trained-age / trainer_state.json
crangana's picture
End of training
57a7089
{
"best_metric": 1.1137409210205078,
"best_model_checkpoint": "./trained-age/checkpoint-5000",
"epoch": 1.1066027296200664,
"eval_steps": 1000,
"global_step": 6000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.000199907783105865,
"loss": 2.1543,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 0.00019981556621172998,
"loss": 2.0322,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 0.000199723349317595,
"loss": 1.9709,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 0.00019963113242345997,
"loss": 1.9224,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 0.00019953891552932499,
"loss": 1.9126,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 0.00019944669863518997,
"loss": 1.9034,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 0.00019935448174105498,
"loss": 1.8643,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 0.00019926226484691997,
"loss": 1.7807,
"step": 80
},
{
"epoch": 0.02,
"learning_rate": 0.00019917004795278495,
"loss": 1.7977,
"step": 90
},
{
"epoch": 0.02,
"learning_rate": 0.00019907783105864993,
"loss": 1.9388,
"step": 100
},
{
"epoch": 0.02,
"learning_rate": 0.00019898561416451495,
"loss": 1.9642,
"step": 110
},
{
"epoch": 0.02,
"learning_rate": 0.00019889339727037993,
"loss": 1.9164,
"step": 120
},
{
"epoch": 0.02,
"learning_rate": 0.00019880118037624494,
"loss": 1.8912,
"step": 130
},
{
"epoch": 0.03,
"learning_rate": 0.00019870896348210993,
"loss": 1.7802,
"step": 140
},
{
"epoch": 0.03,
"learning_rate": 0.00019861674658797494,
"loss": 1.7922,
"step": 150
},
{
"epoch": 0.03,
"learning_rate": 0.00019852452969383992,
"loss": 1.8446,
"step": 160
},
{
"epoch": 0.03,
"learning_rate": 0.0001984323127997049,
"loss": 1.8217,
"step": 170
},
{
"epoch": 0.03,
"learning_rate": 0.0001983400959055699,
"loss": 1.8406,
"step": 180
},
{
"epoch": 0.04,
"learning_rate": 0.0001982478790114349,
"loss": 1.8379,
"step": 190
},
{
"epoch": 0.04,
"learning_rate": 0.0001981556621172999,
"loss": 1.7822,
"step": 200
},
{
"epoch": 0.04,
"learning_rate": 0.0001980634452231649,
"loss": 1.8287,
"step": 210
},
{
"epoch": 0.04,
"learning_rate": 0.00019797122832902988,
"loss": 1.8191,
"step": 220
},
{
"epoch": 0.04,
"learning_rate": 0.0001978790114348949,
"loss": 1.7958,
"step": 230
},
{
"epoch": 0.04,
"learning_rate": 0.00019778679454075988,
"loss": 1.7708,
"step": 240
},
{
"epoch": 0.05,
"learning_rate": 0.00019769457764662486,
"loss": 1.7059,
"step": 250
},
{
"epoch": 0.05,
"learning_rate": 0.00019760236075248985,
"loss": 1.7921,
"step": 260
},
{
"epoch": 0.05,
"learning_rate": 0.00019751014385835486,
"loss": 1.8458,
"step": 270
},
{
"epoch": 0.05,
"learning_rate": 0.00019741792696421984,
"loss": 1.7092,
"step": 280
},
{
"epoch": 0.05,
"learning_rate": 0.00019732571007008486,
"loss": 1.7765,
"step": 290
},
{
"epoch": 0.06,
"learning_rate": 0.00019723349317594984,
"loss": 1.7186,
"step": 300
},
{
"epoch": 0.06,
"learning_rate": 0.00019714127628181485,
"loss": 1.7108,
"step": 310
},
{
"epoch": 0.06,
"learning_rate": 0.00019704905938767984,
"loss": 1.5981,
"step": 320
},
{
"epoch": 0.06,
"learning_rate": 0.00019695684249354482,
"loss": 1.7238,
"step": 330
},
{
"epoch": 0.06,
"learning_rate": 0.0001968646255994098,
"loss": 1.677,
"step": 340
},
{
"epoch": 0.06,
"learning_rate": 0.00019677240870527482,
"loss": 1.6465,
"step": 350
},
{
"epoch": 0.07,
"learning_rate": 0.0001966801918111398,
"loss": 1.6533,
"step": 360
},
{
"epoch": 0.07,
"learning_rate": 0.0001965879749170048,
"loss": 1.5514,
"step": 370
},
{
"epoch": 0.07,
"learning_rate": 0.0001964957580228698,
"loss": 1.5717,
"step": 380
},
{
"epoch": 0.07,
"learning_rate": 0.0001964035411287348,
"loss": 1.6208,
"step": 390
},
{
"epoch": 0.07,
"learning_rate": 0.0001963113242345998,
"loss": 1.7294,
"step": 400
},
{
"epoch": 0.08,
"learning_rate": 0.00019621910734046478,
"loss": 1.6014,
"step": 410
},
{
"epoch": 0.08,
"learning_rate": 0.00019612689044632976,
"loss": 1.7207,
"step": 420
},
{
"epoch": 0.08,
"learning_rate": 0.00019603467355219477,
"loss": 1.6452,
"step": 430
},
{
"epoch": 0.08,
"learning_rate": 0.00019594245665805976,
"loss": 1.5979,
"step": 440
},
{
"epoch": 0.08,
"learning_rate": 0.00019585023976392477,
"loss": 1.5809,
"step": 450
},
{
"epoch": 0.08,
"learning_rate": 0.00019575802286978975,
"loss": 1.5626,
"step": 460
},
{
"epoch": 0.09,
"learning_rate": 0.00019566580597565476,
"loss": 1.4701,
"step": 470
},
{
"epoch": 0.09,
"learning_rate": 0.00019557358908151975,
"loss": 1.6025,
"step": 480
},
{
"epoch": 0.09,
"learning_rate": 0.00019548137218738473,
"loss": 1.4946,
"step": 490
},
{
"epoch": 0.09,
"learning_rate": 0.00019538915529324972,
"loss": 1.6431,
"step": 500
},
{
"epoch": 0.09,
"learning_rate": 0.00019529693839911473,
"loss": 1.5584,
"step": 510
},
{
"epoch": 0.1,
"learning_rate": 0.00019520472150497971,
"loss": 1.6565,
"step": 520
},
{
"epoch": 0.1,
"learning_rate": 0.00019511250461084473,
"loss": 1.5616,
"step": 530
},
{
"epoch": 0.1,
"learning_rate": 0.0001950202877167097,
"loss": 1.5366,
"step": 540
},
{
"epoch": 0.1,
"learning_rate": 0.00019492807082257472,
"loss": 1.6421,
"step": 550
},
{
"epoch": 0.1,
"learning_rate": 0.0001948358539284397,
"loss": 1.5919,
"step": 560
},
{
"epoch": 0.11,
"learning_rate": 0.0001947436370343047,
"loss": 1.594,
"step": 570
},
{
"epoch": 0.11,
"learning_rate": 0.00019465142014016967,
"loss": 1.5947,
"step": 580
},
{
"epoch": 0.11,
"learning_rate": 0.00019455920324603469,
"loss": 1.612,
"step": 590
},
{
"epoch": 0.11,
"learning_rate": 0.00019446698635189967,
"loss": 1.4975,
"step": 600
},
{
"epoch": 0.11,
"learning_rate": 0.00019437476945776468,
"loss": 1.5175,
"step": 610
},
{
"epoch": 0.11,
"learning_rate": 0.00019428255256362967,
"loss": 1.3869,
"step": 620
},
{
"epoch": 0.12,
"learning_rate": 0.00019419033566949468,
"loss": 1.494,
"step": 630
},
{
"epoch": 0.12,
"learning_rate": 0.00019409811877535966,
"loss": 1.557,
"step": 640
},
{
"epoch": 0.12,
"learning_rate": 0.00019400590188122465,
"loss": 1.4168,
"step": 650
},
{
"epoch": 0.12,
"learning_rate": 0.00019391368498708963,
"loss": 1.4237,
"step": 660
},
{
"epoch": 0.12,
"learning_rate": 0.00019382146809295462,
"loss": 1.4369,
"step": 670
},
{
"epoch": 0.13,
"learning_rate": 0.00019372925119881963,
"loss": 1.399,
"step": 680
},
{
"epoch": 0.13,
"learning_rate": 0.00019363703430468464,
"loss": 1.4145,
"step": 690
},
{
"epoch": 0.13,
"learning_rate": 0.00019354481741054962,
"loss": 1.5005,
"step": 700
},
{
"epoch": 0.13,
"learning_rate": 0.0001934526005164146,
"loss": 1.5179,
"step": 710
},
{
"epoch": 0.13,
"learning_rate": 0.00019336038362227962,
"loss": 1.4201,
"step": 720
},
{
"epoch": 0.13,
"learning_rate": 0.0001932681667281446,
"loss": 1.5546,
"step": 730
},
{
"epoch": 0.14,
"learning_rate": 0.0001931759498340096,
"loss": 1.5961,
"step": 740
},
{
"epoch": 0.14,
"learning_rate": 0.00019308373293987457,
"loss": 1.4922,
"step": 750
},
{
"epoch": 0.14,
"learning_rate": 0.00019299151604573958,
"loss": 1.4039,
"step": 760
},
{
"epoch": 0.14,
"learning_rate": 0.0001928992991516046,
"loss": 1.4541,
"step": 770
},
{
"epoch": 0.14,
"learning_rate": 0.00019280708225746958,
"loss": 1.4385,
"step": 780
},
{
"epoch": 0.15,
"learning_rate": 0.00019271486536333456,
"loss": 1.4652,
"step": 790
},
{
"epoch": 0.15,
"learning_rate": 0.00019262264846919958,
"loss": 1.4903,
"step": 800
},
{
"epoch": 0.15,
"learning_rate": 0.00019253043157506456,
"loss": 1.5028,
"step": 810
},
{
"epoch": 0.15,
"learning_rate": 0.00019243821468092954,
"loss": 1.4647,
"step": 820
},
{
"epoch": 0.15,
"learning_rate": 0.00019234599778679453,
"loss": 1.4421,
"step": 830
},
{
"epoch": 0.15,
"learning_rate": 0.00019225378089265954,
"loss": 1.483,
"step": 840
},
{
"epoch": 0.16,
"learning_rate": 0.00019216156399852455,
"loss": 1.5329,
"step": 850
},
{
"epoch": 0.16,
"learning_rate": 0.00019206934710438954,
"loss": 1.4918,
"step": 860
},
{
"epoch": 0.16,
"learning_rate": 0.00019197713021025452,
"loss": 1.4519,
"step": 870
},
{
"epoch": 0.16,
"learning_rate": 0.00019188491331611953,
"loss": 1.2952,
"step": 880
},
{
"epoch": 0.16,
"learning_rate": 0.00019179269642198452,
"loss": 1.4764,
"step": 890
},
{
"epoch": 0.17,
"learning_rate": 0.0001917004795278495,
"loss": 1.419,
"step": 900
},
{
"epoch": 0.17,
"learning_rate": 0.00019160826263371449,
"loss": 1.4126,
"step": 910
},
{
"epoch": 0.17,
"learning_rate": 0.0001915160457395795,
"loss": 1.4495,
"step": 920
},
{
"epoch": 0.17,
"learning_rate": 0.0001914238288454445,
"loss": 1.4355,
"step": 930
},
{
"epoch": 0.17,
"learning_rate": 0.0001913316119513095,
"loss": 1.3425,
"step": 940
},
{
"epoch": 0.18,
"learning_rate": 0.00019123939505717448,
"loss": 1.3806,
"step": 950
},
{
"epoch": 0.18,
"learning_rate": 0.0001911471781630395,
"loss": 1.3833,
"step": 960
},
{
"epoch": 0.18,
"learning_rate": 0.00019105496126890447,
"loss": 1.4533,
"step": 970
},
{
"epoch": 0.18,
"learning_rate": 0.00019096274437476946,
"loss": 1.4369,
"step": 980
},
{
"epoch": 0.18,
"learning_rate": 0.00019087052748063444,
"loss": 1.4233,
"step": 990
},
{
"epoch": 0.18,
"learning_rate": 0.00019077831058649945,
"loss": 1.3347,
"step": 1000
},
{
"epoch": 0.18,
"eval_accuracy": 0.4296147526017893,
"eval_loss": 1.3819409608840942,
"eval_runtime": 98.0284,
"eval_samples_per_second": 111.743,
"eval_steps_per_second": 13.976,
"step": 1000
},
{
"epoch": 0.19,
"learning_rate": 0.00019068609369236446,
"loss": 1.3295,
"step": 1010
},
{
"epoch": 0.19,
"learning_rate": 0.00019059387679822945,
"loss": 1.4622,
"step": 1020
},
{
"epoch": 0.19,
"learning_rate": 0.00019050165990409443,
"loss": 1.3483,
"step": 1030
},
{
"epoch": 0.19,
"learning_rate": 0.00019040944300995944,
"loss": 1.4762,
"step": 1040
},
{
"epoch": 0.19,
"learning_rate": 0.00019031722611582443,
"loss": 1.462,
"step": 1050
},
{
"epoch": 0.2,
"learning_rate": 0.00019022500922168941,
"loss": 1.5086,
"step": 1060
},
{
"epoch": 0.2,
"learning_rate": 0.0001901327923275544,
"loss": 1.4992,
"step": 1070
},
{
"epoch": 0.2,
"learning_rate": 0.0001900405754334194,
"loss": 1.3563,
"step": 1080
},
{
"epoch": 0.2,
"learning_rate": 0.00018994835853928442,
"loss": 1.3295,
"step": 1090
},
{
"epoch": 0.2,
"learning_rate": 0.0001898561416451494,
"loss": 1.3227,
"step": 1100
},
{
"epoch": 0.2,
"learning_rate": 0.0001897639247510144,
"loss": 1.4465,
"step": 1110
},
{
"epoch": 0.21,
"learning_rate": 0.0001896717078568794,
"loss": 1.4442,
"step": 1120
},
{
"epoch": 0.21,
"learning_rate": 0.00018957949096274439,
"loss": 1.3804,
"step": 1130
},
{
"epoch": 0.21,
"learning_rate": 0.00018948727406860937,
"loss": 1.3868,
"step": 1140
},
{
"epoch": 0.21,
"learning_rate": 0.00018939505717447435,
"loss": 1.4905,
"step": 1150
},
{
"epoch": 0.21,
"learning_rate": 0.00018930284028033937,
"loss": 1.3099,
"step": 1160
},
{
"epoch": 0.22,
"learning_rate": 0.00018921062338620438,
"loss": 1.4865,
"step": 1170
},
{
"epoch": 0.22,
"learning_rate": 0.00018911840649206936,
"loss": 1.4155,
"step": 1180
},
{
"epoch": 0.22,
"learning_rate": 0.00018902618959793435,
"loss": 1.4095,
"step": 1190
},
{
"epoch": 0.22,
"learning_rate": 0.00018893397270379936,
"loss": 1.3217,
"step": 1200
},
{
"epoch": 0.22,
"learning_rate": 0.00018884175580966434,
"loss": 1.5028,
"step": 1210
},
{
"epoch": 0.23,
"learning_rate": 0.00018874953891552933,
"loss": 1.4024,
"step": 1220
},
{
"epoch": 0.23,
"learning_rate": 0.0001886573220213943,
"loss": 1.4699,
"step": 1230
},
{
"epoch": 0.23,
"learning_rate": 0.00018856510512725932,
"loss": 1.4158,
"step": 1240
},
{
"epoch": 0.23,
"learning_rate": 0.00018847288823312433,
"loss": 1.4024,
"step": 1250
},
{
"epoch": 0.23,
"learning_rate": 0.00018838067133898932,
"loss": 1.4017,
"step": 1260
},
{
"epoch": 0.23,
"learning_rate": 0.0001882884544448543,
"loss": 1.3641,
"step": 1270
},
{
"epoch": 0.24,
"learning_rate": 0.0001881962375507193,
"loss": 1.4008,
"step": 1280
},
{
"epoch": 0.24,
"learning_rate": 0.0001881040206565843,
"loss": 1.3428,
"step": 1290
},
{
"epoch": 0.24,
"learning_rate": 0.00018801180376244928,
"loss": 1.3389,
"step": 1300
},
{
"epoch": 0.24,
"learning_rate": 0.00018791958686831427,
"loss": 1.3816,
"step": 1310
},
{
"epoch": 0.24,
"learning_rate": 0.00018782736997417928,
"loss": 1.3573,
"step": 1320
},
{
"epoch": 0.25,
"learning_rate": 0.0001877351530800443,
"loss": 1.3648,
"step": 1330
},
{
"epoch": 0.25,
"learning_rate": 0.00018764293618590928,
"loss": 1.4559,
"step": 1340
},
{
"epoch": 0.25,
"learning_rate": 0.00018755071929177426,
"loss": 1.3925,
"step": 1350
},
{
"epoch": 0.25,
"learning_rate": 0.00018745850239763924,
"loss": 1.3426,
"step": 1360
},
{
"epoch": 0.25,
"learning_rate": 0.00018736628550350426,
"loss": 1.3808,
"step": 1370
},
{
"epoch": 0.25,
"learning_rate": 0.00018727406860936924,
"loss": 1.4028,
"step": 1380
},
{
"epoch": 0.26,
"learning_rate": 0.00018718185171523422,
"loss": 1.4092,
"step": 1390
},
{
"epoch": 0.26,
"learning_rate": 0.00018708963482109924,
"loss": 1.3941,
"step": 1400
},
{
"epoch": 0.26,
"learning_rate": 0.00018699741792696425,
"loss": 1.3246,
"step": 1410
},
{
"epoch": 0.26,
"learning_rate": 0.00018690520103282923,
"loss": 1.3828,
"step": 1420
},
{
"epoch": 0.26,
"learning_rate": 0.00018681298413869422,
"loss": 1.3388,
"step": 1430
},
{
"epoch": 0.27,
"learning_rate": 0.0001867207672445592,
"loss": 1.3951,
"step": 1440
},
{
"epoch": 0.27,
"learning_rate": 0.0001866285503504242,
"loss": 1.3484,
"step": 1450
},
{
"epoch": 0.27,
"learning_rate": 0.0001865363334562892,
"loss": 1.5975,
"step": 1460
},
{
"epoch": 0.27,
"learning_rate": 0.00018644411656215418,
"loss": 1.4879,
"step": 1470
},
{
"epoch": 0.27,
"learning_rate": 0.0001863518996680192,
"loss": 1.3751,
"step": 1480
},
{
"epoch": 0.27,
"learning_rate": 0.0001862596827738842,
"loss": 1.3561,
"step": 1490
},
{
"epoch": 0.28,
"learning_rate": 0.0001861674658797492,
"loss": 1.3283,
"step": 1500
},
{
"epoch": 0.28,
"learning_rate": 0.00018607524898561417,
"loss": 1.4457,
"step": 1510
},
{
"epoch": 0.28,
"learning_rate": 0.00018598303209147916,
"loss": 1.4338,
"step": 1520
},
{
"epoch": 0.28,
"learning_rate": 0.00018589081519734417,
"loss": 1.313,
"step": 1530
},
{
"epoch": 0.28,
"learning_rate": 0.00018579859830320915,
"loss": 1.4286,
"step": 1540
},
{
"epoch": 0.29,
"learning_rate": 0.00018570638140907414,
"loss": 1.3152,
"step": 1550
},
{
"epoch": 0.29,
"learning_rate": 0.00018561416451493915,
"loss": 1.3988,
"step": 1560
},
{
"epoch": 0.29,
"learning_rate": 0.00018552194762080416,
"loss": 1.3082,
"step": 1570
},
{
"epoch": 0.29,
"learning_rate": 0.00018542973072666915,
"loss": 1.2954,
"step": 1580
},
{
"epoch": 0.29,
"learning_rate": 0.00018533751383253413,
"loss": 1.2728,
"step": 1590
},
{
"epoch": 0.3,
"learning_rate": 0.00018524529693839911,
"loss": 1.3098,
"step": 1600
},
{
"epoch": 0.3,
"learning_rate": 0.00018515308004426413,
"loss": 1.3343,
"step": 1610
},
{
"epoch": 0.3,
"learning_rate": 0.0001850608631501291,
"loss": 1.3702,
"step": 1620
},
{
"epoch": 0.3,
"learning_rate": 0.0001849686462559941,
"loss": 1.3413,
"step": 1630
},
{
"epoch": 0.3,
"learning_rate": 0.0001848764293618591,
"loss": 1.3541,
"step": 1640
},
{
"epoch": 0.3,
"learning_rate": 0.00018478421246772412,
"loss": 1.3882,
"step": 1650
},
{
"epoch": 0.31,
"learning_rate": 0.0001846919955735891,
"loss": 1.338,
"step": 1660
},
{
"epoch": 0.31,
"learning_rate": 0.00018459977867945409,
"loss": 1.3311,
"step": 1670
},
{
"epoch": 0.31,
"learning_rate": 0.00018450756178531907,
"loss": 1.3407,
"step": 1680
},
{
"epoch": 0.31,
"learning_rate": 0.00018441534489118408,
"loss": 1.4169,
"step": 1690
},
{
"epoch": 0.31,
"learning_rate": 0.00018432312799704907,
"loss": 1.2783,
"step": 1700
},
{
"epoch": 0.32,
"learning_rate": 0.00018423091110291405,
"loss": 1.3291,
"step": 1710
},
{
"epoch": 0.32,
"learning_rate": 0.00018413869420877906,
"loss": 1.4276,
"step": 1720
},
{
"epoch": 0.32,
"learning_rate": 0.00018404647731464407,
"loss": 1.4504,
"step": 1730
},
{
"epoch": 0.32,
"learning_rate": 0.00018395426042050906,
"loss": 1.356,
"step": 1740
},
{
"epoch": 0.32,
"learning_rate": 0.00018386204352637404,
"loss": 1.3567,
"step": 1750
},
{
"epoch": 0.32,
"learning_rate": 0.00018376982663223903,
"loss": 1.2416,
"step": 1760
},
{
"epoch": 0.33,
"learning_rate": 0.00018367760973810404,
"loss": 1.2971,
"step": 1770
},
{
"epoch": 0.33,
"learning_rate": 0.00018358539284396902,
"loss": 1.2429,
"step": 1780
},
{
"epoch": 0.33,
"learning_rate": 0.000183493175949834,
"loss": 1.3004,
"step": 1790
},
{
"epoch": 0.33,
"learning_rate": 0.00018340095905569902,
"loss": 1.3765,
"step": 1800
},
{
"epoch": 0.33,
"learning_rate": 0.00018330874216156403,
"loss": 1.4921,
"step": 1810
},
{
"epoch": 0.34,
"learning_rate": 0.00018321652526742901,
"loss": 1.3344,
"step": 1820
},
{
"epoch": 0.34,
"learning_rate": 0.000183124308373294,
"loss": 1.4283,
"step": 1830
},
{
"epoch": 0.34,
"learning_rate": 0.00018303209147915898,
"loss": 1.2761,
"step": 1840
},
{
"epoch": 0.34,
"learning_rate": 0.000182939874585024,
"loss": 1.3461,
"step": 1850
},
{
"epoch": 0.34,
"learning_rate": 0.00018284765769088898,
"loss": 1.2124,
"step": 1860
},
{
"epoch": 0.34,
"learning_rate": 0.00018275544079675396,
"loss": 1.3249,
"step": 1870
},
{
"epoch": 0.35,
"learning_rate": 0.00018266322390261898,
"loss": 1.3656,
"step": 1880
},
{
"epoch": 0.35,
"learning_rate": 0.000182571007008484,
"loss": 1.3039,
"step": 1890
},
{
"epoch": 0.35,
"learning_rate": 0.00018247879011434897,
"loss": 1.3722,
"step": 1900
},
{
"epoch": 0.35,
"learning_rate": 0.00018238657322021396,
"loss": 1.1888,
"step": 1910
},
{
"epoch": 0.35,
"learning_rate": 0.00018229435632607894,
"loss": 1.3604,
"step": 1920
},
{
"epoch": 0.36,
"learning_rate": 0.00018220213943194392,
"loss": 1.4169,
"step": 1930
},
{
"epoch": 0.36,
"learning_rate": 0.00018210992253780894,
"loss": 1.2332,
"step": 1940
},
{
"epoch": 0.36,
"learning_rate": 0.00018201770564367392,
"loss": 1.2774,
"step": 1950
},
{
"epoch": 0.36,
"learning_rate": 0.00018192548874953893,
"loss": 1.4248,
"step": 1960
},
{
"epoch": 0.36,
"learning_rate": 0.00018183327185540392,
"loss": 1.3928,
"step": 1970
},
{
"epoch": 0.37,
"learning_rate": 0.00018174105496126893,
"loss": 1.2566,
"step": 1980
},
{
"epoch": 0.37,
"learning_rate": 0.0001816488380671339,
"loss": 1.2803,
"step": 1990
},
{
"epoch": 0.37,
"learning_rate": 0.0001815566211729989,
"loss": 1.3071,
"step": 2000
},
{
"epoch": 0.37,
"eval_accuracy": 0.464213985758627,
"eval_loss": 1.279906988143921,
"eval_runtime": 97.8688,
"eval_samples_per_second": 111.925,
"eval_steps_per_second": 13.998,
"step": 2000
},
{
"epoch": 0.37,
"learning_rate": 0.00018146440427886388,
"loss": 1.3159,
"step": 2010
},
{
"epoch": 0.37,
"learning_rate": 0.0001813721873847289,
"loss": 1.4002,
"step": 2020
},
{
"epoch": 0.37,
"learning_rate": 0.00018127997049059388,
"loss": 1.2217,
"step": 2030
},
{
"epoch": 0.38,
"learning_rate": 0.0001811877535964589,
"loss": 1.2869,
"step": 2040
},
{
"epoch": 0.38,
"learning_rate": 0.00018109553670232387,
"loss": 1.2793,
"step": 2050
},
{
"epoch": 0.38,
"learning_rate": 0.00018100331980818888,
"loss": 1.3284,
"step": 2060
},
{
"epoch": 0.38,
"learning_rate": 0.00018091110291405387,
"loss": 1.1991,
"step": 2070
},
{
"epoch": 0.38,
"learning_rate": 0.00018081888601991885,
"loss": 1.1353,
"step": 2080
},
{
"epoch": 0.39,
"learning_rate": 0.00018072666912578384,
"loss": 1.3133,
"step": 2090
},
{
"epoch": 0.39,
"learning_rate": 0.00018063445223164885,
"loss": 1.3075,
"step": 2100
},
{
"epoch": 0.39,
"learning_rate": 0.00018054223533751383,
"loss": 1.4026,
"step": 2110
},
{
"epoch": 0.39,
"learning_rate": 0.00018045001844337885,
"loss": 1.3367,
"step": 2120
},
{
"epoch": 0.39,
"learning_rate": 0.00018035780154924383,
"loss": 1.3156,
"step": 2130
},
{
"epoch": 0.39,
"learning_rate": 0.00018026558465510884,
"loss": 1.2022,
"step": 2140
},
{
"epoch": 0.4,
"learning_rate": 0.00018017336776097383,
"loss": 1.3409,
"step": 2150
},
{
"epoch": 0.4,
"learning_rate": 0.0001800811508668388,
"loss": 1.2041,
"step": 2160
},
{
"epoch": 0.4,
"learning_rate": 0.0001799889339727038,
"loss": 1.3062,
"step": 2170
},
{
"epoch": 0.4,
"learning_rate": 0.0001798967170785688,
"loss": 1.2372,
"step": 2180
},
{
"epoch": 0.4,
"learning_rate": 0.0001798045001844338,
"loss": 1.2237,
"step": 2190
},
{
"epoch": 0.41,
"learning_rate": 0.0001797122832902988,
"loss": 1.2524,
"step": 2200
},
{
"epoch": 0.41,
"learning_rate": 0.00017962006639616379,
"loss": 1.4144,
"step": 2210
},
{
"epoch": 0.41,
"learning_rate": 0.0001795278495020288,
"loss": 1.1676,
"step": 2220
},
{
"epoch": 0.41,
"learning_rate": 0.00017943563260789378,
"loss": 1.2909,
"step": 2230
},
{
"epoch": 0.41,
"learning_rate": 0.00017934341571375877,
"loss": 1.372,
"step": 2240
},
{
"epoch": 0.41,
"learning_rate": 0.00017925119881962375,
"loss": 1.2902,
"step": 2250
},
{
"epoch": 0.42,
"learning_rate": 0.00017915898192548876,
"loss": 1.2131,
"step": 2260
},
{
"epoch": 0.42,
"learning_rate": 0.00017906676503135375,
"loss": 1.198,
"step": 2270
},
{
"epoch": 0.42,
"learning_rate": 0.00017897454813721876,
"loss": 1.2151,
"step": 2280
},
{
"epoch": 0.42,
"learning_rate": 0.00017888233124308374,
"loss": 1.3141,
"step": 2290
},
{
"epoch": 0.42,
"learning_rate": 0.00017879011434894875,
"loss": 1.3788,
"step": 2300
},
{
"epoch": 0.43,
"learning_rate": 0.00017869789745481374,
"loss": 1.2766,
"step": 2310
},
{
"epoch": 0.43,
"learning_rate": 0.00017860568056067872,
"loss": 1.2166,
"step": 2320
},
{
"epoch": 0.43,
"learning_rate": 0.0001785134636665437,
"loss": 1.3074,
"step": 2330
},
{
"epoch": 0.43,
"learning_rate": 0.00017842124677240872,
"loss": 1.2592,
"step": 2340
},
{
"epoch": 0.43,
"learning_rate": 0.0001783290298782737,
"loss": 1.2932,
"step": 2350
},
{
"epoch": 0.44,
"learning_rate": 0.00017823681298413871,
"loss": 1.2729,
"step": 2360
},
{
"epoch": 0.44,
"learning_rate": 0.0001781445960900037,
"loss": 1.256,
"step": 2370
},
{
"epoch": 0.44,
"learning_rate": 0.0001780523791958687,
"loss": 1.284,
"step": 2380
},
{
"epoch": 0.44,
"learning_rate": 0.0001779601623017337,
"loss": 1.2473,
"step": 2390
},
{
"epoch": 0.44,
"learning_rate": 0.00017786794540759868,
"loss": 1.3336,
"step": 2400
},
{
"epoch": 0.44,
"learning_rate": 0.00017777572851346366,
"loss": 1.3713,
"step": 2410
},
{
"epoch": 0.45,
"learning_rate": 0.00017768351161932868,
"loss": 1.3888,
"step": 2420
},
{
"epoch": 0.45,
"learning_rate": 0.00017759129472519366,
"loss": 1.2189,
"step": 2430
},
{
"epoch": 0.45,
"learning_rate": 0.00017749907783105864,
"loss": 1.3783,
"step": 2440
},
{
"epoch": 0.45,
"learning_rate": 0.00017740686093692366,
"loss": 1.2576,
"step": 2450
},
{
"epoch": 0.45,
"learning_rate": 0.00017731464404278867,
"loss": 1.2524,
"step": 2460
},
{
"epoch": 0.46,
"learning_rate": 0.00017722242714865365,
"loss": 1.1614,
"step": 2470
},
{
"epoch": 0.46,
"learning_rate": 0.00017713021025451864,
"loss": 1.2631,
"step": 2480
},
{
"epoch": 0.46,
"learning_rate": 0.00017703799336038362,
"loss": 1.2215,
"step": 2490
},
{
"epoch": 0.46,
"learning_rate": 0.00017694577646624863,
"loss": 1.266,
"step": 2500
},
{
"epoch": 0.46,
"learning_rate": 0.00017685355957211362,
"loss": 1.1883,
"step": 2510
},
{
"epoch": 0.46,
"learning_rate": 0.0001767613426779786,
"loss": 1.2202,
"step": 2520
},
{
"epoch": 0.47,
"learning_rate": 0.0001766691257838436,
"loss": 1.238,
"step": 2530
},
{
"epoch": 0.47,
"learning_rate": 0.0001765769088897086,
"loss": 1.2836,
"step": 2540
},
{
"epoch": 0.47,
"learning_rate": 0.0001764846919955736,
"loss": 1.2879,
"step": 2550
},
{
"epoch": 0.47,
"learning_rate": 0.0001763924751014386,
"loss": 1.17,
"step": 2560
},
{
"epoch": 0.47,
"learning_rate": 0.00017630025820730358,
"loss": 1.1675,
"step": 2570
},
{
"epoch": 0.48,
"learning_rate": 0.00017620804131316856,
"loss": 1.1862,
"step": 2580
},
{
"epoch": 0.48,
"learning_rate": 0.00017611582441903357,
"loss": 1.2787,
"step": 2590
},
{
"epoch": 0.48,
"learning_rate": 0.00017602360752489856,
"loss": 1.1561,
"step": 2600
},
{
"epoch": 0.48,
"learning_rate": 0.00017593139063076357,
"loss": 1.3317,
"step": 2610
},
{
"epoch": 0.48,
"learning_rate": 0.00017583917373662855,
"loss": 1.2562,
"step": 2620
},
{
"epoch": 0.49,
"learning_rate": 0.00017574695684249356,
"loss": 1.3731,
"step": 2630
},
{
"epoch": 0.49,
"learning_rate": 0.00017565473994835855,
"loss": 1.304,
"step": 2640
},
{
"epoch": 0.49,
"learning_rate": 0.00017556252305422353,
"loss": 1.2217,
"step": 2650
},
{
"epoch": 0.49,
"learning_rate": 0.00017547030616008852,
"loss": 1.2968,
"step": 2660
},
{
"epoch": 0.49,
"learning_rate": 0.00017537808926595353,
"loss": 1.2932,
"step": 2670
},
{
"epoch": 0.49,
"learning_rate": 0.00017528587237181851,
"loss": 1.3466,
"step": 2680
},
{
"epoch": 0.5,
"learning_rate": 0.00017519365547768353,
"loss": 1.272,
"step": 2690
},
{
"epoch": 0.5,
"learning_rate": 0.0001751014385835485,
"loss": 1.1447,
"step": 2700
},
{
"epoch": 0.5,
"learning_rate": 0.00017500922168941352,
"loss": 1.2865,
"step": 2710
},
{
"epoch": 0.5,
"learning_rate": 0.0001749170047952785,
"loss": 1.287,
"step": 2720
},
{
"epoch": 0.5,
"learning_rate": 0.0001748247879011435,
"loss": 1.2388,
"step": 2730
},
{
"epoch": 0.51,
"learning_rate": 0.00017473257100700847,
"loss": 1.2865,
"step": 2740
},
{
"epoch": 0.51,
"learning_rate": 0.00017464035411287349,
"loss": 1.2697,
"step": 2750
},
{
"epoch": 0.51,
"learning_rate": 0.00017454813721873847,
"loss": 1.2994,
"step": 2760
},
{
"epoch": 0.51,
"learning_rate": 0.00017445592032460348,
"loss": 1.3243,
"step": 2770
},
{
"epoch": 0.51,
"learning_rate": 0.00017436370343046847,
"loss": 1.1788,
"step": 2780
},
{
"epoch": 0.51,
"learning_rate": 0.00017427148653633348,
"loss": 1.3052,
"step": 2790
},
{
"epoch": 0.52,
"learning_rate": 0.00017417926964219846,
"loss": 1.2467,
"step": 2800
},
{
"epoch": 0.52,
"learning_rate": 0.00017408705274806345,
"loss": 1.2646,
"step": 2810
},
{
"epoch": 0.52,
"learning_rate": 0.00017399483585392843,
"loss": 1.3098,
"step": 2820
},
{
"epoch": 0.52,
"learning_rate": 0.00017390261895979344,
"loss": 1.3249,
"step": 2830
},
{
"epoch": 0.52,
"learning_rate": 0.00017381040206565843,
"loss": 1.3779,
"step": 2840
},
{
"epoch": 0.53,
"learning_rate": 0.00017371818517152344,
"loss": 1.3639,
"step": 2850
},
{
"epoch": 0.53,
"learning_rate": 0.00017362596827738842,
"loss": 1.2494,
"step": 2860
},
{
"epoch": 0.53,
"learning_rate": 0.00017353375138325343,
"loss": 1.2869,
"step": 2870
},
{
"epoch": 0.53,
"learning_rate": 0.00017344153448911842,
"loss": 1.2766,
"step": 2880
},
{
"epoch": 0.53,
"learning_rate": 0.0001733493175949834,
"loss": 1.1126,
"step": 2890
},
{
"epoch": 0.53,
"learning_rate": 0.0001732571007008484,
"loss": 1.1705,
"step": 2900
},
{
"epoch": 0.54,
"learning_rate": 0.0001731648838067134,
"loss": 1.2194,
"step": 2910
},
{
"epoch": 0.54,
"learning_rate": 0.00017307266691257838,
"loss": 1.2963,
"step": 2920
},
{
"epoch": 0.54,
"learning_rate": 0.0001729804500184434,
"loss": 1.2211,
"step": 2930
},
{
"epoch": 0.54,
"learning_rate": 0.00017288823312430838,
"loss": 1.1875,
"step": 2940
},
{
"epoch": 0.54,
"learning_rate": 0.0001727960162301734,
"loss": 1.3088,
"step": 2950
},
{
"epoch": 0.55,
"learning_rate": 0.00017270379933603838,
"loss": 1.3143,
"step": 2960
},
{
"epoch": 0.55,
"learning_rate": 0.00017261158244190336,
"loss": 1.2684,
"step": 2970
},
{
"epoch": 0.55,
"learning_rate": 0.00017251936554776834,
"loss": 1.1308,
"step": 2980
},
{
"epoch": 0.55,
"learning_rate": 0.00017242714865363336,
"loss": 1.2508,
"step": 2990
},
{
"epoch": 0.55,
"learning_rate": 0.00017233493175949834,
"loss": 1.297,
"step": 3000
},
{
"epoch": 0.55,
"eval_accuracy": 0.4720649990870915,
"eval_loss": 1.250298261642456,
"eval_runtime": 98.4328,
"eval_samples_per_second": 111.284,
"eval_steps_per_second": 13.918,
"step": 3000
},
{
"epoch": 0.56,
"learning_rate": 0.00017224271486536335,
"loss": 1.2519,
"step": 3010
},
{
"epoch": 0.56,
"learning_rate": 0.00017215049797122834,
"loss": 1.1632,
"step": 3020
},
{
"epoch": 0.56,
"learning_rate": 0.00017205828107709335,
"loss": 1.2063,
"step": 3030
},
{
"epoch": 0.56,
"learning_rate": 0.00017196606418295833,
"loss": 1.2205,
"step": 3040
},
{
"epoch": 0.56,
"learning_rate": 0.00017187384728882332,
"loss": 1.2787,
"step": 3050
},
{
"epoch": 0.56,
"learning_rate": 0.0001717816303946883,
"loss": 1.1501,
"step": 3060
},
{
"epoch": 0.57,
"learning_rate": 0.0001716894135005533,
"loss": 1.4336,
"step": 3070
},
{
"epoch": 0.57,
"learning_rate": 0.0001715971966064183,
"loss": 1.228,
"step": 3080
},
{
"epoch": 0.57,
"learning_rate": 0.0001715049797122833,
"loss": 1.2311,
"step": 3090
},
{
"epoch": 0.57,
"learning_rate": 0.0001714127628181483,
"loss": 1.2151,
"step": 3100
},
{
"epoch": 0.57,
"learning_rate": 0.0001713205459240133,
"loss": 1.324,
"step": 3110
},
{
"epoch": 0.58,
"learning_rate": 0.0001712283290298783,
"loss": 1.2236,
"step": 3120
},
{
"epoch": 0.58,
"learning_rate": 0.00017113611213574327,
"loss": 1.1156,
"step": 3130
},
{
"epoch": 0.58,
"learning_rate": 0.00017104389524160826,
"loss": 1.1789,
"step": 3140
},
{
"epoch": 0.58,
"learning_rate": 0.00017095167834747327,
"loss": 1.1482,
"step": 3150
},
{
"epoch": 0.58,
"learning_rate": 0.00017085946145333825,
"loss": 1.2907,
"step": 3160
},
{
"epoch": 0.58,
"learning_rate": 0.00017076724455920326,
"loss": 1.255,
"step": 3170
},
{
"epoch": 0.59,
"learning_rate": 0.00017067502766506825,
"loss": 1.1669,
"step": 3180
},
{
"epoch": 0.59,
"learning_rate": 0.00017058281077093323,
"loss": 1.2531,
"step": 3190
},
{
"epoch": 0.59,
"learning_rate": 0.00017049059387679825,
"loss": 1.3122,
"step": 3200
},
{
"epoch": 0.59,
"learning_rate": 0.00017039837698266323,
"loss": 1.2077,
"step": 3210
},
{
"epoch": 0.59,
"learning_rate": 0.00017030616008852821,
"loss": 1.2112,
"step": 3220
},
{
"epoch": 0.6,
"learning_rate": 0.0001702139431943932,
"loss": 1.2232,
"step": 3230
},
{
"epoch": 0.6,
"learning_rate": 0.0001701217263002582,
"loss": 1.2612,
"step": 3240
},
{
"epoch": 0.6,
"learning_rate": 0.00017002950940612322,
"loss": 1.2819,
"step": 3250
},
{
"epoch": 0.6,
"learning_rate": 0.0001699372925119882,
"loss": 1.3206,
"step": 3260
},
{
"epoch": 0.6,
"learning_rate": 0.0001698450756178532,
"loss": 1.1989,
"step": 3270
},
{
"epoch": 0.6,
"learning_rate": 0.0001697528587237182,
"loss": 1.204,
"step": 3280
},
{
"epoch": 0.61,
"learning_rate": 0.00016966064182958319,
"loss": 1.1277,
"step": 3290
},
{
"epoch": 0.61,
"learning_rate": 0.00016956842493544817,
"loss": 1.1263,
"step": 3300
},
{
"epoch": 0.61,
"learning_rate": 0.00016947620804131316,
"loss": 1.1812,
"step": 3310
},
{
"epoch": 0.61,
"learning_rate": 0.00016938399114717817,
"loss": 1.2092,
"step": 3320
},
{
"epoch": 0.61,
"learning_rate": 0.00016929177425304318,
"loss": 1.1473,
"step": 3330
},
{
"epoch": 0.62,
"learning_rate": 0.00016919955735890816,
"loss": 1.3631,
"step": 3340
},
{
"epoch": 0.62,
"learning_rate": 0.00016910734046477315,
"loss": 1.2097,
"step": 3350
},
{
"epoch": 0.62,
"learning_rate": 0.00016901512357063816,
"loss": 1.1183,
"step": 3360
},
{
"epoch": 0.62,
"learning_rate": 0.00016892290667650314,
"loss": 1.1925,
"step": 3370
},
{
"epoch": 0.62,
"learning_rate": 0.00016883068978236813,
"loss": 1.2737,
"step": 3380
},
{
"epoch": 0.63,
"learning_rate": 0.0001687384728882331,
"loss": 1.0825,
"step": 3390
},
{
"epoch": 0.63,
"learning_rate": 0.00016864625599409812,
"loss": 1.2121,
"step": 3400
},
{
"epoch": 0.63,
"learning_rate": 0.00016855403909996313,
"loss": 1.167,
"step": 3410
},
{
"epoch": 0.63,
"learning_rate": 0.00016846182220582812,
"loss": 1.3436,
"step": 3420
},
{
"epoch": 0.63,
"learning_rate": 0.0001683696053116931,
"loss": 1.1877,
"step": 3430
},
{
"epoch": 0.63,
"learning_rate": 0.00016827738841755812,
"loss": 1.2584,
"step": 3440
},
{
"epoch": 0.64,
"learning_rate": 0.0001681851715234231,
"loss": 1.3245,
"step": 3450
},
{
"epoch": 0.64,
"learning_rate": 0.00016809295462928808,
"loss": 1.2784,
"step": 3460
},
{
"epoch": 0.64,
"learning_rate": 0.00016800073773515307,
"loss": 1.0824,
"step": 3470
},
{
"epoch": 0.64,
"learning_rate": 0.00016790852084101808,
"loss": 1.1694,
"step": 3480
},
{
"epoch": 0.64,
"learning_rate": 0.0001678163039468831,
"loss": 1.1642,
"step": 3490
},
{
"epoch": 0.65,
"learning_rate": 0.00016772408705274808,
"loss": 1.1797,
"step": 3500
},
{
"epoch": 0.65,
"learning_rate": 0.00016763187015861306,
"loss": 1.2161,
"step": 3510
},
{
"epoch": 0.65,
"learning_rate": 0.00016753965326447807,
"loss": 1.2212,
"step": 3520
},
{
"epoch": 0.65,
"learning_rate": 0.00016744743637034306,
"loss": 1.0782,
"step": 3530
},
{
"epoch": 0.65,
"learning_rate": 0.00016735521947620804,
"loss": 1.2315,
"step": 3540
},
{
"epoch": 0.65,
"learning_rate": 0.00016726300258207302,
"loss": 1.1335,
"step": 3550
},
{
"epoch": 0.66,
"learning_rate": 0.00016717078568793804,
"loss": 1.1268,
"step": 3560
},
{
"epoch": 0.66,
"learning_rate": 0.00016707856879380305,
"loss": 1.3353,
"step": 3570
},
{
"epoch": 0.66,
"learning_rate": 0.00016698635189966803,
"loss": 1.2586,
"step": 3580
},
{
"epoch": 0.66,
"learning_rate": 0.00016689413500553302,
"loss": 1.3272,
"step": 3590
},
{
"epoch": 0.66,
"learning_rate": 0.00016680191811139803,
"loss": 1.1169,
"step": 3600
},
{
"epoch": 0.67,
"learning_rate": 0.000166709701217263,
"loss": 1.1928,
"step": 3610
},
{
"epoch": 0.67,
"learning_rate": 0.000166617484323128,
"loss": 1.0965,
"step": 3620
},
{
"epoch": 0.67,
"learning_rate": 0.00016652526742899298,
"loss": 1.2023,
"step": 3630
},
{
"epoch": 0.67,
"learning_rate": 0.000166433050534858,
"loss": 1.239,
"step": 3640
},
{
"epoch": 0.67,
"learning_rate": 0.000166340833640723,
"loss": 1.2667,
"step": 3650
},
{
"epoch": 0.68,
"learning_rate": 0.000166248616746588,
"loss": 1.3098,
"step": 3660
},
{
"epoch": 0.68,
"learning_rate": 0.00016615639985245297,
"loss": 1.1174,
"step": 3670
},
{
"epoch": 0.68,
"learning_rate": 0.00016606418295831798,
"loss": 1.1965,
"step": 3680
},
{
"epoch": 0.68,
"learning_rate": 0.00016597196606418297,
"loss": 1.1481,
"step": 3690
},
{
"epoch": 0.68,
"learning_rate": 0.00016587974917004795,
"loss": 1.1209,
"step": 3700
},
{
"epoch": 0.68,
"learning_rate": 0.00016578753227591294,
"loss": 1.1346,
"step": 3710
},
{
"epoch": 0.69,
"learning_rate": 0.00016569531538177795,
"loss": 1.2816,
"step": 3720
},
{
"epoch": 0.69,
"learning_rate": 0.00016560309848764296,
"loss": 1.1948,
"step": 3730
},
{
"epoch": 0.69,
"learning_rate": 0.00016551088159350795,
"loss": 1.1452,
"step": 3740
},
{
"epoch": 0.69,
"learning_rate": 0.00016541866469937293,
"loss": 1.1751,
"step": 3750
},
{
"epoch": 0.69,
"learning_rate": 0.00016532644780523794,
"loss": 1.212,
"step": 3760
},
{
"epoch": 0.7,
"learning_rate": 0.00016523423091110293,
"loss": 1.1469,
"step": 3770
},
{
"epoch": 0.7,
"learning_rate": 0.0001651420140169679,
"loss": 1.2593,
"step": 3780
},
{
"epoch": 0.7,
"learning_rate": 0.0001650497971228329,
"loss": 1.1924,
"step": 3790
},
{
"epoch": 0.7,
"learning_rate": 0.0001649575802286979,
"loss": 1.1856,
"step": 3800
},
{
"epoch": 0.7,
"learning_rate": 0.00016486536333456292,
"loss": 1.2306,
"step": 3810
},
{
"epoch": 0.7,
"learning_rate": 0.0001647731464404279,
"loss": 1.2943,
"step": 3820
},
{
"epoch": 0.71,
"learning_rate": 0.00016468092954629289,
"loss": 1.1842,
"step": 3830
},
{
"epoch": 0.71,
"learning_rate": 0.00016458871265215787,
"loss": 1.322,
"step": 3840
},
{
"epoch": 0.71,
"learning_rate": 0.00016449649575802288,
"loss": 1.1888,
"step": 3850
},
{
"epoch": 0.71,
"learning_rate": 0.00016440427886388787,
"loss": 1.1909,
"step": 3860
},
{
"epoch": 0.71,
"learning_rate": 0.00016431206196975285,
"loss": 1.2228,
"step": 3870
},
{
"epoch": 0.72,
"learning_rate": 0.00016421984507561786,
"loss": 1.1169,
"step": 3880
},
{
"epoch": 0.72,
"learning_rate": 0.00016412762818148287,
"loss": 1.2129,
"step": 3890
},
{
"epoch": 0.72,
"learning_rate": 0.00016403541128734786,
"loss": 1.2108,
"step": 3900
},
{
"epoch": 0.72,
"learning_rate": 0.00016394319439321284,
"loss": 1.3192,
"step": 3910
},
{
"epoch": 0.72,
"learning_rate": 0.00016385097749907783,
"loss": 1.11,
"step": 3920
},
{
"epoch": 0.72,
"learning_rate": 0.00016375876060494284,
"loss": 1.1571,
"step": 3930
},
{
"epoch": 0.73,
"learning_rate": 0.00016366654371080782,
"loss": 1.2533,
"step": 3940
},
{
"epoch": 0.73,
"learning_rate": 0.0001635743268166728,
"loss": 1.0954,
"step": 3950
},
{
"epoch": 0.73,
"learning_rate": 0.00016348210992253782,
"loss": 1.1373,
"step": 3960
},
{
"epoch": 0.73,
"learning_rate": 0.00016338989302840283,
"loss": 1.1435,
"step": 3970
},
{
"epoch": 0.73,
"learning_rate": 0.00016329767613426782,
"loss": 1.1704,
"step": 3980
},
{
"epoch": 0.74,
"learning_rate": 0.0001632054592401328,
"loss": 1.0662,
"step": 3990
},
{
"epoch": 0.74,
"learning_rate": 0.00016311324234599778,
"loss": 1.3121,
"step": 4000
},
{
"epoch": 0.74,
"eval_accuracy": 0.49945225488406064,
"eval_loss": 1.1661431789398193,
"eval_runtime": 98.5644,
"eval_samples_per_second": 111.135,
"eval_steps_per_second": 13.9,
"step": 4000
},
{
"epoch": 0.74,
"learning_rate": 0.0001630210254518628,
"loss": 1.2862,
"step": 4010
},
{
"epoch": 0.74,
"learning_rate": 0.00016292880855772778,
"loss": 1.2184,
"step": 4020
},
{
"epoch": 0.74,
"learning_rate": 0.00016283659166359276,
"loss": 1.1609,
"step": 4030
},
{
"epoch": 0.75,
"learning_rate": 0.00016274437476945778,
"loss": 1.1033,
"step": 4040
},
{
"epoch": 0.75,
"learning_rate": 0.0001626521578753228,
"loss": 1.1446,
"step": 4050
},
{
"epoch": 0.75,
"learning_rate": 0.00016255994098118777,
"loss": 1.2345,
"step": 4060
},
{
"epoch": 0.75,
"learning_rate": 0.00016246772408705276,
"loss": 1.1732,
"step": 4070
},
{
"epoch": 0.75,
"learning_rate": 0.00016237550719291774,
"loss": 1.2738,
"step": 4080
},
{
"epoch": 0.75,
"learning_rate": 0.00016228329029878275,
"loss": 1.2372,
"step": 4090
},
{
"epoch": 0.76,
"learning_rate": 0.00016219107340464774,
"loss": 1.142,
"step": 4100
},
{
"epoch": 0.76,
"learning_rate": 0.00016209885651051272,
"loss": 1.277,
"step": 4110
},
{
"epoch": 0.76,
"learning_rate": 0.00016200663961637773,
"loss": 1.1757,
"step": 4120
},
{
"epoch": 0.76,
"learning_rate": 0.00016191442272224274,
"loss": 1.239,
"step": 4130
},
{
"epoch": 0.76,
"learning_rate": 0.00016182220582810773,
"loss": 1.1598,
"step": 4140
},
{
"epoch": 0.77,
"learning_rate": 0.0001617299889339727,
"loss": 1.2175,
"step": 4150
},
{
"epoch": 0.77,
"learning_rate": 0.0001616377720398377,
"loss": 1.1578,
"step": 4160
},
{
"epoch": 0.77,
"learning_rate": 0.0001615455551457027,
"loss": 1.2052,
"step": 4170
},
{
"epoch": 0.77,
"learning_rate": 0.0001614533382515677,
"loss": 1.1283,
"step": 4180
},
{
"epoch": 0.77,
"learning_rate": 0.00016136112135743268,
"loss": 1.233,
"step": 4190
},
{
"epoch": 0.77,
"learning_rate": 0.0001612689044632977,
"loss": 1.1148,
"step": 4200
},
{
"epoch": 0.78,
"learning_rate": 0.0001611766875691627,
"loss": 1.1895,
"step": 4210
},
{
"epoch": 0.78,
"learning_rate": 0.00016108447067502768,
"loss": 1.3549,
"step": 4220
},
{
"epoch": 0.78,
"learning_rate": 0.00016099225378089267,
"loss": 1.2073,
"step": 4230
},
{
"epoch": 0.78,
"learning_rate": 0.00016090003688675765,
"loss": 1.194,
"step": 4240
},
{
"epoch": 0.78,
"learning_rate": 0.00016080781999262267,
"loss": 1.2183,
"step": 4250
},
{
"epoch": 0.79,
"learning_rate": 0.00016071560309848765,
"loss": 1.2088,
"step": 4260
},
{
"epoch": 0.79,
"learning_rate": 0.00016062338620435263,
"loss": 1.3126,
"step": 4270
},
{
"epoch": 0.79,
"learning_rate": 0.00016053116931021765,
"loss": 1.2154,
"step": 4280
},
{
"epoch": 0.79,
"learning_rate": 0.00016043895241608266,
"loss": 1.1869,
"step": 4290
},
{
"epoch": 0.79,
"learning_rate": 0.00016034673552194764,
"loss": 1.1124,
"step": 4300
},
{
"epoch": 0.79,
"learning_rate": 0.00016025451862781263,
"loss": 1.1789,
"step": 4310
},
{
"epoch": 0.8,
"learning_rate": 0.0001601623017336776,
"loss": 1.1254,
"step": 4320
},
{
"epoch": 0.8,
"learning_rate": 0.00016007008483954262,
"loss": 1.3232,
"step": 4330
},
{
"epoch": 0.8,
"learning_rate": 0.0001599778679454076,
"loss": 1.1419,
"step": 4340
},
{
"epoch": 0.8,
"learning_rate": 0.0001598856510512726,
"loss": 1.2861,
"step": 4350
},
{
"epoch": 0.8,
"learning_rate": 0.0001597934341571376,
"loss": 1.1492,
"step": 4360
},
{
"epoch": 0.81,
"learning_rate": 0.0001597012172630026,
"loss": 1.2304,
"step": 4370
},
{
"epoch": 0.81,
"learning_rate": 0.0001596090003688676,
"loss": 1.2289,
"step": 4380
},
{
"epoch": 0.81,
"learning_rate": 0.00015951678347473258,
"loss": 1.1479,
"step": 4390
},
{
"epoch": 0.81,
"learning_rate": 0.00015942456658059757,
"loss": 1.222,
"step": 4400
},
{
"epoch": 0.81,
"learning_rate": 0.00015933234968646258,
"loss": 1.105,
"step": 4410
},
{
"epoch": 0.82,
"learning_rate": 0.00015924013279232756,
"loss": 1.1094,
"step": 4420
},
{
"epoch": 0.82,
"learning_rate": 0.00015914791589819255,
"loss": 1.0859,
"step": 4430
},
{
"epoch": 0.82,
"learning_rate": 0.00015905569900405756,
"loss": 1.2148,
"step": 4440
},
{
"epoch": 0.82,
"learning_rate": 0.00015896348210992254,
"loss": 1.2015,
"step": 4450
},
{
"epoch": 0.82,
"learning_rate": 0.00015887126521578755,
"loss": 1.0869,
"step": 4460
},
{
"epoch": 0.82,
"learning_rate": 0.00015877904832165254,
"loss": 1.2852,
"step": 4470
},
{
"epoch": 0.83,
"learning_rate": 0.00015868683142751752,
"loss": 1.14,
"step": 4480
},
{
"epoch": 0.83,
"learning_rate": 0.0001585946145333825,
"loss": 1.2118,
"step": 4490
},
{
"epoch": 0.83,
"learning_rate": 0.00015850239763924752,
"loss": 1.1661,
"step": 4500
},
{
"epoch": 0.83,
"learning_rate": 0.0001584101807451125,
"loss": 1.07,
"step": 4510
},
{
"epoch": 0.83,
"learning_rate": 0.00015831796385097752,
"loss": 1.1214,
"step": 4520
},
{
"epoch": 0.84,
"learning_rate": 0.0001582257469568425,
"loss": 1.285,
"step": 4530
},
{
"epoch": 0.84,
"learning_rate": 0.0001581335300627075,
"loss": 1.1742,
"step": 4540
},
{
"epoch": 0.84,
"learning_rate": 0.0001580413131685725,
"loss": 1.1425,
"step": 4550
},
{
"epoch": 0.84,
"learning_rate": 0.00015794909627443748,
"loss": 1.0878,
"step": 4560
},
{
"epoch": 0.84,
"learning_rate": 0.00015785687938030246,
"loss": 1.2311,
"step": 4570
},
{
"epoch": 0.84,
"learning_rate": 0.00015776466248616748,
"loss": 1.1238,
"step": 4580
},
{
"epoch": 0.85,
"learning_rate": 0.00015767244559203246,
"loss": 1.0743,
"step": 4590
},
{
"epoch": 0.85,
"learning_rate": 0.00015758022869789747,
"loss": 1.0789,
"step": 4600
},
{
"epoch": 0.85,
"learning_rate": 0.00015748801180376246,
"loss": 1.1919,
"step": 4610
},
{
"epoch": 0.85,
"learning_rate": 0.00015739579490962747,
"loss": 1.1697,
"step": 4620
},
{
"epoch": 0.85,
"learning_rate": 0.00015730357801549245,
"loss": 1.2384,
"step": 4630
},
{
"epoch": 0.86,
"learning_rate": 0.00015721136112135744,
"loss": 1.1858,
"step": 4640
},
{
"epoch": 0.86,
"learning_rate": 0.00015711914422722242,
"loss": 1.1766,
"step": 4650
},
{
"epoch": 0.86,
"learning_rate": 0.00015702692733308743,
"loss": 1.0852,
"step": 4660
},
{
"epoch": 0.86,
"learning_rate": 0.00015693471043895242,
"loss": 1.1499,
"step": 4670
},
{
"epoch": 0.86,
"learning_rate": 0.00015684249354481743,
"loss": 1.2804,
"step": 4680
},
{
"epoch": 0.86,
"learning_rate": 0.0001567502766506824,
"loss": 1.2195,
"step": 4690
},
{
"epoch": 0.87,
"learning_rate": 0.00015665805975654742,
"loss": 1.1809,
"step": 4700
},
{
"epoch": 0.87,
"learning_rate": 0.0001565658428624124,
"loss": 1.2306,
"step": 4710
},
{
"epoch": 0.87,
"learning_rate": 0.0001564736259682774,
"loss": 1.1516,
"step": 4720
},
{
"epoch": 0.87,
"learning_rate": 0.00015638140907414238,
"loss": 1.1354,
"step": 4730
},
{
"epoch": 0.87,
"learning_rate": 0.0001562891921800074,
"loss": 1.1047,
"step": 4740
},
{
"epoch": 0.88,
"learning_rate": 0.00015619697528587237,
"loss": 1.1401,
"step": 4750
},
{
"epoch": 0.88,
"learning_rate": 0.00015610475839173736,
"loss": 1.1011,
"step": 4760
},
{
"epoch": 0.88,
"learning_rate": 0.00015601254149760237,
"loss": 1.0627,
"step": 4770
},
{
"epoch": 0.88,
"learning_rate": 0.00015592032460346738,
"loss": 1.2008,
"step": 4780
},
{
"epoch": 0.88,
"learning_rate": 0.00015582810770933237,
"loss": 1.0876,
"step": 4790
},
{
"epoch": 0.89,
"learning_rate": 0.00015573589081519735,
"loss": 1.2179,
"step": 4800
},
{
"epoch": 0.89,
"learning_rate": 0.00015564367392106233,
"loss": 1.1274,
"step": 4810
},
{
"epoch": 0.89,
"learning_rate": 0.00015555145702692735,
"loss": 1.2143,
"step": 4820
},
{
"epoch": 0.89,
"learning_rate": 0.00015545924013279233,
"loss": 1.264,
"step": 4830
},
{
"epoch": 0.89,
"learning_rate": 0.00015536702323865731,
"loss": 1.0355,
"step": 4840
},
{
"epoch": 0.89,
"learning_rate": 0.00015527480634452233,
"loss": 1.1883,
"step": 4850
},
{
"epoch": 0.9,
"learning_rate": 0.00015518258945038734,
"loss": 1.151,
"step": 4860
},
{
"epoch": 0.9,
"learning_rate": 0.00015509037255625232,
"loss": 1.1937,
"step": 4870
},
{
"epoch": 0.9,
"learning_rate": 0.0001549981556621173,
"loss": 1.1426,
"step": 4880
},
{
"epoch": 0.9,
"learning_rate": 0.0001549059387679823,
"loss": 1.1356,
"step": 4890
},
{
"epoch": 0.9,
"learning_rate": 0.0001548137218738473,
"loss": 1.0953,
"step": 4900
},
{
"epoch": 0.91,
"learning_rate": 0.0001547215049797123,
"loss": 1.2168,
"step": 4910
},
{
"epoch": 0.91,
"learning_rate": 0.00015462928808557727,
"loss": 1.2641,
"step": 4920
},
{
"epoch": 0.91,
"learning_rate": 0.00015453707119144228,
"loss": 0.9988,
"step": 4930
},
{
"epoch": 0.91,
"learning_rate": 0.0001544448542973073,
"loss": 1.2423,
"step": 4940
},
{
"epoch": 0.91,
"learning_rate": 0.00015435263740317228,
"loss": 1.1201,
"step": 4950
},
{
"epoch": 0.91,
"learning_rate": 0.00015426042050903726,
"loss": 1.1261,
"step": 4960
},
{
"epoch": 0.92,
"learning_rate": 0.00015416820361490225,
"loss": 1.1374,
"step": 4970
},
{
"epoch": 0.92,
"learning_rate": 0.00015407598672076726,
"loss": 0.9945,
"step": 4980
},
{
"epoch": 0.92,
"learning_rate": 0.00015398376982663224,
"loss": 1.1362,
"step": 4990
},
{
"epoch": 0.92,
"learning_rate": 0.00015389155293249723,
"loss": 1.1806,
"step": 5000
},
{
"epoch": 0.92,
"eval_accuracy": 0.5240094942486763,
"eval_loss": 1.1137409210205078,
"eval_runtime": 98.12,
"eval_samples_per_second": 111.639,
"eval_steps_per_second": 13.963,
"step": 5000
},
{
"epoch": 0.92,
"learning_rate": 0.00015379933603836224,
"loss": 1.1386,
"step": 5010
},
{
"epoch": 0.93,
"learning_rate": 0.00015370711914422725,
"loss": 1.129,
"step": 5020
},
{
"epoch": 0.93,
"learning_rate": 0.00015361490225009223,
"loss": 1.1191,
"step": 5030
},
{
"epoch": 0.93,
"learning_rate": 0.00015352268535595722,
"loss": 1.2112,
"step": 5040
},
{
"epoch": 0.93,
"learning_rate": 0.0001534304684618222,
"loss": 1.0587,
"step": 5050
},
{
"epoch": 0.93,
"learning_rate": 0.0001533382515676872,
"loss": 1.2067,
"step": 5060
},
{
"epoch": 0.94,
"learning_rate": 0.0001532460346735522,
"loss": 1.1811,
"step": 5070
},
{
"epoch": 0.94,
"learning_rate": 0.00015315381777941718,
"loss": 1.1983,
"step": 5080
},
{
"epoch": 0.94,
"learning_rate": 0.0001530616008852822,
"loss": 1.2142,
"step": 5090
},
{
"epoch": 0.94,
"learning_rate": 0.00015296938399114718,
"loss": 1.1877,
"step": 5100
},
{
"epoch": 0.94,
"learning_rate": 0.0001528771670970122,
"loss": 1.1208,
"step": 5110
},
{
"epoch": 0.94,
"learning_rate": 0.00015278495020287718,
"loss": 1.2037,
"step": 5120
},
{
"epoch": 0.95,
"learning_rate": 0.00015269273330874216,
"loss": 1.0518,
"step": 5130
},
{
"epoch": 0.95,
"learning_rate": 0.00015260051641460714,
"loss": 1.1385,
"step": 5140
},
{
"epoch": 0.95,
"learning_rate": 0.00015250829952047216,
"loss": 1.2212,
"step": 5150
},
{
"epoch": 0.95,
"learning_rate": 0.00015241608262633714,
"loss": 1.2147,
"step": 5160
},
{
"epoch": 0.95,
"learning_rate": 0.00015232386573220215,
"loss": 1.0961,
"step": 5170
},
{
"epoch": 0.96,
"learning_rate": 0.00015223164883806714,
"loss": 1.1507,
"step": 5180
},
{
"epoch": 0.96,
"learning_rate": 0.00015213943194393215,
"loss": 1.2598,
"step": 5190
},
{
"epoch": 0.96,
"learning_rate": 0.00015204721504979713,
"loss": 1.1551,
"step": 5200
},
{
"epoch": 0.96,
"learning_rate": 0.00015195499815566212,
"loss": 1.3621,
"step": 5210
},
{
"epoch": 0.96,
"learning_rate": 0.0001518627812615271,
"loss": 1.1444,
"step": 5220
},
{
"epoch": 0.96,
"learning_rate": 0.0001517705643673921,
"loss": 1.1967,
"step": 5230
},
{
"epoch": 0.97,
"learning_rate": 0.0001516783474732571,
"loss": 1.1623,
"step": 5240
},
{
"epoch": 0.97,
"learning_rate": 0.0001515861305791221,
"loss": 1.1205,
"step": 5250
},
{
"epoch": 0.97,
"learning_rate": 0.0001514939136849871,
"loss": 1.0907,
"step": 5260
},
{
"epoch": 0.97,
"learning_rate": 0.0001514016967908521,
"loss": 1.0634,
"step": 5270
},
{
"epoch": 0.97,
"learning_rate": 0.0001513094798967171,
"loss": 1.1764,
"step": 5280
},
{
"epoch": 0.98,
"learning_rate": 0.00015121726300258207,
"loss": 1.169,
"step": 5290
},
{
"epoch": 0.98,
"learning_rate": 0.00015112504610844706,
"loss": 1.0883,
"step": 5300
},
{
"epoch": 0.98,
"learning_rate": 0.00015103282921431207,
"loss": 1.2949,
"step": 5310
},
{
"epoch": 0.98,
"learning_rate": 0.00015094061232017705,
"loss": 1.1286,
"step": 5320
},
{
"epoch": 0.98,
"learning_rate": 0.00015084839542604207,
"loss": 1.08,
"step": 5330
},
{
"epoch": 0.98,
"learning_rate": 0.00015075617853190705,
"loss": 1.146,
"step": 5340
},
{
"epoch": 0.99,
"learning_rate": 0.00015066396163777206,
"loss": 1.2019,
"step": 5350
},
{
"epoch": 0.99,
"learning_rate": 0.00015057174474363705,
"loss": 1.1424,
"step": 5360
},
{
"epoch": 0.99,
"learning_rate": 0.00015047952784950203,
"loss": 1.114,
"step": 5370
},
{
"epoch": 0.99,
"learning_rate": 0.00015038731095536701,
"loss": 1.1133,
"step": 5380
},
{
"epoch": 0.99,
"learning_rate": 0.00015029509406123203,
"loss": 1.1234,
"step": 5390
},
{
"epoch": 1.0,
"learning_rate": 0.000150202877167097,
"loss": 1.2356,
"step": 5400
},
{
"epoch": 1.0,
"learning_rate": 0.00015011066027296202,
"loss": 1.2222,
"step": 5410
},
{
"epoch": 1.0,
"learning_rate": 0.000150018443378827,
"loss": 1.1921,
"step": 5420
},
{
"epoch": 1.0,
"learning_rate": 0.00014992622648469202,
"loss": 1.1302,
"step": 5430
},
{
"epoch": 1.0,
"learning_rate": 0.000149834009590557,
"loss": 1.1424,
"step": 5440
},
{
"epoch": 1.01,
"learning_rate": 0.000149741792696422,
"loss": 1.1571,
"step": 5450
},
{
"epoch": 1.01,
"learning_rate": 0.00014964957580228697,
"loss": 1.0979,
"step": 5460
},
{
"epoch": 1.01,
"learning_rate": 0.00014955735890815198,
"loss": 1.0564,
"step": 5470
},
{
"epoch": 1.01,
"learning_rate": 0.00014946514201401697,
"loss": 1.007,
"step": 5480
},
{
"epoch": 1.01,
"learning_rate": 0.00014937292511988198,
"loss": 1.2216,
"step": 5490
},
{
"epoch": 1.01,
"learning_rate": 0.00014928070822574696,
"loss": 0.9655,
"step": 5500
},
{
"epoch": 1.02,
"learning_rate": 0.00014918849133161197,
"loss": 0.9971,
"step": 5510
},
{
"epoch": 1.02,
"learning_rate": 0.00014909627443747696,
"loss": 1.0476,
"step": 5520
},
{
"epoch": 1.02,
"learning_rate": 0.00014900405754334194,
"loss": 1.0946,
"step": 5530
},
{
"epoch": 1.02,
"learning_rate": 0.00014891184064920693,
"loss": 1.128,
"step": 5540
},
{
"epoch": 1.02,
"learning_rate": 0.00014881962375507194,
"loss": 1.124,
"step": 5550
},
{
"epoch": 1.03,
"learning_rate": 0.00014872740686093692,
"loss": 1.0277,
"step": 5560
},
{
"epoch": 1.03,
"learning_rate": 0.00014863518996680193,
"loss": 1.2334,
"step": 5570
},
{
"epoch": 1.03,
"learning_rate": 0.00014854297307266692,
"loss": 0.9921,
"step": 5580
},
{
"epoch": 1.03,
"learning_rate": 0.00014845075617853193,
"loss": 1.0135,
"step": 5590
},
{
"epoch": 1.03,
"learning_rate": 0.00014835853928439692,
"loss": 1.0203,
"step": 5600
},
{
"epoch": 1.03,
"learning_rate": 0.0001482663223902619,
"loss": 1.0778,
"step": 5610
},
{
"epoch": 1.04,
"learning_rate": 0.00014817410549612688,
"loss": 1.0985,
"step": 5620
},
{
"epoch": 1.04,
"learning_rate": 0.0001480818886019919,
"loss": 1.1,
"step": 5630
},
{
"epoch": 1.04,
"learning_rate": 0.00014798967170785688,
"loss": 1.1413,
"step": 5640
},
{
"epoch": 1.04,
"learning_rate": 0.0001478974548137219,
"loss": 1.0165,
"step": 5650
},
{
"epoch": 1.04,
"learning_rate": 0.00014780523791958688,
"loss": 1.0329,
"step": 5660
},
{
"epoch": 1.05,
"learning_rate": 0.0001477130210254519,
"loss": 1.0341,
"step": 5670
},
{
"epoch": 1.05,
"learning_rate": 0.00014762080413131687,
"loss": 0.9721,
"step": 5680
},
{
"epoch": 1.05,
"learning_rate": 0.00014752858723718186,
"loss": 1.1558,
"step": 5690
},
{
"epoch": 1.05,
"learning_rate": 0.00014743637034304684,
"loss": 1.0964,
"step": 5700
},
{
"epoch": 1.05,
"learning_rate": 0.00014734415344891183,
"loss": 0.9984,
"step": 5710
},
{
"epoch": 1.05,
"learning_rate": 0.00014725193655477684,
"loss": 1.1214,
"step": 5720
},
{
"epoch": 1.06,
"learning_rate": 0.00014715971966064185,
"loss": 1.0954,
"step": 5730
},
{
"epoch": 1.06,
"learning_rate": 0.00014706750276650683,
"loss": 1.0381,
"step": 5740
},
{
"epoch": 1.06,
"learning_rate": 0.00014697528587237182,
"loss": 1.0516,
"step": 5750
},
{
"epoch": 1.06,
"learning_rate": 0.00014688306897823683,
"loss": 1.1157,
"step": 5760
},
{
"epoch": 1.06,
"learning_rate": 0.0001467908520841018,
"loss": 0.9874,
"step": 5770
},
{
"epoch": 1.07,
"learning_rate": 0.0001466986351899668,
"loss": 1.0634,
"step": 5780
},
{
"epoch": 1.07,
"learning_rate": 0.00014660641829583178,
"loss": 1.1058,
"step": 5790
},
{
"epoch": 1.07,
"learning_rate": 0.0001465142014016968,
"loss": 1.0966,
"step": 5800
},
{
"epoch": 1.07,
"learning_rate": 0.0001464219845075618,
"loss": 1.0457,
"step": 5810
},
{
"epoch": 1.07,
"learning_rate": 0.0001463297676134268,
"loss": 1.1258,
"step": 5820
},
{
"epoch": 1.08,
"learning_rate": 0.00014623755071929177,
"loss": 1.1258,
"step": 5830
},
{
"epoch": 1.08,
"learning_rate": 0.00014614533382515679,
"loss": 1.2046,
"step": 5840
},
{
"epoch": 1.08,
"learning_rate": 0.00014605311693102177,
"loss": 1.0688,
"step": 5850
},
{
"epoch": 1.08,
"learning_rate": 0.00014596090003688675,
"loss": 0.9497,
"step": 5860
},
{
"epoch": 1.08,
"learning_rate": 0.00014586868314275174,
"loss": 1.1829,
"step": 5870
},
{
"epoch": 1.08,
"learning_rate": 0.00014577646624861675,
"loss": 1.1155,
"step": 5880
},
{
"epoch": 1.09,
"learning_rate": 0.00014568424935448176,
"loss": 1.1273,
"step": 5890
},
{
"epoch": 1.09,
"learning_rate": 0.00014559203246034675,
"loss": 1.011,
"step": 5900
},
{
"epoch": 1.09,
"learning_rate": 0.00014549981556621173,
"loss": 1.081,
"step": 5910
},
{
"epoch": 1.09,
"learning_rate": 0.00014540759867207674,
"loss": 1.041,
"step": 5920
},
{
"epoch": 1.09,
"learning_rate": 0.00014531538177794173,
"loss": 1.1286,
"step": 5930
},
{
"epoch": 1.1,
"learning_rate": 0.0001452231648838067,
"loss": 0.9914,
"step": 5940
},
{
"epoch": 1.1,
"learning_rate": 0.0001451309479896717,
"loss": 1.0105,
"step": 5950
},
{
"epoch": 1.1,
"learning_rate": 0.0001450387310955367,
"loss": 1.0517,
"step": 5960
},
{
"epoch": 1.1,
"learning_rate": 0.00014494651420140172,
"loss": 1.0245,
"step": 5970
},
{
"epoch": 1.1,
"learning_rate": 0.0001448542973072667,
"loss": 1.0713,
"step": 5980
},
{
"epoch": 1.1,
"learning_rate": 0.0001447620804131317,
"loss": 1.0638,
"step": 5990
},
{
"epoch": 1.11,
"learning_rate": 0.0001446698635189967,
"loss": 1.0839,
"step": 6000
},
{
"epoch": 1.11,
"eval_accuracy": 0.5164323534781815,
"eval_loss": 1.1340410709381104,
"eval_runtime": 98.4525,
"eval_samples_per_second": 111.262,
"eval_steps_per_second": 13.915,
"step": 6000
},
{
"epoch": 1.11,
"step": 6000,
"total_flos": 2.0396723395200123e+18,
"train_loss": 1.29178360859553,
"train_runtime": 1561.0386,
"train_samples_per_second": 222.273,
"train_steps_per_second": 13.893
}
],
"logging_steps": 10,
"max_steps": 21688,
"num_train_epochs": 4,
"save_steps": 1000,
"total_flos": 2.0396723395200123e+18,
"trial_name": null,
"trial_params": null
}