nllg
/

tikz-llama-13b / trainer_state.json
Jonas Belouadi
add model files
e026a0f
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 11.993683102298649,
"global_step": 8544,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1.945525291828794e-05,
"loss": 0.7863,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 3.891050583657588e-05,
"loss": 0.7499,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 5.836575875486382e-05,
"loss": 0.687,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 7.782101167315176e-05,
"loss": 0.6787,
"step": 40
},
{
"epoch": 0.07,
"learning_rate": 9.72762645914397e-05,
"loss": 0.6606,
"step": 50
},
{
"epoch": 0.08,
"learning_rate": 0.00011673151750972763,
"loss": 0.6516,
"step": 60
},
{
"epoch": 0.1,
"learning_rate": 0.00013618677042801555,
"loss": 0.6509,
"step": 70
},
{
"epoch": 0.11,
"learning_rate": 0.0001556420233463035,
"loss": 0.6522,
"step": 80
},
{
"epoch": 0.13,
"learning_rate": 0.00017509727626459142,
"loss": 0.6525,
"step": 90
},
{
"epoch": 0.14,
"learning_rate": 0.0001945525291828794,
"loss": 0.6413,
"step": 100
},
{
"epoch": 0.15,
"learning_rate": 0.0002140077821011673,
"loss": 0.6445,
"step": 110
},
{
"epoch": 0.17,
"learning_rate": 0.00023346303501945527,
"loss": 0.6452,
"step": 120
},
{
"epoch": 0.18,
"learning_rate": 0.0002529182879377432,
"loss": 0.6352,
"step": 130
},
{
"epoch": 0.2,
"learning_rate": 0.0002723735408560311,
"loss": 0.6515,
"step": 140
},
{
"epoch": 0.21,
"learning_rate": 0.0002918287937743191,
"loss": 0.6412,
"step": 150
},
{
"epoch": 0.22,
"learning_rate": 0.000311284046692607,
"loss": 0.6401,
"step": 160
},
{
"epoch": 0.24,
"learning_rate": 0.00033073929961089494,
"loss": 0.6444,
"step": 170
},
{
"epoch": 0.25,
"learning_rate": 0.00035019455252918285,
"loss": 0.6319,
"step": 180
},
{
"epoch": 0.27,
"learning_rate": 0.00036964980544747087,
"loss": 0.6369,
"step": 190
},
{
"epoch": 0.28,
"learning_rate": 0.0003891050583657588,
"loss": 0.628,
"step": 200
},
{
"epoch": 0.29,
"learning_rate": 0.0004085603112840467,
"loss": 0.6379,
"step": 210
},
{
"epoch": 0.31,
"learning_rate": 0.0004280155642023346,
"loss": 0.6357,
"step": 220
},
{
"epoch": 0.32,
"learning_rate": 0.00044747081712062257,
"loss": 0.6379,
"step": 230
},
{
"epoch": 0.34,
"learning_rate": 0.00046692607003891054,
"loss": 0.6286,
"step": 240
},
{
"epoch": 0.35,
"learning_rate": 0.00048638132295719845,
"loss": 0.6289,
"step": 250
},
{
"epoch": 0.36,
"learning_rate": 0.0004999998383195374,
"loss": 0.6285,
"step": 260
},
{
"epoch": 0.38,
"learning_rate": 0.0004999969640060184,
"loss": 0.6318,
"step": 270
},
{
"epoch": 0.39,
"learning_rate": 0.0004999904968408763,
"loss": 0.6203,
"step": 280
},
{
"epoch": 0.41,
"learning_rate": 0.0004999804369170547,
"loss": 0.629,
"step": 290
},
{
"epoch": 0.42,
"learning_rate": 0.0004999667843791306,
"loss": 0.6315,
"step": 300
},
{
"epoch": 0.44,
"learning_rate": 0.0004999495394233122,
"loss": 0.6262,
"step": 310
},
{
"epoch": 0.45,
"learning_rate": 0.0004999287022974372,
"loss": 0.6194,
"step": 320
},
{
"epoch": 0.46,
"learning_rate": 0.0004999042733009678,
"loss": 0.6174,
"step": 330
},
{
"epoch": 0.48,
"learning_rate": 0.0004998762527849873,
"loss": 0.622,
"step": 340
},
{
"epoch": 0.49,
"learning_rate": 0.000499844641152195,
"loss": 0.6192,
"step": 350
},
{
"epoch": 0.51,
"learning_rate": 0.0004998094388568999,
"loss": 0.623,
"step": 360
},
{
"epoch": 0.52,
"learning_rate": 0.0004997706464050146,
"loss": 0.6151,
"step": 370
},
{
"epoch": 0.53,
"learning_rate": 0.000499728264354048,
"loss": 0.6,
"step": 380
},
{
"epoch": 0.55,
"learning_rate": 0.0004996822933130973,
"loss": 0.6116,
"step": 390
},
{
"epoch": 0.56,
"learning_rate": 0.000499632733942839,
"loss": 0.611,
"step": 400
},
{
"epoch": 0.58,
"learning_rate": 0.0004995795869555194,
"loss": 0.5975,
"step": 410
},
{
"epoch": 0.59,
"learning_rate": 0.0004995228531149451,
"loss": 0.6124,
"step": 420
},
{
"epoch": 0.6,
"learning_rate": 0.0004994625332364707,
"loss": 0.6025,
"step": 430
},
{
"epoch": 0.62,
"learning_rate": 0.0004993986281869884,
"loss": 0.6121,
"step": 440
},
{
"epoch": 0.63,
"learning_rate": 0.0004993311388849148,
"loss": 0.6107,
"step": 450
},
{
"epoch": 0.65,
"learning_rate": 0.0004992600663001779,
"loss": 0.609,
"step": 460
},
{
"epoch": 0.66,
"learning_rate": 0.000499185411454203,
"loss": 0.6117,
"step": 470
},
{
"epoch": 0.67,
"learning_rate": 0.0004991071754198985,
"loss": 0.6118,
"step": 480
},
{
"epoch": 0.69,
"learning_rate": 0.0004990253593216397,
"loss": 0.6017,
"step": 490
},
{
"epoch": 0.7,
"learning_rate": 0.0004989399643352531,
"loss": 0.6133,
"step": 500
},
{
"epoch": 0.72,
"learning_rate": 0.0004988509916880002,
"loss": 0.6005,
"step": 510
},
{
"epoch": 0.73,
"learning_rate": 0.0004987584426585581,
"loss": 0.6011,
"step": 520
},
{
"epoch": 0.74,
"learning_rate": 0.000498662318577003,
"loss": 0.602,
"step": 530
},
{
"epoch": 0.76,
"learning_rate": 0.0004985626208247897,
"loss": 0.5905,
"step": 540
},
{
"epoch": 0.77,
"learning_rate": 0.0004984593508347327,
"loss": 0.6065,
"step": 550
},
{
"epoch": 0.79,
"learning_rate": 0.0004983525100909849,
"loss": 0.6087,
"step": 560
},
{
"epoch": 0.8,
"learning_rate": 0.0004982421001290169,
"loss": 0.5962,
"step": 570
},
{
"epoch": 0.81,
"learning_rate": 0.0004981281225355941,
"loss": 0.6002,
"step": 580
},
{
"epoch": 0.83,
"learning_rate": 0.000498010578948755,
"loss": 0.5915,
"step": 590
},
{
"epoch": 0.84,
"learning_rate": 0.0004978894710577867,
"loss": 0.6008,
"step": 600
},
{
"epoch": 0.86,
"learning_rate": 0.0004977648006032011,
"loss": 0.5914,
"step": 610
},
{
"epoch": 0.87,
"learning_rate": 0.0004976365693767095,
"loss": 0.5871,
"step": 620
},
{
"epoch": 0.88,
"learning_rate": 0.0004975047792211976,
"loss": 0.597,
"step": 630
},
{
"epoch": 0.9,
"learning_rate": 0.0004973694320306983,
"loss": 0.5929,
"step": 640
},
{
"epoch": 0.91,
"learning_rate": 0.0004972305297503646,
"loss": 0.5927,
"step": 650
},
{
"epoch": 0.93,
"learning_rate": 0.0004970880743764421,
"loss": 0.595,
"step": 660
},
{
"epoch": 0.94,
"learning_rate": 0.0004969420679562394,
"loss": 0.5914,
"step": 670
},
{
"epoch": 0.95,
"learning_rate": 0.0004967925125880998,
"loss": 0.5919,
"step": 680
},
{
"epoch": 0.97,
"learning_rate": 0.0004966394104213704,
"loss": 0.596,
"step": 690
},
{
"epoch": 0.98,
"learning_rate": 0.0004964827636563713,
"loss": 0.584,
"step": 700
},
{
"epoch": 1.0,
"learning_rate": 0.0004963225745443643,
"loss": 0.5826,
"step": 710
},
{
"epoch": 1.01,
"learning_rate": 0.0004961588453875202,
"loss": 0.5518,
"step": 720
},
{
"epoch": 1.02,
"learning_rate": 0.0004959915785388856,
"loss": 0.5273,
"step": 730
},
{
"epoch": 1.04,
"learning_rate": 0.0004958207764023499,
"loss": 0.5329,
"step": 740
},
{
"epoch": 1.05,
"learning_rate": 0.0004956464414326096,
"loss": 0.5333,
"step": 750
},
{
"epoch": 1.07,
"learning_rate": 0.0004954685761351341,
"loss": 0.5299,
"step": 760
},
{
"epoch": 1.08,
"learning_rate": 0.0004952871830661286,
"loss": 0.538,
"step": 770
},
{
"epoch": 1.09,
"learning_rate": 0.0004951022648324985,
"loss": 0.5384,
"step": 780
},
{
"epoch": 1.11,
"learning_rate": 0.0004949138240918111,
"loss": 0.5343,
"step": 790
},
{
"epoch": 1.12,
"learning_rate": 0.0004947218635522579,
"loss": 0.528,
"step": 800
},
{
"epoch": 1.14,
"learning_rate": 0.0004945263859726151,
"loss": 0.5236,
"step": 810
},
{
"epoch": 1.15,
"learning_rate": 0.0004943273941622049,
"loss": 0.5379,
"step": 820
},
{
"epoch": 1.17,
"learning_rate": 0.0004941248909808538,
"loss": 0.5354,
"step": 830
},
{
"epoch": 1.18,
"learning_rate": 0.0004939188793388531,
"loss": 0.5355,
"step": 840
},
{
"epoch": 1.19,
"learning_rate": 0.0004937093621969156,
"loss": 0.5327,
"step": 850
},
{
"epoch": 1.21,
"learning_rate": 0.0004934963425661339,
"loss": 0.5365,
"step": 860
},
{
"epoch": 1.22,
"learning_rate": 0.000493279823507937,
"loss": 0.5237,
"step": 870
},
{
"epoch": 1.24,
"learning_rate": 0.0004930598081340459,
"loss": 0.5271,
"step": 880
},
{
"epoch": 1.25,
"learning_rate": 0.0004928362996064295,
"loss": 0.5305,
"step": 890
},
{
"epoch": 1.26,
"learning_rate": 0.0004926093011372587,
"loss": 0.5324,
"step": 900
},
{
"epoch": 1.28,
"learning_rate": 0.0004923788159888602,
"loss": 0.5366,
"step": 910
},
{
"epoch": 1.29,
"learning_rate": 0.0004921448474736701,
"loss": 0.5359,
"step": 920
},
{
"epoch": 1.31,
"learning_rate": 0.0004919073989541861,
"loss": 0.5263,
"step": 930
},
{
"epoch": 1.32,
"learning_rate": 0.0004916664738429187,
"loss": 0.5219,
"step": 940
},
{
"epoch": 1.33,
"learning_rate": 0.0004914220756023425,
"loss": 0.5312,
"step": 950
},
{
"epoch": 1.35,
"learning_rate": 0.0004911742077448466,
"loss": 0.5283,
"step": 960
},
{
"epoch": 1.36,
"learning_rate": 0.0004909228738326844,
"loss": 0.5252,
"step": 970
},
{
"epoch": 1.38,
"learning_rate": 0.000490668077477921,
"loss": 0.5197,
"step": 980
},
{
"epoch": 1.39,
"learning_rate": 0.0004904098223423833,
"loss": 0.5192,
"step": 990
},
{
"epoch": 1.4,
"learning_rate": 0.0004901481121376058,
"loss": 0.5267,
"step": 1000
},
{
"epoch": 1.42,
"learning_rate": 0.0004898829506247778,
"loss": 0.5177,
"step": 1010
},
{
"epoch": 1.43,
"learning_rate": 0.0004896143416146895,
"loss": 0.5252,
"step": 1020
},
{
"epoch": 1.45,
"learning_rate": 0.0004893422889676772,
"loss": 0.5255,
"step": 1030
},
{
"epoch": 1.46,
"learning_rate": 0.0004890667965935674,
"loss": 0.5295,
"step": 1040
},
{
"epoch": 1.47,
"learning_rate": 0.000488787868451621,
"loss": 0.5232,
"step": 1050
},
{
"epoch": 1.49,
"learning_rate": 0.0004885055085504767,
"loss": 0.5273,
"step": 1060
},
{
"epoch": 1.5,
"learning_rate": 0.0004882197209480924,
"loss": 0.5137,
"step": 1070
},
{
"epoch": 1.52,
"learning_rate": 0.00048793050975168794,
"loss": 0.5305,
"step": 1080
},
{
"epoch": 1.53,
"learning_rate": 0.0004876378791176854,
"loss": 0.5272,
"step": 1090
},
{
"epoch": 1.54,
"learning_rate": 0.0004873418332516497,
"loss": 0.52,
"step": 1100
},
{
"epoch": 1.56,
"learning_rate": 0.0004870423764082279,
"loss": 0.5237,
"step": 1110
},
{
"epoch": 1.57,
"learning_rate": 0.0004867395128910883,
"loss": 0.5314,
"step": 1120
},
{
"epoch": 1.59,
"learning_rate": 0.00048643324705285857,
"loss": 0.526,
"step": 1130
},
{
"epoch": 1.6,
"learning_rate": 0.00048612358329506295,
"loss": 0.5272,
"step": 1140
},
{
"epoch": 1.61,
"learning_rate": 0.0004858105260680592,
"loss": 0.52,
"step": 1150
},
{
"epoch": 1.63,
"learning_rate": 0.00048549407987097463,
"loss": 0.5166,
"step": 1160
},
{
"epoch": 1.64,
"learning_rate": 0.0004851742492516415,
"loss": 0.5257,
"step": 1170
},
{
"epoch": 1.66,
"learning_rate": 0.00048485103880653135,
"loss": 0.5205,
"step": 1180
},
{
"epoch": 1.67,
"learning_rate": 0.00048452445318068933,
"loss": 0.5131,
"step": 1190
},
{
"epoch": 1.68,
"learning_rate": 0.00048419449706766716,
"loss": 0.5203,
"step": 1200
},
{
"epoch": 1.7,
"learning_rate": 0.000483861175209456,
"loss": 0.5136,
"step": 1210
},
{
"epoch": 1.71,
"learning_rate": 0.0004835244923964178,
"loss": 0.5256,
"step": 1220
},
{
"epoch": 1.73,
"learning_rate": 0.0004831844534672169,
"loss": 0.5123,
"step": 1230
},
{
"epoch": 1.74,
"learning_rate": 0.00048284106330875035,
"loss": 0.5099,
"step": 1240
},
{
"epoch": 1.75,
"learning_rate": 0.0004824943268560776,
"loss": 0.5149,
"step": 1250
},
{
"epoch": 1.77,
"learning_rate": 0.0004821442490923498,
"loss": 0.5242,
"step": 1260
},
{
"epoch": 1.78,
"learning_rate": 0.0004817908350487378,
"loss": 0.5202,
"step": 1270
},
{
"epoch": 1.8,
"learning_rate": 0.0004814340898043601,
"loss": 0.5128,
"step": 1280
},
{
"epoch": 1.81,
"learning_rate": 0.00048107401848621,
"loss": 0.5121,
"step": 1290
},
{
"epoch": 1.82,
"learning_rate": 0.00048071062626908154,
"loss": 0.5112,
"step": 1300
},
{
"epoch": 1.84,
"learning_rate": 0.0004803439183754954,
"loss": 0.5222,
"step": 1310
},
{
"epoch": 1.85,
"learning_rate": 0.0004799739000756239,
"loss": 0.5131,
"step": 1320
},
{
"epoch": 1.87,
"learning_rate": 0.0004796005766872149,
"loss": 0.5096,
"step": 1330
},
{
"epoch": 1.88,
"learning_rate": 0.0004792239535755157,
"loss": 0.5223,
"step": 1340
},
{
"epoch": 1.9,
"learning_rate": 0.0004788440361531961,
"loss": 0.5184,
"step": 1350
},
{
"epoch": 1.91,
"learning_rate": 0.00047846082988026975,
"loss": 0.512,
"step": 1360
},
{
"epoch": 1.92,
"learning_rate": 0.0004780743402640169,
"loss": 0.5009,
"step": 1370
},
{
"epoch": 1.94,
"learning_rate": 0.00047768457285890433,
"loss": 0.513,
"step": 1380
},
{
"epoch": 1.95,
"learning_rate": 0.0004772915332665059,
"loss": 0.5149,
"step": 1390
},
{
"epoch": 1.97,
"learning_rate": 0.0004768952271354219,
"loss": 0.5178,
"step": 1400
},
{
"epoch": 1.98,
"learning_rate": 0.00047649566016119807,
"loss": 0.515,
"step": 1410
},
{
"epoch": 1.99,
"learning_rate": 0.0004760928380862435,
"loss": 0.4978,
"step": 1420
},
{
"epoch": 2.01,
"learning_rate": 0.0004756867666997482,
"loss": 0.4615,
"step": 1430
},
{
"epoch": 2.02,
"learning_rate": 0.0004752774518376002,
"loss": 0.4393,
"step": 1440
},
{
"epoch": 2.04,
"learning_rate": 0.00047486489938230103,
"loss": 0.4261,
"step": 1450
},
{
"epoch": 2.05,
"learning_rate": 0.00047444911526288186,
"loss": 0.431,
"step": 1460
},
{
"epoch": 2.06,
"learning_rate": 0.00047403010545481774,
"loss": 0.4347,
"step": 1470
},
{
"epoch": 2.08,
"learning_rate": 0.00047360787597994214,
"loss": 0.4291,
"step": 1480
},
{
"epoch": 2.09,
"learning_rate": 0.00047318243290636017,
"loss": 0.4344,
"step": 1490
},
{
"epoch": 2.11,
"learning_rate": 0.00047275378234836135,
"loss": 0.4306,
"step": 1500
},
{
"epoch": 2.12,
"learning_rate": 0.00047232193046633196,
"loss": 0.4366,
"step": 1510
},
{
"epoch": 2.13,
"learning_rate": 0.00047188688346666633,
"loss": 0.4361,
"step": 1520
},
{
"epoch": 2.15,
"learning_rate": 0.0004714486476016777,
"loss": 0.4312,
"step": 1530
},
{
"epoch": 2.16,
"learning_rate": 0.0004710072291695082,
"loss": 0.4364,
"step": 1540
},
{
"epoch": 2.18,
"learning_rate": 0.00047056263451403864,
"loss": 0.4399,
"step": 1550
},
{
"epoch": 2.19,
"learning_rate": 0.00047011487002479715,
"loss": 0.4294,
"step": 1560
},
{
"epoch": 2.2,
"learning_rate": 0.0004696639421368674,
"loss": 0.4417,
"step": 1570
},
{
"epoch": 2.22,
"learning_rate": 0.00046920985733079593,
"loss": 0.4278,
"step": 1580
},
{
"epoch": 2.23,
"learning_rate": 0.00046875262213249945,
"loss": 0.4337,
"step": 1590
},
{
"epoch": 2.25,
"learning_rate": 0.0004682922431131706,
"loss": 0.4327,
"step": 1600
},
{
"epoch": 2.26,
"learning_rate": 0.00046782872688918377,
"loss": 0.4337,
"step": 1610
},
{
"epoch": 2.27,
"learning_rate": 0.000467362080122,
"loss": 0.4404,
"step": 1620
},
{
"epoch": 2.29,
"learning_rate": 0.00046689230951807095,
"loss": 0.4458,
"step": 1630
},
{
"epoch": 2.3,
"learning_rate": 0.0004664194218287431,
"loss": 0.4429,
"step": 1640
},
{
"epoch": 2.32,
"learning_rate": 0.00046594342385015996,
"loss": 0.4385,
"step": 1650
},
{
"epoch": 2.33,
"learning_rate": 0.00046546432242316533,
"loss": 0.4387,
"step": 1660
},
{
"epoch": 2.34,
"learning_rate": 0.000464982124433204,
"loss": 0.4442,
"step": 1670
},
{
"epoch": 2.36,
"learning_rate": 0.0004644968368102235,
"loss": 0.4414,
"step": 1680
},
{
"epoch": 2.37,
"learning_rate": 0.0004640084665285741,
"loss": 0.4366,
"step": 1690
},
{
"epoch": 2.39,
"learning_rate": 0.00046351702060690907,
"loss": 0.4296,
"step": 1700
},
{
"epoch": 2.4,
"learning_rate": 0.00046302250610808323,
"loss": 0.4373,
"step": 1710
},
{
"epoch": 2.41,
"learning_rate": 0.00046252493013905174,
"loss": 0.4413,
"step": 1720
},
{
"epoch": 2.43,
"learning_rate": 0.00046202429985076787,
"loss": 0.434,
"step": 1730
},
{
"epoch": 2.44,
"learning_rate": 0.00046152062243808045,
"loss": 0.4411,
"step": 1740
},
{
"epoch": 2.46,
"learning_rate": 0.00046101390513963027,
"loss": 0.4463,
"step": 1750
},
{
"epoch": 2.47,
"learning_rate": 0.00046050415523774603,
"loss": 0.4457,
"step": 1760
},
{
"epoch": 2.48,
"learning_rate": 0.00045999138005833965,
"loss": 0.4409,
"step": 1770
},
{
"epoch": 2.5,
"learning_rate": 0.0004594755869708012,
"loss": 0.4234,
"step": 1780
},
{
"epoch": 2.51,
"learning_rate": 0.0004589567833878929,
"loss": 0.4377,
"step": 1790
},
{
"epoch": 2.53,
"learning_rate": 0.0004584349767656424,
"loss": 0.4327,
"step": 1800
},
{
"epoch": 2.54,
"learning_rate": 0.0004579101746032359,
"loss": 0.4352,
"step": 1810
},
{
"epoch": 2.55,
"learning_rate": 0.0004573823844429101,
"loss": 0.4381,
"step": 1820
},
{
"epoch": 2.57,
"learning_rate": 0.0004568516138698442,
"loss": 0.4405,
"step": 1830
},
{
"epoch": 2.58,
"learning_rate": 0.00045631787051205044,
"loss": 0.4366,
"step": 1840
},
{
"epoch": 2.6,
"learning_rate": 0.00045578116204026466,
"loss": 0.4427,
"step": 1850
},
{
"epoch": 2.61,
"learning_rate": 0.00045524149616783615,
"loss": 0.439,
"step": 1860
},
{
"epoch": 2.63,
"learning_rate": 0.00045469888065061685,
"loss": 0.4415,
"step": 1870
},
{
"epoch": 2.64,
"learning_rate": 0.00045415332328684944,
"loss": 0.434,
"step": 1880
},
{
"epoch": 2.65,
"learning_rate": 0.00045360483191705594,
"loss": 0.4377,
"step": 1890
},
{
"epoch": 2.67,
"learning_rate": 0.00045305341442392446,
"loss": 0.4356,
"step": 1900
},
{
"epoch": 2.68,
"learning_rate": 0.0004524990787321961,
"loss": 0.4443,
"step": 1910
},
{
"epoch": 2.7,
"learning_rate": 0.00045194183280855126,
"loss": 0.4358,
"step": 1920
},
{
"epoch": 2.71,
"learning_rate": 0.00045138168466149486,
"loss": 0.4268,
"step": 1930
},
{
"epoch": 2.72,
"learning_rate": 0.00045081864234124136,
"loss": 0.4354,
"step": 1940
},
{
"epoch": 2.74,
"learning_rate": 0.0004502527139395991,
"loss": 0.4448,
"step": 1950
},
{
"epoch": 2.75,
"learning_rate": 0.00044968390758985395,
"loss": 0.4239,
"step": 1960
},
{
"epoch": 2.77,
"learning_rate": 0.0004491122314666525,
"loss": 0.4337,
"step": 1970
},
{
"epoch": 2.78,
"learning_rate": 0.00044853769378588426,
"loss": 0.4404,
"step": 1980
},
{
"epoch": 2.79,
"learning_rate": 0.00044796030280456437,
"loss": 0.4273,
"step": 1990
},
{
"epoch": 2.81,
"learning_rate": 0.0004473800668207139,
"loss": 0.4301,
"step": 2000
},
{
"epoch": 2.82,
"learning_rate": 0.0004467969941732413,
"loss": 0.4326,
"step": 2010
},
{
"epoch": 2.84,
"learning_rate": 0.0004462110932418225,
"loss": 0.4372,
"step": 2020
},
{
"epoch": 2.85,
"learning_rate": 0.0004456223724467801,
"loss": 0.4324,
"step": 2030
},
{
"epoch": 2.86,
"learning_rate": 0.0004450308402489626,
"loss": 0.4315,
"step": 2040
},
{
"epoch": 2.88,
"learning_rate": 0.0004444365051496231,
"loss": 0.4265,
"step": 2050
},
{
"epoch": 2.89,
"learning_rate": 0.00044383937569029665,
"loss": 0.4311,
"step": 2060
},
{
"epoch": 2.91,
"learning_rate": 0.0004432394604526775,
"loss": 0.4368,
"step": 2070
},
{
"epoch": 2.92,
"learning_rate": 0.00044263676805849614,
"loss": 0.4298,
"step": 2080
},
{
"epoch": 2.93,
"learning_rate": 0.00044203130716939524,
"loss": 0.4313,
"step": 2090
},
{
"epoch": 2.95,
"learning_rate": 0.00044142308648680484,
"loss": 0.4337,
"step": 2100
},
{
"epoch": 2.96,
"learning_rate": 0.0004408121147518179,
"loss": 0.4288,
"step": 2110
},
{
"epoch": 2.98,
"learning_rate": 0.0004401984007450642,
"loss": 0.4444,
"step": 2120
},
{
"epoch": 2.99,
"learning_rate": 0.00043958195328658425,
"loss": 0.4356,
"step": 2130
},
{
"epoch": 3.0,
"learning_rate": 0.00043896278123570264,
"loss": 0.4148,
"step": 2140
},
{
"epoch": 3.02,
"learning_rate": 0.0004383408934909008,
"loss": 0.3457,
"step": 2150
},
{
"epoch": 3.03,
"learning_rate": 0.0004377162989896887,
"loss": 0.3431,
"step": 2160
},
{
"epoch": 3.05,
"learning_rate": 0.00043708900670847686,
"loss": 0.3485,
"step": 2170
},
{
"epoch": 3.06,
"learning_rate": 0.0004364590256624471,
"loss": 0.3518,
"step": 2180
},
{
"epoch": 3.07,
"learning_rate": 0.00043582636490542315,
"loss": 0.3371,
"step": 2190
},
{
"epoch": 3.09,
"learning_rate": 0.0004351910335297402,
"loss": 0.3421,
"step": 2200
},
{
"epoch": 3.1,
"learning_rate": 0.0004345530406661148,
"loss": 0.3415,
"step": 2210
},
{
"epoch": 3.12,
"learning_rate": 0.0004339123954835128,
"loss": 0.3398,
"step": 2220
},
{
"epoch": 3.13,
"learning_rate": 0.0004332691071890186,
"loss": 0.3438,
"step": 2230
},
{
"epoch": 3.14,
"learning_rate": 0.00043262318502770185,
"loss": 0.3476,
"step": 2240
},
{
"epoch": 3.16,
"learning_rate": 0.0004319746382824854,
"loss": 0.3421,
"step": 2250
},
{
"epoch": 3.17,
"learning_rate": 0.0004313234762740111,
"loss": 0.3426,
"step": 2260
},
{
"epoch": 3.19,
"learning_rate": 0.0004306697083605068,
"loss": 0.3475,
"step": 2270
},
{
"epoch": 3.2,
"learning_rate": 0.0004300133439376509,
"loss": 0.3514,
"step": 2280
},
{
"epoch": 3.21,
"learning_rate": 0.0004293543924384379,
"loss": 0.3524,
"step": 2290
},
{
"epoch": 3.23,
"learning_rate": 0.0004286928633330426,
"loss": 0.3475,
"step": 2300
},
{
"epoch": 3.24,
"learning_rate": 0.00042802876612868426,
"loss": 0.347,
"step": 2310
},
{
"epoch": 3.26,
"learning_rate": 0.00042736211036948946,
"loss": 0.353,
"step": 2320
},
{
"epoch": 3.27,
"learning_rate": 0.0004266929056363557,
"loss": 0.3518,
"step": 2330
},
{
"epoch": 3.28,
"learning_rate": 0.00042602116154681277,
"loss": 0.359,
"step": 2340
},
{
"epoch": 3.3,
"learning_rate": 0.0004253468877548855,
"loss": 0.344,
"step": 2350
},
{
"epoch": 3.31,
"learning_rate": 0.0004246700939509542,
"loss": 0.3493,
"step": 2360
},
{
"epoch": 3.33,
"learning_rate": 0.0004239907898616159,
"loss": 0.3584,
"step": 2370
},
{
"epoch": 3.34,
"learning_rate": 0.00042330898524954423,
"loss": 0.349,
"step": 2380
},
{
"epoch": 3.35,
"learning_rate": 0.0004226246899133496,
"loss": 0.3578,
"step": 2390
},
{
"epoch": 3.37,
"learning_rate": 0.0004219379136874378,
"loss": 0.3439,
"step": 2400
},
{
"epoch": 3.38,
"learning_rate": 0.000421248666441869,
"loss": 0.3511,
"step": 2410
},
{
"epoch": 3.4,
"learning_rate": 0.0004205569580822158,
"loss": 0.3526,
"step": 2420
},
{
"epoch": 3.41,
"learning_rate": 0.0004198627985494211,
"loss": 0.355,
"step": 2430
},
{
"epoch": 3.43,
"learning_rate": 0.0004191661978196546,
"loss": 0.3509,
"step": 2440
},
{
"epoch": 3.44,
"learning_rate": 0.0004184671659041703,
"loss": 0.3535,
"step": 2450
},
{
"epoch": 3.45,
"learning_rate": 0.000417765712849162,
"loss": 0.3531,
"step": 2460
},
{
"epoch": 3.47,
"learning_rate": 0.00041706184873561904,
"loss": 0.354,
"step": 2470
},
{
"epoch": 3.48,
"learning_rate": 0.0004163555836791816,
"loss": 0.3536,
"step": 2480
},
{
"epoch": 3.5,
"learning_rate": 0.0004156469278299951,
"loss": 0.3573,
"step": 2490
},
{
"epoch": 3.51,
"learning_rate": 0.00041493589137256464,
"loss": 0.3544,
"step": 2500
},
{
"epoch": 3.52,
"learning_rate": 0.00041422248452560817,
"loss": 0.3564,
"step": 2510
},
{
"epoch": 3.54,
"learning_rate": 0.00041350671754190996,
"loss": 0.3584,
"step": 2520
},
{
"epoch": 3.55,
"learning_rate": 0.00041278860070817323,
"loss": 0.3472,
"step": 2530
},
{
"epoch": 3.57,
"learning_rate": 0.0004120681443448724,
"loss": 0.3544,
"step": 2540
},
{
"epoch": 3.58,
"learning_rate": 0.00041134535880610427,
"loss": 0.3525,
"step": 2550
},
{
"epoch": 3.59,
"learning_rate": 0.00041062025447943974,
"loss": 0.3524,
"step": 2560
},
{
"epoch": 3.61,
"learning_rate": 0.0004098928417857746,
"loss": 0.3544,
"step": 2570
},
{
"epoch": 3.62,
"learning_rate": 0.0004091631311791791,
"loss": 0.36,
"step": 2580
},
{
"epoch": 3.64,
"learning_rate": 0.0004084311331467484,
"loss": 0.3522,
"step": 2590
},
{
"epoch": 3.65,
"learning_rate": 0.0004076968582084517,
"loss": 0.3516,
"step": 2600
},
{
"epoch": 3.66,
"learning_rate": 0.0004069603169169805,
"loss": 0.3473,
"step": 2610
},
{
"epoch": 3.68,
"learning_rate": 0.0004062215198575978,
"loss": 0.3471,
"step": 2620
},
{
"epoch": 3.69,
"learning_rate": 0.00040548047764798545,
"loss": 0.3577,
"step": 2630
},
{
"epoch": 3.71,
"learning_rate": 0.0004047372009380914,
"loss": 0.348,
"step": 2640
},
{
"epoch": 3.72,
"learning_rate": 0.00040399170040997733,
"loss": 0.3482,
"step": 2650
},
{
"epoch": 3.73,
"learning_rate": 0.00040324398677766437,
"loss": 0.3566,
"step": 2660
},
{
"epoch": 3.75,
"learning_rate": 0.0004024940707869796,
"loss": 0.3506,
"step": 2670
},
{
"epoch": 3.76,
"learning_rate": 0.00040174196321540143,
"loss": 0.351,
"step": 2680
},
{
"epoch": 3.78,
"learning_rate": 0.00040098767487190467,
"loss": 0.3591,
"step": 2690
},
{
"epoch": 3.79,
"learning_rate": 0.0004002312165968055,
"loss": 0.3555,
"step": 2700
},
{
"epoch": 3.8,
"learning_rate": 0.00039947259926160524,
"loss": 0.3529,
"step": 2710
},
{
"epoch": 3.82,
"learning_rate": 0.00039871183376883435,
"loss": 0.3533,
"step": 2720
},
{
"epoch": 3.83,
"learning_rate": 0.0003979489310518958,
"loss": 0.3443,
"step": 2730
},
{
"epoch": 3.85,
"learning_rate": 0.00039718390207490784,
"loss": 0.3605,
"step": 2740
},
{
"epoch": 3.86,
"learning_rate": 0.0003964167578325463,
"loss": 0.3493,
"step": 2750
},
{
"epoch": 3.87,
"learning_rate": 0.0003956475093498869,
"loss": 0.3553,
"step": 2760
},
{
"epoch": 3.89,
"learning_rate": 0.00039487616768224646,
"loss": 0.3567,
"step": 2770
},
{
"epoch": 3.9,
"learning_rate": 0.0003941027439150243,
"loss": 0.353,
"step": 2780
},
{
"epoch": 3.92,
"learning_rate": 0.0003933272491635428,
"loss": 0.3457,
"step": 2790
},
{
"epoch": 3.93,
"learning_rate": 0.0003925496945728875,
"loss": 0.349,
"step": 2800
},
{
"epoch": 3.94,
"learning_rate": 0.00039177009131774714,
"loss": 0.3552,
"step": 2810
},
{
"epoch": 3.96,
"learning_rate": 0.0003909884506022533,
"loss": 0.3598,
"step": 2820
},
{
"epoch": 3.97,
"learning_rate": 0.00039020478365981863,
"loss": 0.3508,
"step": 2830
},
{
"epoch": 3.99,
"learning_rate": 0.0003894191017529762,
"loss": 0.3526,
"step": 2840
},
{
"epoch": 4.0,
"learning_rate": 0.00038863141617321716,
"loss": 0.3501,
"step": 2850
},
{
"epoch": 4.01,
"learning_rate": 0.0003878417382408287,
"loss": 0.2593,
"step": 2860
},
{
"epoch": 4.03,
"learning_rate": 0.00038705007930473113,
"loss": 0.2563,
"step": 2870
},
{
"epoch": 4.04,
"learning_rate": 0.00038625645074231497,
"loss": 0.2593,
"step": 2880
},
{
"epoch": 4.06,
"learning_rate": 0.0003854608639592775,
"loss": 0.2586,
"step": 2890
},
{
"epoch": 4.07,
"learning_rate": 0.00038466333038945856,
"loss": 0.2591,
"step": 2900
},
{
"epoch": 4.08,
"learning_rate": 0.00038386386149467645,
"loss": 0.2563,
"step": 2910
},
{
"epoch": 4.1,
"learning_rate": 0.0003830624687645633,
"loss": 0.275,
"step": 2920
},
{
"epoch": 4.11,
"learning_rate": 0.00038225916371639946,
"loss": 0.2633,
"step": 2930
},
{
"epoch": 4.13,
"learning_rate": 0.0003814539578949486,
"loss": 0.2662,
"step": 2940
},
{
"epoch": 4.14,
"learning_rate": 0.00038064686287229147,
"loss": 0.2752,
"step": 2950
},
{
"epoch": 4.16,
"learning_rate": 0.00037983789024765945,
"loss": 0.2747,
"step": 2960
},
{
"epoch": 4.17,
"learning_rate": 0.00037902705164726837,
"loss": 0.2657,
"step": 2970
},
{
"epoch": 4.18,
"learning_rate": 0.0003782143587241507,
"loss": 0.2677,
"step": 2980
},
{
"epoch": 4.2,
"learning_rate": 0.00037739982315798865,
"loss": 0.2771,
"step": 2990
},
{
"epoch": 4.21,
"learning_rate": 0.0003765834566549462,
"loss": 0.2604,
"step": 3000
},
{
"epoch": 4.23,
"learning_rate": 0.00037576527094750057,
"loss": 0.2678,
"step": 3010
},
{
"epoch": 4.24,
"learning_rate": 0.00037494527779427403,
"loss": 0.2716,
"step": 3020
},
{
"epoch": 4.25,
"learning_rate": 0.0003741234889798645,
"loss": 0.2692,
"step": 3030
},
{
"epoch": 4.27,
"learning_rate": 0.00037329991631467665,
"loss": 0.2658,
"step": 3040
},
{
"epoch": 4.28,
"learning_rate": 0.0003724745716347516,
"loss": 0.2766,
"step": 3050
},
{
"epoch": 4.3,
"learning_rate": 0.0003716474668015975,
"loss": 0.2732,
"step": 3060
},
{
"epoch": 4.31,
"learning_rate": 0.0003708186137020184,
"loss": 0.268,
"step": 3070
},
{
"epoch": 4.32,
"learning_rate": 0.00036998802424794363,
"loss": 0.2762,
"step": 3080
},
{
"epoch": 4.34,
"learning_rate": 0.00036915571037625703,
"loss": 0.2742,
"step": 3090
},
{
"epoch": 4.35,
"learning_rate": 0.00036832168404862467,
"loss": 0.2708,
"step": 3100
},
{
"epoch": 4.37,
"learning_rate": 0.00036748595725132353,
"loss": 0.2723,
"step": 3110
},
{
"epoch": 4.38,
"learning_rate": 0.0003666485419950691,
"loss": 0.281,
"step": 3120
},
{
"epoch": 4.39,
"learning_rate": 0.00036580945031484247,
"loss": 0.2724,
"step": 3130
},
{
"epoch": 4.41,
"learning_rate": 0.0003649686942697178,
"loss": 0.2731,
"step": 3140
},
{
"epoch": 4.42,
"learning_rate": 0.0003641262859426885,
"loss": 0.2768,
"step": 3150
},
{
"epoch": 4.44,
"learning_rate": 0.00036328223744049433,
"loss": 0.2784,
"step": 3160
},
{
"epoch": 4.45,
"learning_rate": 0.0003624365608934467,
"loss": 0.2747,
"step": 3170
},
{
"epoch": 4.46,
"learning_rate": 0.00036158926845525444,
"loss": 0.2763,
"step": 3180
},
{
"epoch": 4.48,
"learning_rate": 0.00036074037230284965,
"loss": 0.2752,
"step": 3190
},
{
"epoch": 4.49,
"learning_rate": 0.00035988988463621206,
"loss": 0.2783,
"step": 3200
},
{
"epoch": 4.51,
"learning_rate": 0.00035903781767819424,
"loss": 0.2708,
"step": 3210
},
{
"epoch": 4.52,
"learning_rate": 0.00035818418367434537,
"loss": 0.2801,
"step": 3220
},
{
"epoch": 4.53,
"learning_rate": 0.00035732899489273565,
"loss": 0.2777,
"step": 3230
},
{
"epoch": 4.55,
"learning_rate": 0.00035647226362378007,
"loss": 0.2763,
"step": 3240
},
{
"epoch": 4.56,
"learning_rate": 0.00035561400218006133,
"loss": 0.2729,
"step": 3250
},
{
"epoch": 4.58,
"learning_rate": 0.0003547542228961535,
"loss": 0.2764,
"step": 3260
},
{
"epoch": 4.59,
"learning_rate": 0.00035389293812844403,
"loss": 0.2775,
"step": 3270
},
{
"epoch": 4.6,
"learning_rate": 0.0003530301602549568,
"loss": 0.279,
"step": 3280
},
{
"epoch": 4.62,
"learning_rate": 0.000352165901675174,
"loss": 0.2821,
"step": 3290
},
{
"epoch": 4.63,
"learning_rate": 0.0003513001748098578,
"loss": 0.2779,
"step": 3300
},
{
"epoch": 4.65,
"learning_rate": 0.00035043299210087196,
"loss": 0.2756,
"step": 3310
},
{
"epoch": 4.66,
"learning_rate": 0.00034956436601100304,
"loss": 0.2732,
"step": 3320
},
{
"epoch": 4.67,
"learning_rate": 0.0003486943090237813,
"loss": 0.2737,
"step": 3330
},
{
"epoch": 4.69,
"learning_rate": 0.00034782283364330116,
"loss": 0.2798,
"step": 3340
},
{
"epoch": 4.7,
"learning_rate": 0.00034694995239404166,
"loss": 0.2794,
"step": 3350
},
{
"epoch": 4.72,
"learning_rate": 0.0003460756778206865,
"loss": 0.2828,
"step": 3360
},
{
"epoch": 4.73,
"learning_rate": 0.00034520002248794335,
"loss": 0.2788,
"step": 3370
},
{
"epoch": 4.74,
"learning_rate": 0.000344322998980364,
"loss": 0.2717,
"step": 3380
},
{
"epoch": 4.76,
"learning_rate": 0.0003434446199021627,
"loss": 0.2771,
"step": 3390
},
{
"epoch": 4.77,
"learning_rate": 0.00034256489787703553,
"loss": 0.2815,
"step": 3400
},
{
"epoch": 4.79,
"learning_rate": 0.000341683845547979,
"loss": 0.2813,
"step": 3410
},
{
"epoch": 4.8,
"learning_rate": 0.0003408014755771078,
"loss": 0.2748,
"step": 3420
},
{
"epoch": 4.81,
"learning_rate": 0.00033991780064547377,
"loss": 0.273,
"step": 3430
},
{
"epoch": 4.83,
"learning_rate": 0.0003390328334528825,
"loss": 0.2762,
"step": 3440
},
{
"epoch": 4.84,
"learning_rate": 0.0003381465867177118,
"loss": 0.2761,
"step": 3450
},
{
"epoch": 4.86,
"learning_rate": 0.0003372590731767284,
"loss": 0.2781,
"step": 3460
},
{
"epoch": 4.87,
"learning_rate": 0.00033637030558490515,
"loss": 0.2745,
"step": 3470
},
{
"epoch": 4.89,
"learning_rate": 0.0003354802967152375,
"loss": 0.2766,
"step": 3480
},
{
"epoch": 4.9,
"learning_rate": 0.0003345890593585599,
"loss": 0.2772,
"step": 3490
},
{
"epoch": 4.91,
"learning_rate": 0.00033369660632336237,
"loss": 0.2877,
"step": 3500
},
{
"epoch": 4.93,
"learning_rate": 0.00033280295043560586,
"loss": 0.2722,
"step": 3510
},
{
"epoch": 4.94,
"learning_rate": 0.0003319081045385385,
"loss": 0.2782,
"step": 3520
},
{
"epoch": 4.96,
"learning_rate": 0.0003310120814925106,
"loss": 0.2842,
"step": 3530
},
{
"epoch": 4.97,
"learning_rate": 0.0003301148941747899,
"loss": 0.2749,
"step": 3540
},
{
"epoch": 4.98,
"learning_rate": 0.00032921655547937665,
"loss": 0.2787,
"step": 3550
},
{
"epoch": 5.0,
"learning_rate": 0.0003283170783168181,
"loss": 0.2718,
"step": 3560
},
{
"epoch": 5.01,
"learning_rate": 0.00032741647561402334,
"loss": 0.2153,
"step": 3570
},
{
"epoch": 5.03,
"learning_rate": 0.000326514760314077,
"loss": 0.1991,
"step": 3580
},
{
"epoch": 5.04,
"learning_rate": 0.0003256119453760535,
"loss": 0.1957,
"step": 3590
},
{
"epoch": 5.05,
"learning_rate": 0.000324708043774831,
"loss": 0.1948,
"step": 3600
},
{
"epoch": 5.07,
"learning_rate": 0.00032380306850090444,
"loss": 0.2007,
"step": 3610
},
{
"epoch": 5.08,
"learning_rate": 0.00032289703256019954,
"loss": 0.2007,
"step": 3620
},
{
"epoch": 5.1,
"learning_rate": 0.00032198994897388494,
"loss": 0.1995,
"step": 3630
},
{
"epoch": 5.11,
"learning_rate": 0.000321081830778186,
"loss": 0.1948,
"step": 3640
},
{
"epoch": 5.12,
"learning_rate": 0.00032017269102419714,
"loss": 0.195,
"step": 3650
},
{
"epoch": 5.14,
"learning_rate": 0.0003192625427776937,
"loss": 0.1988,
"step": 3660
},
{
"epoch": 5.15,
"learning_rate": 0.00031835139911894506,
"loss": 0.192,
"step": 3670
},
{
"epoch": 5.17,
"learning_rate": 0.0003174392731425262,
"loss": 0.2004,
"step": 3680
},
{
"epoch": 5.18,
"learning_rate": 0.00031652617795712936,
"loss": 0.1988,
"step": 3690
},
{
"epoch": 5.19,
"learning_rate": 0.0003156121266853761,
"loss": 0.2009,
"step": 3700
},
{
"epoch": 5.21,
"learning_rate": 0.0003146971324636282,
"loss": 0.2006,
"step": 3710
},
{
"epoch": 5.22,
"learning_rate": 0.0003137812084417994,
"loss": 0.2021,
"step": 3720
},
{
"epoch": 5.24,
"learning_rate": 0.0003128643677831659,
"loss": 0.2075,
"step": 3730
},
{
"epoch": 5.25,
"learning_rate": 0.00031194662366417755,
"loss": 0.1995,
"step": 3740
},
{
"epoch": 5.26,
"learning_rate": 0.0003110279892742682,
"loss": 0.197,
"step": 3750
},
{
"epoch": 5.28,
"learning_rate": 0.0003101084778156666,
"loss": 0.201,
"step": 3760
},
{
"epoch": 5.29,
"learning_rate": 0.00030918810250320607,
"loss": 0.2033,
"step": 3770
},
{
"epoch": 5.31,
"learning_rate": 0.0003082668765641349,
"loss": 0.2054,
"step": 3780
},
{
"epoch": 5.32,
"learning_rate": 0.0003073448132379264,
"loss": 0.2076,
"step": 3790
},
{
"epoch": 5.33,
"learning_rate": 0.0003064219257760884,
"loss": 0.2095,
"step": 3800
},
{
"epoch": 5.35,
"learning_rate": 0.0003054982274419728,
"loss": 0.2033,
"step": 3810
},
{
"epoch": 5.36,
"learning_rate": 0.00030457373151058506,
"loss": 0.2048,
"step": 3820
},
{
"epoch": 5.38,
"learning_rate": 0.00030364845126839326,
"loss": 0.1994,
"step": 3830
},
{
"epoch": 5.39,
"learning_rate": 0.0003027224000131375,
"loss": 0.211,
"step": 3840
},
{
"epoch": 5.4,
"learning_rate": 0.00030179559105363837,
"loss": 0.196,
"step": 3850
},
{
"epoch": 5.42,
"learning_rate": 0.000300868037709606,
"loss": 0.2029,
"step": 3860
},
{
"epoch": 5.43,
"learning_rate": 0.00029993975331144826,
"loss": 0.1951,
"step": 3870
},
{
"epoch": 5.45,
"learning_rate": 0.0002990107512000796,
"loss": 0.2014,
"step": 3880
},
{
"epoch": 5.46,
"learning_rate": 0.0002980810447267294,
"loss": 0.1984,
"step": 3890
},
{
"epoch": 5.47,
"learning_rate": 0.00029715064725274927,
"loss": 0.1987,
"step": 3900
},
{
"epoch": 5.49,
"learning_rate": 0.000296219572149422,
"loss": 0.2082,
"step": 3910
},
{
"epoch": 5.5,
"learning_rate": 0.0002952878327977688,
"loss": 0.1999,
"step": 3920
},
{
"epoch": 5.52,
"learning_rate": 0.0002943554425883574,
"loss": 0.2027,
"step": 3930
},
{
"epoch": 5.53,
"learning_rate": 0.00029342241492110924,
"loss": 0.2015,
"step": 3940
},
{
"epoch": 5.54,
"learning_rate": 0.00029248876320510673,
"loss": 0.203,
"step": 3950
},
{
"epoch": 5.56,
"learning_rate": 0.0002915545008584016,
"loss": 0.2082,
"step": 3960
},
{
"epoch": 5.57,
"learning_rate": 0.0002906196413078205,
"loss": 0.1998,
"step": 3970
},
{
"epoch": 5.59,
"learning_rate": 0.00028968419798877334,
"loss": 0.2045,
"step": 3980
},
{
"epoch": 5.6,
"learning_rate": 0.00028874818434505964,
"loss": 0.2071,
"step": 3990
},
{
"epoch": 5.62,
"learning_rate": 0.00028781161382867513,
"loss": 0.209,
"step": 4000
},
{
"epoch": 5.63,
"learning_rate": 0.00028687449989961905,
"loss": 0.2027,
"step": 4010
},
{
"epoch": 5.64,
"learning_rate": 0.00028593685602570007,
"loss": 0.2067,
"step": 4020
},
{
"epoch": 5.66,
"learning_rate": 0.00028499869568234307,
"loss": 0.207,
"step": 4030
},
{
"epoch": 5.67,
"learning_rate": 0.00028406003235239554,
"loss": 0.215,
"step": 4040
},
{
"epoch": 5.69,
"learning_rate": 0.0002831208795259334,
"loss": 0.2028,
"step": 4050
},
{
"epoch": 5.7,
"learning_rate": 0.00028218125070006786,
"loss": 0.2015,
"step": 4060
},
{
"epoch": 5.71,
"learning_rate": 0.0002812411593787504,
"loss": 0.2036,
"step": 4070
},
{
"epoch": 5.73,
"learning_rate": 0.0002803006190725798,
"loss": 0.2016,
"step": 4080
},
{
"epoch": 5.74,
"learning_rate": 0.00027935964329860733,
"loss": 0.2093,
"step": 4090
},
{
"epoch": 5.76,
"learning_rate": 0.0002784182455801423,
"loss": 0.2013,
"step": 4100
},
{
"epoch": 5.77,
"learning_rate": 0.00027747643944655865,
"loss": 0.2082,
"step": 4110
},
{
"epoch": 5.78,
"learning_rate": 0.0002765342384330992,
"loss": 0.2067,
"step": 4120
},
{
"epoch": 5.8,
"learning_rate": 0.00027559165608068246,
"loss": 0.2086,
"step": 4130
},
{
"epoch": 5.81,
"learning_rate": 0.00027464870593570676,
"loss": 0.2013,
"step": 4140
},
{
"epoch": 5.83,
"learning_rate": 0.0002737054015498567,
"loss": 0.2053,
"step": 4150
},
{
"epoch": 5.84,
"learning_rate": 0.0002727617564799077,
"loss": 0.2044,
"step": 4160
},
{
"epoch": 5.85,
"learning_rate": 0.00027181778428753123,
"loss": 0.2097,
"step": 4170
},
{
"epoch": 5.87,
"learning_rate": 0.0002708734985391002,
"loss": 0.204,
"step": 4180
},
{
"epoch": 5.88,
"learning_rate": 0.0002699289128054938,
"loss": 0.2083,
"step": 4190
},
{
"epoch": 5.9,
"learning_rate": 0.0002689840406619023,
"loss": 0.199,
"step": 4200
},
{
"epoch": 5.91,
"learning_rate": 0.0002680388956876324,
"loss": 0.2085,
"step": 4210
},
{
"epoch": 5.92,
"learning_rate": 0.00026709349146591157,
"loss": 0.2082,
"step": 4220
},
{
"epoch": 5.94,
"learning_rate": 0.00026614784158369325,
"loss": 0.2041,
"step": 4230
},
{
"epoch": 5.95,
"learning_rate": 0.0002652019596314613,
"loss": 0.2147,
"step": 4240
},
{
"epoch": 5.97,
"learning_rate": 0.0002642558592030348,
"loss": 0.2083,
"step": 4250
},
{
"epoch": 5.98,
"learning_rate": 0.00026330955389537275,
"loss": 0.2069,
"step": 4260
},
{
"epoch": 5.99,
"learning_rate": 0.0002623630573083786,
"loss": 0.2074,
"step": 4270
},
{
"epoch": 6.01,
"learning_rate": 0.00026141638304470467,
"loss": 0.1651,
"step": 4280
},
{
"epoch": 6.02,
"learning_rate": 0.0002604695447095568,
"loss": 0.1415,
"step": 4290
},
{
"epoch": 6.04,
"learning_rate": 0.000259522555910499,
"loss": 0.1371,
"step": 4300
},
{
"epoch": 6.05,
"learning_rate": 0.0002585754302572574,
"loss": 0.1379,
"step": 4310
},
{
"epoch": 6.06,
"learning_rate": 0.000257628181361525,
"loss": 0.1381,
"step": 4320
},
{
"epoch": 6.08,
"learning_rate": 0.00025668082283676613,
"loss": 0.1404,
"step": 4330
},
{
"epoch": 6.09,
"learning_rate": 0.0002557333682980206,
"loss": 0.1379,
"step": 4340
},
{
"epoch": 6.11,
"learning_rate": 0.0002547858313617081,
"loss": 0.1398,
"step": 4350
},
{
"epoch": 6.12,
"learning_rate": 0.00025383822564543234,
"loss": 0.1387,
"step": 4360
},
{
"epoch": 6.13,
"learning_rate": 0.0002528905647677859,
"loss": 0.1401,
"step": 4370
},
{
"epoch": 6.15,
"learning_rate": 0.00025194286234815356,
"loss": 0.1394,
"step": 4380
},
{
"epoch": 6.16,
"learning_rate": 0.0002509951320065176,
"loss": 0.1447,
"step": 4390
},
{
"epoch": 6.18,
"learning_rate": 0.00025004738736326135,
"loss": 0.141,
"step": 4400
},
{
"epoch": 6.19,
"learning_rate": 0.0002490996420389738,
"loss": 0.1442,
"step": 4410
},
{
"epoch": 6.2,
"learning_rate": 0.0002481519096542537,
"loss": 0.1398,
"step": 4420
},
{
"epoch": 6.22,
"learning_rate": 0.0002472042038295137,
"loss": 0.1412,
"step": 4430
},
{
"epoch": 6.23,
"learning_rate": 0.0002462565381847849,
"loss": 0.1442,
"step": 4440
},
{
"epoch": 6.25,
"learning_rate": 0.00024530892633952084,
"loss": 0.1383,
"step": 4450
},
{
"epoch": 6.26,
"learning_rate": 0.000244361381912402,
"loss": 0.1383,
"step": 4460
},
{
"epoch": 6.27,
"learning_rate": 0.00024341391852113984,
"loss": 0.1476,
"step": 4470
},
{
"epoch": 6.29,
"learning_rate": 0.0002424665497822812,
"loss": 0.1414,
"step": 4480
},
{
"epoch": 6.3,
"learning_rate": 0.0002415192893110128,
"loss": 0.1399,
"step": 4490
},
{
"epoch": 6.32,
"learning_rate": 0.0002405721507209651,
"loss": 0.1471,
"step": 4500
},
{
"epoch": 6.33,
"learning_rate": 0.00023962514762401721,
"loss": 0.1402,
"step": 4510
},
{
"epoch": 6.34,
"learning_rate": 0.0002386782936301008,
"loss": 0.1449,
"step": 4520
},
{
"epoch": 6.36,
"learning_rate": 0.0002377316023470048,
"loss": 0.1442,
"step": 4530
},
{
"epoch": 6.37,
"learning_rate": 0.00023678508738017958,
"loss": 0.1468,
"step": 4540
},
{
"epoch": 6.39,
"learning_rate": 0.00023583876233254183,
"loss": 0.1475,
"step": 4550
},
{
"epoch": 6.4,
"learning_rate": 0.00023489264080427854,
"loss": 0.1465,
"step": 4560
},
{
"epoch": 6.42,
"learning_rate": 0.00023394673639265192,
"loss": 0.1433,
"step": 4570
},
{
"epoch": 6.43,
"learning_rate": 0.00023300106269180394,
"loss": 0.1443,
"step": 4580
},
{
"epoch": 6.44,
"learning_rate": 0.00023205563329256062,
"loss": 0.1407,
"step": 4590
},
{
"epoch": 6.46,
"learning_rate": 0.0002311104617822374,
"loss": 0.1456,
"step": 4600
},
{
"epoch": 6.47,
"learning_rate": 0.00023016556174444298,
"loss": 0.1423,
"step": 4610
},
{
"epoch": 6.49,
"learning_rate": 0.0002292209467588851,
"loss": 0.148,
"step": 4620
},
{
"epoch": 6.5,
"learning_rate": 0.00022827663040117424,
"loss": 0.1431,
"step": 4630
},
{
"epoch": 6.51,
"learning_rate": 0.00022733262624262976,
"loss": 0.1495,
"step": 4640
},
{
"epoch": 6.53,
"learning_rate": 0.00022638894785008358,
"loss": 0.1472,
"step": 4650
},
{
"epoch": 6.54,
"learning_rate": 0.00022544560878568645,
"loss": 0.1462,
"step": 4660
},
{
"epoch": 6.56,
"learning_rate": 0.00022450262260671202,
"loss": 0.145,
"step": 4670
},
{
"epoch": 6.57,
"learning_rate": 0.00022356000286536266,
"loss": 0.1507,
"step": 4680
},
{
"epoch": 6.58,
"learning_rate": 0.00022261776310857434,
"loss": 0.1458,
"step": 4690
},
{
"epoch": 6.6,
"learning_rate": 0.00022167591687782186,
"loss": 0.15,
"step": 4700
},
{
"epoch": 6.61,
"learning_rate": 0.00022073447770892487,
"loss": 0.1394,
"step": 4710
},
{
"epoch": 6.63,
"learning_rate": 0.00021979345913185255,
"loss": 0.1477,
"step": 4720
},
{
"epoch": 6.64,
"learning_rate": 0.00021885287467052973,
"loss": 0.1436,
"step": 4730
},
{
"epoch": 6.65,
"learning_rate": 0.00021791273784264203,
"loss": 0.145,
"step": 4740
},
{
"epoch": 6.67,
"learning_rate": 0.00021697306215944222,
"loss": 0.1427,
"step": 4750
},
{
"epoch": 6.68,
"learning_rate": 0.0002160338611255554,
"loss": 0.1488,
"step": 4760
},
{
"epoch": 6.7,
"learning_rate": 0.00021509514823878537,
"loss": 0.1471,
"step": 4770
},
{
"epoch": 6.71,
"learning_rate": 0.0002141569369899204,
"loss": 0.1477,
"step": 4780
},
{
"epoch": 6.72,
"learning_rate": 0.00021321924086253953,
"loss": 0.1487,
"step": 4790
},
{
"epoch": 6.74,
"learning_rate": 0.0002122820733328186,
"loss": 0.1449,
"step": 4800
},
{
"epoch": 6.75,
"learning_rate": 0.00021134544786933663,
"loss": 0.1401,
"step": 4810
},
{
"epoch": 6.77,
"learning_rate": 0.00021040937793288242,
"loss": 0.1485,
"step": 4820
},
{
"epoch": 6.78,
"learning_rate": 0.00020947387697626085,
"loss": 0.1417,
"step": 4830
},
{
"epoch": 6.79,
"learning_rate": 0.00020853895844409983,
"loss": 0.1404,
"step": 4840
},
{
"epoch": 6.81,
"learning_rate": 0.0002076046357726566,
"loss": 0.1504,
"step": 4850
},
{
"epoch": 6.82,
"learning_rate": 0.00020667092238962537,
"loss": 0.1444,
"step": 4860
},
{
"epoch": 6.84,
"learning_rate": 0.00020573783171394343,
"loss": 0.1377,
"step": 4870
},
{
"epoch": 6.85,
"learning_rate": 0.00020480537715559927,
"loss": 0.1479,
"step": 4880
},
{
"epoch": 6.86,
"learning_rate": 0.00020387357211543882,
"loss": 0.148,
"step": 4890
},
{
"epoch": 6.88,
"learning_rate": 0.00020294242998497404,
"loss": 0.1494,
"step": 4900
},
{
"epoch": 6.89,
"learning_rate": 0.00020201196414618936,
"loss": 0.1492,
"step": 4910
},
{
"epoch": 6.91,
"learning_rate": 0.0002010821879713498,
"loss": 0.141,
"step": 4920
},
{
"epoch": 6.92,
"learning_rate": 0.00020015311482280925,
"loss": 0.1546,
"step": 4930
},
{
"epoch": 6.93,
"learning_rate": 0.00019922475805281758,
"loss": 0.1451,
"step": 4940
},
{
"epoch": 6.95,
"learning_rate": 0.00019829713100332942,
"loss": 0.1454,
"step": 4950
},
{
"epoch": 6.96,
"learning_rate": 0.00019737024700581195,
"loss": 0.147,
"step": 4960
},
{
"epoch": 6.98,
"learning_rate": 0.0001964441193810538,
"loss": 0.1433,
"step": 4970
},
{
"epoch": 6.99,
"learning_rate": 0.00019551876143897298,
"loss": 0.1449,
"step": 4980
},
{
"epoch": 7.0,
"learning_rate": 0.00019459418647842632,
"loss": 0.1262,
"step": 4990
},
{
"epoch": 7.02,
"learning_rate": 0.0001936704077870176,
"loss": 0.1014,
"step": 5000
},
{
"epoch": 7.03,
"learning_rate": 0.0001927474386409072,
"loss": 0.1003,
"step": 5010
},
{
"epoch": 7.05,
"learning_rate": 0.00019182529230462106,
"loss": 0.0939,
"step": 5020
},
{
"epoch": 7.06,
"learning_rate": 0.0001909039820308598,
"loss": 0.0988,
"step": 5030
},
{
"epoch": 7.07,
"learning_rate": 0.00018998352106030882,
"loss": 0.0953,
"step": 5040
},
{
"epoch": 7.09,
"learning_rate": 0.0001890639226214474,
"loss": 0.0919,
"step": 5050
},
{
"epoch": 7.1,
"learning_rate": 0.00018814519993035913,
"loss": 0.0908,
"step": 5060
},
{
"epoch": 7.12,
"learning_rate": 0.0001872273661905415,
"loss": 0.0952,
"step": 5070
},
{
"epoch": 7.13,
"learning_rate": 0.00018631043459271657,
"loss": 0.0959,
"step": 5080
},
{
"epoch": 7.15,
"learning_rate": 0.00018539441831464092,
"loss": 0.0949,
"step": 5090
},
{
"epoch": 7.16,
"learning_rate": 0.00018447933052091698,
"loss": 0.0992,
"step": 5100
},
{
"epoch": 7.17,
"learning_rate": 0.0001835651843628028,
"loss": 0.0979,
"step": 5110
},
{
"epoch": 7.19,
"learning_rate": 0.00018265199297802425,
"loss": 0.0988,
"step": 5120
},
{
"epoch": 7.2,
"learning_rate": 0.00018173976949058512,
"loss": 0.098,
"step": 5130
},
{
"epoch": 7.22,
"learning_rate": 0.00018082852701057915,
"loss": 0.0995,
"step": 5140
},
{
"epoch": 7.23,
"learning_rate": 0.0001799182786340016,
"loss": 0.0993,
"step": 5150
},
{
"epoch": 7.24,
"learning_rate": 0.00017900903744256063,
"loss": 0.0919,
"step": 5160
},
{
"epoch": 7.26,
"learning_rate": 0.0001781008165034898,
"loss": 0.0939,
"step": 5170
},
{
"epoch": 7.27,
"learning_rate": 0.00017719362886935985,
"loss": 0.1004,
"step": 5180
},
{
"epoch": 7.29,
"learning_rate": 0.00017628748757789143,
"loss": 0.0939,
"step": 5190
},
{
"epoch": 7.3,
"learning_rate": 0.00017538240565176743,
"loss": 0.0975,
"step": 5200
},
{
"epoch": 7.31,
"learning_rate": 0.00017447839609844622,
"loss": 0.102,
"step": 5210
},
{
"epoch": 7.33,
"learning_rate": 0.00017357547190997416,
"loss": 0.0981,
"step": 5220
},
{
"epoch": 7.34,
"learning_rate": 0.00017267364606279954,
"loss": 0.0927,
"step": 5230
},
{
"epoch": 7.36,
"learning_rate": 0.00017177293151758553,
"loss": 0.094,
"step": 5240
},
{
"epoch": 7.37,
"learning_rate": 0.0001708733412190241,
"loss": 0.0926,
"step": 5250
},
{
"epoch": 7.38,
"learning_rate": 0.0001699748880956503,
"loss": 0.0967,
"step": 5260
},
{
"epoch": 7.4,
"learning_rate": 0.0001690775850596558,
"loss": 0.0939,
"step": 5270
},
{
"epoch": 7.41,
"learning_rate": 0.000168181445006704,
"loss": 0.1029,
"step": 5280
},
{
"epoch": 7.43,
"learning_rate": 0.00016728648081574423,
"loss": 0.0947,
"step": 5290
},
{
"epoch": 7.44,
"learning_rate": 0.00016639270534882691,
"loss": 0.0967,
"step": 5300
},
{
"epoch": 7.45,
"learning_rate": 0.00016550013145091852,
"loss": 0.0969,
"step": 5310
},
{
"epoch": 7.47,
"learning_rate": 0.00016460877194971718,
"loss": 0.0974,
"step": 5320
},
{
"epoch": 7.48,
"learning_rate": 0.00016371863965546825,
"loss": 0.0989,
"step": 5330
},
{
"epoch": 7.5,
"learning_rate": 0.00016282974736077995,
"loss": 0.098,
"step": 5340
},
{
"epoch": 7.51,
"learning_rate": 0.00016194210784044,
"loss": 0.1037,
"step": 5350
},
{
"epoch": 7.52,
"learning_rate": 0.00016105573385123166,
"loss": 0.1009,
"step": 5360
},
{
"epoch": 7.54,
"learning_rate": 0.00016017063813175068,
"loss": 0.1014,
"step": 5370
},
{
"epoch": 7.55,
"learning_rate": 0.0001592868334022216,
"loss": 0.1007,
"step": 5380
},
{
"epoch": 7.57,
"learning_rate": 0.0001584043323643161,
"loss": 0.0973,
"step": 5390
},
{
"epoch": 7.58,
"learning_rate": 0.00015752314770096893,
"loss": 0.0946,
"step": 5400
},
{
"epoch": 7.59,
"learning_rate": 0.00015664329207619714,
"loss": 0.0954,
"step": 5410
},
{
"epoch": 7.61,
"learning_rate": 0.00015576477813491706,
"loss": 0.1018,
"step": 5420
},
{
"epoch": 7.62,
"learning_rate": 0.000154887618502763,
"loss": 0.1034,
"step": 5430
},
{
"epoch": 7.64,
"learning_rate": 0.00015401182578590568,
"loss": 0.0986,
"step": 5440
},
{
"epoch": 7.65,
"learning_rate": 0.0001531374125708709,
"loss": 0.0949,
"step": 5450
},
{
"epoch": 7.66,
"learning_rate": 0.00015226439142435933,
"loss": 0.0978,
"step": 5460
},
{
"epoch": 7.68,
"learning_rate": 0.00015139277489306487,
"loss": 0.1013,
"step": 5470
},
{
"epoch": 7.69,
"learning_rate": 0.00015052257550349528,
"loss": 0.1013,
"step": 5480
},
{
"epoch": 7.71,
"learning_rate": 0.00014965380576179143,
"loss": 0.0935,
"step": 5490
},
{
"epoch": 7.72,
"learning_rate": 0.00014878647815354823,
"loss": 0.0978,
"step": 5500
},
{
"epoch": 7.73,
"learning_rate": 0.00014792060514363454,
"loss": 0.1031,
"step": 5510
},
{
"epoch": 7.75,
"learning_rate": 0.00014705619917601453,
"loss": 0.0963,
"step": 5520
},
{
"epoch": 7.76,
"learning_rate": 0.00014619327267356857,
"loss": 0.1045,
"step": 5530
},
{
"epoch": 7.78,
"learning_rate": 0.00014533183803791487,
"loss": 0.1034,
"step": 5540
},
{
"epoch": 7.79,
"learning_rate": 0.00014447190764923108,
"loss": 0.0966,
"step": 5550
},
{
"epoch": 7.8,
"learning_rate": 0.0001436992666453736,
"loss": 0.103,
"step": 5560
},
{
"epoch": 7.82,
"learning_rate": 0.00014284222835575245,
"loss": 0.1007,
"step": 5570
},
{
"epoch": 7.83,
"learning_rate": 0.0001419867300927284,
"loss": 0.0968,
"step": 5580
},
{
"epoch": 7.85,
"learning_rate": 0.00014113278415116414,
"loss": 0.0996,
"step": 5590
},
{
"epoch": 7.86,
"learning_rate": 0.00014028040280361295,
"loss": 0.1023,
"step": 5600
},
{
"epoch": 7.88,
"learning_rate": 0.00013942959830014228,
"loss": 0.0986,
"step": 5610
},
{
"epoch": 7.89,
"learning_rate": 0.0001385803828681581,
"loss": 0.0988,
"step": 5620
},
{
"epoch": 7.9,
"learning_rate": 0.00013773276871222872,
"loss": 0.1021,
"step": 5630
},
{
"epoch": 7.92,
"learning_rate": 0.00013688676801390986,
"loss": 0.1016,
"step": 5640
},
{
"epoch": 7.93,
"learning_rate": 0.00013604239293156878,
"loss": 0.0938,
"step": 5650
},
{
"epoch": 7.95,
"learning_rate": 0.0001351996556002106,
"loss": 0.1014,
"step": 5660
},
{
"epoch": 7.96,
"learning_rate": 0.0001343585681313032,
"loss": 0.1038,
"step": 5670
},
{
"epoch": 7.97,
"learning_rate": 0.00013351914261260306,
"loss": 0.1061,
"step": 5680
},
{
"epoch": 7.99,
"learning_rate": 0.00013268139110798215,
"loss": 0.1006,
"step": 5690
},
{
"epoch": 8.0,
"learning_rate": 0.00013184532565725416,
"loss": 0.0973,
"step": 5700
},
{
"epoch": 8.02,
"learning_rate": 0.00013101095827600147,
"loss": 0.0637,
"step": 5710
},
{
"epoch": 8.03,
"learning_rate": 0.00013017830095540223,
"loss": 0.0653,
"step": 5720
},
{
"epoch": 8.04,
"learning_rate": 0.00012934736566205902,
"loss": 0.069,
"step": 5730
},
{
"epoch": 8.06,
"learning_rate": 0.00012851816433782535,
"loss": 0.0664,
"step": 5740
},
{
"epoch": 8.07,
"learning_rate": 0.0001276907088996354,
"loss": 0.065,
"step": 5750
},
{
"epoch": 8.09,
"learning_rate": 0.000126865011239332,
"loss": 0.0648,
"step": 5760
},
{
"epoch": 8.1,
"learning_rate": 0.00012604108322349612,
"loss": 0.0661,
"step": 5770
},
{
"epoch": 8.11,
"learning_rate": 0.00012521893669327583,
"loss": 0.0661,
"step": 5780
},
{
"epoch": 8.13,
"learning_rate": 0.00012439858346421646,
"loss": 0.0652,
"step": 5790
},
{
"epoch": 8.14,
"learning_rate": 0.00012358003532609126,
"loss": 0.0698,
"step": 5800
},
{
"epoch": 8.16,
"learning_rate": 0.00012276330404273087,
"loss": 0.0604,
"step": 5810
},
{
"epoch": 8.17,
"learning_rate": 0.00012194840135185517,
"loss": 0.0644,
"step": 5820
},
{
"epoch": 8.18,
"learning_rate": 0.0001211353389649042,
"loss": 0.0645,
"step": 5830
},
{
"epoch": 8.2,
"learning_rate": 0.00012032412856687,
"loss": 0.0676,
"step": 5840
},
{
"epoch": 8.21,
"learning_rate": 0.0001195147818161284,
"loss": 0.0673,
"step": 5850
},
{
"epoch": 8.23,
"learning_rate": 0.00011870731034427185,
"loss": 0.0646,
"step": 5860
},
{
"epoch": 8.24,
"learning_rate": 0.00011790172575594205,
"loss": 0.0658,
"step": 5870
},
{
"epoch": 8.25,
"learning_rate": 0.00011709803962866328,
"loss": 0.0662,
"step": 5880
},
{
"epoch": 8.27,
"learning_rate": 0.00011629626351267561,
"loss": 0.0682,
"step": 5890
},
{
"epoch": 8.28,
"learning_rate": 0.00011549640893076957,
"loss": 0.0641,
"step": 5900
},
{
"epoch": 8.3,
"learning_rate": 0.0001146984873781202,
"loss": 0.0676,
"step": 5910
},
{
"epoch": 8.31,
"learning_rate": 0.00011390251032212151,
"loss": 0.0676,
"step": 5920
},
{
"epoch": 8.32,
"learning_rate": 0.00011310848920222238,
"loss": 0.0633,
"step": 5930
},
{
"epoch": 8.34,
"learning_rate": 0.00011231643542976166,
"loss": 0.0659,
"step": 5940
},
{
"epoch": 8.35,
"learning_rate": 0.0001115263603878044,
"loss": 0.0674,
"step": 5950
},
{
"epoch": 8.37,
"learning_rate": 0.00011073827543097779,
"loss": 0.0641,
"step": 5960
},
{
"epoch": 8.38,
"learning_rate": 0.00010995219188530903,
"loss": 0.0626,
"step": 5970
},
{
"epoch": 8.39,
"learning_rate": 0.00010916812104806118,
"loss": 0.0668,
"step": 5980
},
{
"epoch": 8.41,
"learning_rate": 0.0001083860741875719,
"loss": 0.064,
"step": 5990
},
{
"epoch": 8.42,
"learning_rate": 0.00010760606254309113,
"loss": 0.0702,
"step": 6000
},
{
"epoch": 8.44,
"learning_rate": 0.00010682809732461923,
"loss": 0.0689,
"step": 6010
},
{
"epoch": 8.45,
"learning_rate": 0.00010605218971274641,
"loss": 0.0616,
"step": 6020
},
{
"epoch": 8.46,
"learning_rate": 0.00010527835085849183,
"loss": 0.0652,
"step": 6030
},
{
"epoch": 8.48,
"learning_rate": 0.00010450659188314335,
"loss": 0.0658,
"step": 6040
},
{
"epoch": 8.49,
"learning_rate": 0.00010373692387809744,
"loss": 0.0606,
"step": 6050
},
{
"epoch": 8.51,
"learning_rate": 0.00010296935790470024,
"loss": 0.0638,
"step": 6060
},
{
"epoch": 8.52,
"learning_rate": 0.00010220390499408841,
"loss": 0.0679,
"step": 6070
},
{
"epoch": 8.53,
"learning_rate": 0.00010144057614703048,
"loss": 0.0647,
"step": 6080
},
{
"epoch": 8.55,
"learning_rate": 0.00010067938233376867,
"loss": 0.0663,
"step": 6090
},
{
"epoch": 8.56,
"learning_rate": 9.992033449386165e-05,
"loss": 0.0639,
"step": 6100
},
{
"epoch": 8.58,
"learning_rate": 9.916344353602702e-05,
"loss": 0.064,
"step": 6110
},
{
"epoch": 8.59,
"learning_rate": 9.840872033798431e-05,
"loss": 0.0729,
"step": 6120
},
{
"epoch": 8.61,
"learning_rate": 9.765617574629923e-05,
"loss": 0.068,
"step": 6130
},
{
"epoch": 8.62,
"learning_rate": 9.690582057622735e-05,
"loss": 0.0701,
"step": 6140
},
{
"epoch": 8.63,
"learning_rate": 9.615766561155884e-05,
"loss": 0.0678,
"step": 6150
},
{
"epoch": 8.65,
"learning_rate": 9.541172160446323e-05,
"loss": 0.0692,
"step": 6160
},
{
"epoch": 8.66,
"learning_rate": 9.466799927533536e-05,
"loss": 0.0693,
"step": 6170
},
{
"epoch": 8.68,
"learning_rate": 9.392650931264097e-05,
"loss": 0.0662,
"step": 6180
},
{
"epoch": 8.69,
"learning_rate": 9.318726237276315e-05,
"loss": 0.0676,
"step": 6190
},
{
"epoch": 8.7,
"learning_rate": 9.245026907984894e-05,
"loss": 0.0699,
"step": 6200
},
{
"epoch": 8.72,
"learning_rate": 9.171554002565755e-05,
"loss": 0.0669,
"step": 6210
},
{
"epoch": 8.73,
"learning_rate": 9.098308576940692e-05,
"loss": 0.0658,
"step": 6220
},
{
"epoch": 8.75,
"learning_rate": 9.025291683762258e-05,
"loss": 0.0696,
"step": 6230
},
{
"epoch": 8.76,
"learning_rate": 8.952504372398679e-05,
"loss": 0.0692,
"step": 6240
},
{
"epoch": 8.77,
"learning_rate": 8.879947688918674e-05,
"loss": 0.0664,
"step": 6250
},
{
"epoch": 8.79,
"learning_rate": 8.807622676076507e-05,
"loss": 0.0689,
"step": 6260
},
{
"epoch": 8.8,
"learning_rate": 8.735530373296962e-05,
"loss": 0.0638,
"step": 6270
},
{
"epoch": 8.82,
"learning_rate": 8.663671816660415e-05,
"loss": 0.0669,
"step": 6280
},
{
"epoch": 8.83,
"learning_rate": 8.592048038887918e-05,
"loss": 0.0644,
"step": 6290
},
{
"epoch": 8.84,
"learning_rate": 8.520660069326405e-05,
"loss": 0.0649,
"step": 6300
},
{
"epoch": 8.86,
"learning_rate": 8.449508933933867e-05,
"loss": 0.0637,
"step": 6310
},
{
"epoch": 8.87,
"learning_rate": 8.378595655264615e-05,
"loss": 0.0657,
"step": 6320
},
{
"epoch": 8.89,
"learning_rate": 8.307921252454565e-05,
"loss": 0.0706,
"step": 6330
},
{
"epoch": 8.9,
"learning_rate": 8.23748674120663e-05,
"loss": 0.0672,
"step": 6340
},
{
"epoch": 8.91,
"learning_rate": 8.167293133776102e-05,
"loss": 0.0664,
"step": 6350
},
{
"epoch": 8.93,
"learning_rate": 8.097341438956085e-05,
"loss": 0.0653,
"step": 6360
},
{
"epoch": 8.94,
"learning_rate": 8.027632662063034e-05,
"loss": 0.0646,
"step": 6370
},
{
"epoch": 8.96,
"learning_rate": 7.958167804922284e-05,
"loss": 0.0651,
"step": 6380
},
{
"epoch": 8.97,
"learning_rate": 7.888947865853666e-05,
"loss": 0.0676,
"step": 6390
},
{
"epoch": 8.98,
"learning_rate": 7.819973839657126e-05,
"loss": 0.0627,
"step": 6400
},
{
"epoch": 9.0,
"learning_rate": 7.751246717598479e-05,
"loss": 0.0664,
"step": 6410
},
{
"epoch": 9.01,
"learning_rate": 7.682767487395125e-05,
"loss": 0.0501,
"step": 6420
},
{
"epoch": 9.03,
"learning_rate": 7.614537133201881e-05,
"loss": 0.0456,
"step": 6430
},
{
"epoch": 9.04,
"learning_rate": 7.546556635596791e-05,
"loss": 0.0417,
"step": 6440
},
{
"epoch": 9.05,
"learning_rate": 7.478826971567096e-05,
"loss": 0.0486,
"step": 6450
},
{
"epoch": 9.07,
"learning_rate": 7.411349114495153e-05,
"loss": 0.0436,
"step": 6460
},
{
"epoch": 9.08,
"learning_rate": 7.344124034144434e-05,
"loss": 0.0444,
"step": 6470
},
{
"epoch": 9.1,
"learning_rate": 7.277152696645653e-05,
"loss": 0.0469,
"step": 6480
},
{
"epoch": 9.11,
"learning_rate": 7.210436064482793e-05,
"loss": 0.0469,
"step": 6490
},
{
"epoch": 9.12,
"learning_rate": 7.143975096479346e-05,
"loss": 0.0486,
"step": 6500
},
{
"epoch": 9.14,
"learning_rate": 7.077770747784502e-05,
"loss": 0.0434,
"step": 6510
},
{
"epoch": 9.15,
"learning_rate": 7.01182396985942e-05,
"loss": 0.0448,
"step": 6520
},
{
"epoch": 9.17,
"learning_rate": 6.946135710463555e-05,
"loss": 0.0462,
"step": 6530
},
{
"epoch": 9.18,
"learning_rate": 6.880706913641055e-05,
"loss": 0.0454,
"step": 6540
},
{
"epoch": 9.19,
"learning_rate": 6.815538519707182e-05,
"loss": 0.045,
"step": 6550
},
{
"epoch": 9.21,
"learning_rate": 6.750631465234774e-05,
"loss": 0.0489,
"step": 6560
},
{
"epoch": 9.22,
"learning_rate": 6.685986683040829e-05,
"loss": 0.0462,
"step": 6570
},
{
"epoch": 9.24,
"learning_rate": 6.621605102173072e-05,
"loss": 0.0486,
"step": 6580
},
{
"epoch": 9.25,
"learning_rate": 6.557487647896621e-05,
"loss": 0.0482,
"step": 6590
},
{
"epoch": 9.26,
"learning_rate": 6.493635241680646e-05,
"loss": 0.0429,
"step": 6600
},
{
"epoch": 9.28,
"learning_rate": 6.430048801185181e-05,
"loss": 0.0451,
"step": 6610
},
{
"epoch": 9.29,
"learning_rate": 6.366729240247913e-05,
"loss": 0.0469,
"step": 6620
},
{
"epoch": 9.31,
"learning_rate": 6.303677468871044e-05,
"loss": 0.0489,
"step": 6630
},
{
"epoch": 9.32,
"learning_rate": 6.2408943932082e-05,
"loss": 0.0449,
"step": 6640
},
{
"epoch": 9.33,
"learning_rate": 6.178380915551462e-05,
"loss": 0.0447,
"step": 6650
},
{
"epoch": 9.35,
"learning_rate": 6.116137934318328e-05,
"loss": 0.0458,
"step": 6660
},
{
"epoch": 9.36,
"learning_rate": 6.054166344038836e-05,
"loss": 0.0453,
"step": 6670
},
{
"epoch": 9.38,
"learning_rate": 5.992467035342727e-05,
"loss": 0.0462,
"step": 6680
},
{
"epoch": 9.39,
"learning_rate": 5.931040894946613e-05,
"loss": 0.0436,
"step": 6690
},
{
"epoch": 9.41,
"learning_rate": 5.8698888056412545e-05,
"loss": 0.0474,
"step": 6700
},
{
"epoch": 9.42,
"learning_rate": 5.809011646278836e-05,
"loss": 0.0479,
"step": 6710
},
{
"epoch": 9.43,
"learning_rate": 5.748410291760414e-05,
"loss": 0.049,
"step": 6720
},
{
"epoch": 9.45,
"learning_rate": 5.6880856130232446e-05,
"loss": 0.0434,
"step": 6730
},
{
"epoch": 9.46,
"learning_rate": 5.628038477028344e-05,
"loss": 0.0451,
"step": 6740
},
{
"epoch": 9.48,
"learning_rate": 5.5682697467479896e-05,
"loss": 0.0457,
"step": 6750
},
{
"epoch": 9.49,
"learning_rate": 5.5087802811533387e-05,
"loss": 0.0456,
"step": 6760
},
{
"epoch": 9.5,
"learning_rate": 5.449570935202053e-05,
"loss": 0.0436,
"step": 6770
},
{
"epoch": 9.52,
"learning_rate": 5.390642559826048e-05,
"loss": 0.0446,
"step": 6780
},
{
"epoch": 9.53,
"learning_rate": 5.3319960019192596e-05,
"loss": 0.0495,
"step": 6790
},
{
"epoch": 9.55,
"learning_rate": 5.2736321043254235e-05,
"loss": 0.0462,
"step": 6800
},
{
"epoch": 9.56,
"learning_rate": 5.215551705826038e-05,
"loss": 0.0424,
"step": 6810
},
{
"epoch": 9.57,
"learning_rate": 5.157755641128248e-05,
"loss": 0.0449,
"step": 6820
},
{
"epoch": 9.59,
"learning_rate": 5.100244740852894e-05,
"loss": 0.041,
"step": 6830
},
{
"epoch": 9.6,
"learning_rate": 5.0430198315225187e-05,
"loss": 0.0464,
"step": 6840
},
{
"epoch": 9.62,
"learning_rate": 4.9860817355495556e-05,
"loss": 0.0452,
"step": 6850
},
{
"epoch": 9.63,
"learning_rate": 4.9294312712244574e-05,
"loss": 0.0443,
"step": 6860
},
{
"epoch": 9.64,
"learning_rate": 4.8730692527039765e-05,
"loss": 0.0445,
"step": 6870
},
{
"epoch": 9.66,
"learning_rate": 4.816996489999409e-05,
"loss": 0.0429,
"step": 6880
},
{
"epoch": 9.67,
"learning_rate": 4.761213788965016e-05,
"loss": 0.0452,
"step": 6890
},
{
"epoch": 9.69,
"learning_rate": 4.7057219512864124e-05,
"loss": 0.0451,
"step": 6900
},
{
"epoch": 9.7,
"learning_rate": 4.650521774469024e-05,
"loss": 0.0442,
"step": 6910
},
{
"epoch": 9.71,
"learning_rate": 4.595614051826671e-05,
"loss": 0.0432,
"step": 6920
},
{
"epoch": 9.73,
"learning_rate": 4.540999572470142e-05,
"loss": 0.0476,
"step": 6930
},
{
"epoch": 9.74,
"learning_rate": 4.486679121295853e-05,
"loss": 0.0462,
"step": 6940
},
{
"epoch": 9.76,
"learning_rate": 4.432653478974555e-05,
"loss": 0.0461,
"step": 6950
},
{
"epoch": 9.77,
"learning_rate": 4.378923421940165e-05,
"loss": 0.0473,
"step": 6960
},
{
"epoch": 9.78,
"learning_rate": 4.3254897223785336e-05,
"loss": 0.0473,
"step": 6970
},
{
"epoch": 9.8,
"learning_rate": 4.2723531482164096e-05,
"loss": 0.0472,
"step": 6980
},
{
"epoch": 9.81,
"learning_rate": 4.21951446311038e-05,
"loss": 0.0477,
"step": 6990
},
{
"epoch": 9.83,
"learning_rate": 4.1669744264358765e-05,
"loss": 0.045,
"step": 7000
},
{
"epoch": 9.84,
"learning_rate": 4.114733793276299e-05,
"loss": 0.0447,
"step": 7010
},
{
"epoch": 9.85,
"learning_rate": 4.062793314412139e-05,
"loss": 0.0431,
"step": 7020
},
{
"epoch": 9.87,
"learning_rate": 4.011153736310202e-05,
"loss": 0.0462,
"step": 7030
},
{
"epoch": 9.88,
"learning_rate": 3.959815801112859e-05,
"loss": 0.0466,
"step": 7040
},
{
"epoch": 9.9,
"learning_rate": 3.908780246627411e-05,
"loss": 0.0437,
"step": 7050
},
{
"epoch": 9.91,
"learning_rate": 3.8580478063154594e-05,
"loss": 0.0442,
"step": 7060
},
{
"epoch": 9.92,
"learning_rate": 3.8076192092823926e-05,
"loss": 0.0437,
"step": 7070
},
{
"epoch": 9.94,
"learning_rate": 3.757495180266865e-05,
"loss": 0.0477,
"step": 7080
},
{
"epoch": 9.95,
"learning_rate": 3.7076764396304224e-05,
"loss": 0.0489,
"step": 7090
},
{
"epoch": 9.97,
"learning_rate": 3.658163703347142e-05,
"loss": 0.0483,
"step": 7100
},
{
"epoch": 9.98,
"learning_rate": 3.6089576829933136e-05,
"loss": 0.0454,
"step": 7110
},
{
"epoch": 9.99,
"learning_rate": 3.5600590857372494e-05,
"loss": 0.0468,
"step": 7120
},
{
"epoch": 10.01,
"learning_rate": 3.511468614329105e-05,
"loss": 0.0384,
"step": 7130
},
{
"epoch": 10.02,
"learning_rate": 3.463186967090776e-05,
"loss": 0.036,
"step": 7140
},
{
"epoch": 10.04,
"learning_rate": 3.4152148379058587e-05,
"loss": 0.0366,
"step": 7150
},
{
"epoch": 10.05,
"learning_rate": 3.3675529162097094e-05,
"loss": 0.0336,
"step": 7160
},
{
"epoch": 10.06,
"learning_rate": 3.320201886979485e-05,
"loss": 0.0324,
"step": 7170
},
{
"epoch": 10.08,
"learning_rate": 3.273162430724347e-05,
"loss": 0.0336,
"step": 7180
},
{
"epoch": 10.09,
"learning_rate": 3.226435223475643e-05,
"loss": 0.034,
"step": 7190
},
{
"epoch": 10.11,
"learning_rate": 3.180020936777225e-05,
"loss": 0.0352,
"step": 7200
},
{
"epoch": 10.12,
"learning_rate": 3.133920237675777e-05,
"loss": 0.0345,
"step": 7210
},
{
"epoch": 10.14,
"learning_rate": 3.088133788711214e-05,
"loss": 0.0323,
"step": 7220
},
{
"epoch": 10.15,
"learning_rate": 3.042662247907224e-05,
"loss": 0.0359,
"step": 7230
},
{
"epoch": 10.16,
"learning_rate": 2.9975062687617182e-05,
"loss": 0.0361,
"step": 7240
},
{
"epoch": 10.18,
"learning_rate": 2.9526665002375162e-05,
"loss": 0.0369,
"step": 7250
},
{
"epoch": 10.19,
"learning_rate": 2.9081435867529872e-05,
"loss": 0.0333,
"step": 7260
},
{
"epoch": 10.21,
"learning_rate": 2.8639381681727915e-05,
"loss": 0.0347,
"step": 7270
},
{
"epoch": 10.22,
"learning_rate": 2.8200508797986745e-05,
"loss": 0.0331,
"step": 7280
},
{
"epoch": 10.23,
"learning_rate": 2.77648235236036e-05,
"loss": 0.0364,
"step": 7290
},
{
"epoch": 10.25,
"learning_rate": 2.733233212006478e-05,
"loss": 0.033,
"step": 7300
},
{
"epoch": 10.26,
"learning_rate": 2.6903040802955415e-05,
"loss": 0.034,
"step": 7310
},
{
"epoch": 10.28,
"learning_rate": 2.6476955741870508e-05,
"loss": 0.0353,
"step": 7320
},
{
"epoch": 10.29,
"learning_rate": 2.6054083060326054e-05,
"loss": 0.033,
"step": 7330
},
{
"epoch": 10.3,
"learning_rate": 2.5634428835671074e-05,
"loss": 0.0334,
"step": 7340
},
{
"epoch": 10.32,
"learning_rate": 2.521799909900016e-05,
"loss": 0.0373,
"step": 7350
},
{
"epoch": 10.33,
"learning_rate": 2.480479983506706e-05,
"loss": 0.0346,
"step": 7360
},
{
"epoch": 10.35,
"learning_rate": 2.4394836982198522e-05,
"loss": 0.0317,
"step": 7370
},
{
"epoch": 10.36,
"learning_rate": 2.3988116432208884e-05,
"loss": 0.0358,
"step": 7380
},
{
"epoch": 10.37,
"learning_rate": 2.358464403031538e-05,
"loss": 0.0331,
"step": 7390
},
{
"epoch": 10.39,
"learning_rate": 2.3184425575054486e-05,
"loss": 0.0329,
"step": 7400
},
{
"epoch": 10.4,
"learning_rate": 2.2787466818198098e-05,
"loss": 0.0352,
"step": 7410
},
{
"epoch": 10.42,
"learning_rate": 2.239377346467106e-05,
"loss": 0.0306,
"step": 7420
},
{
"epoch": 10.43,
"learning_rate": 2.2003351172469406e-05,
"loss": 0.0336,
"step": 7430
},
{
"epoch": 10.44,
"learning_rate": 2.1616205552578676e-05,
"loss": 0.0345,
"step": 7440
},
{
"epoch": 10.46,
"learning_rate": 2.1232342168893608e-05,
"loss": 0.0357,
"step": 7450
},
{
"epoch": 10.47,
"learning_rate": 2.085176653813775e-05,
"loss": 0.0325,
"step": 7460
},
{
"epoch": 10.49,
"learning_rate": 2.047448412978481e-05,
"loss": 0.0321,
"step": 7470
},
{
"epoch": 10.5,
"learning_rate": 2.010050036597935e-05,
"loss": 0.0349,
"step": 7480
},
{
"epoch": 10.51,
"learning_rate": 1.9729820621459393e-05,
"loss": 0.0351,
"step": 7490
},
{
"epoch": 10.53,
"learning_rate": 1.936245022347888e-05,
"loss": 0.0347,
"step": 7500
},
{
"epoch": 10.54,
"learning_rate": 1.899839445173135e-05,
"loss": 0.0337,
"step": 7510
},
{
"epoch": 10.56,
"learning_rate": 1.8637658538273678e-05,
"loss": 0.0377,
"step": 7520
},
{
"epoch": 10.57,
"learning_rate": 1.8280247667451344e-05,
"loss": 0.034,
"step": 7530
},
{
"epoch": 10.58,
"learning_rate": 1.7926166975823692e-05,
"loss": 0.0362,
"step": 7540
},
{
"epoch": 10.6,
"learning_rate": 1.7575421552089965e-05,
"loss": 0.0352,
"step": 7550
},
{
"epoch": 10.61,
"learning_rate": 1.7228016437016463e-05,
"loss": 0.038,
"step": 7560
},
{
"epoch": 10.63,
"learning_rate": 1.6883956623363976e-05,
"loss": 0.0377,
"step": 7570
},
{
"epoch": 10.64,
"learning_rate": 1.654324705581603e-05,
"loss": 0.0335,
"step": 7580
},
{
"epoch": 10.65,
"learning_rate": 1.620589263090766e-05,
"loss": 0.0351,
"step": 7590
},
{
"epoch": 10.67,
"learning_rate": 1.587189819695542e-05,
"loss": 0.0364,
"step": 7600
},
{
"epoch": 10.68,
"learning_rate": 1.5541268553987326e-05,
"loss": 0.0359,
"step": 7610
},
{
"epoch": 10.7,
"learning_rate": 1.5214008453674127e-05,
"loss": 0.0316,
"step": 7620
},
{
"epoch": 10.71,
"learning_rate": 1.4890122599260786e-05,
"loss": 0.0348,
"step": 7630
},
{
"epoch": 10.72,
"learning_rate": 1.456961564549919e-05,
"loss": 0.0359,
"step": 7640
},
{
"epoch": 10.74,
"learning_rate": 1.4252492198580963e-05,
"loss": 0.0396,
"step": 7650
},
{
"epoch": 10.75,
"learning_rate": 1.3938756816071346e-05,
"loss": 0.0341,
"step": 7660
},
{
"epoch": 10.77,
"learning_rate": 1.3628414006843948e-05,
"loss": 0.0328,
"step": 7670
},
{
"epoch": 10.78,
"learning_rate": 1.3321468231015487e-05,
"loss": 0.0358,
"step": 7680
},
{
"epoch": 10.79,
"learning_rate": 1.30179238998821e-05,
"loss": 0.0326,
"step": 7690
},
{
"epoch": 10.81,
"learning_rate": 1.2717785375855662e-05,
"loss": 0.0332,
"step": 7700
},
{
"epoch": 10.82,
"learning_rate": 1.2421056972401396e-05,
"loss": 0.0349,
"step": 7710
},
{
"epoch": 10.84,
"learning_rate": 1.2127742953975506e-05,
"loss": 0.0345,
"step": 7720
},
{
"epoch": 10.85,
"learning_rate": 1.1837847535964203e-05,
"loss": 0.0342,
"step": 7730
},
{
"epoch": 10.87,
"learning_rate": 1.1551374884623017e-05,
"loss": 0.0351,
"step": 7740
},
{
"epoch": 10.88,
"learning_rate": 1.1268329117016807e-05,
"loss": 0.0326,
"step": 7750
},
{
"epoch": 10.89,
"learning_rate": 1.0988714300960739e-05,
"loss": 0.0346,
"step": 7760
},
{
"epoch": 10.91,
"learning_rate": 1.071253445496187e-05,
"loss": 0.0368,
"step": 7770
},
{
"epoch": 10.92,
"learning_rate": 1.0439793548161186e-05,
"loss": 0.0347,
"step": 7780
},
{
"epoch": 10.94,
"learning_rate": 1.0170495500276739e-05,
"loss": 0.0356,
"step": 7790
},
{
"epoch": 10.95,
"learning_rate": 9.904644181547211e-06,
"loss": 0.0354,
"step": 7800
},
{
"epoch": 10.96,
"learning_rate": 9.642243412676415e-06,
"loss": 0.0335,
"step": 7810
},
{
"epoch": 10.98,
"learning_rate": 9.38329696477827e-06,
"loss": 0.0378,
"step": 7820
},
{
"epoch": 10.99,
"learning_rate": 9.127808559322548e-06,
"loss": 0.0312,
"step": 7830
},
{
"epoch": 11.01,
"learning_rate": 8.875781868081662e-06,
"loss": 0.0334,
"step": 7840
},
{
"epoch": 11.02,
"learning_rate": 8.62722051307757e-06,
"loss": 0.0294,
"step": 7850
},
{
"epoch": 11.03,
"learning_rate": 8.382128066529937e-06,
"loss": 0.0322,
"step": 7860
},
{
"epoch": 11.05,
"learning_rate": 8.140508050804741e-06,
"loss": 0.0297,
"step": 7870
},
{
"epoch": 11.06,
"learning_rate": 7.90236393836355e-06,
"loss": 0.0327,
"step": 7880
},
{
"epoch": 11.08,
"learning_rate": 7.667699151713864e-06,
"loss": 0.029,
"step": 7890
},
{
"epoch": 11.09,
"learning_rate": 7.436517063359571e-06,
"loss": 0.0313,
"step": 7900
},
{
"epoch": 11.1,
"learning_rate": 7.208820995752874e-06,
"loss": 0.0319,
"step": 7910
},
{
"epoch": 11.12,
"learning_rate": 6.984614221246188e-06,
"loss": 0.0303,
"step": 7920
},
{
"epoch": 11.13,
"learning_rate": 6.763899962045433e-06,
"loss": 0.0319,
"step": 7930
},
{
"epoch": 11.15,
"learning_rate": 6.546681390163317e-06,
"loss": 0.0295,
"step": 7940
},
{
"epoch": 11.16,
"learning_rate": 6.3329616273742895e-06,
"loss": 0.0307,
"step": 7950
},
{
"epoch": 11.17,
"learning_rate": 6.12274374516919e-06,
"loss": 0.029,
"step": 7960
},
{
"epoch": 11.19,
"learning_rate": 5.916030764711283e-06,
"loss": 0.0318,
"step": 7970
},
{
"epoch": 11.2,
"learning_rate": 5.712825656793042e-06,
"loss": 0.031,
"step": 7980
},
{
"epoch": 11.22,
"learning_rate": 5.513131341793015e-06,
"loss": 0.0288,
"step": 7990
},
{
"epoch": 11.23,
"learning_rate": 5.316950689634281e-06,
"loss": 0.0309,
"step": 8000
},
{
"epoch": 11.24,
"learning_rate": 5.124286519742949e-06,
"loss": 0.032,
"step": 8010
},
{
"epoch": 11.26,
"learning_rate": 4.935141601007831e-06,
"loss": 0.0295,
"step": 8020
},
{
"epoch": 11.27,
"learning_rate": 4.749518651740364e-06,
"loss": 0.0308,
"step": 8030
},
{
"epoch": 11.29,
"learning_rate": 4.567420339635808e-06,
"loss": 0.0299,
"step": 8040
},
{
"epoch": 11.3,
"learning_rate": 4.3888492817348576e-06,
"loss": 0.0308,
"step": 8050
},
{
"epoch": 11.31,
"learning_rate": 4.213808044385925e-06,
"loss": 0.0311,
"step": 8060
},
{
"epoch": 11.33,
"learning_rate": 4.042299143208306e-06,
"loss": 0.0338,
"step": 8070
},
{
"epoch": 11.34,
"learning_rate": 3.874325043056071e-06,
"loss": 0.0304,
"step": 8080
},
{
"epoch": 11.36,
"learning_rate": 3.7098881579826492e-06,
"loss": 0.0292,
"step": 8090
},
{
"epoch": 11.37,
"learning_rate": 3.5489908512060244e-06,
"loss": 0.0297,
"step": 8100
},
{
"epoch": 11.38,
"learning_rate": 3.391635435074869e-06,
"loss": 0.0322,
"step": 8110
},
{
"epoch": 11.4,
"learning_rate": 3.237824171035325e-06,
"loss": 0.0309,
"step": 8120
},
{
"epoch": 11.41,
"learning_rate": 3.0875592695984443e-06,
"loss": 0.0316,
"step": 8130
},
{
"epoch": 11.43,
"learning_rate": 2.9408428903083816e-06,
"loss": 0.0278,
"step": 8140
},
{
"epoch": 11.44,
"learning_rate": 2.797677141711502e-06,
"loss": 0.0323,
"step": 8150
},
{
"epoch": 11.45,
"learning_rate": 2.6580640813259616e-06,
"loss": 0.0276,
"step": 8160
},
{
"epoch": 11.47,
"learning_rate": 2.5220057156121747e-06,
"loss": 0.03,
"step": 8170
},
{
"epoch": 11.48,
"learning_rate": 2.3895039999439483e-06,
"loss": 0.0281,
"step": 8180
},
{
"epoch": 11.5,
"learning_rate": 2.260560838580422e-06,
"loss": 0.0267,
"step": 8190
},
{
"epoch": 11.51,
"learning_rate": 2.1351780846387e-06,
"loss": 0.029,
"step": 8200
},
{
"epoch": 11.52,
"learning_rate": 2.013357540067179e-06,
"loss": 0.0331,
"step": 8210
},
{
"epoch": 11.54,
"learning_rate": 1.8951009556197052e-06,
"loss": 0.0293,
"step": 8220
},
{
"epoch": 11.55,
"learning_rate": 1.7804100308303484e-06,
"loss": 0.0296,
"step": 8230
},
{
"epoch": 11.57,
"learning_rate": 1.6692864139890018e-06,
"loss": 0.0282,
"step": 8240
},
{
"epoch": 11.58,
"learning_rate": 1.5617317021177912e-06,
"loss": 0.028,
"step": 8250
},
{
"epoch": 11.6,
"learning_rate": 1.4577474409479264e-06,
"loss": 0.0333,
"step": 8260
},
{
"epoch": 11.61,
"learning_rate": 1.3573351248976352e-06,
"loss": 0.0305,
"step": 8270
},
{
"epoch": 11.62,
"learning_rate": 1.2604961970506813e-06,
"loss": 0.0288,
"step": 8280
},
{
"epoch": 11.64,
"learning_rate": 1.1672320491355747e-06,
"loss": 0.0296,
"step": 8290
},
{
"epoch": 11.65,
"learning_rate": 1.0775440215055054e-06,
"loss": 0.0306,
"step": 8300
},
{
"epoch": 11.67,
"learning_rate": 9.914334031193017e-07,
"loss": 0.0274,
"step": 8310
},
{
"epoch": 11.68,
"learning_rate": 9.089014315226407e-07,
"loss": 0.0309,
"step": 8320
},
{
"epoch": 11.69,
"learning_rate": 8.299492928304786e-07,
"loss": 0.0305,
"step": 8330
},
{
"epoch": 11.71,
"learning_rate": 7.545781217098424e-07,
"loss": 0.0278,
"step": 8340
},
{
"epoch": 11.72,
"learning_rate": 6.827890013636484e-07,
"loss": 0.0261,
"step": 8350
},
{
"epoch": 11.74,
"learning_rate": 6.14582963515048e-07,
"loss": 0.0285,
"step": 8360
},
{
"epoch": 11.75,
"learning_rate": 5.499609883926337e-07,
"loss": 0.0292,
"step": 8370
},
{
"epoch": 11.76,
"learning_rate": 4.889240047163401e-07,
"loss": 0.0278,
"step": 8380
},
{
"epoch": 11.78,
"learning_rate": 4.3147288968417576e-07,
"loss": 0.0283,
"step": 8390
},
{
"epoch": 11.79,
"learning_rate": 3.776084689594561e-07,
"loss": 0.0306,
"step": 8400
},
{
"epoch": 11.81,
"learning_rate": 3.273315166590629e-07,
"loss": 0.0299,
"step": 8410
},
{
"epoch": 11.82,
"learning_rate": 2.806427553423141e-07,
"loss": 0.0307,
"step": 8420
},
{
"epoch": 11.83,
"learning_rate": 2.3754285600049997e-07,
"loss": 0.0304,
"step": 8430
},
{
"epoch": 11.85,
"learning_rate": 1.9803243804733528e-07,
"loss": 0.0295,
"step": 8440
},
{
"epoch": 11.86,
"learning_rate": 1.6211206930996647e-07,
"loss": 0.0323,
"step": 8450
},
{
"epoch": 11.88,
"learning_rate": 1.2978226602092246e-07,
"loss": 0.0334,
"step": 8460
},
{
"epoch": 11.89,
"learning_rate": 1.0104349281059299e-07,
"loss": 0.0313,
"step": 8470
},
{
"epoch": 11.9,
"learning_rate": 7.589616270053944e-08,
"loss": 0.0312,
"step": 8480
},
{
"epoch": 11.92,
"learning_rate": 5.434063709766624e-08,
"loss": 0.0309,
"step": 8490
},
{
"epoch": 11.93,
"learning_rate": 3.637722578900271e-08,
"loss": 0.0295,
"step": 8500
},
{
"epoch": 11.95,
"learning_rate": 2.2006186937095772e-08,
"loss": 0.0313,
"step": 8510
},
{
"epoch": 11.96,
"learning_rate": 1.1227727076568162e-08,
"loss": 0.0304,
"step": 8520
},
{
"epoch": 11.97,
"learning_rate": 4.042001110871052e-09,
"loss": 0.0312,
"step": 8530
},
{
"epoch": 11.99,
"learning_rate": 4.491123102856598e-10,
"loss": 0.0324,
"step": 8540
},
{
"epoch": 11.99,
"step": 8544,
"total_flos": 5.292842784612208e+19,
"train_loss": 0.23587711789551075,
"train_runtime": 325306.0241,
"train_samples_per_second": 3.364,
"train_steps_per_second": 0.026
}
],
"max_steps": 8544,
"num_train_epochs": 12,
"total_flos": 5.292842784612208e+19,
"trial_name": null,
"trial_params": null
}