07119010100651514,
 "learning_rate": 5e-06,
 "loss": 0.891,
 "step": 1580
 },
 {
 "epoch": 0.8124680633622893,
 "grad_norm": 0.06814136288038194,
 "learning_rate": 5e-06,
 "loss": 0.8882,
 "step": 1590
 },
 {
 "epoch": 0.8175779253960143,
 "grad_norm": 0.14101206207855727,
 "learning_rate": 5e-06,
 "loss": 0.8901,
 "step": 1600
 },
 {
 "epoch": 0.8226877874297394,
 "grad_norm": 0.06823593991844153,
 "learning_rate": 5e-06,
 "loss": 0.8969,
 "step": 1610
 },
 {
 "epoch": 0.8277976494634645,
 "grad_norm": 0.0781844807225488,
 "learning_rate": 5e-06,
 "loss": 0.9092,
 "step": 1620
 },
 {
 "epoch": 0.8329075114971896,
 "grad_norm": 0.07770931010296782,
 "learning_rate": 5e-06,
 "loss": 0.9099,
 "step": 1630
 },
 {
 "epoch": 0.8380173735309147,
 "grad_norm": 0.07037044497495822,
 "learning_rate": 5e-06,
 "loss": 0.8955,
 "step": 1640
 },
 {
 "epoch": 0.8431272355646398,
 "grad_norm": 0.0765067693249436,
 "learning_rate": 5e-06,
 "loss": 0.8839,
 "step": 1650
 },
 {
 "epoch": 0.8482370975983649,
 "grad_norm": 0.09158943006728,
 "learning_rate": 5e-06,
 "loss": 0.9055,
 "step": 1660
 },
 {
 "epoch": 0.85334695963209,
 "grad_norm": 0.07388296884455732,
 "learning_rate": 5e-06,
 "loss": 0.8829,
 "step": 1670
 },
 {
 "epoch": 0.858456821665815,
 "grad_norm": 0.07364367251534173,
 "learning_rate": 5e-06,
 "loss": 0.8906,
 "step": 1680
 },
 {
 "epoch": 0.8635666836995401,
 "grad_norm": 0.10472917075697648,
 "learning_rate": 5e-06,
 "loss": 0.8998,
 "step": 1690
 },
 {
 "epoch": 0.8686765457332652,
 "grad_norm": 0.07209129300287077,
 "learning_rate": 5e-06,
 "loss": 0.9079,
 "step": 1700
 },
 {
 "epoch": 0.8737864077669902,
 "grad_norm": 0.06988678080238575,
 "learning_rate": 5e-06,
 "loss": 0.903,
 "step": 1710
 },
 {
 "epoch": 0.8788962698007153,
 "grad_norm": 0.07515978821834793,
 "learning_rate": 5e-06,
 "loss": 0.8904,
 "step": 1720
 },
 {
 "epoch": 0.8840061318344404,
 "grad_norm": 0.07433094849872902,
 "learning_rate": 5e-06,
 "loss": 0.889,
 "step": 1730
 },
 {
 "epoch": 0.8891159938681655,
 "grad_norm": 0.08433306671757082,
 "learning_rate": 5e-06,
 "loss": 0.8986,
 "step": 1740
 },
 {
 "epoch": 0.8942258559018906,
 "grad_norm": 0.07396884075939439,
 "learning_rate": 5e-06,
 "loss": 0.8874,
 "step": 1750
 },
 {
 "epoch": 0.8993357179356157,
 "grad_norm": 0.07751456977281067,
 "learning_rate": 5e-06,
 "loss": 0.8992,
 "step": 1760
 },
 {
 "epoch": 0.9044455799693408,
 "grad_norm": 0.0789527788405623,
 "learning_rate": 5e-06,
 "loss": 0.8969,
 "step": 1770
 },
 {
 "epoch": 0.9095554420030659,
 "grad_norm": 0.07602904790252976,
 "learning_rate": 5e-06,
 "loss": 0.8901,
 "step": 1780
 },
 {
 "epoch": 0.914665304036791,
 "grad_norm": 0.06982248060839691,
 "learning_rate": 5e-06,
 "loss": 0.8968,
 "step": 1790
 },
 {
 "epoch": 0.9197751660705161,
 "grad_norm": 0.07169359819101034,
 "learning_rate": 5e-06,
 "loss": 0.9087,
 "step": 1800
 },
 {
 "epoch": 0.9248850281042412,
 "grad_norm": 0.07321342917964954,
 "learning_rate": 5e-06,
 "loss": 0.8969,
 "step": 1810
 },
 {
 "epoch": 0.9299948901379663,
 "grad_norm": 0.07444618890892986,
 "learning_rate": 5e-06,
 "loss": 0.9045,
 "step": 1820
 },
 {
 "epoch": 0.9351047521716913,
 "grad_norm": 0.11365069738490574,
 "learning_rate": 5e-06,
 "loss": 0.8909,
 "step": 1830
 },
 {
 "epoch": 0.9402146142054164,
 "grad_norm": 0.380588282512115,
 "learning_rate": 5e-06,
 "loss": 0.8803,
 "step": 1840
 },
 {
 "epoch": 0.9453244762391415,
 "grad_norm": 0.07262951461490495,
 "learning_rate": 5e-06,
 "loss": 0.8718,
 "step": 1850
 },
 {
 "epoch": 0.9504343382728666,
 "grad_norm": 0.06829017808656876,
 "learning_rate": 5e-06,
 "loss": 0.8822,
 "step": 1860
 },
 {
 "epoch": 0.9555442003065917,
 "grad_norm": 0.07878675404968587,
 "learning_rate": 5e-06,
 "loss": 0.878,
 "step": 1870
 },
 {
 "epoch": 0.9606540623403168,
 "grad_norm": 0.0760531098736545,
 "learning_rate": 5e-06,
 "loss": 0.8808,
 "step": 1880
 },
 {
 "epoch": 0.9657639243740419,
 "grad_norm": 0.12494712249352007,
 "learning_rate": 5e-06,
 "loss": 0.8829,
 "step": 1890
 },
 {
 "epoch": 0.970873786407767,
 "grad_norm": 0.07219974763591076,
 "learning_rate": 5e-06,
 "loss": 0.8875,
 "step": 1900
 },
 {
 "epoch": 0.9759836484414921,
 "grad_norm": 0.0678705623185834,
 "learning_rate": 5e-06,
 "loss": 0.9012,
 "step": 1910
 },
 {
 "epoch": 0.9810935104752172,
 "grad_norm": 0.07156172069177699,
 "learning_rate": 5e-06,
 "loss": 0.898,
 "step": 1920
 },
 {
 "epoch": 0.9862033725089423,
 "grad_norm": 0.0732677504535335,
 "learning_rate": 5e-06,
 "loss": 0.8962,
 "step": 1930
 },
 {
 "epoch": 0.9913132345426674,
 "grad_norm": 0.07202912622478508,
 "learning_rate": 5e-06,
 "loss": 0.8951,
 "step": 1940
 },
 {
 "epoch": 0.9964230965763924,
 "grad_norm": 0.10969747960973296,
 "learning_rate": 5e-06,
 "loss": 0.9097,
 "step": 1950
 },
 {
 "epoch": 1.0015329586101176,
 "grad_norm": 0.06912267564528896,
 "learning_rate": 5e-06,
 "loss": 0.8839,
 "step": 1960
 },
 {
 "epoch": 1.0066428206438427,
 "grad_norm": 0.07686255349334188,
 "learning_rate": 5e-06,
 "loss": 0.8895,
 "step": 1970
 },
 {
 "epoch": 1.0117526826775678,
 "grad_norm": 0.07239494301457147,
 "learning_rate": 5e-06,
 "loss": 0.8802,
 "step": 1980
 },
 {
 "epoch": 1.016862544711293,
 "grad_norm": 0.06896146275536877,
 "learning_rate": 5e-06,
 "loss": 0.8743,
 "step": 1990
 },
 {
 "epoch": 1.021972406745018,
 "grad_norm": 0.06973937218730168,
 "learning_rate": 5e-06,
 "loss": 0.8858,
 "step": 2000
 },
 {
 "epoch": 1.0270822687787429,
 "grad_norm": 0.07590849152549478,
 "learning_rate": 5e-06,
 "loss": 0.8702,
 "step": 2010
 },
 {
 "epoch": 1.032192130812468,
 "grad_norm": 0.07727922335579492,
 "learning_rate": 5e-06,
 "loss": 0.8802,
 "step": 2020
 },
 {
 "epoch": 1.037301992846193,
 "grad_norm": 0.07317945118774036,
 "learning_rate": 5e-06,
 "loss": 0.8764,
 "step": 2030
 },
 {
 "epoch": 1.0424118548799182,
 "grad_norm": 0.0790764962189524,
 "learning_rate": 5e-06,
 "loss": 0.8675,
 "step": 2040
 },
 {
 "epoch": 1.0475217169136433,
 "grad_norm": 0.14927111441309496,
 "learning_rate": 5e-06,
 "loss": 0.8795,
 "step": 2050
 },
 {
 "epoch": 1.0526315789473684,
 "grad_norm": 0.09144412400190963,
 "learning_rate": 5e-06,
 "loss": 0.8787,
 "step": 2060
 },
 {
 "epoch": 1.0577414409810935,
 "grad_norm": 0.07045354181303777,
 "learning_rate": 5e-06,
 "loss": 0.8797,
 "step": 2070
 },
 {
 "epoch": 1.0628513030148186,
 "grad_norm": 0.07891724899455275,
 "learning_rate": 5e-06,
 "loss": 0.8905,
 "step": 2080
 },
 {
 "epoch": 1.0679611650485437,
 "grad_norm": 0.06772214066866822,
 "learning_rate": 5e-06,
 "loss": 0.8872,
 "step": 2090
 },
 {
 "epoch": 1.0730710270822688,
 "grad_norm": 0.0712589563903319,
 "learning_rate": 5e-06,
 "loss": 0.8855,
 "step": 2100
 },
 {
 "epoch": 1.0781808891159939,
 "grad_norm": 0.06862698369349315,
 "learning_rate": 5e-06,
 "loss": 0.881,
 "step": 2110
 },
 {
 "epoch": 1.083290751149719,
 "grad_norm": 0.0736606231100836,
 "learning_rate": 5e-06,
 "loss": 0.8674,
 "step": 2120
 },
 {
 "epoch": 1.088400613183444,
 "grad_norm": 0.07106355054734692,
 "learning_rate": 5e-06,
 "loss": 0.8946,
 "step": 2130
 },
 {
 "epoch": 1.0935104752171692,
 "grad_norm": 0.07255234123815231,
 "learning_rate": 5e-06,
 "loss": 0.882,
 "step": 2140
 },
 {
 "epoch": 1.0986203372508943,
 "grad_norm": 0.0732742082692386,
 "learning_rate": 5e-06,
 "loss": 0.8676,
 "step": 2150
 },
 {
 "epoch": 1.1037301992846194,
 "grad_norm": 0.06964362410343532,
 "learning_rate": 5e-06,
 "loss": 0.8774,
 "step": 2160
 },
 {
 "epoch": 1.1088400613183444,
 "grad_norm": 0.06779365708748122,
 "learning_rate": 5e-06,
 "loss": 0.8746,
 "step": 2170
 },
 {
 "epoch": 1.1139499233520695,
 "grad_norm": 0.1233845297748753,
 "learning_rate": 5e-06,
 "loss": 0.8765,
 "step": 2180
 },
 {
 "epoch": 1.1190597853857946,
 "grad_norm": 0.08906300490745893,
 "learning_rate": 5e-06,
 "loss": 0.8887,
 "step": 2190
 },
 {
 "epoch": 1.1241696474195197,
 "grad_norm": 0.09632061303323498,
 "learning_rate": 5e-06,
 "loss": 0.873,
 "step": 2200
 },
 {
 "epoch": 1.1292795094532448,
 "grad_norm": 0.08521280891691754,
 "learning_rate": 5e-06,
 "loss": 0.8898,
 "step": 2210
 },
 {
 "epoch": 1.13438937148697,
 "grad_norm": 0.08360918869150777,
 "learning_rate": 5e-06,
 "loss": 0.8744,
 "step": 2220
 },
 {
 "epoch": 1.139499233520695,
 "grad_norm": 0.07235955845669943,
 "learning_rate": 5e-06,
 "loss": 0.871,
 "step": 2230
 },
 {
 "epoch": 1.14460909555442,
 "grad_norm": 0.0730315588992174,
 "learning_rate": 5e-06,
 "loss": 0.8821,
 "step": 2240
 },
 {
 "epoch": 1.1497189575881452,
 "grad_norm": 0.11078438063259888,
 "learning_rate": 5e-06,
 "loss": 0.8769,
 "step": 2250
 },
 {
 "epoch": 1.1548288196218701,
 "grad_norm": 0.07056038440126992,
 "learning_rate": 5e-06,
 "loss": 0.8794,
 "step": 2260
 },
 {
 "epoch": 1.1599386816555952,
 "grad_norm": 0.0708667161304354,
 "learning_rate": 5e-06,
 "loss": 0.8816,
 "step": 2270
 },
 {
 "epoch": 1.1650485436893203,
 "grad_norm": 0.07609323526554022,
 "learning_rate": 5e-06,
 "loss": 0.8819,
 "step": 2280
 },
 {
 "epoch": 1.1701584057230454,
 "grad_norm": 0.0735028145209297,
 "learning_rate": 5e-06,
 "loss": 0.8703,
 "step": 2290
 },
 {
 "epoch": 1.1752682677567705,
 "grad_norm": 0.07069493332631555,
 "learning_rate": 5e-06,
 "loss": 0.8847,
 "step": 2300
 },
 {
 "epoch": 1.1803781297904956,
 "grad_norm": 0.072283465693465,
 "learning_rate": 5e-06,
 "loss": 0.8821,
 "step": 2310
 },
 {
 "epoch": 1.1854879918242207,
 "grad_norm": 0.0682393777040698,
 "learning_rate": 5e-06,
 "loss": 0.8783,
 "step": 2320
 },
 {
 "epoch": 1.1905978538579458,
 "grad_norm": 0.07033706862496379,
 "learning_rate": 5e-06,
 "loss": 0.8803,
 "step": 2330
 },
 {
 "epoch": 1.195707715891671,
 "grad_norm": 0.07616585487021542,
 "learning_rate": 5e-06,
 "loss": 0.8797,
 "step": 2340
 },
 {
 "epoch": 1.200817577925396,
 "grad_norm": 0.09257368897028359,
 "learning_rate": 5e-06,
 "loss": 0.8848,
 "step": 2350
 },
 {
 "epoch": 1.205927439959121,
 "grad_norm": 0.07218601192609732,
 "learning_rate": 5e-06,
 "loss": 0.88,
 "step": 2360
 },
 {
 "epoch": 1.2110373019928462,
 "grad_norm": 0.06958174210341682,
 "learning_rate": 5e-06,
 "loss": 0.8736,
 "step": 2370
 },
 {
 "epoch": 1.2161471640265713,
 "grad_norm": 0.07752486671959553,
 "learning_rate": 5e-06,
 "loss": 0.8872,
 "step": 2380
 },
 {
 "epoch": 1.2212570260602964,
 "grad_norm": 0.06925884038134095,
 "learning_rate": 5e-06,
 "loss": 0.8723,
 "step": 2390
 },
 {
 "epoch": 1.2263668880940215,
 "grad_norm": 0.08334609436821461,
 "learning_rate": 5e-06,
 "loss": 0.8733,
 "step": 2400
 },
 {
 "epoch": 1.2314767501277466,
 "grad_norm": 0.07385728362174653,
 "learning_rate": 5e-06,
 "loss": 0.884,
 "step": 2410
 },
 {
 "epoch": 1.2365866121614717,
 "grad_norm": 0.07450268605349716,
 "learning_rate": 5e-06,
 "loss": 0.8759,
 "step": 2420
 },
 {
 "epoch": 1.2416964741951968,
 "grad_norm": 0.07354090310210888,
 "learning_rate": 5e-06,
 "loss": 0.8688,
 "step": 2430
 },
 {
 "epoch": 1.246806336228922,
 "grad_norm": 0.07320978260247811,
 "learning_rate": 5e-06,
 "loss": 0.8714,
 "step": 2440
 },
 {
 "epoch": 1.2519161982626468,
 "grad_norm": 0.11135661739097093,
 "learning_rate": 5e-06,
 "loss": 0.8739,
 "step": 2450
 },
 {
 "epoch": 1.257026060296372,
 "grad_norm": 0.06689839605333785,
 "learning_rate": 5e-06,
 "loss": 0.8765,
 "step": 2460
 },
 {
 "epoch": 1.262135922330097,
 "grad_norm": 0.06878455740414403,
 "learning_rate": 5e-06,
 "loss": 0.8689,
 "step": 2470
 },
 {
 "epoch": 1.2672457843638223,
 "grad_norm": 0.07939944943381874,
 "learning_rate": 5e-06,
 "loss": 0.8746,
 "step": 2480
 },
 {
 "epoch": 1.2723556463975472,
 "grad_norm": 0.0847486139125745,
 "learning_rate": 5e-06,
 "loss": 0.8559,
 "step": 2490
 },
 {
 "epoch": 1.2774655084312725,
 "grad_norm": 0.07908001512097204,
 "learning_rate": 5e-06,
 "loss": 0.8837,
 "step": 2500
 },
 {
 "epoch": 1.2825753704649974,
 "grad_norm": 0.07179831207428604,
 "learning_rate": 5e-06,
 "loss": 0.8719,
 "step": 2510
 },
 {
 "epoch": 1.2876852324987225,
 "grad_norm": 0.06908942799455607,
 "learning_rate": 5e-06,
 "loss": 0.8719,
 "step": 2520
 },
 {
 "epoch": 1.2927950945324476,
 "grad_norm": 0.18170225872460127,
 "learning_rate": 5e-06,
 "loss": 0.8716,
 "step": 2530
 },
 {
 "epoch": 1.2979049565661727,
 "grad_norm": 0.07191218825096998,
 "learning_rate": 5e-06,
 "loss": 0.8722,
 "step": 2540
 },
 {
 "epoch": 1.3030148185998978,
 "grad_norm": 0.07372060023260767,
 "learning_rate": 5e-06,
 "loss": 0.864,
 "step": 2550
 },
 {
 "epoch": 1.3081246806336229,
 "grad_norm": 0.06857070499864196,
 "learning_rate": 5e-06,
 "loss": 0.8737,
 "step": 2560
 },
 {
 "epoch": 1.313234542667348,
 "grad_norm": 0.07004154529738099,
 "learning_rate": 5e-06,
 "loss": 0.8813,
 "step": 2570
 },
 {
 "epoch": 1.318344404701073,
 "grad_norm": 0.07646266858295366,
 "learning_rate": 5e-06,
 "loss": 0.8673,
 "step": 2580
 },
 {
 "epoch": 1.3234542667347982,
 "grad_norm": 0.22621512935898874,
 "learning_rate": 5e-06,
 "loss": 0.874,
 "step": 2590
 },
 {
 "epoch": 1.3285641287685233,
 "grad_norm": 0.07172127109965361,
 "learning_rate": 5e-06,
 "loss": 0.8702,
 "step": 2600
 },
 {
 "epoch": 1.3336739908022484,
 "grad_norm": 0.07919820863816981,
 "learning_rate": 5e-06,
 "loss": 0.8714,
 "step": 2610
 },
 {
 "epoch": 1.3387838528359735,
 "grad_norm": 0.0737384119314816,
 "learning_rate": 5e-06,
 "loss": 0.8596,
 "step": 2620
 },
 {
 "epoch": 1.3438937148696986,
 "grad_norm": 0.07649678940149303,
 "learning_rate": 5e-06,
 "loss": 0.8762,
 "step": 2630
 },
 {
 "epoch": 1.3490035769034237,
 "grad_norm": 0.07616587969512677,
 "learning_rate": 5e-06,
 "loss": 0.8752,
 "step": 2640
 },
 {
 "epoch": 1.3541134389371488,
 "grad_norm": 0.07029295823641774,
 "learning_rate": 5e-06,
 "loss": 0.8873,
 "step": 2650
 },
 {
 "epoch": 1.3592233009708738,
 "grad_norm": 0.09494349210733874,
 "learning_rate": 5e-06,
 "loss": 0.8711,
 "step": 2660
 },
 {
 "epoch": 1.364333163004599,
 "grad_norm": 0.07259460873158792,
 "learning_rate": 5e-06,
 "loss": 0.8637,
 "step": 2670
 },
 {
 "epoch": 1.369443025038324,
 "grad_norm": 0.07116222480426102,
 "learning_rate": 5e-06,
 "loss": 0.871,
 "step": 2680
 },
 {
 "epoch": 1.3745528870720491,
 "grad_norm": 0.07020506586822424,
 "learning_rate": 5e-06,
 "loss": 0.8695,
 "step": 2690
 },
 {
 "epoch": 1.379662749105774,
 "grad_norm": 0.07347815298194012,
 "learning_rate": 5e-06,
 "loss": 0.8635,
 "step": 2700
 },
 {
 "epoch": 1.3847726111394993,
 "grad_norm": 0.07534096599250913,
 "learning_rate": 5e-06,
 "loss": 0.874,
 "step": 2710
 },
 {
 "epoch": 1.3898824731732242,
 "grad_norm": 0.07312451287982565,
 "learning_rate": 5e-06,
 "loss": 0.8583,
 "step": 2720
 },
 {
 "epoch": 1.3949923352069495,
 "grad_norm": 0.07656396202261084,
 "learning_rate": 5e-06,
 "loss": 0.8757,
 "step": 2730
 },
 {
 "epoch": 1.4001021972406744,
 "grad_norm": 0.06967035802932788,
 "learning_rate": 5e-06,
 "loss": 0.8679,
 "step": 2740
 },
 {
 "epoch": 1.4052120592743995,
 "grad_norm": 0.07040784275347066,
 "learning_rate": 5e-06,
 "loss": 0.8691,
 "step": 2750
 },
 {
 "epoch": 1.4103219213081246,
 "grad_norm": 0.07613577722321895,
 "learning_rate": 5e-06,
 "loss": 0.8622,
 "step": 2760
 },
 {
 "epoch": 1.4154317833418497,
 "grad_norm": 0.0864741566205661,
 "learning_rate": 5e-06,
 "loss": 0.8795,
 "step": 2770
 },
 {
 "epoch": 1.4205416453755748,
 "grad_norm": 0.07310285802451263,
 "learning_rate": 5e-06,
 "loss": 0.8652,
 "step": 2780
 },
 {
 "epoch": 1.4256515074093,
 "grad_norm": 0.09973189293248541,
 "learning_rate": 5e-06,
 "loss": 0.8588,
 "step": 2790
 },
 {
 "epoch": 1.430761369443025,
 "grad_norm": 0.06701808614361114,
 "learning_rate": 5e-06,
 "loss": 0.8618,
 "step": 2800
 },
 {
 "epoch": 1.43587123147675,
 "grad_norm": 0.07371045895798196,
 "learning_rate": 5e-06,
 "loss": 0.868,
 "step": 2810
 },
 {
 "epoch": 1.4409810935104752,
 "grad_norm": 0.07317697928871572,
 "learning_rate": 5e-06,
 "loss": 0.8696,
 "step": 2820
 },
 {
 "epoch": 1.4460909555442003,
 "grad_norm": 0.07564444911927448,
 "learning_rate": 5e-06,
 "loss": 0.8752,
 "step": 2830
 },
 {
 "epoch": 1.4512008175779254,
 "grad_norm": 0.07293430197763458,
 "learning_rate": 5e-06,
 "loss": 0.8739,
 "step": 2840
 },
 {
 "epoch": 1.4563106796116505,
 "grad_norm": 0.08105248343525902,
 "learning_rate": 5e-06,
 "loss": 0.8657,
 "step": 2850
 },
 {
 "epoch": 1.4614205416453756,
 "grad_norm": 0.06997018312332681,
 "learning_rate": 5e-06,
 "loss": 0.8687,
 "step": 2860
 },
 {
 "epoch": 1.4665304036791007,
 "grad_norm": 0.0747583962947945,
 "learning_rate": 5e-06,
 "loss": 0.876,
 "step": 2870
 },
 {
 "epoch": 1.4716402657128258,
 "grad_norm": 0.07233657303691476,
 "learning_rate": 5e-06,
 "loss": 0.8737,
 "step": 2880
 },
 {
 "epoch": 1.476750127746551,
 "grad_norm": 0.09587028399395618,
 "learning_rate": 5e-06,
 "loss": 0.8737,
 "step": 2890
 },
 {
 "epoch": 1.481859989780276,
 "grad_norm": 0.07573225439316397,
 "learning_rate": 5e-06,
 "loss": 0.8768,
 "step": 2900
 },
 {
 "epoch": 1.486969851814001,
 "grad_norm": 0.07814308912110395,
 "learning_rate": 5e-06,
 "loss": 0.8585,
 "step": 2910
 },
 {
 "epoch": 1.4920797138477262,
 "grad_norm": 0.07563890740598028,
 "learning_rate": 5e-06,
 "loss": 0.8688,
 "step": 2920
 },
 {
 "epoch": 1.497189575881451,
 "grad_norm": 0.09576148511380349,
 "learning_rate": 5e-06,
 "loss": 0.8664,
 "step": 2930
 },
 {
 "epoch": 1.5022994379151764,
 "grad_norm": 0.07323289783838559,
 "learning_rate": 5e-06,
 "loss": 0.8635,
 "step": 2940
 },
 {
 "epoch": 1.5074092999489013,
 "grad_norm": 0.06803171848149765,
 "learning_rate": 5e-06,
 "loss": 0.87,
 "step": 2950
 },
 {
 "epoch": 1.5125191619826266,
 "grad_norm": 0.0750090128477362,
 "learning_rate": 5e-06,
 "loss": 0.8772,
 "step": 2960
 },
 {
 "epoch": 1.5176290240163515,
 "grad_norm": 0.07137689878588128,
 "learning_rate": 5e-06,
 "loss": 0.8751,
 "step": 2970
 },
 {
 "epoch": 1.5227388860500768,
 "grad_norm": 0.07023359972800564,
 "learning_rate": 5e-06,
 "loss": 0.8643,
 "step": 2980
 },
 {
 "epoch": 1.5278487480838017,
 "grad_norm": 0.07455037859546688,
 "learning_rate": 5e-06,
 "loss": 0.861,
 "step": 2990
 },
 {
 "epoch": 1.532958610117527,
 "grad_norm": 0.25433406248411833,
 "learning_rate": 5e-06,
 "loss": 0.8647,
 "step": 3000
 },
 {
 "epoch": 1.5380684721512519,
 "grad_norm": 0.07418037183166513,
 "learning_rate": 5e-06,
 "loss": 0.8722,
 "step": 3010
 },
 {
 "epoch": 1.543178334184977,
 "grad_norm": 0.527753296001325,
 "learning_rate": 5e-06,
 "loss": 0.8487,
 "step": 3020
 },
 {
 "epoch": 1.548288196218702,
 "grad_norm": 0.08808550920766758,
 "learning_rate": 5e-06,
 "loss": 0.8496,
 "step": 3030
 },
 {
 "epoch": 1.5533980582524272,
 "grad_norm": 0.2138159671824102,
 "learning_rate": 5e-06,
 "loss": 0.8589,
 "step": 3040
 },
 {
 "epoch": 1.5585079202861523,
 "grad_norm": 0.0756879397945152,
 "learning_rate": 5e-06,
 "loss": 0.8611,
 "step": 3050
 },
 {
 "epoch": 1.5636177823198774,
 "grad_norm": 0.07261770215074904,
 "learning_rate": 5e-06,
 "loss": 0.8653,
 "step": 3060
 },
 {
 "epoch": 1.5687276443536025,
 "grad_norm": 0.0716298530862272,
 "learning_rate": 5e-06,
 "loss": 0.8742,
 "step": 3070
 },
 {
 "epoch": 1.5738375063873276,
 "grad_norm": 0.07104512740332262,
 "learning_rate": 5e-06,
 "loss": 0.8639,
 "step": 3080
 },
 {
 "epoch": 1.5789473684210527,
 "grad_norm": 0.0734502304224508,
 "learning_rate": 5e-06,
 "loss": 0.8654,
 "step": 3090
 },
 {
 "epoch": 1.5840572304547778,
 "grad_norm": 0.0718119752165925,
 "learning_rate": 5e-06,
 "loss": 0.8829,
 "step": 3100
 },
 {
 "epoch": 1.5891670924885029,
 "grad_norm": 0.09084312572124162,
 "learning_rate": 5e-06,
 "loss": 0.87,
 "step": 3110
 },
 {
 "epoch": 1.594276954522228,
 "grad_norm": 0.0718386089812322,
 "learning_rate": 5e-06,
 "loss": 0.8674,
 "step": 3120
 },
 {
 "epoch": 1.599386816555953,
 "grad_norm": 0.07237170282771108,
 "learning_rate": 5e-06,
 "loss": 0.8773,
 "step": 3130
 },
 {
 "epoch": 1.604496678589678,
 "grad_norm": 0.08717441511772783,
 "learning_rate": 5e-06,
 "loss": 0.8596,
 "step": 3140
 },
 {
 "epoch": 1.6096065406234032,
 "grad_norm": 0.07543204298441727,
 "learning_rate": 5e-06,
 "loss": 0.8662,
 "step": 3150
 },
 {
 "epoch": 1.6147164026571281,
 "grad_norm": 0.16450122906983272,
 "learning_rate": 5e-06,
 "loss": 0.8521,
 "step": 3160
 },
 {
 "epoch": 1.6198262646908534,
 "grad_norm": 0.0761301308978785,
 "learning_rate": 5e-06,
 "loss": 0.8676,
 "step": 3170
 },
 {
 "epoch": 1.6249361267245783,
 "grad_norm": 0.07342038953957022,
 "learning_rate": 5e-06,
 "loss": 0.858,
 "step": 3180
 },
 {
 "epoch": 1.6300459887583036,
 "grad_norm": 0.07763414058632681,
 "learning_rate": 5e-06,
 "loss": 0.8515,
 "step": 3190
 },
 {
 "epoch": 1.6351558507920285,
 "grad_norm": 0.07214206206945292,
 "learning_rate": 5e-06,
 "loss": 0.8552,
 "step": 3200
 },
 {
 "epoch": 1.6402657128257538,
 "grad_norm": 0.07217350290839333,
 "learning_rate": 5e-06,
 "loss": 0.8692,
 "step": 3210
 },
 {
 "epoch": 1.6453755748594787,
 "grad_norm": 0.07049849978950093,
 "learning_rate": 5e-06,
 "loss": 0.8637,
 "step": 3220
 },
 {
 "epoch": 1.650485436893204,
 "grad_norm": 0.07280794458006132,
 "learning_rate": 5e-06,
 "loss": 0.865,
 "step": 3230
 },
 {
 "epoch": 1.655595298926929,
 "grad_norm": 0.0725642747319213,
 "learning_rate": 5e-06,
 "loss": 0.8707,
 "step": 3240
 },
 {
 "epoch": 1.660705160960654,
 "grad_norm": 0.0833892314403624,
 "learning_rate": 5e-06,
 "loss": 0.8563,
 "step": 3250
 },
 {
 "epoch": 1.6658150229943791,
 "grad_norm": 0.07584097737400752,
 "learning_rate": 5e-06,
 "loss": 0.8641,
 "step": 3260
 },
 {
 "epoch": 1.6709248850281042,
 "grad_norm": 0.07213631314506445,
 "learning_rate": 5e-06,
 "loss": 0.8481,
 "step": 3270
 },
 {
 "epoch": 1.6760347470618293,
 "grad_norm": 0.09381953559357656,
 "learning_rate": 5e-06,
 "loss": 0.8701,
 "step": 3280
 },
 {
 "epoch": 1.6811446090955544,
 "grad_norm": 0.08666983262995791,
 "learning_rate": 5e-06,
 "loss": 0.8647,
 "step": 3290
 },
 {
 "epoch": 1.6862544711292795,
 "grad_norm": 0.07241102137300287,
 "learning_rate": 5e-06,
 "loss": 0.8659,
 "step": 3300
 },
 {
 "epoch": 1.6913643331630046,
 "grad_norm": 0.07570259861415368,
 "learning_rate": 5e-06,
 "loss": 0.857,
 "step": 3310
 },
 {
 "epoch": 1.6964741951967297,
 "grad_norm": 0.0712132785838072,
 "learning_rate": 5e-06,
 "loss": 0.8628,
 "step": 3320
 },
 {
 "epoch": 1.7015840572304548,
 "grad_norm": 0.08048218877183527,
 "learning_rate": 5e-06,
 "loss": 0.8695,
 "step": 3330
 },
 {
 "epoch": 1.70669391926418,
 "grad_norm": 0.09318443713082784,
 "learning_rate": 5e-06,
 "loss": 0.8517,
 "step": 3340
 },
 {
 "epoch": 1.711803781297905,
 "grad_norm": 0.07475815362258889,
 "learning_rate": 5e-06,
 "loss": 0.8511,
 "step": 3350
 },
 {
 "epoch": 1.71691364333163,
 "grad_norm": 0.17675220557910395,
 "learning_rate": 5e-06,
 "loss": 0.8704,
 "step": 3360
 },
 {
 "epoch": 1.722023505365355,
 "grad_norm": 0.08155115744528993,
 "learning_rate": 5e-06,
 "loss": 0.8782,
 "step": 3370
 },
 {
 "epoch": 1.7271333673990803,
 "grad_norm": 0.0688426924243207,
 "learning_rate": 5e-06,
 "loss": 0.8745,
 "step": 3380
 },
 {
 "epoch": 1.7322432294328052,
 "grad_norm": 0.20082535327419024,
 "learning_rate": 5e-06,
 "loss": 0.8714,
 "step": 3390
 },
 {
 "epoch": 1.7373530914665305,
 "grad_norm": 0.07080189321410434,
 "learning_rate": 5e-06,
 "loss": 0.8599,
 "step": 3400
 },
 {
 "epoch": 1.7424629535002554,
 "grad_norm": 0.07121276144536708,
 "learning_rate": 5e-06,
 "loss": 0.8559,
 "step": 3410
 },
 {
 "epoch": 1.7475728155339807,
 "grad_norm": 0.07900066453877426,
 "learning_rate": 5e-06,
 "loss": 0.8478,
 "step": 3420
 },
 {
 "epoch": 1.7526826775677056,
 "grad_norm": 0.06739380270330443,
 "learning_rate": 5e-06,
 "loss": 0.8607,
 "step": 3430
 },
 {
 "epoch": 1.757792539601431,
 "grad_norm": 0.07034902532215459,
 "learning_rate": 5e-06,
 "loss": 0.8571,
 "step": 3440
 },
 {
 "epoch": 1.7629024016351558,
 "grad_norm": 0.12075846844627011,
 "learning_rate": 5e-06,
 "loss": 0.8656,
 "step": 3450
 },
 {
 "epoch": 1.768012263668881,
 "grad_norm": 0.06907079017712828,
 "learning_rate": 5e-06,
 "loss": 0.8639,
 "step": 3460
 },
 {
 "epoch": 1.773122125702606,
 "grad_norm": 0.07179248413436795,
 "learning_rate": 5e-06,
 "loss": 0.8576,
 "step": 3470
 },
 {
 "epoch": 1.778231987736331,
 "grad_norm": 0.07132838373781546,
 "learning_rate": 5e-06,
 "loss": 0.8491,
 "step": 3480
 },
 {
 "epoch": 1.7833418497700562,
 "grad_norm": 0.06976172529981421,
 "learning_rate": 5e-06,
 "loss": 0.862,
 "step": 3490
 },
 {
 "epoch": 1.7884517118037813,
 "grad_norm": 0.07698270839551638,
 "learning_rate": 5e-06,
 "loss": 0.8798,
 "step": 3500
 },
 {
 "epoch": 1.7935615738375064,
 "grad_norm": 0.07221517095149313,
 "learning_rate": 5e-06,
 "loss": 0.8614,
 "step": 3510
 },
 {
 "epoch": 1.7986714358712315,
 "grad_norm": 0.06942929153366358,
 "learning_rate": 5e-06,
 "loss": 0.8516,
 "step": 3520
 },
 {
 "epoch": 1.8037812979049566,
 "grad_norm": 0.07515778700424314,
 "learning_rate": 5e-06,
 "loss": 0.8513,
 "step": 3530
 },
 {
 "epoch": 1.8088911599386817,
 "grad_norm": 0.09189050887868352,
 "learning_rate": 5e-06,
 "loss": 0.8516,
 "step": 3540
 },
 {
 "epoch": 1.8140010219724068,
 "grad_norm": 0.0728814328355567,
 "learning_rate": 5e-06,
 "loss": 0.8621,
 "step": 3550
 },
 {
 "epoch": 1.8191108840061319,
 "grad_norm": 0.10913457550732027,
 "learning_rate": 5e-06,
 "loss": 0.8646,
 "step": 3560
 },
 {
 "epoch": 1.824220746039857,
 "grad_norm": 0.07052348211530159,
 "learning_rate": 5e-06,
 "loss": 0.8681,
 "step": 3570
 },
 {
 "epoch": 1.829330608073582,
 "grad_norm": 0.07264597385076586,
 "learning_rate": 5e-06,
 "loss": 0.8511,
 "step": 3580
 },
 {
 "epoch": 1.8344404701073072,
 "grad_norm": 0.07018720603142706,
 "learning_rate": 5e-06,
 "loss": 0.8496,
 "step": 3590
 },
 {
 "epoch": 1.839550332141032,
 "grad_norm": 0.07405274174709763,
 "learning_rate": 5e-06,
 "loss": 0.8642,
 "step": 3600
 },
 {
 "epoch": 1.8446601941747574,
 "grad_norm": 0.06823076228063171,
 "learning_rate": 5e-06,
 "loss": 0.8688,
 "step": 3610
 },
 {
 "epoch": 1.8497700562084822,
 "grad_norm": 0.07162073827665592,
 "learning_rate": 5e-06,
 "loss": 0.8539,
 "step": 3620
 },
 {
 "epoch": 1.8548799182422075,
 "grad_norm": 0.08920479490208502,
 "learning_rate": 5e-06,
 "loss": 0.8654,
 "step": 3630
 },
 {
 "epoch": 1.8599897802759324,
 "grad_norm": 0.06984715874447373,
 "learning_rate": 5e-06,
 "loss": 0.8398,
 "step": 3640
 },
 {
 "epoch": 1.8650996423096577,
 "grad_norm": 0.07140680546752168,
 "learning_rate": 5e-06,
 "loss": 0.8563,
 "step": 3650
 },
 {
 "epoch": 1.8702095043433826,
 "grad_norm": 0.074558519928601,
 "learning_rate": 5e-06,
 "loss": 0.8538,
 "step": 3660
 },
 {
 "epoch": 1.875319366377108,
 "grad_norm": 0.0721153352880791,
 "learning_rate": 5e-06,
 "loss": 0.8681,
 "step": 3670
 },
 {
 "epoch": 1.8804292284108328,
 "grad_norm": 0.0758789196857535,
 "learning_rate": 5e-06,
 "loss": 0.8635,
 "step": 3680
 },
 {
 "epoch": 1.8855390904445581,
 "grad_norm": 0.14485848629874987,
 "learning_rate": 5e-06,
 "loss": 0.8481,
 "step": 3690
 },
 {
 "epoch": 1.890648952478283,
 "grad_norm": 0.0819983215124987,
 "learning_rate": 5e-06,
 "loss": 0.8629,
 "step": 3700
 },
 {
 "epoch": 1.8957588145120083,
 "grad_norm": 0.12069351872374186,
 "learning_rate": 5e-06,
 "loss": 0.8586,
 "step": 3710
 },
 {
 "epoch": 1.9008686765457332,
 "grad_norm": 0.07900003124096018,
 "learning_rate": 5e-06,
 "loss": 0.8601,
 "step": 3720
 },
 {
 "epoch": 1.9059785385794583,
 "grad_norm": 0.07294378619834212,
 "learning_rate": 5e-06,
 "loss": 0.8587,
 "step": 3730
 },
 {
 "epoch": 1.9110884006131834,
 "grad_norm": 0.07407840442755602,
 "learning_rate": 5e-06,
 "loss": 0.8528,
 "step": 3740
 },
 {
 "epoch": 1.9161982626469085,
 "grad_norm": 0.06874497219883488,
 "learning_rate": 5e-06,
 "loss": 0.8605,
 "step": 3750
 },
 {
 "epoch": 1.9213081246806336,
 "grad_norm": 0.07843559919629378,
 "learning_rate": 5e-06,
 "loss": 0.8527,
 "step": 3760
 },
 {
 "epoch": 1.9264179867143587,
 "grad_norm": 0.07180996099623314,
 "learning_rate": 5e-06,
 "loss": 0.8523,
 "step": 3770
 },
 {
 "epoch": 1.9315278487480838,
 "grad_norm": 0.08056676529863596,
 "learning_rate": 5e-06,
 "loss": 0.8633,
 "step": 3780
 },
 {
 "epoch": 1.936637710781809,
 "grad_norm": 0.07275382170948991,
 "learning_rate": 5e-06,
 "loss": 0.8515,
 "step": 3790
 },
 {
 "epoch": 1.941747572815534,
 "grad_norm": 0.07098939053342133,
 "learning_rate": 5e-06,
 "loss": 0.8547,
 "step": 3800
 },
 {
 "epoch": 1.946857434849259,
 "grad_norm": 0.06701155010213629,
 "learning_rate": 5e-06,
 "loss": 0.8481,
 "step": 3810
 },
 {
 "epoch": 1.9519672968829842,
 "grad_norm": 0.07031575089856135,
 "learning_rate": 5e-06,
 "loss": 0.8438,
 "step": 3820
 },
 {
 "epoch": 1.9570771589167093,
 "grad_norm": 0.07564841797187823,
 "learning_rate": 5e-06,
 "loss": 0.8582,
 "step": 3830
 },
 {
 "epoch": 1.9621870209504344,
 "grad_norm": 0.07024404592017057,
 "learning_rate": 5e-06,
 "loss": 0.8621,
 "step": 3840
 },
 {
 "epoch": 1.9672968829841593,
 "grad_norm": 0.06812867527901585,
 "learning_rate": 5e-06,
 "loss": 0.8535,
 "step": 3850
 },
 {
 "epoch": 1.9724067450178846,
 "grad_norm": 0.06914782077210797,
 "learning_rate": 5e-06,
 "loss": 0.8579,
 "step": 3860
 },
 {
 "epoch": 1.9775166070516095,
 "grad_norm": 0.07264208755659882,
 "learning_rate": 5e-06,
 "loss": 0.8587,
 "step": 3870
 },
 {
 "epoch": 1.9826264690853348,
 "grad_norm": 0.07656435460747489,
 "learning_rate": 5e-06,
 "loss": 0.8569,
 "step": 3880
 },
 {
 "epoch": 1.9877363311190597,
 "grad_norm": 0.07973389243138154,
 "learning_rate": 5e-06,
 "loss": 0.8519,
 "step": 3890
 },
 {
 "epoch": 1.992846193152785,
 "grad_norm": 0.07179271046170288,
 "learning_rate": 5e-06,
 "loss": 0.8622,
 "step": 3900
 },
 {
 "epoch": 1.9979560551865099,
 "grad_norm": 0.11365614273983228,
 "learning_rate": 5e-06,
 "loss": 0.8573,
 "step": 3910
 },
 {
 "epoch": 2.003065917220235,
 "grad_norm": 0.07141837340160201,
 "learning_rate": 5e-06,
 "loss": 0.8513,
 "step": 3920
 },
 {
 "epoch": 2.00817577925396,
 "grad_norm": 0.10505624480952601,
 "learning_rate": 5e-06,
 "loss": 0.8631,
 "step": 3930
 },
 {
 "epoch": 2.0132856412876854,
 "grad_norm": 0.07301133387642879,
 "learning_rate": 5e-06,
 "loss": 0.851,
 "step": 3940
 },
 {
 "epoch": 2.0183955033214103,
 "grad_norm": 0.08124439773368344,
 "learning_rate": 5e-06,
 "loss": 0.8556,
 "step": 3950
 },
 {
 "epoch": 2.0235053653551356,
 "grad_norm": 0.18456635683801864,
 "learning_rate": 5e-06,
 "loss": 0.8601,
 "step": 3960
 },
 {
 "epoch": 2.0286152273888605,
 "grad_norm": 0.0839091878240074,
 "learning_rate": 5e-06,
 "loss": 0.8476,
 "step": 3970
 },
 {
 "epoch": 2.033725089422586,
 "grad_norm": 0.06923549834655754,
 "learning_rate": 5e-06,
 "loss": 0.836,
 "step": 3980
 },
 {
 "epoch": 2.0388349514563107,
 "grad_norm": 0.07270485015207773,
 "learning_rate": 5e-06,
 "loss": 0.8559,
 "step": 3990
 },
 {
 "epoch": 2.043944813490036,
 "grad_norm": 0.0855738032972615,
 "learning_rate": 5e-06,
 "loss": 0.8527,
 "step": 4000
 },
 {
 "epoch": 2.049054675523761,
 "grad_norm": 0.0737050057656388,
 "learning_rate": 5e-06,
 "loss": 0.8532,
 "step": 4010
 },
 {
 "epoch": 2.0541645375574857,
 "grad_norm": 0.10214471523135125,
 "learning_rate": 5e-06,
 "loss": 0.8428,
 "step": 4020
 },
 {
 "epoch": 2.059274399591211,
 "grad_norm": 0.0883446336624383,
 "learning_rate": 5e-06,
 "loss": 0.8451,
 "step": 4030
 },
 {
 "epoch": 2.064384261624936,
 "grad_norm": 0.07417051518736814,
 "learning_rate": 5e-06,
 "loss": 0.8536,
 "step": 4040
 },
 {
 "epoch": 2.0694941236586613,
 "grad_norm": 0.06790782347477319,
 "learning_rate": 5e-06,
 "loss": 0.8375,
 "step": 4050
 },
 {
 "epoch": 2.074603985692386,
 "grad_norm": 0.07032456253507346,
 "learning_rate": 5e-06,
 "loss": 0.8429,
 "step": 4060
 },
 {
 "epoch": 2.0797138477261115,
 "grad_norm": 0.10296354446960965,
 "learning_rate": 5e-06,
 "loss": 0.8459,
 "step": 4070
 },
 {
 "epoch": 2.0848237097598363,
 "grad_norm": 0.11146967299257413,
 "learning_rate": 5e-06,
 "loss": 0.8368,
 "step": 4080
 },
 {
 "epoch": 2.0899335717935617,
 "grad_norm": 0.07549742436944092,
 "learning_rate": 5e-06,
 "loss": 0.8523,
 "step": 4090
 },
 {
 "epoch": 2.0950434338272865,
 "grad_norm": 0.07340256510209953,
 "learning_rate": 5e-06,
 "loss": 0.8322,
 "step": 4100
 },
 {
 "epoch": 2.100153295861012,
 "grad_norm": 0.0757031546197513,
 "learning_rate": 5e-06,
 "loss": 0.8551,
 "step": 4110
 },
 {
 "epoch": 2.1052631578947367,
 "grad_norm": 0.15844891302909508,
 "learning_rate": 5e-06,
 "loss": 0.8361,
 "step": 4120
 },
 {
 "epoch": 2.110373019928462,
 "grad_norm": 0.07913043954436448,
 "learning_rate": 5e-06,
 "loss": 0.8478,
 "step": 4130
 },
 {
 "epoch": 2.115482881962187,
 "grad_norm": 0.07876653993674046,
 "learning_rate": 5e-06,
 "loss": 0.8491,
 "step": 4140
 },
 {
 "epoch": 2.1205927439959122,
 "grad_norm": 0.1767146264245717,
 "learning_rate": 5e-06,
 "loss": 0.8451,
 "step": 4150
 },
 {
 "epoch": 2.125702606029637,
 "grad_norm": 0.06871322115584581,
 "learning_rate": 5e-06,
 "loss": 0.8586,
 "step": 4160
 },
 {
 "epoch": 2.1308124680633624,
 "grad_norm": 0.07906449831613256,
 "learning_rate": 5e-06,
 "loss": 0.8477,
 "step": 4170
 },
 {
 "epoch": 2.1359223300970873,
 "grad_norm": 0.09775775034969345,
 "learning_rate": 5e-06,
 "loss": 0.8522,
 "step": 4180
 },
 {
 "epoch": 2.1410321921308126,
 "grad_norm": 0.0760441138088996,
 "learning_rate": 5e-06,
 "loss": 0.8469,
 "step": 4190
 },
 {
 "epoch": 2.1461420541645375,
 "grad_norm": 0.07225182587888014,
 "learning_rate": 5e-06,
 "loss": 0.8608,
 "step": 4200
 },
 {
 "epoch": 2.151251916198263,
 "grad_norm": 0.13154761525803269,
 "learning_rate": 5e-06,
 "loss": 0.8488,
 "step": 4210
 },
 {
 "epoch": 2.1563617782319877,
 "grad_norm": 0.07374851045064566,
 "learning_rate": 5e-06,
 "loss": 0.841,
 "step": 4220
 },
 {
 "epoch": 2.161471640265713,
 "grad_norm": 0.07031542242629284,
 "learning_rate": 5e-06,
 "loss": 0.8568,
 "step": 4230
 },
 {
 "epoch": 2.166581502299438,
 "grad_norm": 0.07651902738251523,
 "learning_rate": 5e-06,
 "loss": 0.8352,
 "step": 4240
 },
 {
 "epoch": 2.171691364333163,
 "grad_norm": 0.071926401689458,
 "learning_rate": 5e-06,
 "loss": 0.8558,
 "step": 4250
 },
 {
 "epoch": 2.176801226366888,
 "grad_norm": 0.07423622272637805,
 "learning_rate": 5e-06,
 "loss": 0.8418,
 "step": 4260
 },
 {
 "epoch": 2.181911088400613,
 "grad_norm": 0.07126311114741704,
 "learning_rate": 5e-06,
 "loss": 0.8522,
 "step": 4270
 },
 {
 "epoch": 2.1870209504343383,
 "grad_norm": 0.07377430376003857,
 "learning_rate": 5e-06,
 "loss": 0.8446,
 "step": 4280
 },
 {
 "epoch": 2.192130812468063,
 "grad_norm": 0.06949191578937867,
 "learning_rate": 5e-06,
 "loss": 0.8454,
 "step": 4290
 },
 {
 "epoch": 2.1972406745017885,
 "grad_norm": 0.07843634966497359,
 "learning_rate": 5e-06,
 "loss": 0.8495,
 "step": 4300
 },
 {
 "epoch": 2.2023505365355134,
 "grad_norm": 0.07396166555039149,
 "learning_rate": 5e-06,
 "loss": 0.8544,
 "step": 4310
 },
 {
 "epoch": 2.2074603985692387,
 "grad_norm": 0.06906877269519048,
 "learning_rate": 5e-06,
 "loss": 0.8519,
 "step": 4320
 },
 {
 "epoch": 2.2125702606029636,
 "grad_norm": 0.07738435381809824,
 "learning_rate": 5e-06,
 "loss": 0.8612,
 "step": 4330
 },
 {
 "epoch": 2.217680122636689,
 "grad_norm": 0.07272677909652538,
 "learning_rate": 5e-06,
 "loss": 0.8483,
 "step": 4340
 },
 {
 "epoch": 2.2227899846704138,
 "grad_norm": 0.1704602161006234,
 "learning_rate": 5e-06,
 "loss": 0.8494,
 "step": 4350
 },
 {
 "epoch": 2.227899846704139,
 "grad_norm": 0.08280430588455355,
 "learning_rate": 5e-06,
 "loss": 0.8369,
 "step": 4360
 },
 {
 "epoch": 2.233009708737864,
 "grad_norm": 0.0778136234869108,
 "learning_rate": 5e-06,
 "loss": 0.8413,
 "step": 4370
 },
 {
 "epoch": 2.2381195707715893,
 "grad_norm": 0.06902177322002463,
 "learning_rate": 5e-06,
 "loss": 0.8555,
 "step": 4380
 },
 {
 "epoch": 2.243229432805314,
 "grad_norm": 0.07436632107648229,
 "learning_rate": 5e-06,
 "loss": 0.8341,
 "step": 4390
 },
 {
 "epoch": 2.2483392948390395,
 "grad_norm": 0.08037131223518179,
 "learning_rate": 5e-06,
 "loss": 0.837,
 "step": 4400
 },
 {
 "epoch": 2.2534491568727644,
 "grad_norm": 0.12080203046044066,
 "learning_rate": 5e-06,
 "loss": 0.8484,
 "step": 4410
 },
 {
 "epoch": 2.2585590189064897,
 "grad_norm": 0.08092569363882715,
 "learning_rate": 5e-06,
 "loss": 0.8387,
 "step": 4420
 },
 {
 "epoch": 2.2636688809402146,
 "grad_norm": 0.07901582143607909,
 "learning_rate": 5e-06,
 "loss": 0.8436,
 "step": 4430
 },
 {
 "epoch": 2.26877874297394,
 "grad_norm": 0.07599584492537564,
 "learning_rate": 5e-06,
 "loss": 0.8603,
 "step": 4440
 },
 {
 "epoch": 2.2738886050076648,
 "grad_norm": 0.07078355889274002,
 "learning_rate": 5e-06,
 "loss": 0.8354,
 "step": 4450
 },
 {
 "epoch": 2.27899846704139,
 "grad_norm": 0.10294533024093251,
 "learning_rate": 5e-06,
 "loss": 0.8515,
 "step": 4460
 },
 {
 "epoch": 2.284108329075115,
 "grad_norm": 0.07272362249279035,
 "learning_rate": 5e-06,
 "loss": 0.8448,
 "step": 4470
 },
 {
 "epoch": 2.28921819110884,
 "grad_norm": 0.07263729571802433,
 "learning_rate": 5e-06,
 "loss": 0.8457,
 "step": 4480
 },
 {
 "epoch": 2.294328053142565,
 "grad_norm": 0.07075340939726783,
 "learning_rate": 5e-06,
 "loss": 0.8479,
 "step": 4490
 },
 {
 "epoch": 2.2994379151762905,
 "grad_norm": 0.07782417357166051,
 "learning_rate": 5e-06,
 "loss": 0.8553,
 "step": 4500
 },
 {
 "epoch": 2.3045477772100154,
 "grad_norm": 0.07531889060674515,
 "learning_rate": 5e-06,
 "loss": 0.8462,
 "step": 4510
 },
 {
 "epoch": 2.3096576392437402,
 "grad_norm": 0.07208019084503213,
 "learning_rate": 5e-06,
 "loss": 0.8525,
 "step": 4520
 },
 {
 "epoch": 2.3147675012774656,
 "grad_norm": 0.0835242862697962,
 "learning_rate": 5e-06,
 "loss": 0.8513,
 "step": 4530
 },
 {
 "epoch": 2.3198773633111904,
 "grad_norm": 0.07119059664069095,
 "learning_rate": 5e-06,
 "loss": 0.8447,
 "step": 4540
 },
 {
 "epoch": 2.3249872253449158,
 "grad_norm": 0.07612636819413399,
 "learning_rate": 5e-06,
 "loss": 0.8392,
 "step": 4550
 },
 {
 "epoch": 2.3300970873786406,
 "grad_norm": 0.19261221848157942,
 "learning_rate": 5e-06,
 "loss": 0.8412,
 "step": 4560
 },
 {
 "epoch": 2.335206949412366,
 "grad_norm": 0.07559214061873046,
 "learning_rate": 5e-06,
 "loss": 0.8439,
 "step": 4570
 },
 {
 "epoch": 2.340316811446091,
 "grad_norm": 0.07642749847907093,
 "learning_rate": 5e-06,
 "loss": 0.8496,
 "step": 4580
 },
 {
 "epoch": 2.345426673479816,
 "grad_norm": 0.08063004427375733,
 "learning_rate": 5e-06,
 "loss": 0.8409,
 "step": 4590
 },
 {
 "epoch": 2.350536535513541,
 "grad_norm": 0.0720684787353252,
 "learning_rate": 5e-06,
 "loss": 0.8307,
 "step": 4600
 },
 {
 "epoch": 2.3556463975472663,
 "grad_norm": 0.0694395988603129,
 "learning_rate": 5e-06,
 "loss": 0.8495,
 "step": 4610
 },
 {
 "epoch": 2.3607562595809912,
 "grad_norm": 0.12026943156490484,
 "learning_rate": 5e-06,
 "loss": 0.853,
 "step": 4620
 },
 {
 "epoch": 2.3658661216147165,
 "grad_norm": 0.07464848880206523,
 "learning_rate": 5e-06,
 "loss": 0.8504,
 "step": 4630
 },
 {
 "epoch": 2.3709759836484414,
 "grad_norm": 0.15496993855974875,
 "learning_rate": 5e-06,
 "loss": 0.8441,
 "step": 4640
 },
 {
 "epoch": 2.3760858456821667,
 "grad_norm": 0.07134185410989129,
 "learning_rate": 5e-06,
 "loss": 0.8447,
 "step": 4650
 },
 {
 "epoch": 2.3811957077158916,
 "grad_norm": 0.07242368272475976,
 "learning_rate": 5e-06,
 "loss": 0.8406,
 "step": 4660
 },
 {
 "epoch": 2.386305569749617,
 "grad_norm": 0.0697443617984476,
 "learning_rate": 5e-06,
 "loss": 0.8329,
 "step": 4670
 },
 {
 "epoch": 2.391415431783342,
 "grad_norm": 0.07044017928388062,
 "learning_rate": 5e-06,
 "loss": 0.8462,
 "step": 4680
 },
 {
 "epoch": 2.396525293817067,
 "grad_norm": 0.06981669634551392,
 "learning_rate": 5e-06,
 "loss": 0.8348,
 "step": 4690
 },
 {
 "epoch": 2.401635155850792,
 "grad_norm": 0.07668972004047576,
 "learning_rate": 5e-06,
 "loss": 0.8398,
 "step": 4700
 },
 {
 "epoch": 2.406745017884517,
 "grad_norm": 0.07415042030571524,
 "learning_rate": 5e-06,
 "loss": 0.8443,
 "step": 4710
 },
 {
 "epoch": 2.411854879918242,
 "grad_norm": 0.07295120303267964,
 "learning_rate": 5e-06,
 "loss": 0.8507,
 "step": 4720
 },
 {
 "epoch": 2.4169647419519675,
 "grad_norm": 0.07741393469112542,
 "learning_rate": 5e-06,
 "loss": 0.8275,
 "step": 4730
 },
 {
 "epoch": 2.4220746039856924,
 "grad_norm": 0.07693385601963627,
 "learning_rate": 5e-06,
 "loss": 0.8308,
 "step": 4740
 },
 {
 "epoch": 2.4271844660194173,
 "grad_norm": 0.0755618799603966,
 "learning_rate": 5e-06,
 "loss": 0.8405,
 "step": 4750
 },
 {
 "epoch": 2.4322943280531426,
 "grad_norm": 0.09159998552156758,
 "learning_rate": 5e-06,
 "loss": 0.8347,
 "step": 4760
 },
 {
 "epoch": 2.4374041900868675,
 "grad_norm": 0.07341845982606449,
 "learning_rate": 5e-06,
 "loss": 0.8322,
 "step": 4770
 },
 {
 "epoch": 2.442514052120593,
 "grad_norm": 0.07237831649311181,
 "learning_rate": 5e-06,
 "loss": 0.8484,
 "step": 4780
 },
 {
 "epoch": 2.4476239141543177,
 "grad_norm": 0.07192165535074778,
 "learning_rate": 5e-06,
 "loss": 0.8408,
 "step": 4790
 },
 {
 "epoch": 2.452733776188043,
 "grad_norm": 0.06648324207306504,
 "learning_rate": 5e-06,
 "loss": 0.8425,
 "step": 4800
 },
 {
 "epoch": 2.457843638221768,
 "grad_norm": 0.07448716190725979,
 "learning_rate": 5e-06,
 "loss": 0.8425,
 "step": 4810
 },
 {
 "epoch": 2.462953500255493,
 "grad_norm": 0.07121284030804295,
 "learning_rate": 5e-06,
 "loss": 0.8375,
 "step": 4820
 },
 {
 "epoch": 2.468063362289218,
 "grad_norm": 0.06909159105773967,
 "learning_rate": 5e-06,
 "loss": 0.854,
 "step": 4830
 },
 {
 "epoch": 2.4731732243229434,
 "grad_norm": 0.13098921577807285,
 "learning_rate": 5e-06,
 "loss": 0.8384,
 "step": 4840
 },
 {
 "epoch": 2.4782830863566683,
 "grad_norm": 0.07170492201621687,
 "learning_rate": 5e-06,
 "loss": 0.8404,
 "step": 4850
 },
 {
 "epoch": 2.4833929483903936,
 "grad_norm": 0.13089324735228272,
 "learning_rate": 5e-06,
 "loss": 0.8348,
 "step": 4860
 },
 {
 "epoch": 2.4885028104241185,
 "grad_norm": 0.08153573679797024,
 "learning_rate": 5e-06,
 "loss": 0.842,
 "step": 4870
 },
 {
 "epoch": 2.493612672457844,
 "grad_norm": 0.07186193556818891,
 "learning_rate": 5e-06,
 "loss": 0.8401,
 "step": 4880
 },
 {
 "epoch": 2.4987225344915687,
 "grad_norm": 0.06985782726108822,
 "learning_rate": 5e-06,
 "loss": 0.8358,
 "step": 4890
 },
 {
 "epoch": 2.5038323965252935,
 "grad_norm": 0.08449885090909025,
 "learning_rate": 5e-06,
 "loss": 0.832,
 "step": 4900
 },
 {
 "epoch": 2.508942258559019,
 "grad_norm": 0.07501130238223368,
 "learning_rate": 5e-06,
 "loss": 0.8418,
 "step": 4910
 },
 {
 "epoch": 2.514052120592744,
 "grad_norm": 0.07141698939838328,
 "learning_rate": 5e-06,
 "loss": 0.8446,
 "step": 4920
 },
 {
 "epoch": 2.519161982626469,
 "grad_norm": 0.08787977387334635,
 "learning_rate": 5e-06,
 "loss": 0.8452,
 "step": 4930
 },
 {
 "epoch": 2.524271844660194,
 "grad_norm": 0.07291979045054302,
 "learning_rate": 5e-06,
 "loss": 0.8272,
 "step": 4940
 },
 {
 "epoch": 2.5293817066939193,
 "grad_norm": 0.09132127326249193,
 "learning_rate": 5e-06,
 "loss": 0.8307,
 "step": 4950
 },
 {
 "epoch": 2.5344915687276446,
 "grad_norm": 0.07043767494061426,
 "learning_rate": 5e-06,
 "loss": 0.8341,
 "step": 4960
 },
 {
 "epoch": 2.5396014307613695,
 "grad_norm": 0.06814985809885249,
 "learning_rate": 5e-06,
 "loss": 0.8434,
 "step": 4970
 },
 {
 "epoch": 2.5447112927950943,
 "grad_norm": 0.06881812234299259,
 "learning_rate": 5e-06,
 "loss": 0.8336,
 "step": 4980
 },
 {
 "epoch": 2.5498211548288197,
 "grad_norm": 0.07479588795644554,
 "learning_rate": 5e-06,
 "loss": 0.841,
 "step": 4990
 },
 {
 "epoch": 2.554931016862545,
 "grad_norm": 0.07030708837765214,
 "learning_rate": 5e-06,
 "loss": 0.8345,
 "step": 5000
 },
 {
 "epoch": 2.56004087889627,
 "grad_norm": 0.07322531185816425,
 "learning_rate": 5e-06,
 "loss": 0.8522,
 "step": 5010
 },
 {
 "epoch": 2.5651507409299947,
 "grad_norm": 0.0773410219834939,
 "learning_rate": 5e-06,
 "loss": 0.8336,
 "step": 5020
 },
 {
 "epoch": 2.57026060296372,
 "grad_norm": 0.07112761941798731,
 "learning_rate": 5e-06,
 "loss": 0.8356,
 "step": 5030
 },
 {
 "epoch": 2.575370464997445,
 "grad_norm": 0.08092671080816972,
 "learning_rate": 5e-06,
 "loss": 0.8395,
 "step": 5040
 },
 {
 "epoch": 2.5804803270311703,
 "grad_norm": 0.0743938817129939,
 "learning_rate": 5e-06,
 "loss": 0.8436,
 "step": 5050
 },
 {
 "epoch": 2.585590189064895,
 "grad_norm": 0.09478134737738281,
 "learning_rate": 5e-06,
 "loss": 0.8346,
 "step": 5060
 },
 {
 "epoch": 2.5907000510986204,
 "grad_norm": 0.07135602438861294,
 "learning_rate": 5e-06,
 "loss": 0.8478,
 "step": 5070
 },
 {
 "epoch": 2.5958099131323453,
 "grad_norm": 0.07891915237359796,
 "learning_rate": 5e-06,
 "loss": 0.8447,
 "step": 5080
 },
 {
 "epoch": 2.6009197751660706,
 "grad_norm": 0.0677288319217476,
 "learning_rate": 5e-06,
 "loss": 0.837,
 "step": 5090
 },
 {
 "epoch": 2.6060296371997955,
 "grad_norm": 0.07944388902515932,
 "learning_rate": 5e-06,
 "loss": 0.835,
 "step": 5100
 },
 {
 "epoch": 2.611139499233521,
 "grad_norm": 0.08111140690525463,
 "learning_rate": 5e-06,
 "loss": 0.8514,
 "step": 5110
 },
 {
 "epoch": 2.6162493612672457,
 "grad_norm": 0.07187495630590449,
 "learning_rate": 5e-06,
 "loss": 0.8218,
 "step": 5120
 },
 {
 "epoch": 2.6213592233009706,
 "grad_norm": 0.07201247333070886,
 "learning_rate": 5e-06,
 "loss": 0.8459,
 "step": 5130
 },
 {
 "epoch": 2.626469085334696,
 "grad_norm": 0.0725250109726293,
 "learning_rate": 5e-06,
 "loss": 0.8316,
 "step": 5140
 },
 {
 "epoch": 2.6315789473684212,
 "grad_norm": 0.06989455908125097,
 "learning_rate": 5e-06,
 "loss": 0.8387,
 "step": 5150
 },
 {
 "epoch": 2.636688809402146,
 "grad_norm": 0.0732170962484253,
 "learning_rate": 5e-06,
 "loss": 0.8293,
 "step": 5160
 },
 {
 "epoch": 2.641798671435871,
 "grad_norm": 0.10306093874083574,
 "learning_rate": 5e-06,
 "loss": 0.8232,
 "step": 5170
 },
 {
 "epoch": 2.6469085334695963,
 "grad_norm": 0.08216331881118105,
 "learning_rate": 5e-06,
 "loss": 0.8313,
 "step": 5180
 },
 {
 "epoch": 2.6520183955033216,
 "grad_norm": 0.076191518190693,
 "learning_rate": 5e-06,
 "loss": 0.8421,
 "step": 5190
 },
 {
 "epoch": 2.6571282575370465,
 "grad_norm": 0.0740134986538764,
 "learning_rate": 5e-06,
 "loss": 0.8299,
 "step": 5200
 },
 {
 "epoch": 2.6622381195707714,
 "grad_norm": 0.07496389694090964,
 "learning_rate": 5e-06,
 "loss": 0.8487,
 "step": 5210
 },
 {
 "epoch": 2.6673479816044967,
 "grad_norm": 0.07747091248924778,
 "learning_rate": 5e-06,
 "loss": 0.8347,
 "step": 5220
 },
 {
 "epoch": 2.672457843638222,
 "grad_norm": 0.07574688789486558,
 "learning_rate": 5e-06,
 "loss": 0.8425,
 "step": 5230
 },
 {
 "epoch": 2.677567705671947,
 "grad_norm": 0.6563717615599837,
 "learning_rate": 5e-06,
 "loss": 0.84,
 "step": 5240
 },
 {
 "epoch": 2.682677567705672,
 "grad_norm": 0.0686367826525851,
 "learning_rate": 5e-06,
 "loss": 0.8379,
 "step": 5250
 },
 {
 "epoch": 2.687787429739397,
 "grad_norm": 0.07371216319372703,
 "learning_rate": 5e-06,
 "loss": 0.8394,
 "step": 5260
 },
 {
 "epoch": 2.692897291773122,
 "grad_norm": 0.08012300669491436,
 "learning_rate": 5e-06,
 "loss": 0.8384,
 "step": 5270
 },
 {
 "epoch": 2.6980071538068473,
 "grad_norm": 0.07316847913612938,
 "learning_rate": 5e-06,
 "loss": 0.8282,
 "step": 5280
 },
 {
 "epoch": 2.703117015840572,
 "grad_norm": 0.07844263026076834,
 "learning_rate": 5e-06,
 "loss": 0.8436,
 "step": 5290
 },
 {
 "epoch": 2.7082268778742975,
 "grad_norm": 0.07050662660833308,
 "learning_rate": 5e-06,
 "loss": 0.8351,
 "step": 5300
 },
 {
 "epoch": 2.7133367399080224,
 "grad_norm": 0.07050037035095988,
 "learning_rate": 5e-06,
 "loss": 0.8316,
 "step": 5310
 },
 {
 "epoch": 2.7184466019417477,
 "grad_norm": 0.08412885461053499,
 "learning_rate": 5e-06,
 "loss": 0.8222,
 "step": 5320
 },
 {
 "epoch": 2.7235564639754726,
 "grad_norm": 0.0687520823166467,
 "learning_rate": 5e-06,
 "loss": 0.8348,
 "step": 5330
 },
 {
 "epoch": 2.728666326009198,
 "grad_norm": 0.06966312923863605,
 "learning_rate": 5e-06,
 "loss": 0.8441,
 "step": 5340
 },
 {
 "epoch": 2.7337761880429228,
 "grad_norm": 0.07226731254674132,
 "learning_rate": 5e-06,
 "loss": 0.848,
 "step": 5350
 },
 {
 "epoch": 2.738886050076648,
 "grad_norm": 0.06981884709594542,
 "learning_rate": 5e-06,
 "loss": 0.8431,
 "step": 5360
 },
 {
 "epoch": 2.743995912110373,
 "grad_norm": 0.2293923868794652,
 "learning_rate": 5e-06,
 "loss": 0.8258,
 "step": 5370
 },
 {
 "epoch": 2.7491057741440983,
 "grad_norm": 0.0711478134486219,
 "learning_rate": 5e-06,
 "loss": 0.8457,
 "step": 5380
 },
 {
 "epoch": 2.754215636177823,
 "grad_norm": 0.0748407931600363,
 "learning_rate": 5e-06,
 "loss": 0.8368,
 "step": 5390
 },
 {
 "epoch": 2.759325498211548,
 "grad_norm": 0.07392069328246453,
 "learning_rate": 5e-06,
 "loss": 0.8352,
 "step": 5400
 },
 {
 "epoch": 2.7644353602452734,
 "grad_norm": 0.0721976398087471,
 "learning_rate": 5e-06,
 "loss": 0.8393,
 "step": 5410
 },
 {
 "epoch": 2.7695452222789987,
 "grad_norm": 0.07095428053471639,
 "learning_rate": 5e-06,
 "loss": 0.8471,
 "step": 5420
 },
 {
 "epoch": 2.7746550843127236,
 "grad_norm": 0.07005521600898579,
 "learning_rate": 5e-06,
 "loss": 0.8313,
 "step": 5430
 },
 {
 "epoch": 2.7797649463464484,
 "grad_norm": 0.07197884091944991,
 "learning_rate": 5e-06,
 "loss": 0.8344,
 "step": 5440
 },
 {
 "epoch": 2.7848748083801738,
 "grad_norm": 0.07344997287379904,
 "learning_rate": 5e-06,
 "loss": 0.8362,
 "step": 5450
 },
 {
 "epoch": 2.789984670413899,
 "grad_norm": 0.08322662489974626,
 "learning_rate": 5e-06,
 "loss": 0.8367,
 "step": 5460
 },
 {
 "epoch": 2.795094532447624,
 "grad_norm": 0.07375885412776004,
 "learning_rate": 5e-06,
 "loss": 0.8512,
 "step": 5470
 },
 {
 "epoch": 2.800204394481349,
 "grad_norm": 0.07070472807893792,
 "learning_rate": 5e-06,
 "loss": 0.8253,
 "step": 5480
 },
 {
 "epoch": 2.805314256515074,
 "grad_norm": 0.07428848558504005,
 "learning_rate": 5e-06,
 "loss": 0.8468,
 "step": 5490
 },
 {
 "epoch": 2.810424118548799,
 "grad_norm": 0.07307806588861744,
 "learning_rate": 5e-06,
 "loss": 0.8234,
 "step": 5500
 },
 {
 "epoch": 2.8155339805825244,
 "grad_norm": 0.06945402346011086,
 "learning_rate": 5e-06,
 "loss": 0.8249,
 "step": 5510
 },
 {
 "epoch": 2.8206438426162492,
 "grad_norm": 0.07097605102696264,
 "learning_rate": 5e-06,
 "loss": 0.825,
 "step": 5520
 },
 {
 "epoch": 2.8257537046499746,
 "grad_norm": 0.06978991852647402,
 "learning_rate": 5e-06,
 "loss": 0.832,
 "step": 5530
 },
 {
 "epoch": 2.8308635666836994,
 "grad_norm": 0.06908078380765026,
 "learning_rate": 5e-06,
 "loss": 0.8399,
 "step": 5540
 },
 {
 "epoch": 2.8359734287174247,
 "grad_norm": 0.07440005138379917,
 "learning_rate": 5e-06,
 "loss": 0.8586,
 "step": 5550
 },
 {
 "epoch": 2.8410832907511496,
 "grad_norm": 0.07215664654991572,
 "learning_rate": 5e-06,
 "loss": 0.8344,
 "step": 5560
 },
 {
 "epoch": 2.846193152784875,
 "grad_norm": 0.07245462980842311,
 "learning_rate": 5e-06,
 "loss": 0.8377,
 "step": 5570
 },
 {
 "epoch": 2.8513030148186,
 "grad_norm": 0.09751916723568736,
 "learning_rate": 5e-06,
 "loss": 0.8359,
 "step": 5580
 },
 {
 "epoch": 2.856412876852325,
 "grad_norm": 0.0855945660262981,
 "learning_rate": 5e-06,
 "loss": 0.8204,
 "step": 5590
 },
 {
 "epoch": 2.86152273888605,
 "grad_norm": 0.07362144431075729,
 "learning_rate": 5e-06,
 "loss": 0.8339,
 "step": 5600
 },
 {
 "epoch": 2.8666326009197753,
 "grad_norm": 0.13422144896661692,
 "learning_rate": 5e-06,
 "loss": 0.8156,
 "step": 5610
 },
 {
 "epoch": 2.8717424629535,
 "grad_norm": 0.07766367283659784,
 "learning_rate": 5e-06,
 "loss": 0.8366,
 "step": 5620
 },
 {
 "epoch": 2.876852324987225,
 "grad_norm": 0.07067764533904561,
 "learning_rate": 5e-06,
 "loss": 0.8319,
 "step": 5630
 },
 {
 "epoch": 2.8819621870209504,
 "grad_norm": 0.07333934553515849,
 "learning_rate": 5e-06,
 "loss": 0.8403,
 "step": 5640
 },
 {
 "epoch": 2.8870720490546757,
 "grad_norm": 0.06944274451784573,
 "learning_rate": 5e-06,
 "loss": 0.8147,
 "step": 5650
 },
 {
 "epoch": 2.8921819110884006,
 "grad_norm": 0.07851574427605637,
 "learning_rate": 5e-06,
 "loss": 0.8324,
 "step": 5660
 },
 {
 "epoch": 2.8972917731221255,
 "grad_norm": 0.07149894775276078,
 "learning_rate": 5e-06,
 "loss": 0.8299,
 "step": 5670
 },
 {
 "epoch": 2.902401635155851,
 "grad_norm": 0.06665250066960869,
 "learning_rate": 5e-06,
 "loss": 0.8375,
 "step": 5680
 },
 {
 "epoch": 2.907511497189576,
 "grad_norm": 0.07577406445198871,
 "learning_rate": 5e-06,
 "loss": 0.8448,
 "step": 5690
 },
 {
 "epoch": 2.912621359223301,
 "grad_norm": 0.0713958097703238,
 "learning_rate": 5e-06,
 "loss": 0.8229,
 "step": 5700
 },
 {
 "epoch": 2.917731221257026,
 "grad_norm": 0.06957330049674462,
 "learning_rate": 5e-06,
 "loss": 0.8183,
 "step": 5710
 },
 {
 "epoch": 2.922841083290751,
 "grad_norm": 0.07288163057814427,
 "learning_rate": 5e-06,
 "loss": 0.8331,
 "step": 5720
 },
 {
 "epoch": 2.927950945324476,
 "grad_norm": 0.08344782116194745,
 "learning_rate": 5e-06,
 "loss": 0.8438,
 "step": 5730
 },
 {
 "epoch": 2.9330608073582014,
 "grad_norm": 0.07775582347773638,
 "learning_rate": 5e-06,
 "loss": 0.8366,
 "step": 5740
 },
 {
 "epoch": 2.9381706693919263,
 "grad_norm": 0.07127430773847676,
 "learning_rate": 5e-06,
 "loss": 0.8292,
 "step": 5750
 },
 {
 "epoch": 2.9432805314256516,
 "grad_norm": 0.07234002587778945,
 "learning_rate": 5e-06,
 "loss": 0.8243,
 "step": 5760
 },
 {
 "epoch": 2.9483903934593765,
 "grad_norm": 0.07200420571093186,
 "learning_rate": 5e-06,
 "loss": 0.8359,
 "step": 5770
 },
 {
 "epoch": 2.953500255493102,
 "grad_norm": 0.07108664442621124,
 "learning_rate": 5e-06,
 "loss": 0.8238,
 "step": 5780
 },
 {
 "epoch": 2.9586101175268267,
 "grad_norm": 0.07157660179737228,
 "learning_rate": 5e-06,
 "loss": 0.8396,
 "step": 5790
 },
 {
 "epoch": 2.963719979560552,
 "grad_norm": 0.0703513442497635,
 "learning_rate": 5e-06,
 "loss": 0.846,
 "step": 5800
 },
 {
 "epoch": 2.968829841594277,
 "grad_norm": 0.07279488037158444,
 "learning_rate": 5e-06,
 "loss": 0.8328,
 "step": 5810
 },
 {
 "epoch": 2.973939703628002,
 "grad_norm": 0.07319627670370121,
 "learning_rate": 5e-06,
 "loss": 0.839,
 "step": 5820
 },
 {
 "epoch": 2.979049565661727,
 "grad_norm": 0.06864454810394688,
 "learning_rate": 5e-06,
 "loss": 0.838,
 "step": 5830
 },
 {
 "epoch": 2.9841594276954524,
 "grad_norm": 0.07409945387796224,
 "learning_rate": 5e-06,
 "loss": 0.8325,
 "step": 5840
 },
 {
 "epoch": 2.9892692897291773,
 "grad_norm": 0.0827828571554194,
 "learning_rate": 5e-06,
 "loss": 0.8348,
 "step": 5850
 },
 {
 "epoch": 2.994379151762902,
 "grad_norm": 0.07176468776677063,
 "learning_rate": 5e-06,
 "loss": 0.8345,
 "step": 5860
 },
 {
 "epoch": 2.9994890137966275,
 "grad_norm": 0.07248509371414884,
 "learning_rate": 5e-06,
 "loss": 0.8471,
 "step": 5870
 },
 {
 "epoch": 3.0,
 "step": 5871,
 "total_flos": 1.808135467381555e+16,
 "train_loss": 0.8794001941176538,
 "train_runtime": 31816.8802,
 "train_samples_per_second": 94.436,
 "train_steps_per_second": 0.185
 }
 ],
 "logging_steps": 10,
 "max_steps": 5871,
 "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": 1.808135467381555e+16,
 "train_batch_size": 16,
 "trial_name": null,
 "trial_params": null
}