Gokulapriyan's picture
End of training
e312edf
raw
history blame contribute delete
No virus
163 kB
{
"best_metric": 0.9785714285714285,
"best_model_checkpoint": "convnext-tiny-224-finetuned-og-dataset-10e\\checkpoint-13230",
"epoch": 5.999886634168462,
"global_step": 13230,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 3.779289493575208e-07,
"loss": 1.4165,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 7.558578987150416e-07,
"loss": 1.422,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 1.1337868480725623e-06,
"loss": 1.4122,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 1.5117157974300832e-06,
"loss": 1.4263,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 1.889644746787604e-06,
"loss": 1.4158,
"step": 50
},
{
"epoch": 0.03,
"learning_rate": 2.2675736961451247e-06,
"loss": 1.3689,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 2.6455026455026455e-06,
"loss": 1.3668,
"step": 70
},
{
"epoch": 0.04,
"learning_rate": 3.0234315948601664e-06,
"loss": 1.3647,
"step": 80
},
{
"epoch": 0.04,
"learning_rate": 3.4013605442176877e-06,
"loss": 1.3373,
"step": 90
},
{
"epoch": 0.05,
"learning_rate": 3.779289493575208e-06,
"loss": 1.3401,
"step": 100
},
{
"epoch": 0.05,
"learning_rate": 4.1572184429327285e-06,
"loss": 1.322,
"step": 110
},
{
"epoch": 0.05,
"learning_rate": 4.535147392290249e-06,
"loss": 1.2856,
"step": 120
},
{
"epoch": 0.06,
"learning_rate": 4.91307634164777e-06,
"loss": 1.2601,
"step": 130
},
{
"epoch": 0.06,
"learning_rate": 5.291005291005291e-06,
"loss": 1.2524,
"step": 140
},
{
"epoch": 0.07,
"learning_rate": 5.668934240362813e-06,
"loss": 1.2537,
"step": 150
},
{
"epoch": 0.07,
"learning_rate": 6.046863189720333e-06,
"loss": 1.2033,
"step": 160
},
{
"epoch": 0.08,
"learning_rate": 6.424792139077854e-06,
"loss": 1.1801,
"step": 170
},
{
"epoch": 0.08,
"learning_rate": 6.802721088435375e-06,
"loss": 1.1386,
"step": 180
},
{
"epoch": 0.09,
"learning_rate": 7.180650037792895e-06,
"loss": 1.1062,
"step": 190
},
{
"epoch": 0.09,
"learning_rate": 7.558578987150416e-06,
"loss": 1.077,
"step": 200
},
{
"epoch": 0.1,
"learning_rate": 7.936507936507936e-06,
"loss": 1.1027,
"step": 210
},
{
"epoch": 0.1,
"learning_rate": 8.314436885865457e-06,
"loss": 1.0604,
"step": 220
},
{
"epoch": 0.1,
"learning_rate": 8.692365835222978e-06,
"loss": 1.0174,
"step": 230
},
{
"epoch": 0.11,
"learning_rate": 9.070294784580499e-06,
"loss": 0.9599,
"step": 240
},
{
"epoch": 0.11,
"learning_rate": 9.448223733938021e-06,
"loss": 0.9752,
"step": 250
},
{
"epoch": 0.12,
"learning_rate": 9.82615268329554e-06,
"loss": 0.9598,
"step": 260
},
{
"epoch": 0.12,
"learning_rate": 1.0204081632653061e-05,
"loss": 0.9273,
"step": 270
},
{
"epoch": 0.13,
"learning_rate": 1.0582010582010582e-05,
"loss": 0.8762,
"step": 280
},
{
"epoch": 0.13,
"learning_rate": 1.0959939531368103e-05,
"loss": 0.8925,
"step": 290
},
{
"epoch": 0.14,
"learning_rate": 1.1337868480725626e-05,
"loss": 0.9003,
"step": 300
},
{
"epoch": 0.14,
"learning_rate": 1.1715797430083145e-05,
"loss": 0.8555,
"step": 310
},
{
"epoch": 0.15,
"learning_rate": 1.2093726379440666e-05,
"loss": 0.8415,
"step": 320
},
{
"epoch": 0.15,
"learning_rate": 1.2471655328798186e-05,
"loss": 0.8507,
"step": 330
},
{
"epoch": 0.15,
"learning_rate": 1.2849584278155707e-05,
"loss": 0.867,
"step": 340
},
{
"epoch": 0.16,
"learning_rate": 1.3227513227513228e-05,
"loss": 0.8274,
"step": 350
},
{
"epoch": 0.16,
"learning_rate": 1.360544217687075e-05,
"loss": 0.807,
"step": 360
},
{
"epoch": 0.17,
"learning_rate": 1.398337112622827e-05,
"loss": 0.8265,
"step": 370
},
{
"epoch": 0.17,
"learning_rate": 1.436130007558579e-05,
"loss": 0.8393,
"step": 380
},
{
"epoch": 0.18,
"learning_rate": 1.473922902494331e-05,
"loss": 0.797,
"step": 390
},
{
"epoch": 0.18,
"learning_rate": 1.5117157974300832e-05,
"loss": 0.8265,
"step": 400
},
{
"epoch": 0.19,
"learning_rate": 1.549508692365835e-05,
"loss": 0.7635,
"step": 410
},
{
"epoch": 0.19,
"learning_rate": 1.5873015873015872e-05,
"loss": 0.7794,
"step": 420
},
{
"epoch": 0.19,
"learning_rate": 1.6250944822373397e-05,
"loss": 0.7555,
"step": 430
},
{
"epoch": 0.2,
"learning_rate": 1.6628873771730914e-05,
"loss": 0.7735,
"step": 440
},
{
"epoch": 0.2,
"learning_rate": 1.7006802721088435e-05,
"loss": 0.7754,
"step": 450
},
{
"epoch": 0.21,
"learning_rate": 1.7384731670445956e-05,
"loss": 0.7319,
"step": 460
},
{
"epoch": 0.21,
"learning_rate": 1.776266061980348e-05,
"loss": 0.7594,
"step": 470
},
{
"epoch": 0.22,
"learning_rate": 1.8140589569160997e-05,
"loss": 0.7585,
"step": 480
},
{
"epoch": 0.22,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.729,
"step": 490
},
{
"epoch": 0.23,
"learning_rate": 1.8896447467876043e-05,
"loss": 0.7032,
"step": 500
},
{
"epoch": 0.23,
"learning_rate": 1.927437641723356e-05,
"loss": 0.7284,
"step": 510
},
{
"epoch": 0.24,
"learning_rate": 1.965230536659108e-05,
"loss": 0.7526,
"step": 520
},
{
"epoch": 0.24,
"learning_rate": 2.0030234315948605e-05,
"loss": 0.7312,
"step": 530
},
{
"epoch": 0.24,
"learning_rate": 2.0408163265306123e-05,
"loss": 0.7246,
"step": 540
},
{
"epoch": 0.25,
"learning_rate": 2.0786092214663643e-05,
"loss": 0.7209,
"step": 550
},
{
"epoch": 0.25,
"learning_rate": 2.1164021164021164e-05,
"loss": 0.7054,
"step": 560
},
{
"epoch": 0.26,
"learning_rate": 2.1541950113378685e-05,
"loss": 0.7114,
"step": 570
},
{
"epoch": 0.26,
"learning_rate": 2.1919879062736206e-05,
"loss": 0.6369,
"step": 580
},
{
"epoch": 0.27,
"learning_rate": 2.2297808012093727e-05,
"loss": 0.7213,
"step": 590
},
{
"epoch": 0.27,
"learning_rate": 2.267573696145125e-05,
"loss": 0.7188,
"step": 600
},
{
"epoch": 0.28,
"learning_rate": 2.305366591080877e-05,
"loss": 0.7079,
"step": 610
},
{
"epoch": 0.28,
"learning_rate": 2.343159486016629e-05,
"loss": 0.6664,
"step": 620
},
{
"epoch": 0.29,
"learning_rate": 2.380952380952381e-05,
"loss": 0.6401,
"step": 630
},
{
"epoch": 0.29,
"learning_rate": 2.418745275888133e-05,
"loss": 0.7459,
"step": 640
},
{
"epoch": 0.29,
"learning_rate": 2.4565381708238852e-05,
"loss": 0.6966,
"step": 650
},
{
"epoch": 0.3,
"learning_rate": 2.4943310657596373e-05,
"loss": 0.6955,
"step": 660
},
{
"epoch": 0.3,
"learning_rate": 2.5321239606953894e-05,
"loss": 0.6823,
"step": 670
},
{
"epoch": 0.31,
"learning_rate": 2.5699168556311414e-05,
"loss": 0.6243,
"step": 680
},
{
"epoch": 0.31,
"learning_rate": 2.6077097505668935e-05,
"loss": 0.7209,
"step": 690
},
{
"epoch": 0.32,
"learning_rate": 2.6455026455026456e-05,
"loss": 0.6517,
"step": 700
},
{
"epoch": 0.32,
"learning_rate": 2.6832955404383974e-05,
"loss": 0.7403,
"step": 710
},
{
"epoch": 0.33,
"learning_rate": 2.72108843537415e-05,
"loss": 0.7303,
"step": 720
},
{
"epoch": 0.33,
"learning_rate": 2.758881330309902e-05,
"loss": 0.6839,
"step": 730
},
{
"epoch": 0.34,
"learning_rate": 2.796674225245654e-05,
"loss": 0.6134,
"step": 740
},
{
"epoch": 0.34,
"learning_rate": 2.834467120181406e-05,
"loss": 0.6677,
"step": 750
},
{
"epoch": 0.34,
"learning_rate": 2.872260015117158e-05,
"loss": 0.6177,
"step": 760
},
{
"epoch": 0.35,
"learning_rate": 2.91005291005291e-05,
"loss": 0.6533,
"step": 770
},
{
"epoch": 0.35,
"learning_rate": 2.947845804988662e-05,
"loss": 0.6245,
"step": 780
},
{
"epoch": 0.36,
"learning_rate": 2.9856386999244147e-05,
"loss": 0.6394,
"step": 790
},
{
"epoch": 0.36,
"learning_rate": 3.0234315948601665e-05,
"loss": 0.6565,
"step": 800
},
{
"epoch": 0.37,
"learning_rate": 3.061224489795919e-05,
"loss": 0.5274,
"step": 810
},
{
"epoch": 0.37,
"learning_rate": 3.09901738473167e-05,
"loss": 0.6378,
"step": 820
},
{
"epoch": 0.38,
"learning_rate": 3.1368102796674224e-05,
"loss": 0.6442,
"step": 830
},
{
"epoch": 0.38,
"learning_rate": 3.1746031746031745e-05,
"loss": 0.6601,
"step": 840
},
{
"epoch": 0.39,
"learning_rate": 3.2123960695389265e-05,
"loss": 0.6273,
"step": 850
},
{
"epoch": 0.39,
"learning_rate": 3.250188964474679e-05,
"loss": 0.6625,
"step": 860
},
{
"epoch": 0.39,
"learning_rate": 3.2879818594104314e-05,
"loss": 0.6033,
"step": 870
},
{
"epoch": 0.4,
"learning_rate": 3.325774754346183e-05,
"loss": 0.627,
"step": 880
},
{
"epoch": 0.4,
"learning_rate": 3.363567649281935e-05,
"loss": 0.5892,
"step": 890
},
{
"epoch": 0.41,
"learning_rate": 3.401360544217687e-05,
"loss": 0.6446,
"step": 900
},
{
"epoch": 0.41,
"learning_rate": 3.439153439153439e-05,
"loss": 0.5716,
"step": 910
},
{
"epoch": 0.42,
"learning_rate": 3.476946334089191e-05,
"loss": 0.6912,
"step": 920
},
{
"epoch": 0.42,
"learning_rate": 3.514739229024944e-05,
"loss": 0.5689,
"step": 930
},
{
"epoch": 0.43,
"learning_rate": 3.552532123960696e-05,
"loss": 0.5738,
"step": 940
},
{
"epoch": 0.43,
"learning_rate": 3.5903250188964474e-05,
"loss": 0.6384,
"step": 950
},
{
"epoch": 0.44,
"learning_rate": 3.6281179138321995e-05,
"loss": 0.6109,
"step": 960
},
{
"epoch": 0.44,
"learning_rate": 3.6659108087679516e-05,
"loss": 0.5934,
"step": 970
},
{
"epoch": 0.44,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.6681,
"step": 980
},
{
"epoch": 0.45,
"learning_rate": 3.7414965986394564e-05,
"loss": 0.5844,
"step": 990
},
{
"epoch": 0.45,
"learning_rate": 3.7792894935752085e-05,
"loss": 0.5806,
"step": 1000
},
{
"epoch": 0.46,
"learning_rate": 3.81708238851096e-05,
"loss": 0.5595,
"step": 1010
},
{
"epoch": 0.46,
"learning_rate": 3.854875283446712e-05,
"loss": 0.5772,
"step": 1020
},
{
"epoch": 0.47,
"learning_rate": 3.892668178382464e-05,
"loss": 0.6216,
"step": 1030
},
{
"epoch": 0.47,
"learning_rate": 3.930461073318216e-05,
"loss": 0.5696,
"step": 1040
},
{
"epoch": 0.48,
"learning_rate": 3.968253968253968e-05,
"loss": 0.5288,
"step": 1050
},
{
"epoch": 0.48,
"learning_rate": 4.006046863189721e-05,
"loss": 0.5692,
"step": 1060
},
{
"epoch": 0.49,
"learning_rate": 4.043839758125473e-05,
"loss": 0.5841,
"step": 1070
},
{
"epoch": 0.49,
"learning_rate": 4.0816326530612245e-05,
"loss": 0.6227,
"step": 1080
},
{
"epoch": 0.49,
"learning_rate": 4.1194255479969766e-05,
"loss": 0.5669,
"step": 1090
},
{
"epoch": 0.5,
"learning_rate": 4.157218442932729e-05,
"loss": 0.5398,
"step": 1100
},
{
"epoch": 0.5,
"learning_rate": 4.195011337868481e-05,
"loss": 0.6483,
"step": 1110
},
{
"epoch": 0.51,
"learning_rate": 4.232804232804233e-05,
"loss": 0.6151,
"step": 1120
},
{
"epoch": 0.51,
"learning_rate": 4.2705971277399856e-05,
"loss": 0.561,
"step": 1130
},
{
"epoch": 0.52,
"learning_rate": 4.308390022675737e-05,
"loss": 0.6134,
"step": 1140
},
{
"epoch": 0.52,
"learning_rate": 4.346182917611489e-05,
"loss": 0.546,
"step": 1150
},
{
"epoch": 0.53,
"learning_rate": 4.383975812547241e-05,
"loss": 0.5949,
"step": 1160
},
{
"epoch": 0.53,
"learning_rate": 4.421768707482993e-05,
"loss": 0.5676,
"step": 1170
},
{
"epoch": 0.54,
"learning_rate": 4.4595616024187454e-05,
"loss": 0.5564,
"step": 1180
},
{
"epoch": 0.54,
"learning_rate": 4.4973544973544974e-05,
"loss": 0.5301,
"step": 1190
},
{
"epoch": 0.54,
"learning_rate": 4.53514739229025e-05,
"loss": 0.4708,
"step": 1200
},
{
"epoch": 0.55,
"learning_rate": 4.5729402872260016e-05,
"loss": 0.5674,
"step": 1210
},
{
"epoch": 0.55,
"learning_rate": 4.610733182161754e-05,
"loss": 0.5213,
"step": 1220
},
{
"epoch": 0.56,
"learning_rate": 4.648526077097506e-05,
"loss": 0.5512,
"step": 1230
},
{
"epoch": 0.56,
"learning_rate": 4.686318972033258e-05,
"loss": 0.5843,
"step": 1240
},
{
"epoch": 0.57,
"learning_rate": 4.72411186696901e-05,
"loss": 0.62,
"step": 1250
},
{
"epoch": 0.57,
"learning_rate": 4.761904761904762e-05,
"loss": 0.5322,
"step": 1260
},
{
"epoch": 0.58,
"learning_rate": 4.799697656840514e-05,
"loss": 0.4994,
"step": 1270
},
{
"epoch": 0.58,
"learning_rate": 4.837490551776266e-05,
"loss": 0.5067,
"step": 1280
},
{
"epoch": 0.58,
"learning_rate": 4.875283446712018e-05,
"loss": 0.5183,
"step": 1290
},
{
"epoch": 0.59,
"learning_rate": 4.9130763416477704e-05,
"loss": 0.5251,
"step": 1300
},
{
"epoch": 0.59,
"learning_rate": 4.9508692365835225e-05,
"loss": 0.4708,
"step": 1310
},
{
"epoch": 0.6,
"learning_rate": 4.9886621315192745e-05,
"loss": 0.5697,
"step": 1320
},
{
"epoch": 0.6,
"learning_rate": 4.9970605526161084e-05,
"loss": 0.4706,
"step": 1330
},
{
"epoch": 0.61,
"learning_rate": 4.992861342067692e-05,
"loss": 0.5122,
"step": 1340
},
{
"epoch": 0.61,
"learning_rate": 4.9886621315192745e-05,
"loss": 0.4892,
"step": 1350
},
{
"epoch": 0.62,
"learning_rate": 4.984462920970858e-05,
"loss": 0.5468,
"step": 1360
},
{
"epoch": 0.62,
"learning_rate": 4.980263710422441e-05,
"loss": 0.5256,
"step": 1370
},
{
"epoch": 0.63,
"learning_rate": 4.976064499874024e-05,
"loss": 0.5246,
"step": 1380
},
{
"epoch": 0.63,
"learning_rate": 4.971865289325607e-05,
"loss": 0.5069,
"step": 1390
},
{
"epoch": 0.63,
"learning_rate": 4.96766607877719e-05,
"loss": 0.4693,
"step": 1400
},
{
"epoch": 0.64,
"learning_rate": 4.9634668682287736e-05,
"loss": 0.5066,
"step": 1410
},
{
"epoch": 0.64,
"learning_rate": 4.959267657680356e-05,
"loss": 0.4981,
"step": 1420
},
{
"epoch": 0.65,
"learning_rate": 4.955068447131939e-05,
"loss": 0.489,
"step": 1430
},
{
"epoch": 0.65,
"learning_rate": 4.9508692365835225e-05,
"loss": 0.4876,
"step": 1440
},
{
"epoch": 0.66,
"learning_rate": 4.946670026035106e-05,
"loss": 0.4718,
"step": 1450
},
{
"epoch": 0.66,
"learning_rate": 4.9424708154866886e-05,
"loss": 0.4818,
"step": 1460
},
{
"epoch": 0.67,
"learning_rate": 4.938271604938271e-05,
"loss": 0.4423,
"step": 1470
},
{
"epoch": 0.67,
"learning_rate": 4.934072394389855e-05,
"loss": 0.4949,
"step": 1480
},
{
"epoch": 0.68,
"learning_rate": 4.929873183841438e-05,
"loss": 0.5366,
"step": 1490
},
{
"epoch": 0.68,
"learning_rate": 4.9256739732930215e-05,
"loss": 0.4482,
"step": 1500
},
{
"epoch": 0.68,
"learning_rate": 4.921474762744604e-05,
"loss": 0.4517,
"step": 1510
},
{
"epoch": 0.69,
"learning_rate": 4.917275552196187e-05,
"loss": 0.4771,
"step": 1520
},
{
"epoch": 0.69,
"learning_rate": 4.9130763416477704e-05,
"loss": 0.5378,
"step": 1530
},
{
"epoch": 0.7,
"learning_rate": 4.908877131099354e-05,
"loss": 0.4747,
"step": 1540
},
{
"epoch": 0.7,
"learning_rate": 4.904677920550937e-05,
"loss": 0.4853,
"step": 1550
},
{
"epoch": 0.71,
"learning_rate": 4.90047871000252e-05,
"loss": 0.4773,
"step": 1560
},
{
"epoch": 0.71,
"learning_rate": 4.8962794994541026e-05,
"loss": 0.5137,
"step": 1570
},
{
"epoch": 0.72,
"learning_rate": 4.892080288905686e-05,
"loss": 0.5007,
"step": 1580
},
{
"epoch": 0.72,
"learning_rate": 4.8878810783572694e-05,
"loss": 0.4381,
"step": 1590
},
{
"epoch": 0.73,
"learning_rate": 4.883681867808852e-05,
"loss": 0.538,
"step": 1600
},
{
"epoch": 0.73,
"learning_rate": 4.879482657260435e-05,
"loss": 0.4259,
"step": 1610
},
{
"epoch": 0.73,
"learning_rate": 4.875283446712018e-05,
"loss": 0.5058,
"step": 1620
},
{
"epoch": 0.74,
"learning_rate": 4.871084236163602e-05,
"loss": 0.4639,
"step": 1630
},
{
"epoch": 0.74,
"learning_rate": 4.8668850256151844e-05,
"loss": 0.4403,
"step": 1640
},
{
"epoch": 0.75,
"learning_rate": 4.862685815066768e-05,
"loss": 0.4005,
"step": 1650
},
{
"epoch": 0.75,
"learning_rate": 4.8584866045183505e-05,
"loss": 0.4838,
"step": 1660
},
{
"epoch": 0.76,
"learning_rate": 4.854287393969934e-05,
"loss": 0.5355,
"step": 1670
},
{
"epoch": 0.76,
"learning_rate": 4.850088183421517e-05,
"loss": 0.4442,
"step": 1680
},
{
"epoch": 0.77,
"learning_rate": 4.8458889728731e-05,
"loss": 0.4494,
"step": 1690
},
{
"epoch": 0.77,
"learning_rate": 4.8416897623246835e-05,
"loss": 0.3887,
"step": 1700
},
{
"epoch": 0.78,
"learning_rate": 4.837490551776266e-05,
"loss": 0.4459,
"step": 1710
},
{
"epoch": 0.78,
"learning_rate": 4.8332913412278496e-05,
"loss": 0.4479,
"step": 1720
},
{
"epoch": 0.78,
"learning_rate": 4.829092130679432e-05,
"loss": 0.4727,
"step": 1730
},
{
"epoch": 0.79,
"learning_rate": 4.824892920131016e-05,
"loss": 0.4005,
"step": 1740
},
{
"epoch": 0.79,
"learning_rate": 4.820693709582599e-05,
"loss": 0.4185,
"step": 1750
},
{
"epoch": 0.8,
"learning_rate": 4.816494499034182e-05,
"loss": 0.3673,
"step": 1760
},
{
"epoch": 0.8,
"learning_rate": 4.8122952884857646e-05,
"loss": 0.3979,
"step": 1770
},
{
"epoch": 0.81,
"learning_rate": 4.808096077937348e-05,
"loss": 0.4585,
"step": 1780
},
{
"epoch": 0.81,
"learning_rate": 4.8038968673889314e-05,
"loss": 0.4774,
"step": 1790
},
{
"epoch": 0.82,
"learning_rate": 4.799697656840514e-05,
"loss": 0.442,
"step": 1800
},
{
"epoch": 0.82,
"learning_rate": 4.795498446292097e-05,
"loss": 0.4968,
"step": 1810
},
{
"epoch": 0.83,
"learning_rate": 4.79129923574368e-05,
"loss": 0.4267,
"step": 1820
},
{
"epoch": 0.83,
"learning_rate": 4.7871000251952637e-05,
"loss": 0.4247,
"step": 1830
},
{
"epoch": 0.83,
"learning_rate": 4.782900814646847e-05,
"loss": 0.4178,
"step": 1840
},
{
"epoch": 0.84,
"learning_rate": 4.77870160409843e-05,
"loss": 0.4372,
"step": 1850
},
{
"epoch": 0.84,
"learning_rate": 4.7745023935500125e-05,
"loss": 0.3706,
"step": 1860
},
{
"epoch": 0.85,
"learning_rate": 4.770303183001596e-05,
"loss": 0.398,
"step": 1870
},
{
"epoch": 0.85,
"learning_rate": 4.766103972453179e-05,
"loss": 0.4691,
"step": 1880
},
{
"epoch": 0.86,
"learning_rate": 4.761904761904762e-05,
"loss": 0.4549,
"step": 1890
},
{
"epoch": 0.86,
"learning_rate": 4.7577055513563454e-05,
"loss": 0.4693,
"step": 1900
},
{
"epoch": 0.87,
"learning_rate": 4.753506340807928e-05,
"loss": 0.444,
"step": 1910
},
{
"epoch": 0.87,
"learning_rate": 4.7493071302595116e-05,
"loss": 0.4401,
"step": 1920
},
{
"epoch": 0.88,
"learning_rate": 4.745107919711095e-05,
"loss": 0.4188,
"step": 1930
},
{
"epoch": 0.88,
"learning_rate": 4.740908709162678e-05,
"loss": 0.4267,
"step": 1940
},
{
"epoch": 0.88,
"learning_rate": 4.7367094986142604e-05,
"loss": 0.4254,
"step": 1950
},
{
"epoch": 0.89,
"learning_rate": 4.732510288065844e-05,
"loss": 0.3607,
"step": 1960
},
{
"epoch": 0.89,
"learning_rate": 4.728311077517427e-05,
"loss": 0.4205,
"step": 1970
},
{
"epoch": 0.9,
"learning_rate": 4.72411186696901e-05,
"loss": 0.4373,
"step": 1980
},
{
"epoch": 0.9,
"learning_rate": 4.7199126564205934e-05,
"loss": 0.4526,
"step": 1990
},
{
"epoch": 0.91,
"learning_rate": 4.715713445872176e-05,
"loss": 0.4346,
"step": 2000
},
{
"epoch": 0.91,
"learning_rate": 4.7115142353237595e-05,
"loss": 0.4045,
"step": 2010
},
{
"epoch": 0.92,
"learning_rate": 4.707315024775342e-05,
"loss": 0.4376,
"step": 2020
},
{
"epoch": 0.92,
"learning_rate": 4.7031158142269256e-05,
"loss": 0.4786,
"step": 2030
},
{
"epoch": 0.93,
"learning_rate": 4.698916603678509e-05,
"loss": 0.4258,
"step": 2040
},
{
"epoch": 0.93,
"learning_rate": 4.694717393130092e-05,
"loss": 0.3977,
"step": 2050
},
{
"epoch": 0.93,
"learning_rate": 4.6905181825816745e-05,
"loss": 0.4299,
"step": 2060
},
{
"epoch": 0.94,
"learning_rate": 4.686318972033258e-05,
"loss": 0.4012,
"step": 2070
},
{
"epoch": 0.94,
"learning_rate": 4.682119761484841e-05,
"loss": 0.3681,
"step": 2080
},
{
"epoch": 0.95,
"learning_rate": 4.677920550936425e-05,
"loss": 0.3386,
"step": 2090
},
{
"epoch": 0.95,
"learning_rate": 4.673721340388007e-05,
"loss": 0.3141,
"step": 2100
},
{
"epoch": 0.96,
"learning_rate": 4.66952212983959e-05,
"loss": 0.3745,
"step": 2110
},
{
"epoch": 0.96,
"learning_rate": 4.6653229192911735e-05,
"loss": 0.3808,
"step": 2120
},
{
"epoch": 0.97,
"learning_rate": 4.661123708742757e-05,
"loss": 0.3737,
"step": 2130
},
{
"epoch": 0.97,
"learning_rate": 4.6569244981943397e-05,
"loss": 0.3756,
"step": 2140
},
{
"epoch": 0.97,
"learning_rate": 4.6527252876459224e-05,
"loss": 0.411,
"step": 2150
},
{
"epoch": 0.98,
"learning_rate": 4.648526077097506e-05,
"loss": 0.3222,
"step": 2160
},
{
"epoch": 0.98,
"learning_rate": 4.644326866549089e-05,
"loss": 0.4328,
"step": 2170
},
{
"epoch": 0.99,
"learning_rate": 4.6401276560006726e-05,
"loss": 0.4091,
"step": 2180
},
{
"epoch": 0.99,
"learning_rate": 4.635928445452255e-05,
"loss": 0.3285,
"step": 2190
},
{
"epoch": 1.0,
"learning_rate": 4.631729234903838e-05,
"loss": 0.3243,
"step": 2200
},
{
"epoch": 1.0,
"eval_accuracy": 0.8909863945578231,
"eval_loss": 0.2716812193393707,
"eval_runtime": 541.5949,
"eval_samples_per_second": 21.714,
"eval_steps_per_second": 2.714,
"step": 2205
},
{
"epoch": 1.0,
"learning_rate": 4.6275300243554214e-05,
"loss": 0.3488,
"step": 2210
},
{
"epoch": 1.01,
"learning_rate": 4.623330813807005e-05,
"loss": 0.3499,
"step": 2220
},
{
"epoch": 1.01,
"learning_rate": 4.6191316032585876e-05,
"loss": 0.3794,
"step": 2230
},
{
"epoch": 1.02,
"learning_rate": 4.614932392710171e-05,
"loss": 0.3982,
"step": 2240
},
{
"epoch": 1.02,
"learning_rate": 4.610733182161754e-05,
"loss": 0.3813,
"step": 2250
},
{
"epoch": 1.02,
"learning_rate": 4.606533971613337e-05,
"loss": 0.4173,
"step": 2260
},
{
"epoch": 1.03,
"learning_rate": 4.60233476106492e-05,
"loss": 0.3497,
"step": 2270
},
{
"epoch": 1.03,
"learning_rate": 4.598135550516503e-05,
"loss": 0.3376,
"step": 2280
},
{
"epoch": 1.04,
"learning_rate": 4.593936339968086e-05,
"loss": 0.4332,
"step": 2290
},
{
"epoch": 1.04,
"learning_rate": 4.5897371294196694e-05,
"loss": 0.3798,
"step": 2300
},
{
"epoch": 1.05,
"learning_rate": 4.585537918871252e-05,
"loss": 0.4159,
"step": 2310
},
{
"epoch": 1.05,
"learning_rate": 4.5813387083228355e-05,
"loss": 0.3364,
"step": 2320
},
{
"epoch": 1.06,
"learning_rate": 4.577139497774419e-05,
"loss": 0.3985,
"step": 2330
},
{
"epoch": 1.06,
"learning_rate": 4.5729402872260016e-05,
"loss": 0.3494,
"step": 2340
},
{
"epoch": 1.07,
"learning_rate": 4.568741076677585e-05,
"loss": 0.4126,
"step": 2350
},
{
"epoch": 1.07,
"learning_rate": 4.564541866129168e-05,
"loss": 0.3279,
"step": 2360
},
{
"epoch": 1.07,
"learning_rate": 4.560342655580751e-05,
"loss": 0.411,
"step": 2370
},
{
"epoch": 1.08,
"learning_rate": 4.5561434450323345e-05,
"loss": 0.324,
"step": 2380
},
{
"epoch": 1.08,
"learning_rate": 4.551944234483917e-05,
"loss": 0.3626,
"step": 2390
},
{
"epoch": 1.09,
"learning_rate": 4.5477450239355e-05,
"loss": 0.3904,
"step": 2400
},
{
"epoch": 1.09,
"learning_rate": 4.5435458133870834e-05,
"loss": 0.3551,
"step": 2410
},
{
"epoch": 1.1,
"learning_rate": 4.539346602838667e-05,
"loss": 0.3877,
"step": 2420
},
{
"epoch": 1.1,
"learning_rate": 4.53514739229025e-05,
"loss": 0.3792,
"step": 2430
},
{
"epoch": 1.11,
"learning_rate": 4.530948181741832e-05,
"loss": 0.3376,
"step": 2440
},
{
"epoch": 1.11,
"learning_rate": 4.5267489711934157e-05,
"loss": 0.4287,
"step": 2450
},
{
"epoch": 1.12,
"learning_rate": 4.522549760644999e-05,
"loss": 0.325,
"step": 2460
},
{
"epoch": 1.12,
"learning_rate": 4.5183505500965825e-05,
"loss": 0.3511,
"step": 2470
},
{
"epoch": 1.12,
"learning_rate": 4.514151339548165e-05,
"loss": 0.3748,
"step": 2480
},
{
"epoch": 1.13,
"learning_rate": 4.509952128999748e-05,
"loss": 0.3579,
"step": 2490
},
{
"epoch": 1.13,
"learning_rate": 4.505752918451331e-05,
"loss": 0.3429,
"step": 2500
},
{
"epoch": 1.14,
"learning_rate": 4.501553707902915e-05,
"loss": 0.4071,
"step": 2510
},
{
"epoch": 1.14,
"learning_rate": 4.4973544973544974e-05,
"loss": 0.3147,
"step": 2520
},
{
"epoch": 1.15,
"learning_rate": 4.493155286806081e-05,
"loss": 0.3598,
"step": 2530
},
{
"epoch": 1.15,
"learning_rate": 4.4889560762576636e-05,
"loss": 0.39,
"step": 2540
},
{
"epoch": 1.16,
"learning_rate": 4.484756865709247e-05,
"loss": 0.3532,
"step": 2550
},
{
"epoch": 1.16,
"learning_rate": 4.48055765516083e-05,
"loss": 0.3213,
"step": 2560
},
{
"epoch": 1.17,
"learning_rate": 4.476358444612413e-05,
"loss": 0.3817,
"step": 2570
},
{
"epoch": 1.17,
"learning_rate": 4.4721592340639965e-05,
"loss": 0.3342,
"step": 2580
},
{
"epoch": 1.17,
"learning_rate": 4.467960023515579e-05,
"loss": 0.3493,
"step": 2590
},
{
"epoch": 1.18,
"learning_rate": 4.4637608129671626e-05,
"loss": 0.3494,
"step": 2600
},
{
"epoch": 1.18,
"learning_rate": 4.4595616024187454e-05,
"loss": 0.3252,
"step": 2610
},
{
"epoch": 1.19,
"learning_rate": 4.455362391870329e-05,
"loss": 0.3471,
"step": 2620
},
{
"epoch": 1.19,
"learning_rate": 4.4511631813219115e-05,
"loss": 0.3104,
"step": 2630
},
{
"epoch": 1.2,
"learning_rate": 4.446963970773495e-05,
"loss": 0.3131,
"step": 2640
},
{
"epoch": 1.2,
"learning_rate": 4.4427647602250776e-05,
"loss": 0.3223,
"step": 2650
},
{
"epoch": 1.21,
"learning_rate": 4.438565549676661e-05,
"loss": 0.376,
"step": 2660
},
{
"epoch": 1.21,
"learning_rate": 4.4343663391282444e-05,
"loss": 0.3351,
"step": 2670
},
{
"epoch": 1.22,
"learning_rate": 4.430167128579827e-05,
"loss": 0.2858,
"step": 2680
},
{
"epoch": 1.22,
"learning_rate": 4.42596791803141e-05,
"loss": 0.2743,
"step": 2690
},
{
"epoch": 1.22,
"learning_rate": 4.421768707482993e-05,
"loss": 0.354,
"step": 2700
},
{
"epoch": 1.23,
"learning_rate": 4.417569496934577e-05,
"loss": 0.4004,
"step": 2710
},
{
"epoch": 1.23,
"learning_rate": 4.41337028638616e-05,
"loss": 0.3416,
"step": 2720
},
{
"epoch": 1.24,
"learning_rate": 4.409171075837743e-05,
"loss": 0.2942,
"step": 2730
},
{
"epoch": 1.24,
"learning_rate": 4.4049718652893255e-05,
"loss": 0.2874,
"step": 2740
},
{
"epoch": 1.25,
"learning_rate": 4.400772654740909e-05,
"loss": 0.2511,
"step": 2750
},
{
"epoch": 1.25,
"learning_rate": 4.396573444192492e-05,
"loss": 0.2691,
"step": 2760
},
{
"epoch": 1.26,
"learning_rate": 4.392374233644075e-05,
"loss": 0.3086,
"step": 2770
},
{
"epoch": 1.26,
"learning_rate": 4.388175023095658e-05,
"loss": 0.2938,
"step": 2780
},
{
"epoch": 1.27,
"learning_rate": 4.383975812547241e-05,
"loss": 0.3348,
"step": 2790
},
{
"epoch": 1.27,
"learning_rate": 4.3797766019988246e-05,
"loss": 0.2655,
"step": 2800
},
{
"epoch": 1.27,
"learning_rate": 4.375577391450408e-05,
"loss": 0.3305,
"step": 2810
},
{
"epoch": 1.28,
"learning_rate": 4.371378180901991e-05,
"loss": 0.3188,
"step": 2820
},
{
"epoch": 1.28,
"learning_rate": 4.3671789703535734e-05,
"loss": 0.2778,
"step": 2830
},
{
"epoch": 1.29,
"learning_rate": 4.362979759805157e-05,
"loss": 0.353,
"step": 2840
},
{
"epoch": 1.29,
"learning_rate": 4.35878054925674e-05,
"loss": 0.3406,
"step": 2850
},
{
"epoch": 1.3,
"learning_rate": 4.354581338708323e-05,
"loss": 0.2692,
"step": 2860
},
{
"epoch": 1.3,
"learning_rate": 4.3503821281599064e-05,
"loss": 0.2975,
"step": 2870
},
{
"epoch": 1.31,
"learning_rate": 4.346182917611489e-05,
"loss": 0.3398,
"step": 2880
},
{
"epoch": 1.31,
"learning_rate": 4.3419837070630725e-05,
"loss": 0.3592,
"step": 2890
},
{
"epoch": 1.32,
"learning_rate": 4.337784496514655e-05,
"loss": 0.288,
"step": 2900
},
{
"epoch": 1.32,
"learning_rate": 4.3335852859662386e-05,
"loss": 0.3553,
"step": 2910
},
{
"epoch": 1.32,
"learning_rate": 4.329386075417822e-05,
"loss": 0.3201,
"step": 2920
},
{
"epoch": 1.33,
"learning_rate": 4.325186864869405e-05,
"loss": 0.3169,
"step": 2930
},
{
"epoch": 1.33,
"learning_rate": 4.3209876543209875e-05,
"loss": 0.3352,
"step": 2940
},
{
"epoch": 1.34,
"learning_rate": 4.316788443772571e-05,
"loss": 0.3387,
"step": 2950
},
{
"epoch": 1.34,
"learning_rate": 4.312589233224154e-05,
"loss": 0.2997,
"step": 2960
},
{
"epoch": 1.35,
"learning_rate": 4.308390022675737e-05,
"loss": 0.3039,
"step": 2970
},
{
"epoch": 1.35,
"learning_rate": 4.30419081212732e-05,
"loss": 0.3112,
"step": 2980
},
{
"epoch": 1.36,
"learning_rate": 4.299991601578903e-05,
"loss": 0.265,
"step": 2990
},
{
"epoch": 1.36,
"learning_rate": 4.2957923910304865e-05,
"loss": 0.3255,
"step": 3000
},
{
"epoch": 1.37,
"learning_rate": 4.29159318048207e-05,
"loss": 0.294,
"step": 3010
},
{
"epoch": 1.37,
"learning_rate": 4.287393969933653e-05,
"loss": 0.3001,
"step": 3020
},
{
"epoch": 1.37,
"learning_rate": 4.2831947593852354e-05,
"loss": 0.2737,
"step": 3030
},
{
"epoch": 1.38,
"learning_rate": 4.278995548836819e-05,
"loss": 0.2774,
"step": 3040
},
{
"epoch": 1.38,
"learning_rate": 4.274796338288402e-05,
"loss": 0.2883,
"step": 3050
},
{
"epoch": 1.39,
"learning_rate": 4.2705971277399856e-05,
"loss": 0.3076,
"step": 3060
},
{
"epoch": 1.39,
"learning_rate": 4.266397917191568e-05,
"loss": 0.3689,
"step": 3070
},
{
"epoch": 1.4,
"learning_rate": 4.262198706643151e-05,
"loss": 0.2816,
"step": 3080
},
{
"epoch": 1.4,
"learning_rate": 4.2579994960947345e-05,
"loss": 0.2837,
"step": 3090
},
{
"epoch": 1.41,
"learning_rate": 4.253800285546318e-05,
"loss": 0.275,
"step": 3100
},
{
"epoch": 1.41,
"learning_rate": 4.2496010749979006e-05,
"loss": 0.2689,
"step": 3110
},
{
"epoch": 1.41,
"learning_rate": 4.245401864449483e-05,
"loss": 0.2561,
"step": 3120
},
{
"epoch": 1.42,
"learning_rate": 4.241202653901067e-05,
"loss": 0.2948,
"step": 3130
},
{
"epoch": 1.42,
"learning_rate": 4.23700344335265e-05,
"loss": 0.2998,
"step": 3140
},
{
"epoch": 1.43,
"learning_rate": 4.232804232804233e-05,
"loss": 0.36,
"step": 3150
},
{
"epoch": 1.43,
"learning_rate": 4.228605022255816e-05,
"loss": 0.3877,
"step": 3160
},
{
"epoch": 1.44,
"learning_rate": 4.224405811707399e-05,
"loss": 0.292,
"step": 3170
},
{
"epoch": 1.44,
"learning_rate": 4.2202066011589824e-05,
"loss": 0.3701,
"step": 3180
},
{
"epoch": 1.45,
"learning_rate": 4.216007390610565e-05,
"loss": 0.2715,
"step": 3190
},
{
"epoch": 1.45,
"learning_rate": 4.2118081800621485e-05,
"loss": 0.3183,
"step": 3200
},
{
"epoch": 1.46,
"learning_rate": 4.207608969513732e-05,
"loss": 0.3222,
"step": 3210
},
{
"epoch": 1.46,
"learning_rate": 4.2034097589653146e-05,
"loss": 0.2744,
"step": 3220
},
{
"epoch": 1.46,
"learning_rate": 4.199210548416898e-05,
"loss": 0.3421,
"step": 3230
},
{
"epoch": 1.47,
"learning_rate": 4.195011337868481e-05,
"loss": 0.301,
"step": 3240
},
{
"epoch": 1.47,
"learning_rate": 4.190812127320064e-05,
"loss": 0.2766,
"step": 3250
},
{
"epoch": 1.48,
"learning_rate": 4.1866129167716476e-05,
"loss": 0.3371,
"step": 3260
},
{
"epoch": 1.48,
"learning_rate": 4.18241370622323e-05,
"loss": 0.41,
"step": 3270
},
{
"epoch": 1.49,
"learning_rate": 4.178214495674813e-05,
"loss": 0.3191,
"step": 3280
},
{
"epoch": 1.49,
"learning_rate": 4.1740152851263964e-05,
"loss": 0.2978,
"step": 3290
},
{
"epoch": 1.5,
"learning_rate": 4.16981607457798e-05,
"loss": 0.3317,
"step": 3300
},
{
"epoch": 1.5,
"learning_rate": 4.1656168640295625e-05,
"loss": 0.329,
"step": 3310
},
{
"epoch": 1.51,
"learning_rate": 4.161417653481145e-05,
"loss": 0.3424,
"step": 3320
},
{
"epoch": 1.51,
"learning_rate": 4.157218442932729e-05,
"loss": 0.2634,
"step": 3330
},
{
"epoch": 1.51,
"learning_rate": 4.153019232384312e-05,
"loss": 0.2914,
"step": 3340
},
{
"epoch": 1.52,
"learning_rate": 4.1488200218358955e-05,
"loss": 0.2754,
"step": 3350
},
{
"epoch": 1.52,
"learning_rate": 4.144620811287478e-05,
"loss": 0.2537,
"step": 3360
},
{
"epoch": 1.53,
"learning_rate": 4.140421600739061e-05,
"loss": 0.3433,
"step": 3370
},
{
"epoch": 1.53,
"learning_rate": 4.136222390190644e-05,
"loss": 0.2858,
"step": 3380
},
{
"epoch": 1.54,
"learning_rate": 4.132023179642228e-05,
"loss": 0.2778,
"step": 3390
},
{
"epoch": 1.54,
"learning_rate": 4.1278239690938105e-05,
"loss": 0.242,
"step": 3400
},
{
"epoch": 1.55,
"learning_rate": 4.123624758545394e-05,
"loss": 0.3188,
"step": 3410
},
{
"epoch": 1.55,
"learning_rate": 4.1194255479969766e-05,
"loss": 0.3187,
"step": 3420
},
{
"epoch": 1.56,
"learning_rate": 4.11522633744856e-05,
"loss": 0.3091,
"step": 3430
},
{
"epoch": 1.56,
"learning_rate": 4.1110271269001434e-05,
"loss": 0.3328,
"step": 3440
},
{
"epoch": 1.56,
"learning_rate": 4.106827916351726e-05,
"loss": 0.2671,
"step": 3450
},
{
"epoch": 1.57,
"learning_rate": 4.102628705803309e-05,
"loss": 0.2558,
"step": 3460
},
{
"epoch": 1.57,
"learning_rate": 4.098429495254892e-05,
"loss": 0.2902,
"step": 3470
},
{
"epoch": 1.58,
"learning_rate": 4.0942302847064757e-05,
"loss": 0.2577,
"step": 3480
},
{
"epoch": 1.58,
"learning_rate": 4.0900310741580584e-05,
"loss": 0.2643,
"step": 3490
},
{
"epoch": 1.59,
"learning_rate": 4.085831863609642e-05,
"loss": 0.2871,
"step": 3500
},
{
"epoch": 1.59,
"learning_rate": 4.0816326530612245e-05,
"loss": 0.2995,
"step": 3510
},
{
"epoch": 1.6,
"learning_rate": 4.077433442512808e-05,
"loss": 0.2713,
"step": 3520
},
{
"epoch": 1.6,
"learning_rate": 4.0732342319643906e-05,
"loss": 0.2621,
"step": 3530
},
{
"epoch": 1.61,
"learning_rate": 4.069035021415974e-05,
"loss": 0.2655,
"step": 3540
},
{
"epoch": 1.61,
"learning_rate": 4.0648358108675574e-05,
"loss": 0.3452,
"step": 3550
},
{
"epoch": 1.61,
"learning_rate": 4.06063660031914e-05,
"loss": 0.2532,
"step": 3560
},
{
"epoch": 1.62,
"learning_rate": 4.056437389770723e-05,
"loss": 0.2972,
"step": 3570
},
{
"epoch": 1.62,
"learning_rate": 4.052238179222306e-05,
"loss": 0.2704,
"step": 3580
},
{
"epoch": 1.63,
"learning_rate": 4.04803896867389e-05,
"loss": 0.2916,
"step": 3590
},
{
"epoch": 1.63,
"learning_rate": 4.043839758125473e-05,
"loss": 0.2351,
"step": 3600
},
{
"epoch": 1.64,
"learning_rate": 4.039640547577055e-05,
"loss": 0.3761,
"step": 3610
},
{
"epoch": 1.64,
"learning_rate": 4.0354413370286385e-05,
"loss": 0.3,
"step": 3620
},
{
"epoch": 1.65,
"learning_rate": 4.031242126480222e-05,
"loss": 0.2661,
"step": 3630
},
{
"epoch": 1.65,
"learning_rate": 4.0270429159318054e-05,
"loss": 0.3624,
"step": 3640
},
{
"epoch": 1.66,
"learning_rate": 4.022843705383388e-05,
"loss": 0.2991,
"step": 3650
},
{
"epoch": 1.66,
"learning_rate": 4.018644494834971e-05,
"loss": 0.3055,
"step": 3660
},
{
"epoch": 1.66,
"learning_rate": 4.014445284286554e-05,
"loss": 0.3182,
"step": 3670
},
{
"epoch": 1.67,
"learning_rate": 4.0102460737381376e-05,
"loss": 0.2791,
"step": 3680
},
{
"epoch": 1.67,
"learning_rate": 4.006046863189721e-05,
"loss": 0.2347,
"step": 3690
},
{
"epoch": 1.68,
"learning_rate": 4.001847652641304e-05,
"loss": 0.2832,
"step": 3700
},
{
"epoch": 1.68,
"learning_rate": 3.9976484420928865e-05,
"loss": 0.2619,
"step": 3710
},
{
"epoch": 1.69,
"learning_rate": 3.99344923154447e-05,
"loss": 0.3122,
"step": 3720
},
{
"epoch": 1.69,
"learning_rate": 3.989250020996053e-05,
"loss": 0.2516,
"step": 3730
},
{
"epoch": 1.7,
"learning_rate": 3.985050810447636e-05,
"loss": 0.2621,
"step": 3740
},
{
"epoch": 1.7,
"learning_rate": 3.9808515998992194e-05,
"loss": 0.2772,
"step": 3750
},
{
"epoch": 1.71,
"learning_rate": 3.976652389350802e-05,
"loss": 0.2718,
"step": 3760
},
{
"epoch": 1.71,
"learning_rate": 3.9724531788023855e-05,
"loss": 0.2869,
"step": 3770
},
{
"epoch": 1.71,
"learning_rate": 3.968253968253968e-05,
"loss": 0.3356,
"step": 3780
},
{
"epoch": 1.72,
"learning_rate": 3.9640547577055517e-05,
"loss": 0.2357,
"step": 3790
},
{
"epoch": 1.72,
"learning_rate": 3.9598555471571344e-05,
"loss": 0.264,
"step": 3800
},
{
"epoch": 1.73,
"learning_rate": 3.955656336608718e-05,
"loss": 0.3543,
"step": 3810
},
{
"epoch": 1.73,
"learning_rate": 3.9514571260603005e-05,
"loss": 0.2564,
"step": 3820
},
{
"epoch": 1.74,
"learning_rate": 3.947257915511884e-05,
"loss": 0.3005,
"step": 3830
},
{
"epoch": 1.74,
"learning_rate": 3.943058704963467e-05,
"loss": 0.2671,
"step": 3840
},
{
"epoch": 1.75,
"learning_rate": 3.93885949441505e-05,
"loss": 0.3224,
"step": 3850
},
{
"epoch": 1.75,
"learning_rate": 3.934660283866633e-05,
"loss": 0.2699,
"step": 3860
},
{
"epoch": 1.76,
"learning_rate": 3.930461073318216e-05,
"loss": 0.2212,
"step": 3870
},
{
"epoch": 1.76,
"learning_rate": 3.9262618627697996e-05,
"loss": 0.2827,
"step": 3880
},
{
"epoch": 1.76,
"learning_rate": 3.922062652221383e-05,
"loss": 0.323,
"step": 3890
},
{
"epoch": 1.77,
"learning_rate": 3.917863441672966e-05,
"loss": 0.2405,
"step": 3900
},
{
"epoch": 1.77,
"learning_rate": 3.9136642311245484e-05,
"loss": 0.2915,
"step": 3910
},
{
"epoch": 1.78,
"learning_rate": 3.909465020576132e-05,
"loss": 0.3259,
"step": 3920
},
{
"epoch": 1.78,
"learning_rate": 3.905265810027715e-05,
"loss": 0.2336,
"step": 3930
},
{
"epoch": 1.79,
"learning_rate": 3.9010665994792986e-05,
"loss": 0.2425,
"step": 3940
},
{
"epoch": 1.79,
"learning_rate": 3.896867388930881e-05,
"loss": 0.2877,
"step": 3950
},
{
"epoch": 1.8,
"learning_rate": 3.892668178382464e-05,
"loss": 0.2551,
"step": 3960
},
{
"epoch": 1.8,
"learning_rate": 3.8884689678340475e-05,
"loss": 0.2711,
"step": 3970
},
{
"epoch": 1.8,
"learning_rate": 3.884269757285631e-05,
"loss": 0.2642,
"step": 3980
},
{
"epoch": 1.81,
"learning_rate": 3.8800705467372136e-05,
"loss": 0.2933,
"step": 3990
},
{
"epoch": 1.81,
"learning_rate": 3.875871336188796e-05,
"loss": 0.2376,
"step": 4000
},
{
"epoch": 1.82,
"learning_rate": 3.87167212564038e-05,
"loss": 0.2111,
"step": 4010
},
{
"epoch": 1.82,
"learning_rate": 3.867472915091963e-05,
"loss": 0.2701,
"step": 4020
},
{
"epoch": 1.83,
"learning_rate": 3.863273704543546e-05,
"loss": 0.222,
"step": 4030
},
{
"epoch": 1.83,
"learning_rate": 3.859074493995129e-05,
"loss": 0.3182,
"step": 4040
},
{
"epoch": 1.84,
"learning_rate": 3.854875283446712e-05,
"loss": 0.2951,
"step": 4050
},
{
"epoch": 1.84,
"learning_rate": 3.8506760728982954e-05,
"loss": 0.263,
"step": 4060
},
{
"epoch": 1.85,
"learning_rate": 3.846476862349878e-05,
"loss": 0.3261,
"step": 4070
},
{
"epoch": 1.85,
"learning_rate": 3.8422776518014615e-05,
"loss": 0.2702,
"step": 4080
},
{
"epoch": 1.85,
"learning_rate": 3.838078441253045e-05,
"loss": 0.2032,
"step": 4090
},
{
"epoch": 1.86,
"learning_rate": 3.8338792307046277e-05,
"loss": 0.2443,
"step": 4100
},
{
"epoch": 1.86,
"learning_rate": 3.829680020156211e-05,
"loss": 0.289,
"step": 4110
},
{
"epoch": 1.87,
"learning_rate": 3.825480809607794e-05,
"loss": 0.2148,
"step": 4120
},
{
"epoch": 1.87,
"learning_rate": 3.821281599059377e-05,
"loss": 0.2434,
"step": 4130
},
{
"epoch": 1.88,
"learning_rate": 3.81708238851096e-05,
"loss": 0.2568,
"step": 4140
},
{
"epoch": 1.88,
"learning_rate": 3.812883177962543e-05,
"loss": 0.3357,
"step": 4150
},
{
"epoch": 1.89,
"learning_rate": 3.808683967414126e-05,
"loss": 0.2972,
"step": 4160
},
{
"epoch": 1.89,
"learning_rate": 3.8044847568657094e-05,
"loss": 0.2893,
"step": 4170
},
{
"epoch": 1.9,
"learning_rate": 3.800285546317293e-05,
"loss": 0.2938,
"step": 4180
},
{
"epoch": 1.9,
"learning_rate": 3.7960863357688756e-05,
"loss": 0.2099,
"step": 4190
},
{
"epoch": 1.9,
"learning_rate": 3.791887125220458e-05,
"loss": 0.2879,
"step": 4200
},
{
"epoch": 1.91,
"learning_rate": 3.787687914672042e-05,
"loss": 0.2413,
"step": 4210
},
{
"epoch": 1.91,
"learning_rate": 3.783488704123625e-05,
"loss": 0.2214,
"step": 4220
},
{
"epoch": 1.92,
"learning_rate": 3.7792894935752085e-05,
"loss": 0.3174,
"step": 4230
},
{
"epoch": 1.92,
"learning_rate": 3.775090283026791e-05,
"loss": 0.2934,
"step": 4240
},
{
"epoch": 1.93,
"learning_rate": 3.770891072478374e-05,
"loss": 0.2019,
"step": 4250
},
{
"epoch": 1.93,
"learning_rate": 3.7666918619299574e-05,
"loss": 0.2993,
"step": 4260
},
{
"epoch": 1.94,
"learning_rate": 3.762492651381541e-05,
"loss": 0.2046,
"step": 4270
},
{
"epoch": 1.94,
"learning_rate": 3.7582934408331235e-05,
"loss": 0.2239,
"step": 4280
},
{
"epoch": 1.95,
"learning_rate": 3.754094230284706e-05,
"loss": 0.3302,
"step": 4290
},
{
"epoch": 1.95,
"learning_rate": 3.7498950197362896e-05,
"loss": 0.2256,
"step": 4300
},
{
"epoch": 1.95,
"learning_rate": 3.745695809187873e-05,
"loss": 0.2555,
"step": 4310
},
{
"epoch": 1.96,
"learning_rate": 3.7414965986394564e-05,
"loss": 0.2288,
"step": 4320
},
{
"epoch": 1.96,
"learning_rate": 3.737297388091039e-05,
"loss": 0.2405,
"step": 4330
},
{
"epoch": 1.97,
"learning_rate": 3.733098177542622e-05,
"loss": 0.2361,
"step": 4340
},
{
"epoch": 1.97,
"learning_rate": 3.728898966994205e-05,
"loss": 0.2615,
"step": 4350
},
{
"epoch": 1.98,
"learning_rate": 3.724699756445789e-05,
"loss": 0.2942,
"step": 4360
},
{
"epoch": 1.98,
"learning_rate": 3.7205005458973714e-05,
"loss": 0.2363,
"step": 4370
},
{
"epoch": 1.99,
"learning_rate": 3.716301335348955e-05,
"loss": 0.2698,
"step": 4380
},
{
"epoch": 1.99,
"learning_rate": 3.7121021248005375e-05,
"loss": 0.3427,
"step": 4390
},
{
"epoch": 2.0,
"learning_rate": 3.707902914252121e-05,
"loss": 0.1907,
"step": 4400
},
{
"epoch": 2.0,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.2524,
"step": 4410
},
{
"epoch": 2.0,
"eval_accuracy": 0.9392006802721088,
"eval_loss": 0.16125372052192688,
"eval_runtime": 402.2527,
"eval_samples_per_second": 29.235,
"eval_steps_per_second": 3.654,
"step": 4410
},
{
"epoch": 2.0,
"learning_rate": 3.699504493155287e-05,
"loss": 0.2664,
"step": 4420
},
{
"epoch": 2.01,
"learning_rate": 3.6953052826068705e-05,
"loss": 0.2957,
"step": 4430
},
{
"epoch": 2.01,
"learning_rate": 3.691106072058453e-05,
"loss": 0.2553,
"step": 4440
},
{
"epoch": 2.02,
"learning_rate": 3.686906861510036e-05,
"loss": 0.2528,
"step": 4450
},
{
"epoch": 2.02,
"learning_rate": 3.682707650961619e-05,
"loss": 0.2673,
"step": 4460
},
{
"epoch": 2.03,
"learning_rate": 3.678508440413203e-05,
"loss": 0.2749,
"step": 4470
},
{
"epoch": 2.03,
"learning_rate": 3.6743092298647854e-05,
"loss": 0.2238,
"step": 4480
},
{
"epoch": 2.04,
"learning_rate": 3.670110019316368e-05,
"loss": 0.2713,
"step": 4490
},
{
"epoch": 2.04,
"learning_rate": 3.6659108087679516e-05,
"loss": 0.2219,
"step": 4500
},
{
"epoch": 2.05,
"learning_rate": 3.661711598219535e-05,
"loss": 0.2495,
"step": 4510
},
{
"epoch": 2.05,
"learning_rate": 3.6575123876711184e-05,
"loss": 0.2566,
"step": 4520
},
{
"epoch": 2.05,
"learning_rate": 3.653313177122701e-05,
"loss": 0.251,
"step": 4530
},
{
"epoch": 2.06,
"learning_rate": 3.649113966574284e-05,
"loss": 0.235,
"step": 4540
},
{
"epoch": 2.06,
"learning_rate": 3.644914756025867e-05,
"loss": 0.2359,
"step": 4550
},
{
"epoch": 2.07,
"learning_rate": 3.6407155454774506e-05,
"loss": 0.2498,
"step": 4560
},
{
"epoch": 2.07,
"learning_rate": 3.636516334929034e-05,
"loss": 0.201,
"step": 4570
},
{
"epoch": 2.08,
"learning_rate": 3.632317124380617e-05,
"loss": 0.2778,
"step": 4580
},
{
"epoch": 2.08,
"learning_rate": 3.6281179138321995e-05,
"loss": 0.2172,
"step": 4590
},
{
"epoch": 2.09,
"learning_rate": 3.623918703283783e-05,
"loss": 0.2144,
"step": 4600
},
{
"epoch": 2.09,
"learning_rate": 3.619719492735366e-05,
"loss": 0.2279,
"step": 4610
},
{
"epoch": 2.1,
"learning_rate": 3.615520282186949e-05,
"loss": 0.283,
"step": 4620
},
{
"epoch": 2.1,
"learning_rate": 3.611321071638532e-05,
"loss": 0.2553,
"step": 4630
},
{
"epoch": 2.1,
"learning_rate": 3.607121861090115e-05,
"loss": 0.2035,
"step": 4640
},
{
"epoch": 2.11,
"learning_rate": 3.6029226505416985e-05,
"loss": 0.2462,
"step": 4650
},
{
"epoch": 2.11,
"learning_rate": 3.598723439993281e-05,
"loss": 0.26,
"step": 4660
},
{
"epoch": 2.12,
"learning_rate": 3.594524229444865e-05,
"loss": 0.2423,
"step": 4670
},
{
"epoch": 2.12,
"learning_rate": 3.5903250188964474e-05,
"loss": 0.2716,
"step": 4680
},
{
"epoch": 2.13,
"learning_rate": 3.586125808348031e-05,
"loss": 0.2016,
"step": 4690
},
{
"epoch": 2.13,
"learning_rate": 3.5819265977996135e-05,
"loss": 0.2512,
"step": 4700
},
{
"epoch": 2.14,
"learning_rate": 3.577727387251197e-05,
"loss": 0.25,
"step": 4710
},
{
"epoch": 2.14,
"learning_rate": 3.57352817670278e-05,
"loss": 0.2214,
"step": 4720
},
{
"epoch": 2.15,
"learning_rate": 3.569328966154363e-05,
"loss": 0.1298,
"step": 4730
},
{
"epoch": 2.15,
"learning_rate": 3.565129755605946e-05,
"loss": 0.2349,
"step": 4740
},
{
"epoch": 2.15,
"learning_rate": 3.560930545057529e-05,
"loss": 0.2824,
"step": 4750
},
{
"epoch": 2.16,
"learning_rate": 3.5567313345091126e-05,
"loss": 0.2753,
"step": 4760
},
{
"epoch": 2.16,
"learning_rate": 3.552532123960696e-05,
"loss": 0.2446,
"step": 4770
},
{
"epoch": 2.17,
"learning_rate": 3.548332913412279e-05,
"loss": 0.273,
"step": 4780
},
{
"epoch": 2.17,
"learning_rate": 3.5441337028638614e-05,
"loss": 0.2542,
"step": 4790
},
{
"epoch": 2.18,
"learning_rate": 3.539934492315445e-05,
"loss": 0.2281,
"step": 4800
},
{
"epoch": 2.18,
"learning_rate": 3.535735281767028e-05,
"loss": 0.2052,
"step": 4810
},
{
"epoch": 2.19,
"learning_rate": 3.531536071218611e-05,
"loss": 0.2259,
"step": 4820
},
{
"epoch": 2.19,
"learning_rate": 3.527336860670194e-05,
"loss": 0.2177,
"step": 4830
},
{
"epoch": 2.19,
"learning_rate": 3.523137650121777e-05,
"loss": 0.201,
"step": 4840
},
{
"epoch": 2.2,
"learning_rate": 3.5189384395733605e-05,
"loss": 0.2702,
"step": 4850
},
{
"epoch": 2.2,
"learning_rate": 3.514739229024944e-05,
"loss": 0.2529,
"step": 4860
},
{
"epoch": 2.21,
"learning_rate": 3.5105400184765266e-05,
"loss": 0.1965,
"step": 4870
},
{
"epoch": 2.21,
"learning_rate": 3.5063408079281094e-05,
"loss": 0.2109,
"step": 4880
},
{
"epoch": 2.22,
"learning_rate": 3.502141597379693e-05,
"loss": 0.1947,
"step": 4890
},
{
"epoch": 2.22,
"learning_rate": 3.497942386831276e-05,
"loss": 0.1822,
"step": 4900
},
{
"epoch": 2.23,
"learning_rate": 3.493743176282859e-05,
"loss": 0.2514,
"step": 4910
},
{
"epoch": 2.23,
"learning_rate": 3.489543965734442e-05,
"loss": 0.2349,
"step": 4920
},
{
"epoch": 2.24,
"learning_rate": 3.485344755186025e-05,
"loss": 0.2164,
"step": 4930
},
{
"epoch": 2.24,
"learning_rate": 3.4811455446376084e-05,
"loss": 0.1938,
"step": 4940
},
{
"epoch": 2.24,
"learning_rate": 3.476946334089191e-05,
"loss": 0.2615,
"step": 4950
},
{
"epoch": 2.25,
"learning_rate": 3.4727471235407745e-05,
"loss": 0.2336,
"step": 4960
},
{
"epoch": 2.25,
"learning_rate": 3.468547912992357e-05,
"loss": 0.2443,
"step": 4970
},
{
"epoch": 2.26,
"learning_rate": 3.464348702443941e-05,
"loss": 0.237,
"step": 4980
},
{
"epoch": 2.26,
"learning_rate": 3.460149491895524e-05,
"loss": 0.2551,
"step": 4990
},
{
"epoch": 2.27,
"learning_rate": 3.455950281347107e-05,
"loss": 0.2258,
"step": 5000
},
{
"epoch": 2.27,
"learning_rate": 3.45175107079869e-05,
"loss": 0.2097,
"step": 5010
},
{
"epoch": 2.28,
"learning_rate": 3.447551860250273e-05,
"loss": 0.2453,
"step": 5020
},
{
"epoch": 2.28,
"learning_rate": 3.443352649701856e-05,
"loss": 0.2446,
"step": 5030
},
{
"epoch": 2.29,
"learning_rate": 3.439153439153439e-05,
"loss": 0.1842,
"step": 5040
},
{
"epoch": 2.29,
"learning_rate": 3.4349542286050225e-05,
"loss": 0.1703,
"step": 5050
},
{
"epoch": 2.29,
"learning_rate": 3.430755018056606e-05,
"loss": 0.2134,
"step": 5060
},
{
"epoch": 2.3,
"learning_rate": 3.4265558075081886e-05,
"loss": 0.1991,
"step": 5070
},
{
"epoch": 2.3,
"learning_rate": 3.422356596959771e-05,
"loss": 0.2584,
"step": 5080
},
{
"epoch": 2.31,
"learning_rate": 3.418157386411355e-05,
"loss": 0.2157,
"step": 5090
},
{
"epoch": 2.31,
"learning_rate": 3.413958175862938e-05,
"loss": 0.2882,
"step": 5100
},
{
"epoch": 2.32,
"learning_rate": 3.4097589653145215e-05,
"loss": 0.2126,
"step": 5110
},
{
"epoch": 2.32,
"learning_rate": 3.4055597547661036e-05,
"loss": 0.2461,
"step": 5120
},
{
"epoch": 2.33,
"learning_rate": 3.401360544217687e-05,
"loss": 0.2387,
"step": 5130
},
{
"epoch": 2.33,
"learning_rate": 3.3971613336692704e-05,
"loss": 0.227,
"step": 5140
},
{
"epoch": 2.34,
"learning_rate": 3.392962123120854e-05,
"loss": 0.2183,
"step": 5150
},
{
"epoch": 2.34,
"learning_rate": 3.3887629125724365e-05,
"loss": 0.235,
"step": 5160
},
{
"epoch": 2.34,
"learning_rate": 3.384563702024019e-05,
"loss": 0.2173,
"step": 5170
},
{
"epoch": 2.35,
"learning_rate": 3.3803644914756026e-05,
"loss": 0.167,
"step": 5180
},
{
"epoch": 2.35,
"learning_rate": 3.376165280927186e-05,
"loss": 0.206,
"step": 5190
},
{
"epoch": 2.36,
"learning_rate": 3.3719660703787694e-05,
"loss": 0.2121,
"step": 5200
},
{
"epoch": 2.36,
"learning_rate": 3.367766859830352e-05,
"loss": 0.2197,
"step": 5210
},
{
"epoch": 2.37,
"learning_rate": 3.363567649281935e-05,
"loss": 0.2213,
"step": 5220
},
{
"epoch": 2.37,
"learning_rate": 3.359368438733518e-05,
"loss": 0.1804,
"step": 5230
},
{
"epoch": 2.38,
"learning_rate": 3.355169228185102e-05,
"loss": 0.2213,
"step": 5240
},
{
"epoch": 2.38,
"learning_rate": 3.3509700176366844e-05,
"loss": 0.2193,
"step": 5250
},
{
"epoch": 2.39,
"learning_rate": 3.346770807088268e-05,
"loss": 0.1834,
"step": 5260
},
{
"epoch": 2.39,
"learning_rate": 3.3425715965398505e-05,
"loss": 0.2221,
"step": 5270
},
{
"epoch": 2.39,
"learning_rate": 3.338372385991434e-05,
"loss": 0.2245,
"step": 5280
},
{
"epoch": 2.4,
"learning_rate": 3.334173175443017e-05,
"loss": 0.2709,
"step": 5290
},
{
"epoch": 2.4,
"learning_rate": 3.3299739648946e-05,
"loss": 0.2103,
"step": 5300
},
{
"epoch": 2.41,
"learning_rate": 3.325774754346183e-05,
"loss": 0.2259,
"step": 5310
},
{
"epoch": 2.41,
"learning_rate": 3.321575543797766e-05,
"loss": 0.2188,
"step": 5320
},
{
"epoch": 2.42,
"learning_rate": 3.317376333249349e-05,
"loss": 0.2065,
"step": 5330
},
{
"epoch": 2.42,
"learning_rate": 3.313177122700932e-05,
"loss": 0.2141,
"step": 5340
},
{
"epoch": 2.43,
"learning_rate": 3.308977912152516e-05,
"loss": 0.2015,
"step": 5350
},
{
"epoch": 2.43,
"learning_rate": 3.3047787016040985e-05,
"loss": 0.2122,
"step": 5360
},
{
"epoch": 2.44,
"learning_rate": 3.300579491055681e-05,
"loss": 0.2172,
"step": 5370
},
{
"epoch": 2.44,
"learning_rate": 3.2963802805072646e-05,
"loss": 0.2294,
"step": 5380
},
{
"epoch": 2.44,
"learning_rate": 3.292181069958848e-05,
"loss": 0.2277,
"step": 5390
},
{
"epoch": 2.45,
"learning_rate": 3.2879818594104314e-05,
"loss": 0.199,
"step": 5400
},
{
"epoch": 2.45,
"learning_rate": 3.283782648862014e-05,
"loss": 0.2305,
"step": 5410
},
{
"epoch": 2.46,
"learning_rate": 3.279583438313597e-05,
"loss": 0.2421,
"step": 5420
},
{
"epoch": 2.46,
"learning_rate": 3.27538422776518e-05,
"loss": 0.2367,
"step": 5430
},
{
"epoch": 2.47,
"learning_rate": 3.2711850172167637e-05,
"loss": 0.1879,
"step": 5440
},
{
"epoch": 2.47,
"learning_rate": 3.266985806668347e-05,
"loss": 0.2006,
"step": 5450
},
{
"epoch": 2.48,
"learning_rate": 3.262786596119929e-05,
"loss": 0.2023,
"step": 5460
},
{
"epoch": 2.48,
"learning_rate": 3.2585873855715125e-05,
"loss": 0.1782,
"step": 5470
},
{
"epoch": 2.49,
"learning_rate": 3.254388175023096e-05,
"loss": 0.1938,
"step": 5480
},
{
"epoch": 2.49,
"learning_rate": 3.250188964474679e-05,
"loss": 0.2185,
"step": 5490
},
{
"epoch": 2.49,
"learning_rate": 3.245989753926262e-05,
"loss": 0.2569,
"step": 5500
},
{
"epoch": 2.5,
"learning_rate": 3.241790543377845e-05,
"loss": 0.1889,
"step": 5510
},
{
"epoch": 2.5,
"learning_rate": 3.237591332829428e-05,
"loss": 0.1505,
"step": 5520
},
{
"epoch": 2.51,
"learning_rate": 3.2333921222810116e-05,
"loss": 0.2459,
"step": 5530
},
{
"epoch": 2.51,
"learning_rate": 3.229192911732594e-05,
"loss": 0.1675,
"step": 5540
},
{
"epoch": 2.52,
"learning_rate": 3.224993701184178e-05,
"loss": 0.1885,
"step": 5550
},
{
"epoch": 2.52,
"learning_rate": 3.2207944906357604e-05,
"loss": 0.1538,
"step": 5560
},
{
"epoch": 2.53,
"learning_rate": 3.216595280087344e-05,
"loss": 0.1912,
"step": 5570
},
{
"epoch": 2.53,
"learning_rate": 3.2123960695389265e-05,
"loss": 0.1634,
"step": 5580
},
{
"epoch": 2.54,
"learning_rate": 3.20819685899051e-05,
"loss": 0.1871,
"step": 5590
},
{
"epoch": 2.54,
"learning_rate": 3.2039976484420934e-05,
"loss": 0.2139,
"step": 5600
},
{
"epoch": 2.54,
"learning_rate": 3.199798437893676e-05,
"loss": 0.1869,
"step": 5610
},
{
"epoch": 2.55,
"learning_rate": 3.1955992273452595e-05,
"loss": 0.2257,
"step": 5620
},
{
"epoch": 2.55,
"learning_rate": 3.191400016796842e-05,
"loss": 0.2067,
"step": 5630
},
{
"epoch": 2.56,
"learning_rate": 3.1872008062484256e-05,
"loss": 0.2073,
"step": 5640
},
{
"epoch": 2.56,
"learning_rate": 3.183001595700008e-05,
"loss": 0.2711,
"step": 5650
},
{
"epoch": 2.57,
"learning_rate": 3.178802385151592e-05,
"loss": 0.1673,
"step": 5660
},
{
"epoch": 2.57,
"learning_rate": 3.1746031746031745e-05,
"loss": 0.2134,
"step": 5670
},
{
"epoch": 2.58,
"learning_rate": 3.170403964054758e-05,
"loss": 0.2386,
"step": 5680
},
{
"epoch": 2.58,
"learning_rate": 3.166204753506341e-05,
"loss": 0.197,
"step": 5690
},
{
"epoch": 2.58,
"learning_rate": 3.162005542957924e-05,
"loss": 0.2269,
"step": 5700
},
{
"epoch": 2.59,
"learning_rate": 3.157806332409507e-05,
"loss": 0.2205,
"step": 5710
},
{
"epoch": 2.59,
"learning_rate": 3.15360712186109e-05,
"loss": 0.2562,
"step": 5720
},
{
"epoch": 2.6,
"learning_rate": 3.1494079113126735e-05,
"loss": 0.1417,
"step": 5730
},
{
"epoch": 2.6,
"learning_rate": 3.145208700764257e-05,
"loss": 0.2346,
"step": 5740
},
{
"epoch": 2.61,
"learning_rate": 3.1410094902158397e-05,
"loss": 0.137,
"step": 5750
},
{
"epoch": 2.61,
"learning_rate": 3.1368102796674224e-05,
"loss": 0.2055,
"step": 5760
},
{
"epoch": 2.62,
"learning_rate": 3.132611069119006e-05,
"loss": 0.2135,
"step": 5770
},
{
"epoch": 2.62,
"learning_rate": 3.128411858570589e-05,
"loss": 0.2076,
"step": 5780
},
{
"epoch": 2.63,
"learning_rate": 3.124212648022172e-05,
"loss": 0.1632,
"step": 5790
},
{
"epoch": 2.63,
"learning_rate": 3.1200134374737546e-05,
"loss": 0.2205,
"step": 5800
},
{
"epoch": 2.63,
"learning_rate": 3.115814226925338e-05,
"loss": 0.2056,
"step": 5810
},
{
"epoch": 2.64,
"learning_rate": 3.1116150163769214e-05,
"loss": 0.1933,
"step": 5820
},
{
"epoch": 2.64,
"learning_rate": 3.107415805828505e-05,
"loss": 0.23,
"step": 5830
},
{
"epoch": 2.65,
"learning_rate": 3.1032165952800876e-05,
"loss": 0.2385,
"step": 5840
},
{
"epoch": 2.65,
"learning_rate": 3.09901738473167e-05,
"loss": 0.2253,
"step": 5850
},
{
"epoch": 2.66,
"learning_rate": 3.094818174183254e-05,
"loss": 0.2139,
"step": 5860
},
{
"epoch": 2.66,
"learning_rate": 3.090618963634837e-05,
"loss": 0.2815,
"step": 5870
},
{
"epoch": 2.67,
"learning_rate": 3.08641975308642e-05,
"loss": 0.2158,
"step": 5880
},
{
"epoch": 2.67,
"learning_rate": 3.082220542538003e-05,
"loss": 0.2129,
"step": 5890
},
{
"epoch": 2.68,
"learning_rate": 3.078021331989586e-05,
"loss": 0.1894,
"step": 5900
},
{
"epoch": 2.68,
"learning_rate": 3.0738221214411694e-05,
"loss": 0.2247,
"step": 5910
},
{
"epoch": 2.68,
"learning_rate": 3.069622910892752e-05,
"loss": 0.2104,
"step": 5920
},
{
"epoch": 2.69,
"learning_rate": 3.0654237003443355e-05,
"loss": 0.1774,
"step": 5930
},
{
"epoch": 2.69,
"learning_rate": 3.061224489795919e-05,
"loss": 0.2049,
"step": 5940
},
{
"epoch": 2.7,
"learning_rate": 3.0570252792475016e-05,
"loss": 0.1984,
"step": 5950
},
{
"epoch": 2.7,
"learning_rate": 3.052826068699084e-05,
"loss": 0.1639,
"step": 5960
},
{
"epoch": 2.71,
"learning_rate": 3.0486268581506677e-05,
"loss": 0.2232,
"step": 5970
},
{
"epoch": 2.71,
"learning_rate": 3.0444276476022508e-05,
"loss": 0.1694,
"step": 5980
},
{
"epoch": 2.72,
"learning_rate": 3.0402284370538342e-05,
"loss": 0.255,
"step": 5990
},
{
"epoch": 2.72,
"learning_rate": 3.036029226505417e-05,
"loss": 0.1945,
"step": 6000
},
{
"epoch": 2.73,
"learning_rate": 3.031830015957e-05,
"loss": 0.2224,
"step": 6010
},
{
"epoch": 2.73,
"learning_rate": 3.0276308054085834e-05,
"loss": 0.2456,
"step": 6020
},
{
"epoch": 2.73,
"learning_rate": 3.0234315948601665e-05,
"loss": 0.2347,
"step": 6030
},
{
"epoch": 2.74,
"learning_rate": 3.0192323843117492e-05,
"loss": 0.2061,
"step": 6040
},
{
"epoch": 2.74,
"learning_rate": 3.0150331737633326e-05,
"loss": 0.2878,
"step": 6050
},
{
"epoch": 2.75,
"learning_rate": 3.0108339632149157e-05,
"loss": 0.2496,
"step": 6060
},
{
"epoch": 2.75,
"learning_rate": 3.006634752666499e-05,
"loss": 0.2021,
"step": 6070
},
{
"epoch": 2.76,
"learning_rate": 3.002435542118082e-05,
"loss": 0.1912,
"step": 6080
},
{
"epoch": 2.76,
"learning_rate": 2.998236331569665e-05,
"loss": 0.133,
"step": 6090
},
{
"epoch": 2.77,
"learning_rate": 2.9940371210212483e-05,
"loss": 0.183,
"step": 6100
},
{
"epoch": 2.77,
"learning_rate": 2.9898379104728313e-05,
"loss": 0.1488,
"step": 6110
},
{
"epoch": 2.78,
"learning_rate": 2.9856386999244147e-05,
"loss": 0.1857,
"step": 6120
},
{
"epoch": 2.78,
"learning_rate": 2.981439489375997e-05,
"loss": 0.2165,
"step": 6130
},
{
"epoch": 2.78,
"learning_rate": 2.9772402788275805e-05,
"loss": 0.1472,
"step": 6140
},
{
"epoch": 2.79,
"learning_rate": 2.9730410682791636e-05,
"loss": 0.2949,
"step": 6150
},
{
"epoch": 2.79,
"learning_rate": 2.968841857730747e-05,
"loss": 0.2194,
"step": 6160
},
{
"epoch": 2.8,
"learning_rate": 2.9646426471823297e-05,
"loss": 0.1517,
"step": 6170
},
{
"epoch": 2.8,
"learning_rate": 2.9604434366339128e-05,
"loss": 0.1856,
"step": 6180
},
{
"epoch": 2.81,
"learning_rate": 2.956244226085496e-05,
"loss": 0.2154,
"step": 6190
},
{
"epoch": 2.81,
"learning_rate": 2.9520450155370792e-05,
"loss": 0.1549,
"step": 6200
},
{
"epoch": 2.82,
"learning_rate": 2.947845804988662e-05,
"loss": 0.2138,
"step": 6210
},
{
"epoch": 2.82,
"learning_rate": 2.9436465944402454e-05,
"loss": 0.2022,
"step": 6220
},
{
"epoch": 2.83,
"learning_rate": 2.9394473838918284e-05,
"loss": 0.2302,
"step": 6230
},
{
"epoch": 2.83,
"learning_rate": 2.9352481733434118e-05,
"loss": 0.1483,
"step": 6240
},
{
"epoch": 2.83,
"learning_rate": 2.9310489627949945e-05,
"loss": 0.2676,
"step": 6250
},
{
"epoch": 2.84,
"learning_rate": 2.9268497522465776e-05,
"loss": 0.2082,
"step": 6260
},
{
"epoch": 2.84,
"learning_rate": 2.922650541698161e-05,
"loss": 0.2137,
"step": 6270
},
{
"epoch": 2.85,
"learning_rate": 2.918451331149744e-05,
"loss": 0.2225,
"step": 6280
},
{
"epoch": 2.85,
"learning_rate": 2.9142521206013275e-05,
"loss": 0.156,
"step": 6290
},
{
"epoch": 2.86,
"learning_rate": 2.91005291005291e-05,
"loss": 0.2768,
"step": 6300
},
{
"epoch": 2.86,
"learning_rate": 2.9058536995044933e-05,
"loss": 0.1932,
"step": 6310
},
{
"epoch": 2.87,
"learning_rate": 2.9016544889560763e-05,
"loss": 0.2075,
"step": 6320
},
{
"epoch": 2.87,
"learning_rate": 2.8974552784076597e-05,
"loss": 0.194,
"step": 6330
},
{
"epoch": 2.88,
"learning_rate": 2.8932560678592425e-05,
"loss": 0.213,
"step": 6340
},
{
"epoch": 2.88,
"learning_rate": 2.8890568573108255e-05,
"loss": 0.1777,
"step": 6350
},
{
"epoch": 2.88,
"learning_rate": 2.884857646762409e-05,
"loss": 0.2057,
"step": 6360
},
{
"epoch": 2.89,
"learning_rate": 2.880658436213992e-05,
"loss": 0.1873,
"step": 6370
},
{
"epoch": 2.89,
"learning_rate": 2.8764592256655747e-05,
"loss": 0.2418,
"step": 6380
},
{
"epoch": 2.9,
"learning_rate": 2.872260015117158e-05,
"loss": 0.1886,
"step": 6390
},
{
"epoch": 2.9,
"learning_rate": 2.8680608045687412e-05,
"loss": 0.208,
"step": 6400
},
{
"epoch": 2.91,
"learning_rate": 2.8638615940203246e-05,
"loss": 0.2454,
"step": 6410
},
{
"epoch": 2.91,
"learning_rate": 2.8596623834719073e-05,
"loss": 0.2601,
"step": 6420
},
{
"epoch": 2.92,
"learning_rate": 2.8554631729234904e-05,
"loss": 0.1714,
"step": 6430
},
{
"epoch": 2.92,
"learning_rate": 2.8512639623750738e-05,
"loss": 0.1876,
"step": 6440
},
{
"epoch": 2.93,
"learning_rate": 2.847064751826657e-05,
"loss": 0.2161,
"step": 6450
},
{
"epoch": 2.93,
"learning_rate": 2.8428655412782396e-05,
"loss": 0.2312,
"step": 6460
},
{
"epoch": 2.93,
"learning_rate": 2.8386663307298226e-05,
"loss": 0.1979,
"step": 6470
},
{
"epoch": 2.94,
"learning_rate": 2.834467120181406e-05,
"loss": 0.2061,
"step": 6480
},
{
"epoch": 2.94,
"learning_rate": 2.830267909632989e-05,
"loss": 0.2284,
"step": 6490
},
{
"epoch": 2.95,
"learning_rate": 2.8260686990845725e-05,
"loss": 0.2119,
"step": 6500
},
{
"epoch": 2.95,
"learning_rate": 2.8218694885361552e-05,
"loss": 0.1662,
"step": 6510
},
{
"epoch": 2.96,
"learning_rate": 2.8176702779877383e-05,
"loss": 0.1754,
"step": 6520
},
{
"epoch": 2.96,
"learning_rate": 2.8134710674393217e-05,
"loss": 0.2138,
"step": 6530
},
{
"epoch": 2.97,
"learning_rate": 2.8092718568909048e-05,
"loss": 0.1715,
"step": 6540
},
{
"epoch": 2.97,
"learning_rate": 2.8050726463424875e-05,
"loss": 0.1775,
"step": 6550
},
{
"epoch": 2.97,
"learning_rate": 2.800873435794071e-05,
"loss": 0.1735,
"step": 6560
},
{
"epoch": 2.98,
"learning_rate": 2.796674225245654e-05,
"loss": 0.1513,
"step": 6570
},
{
"epoch": 2.98,
"learning_rate": 2.7924750146972374e-05,
"loss": 0.2254,
"step": 6580
},
{
"epoch": 2.99,
"learning_rate": 2.78827580414882e-05,
"loss": 0.2005,
"step": 6590
},
{
"epoch": 2.99,
"learning_rate": 2.784076593600403e-05,
"loss": 0.2394,
"step": 6600
},
{
"epoch": 3.0,
"learning_rate": 2.7798773830519865e-05,
"loss": 0.2044,
"step": 6610
},
{
"epoch": 3.0,
"eval_accuracy": 0.9618197278911564,
"eval_loss": 0.1043727844953537,
"eval_runtime": 407.7074,
"eval_samples_per_second": 28.844,
"eval_steps_per_second": 3.606,
"step": 6615
},
{
"epoch": 3.0,
"learning_rate": 2.7756781725035696e-05,
"loss": 0.17,
"step": 6620
},
{
"epoch": 3.01,
"learning_rate": 2.7714789619551523e-05,
"loss": 0.166,
"step": 6630
},
{
"epoch": 3.01,
"learning_rate": 2.7672797514067354e-05,
"loss": 0.1696,
"step": 6640
},
{
"epoch": 3.02,
"learning_rate": 2.7630805408583188e-05,
"loss": 0.1954,
"step": 6650
},
{
"epoch": 3.02,
"learning_rate": 2.758881330309902e-05,
"loss": 0.1527,
"step": 6660
},
{
"epoch": 3.02,
"learning_rate": 2.7546821197614846e-05,
"loss": 0.1774,
"step": 6670
},
{
"epoch": 3.03,
"learning_rate": 2.750482909213068e-05,
"loss": 0.1867,
"step": 6680
},
{
"epoch": 3.03,
"learning_rate": 2.746283698664651e-05,
"loss": 0.1452,
"step": 6690
},
{
"epoch": 3.04,
"learning_rate": 2.7420844881162345e-05,
"loss": 0.2302,
"step": 6700
},
{
"epoch": 3.04,
"learning_rate": 2.7378852775678175e-05,
"loss": 0.1676,
"step": 6710
},
{
"epoch": 3.05,
"learning_rate": 2.7336860670194003e-05,
"loss": 0.1812,
"step": 6720
},
{
"epoch": 3.05,
"learning_rate": 2.7294868564709837e-05,
"loss": 0.1587,
"step": 6730
},
{
"epoch": 3.06,
"learning_rate": 2.7252876459225667e-05,
"loss": 0.2074,
"step": 6740
},
{
"epoch": 3.06,
"learning_rate": 2.72108843537415e-05,
"loss": 0.2062,
"step": 6750
},
{
"epoch": 3.07,
"learning_rate": 2.716889224825733e-05,
"loss": 0.1904,
"step": 6760
},
{
"epoch": 3.07,
"learning_rate": 2.712690014277316e-05,
"loss": 0.2002,
"step": 6770
},
{
"epoch": 3.07,
"learning_rate": 2.7084908037288993e-05,
"loss": 0.1738,
"step": 6780
},
{
"epoch": 3.08,
"learning_rate": 2.7042915931804824e-05,
"loss": 0.175,
"step": 6790
},
{
"epoch": 3.08,
"learning_rate": 2.700092382632065e-05,
"loss": 0.1767,
"step": 6800
},
{
"epoch": 3.09,
"learning_rate": 2.695893172083648e-05,
"loss": 0.2128,
"step": 6810
},
{
"epoch": 3.09,
"learning_rate": 2.6916939615352316e-05,
"loss": 0.1473,
"step": 6820
},
{
"epoch": 3.1,
"learning_rate": 2.6874947509868146e-05,
"loss": 0.182,
"step": 6830
},
{
"epoch": 3.1,
"learning_rate": 2.6832955404383974e-05,
"loss": 0.213,
"step": 6840
},
{
"epoch": 3.11,
"learning_rate": 2.6790963298899808e-05,
"loss": 0.1471,
"step": 6850
},
{
"epoch": 3.11,
"learning_rate": 2.6748971193415638e-05,
"loss": 0.1774,
"step": 6860
},
{
"epoch": 3.12,
"learning_rate": 2.6706979087931472e-05,
"loss": 0.1822,
"step": 6870
},
{
"epoch": 3.12,
"learning_rate": 2.66649869824473e-05,
"loss": 0.2068,
"step": 6880
},
{
"epoch": 3.12,
"learning_rate": 2.662299487696313e-05,
"loss": 0.1796,
"step": 6890
},
{
"epoch": 3.13,
"learning_rate": 2.6581002771478964e-05,
"loss": 0.2225,
"step": 6900
},
{
"epoch": 3.13,
"learning_rate": 2.6539010665994795e-05,
"loss": 0.2022,
"step": 6910
},
{
"epoch": 3.14,
"learning_rate": 2.649701856051063e-05,
"loss": 0.1641,
"step": 6920
},
{
"epoch": 3.14,
"learning_rate": 2.6455026455026456e-05,
"loss": 0.1812,
"step": 6930
},
{
"epoch": 3.15,
"learning_rate": 2.6413034349542287e-05,
"loss": 0.213,
"step": 6940
},
{
"epoch": 3.15,
"learning_rate": 2.637104224405812e-05,
"loss": 0.2162,
"step": 6950
},
{
"epoch": 3.16,
"learning_rate": 2.632905013857395e-05,
"loss": 0.1417,
"step": 6960
},
{
"epoch": 3.16,
"learning_rate": 2.628705803308978e-05,
"loss": 0.1449,
"step": 6970
},
{
"epoch": 3.17,
"learning_rate": 2.624506592760561e-05,
"loss": 0.1703,
"step": 6980
},
{
"epoch": 3.17,
"learning_rate": 2.6203073822121443e-05,
"loss": 0.1935,
"step": 6990
},
{
"epoch": 3.17,
"learning_rate": 2.6161081716637274e-05,
"loss": 0.1993,
"step": 7000
},
{
"epoch": 3.18,
"learning_rate": 2.61190896111531e-05,
"loss": 0.2399,
"step": 7010
},
{
"epoch": 3.18,
"learning_rate": 2.6077097505668935e-05,
"loss": 0.1497,
"step": 7020
},
{
"epoch": 3.19,
"learning_rate": 2.6035105400184766e-05,
"loss": 0.183,
"step": 7030
},
{
"epoch": 3.19,
"learning_rate": 2.59931132947006e-05,
"loss": 0.2033,
"step": 7040
},
{
"epoch": 3.2,
"learning_rate": 2.5951121189216427e-05,
"loss": 0.1562,
"step": 7050
},
{
"epoch": 3.2,
"learning_rate": 2.5909129083732258e-05,
"loss": 0.1547,
"step": 7060
},
{
"epoch": 3.21,
"learning_rate": 2.5867136978248092e-05,
"loss": 0.1699,
"step": 7070
},
{
"epoch": 3.21,
"learning_rate": 2.5825144872763923e-05,
"loss": 0.1913,
"step": 7080
},
{
"epoch": 3.22,
"learning_rate": 2.578315276727975e-05,
"loss": 0.1469,
"step": 7090
},
{
"epoch": 3.22,
"learning_rate": 2.5741160661795584e-05,
"loss": 0.1584,
"step": 7100
},
{
"epoch": 3.22,
"learning_rate": 2.5699168556311414e-05,
"loss": 0.1702,
"step": 7110
},
{
"epoch": 3.23,
"learning_rate": 2.565717645082725e-05,
"loss": 0.2061,
"step": 7120
},
{
"epoch": 3.23,
"learning_rate": 2.5615184345343072e-05,
"loss": 0.1693,
"step": 7130
},
{
"epoch": 3.24,
"learning_rate": 2.5573192239858906e-05,
"loss": 0.1589,
"step": 7140
},
{
"epoch": 3.24,
"learning_rate": 2.5531200134374737e-05,
"loss": 0.1786,
"step": 7150
},
{
"epoch": 3.25,
"learning_rate": 2.548920802889057e-05,
"loss": 0.1204,
"step": 7160
},
{
"epoch": 3.25,
"learning_rate": 2.5447215923406405e-05,
"loss": 0.1681,
"step": 7170
},
{
"epoch": 3.26,
"learning_rate": 2.540522381792223e-05,
"loss": 0.1173,
"step": 7180
},
{
"epoch": 3.26,
"learning_rate": 2.5363231712438063e-05,
"loss": 0.1604,
"step": 7190
},
{
"epoch": 3.27,
"learning_rate": 2.5321239606953894e-05,
"loss": 0.1969,
"step": 7200
},
{
"epoch": 3.27,
"learning_rate": 2.5279247501469728e-05,
"loss": 0.1999,
"step": 7210
},
{
"epoch": 3.27,
"learning_rate": 2.5237255395985555e-05,
"loss": 0.2007,
"step": 7220
},
{
"epoch": 3.28,
"learning_rate": 2.5195263290501386e-05,
"loss": 0.1739,
"step": 7230
},
{
"epoch": 3.28,
"learning_rate": 2.515327118501722e-05,
"loss": 0.1841,
"step": 7240
},
{
"epoch": 3.29,
"learning_rate": 2.511127907953305e-05,
"loss": 0.1759,
"step": 7250
},
{
"epoch": 3.29,
"learning_rate": 2.5069286974048877e-05,
"loss": 0.2122,
"step": 7260
},
{
"epoch": 3.3,
"learning_rate": 2.502729486856471e-05,
"loss": 0.1356,
"step": 7270
},
{
"epoch": 3.3,
"learning_rate": 2.4985302763080542e-05,
"loss": 0.1314,
"step": 7280
},
{
"epoch": 3.31,
"learning_rate": 2.4943310657596373e-05,
"loss": 0.1754,
"step": 7290
},
{
"epoch": 3.31,
"learning_rate": 2.4901318552112203e-05,
"loss": 0.1549,
"step": 7300
},
{
"epoch": 3.32,
"learning_rate": 2.4859326446628034e-05,
"loss": 0.1439,
"step": 7310
},
{
"epoch": 3.32,
"learning_rate": 2.4817334341143868e-05,
"loss": 0.1758,
"step": 7320
},
{
"epoch": 3.32,
"learning_rate": 2.4775342235659695e-05,
"loss": 0.1644,
"step": 7330
},
{
"epoch": 3.33,
"learning_rate": 2.473335013017553e-05,
"loss": 0.1767,
"step": 7340
},
{
"epoch": 3.33,
"learning_rate": 2.4691358024691357e-05,
"loss": 0.1807,
"step": 7350
},
{
"epoch": 3.34,
"learning_rate": 2.464936591920719e-05,
"loss": 0.1713,
"step": 7360
},
{
"epoch": 3.34,
"learning_rate": 2.460737381372302e-05,
"loss": 0.1759,
"step": 7370
},
{
"epoch": 3.35,
"learning_rate": 2.4565381708238852e-05,
"loss": 0.1566,
"step": 7380
},
{
"epoch": 3.35,
"learning_rate": 2.4523389602754686e-05,
"loss": 0.1668,
"step": 7390
},
{
"epoch": 3.36,
"learning_rate": 2.4481397497270513e-05,
"loss": 0.1492,
"step": 7400
},
{
"epoch": 3.36,
"learning_rate": 2.4439405391786347e-05,
"loss": 0.2409,
"step": 7410
},
{
"epoch": 3.37,
"learning_rate": 2.4397413286302174e-05,
"loss": 0.1309,
"step": 7420
},
{
"epoch": 3.37,
"learning_rate": 2.435542118081801e-05,
"loss": 0.1968,
"step": 7430
},
{
"epoch": 3.37,
"learning_rate": 2.431342907533384e-05,
"loss": 0.124,
"step": 7440
},
{
"epoch": 3.38,
"learning_rate": 2.427143696984967e-05,
"loss": 0.2252,
"step": 7450
},
{
"epoch": 3.38,
"learning_rate": 2.42294448643655e-05,
"loss": 0.1758,
"step": 7460
},
{
"epoch": 3.39,
"learning_rate": 2.418745275888133e-05,
"loss": 0.206,
"step": 7470
},
{
"epoch": 3.39,
"learning_rate": 2.414546065339716e-05,
"loss": 0.1855,
"step": 7480
},
{
"epoch": 3.4,
"learning_rate": 2.4103468547912996e-05,
"loss": 0.1816,
"step": 7490
},
{
"epoch": 3.4,
"learning_rate": 2.4061476442428823e-05,
"loss": 0.1624,
"step": 7500
},
{
"epoch": 3.41,
"learning_rate": 2.4019484336944657e-05,
"loss": 0.1393,
"step": 7510
},
{
"epoch": 3.41,
"learning_rate": 2.3977492231460484e-05,
"loss": 0.181,
"step": 7520
},
{
"epoch": 3.41,
"learning_rate": 2.3935500125976318e-05,
"loss": 0.1358,
"step": 7530
},
{
"epoch": 3.42,
"learning_rate": 2.389350802049215e-05,
"loss": 0.1819,
"step": 7540
},
{
"epoch": 3.42,
"learning_rate": 2.385151591500798e-05,
"loss": 0.1737,
"step": 7550
},
{
"epoch": 3.43,
"learning_rate": 2.380952380952381e-05,
"loss": 0.1925,
"step": 7560
},
{
"epoch": 3.43,
"learning_rate": 2.376753170403964e-05,
"loss": 0.1934,
"step": 7570
},
{
"epoch": 3.44,
"learning_rate": 2.3725539598555475e-05,
"loss": 0.2158,
"step": 7580
},
{
"epoch": 3.44,
"learning_rate": 2.3683547493071302e-05,
"loss": 0.1461,
"step": 7590
},
{
"epoch": 3.45,
"learning_rate": 2.3641555387587136e-05,
"loss": 0.197,
"step": 7600
},
{
"epoch": 3.45,
"learning_rate": 2.3599563282102967e-05,
"loss": 0.2002,
"step": 7610
},
{
"epoch": 3.46,
"learning_rate": 2.3557571176618797e-05,
"loss": 0.1999,
"step": 7620
},
{
"epoch": 3.46,
"learning_rate": 2.3515579071134628e-05,
"loss": 0.1937,
"step": 7630
},
{
"epoch": 3.46,
"learning_rate": 2.347358696565046e-05,
"loss": 0.2235,
"step": 7640
},
{
"epoch": 3.47,
"learning_rate": 2.343159486016629e-05,
"loss": 0.1629,
"step": 7650
},
{
"epoch": 3.47,
"learning_rate": 2.3389602754682123e-05,
"loss": 0.1841,
"step": 7660
},
{
"epoch": 3.48,
"learning_rate": 2.334761064919795e-05,
"loss": 0.1777,
"step": 7670
},
{
"epoch": 3.48,
"learning_rate": 2.3305618543713785e-05,
"loss": 0.1614,
"step": 7680
},
{
"epoch": 3.49,
"learning_rate": 2.3263626438229612e-05,
"loss": 0.1603,
"step": 7690
},
{
"epoch": 3.49,
"learning_rate": 2.3221634332745446e-05,
"loss": 0.1738,
"step": 7700
},
{
"epoch": 3.5,
"learning_rate": 2.3179642227261277e-05,
"loss": 0.1783,
"step": 7710
},
{
"epoch": 3.5,
"learning_rate": 2.3137650121777107e-05,
"loss": 0.1138,
"step": 7720
},
{
"epoch": 3.51,
"learning_rate": 2.3095658016292938e-05,
"loss": 0.2049,
"step": 7730
},
{
"epoch": 3.51,
"learning_rate": 2.305366591080877e-05,
"loss": 0.1822,
"step": 7740
},
{
"epoch": 3.51,
"learning_rate": 2.30116738053246e-05,
"loss": 0.1557,
"step": 7750
},
{
"epoch": 3.52,
"learning_rate": 2.296968169984043e-05,
"loss": 0.1164,
"step": 7760
},
{
"epoch": 3.52,
"learning_rate": 2.292768959435626e-05,
"loss": 0.1758,
"step": 7770
},
{
"epoch": 3.53,
"learning_rate": 2.2885697488872094e-05,
"loss": 0.1895,
"step": 7780
},
{
"epoch": 3.53,
"learning_rate": 2.2843705383387925e-05,
"loss": 0.1773,
"step": 7790
},
{
"epoch": 3.54,
"learning_rate": 2.2801713277903756e-05,
"loss": 0.1436,
"step": 7800
},
{
"epoch": 3.54,
"learning_rate": 2.2759721172419586e-05,
"loss": 0.1845,
"step": 7810
},
{
"epoch": 3.55,
"learning_rate": 2.2717729066935417e-05,
"loss": 0.114,
"step": 7820
},
{
"epoch": 3.55,
"learning_rate": 2.267573696145125e-05,
"loss": 0.1862,
"step": 7830
},
{
"epoch": 3.56,
"learning_rate": 2.2633744855967078e-05,
"loss": 0.1607,
"step": 7840
},
{
"epoch": 3.56,
"learning_rate": 2.2591752750482912e-05,
"loss": 0.1789,
"step": 7850
},
{
"epoch": 3.56,
"learning_rate": 2.254976064499874e-05,
"loss": 0.182,
"step": 7860
},
{
"epoch": 3.57,
"learning_rate": 2.2507768539514574e-05,
"loss": 0.2082,
"step": 7870
},
{
"epoch": 3.57,
"learning_rate": 2.2465776434030404e-05,
"loss": 0.1971,
"step": 7880
},
{
"epoch": 3.58,
"learning_rate": 2.2423784328546235e-05,
"loss": 0.1448,
"step": 7890
},
{
"epoch": 3.58,
"learning_rate": 2.2381792223062065e-05,
"loss": 0.1773,
"step": 7900
},
{
"epoch": 3.59,
"learning_rate": 2.2339800117577896e-05,
"loss": 0.2034,
"step": 7910
},
{
"epoch": 3.59,
"learning_rate": 2.2297808012093727e-05,
"loss": 0.1992,
"step": 7920
},
{
"epoch": 3.6,
"learning_rate": 2.2255815906609557e-05,
"loss": 0.161,
"step": 7930
},
{
"epoch": 3.6,
"learning_rate": 2.2213823801125388e-05,
"loss": 0.1553,
"step": 7940
},
{
"epoch": 3.61,
"learning_rate": 2.2171831695641222e-05,
"loss": 0.2055,
"step": 7950
},
{
"epoch": 3.61,
"learning_rate": 2.212983959015705e-05,
"loss": 0.1869,
"step": 7960
},
{
"epoch": 3.61,
"learning_rate": 2.2087847484672883e-05,
"loss": 0.1552,
"step": 7970
},
{
"epoch": 3.62,
"learning_rate": 2.2045855379188714e-05,
"loss": 0.1365,
"step": 7980
},
{
"epoch": 3.62,
"learning_rate": 2.2003863273704545e-05,
"loss": 0.1701,
"step": 7990
},
{
"epoch": 3.63,
"learning_rate": 2.1961871168220375e-05,
"loss": 0.155,
"step": 8000
},
{
"epoch": 3.63,
"learning_rate": 2.1919879062736206e-05,
"loss": 0.1897,
"step": 8010
},
{
"epoch": 3.64,
"learning_rate": 2.187788695725204e-05,
"loss": 0.1694,
"step": 8020
},
{
"epoch": 3.64,
"learning_rate": 2.1835894851767867e-05,
"loss": 0.1441,
"step": 8030
},
{
"epoch": 3.65,
"learning_rate": 2.17939027462837e-05,
"loss": 0.1432,
"step": 8040
},
{
"epoch": 3.65,
"learning_rate": 2.1751910640799532e-05,
"loss": 0.1632,
"step": 8050
},
{
"epoch": 3.66,
"learning_rate": 2.1709918535315363e-05,
"loss": 0.1736,
"step": 8060
},
{
"epoch": 3.66,
"learning_rate": 2.1667926429831193e-05,
"loss": 0.1558,
"step": 8070
},
{
"epoch": 3.66,
"learning_rate": 2.1625934324347024e-05,
"loss": 0.208,
"step": 8080
},
{
"epoch": 3.67,
"learning_rate": 2.1583942218862854e-05,
"loss": 0.2087,
"step": 8090
},
{
"epoch": 3.67,
"learning_rate": 2.1541950113378685e-05,
"loss": 0.1949,
"step": 8100
},
{
"epoch": 3.68,
"learning_rate": 2.1499958007894516e-05,
"loss": 0.143,
"step": 8110
},
{
"epoch": 3.68,
"learning_rate": 2.145796590241035e-05,
"loss": 0.1497,
"step": 8120
},
{
"epoch": 3.69,
"learning_rate": 2.1415973796926177e-05,
"loss": 0.1881,
"step": 8130
},
{
"epoch": 3.69,
"learning_rate": 2.137398169144201e-05,
"loss": 0.1501,
"step": 8140
},
{
"epoch": 3.7,
"learning_rate": 2.133198958595784e-05,
"loss": 0.1381,
"step": 8150
},
{
"epoch": 3.7,
"learning_rate": 2.1289997480473672e-05,
"loss": 0.1759,
"step": 8160
},
{
"epoch": 3.71,
"learning_rate": 2.1248005374989503e-05,
"loss": 0.1658,
"step": 8170
},
{
"epoch": 3.71,
"learning_rate": 2.1206013269505334e-05,
"loss": 0.1768,
"step": 8180
},
{
"epoch": 3.71,
"learning_rate": 2.1164021164021164e-05,
"loss": 0.1881,
"step": 8190
},
{
"epoch": 3.72,
"learning_rate": 2.1122029058536995e-05,
"loss": 0.1735,
"step": 8200
},
{
"epoch": 3.72,
"learning_rate": 2.1080036953052826e-05,
"loss": 0.2223,
"step": 8210
},
{
"epoch": 3.73,
"learning_rate": 2.103804484756866e-05,
"loss": 0.1432,
"step": 8220
},
{
"epoch": 3.73,
"learning_rate": 2.099605274208449e-05,
"loss": 0.1662,
"step": 8230
},
{
"epoch": 3.74,
"learning_rate": 2.095406063660032e-05,
"loss": 0.1636,
"step": 8240
},
{
"epoch": 3.74,
"learning_rate": 2.091206853111615e-05,
"loss": 0.1835,
"step": 8250
},
{
"epoch": 3.75,
"learning_rate": 2.0870076425631982e-05,
"loss": 0.1545,
"step": 8260
},
{
"epoch": 3.75,
"learning_rate": 2.0828084320147813e-05,
"loss": 0.2281,
"step": 8270
},
{
"epoch": 3.76,
"learning_rate": 2.0786092214663643e-05,
"loss": 0.1726,
"step": 8280
},
{
"epoch": 3.76,
"learning_rate": 2.0744100109179477e-05,
"loss": 0.1248,
"step": 8290
},
{
"epoch": 3.76,
"learning_rate": 2.0702108003695305e-05,
"loss": 0.1508,
"step": 8300
},
{
"epoch": 3.77,
"learning_rate": 2.066011589821114e-05,
"loss": 0.1565,
"step": 8310
},
{
"epoch": 3.77,
"learning_rate": 2.061812379272697e-05,
"loss": 0.2121,
"step": 8320
},
{
"epoch": 3.78,
"learning_rate": 2.05761316872428e-05,
"loss": 0.1587,
"step": 8330
},
{
"epoch": 3.78,
"learning_rate": 2.053413958175863e-05,
"loss": 0.1541,
"step": 8340
},
{
"epoch": 3.79,
"learning_rate": 2.049214747627446e-05,
"loss": 0.1835,
"step": 8350
},
{
"epoch": 3.79,
"learning_rate": 2.0450155370790292e-05,
"loss": 0.1886,
"step": 8360
},
{
"epoch": 3.8,
"learning_rate": 2.0408163265306123e-05,
"loss": 0.1581,
"step": 8370
},
{
"epoch": 3.8,
"learning_rate": 2.0366171159821953e-05,
"loss": 0.1578,
"step": 8380
},
{
"epoch": 3.8,
"learning_rate": 2.0324179054337787e-05,
"loss": 0.1441,
"step": 8390
},
{
"epoch": 3.81,
"learning_rate": 2.0282186948853614e-05,
"loss": 0.1729,
"step": 8400
},
{
"epoch": 3.81,
"learning_rate": 2.024019484336945e-05,
"loss": 0.2067,
"step": 8410
},
{
"epoch": 3.82,
"learning_rate": 2.0198202737885276e-05,
"loss": 0.179,
"step": 8420
},
{
"epoch": 3.82,
"learning_rate": 2.015621063240111e-05,
"loss": 0.1642,
"step": 8430
},
{
"epoch": 3.83,
"learning_rate": 2.011421852691694e-05,
"loss": 0.1976,
"step": 8440
},
{
"epoch": 3.83,
"learning_rate": 2.007222642143277e-05,
"loss": 0.1712,
"step": 8450
},
{
"epoch": 3.84,
"learning_rate": 2.0030234315948605e-05,
"loss": 0.2516,
"step": 8460
},
{
"epoch": 3.84,
"learning_rate": 1.9988242210464432e-05,
"loss": 0.1858,
"step": 8470
},
{
"epoch": 3.85,
"learning_rate": 1.9946250104980266e-05,
"loss": 0.1805,
"step": 8480
},
{
"epoch": 3.85,
"learning_rate": 1.9904257999496097e-05,
"loss": 0.1791,
"step": 8490
},
{
"epoch": 3.85,
"learning_rate": 1.9862265894011928e-05,
"loss": 0.2049,
"step": 8500
},
{
"epoch": 3.86,
"learning_rate": 1.9820273788527758e-05,
"loss": 0.1448,
"step": 8510
},
{
"epoch": 3.86,
"learning_rate": 1.977828168304359e-05,
"loss": 0.1592,
"step": 8520
},
{
"epoch": 3.87,
"learning_rate": 1.973628957755942e-05,
"loss": 0.1704,
"step": 8530
},
{
"epoch": 3.87,
"learning_rate": 1.969429747207525e-05,
"loss": 0.1484,
"step": 8540
},
{
"epoch": 3.88,
"learning_rate": 1.965230536659108e-05,
"loss": 0.1747,
"step": 8550
},
{
"epoch": 3.88,
"learning_rate": 1.9610313261106915e-05,
"loss": 0.1985,
"step": 8560
},
{
"epoch": 3.89,
"learning_rate": 1.9568321155622742e-05,
"loss": 0.1557,
"step": 8570
},
{
"epoch": 3.89,
"learning_rate": 1.9526329050138576e-05,
"loss": 0.1058,
"step": 8580
},
{
"epoch": 3.9,
"learning_rate": 1.9484336944654403e-05,
"loss": 0.1576,
"step": 8590
},
{
"epoch": 3.9,
"learning_rate": 1.9442344839170237e-05,
"loss": 0.1813,
"step": 8600
},
{
"epoch": 3.9,
"learning_rate": 1.9400352733686068e-05,
"loss": 0.1937,
"step": 8610
},
{
"epoch": 3.91,
"learning_rate": 1.93583606282019e-05,
"loss": 0.1858,
"step": 8620
},
{
"epoch": 3.91,
"learning_rate": 1.931636852271773e-05,
"loss": 0.1325,
"step": 8630
},
{
"epoch": 3.92,
"learning_rate": 1.927437641723356e-05,
"loss": 0.1994,
"step": 8640
},
{
"epoch": 3.92,
"learning_rate": 1.923238431174939e-05,
"loss": 0.1609,
"step": 8650
},
{
"epoch": 3.93,
"learning_rate": 1.9190392206265225e-05,
"loss": 0.1663,
"step": 8660
},
{
"epoch": 3.93,
"learning_rate": 1.9148400100781055e-05,
"loss": 0.1572,
"step": 8670
},
{
"epoch": 3.94,
"learning_rate": 1.9106407995296886e-05,
"loss": 0.1186,
"step": 8680
},
{
"epoch": 3.94,
"learning_rate": 1.9064415889812717e-05,
"loss": 0.181,
"step": 8690
},
{
"epoch": 3.95,
"learning_rate": 1.9022423784328547e-05,
"loss": 0.1629,
"step": 8700
},
{
"epoch": 3.95,
"learning_rate": 1.8980431678844378e-05,
"loss": 0.1856,
"step": 8710
},
{
"epoch": 3.95,
"learning_rate": 1.893843957336021e-05,
"loss": 0.1444,
"step": 8720
},
{
"epoch": 3.96,
"learning_rate": 1.8896447467876043e-05,
"loss": 0.1074,
"step": 8730
},
{
"epoch": 3.96,
"learning_rate": 1.885445536239187e-05,
"loss": 0.1431,
"step": 8740
},
{
"epoch": 3.97,
"learning_rate": 1.8812463256907704e-05,
"loss": 0.1132,
"step": 8750
},
{
"epoch": 3.97,
"learning_rate": 1.877047115142353e-05,
"loss": 0.1309,
"step": 8760
},
{
"epoch": 3.98,
"learning_rate": 1.8728479045939365e-05,
"loss": 0.1658,
"step": 8770
},
{
"epoch": 3.98,
"learning_rate": 1.8686486940455196e-05,
"loss": 0.2118,
"step": 8780
},
{
"epoch": 3.99,
"learning_rate": 1.8644494834971026e-05,
"loss": 0.17,
"step": 8790
},
{
"epoch": 3.99,
"learning_rate": 1.8602502729486857e-05,
"loss": 0.1305,
"step": 8800
},
{
"epoch": 4.0,
"learning_rate": 1.8560510624002688e-05,
"loss": 0.1293,
"step": 8810
},
{
"epoch": 4.0,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.1396,
"step": 8820
},
{
"epoch": 4.0,
"eval_accuracy": 0.9577380952380953,
"eval_loss": 0.10973117500543594,
"eval_runtime": 367.2076,
"eval_samples_per_second": 32.025,
"eval_steps_per_second": 4.003,
"step": 8820
},
{
"epoch": 4.0,
"learning_rate": 1.8476526413034352e-05,
"loss": 0.1761,
"step": 8830
},
{
"epoch": 4.01,
"learning_rate": 1.843453430755018e-05,
"loss": 0.1402,
"step": 8840
},
{
"epoch": 4.01,
"learning_rate": 1.8392542202066014e-05,
"loss": 0.1743,
"step": 8850
},
{
"epoch": 4.02,
"learning_rate": 1.835055009658184e-05,
"loss": 0.1561,
"step": 8860
},
{
"epoch": 4.02,
"learning_rate": 1.8308557991097675e-05,
"loss": 0.1631,
"step": 8870
},
{
"epoch": 4.03,
"learning_rate": 1.8266565885613506e-05,
"loss": 0.1708,
"step": 8880
},
{
"epoch": 4.03,
"learning_rate": 1.8224573780129336e-05,
"loss": 0.1816,
"step": 8890
},
{
"epoch": 4.04,
"learning_rate": 1.818258167464517e-05,
"loss": 0.1636,
"step": 8900
},
{
"epoch": 4.04,
"learning_rate": 1.8140589569160997e-05,
"loss": 0.2342,
"step": 8910
},
{
"epoch": 4.05,
"learning_rate": 1.809859746367683e-05,
"loss": 0.2459,
"step": 8920
},
{
"epoch": 4.05,
"learning_rate": 1.805660535819266e-05,
"loss": 0.1901,
"step": 8930
},
{
"epoch": 4.05,
"learning_rate": 1.8014613252708493e-05,
"loss": 0.162,
"step": 8940
},
{
"epoch": 4.06,
"learning_rate": 1.7972621147224323e-05,
"loss": 0.1993,
"step": 8950
},
{
"epoch": 4.06,
"learning_rate": 1.7930629041740154e-05,
"loss": 0.1481,
"step": 8960
},
{
"epoch": 4.07,
"learning_rate": 1.7888636936255985e-05,
"loss": 0.1586,
"step": 8970
},
{
"epoch": 4.07,
"learning_rate": 1.7846644830771815e-05,
"loss": 0.1775,
"step": 8980
},
{
"epoch": 4.08,
"learning_rate": 1.7804652725287646e-05,
"loss": 0.1907,
"step": 8990
},
{
"epoch": 4.08,
"learning_rate": 1.776266061980348e-05,
"loss": 0.1314,
"step": 9000
},
{
"epoch": 4.09,
"learning_rate": 1.7720668514319307e-05,
"loss": 0.1537,
"step": 9010
},
{
"epoch": 4.09,
"learning_rate": 1.767867640883514e-05,
"loss": 0.158,
"step": 9020
},
{
"epoch": 4.1,
"learning_rate": 1.763668430335097e-05,
"loss": 0.1314,
"step": 9030
},
{
"epoch": 4.1,
"learning_rate": 1.7594692197866803e-05,
"loss": 0.1674,
"step": 9040
},
{
"epoch": 4.1,
"learning_rate": 1.7552700092382633e-05,
"loss": 0.1222,
"step": 9050
},
{
"epoch": 4.11,
"learning_rate": 1.7510707986898464e-05,
"loss": 0.1355,
"step": 9060
},
{
"epoch": 4.11,
"learning_rate": 1.7468715881414294e-05,
"loss": 0.1368,
"step": 9070
},
{
"epoch": 4.12,
"learning_rate": 1.7426723775930125e-05,
"loss": 0.1906,
"step": 9080
},
{
"epoch": 4.12,
"learning_rate": 1.7384731670445956e-05,
"loss": 0.1932,
"step": 9090
},
{
"epoch": 4.13,
"learning_rate": 1.7342739564961786e-05,
"loss": 0.1273,
"step": 9100
},
{
"epoch": 4.13,
"learning_rate": 1.730074745947762e-05,
"loss": 0.1483,
"step": 9110
},
{
"epoch": 4.14,
"learning_rate": 1.725875535399345e-05,
"loss": 0.1102,
"step": 9120
},
{
"epoch": 4.14,
"learning_rate": 1.721676324850928e-05,
"loss": 0.157,
"step": 9130
},
{
"epoch": 4.15,
"learning_rate": 1.7174771143025112e-05,
"loss": 0.1757,
"step": 9140
},
{
"epoch": 4.15,
"learning_rate": 1.7132779037540943e-05,
"loss": 0.1424,
"step": 9150
},
{
"epoch": 4.15,
"learning_rate": 1.7090786932056774e-05,
"loss": 0.1598,
"step": 9160
},
{
"epoch": 4.16,
"learning_rate": 1.7048794826572608e-05,
"loss": 0.1767,
"step": 9170
},
{
"epoch": 4.16,
"learning_rate": 1.7006802721088435e-05,
"loss": 0.1645,
"step": 9180
},
{
"epoch": 4.17,
"learning_rate": 1.696481061560427e-05,
"loss": 0.1674,
"step": 9190
},
{
"epoch": 4.17,
"learning_rate": 1.6922818510120096e-05,
"loss": 0.1508,
"step": 9200
},
{
"epoch": 4.18,
"learning_rate": 1.688082640463593e-05,
"loss": 0.2066,
"step": 9210
},
{
"epoch": 4.18,
"learning_rate": 1.683883429915176e-05,
"loss": 0.1563,
"step": 9220
},
{
"epoch": 4.19,
"learning_rate": 1.679684219366759e-05,
"loss": 0.123,
"step": 9230
},
{
"epoch": 4.19,
"learning_rate": 1.6754850088183422e-05,
"loss": 0.1346,
"step": 9240
},
{
"epoch": 4.19,
"learning_rate": 1.6712857982699253e-05,
"loss": 0.1415,
"step": 9250
},
{
"epoch": 4.2,
"learning_rate": 1.6670865877215083e-05,
"loss": 0.1549,
"step": 9260
},
{
"epoch": 4.2,
"learning_rate": 1.6628873771730914e-05,
"loss": 0.1502,
"step": 9270
},
{
"epoch": 4.21,
"learning_rate": 1.6586881666246745e-05,
"loss": 0.106,
"step": 9280
},
{
"epoch": 4.21,
"learning_rate": 1.654488956076258e-05,
"loss": 0.1116,
"step": 9290
},
{
"epoch": 4.22,
"learning_rate": 1.6502897455278406e-05,
"loss": 0.1071,
"step": 9300
},
{
"epoch": 4.22,
"learning_rate": 1.646090534979424e-05,
"loss": 0.1642,
"step": 9310
},
{
"epoch": 4.23,
"learning_rate": 1.641891324431007e-05,
"loss": 0.1327,
"step": 9320
},
{
"epoch": 4.23,
"learning_rate": 1.63769211388259e-05,
"loss": 0.1179,
"step": 9330
},
{
"epoch": 4.24,
"learning_rate": 1.6334929033341735e-05,
"loss": 0.1253,
"step": 9340
},
{
"epoch": 4.24,
"learning_rate": 1.6292936927857563e-05,
"loss": 0.145,
"step": 9350
},
{
"epoch": 4.24,
"learning_rate": 1.6250944822373397e-05,
"loss": 0.164,
"step": 9360
},
{
"epoch": 4.25,
"learning_rate": 1.6208952716889224e-05,
"loss": 0.1161,
"step": 9370
},
{
"epoch": 4.25,
"learning_rate": 1.6166960611405058e-05,
"loss": 0.1387,
"step": 9380
},
{
"epoch": 4.26,
"learning_rate": 1.612496850592089e-05,
"loss": 0.1617,
"step": 9390
},
{
"epoch": 4.26,
"learning_rate": 1.608297640043672e-05,
"loss": 0.1252,
"step": 9400
},
{
"epoch": 4.27,
"learning_rate": 1.604098429495255e-05,
"loss": 0.0922,
"step": 9410
},
{
"epoch": 4.27,
"learning_rate": 1.599899218946838e-05,
"loss": 0.2111,
"step": 9420
},
{
"epoch": 4.28,
"learning_rate": 1.595700008398421e-05,
"loss": 0.1315,
"step": 9430
},
{
"epoch": 4.28,
"learning_rate": 1.591500797850004e-05,
"loss": 0.1494,
"step": 9440
},
{
"epoch": 4.29,
"learning_rate": 1.5873015873015872e-05,
"loss": 0.1445,
"step": 9450
},
{
"epoch": 4.29,
"learning_rate": 1.5831023767531706e-05,
"loss": 0.1181,
"step": 9460
},
{
"epoch": 4.29,
"learning_rate": 1.5789031662047534e-05,
"loss": 0.1333,
"step": 9470
},
{
"epoch": 4.3,
"learning_rate": 1.5747039556563368e-05,
"loss": 0.1353,
"step": 9480
},
{
"epoch": 4.3,
"learning_rate": 1.5705047451079198e-05,
"loss": 0.1011,
"step": 9490
},
{
"epoch": 4.31,
"learning_rate": 1.566305534559503e-05,
"loss": 0.2215,
"step": 9500
},
{
"epoch": 4.31,
"learning_rate": 1.562106324011086e-05,
"loss": 0.143,
"step": 9510
},
{
"epoch": 4.32,
"learning_rate": 1.557907113462669e-05,
"loss": 0.1381,
"step": 9520
},
{
"epoch": 4.32,
"learning_rate": 1.5537079029142524e-05,
"loss": 0.1706,
"step": 9530
},
{
"epoch": 4.33,
"learning_rate": 1.549508692365835e-05,
"loss": 0.1207,
"step": 9540
},
{
"epoch": 4.33,
"learning_rate": 1.5453094818174186e-05,
"loss": 0.2268,
"step": 9550
},
{
"epoch": 4.34,
"learning_rate": 1.5411102712690016e-05,
"loss": 0.1693,
"step": 9560
},
{
"epoch": 4.34,
"learning_rate": 1.5369110607205847e-05,
"loss": 0.1384,
"step": 9570
},
{
"epoch": 4.34,
"learning_rate": 1.5327118501721677e-05,
"loss": 0.1954,
"step": 9580
},
{
"epoch": 4.35,
"learning_rate": 1.5285126396237508e-05,
"loss": 0.1763,
"step": 9590
},
{
"epoch": 4.35,
"learning_rate": 1.5243134290753339e-05,
"loss": 0.1152,
"step": 9600
},
{
"epoch": 4.36,
"learning_rate": 1.5201142185269171e-05,
"loss": 0.1185,
"step": 9610
},
{
"epoch": 4.36,
"learning_rate": 1.5159150079785e-05,
"loss": 0.1546,
"step": 9620
},
{
"epoch": 4.37,
"learning_rate": 1.5117157974300832e-05,
"loss": 0.1798,
"step": 9630
},
{
"epoch": 4.37,
"learning_rate": 1.5075165868816663e-05,
"loss": 0.1798,
"step": 9640
},
{
"epoch": 4.38,
"learning_rate": 1.5033173763332495e-05,
"loss": 0.1469,
"step": 9650
},
{
"epoch": 4.38,
"learning_rate": 1.4991181657848324e-05,
"loss": 0.1323,
"step": 9660
},
{
"epoch": 4.39,
"learning_rate": 1.4949189552364157e-05,
"loss": 0.1291,
"step": 9670
},
{
"epoch": 4.39,
"learning_rate": 1.4907197446879986e-05,
"loss": 0.1488,
"step": 9680
},
{
"epoch": 4.39,
"learning_rate": 1.4865205341395818e-05,
"loss": 0.1434,
"step": 9690
},
{
"epoch": 4.4,
"learning_rate": 1.4823213235911648e-05,
"loss": 0.1468,
"step": 9700
},
{
"epoch": 4.4,
"learning_rate": 1.478122113042748e-05,
"loss": 0.1705,
"step": 9710
},
{
"epoch": 4.41,
"learning_rate": 1.473922902494331e-05,
"loss": 0.1306,
"step": 9720
},
{
"epoch": 4.41,
"learning_rate": 1.4697236919459142e-05,
"loss": 0.2007,
"step": 9730
},
{
"epoch": 4.42,
"learning_rate": 1.4655244813974973e-05,
"loss": 0.125,
"step": 9740
},
{
"epoch": 4.42,
"learning_rate": 1.4613252708490805e-05,
"loss": 0.1088,
"step": 9750
},
{
"epoch": 4.43,
"learning_rate": 1.4571260603006637e-05,
"loss": 0.1026,
"step": 9760
},
{
"epoch": 4.43,
"learning_rate": 1.4529268497522466e-05,
"loss": 0.1476,
"step": 9770
},
{
"epoch": 4.44,
"learning_rate": 1.4487276392038299e-05,
"loss": 0.2452,
"step": 9780
},
{
"epoch": 4.44,
"learning_rate": 1.4445284286554128e-05,
"loss": 0.109,
"step": 9790
},
{
"epoch": 4.44,
"learning_rate": 1.440329218106996e-05,
"loss": 0.1544,
"step": 9800
},
{
"epoch": 4.45,
"learning_rate": 1.436130007558579e-05,
"loss": 0.1193,
"step": 9810
},
{
"epoch": 4.45,
"learning_rate": 1.4319307970101623e-05,
"loss": 0.1186,
"step": 9820
},
{
"epoch": 4.46,
"learning_rate": 1.4277315864617452e-05,
"loss": 0.1424,
"step": 9830
},
{
"epoch": 4.46,
"learning_rate": 1.4235323759133284e-05,
"loss": 0.1219,
"step": 9840
},
{
"epoch": 4.47,
"learning_rate": 1.4193331653649113e-05,
"loss": 0.1719,
"step": 9850
},
{
"epoch": 4.47,
"learning_rate": 1.4151339548164946e-05,
"loss": 0.1555,
"step": 9860
},
{
"epoch": 4.48,
"learning_rate": 1.4109347442680776e-05,
"loss": 0.1171,
"step": 9870
},
{
"epoch": 4.48,
"learning_rate": 1.4067355337196608e-05,
"loss": 0.1117,
"step": 9880
},
{
"epoch": 4.49,
"learning_rate": 1.4025363231712437e-05,
"loss": 0.1905,
"step": 9890
},
{
"epoch": 4.49,
"learning_rate": 1.398337112622827e-05,
"loss": 0.1336,
"step": 9900
},
{
"epoch": 4.49,
"learning_rate": 1.39413790207441e-05,
"loss": 0.1135,
"step": 9910
},
{
"epoch": 4.5,
"learning_rate": 1.3899386915259933e-05,
"loss": 0.1345,
"step": 9920
},
{
"epoch": 4.5,
"learning_rate": 1.3857394809775762e-05,
"loss": 0.1361,
"step": 9930
},
{
"epoch": 4.51,
"learning_rate": 1.3815402704291594e-05,
"loss": 0.167,
"step": 9940
},
{
"epoch": 4.51,
"learning_rate": 1.3773410598807423e-05,
"loss": 0.1534,
"step": 9950
},
{
"epoch": 4.52,
"learning_rate": 1.3731418493323255e-05,
"loss": 0.1341,
"step": 9960
},
{
"epoch": 4.52,
"learning_rate": 1.3689426387839088e-05,
"loss": 0.1112,
"step": 9970
},
{
"epoch": 4.53,
"learning_rate": 1.3647434282354918e-05,
"loss": 0.1508,
"step": 9980
},
{
"epoch": 4.53,
"learning_rate": 1.360544217687075e-05,
"loss": 0.1629,
"step": 9990
},
{
"epoch": 4.54,
"learning_rate": 1.356345007138658e-05,
"loss": 0.1903,
"step": 10000
},
{
"epoch": 4.54,
"learning_rate": 1.3521457965902412e-05,
"loss": 0.196,
"step": 10010
},
{
"epoch": 4.54,
"learning_rate": 1.347946586041824e-05,
"loss": 0.1564,
"step": 10020
},
{
"epoch": 4.55,
"learning_rate": 1.3437473754934073e-05,
"loss": 0.1358,
"step": 10030
},
{
"epoch": 4.55,
"learning_rate": 1.3395481649449904e-05,
"loss": 0.1142,
"step": 10040
},
{
"epoch": 4.56,
"learning_rate": 1.3353489543965736e-05,
"loss": 0.087,
"step": 10050
},
{
"epoch": 4.56,
"learning_rate": 1.3311497438481565e-05,
"loss": 0.0977,
"step": 10060
},
{
"epoch": 4.57,
"learning_rate": 1.3269505332997397e-05,
"loss": 0.143,
"step": 10070
},
{
"epoch": 4.57,
"learning_rate": 1.3227513227513228e-05,
"loss": 0.1471,
"step": 10080
},
{
"epoch": 4.58,
"learning_rate": 1.318552112202906e-05,
"loss": 0.1217,
"step": 10090
},
{
"epoch": 4.58,
"learning_rate": 1.314352901654489e-05,
"loss": 0.1614,
"step": 10100
},
{
"epoch": 4.58,
"learning_rate": 1.3101536911060722e-05,
"loss": 0.1489,
"step": 10110
},
{
"epoch": 4.59,
"learning_rate": 1.305954480557655e-05,
"loss": 0.1654,
"step": 10120
},
{
"epoch": 4.59,
"learning_rate": 1.3017552700092383e-05,
"loss": 0.1685,
"step": 10130
},
{
"epoch": 4.6,
"learning_rate": 1.2975560594608214e-05,
"loss": 0.1608,
"step": 10140
},
{
"epoch": 4.6,
"learning_rate": 1.2933568489124046e-05,
"loss": 0.1644,
"step": 10150
},
{
"epoch": 4.61,
"learning_rate": 1.2891576383639875e-05,
"loss": 0.1315,
"step": 10160
},
{
"epoch": 4.61,
"learning_rate": 1.2849584278155707e-05,
"loss": 0.1899,
"step": 10170
},
{
"epoch": 4.62,
"learning_rate": 1.2807592172671536e-05,
"loss": 0.1803,
"step": 10180
},
{
"epoch": 4.62,
"learning_rate": 1.2765600067187368e-05,
"loss": 0.1755,
"step": 10190
},
{
"epoch": 4.63,
"learning_rate": 1.2723607961703203e-05,
"loss": 0.1142,
"step": 10200
},
{
"epoch": 4.63,
"learning_rate": 1.2681615856219031e-05,
"loss": 0.1808,
"step": 10210
},
{
"epoch": 4.63,
"learning_rate": 1.2639623750734864e-05,
"loss": 0.1223,
"step": 10220
},
{
"epoch": 4.64,
"learning_rate": 1.2597631645250693e-05,
"loss": 0.1324,
"step": 10230
},
{
"epoch": 4.64,
"learning_rate": 1.2555639539766525e-05,
"loss": 0.1716,
"step": 10240
},
{
"epoch": 4.65,
"learning_rate": 1.2513647434282356e-05,
"loss": 0.1852,
"step": 10250
},
{
"epoch": 4.65,
"learning_rate": 1.2471655328798186e-05,
"loss": 0.2009,
"step": 10260
},
{
"epoch": 4.66,
"learning_rate": 1.2429663223314017e-05,
"loss": 0.1367,
"step": 10270
},
{
"epoch": 4.66,
"learning_rate": 1.2387671117829848e-05,
"loss": 0.146,
"step": 10280
},
{
"epoch": 4.67,
"learning_rate": 1.2345679012345678e-05,
"loss": 0.1771,
"step": 10290
},
{
"epoch": 4.67,
"learning_rate": 1.230368690686151e-05,
"loss": 0.134,
"step": 10300
},
{
"epoch": 4.68,
"learning_rate": 1.2261694801377343e-05,
"loss": 0.1289,
"step": 10310
},
{
"epoch": 4.68,
"learning_rate": 1.2219702695893174e-05,
"loss": 0.1955,
"step": 10320
},
{
"epoch": 4.68,
"learning_rate": 1.2177710590409004e-05,
"loss": 0.1249,
"step": 10330
},
{
"epoch": 4.69,
"learning_rate": 1.2135718484924835e-05,
"loss": 0.1225,
"step": 10340
},
{
"epoch": 4.69,
"learning_rate": 1.2093726379440666e-05,
"loss": 0.1328,
"step": 10350
},
{
"epoch": 4.7,
"learning_rate": 1.2051734273956498e-05,
"loss": 0.0755,
"step": 10360
},
{
"epoch": 4.7,
"learning_rate": 1.2009742168472328e-05,
"loss": 0.1389,
"step": 10370
},
{
"epoch": 4.71,
"learning_rate": 1.1967750062988159e-05,
"loss": 0.1366,
"step": 10380
},
{
"epoch": 4.71,
"learning_rate": 1.192575795750399e-05,
"loss": 0.0994,
"step": 10390
},
{
"epoch": 4.72,
"learning_rate": 1.188376585201982e-05,
"loss": 0.1095,
"step": 10400
},
{
"epoch": 4.72,
"learning_rate": 1.1841773746535651e-05,
"loss": 0.1878,
"step": 10410
},
{
"epoch": 4.73,
"learning_rate": 1.1799781641051483e-05,
"loss": 0.1576,
"step": 10420
},
{
"epoch": 4.73,
"learning_rate": 1.1757789535567314e-05,
"loss": 0.1459,
"step": 10430
},
{
"epoch": 4.73,
"learning_rate": 1.1715797430083145e-05,
"loss": 0.1711,
"step": 10440
},
{
"epoch": 4.74,
"learning_rate": 1.1673805324598975e-05,
"loss": 0.1407,
"step": 10450
},
{
"epoch": 4.74,
"learning_rate": 1.1631813219114806e-05,
"loss": 0.1291,
"step": 10460
},
{
"epoch": 4.75,
"learning_rate": 1.1589821113630638e-05,
"loss": 0.1389,
"step": 10470
},
{
"epoch": 4.75,
"learning_rate": 1.1547829008146469e-05,
"loss": 0.0984,
"step": 10480
},
{
"epoch": 4.76,
"learning_rate": 1.15058369026623e-05,
"loss": 0.0981,
"step": 10490
},
{
"epoch": 4.76,
"learning_rate": 1.146384479717813e-05,
"loss": 0.1302,
"step": 10500
},
{
"epoch": 4.77,
"learning_rate": 1.1421852691693963e-05,
"loss": 0.0999,
"step": 10510
},
{
"epoch": 4.77,
"learning_rate": 1.1379860586209793e-05,
"loss": 0.1605,
"step": 10520
},
{
"epoch": 4.78,
"learning_rate": 1.1337868480725626e-05,
"loss": 0.1704,
"step": 10530
},
{
"epoch": 4.78,
"learning_rate": 1.1295876375241456e-05,
"loss": 0.1254,
"step": 10540
},
{
"epoch": 4.78,
"learning_rate": 1.1253884269757287e-05,
"loss": 0.165,
"step": 10550
},
{
"epoch": 4.79,
"learning_rate": 1.1211892164273117e-05,
"loss": 0.1244,
"step": 10560
},
{
"epoch": 4.79,
"learning_rate": 1.1169900058788948e-05,
"loss": 0.2059,
"step": 10570
},
{
"epoch": 4.8,
"learning_rate": 1.1127907953304779e-05,
"loss": 0.1142,
"step": 10580
},
{
"epoch": 4.8,
"learning_rate": 1.1085915847820611e-05,
"loss": 0.1311,
"step": 10590
},
{
"epoch": 4.81,
"learning_rate": 1.1043923742336442e-05,
"loss": 0.1812,
"step": 10600
},
{
"epoch": 4.81,
"learning_rate": 1.1001931636852272e-05,
"loss": 0.1265,
"step": 10610
},
{
"epoch": 4.82,
"learning_rate": 1.0959939531368103e-05,
"loss": 0.1313,
"step": 10620
},
{
"epoch": 4.82,
"learning_rate": 1.0917947425883934e-05,
"loss": 0.1423,
"step": 10630
},
{
"epoch": 4.83,
"learning_rate": 1.0875955320399766e-05,
"loss": 0.1682,
"step": 10640
},
{
"epoch": 4.83,
"learning_rate": 1.0833963214915597e-05,
"loss": 0.1166,
"step": 10650
},
{
"epoch": 4.83,
"learning_rate": 1.0791971109431427e-05,
"loss": 0.1204,
"step": 10660
},
{
"epoch": 4.84,
"learning_rate": 1.0749979003947258e-05,
"loss": 0.1602,
"step": 10670
},
{
"epoch": 4.84,
"learning_rate": 1.0707986898463088e-05,
"loss": 0.1053,
"step": 10680
},
{
"epoch": 4.85,
"learning_rate": 1.066599479297892e-05,
"loss": 0.1445,
"step": 10690
},
{
"epoch": 4.85,
"learning_rate": 1.0624002687494751e-05,
"loss": 0.1155,
"step": 10700
},
{
"epoch": 4.86,
"learning_rate": 1.0582010582010582e-05,
"loss": 0.2259,
"step": 10710
},
{
"epoch": 4.86,
"learning_rate": 1.0540018476526413e-05,
"loss": 0.1797,
"step": 10720
},
{
"epoch": 4.87,
"learning_rate": 1.0498026371042245e-05,
"loss": 0.1197,
"step": 10730
},
{
"epoch": 4.87,
"learning_rate": 1.0456034265558076e-05,
"loss": 0.1076,
"step": 10740
},
{
"epoch": 4.88,
"learning_rate": 1.0414042160073906e-05,
"loss": 0.1422,
"step": 10750
},
{
"epoch": 4.88,
"learning_rate": 1.0372050054589739e-05,
"loss": 0.1681,
"step": 10760
},
{
"epoch": 4.88,
"learning_rate": 1.033005794910557e-05,
"loss": 0.1425,
"step": 10770
},
{
"epoch": 4.89,
"learning_rate": 1.02880658436214e-05,
"loss": 0.1195,
"step": 10780
},
{
"epoch": 4.89,
"learning_rate": 1.024607373813723e-05,
"loss": 0.1085,
"step": 10790
},
{
"epoch": 4.9,
"learning_rate": 1.0204081632653061e-05,
"loss": 0.1748,
"step": 10800
},
{
"epoch": 4.9,
"learning_rate": 1.0162089527168894e-05,
"loss": 0.1153,
"step": 10810
},
{
"epoch": 4.91,
"learning_rate": 1.0120097421684724e-05,
"loss": 0.1013,
"step": 10820
},
{
"epoch": 4.91,
"learning_rate": 1.0078105316200555e-05,
"loss": 0.1102,
"step": 10830
},
{
"epoch": 4.92,
"learning_rate": 1.0036113210716386e-05,
"loss": 0.1761,
"step": 10840
},
{
"epoch": 4.92,
"learning_rate": 9.994121105232216e-06,
"loss": 0.1403,
"step": 10850
},
{
"epoch": 4.93,
"learning_rate": 9.952128999748048e-06,
"loss": 0.1463,
"step": 10860
},
{
"epoch": 4.93,
"learning_rate": 9.910136894263879e-06,
"loss": 0.1321,
"step": 10870
},
{
"epoch": 4.93,
"learning_rate": 9.86814478877971e-06,
"loss": 0.1005,
"step": 10880
},
{
"epoch": 4.94,
"learning_rate": 9.82615268329554e-06,
"loss": 0.1104,
"step": 10890
},
{
"epoch": 4.94,
"learning_rate": 9.784160577811371e-06,
"loss": 0.1182,
"step": 10900
},
{
"epoch": 4.95,
"learning_rate": 9.742168472327202e-06,
"loss": 0.1172,
"step": 10910
},
{
"epoch": 4.95,
"learning_rate": 9.700176366843034e-06,
"loss": 0.0983,
"step": 10920
},
{
"epoch": 4.96,
"learning_rate": 9.658184261358865e-06,
"loss": 0.134,
"step": 10930
},
{
"epoch": 4.96,
"learning_rate": 9.616192155874695e-06,
"loss": 0.1523,
"step": 10940
},
{
"epoch": 4.97,
"learning_rate": 9.574200050390528e-06,
"loss": 0.2092,
"step": 10950
},
{
"epoch": 4.97,
"learning_rate": 9.532207944906358e-06,
"loss": 0.1306,
"step": 10960
},
{
"epoch": 4.97,
"learning_rate": 9.490215839422189e-06,
"loss": 0.1116,
"step": 10970
},
{
"epoch": 4.98,
"learning_rate": 9.448223733938021e-06,
"loss": 0.1711,
"step": 10980
},
{
"epoch": 4.98,
"learning_rate": 9.406231628453852e-06,
"loss": 0.1727,
"step": 10990
},
{
"epoch": 4.99,
"learning_rate": 9.364239522969683e-06,
"loss": 0.1505,
"step": 11000
},
{
"epoch": 4.99,
"learning_rate": 9.322247417485513e-06,
"loss": 0.1533,
"step": 11010
},
{
"epoch": 5.0,
"learning_rate": 9.280255312001344e-06,
"loss": 0.1177,
"step": 11020
},
{
"epoch": 5.0,
"eval_accuracy": 0.9757653061224489,
"eval_loss": 0.0650193989276886,
"eval_runtime": 478.5406,
"eval_samples_per_second": 24.575,
"eval_steps_per_second": 3.072,
"step": 11025
},
{
"epoch": 5.0,
"learning_rate": 9.238263206517176e-06,
"loss": 0.1531,
"step": 11030
},
{
"epoch": 5.01,
"learning_rate": 9.196271101033007e-06,
"loss": 0.1578,
"step": 11040
},
{
"epoch": 5.01,
"learning_rate": 9.154278995548837e-06,
"loss": 0.1007,
"step": 11050
},
{
"epoch": 5.02,
"learning_rate": 9.112286890064668e-06,
"loss": 0.1154,
"step": 11060
},
{
"epoch": 5.02,
"learning_rate": 9.070294784580499e-06,
"loss": 0.1624,
"step": 11070
},
{
"epoch": 5.02,
"learning_rate": 9.02830267909633e-06,
"loss": 0.0991,
"step": 11080
},
{
"epoch": 5.03,
"learning_rate": 8.986310573612162e-06,
"loss": 0.1706,
"step": 11090
},
{
"epoch": 5.03,
"learning_rate": 8.944318468127992e-06,
"loss": 0.1551,
"step": 11100
},
{
"epoch": 5.04,
"learning_rate": 8.902326362643823e-06,
"loss": 0.1213,
"step": 11110
},
{
"epoch": 5.04,
"learning_rate": 8.860334257159654e-06,
"loss": 0.0783,
"step": 11120
},
{
"epoch": 5.05,
"learning_rate": 8.818342151675484e-06,
"loss": 0.1175,
"step": 11130
},
{
"epoch": 5.05,
"learning_rate": 8.776350046191317e-06,
"loss": 0.135,
"step": 11140
},
{
"epoch": 5.06,
"learning_rate": 8.734357940707147e-06,
"loss": 0.1053,
"step": 11150
},
{
"epoch": 5.06,
"learning_rate": 8.692365835222978e-06,
"loss": 0.1459,
"step": 11160
},
{
"epoch": 5.07,
"learning_rate": 8.65037372973881e-06,
"loss": 0.1215,
"step": 11170
},
{
"epoch": 5.07,
"learning_rate": 8.60838162425464e-06,
"loss": 0.0972,
"step": 11180
},
{
"epoch": 5.07,
"learning_rate": 8.566389518770471e-06,
"loss": 0.1358,
"step": 11190
},
{
"epoch": 5.08,
"learning_rate": 8.524397413286304e-06,
"loss": 0.0891,
"step": 11200
},
{
"epoch": 5.08,
"learning_rate": 8.482405307802134e-06,
"loss": 0.1903,
"step": 11210
},
{
"epoch": 5.09,
"learning_rate": 8.440413202317965e-06,
"loss": 0.1794,
"step": 11220
},
{
"epoch": 5.09,
"learning_rate": 8.398421096833796e-06,
"loss": 0.1384,
"step": 11230
},
{
"epoch": 5.1,
"learning_rate": 8.356428991349626e-06,
"loss": 0.1902,
"step": 11240
},
{
"epoch": 5.1,
"learning_rate": 8.314436885865457e-06,
"loss": 0.1188,
"step": 11250
},
{
"epoch": 5.11,
"learning_rate": 8.27244478038129e-06,
"loss": 0.1066,
"step": 11260
},
{
"epoch": 5.11,
"learning_rate": 8.23045267489712e-06,
"loss": 0.1445,
"step": 11270
},
{
"epoch": 5.12,
"learning_rate": 8.18846056941295e-06,
"loss": 0.1754,
"step": 11280
},
{
"epoch": 5.12,
"learning_rate": 8.146468463928781e-06,
"loss": 0.1395,
"step": 11290
},
{
"epoch": 5.12,
"learning_rate": 8.104476358444612e-06,
"loss": 0.1531,
"step": 11300
},
{
"epoch": 5.13,
"learning_rate": 8.062484252960444e-06,
"loss": 0.1188,
"step": 11310
},
{
"epoch": 5.13,
"learning_rate": 8.020492147476275e-06,
"loss": 0.1344,
"step": 11320
},
{
"epoch": 5.14,
"learning_rate": 7.978500041992106e-06,
"loss": 0.144,
"step": 11330
},
{
"epoch": 5.14,
"learning_rate": 7.936507936507936e-06,
"loss": 0.1306,
"step": 11340
},
{
"epoch": 5.15,
"learning_rate": 7.894515831023767e-06,
"loss": 0.1789,
"step": 11350
},
{
"epoch": 5.15,
"learning_rate": 7.852523725539599e-06,
"loss": 0.1291,
"step": 11360
},
{
"epoch": 5.16,
"learning_rate": 7.81053162005543e-06,
"loss": 0.116,
"step": 11370
},
{
"epoch": 5.16,
"learning_rate": 7.768539514571262e-06,
"loss": 0.1477,
"step": 11380
},
{
"epoch": 5.17,
"learning_rate": 7.726547409087093e-06,
"loss": 0.1365,
"step": 11390
},
{
"epoch": 5.17,
"learning_rate": 7.684555303602923e-06,
"loss": 0.1187,
"step": 11400
},
{
"epoch": 5.17,
"learning_rate": 7.642563198118754e-06,
"loss": 0.1418,
"step": 11410
},
{
"epoch": 5.18,
"learning_rate": 7.6005710926345855e-06,
"loss": 0.1115,
"step": 11420
},
{
"epoch": 5.18,
"learning_rate": 7.558578987150416e-06,
"loss": 0.1762,
"step": 11430
},
{
"epoch": 5.19,
"learning_rate": 7.516586881666248e-06,
"loss": 0.124,
"step": 11440
},
{
"epoch": 5.19,
"learning_rate": 7.474594776182078e-06,
"loss": 0.1301,
"step": 11450
},
{
"epoch": 5.2,
"learning_rate": 7.432602670697909e-06,
"loss": 0.1246,
"step": 11460
},
{
"epoch": 5.2,
"learning_rate": 7.39061056521374e-06,
"loss": 0.0906,
"step": 11470
},
{
"epoch": 5.21,
"learning_rate": 7.348618459729571e-06,
"loss": 0.1391,
"step": 11480
},
{
"epoch": 5.21,
"learning_rate": 7.3066263542454025e-06,
"loss": 0.1296,
"step": 11490
},
{
"epoch": 5.22,
"learning_rate": 7.264634248761233e-06,
"loss": 0.0977,
"step": 11500
},
{
"epoch": 5.22,
"learning_rate": 7.222642143277064e-06,
"loss": 0.1623,
"step": 11510
},
{
"epoch": 5.22,
"learning_rate": 7.180650037792895e-06,
"loss": 0.1041,
"step": 11520
},
{
"epoch": 5.23,
"learning_rate": 7.138657932308726e-06,
"loss": 0.1379,
"step": 11530
},
{
"epoch": 5.23,
"learning_rate": 7.096665826824557e-06,
"loss": 0.1142,
"step": 11540
},
{
"epoch": 5.24,
"learning_rate": 7.054673721340388e-06,
"loss": 0.1486,
"step": 11550
},
{
"epoch": 5.24,
"learning_rate": 7.012681615856219e-06,
"loss": 0.1324,
"step": 11560
},
{
"epoch": 5.25,
"learning_rate": 6.97068951037205e-06,
"loss": 0.1177,
"step": 11570
},
{
"epoch": 5.25,
"learning_rate": 6.928697404887881e-06,
"loss": 0.0854,
"step": 11580
},
{
"epoch": 5.26,
"learning_rate": 6.8867052994037115e-06,
"loss": 0.1593,
"step": 11590
},
{
"epoch": 5.26,
"learning_rate": 6.844713193919544e-06,
"loss": 0.1282,
"step": 11600
},
{
"epoch": 5.27,
"learning_rate": 6.802721088435375e-06,
"loss": 0.1296,
"step": 11610
},
{
"epoch": 5.27,
"learning_rate": 6.760728982951206e-06,
"loss": 0.1512,
"step": 11620
},
{
"epoch": 5.27,
"learning_rate": 6.718736877467037e-06,
"loss": 0.1246,
"step": 11630
},
{
"epoch": 5.28,
"learning_rate": 6.676744771982868e-06,
"loss": 0.1,
"step": 11640
},
{
"epoch": 5.28,
"learning_rate": 6.634752666498699e-06,
"loss": 0.1089,
"step": 11650
},
{
"epoch": 5.29,
"learning_rate": 6.59276056101453e-06,
"loss": 0.1094,
"step": 11660
},
{
"epoch": 5.29,
"learning_rate": 6.550768455530361e-06,
"loss": 0.1344,
"step": 11670
},
{
"epoch": 5.3,
"learning_rate": 6.5087763500461915e-06,
"loss": 0.1075,
"step": 11680
},
{
"epoch": 5.3,
"learning_rate": 6.466784244562023e-06,
"loss": 0.1848,
"step": 11690
},
{
"epoch": 5.31,
"learning_rate": 6.424792139077854e-06,
"loss": 0.0696,
"step": 11700
},
{
"epoch": 5.31,
"learning_rate": 6.382800033593684e-06,
"loss": 0.115,
"step": 11710
},
{
"epoch": 5.32,
"learning_rate": 6.340807928109516e-06,
"loss": 0.1111,
"step": 11720
},
{
"epoch": 5.32,
"learning_rate": 6.298815822625346e-06,
"loss": 0.1595,
"step": 11730
},
{
"epoch": 5.32,
"learning_rate": 6.256823717141178e-06,
"loss": 0.1652,
"step": 11740
},
{
"epoch": 5.33,
"learning_rate": 6.2148316116570085e-06,
"loss": 0.0966,
"step": 11750
},
{
"epoch": 5.33,
"learning_rate": 6.172839506172839e-06,
"loss": 0.14,
"step": 11760
},
{
"epoch": 5.34,
"learning_rate": 6.1308474006886715e-06,
"loss": 0.1595,
"step": 11770
},
{
"epoch": 5.34,
"learning_rate": 6.088855295204502e-06,
"loss": 0.1855,
"step": 11780
},
{
"epoch": 5.35,
"learning_rate": 6.046863189720333e-06,
"loss": 0.1506,
"step": 11790
},
{
"epoch": 5.35,
"learning_rate": 6.004871084236164e-06,
"loss": 0.1183,
"step": 11800
},
{
"epoch": 5.36,
"learning_rate": 5.962878978751995e-06,
"loss": 0.1576,
"step": 11810
},
{
"epoch": 5.36,
"learning_rate": 5.9208868732678255e-06,
"loss": 0.1194,
"step": 11820
},
{
"epoch": 5.37,
"learning_rate": 5.878894767783657e-06,
"loss": 0.0819,
"step": 11830
},
{
"epoch": 5.37,
"learning_rate": 5.836902662299488e-06,
"loss": 0.1092,
"step": 11840
},
{
"epoch": 5.37,
"learning_rate": 5.794910556815319e-06,
"loss": 0.1178,
"step": 11850
},
{
"epoch": 5.38,
"learning_rate": 5.75291845133115e-06,
"loss": 0.1205,
"step": 11860
},
{
"epoch": 5.38,
"learning_rate": 5.710926345846981e-06,
"loss": 0.1396,
"step": 11870
},
{
"epoch": 5.39,
"learning_rate": 5.668934240362813e-06,
"loss": 0.1479,
"step": 11880
},
{
"epoch": 5.39,
"learning_rate": 5.626942134878643e-06,
"loss": 0.0969,
"step": 11890
},
{
"epoch": 5.4,
"learning_rate": 5.584950029394474e-06,
"loss": 0.1044,
"step": 11900
},
{
"epoch": 5.4,
"learning_rate": 5.5429579239103055e-06,
"loss": 0.1169,
"step": 11910
},
{
"epoch": 5.41,
"learning_rate": 5.500965818426136e-06,
"loss": 0.1112,
"step": 11920
},
{
"epoch": 5.41,
"learning_rate": 5.458973712941967e-06,
"loss": 0.1284,
"step": 11930
},
{
"epoch": 5.41,
"learning_rate": 5.416981607457798e-06,
"loss": 0.1209,
"step": 11940
},
{
"epoch": 5.42,
"learning_rate": 5.374989501973629e-06,
"loss": 0.1329,
"step": 11950
},
{
"epoch": 5.42,
"learning_rate": 5.33299739648946e-06,
"loss": 0.1228,
"step": 11960
},
{
"epoch": 5.43,
"learning_rate": 5.291005291005291e-06,
"loss": 0.0962,
"step": 11970
},
{
"epoch": 5.43,
"learning_rate": 5.2490131855211225e-06,
"loss": 0.134,
"step": 11980
},
{
"epoch": 5.44,
"learning_rate": 5.207021080036953e-06,
"loss": 0.1116,
"step": 11990
},
{
"epoch": 5.44,
"learning_rate": 5.165028974552785e-06,
"loss": 0.1492,
"step": 12000
},
{
"epoch": 5.45,
"learning_rate": 5.123036869068615e-06,
"loss": 0.1381,
"step": 12010
},
{
"epoch": 5.45,
"learning_rate": 5.081044763584447e-06,
"loss": 0.1245,
"step": 12020
},
{
"epoch": 5.46,
"learning_rate": 5.0390526581002774e-06,
"loss": 0.1146,
"step": 12030
},
{
"epoch": 5.46,
"learning_rate": 4.997060552616108e-06,
"loss": 0.1008,
"step": 12040
},
{
"epoch": 5.46,
"learning_rate": 4.9550684471319396e-06,
"loss": 0.1236,
"step": 12050
},
{
"epoch": 5.47,
"learning_rate": 4.91307634164777e-06,
"loss": 0.0956,
"step": 12060
},
{
"epoch": 5.47,
"learning_rate": 4.871084236163601e-06,
"loss": 0.1599,
"step": 12070
},
{
"epoch": 5.48,
"learning_rate": 4.829092130679432e-06,
"loss": 0.1077,
"step": 12080
},
{
"epoch": 5.48,
"learning_rate": 4.787100025195264e-06,
"loss": 0.128,
"step": 12090
},
{
"epoch": 5.49,
"learning_rate": 4.7451079197110945e-06,
"loss": 0.1146,
"step": 12100
},
{
"epoch": 5.49,
"learning_rate": 4.703115814226926e-06,
"loss": 0.103,
"step": 12110
},
{
"epoch": 5.5,
"learning_rate": 4.661123708742757e-06,
"loss": 0.1386,
"step": 12120
},
{
"epoch": 5.5,
"learning_rate": 4.619131603258588e-06,
"loss": 0.1162,
"step": 12130
},
{
"epoch": 5.51,
"learning_rate": 4.577139497774419e-06,
"loss": 0.1586,
"step": 12140
},
{
"epoch": 5.51,
"learning_rate": 4.535147392290249e-06,
"loss": 0.135,
"step": 12150
},
{
"epoch": 5.51,
"learning_rate": 4.493155286806081e-06,
"loss": 0.1516,
"step": 12160
},
{
"epoch": 5.52,
"learning_rate": 4.4511631813219115e-06,
"loss": 0.1516,
"step": 12170
},
{
"epoch": 5.52,
"learning_rate": 4.409171075837742e-06,
"loss": 0.1589,
"step": 12180
},
{
"epoch": 5.53,
"learning_rate": 4.367178970353574e-06,
"loss": 0.1314,
"step": 12190
},
{
"epoch": 5.53,
"learning_rate": 4.325186864869405e-06,
"loss": 0.1199,
"step": 12200
},
{
"epoch": 5.54,
"learning_rate": 4.283194759385236e-06,
"loss": 0.1123,
"step": 12210
},
{
"epoch": 5.54,
"learning_rate": 4.241202653901067e-06,
"loss": 0.1387,
"step": 12220
},
{
"epoch": 5.55,
"learning_rate": 4.199210548416898e-06,
"loss": 0.152,
"step": 12230
},
{
"epoch": 5.55,
"learning_rate": 4.1572184429327285e-06,
"loss": 0.1564,
"step": 12240
},
{
"epoch": 5.56,
"learning_rate": 4.11522633744856e-06,
"loss": 0.0866,
"step": 12250
},
{
"epoch": 5.56,
"learning_rate": 4.073234231964391e-06,
"loss": 0.1415,
"step": 12260
},
{
"epoch": 5.56,
"learning_rate": 4.031242126480222e-06,
"loss": 0.1495,
"step": 12270
},
{
"epoch": 5.57,
"learning_rate": 3.989250020996053e-06,
"loss": 0.1349,
"step": 12280
},
{
"epoch": 5.57,
"learning_rate": 3.947257915511883e-06,
"loss": 0.121,
"step": 12290
},
{
"epoch": 5.58,
"learning_rate": 3.905265810027715e-06,
"loss": 0.1219,
"step": 12300
},
{
"epoch": 5.58,
"learning_rate": 3.863273704543546e-06,
"loss": 0.1381,
"step": 12310
},
{
"epoch": 5.59,
"learning_rate": 3.821281599059377e-06,
"loss": 0.1785,
"step": 12320
},
{
"epoch": 5.59,
"learning_rate": 3.779289493575208e-06,
"loss": 0.1344,
"step": 12330
},
{
"epoch": 5.6,
"learning_rate": 3.737297388091039e-06,
"loss": 0.1306,
"step": 12340
},
{
"epoch": 5.6,
"learning_rate": 3.69530528260687e-06,
"loss": 0.1218,
"step": 12350
},
{
"epoch": 5.61,
"learning_rate": 3.6533131771227013e-06,
"loss": 0.1513,
"step": 12360
},
{
"epoch": 5.61,
"learning_rate": 3.611321071638532e-06,
"loss": 0.0894,
"step": 12370
},
{
"epoch": 5.61,
"learning_rate": 3.569328966154363e-06,
"loss": 0.1222,
"step": 12380
},
{
"epoch": 5.62,
"learning_rate": 3.527336860670194e-06,
"loss": 0.1845,
"step": 12390
},
{
"epoch": 5.62,
"learning_rate": 3.485344755186025e-06,
"loss": 0.1214,
"step": 12400
},
{
"epoch": 5.63,
"learning_rate": 3.4433526497018557e-06,
"loss": 0.1121,
"step": 12410
},
{
"epoch": 5.63,
"learning_rate": 3.4013605442176877e-06,
"loss": 0.1031,
"step": 12420
},
{
"epoch": 5.64,
"learning_rate": 3.3593684387335183e-06,
"loss": 0.1289,
"step": 12430
},
{
"epoch": 5.64,
"learning_rate": 3.3173763332493494e-06,
"loss": 0.1596,
"step": 12440
},
{
"epoch": 5.65,
"learning_rate": 3.2753842277651804e-06,
"loss": 0.1293,
"step": 12450
},
{
"epoch": 5.65,
"learning_rate": 3.2333921222810115e-06,
"loss": 0.1249,
"step": 12460
},
{
"epoch": 5.66,
"learning_rate": 3.191400016796842e-06,
"loss": 0.1587,
"step": 12470
},
{
"epoch": 5.66,
"learning_rate": 3.149407911312673e-06,
"loss": 0.1426,
"step": 12480
},
{
"epoch": 5.66,
"learning_rate": 3.1074158058285043e-06,
"loss": 0.1336,
"step": 12490
},
{
"epoch": 5.67,
"learning_rate": 3.0654237003443357e-06,
"loss": 0.1461,
"step": 12500
},
{
"epoch": 5.67,
"learning_rate": 3.0234315948601664e-06,
"loss": 0.0858,
"step": 12510
},
{
"epoch": 5.68,
"learning_rate": 2.9814394893759974e-06,
"loss": 0.1287,
"step": 12520
},
{
"epoch": 5.68,
"learning_rate": 2.9394473838918285e-06,
"loss": 0.1574,
"step": 12530
},
{
"epoch": 5.69,
"learning_rate": 2.8974552784076596e-06,
"loss": 0.1482,
"step": 12540
},
{
"epoch": 5.69,
"learning_rate": 2.8554631729234906e-06,
"loss": 0.1192,
"step": 12550
},
{
"epoch": 5.7,
"learning_rate": 2.8134710674393217e-06,
"loss": 0.1105,
"step": 12560
},
{
"epoch": 5.7,
"learning_rate": 2.7714789619551528e-06,
"loss": 0.1151,
"step": 12570
},
{
"epoch": 5.71,
"learning_rate": 2.7294868564709834e-06,
"loss": 0.0852,
"step": 12580
},
{
"epoch": 5.71,
"learning_rate": 2.6874947509868145e-06,
"loss": 0.1137,
"step": 12590
},
{
"epoch": 5.71,
"learning_rate": 2.6455026455026455e-06,
"loss": 0.0914,
"step": 12600
},
{
"epoch": 5.72,
"learning_rate": 2.6035105400184766e-06,
"loss": 0.1366,
"step": 12610
},
{
"epoch": 5.72,
"learning_rate": 2.5615184345343077e-06,
"loss": 0.1319,
"step": 12620
},
{
"epoch": 5.73,
"learning_rate": 2.5195263290501387e-06,
"loss": 0.1391,
"step": 12630
},
{
"epoch": 5.73,
"learning_rate": 2.4775342235659698e-06,
"loss": 0.1175,
"step": 12640
},
{
"epoch": 5.74,
"learning_rate": 2.4355421180818004e-06,
"loss": 0.103,
"step": 12650
},
{
"epoch": 5.74,
"learning_rate": 2.393550012597632e-06,
"loss": 0.1135,
"step": 12660
},
{
"epoch": 5.75,
"learning_rate": 2.351557907113463e-06,
"loss": 0.1411,
"step": 12670
},
{
"epoch": 5.75,
"learning_rate": 2.309565801629294e-06,
"loss": 0.1542,
"step": 12680
},
{
"epoch": 5.76,
"learning_rate": 2.2675736961451247e-06,
"loss": 0.0942,
"step": 12690
},
{
"epoch": 5.76,
"learning_rate": 2.2255815906609557e-06,
"loss": 0.1131,
"step": 12700
},
{
"epoch": 5.76,
"learning_rate": 2.183589485176787e-06,
"loss": 0.079,
"step": 12710
},
{
"epoch": 5.77,
"learning_rate": 2.141597379692618e-06,
"loss": 0.1227,
"step": 12720
},
{
"epoch": 5.77,
"learning_rate": 2.099605274208449e-06,
"loss": 0.1412,
"step": 12730
},
{
"epoch": 5.78,
"learning_rate": 2.05761316872428e-06,
"loss": 0.0994,
"step": 12740
},
{
"epoch": 5.78,
"learning_rate": 2.015621063240111e-06,
"loss": 0.0807,
"step": 12750
},
{
"epoch": 5.79,
"learning_rate": 1.9736289577559417e-06,
"loss": 0.1033,
"step": 12760
},
{
"epoch": 5.79,
"learning_rate": 1.931636852271773e-06,
"loss": 0.1151,
"step": 12770
},
{
"epoch": 5.8,
"learning_rate": 1.889644746787604e-06,
"loss": 0.1231,
"step": 12780
},
{
"epoch": 5.8,
"learning_rate": 1.847652641303435e-06,
"loss": 0.152,
"step": 12790
},
{
"epoch": 5.8,
"learning_rate": 1.805660535819266e-06,
"loss": 0.1277,
"step": 12800
},
{
"epoch": 5.81,
"learning_rate": 1.763668430335097e-06,
"loss": 0.1056,
"step": 12810
},
{
"epoch": 5.81,
"learning_rate": 1.7216763248509279e-06,
"loss": 0.1628,
"step": 12820
},
{
"epoch": 5.82,
"learning_rate": 1.6796842193667591e-06,
"loss": 0.1469,
"step": 12830
},
{
"epoch": 5.82,
"learning_rate": 1.6376921138825902e-06,
"loss": 0.0967,
"step": 12840
},
{
"epoch": 5.83,
"learning_rate": 1.595700008398421e-06,
"loss": 0.1721,
"step": 12850
},
{
"epoch": 5.83,
"learning_rate": 1.5537079029142521e-06,
"loss": 0.0978,
"step": 12860
},
{
"epoch": 5.84,
"learning_rate": 1.5117157974300832e-06,
"loss": 0.1061,
"step": 12870
},
{
"epoch": 5.84,
"learning_rate": 1.4697236919459143e-06,
"loss": 0.0853,
"step": 12880
},
{
"epoch": 5.85,
"learning_rate": 1.4277315864617453e-06,
"loss": 0.1234,
"step": 12890
},
{
"epoch": 5.85,
"learning_rate": 1.3857394809775764e-06,
"loss": 0.143,
"step": 12900
},
{
"epoch": 5.85,
"learning_rate": 1.3437473754934072e-06,
"loss": 0.1418,
"step": 12910
},
{
"epoch": 5.86,
"learning_rate": 1.3017552700092383e-06,
"loss": 0.1087,
"step": 12920
},
{
"epoch": 5.86,
"learning_rate": 1.2597631645250694e-06,
"loss": 0.1486,
"step": 12930
},
{
"epoch": 5.87,
"learning_rate": 1.2177710590409002e-06,
"loss": 0.0896,
"step": 12940
},
{
"epoch": 5.87,
"learning_rate": 1.1757789535567315e-06,
"loss": 0.1538,
"step": 12950
},
{
"epoch": 5.88,
"learning_rate": 1.1337868480725623e-06,
"loss": 0.0829,
"step": 12960
},
{
"epoch": 5.88,
"learning_rate": 1.0917947425883934e-06,
"loss": 0.102,
"step": 12970
},
{
"epoch": 5.89,
"learning_rate": 1.0498026371042245e-06,
"loss": 0.1598,
"step": 12980
},
{
"epoch": 5.89,
"learning_rate": 1.0078105316200555e-06,
"loss": 0.1041,
"step": 12990
},
{
"epoch": 5.9,
"learning_rate": 9.658184261358866e-07,
"loss": 0.1262,
"step": 13000
},
{
"epoch": 5.9,
"learning_rate": 9.238263206517176e-07,
"loss": 0.1289,
"step": 13010
},
{
"epoch": 5.9,
"learning_rate": 8.818342151675485e-07,
"loss": 0.1475,
"step": 13020
},
{
"epoch": 5.91,
"learning_rate": 8.398421096833796e-07,
"loss": 0.1631,
"step": 13030
},
{
"epoch": 5.91,
"learning_rate": 7.978500041992105e-07,
"loss": 0.0689,
"step": 13040
},
{
"epoch": 5.92,
"learning_rate": 7.558578987150416e-07,
"loss": 0.1055,
"step": 13050
},
{
"epoch": 5.92,
"learning_rate": 7.138657932308727e-07,
"loss": 0.1175,
"step": 13060
},
{
"epoch": 5.93,
"learning_rate": 6.718736877467036e-07,
"loss": 0.1175,
"step": 13070
},
{
"epoch": 5.93,
"learning_rate": 6.298815822625347e-07,
"loss": 0.1188,
"step": 13080
},
{
"epoch": 5.94,
"learning_rate": 5.878894767783657e-07,
"loss": 0.132,
"step": 13090
},
{
"epoch": 5.94,
"learning_rate": 5.458973712941967e-07,
"loss": 0.0698,
"step": 13100
},
{
"epoch": 5.95,
"learning_rate": 5.039052658100278e-07,
"loss": 0.0942,
"step": 13110
},
{
"epoch": 5.95,
"learning_rate": 4.619131603258588e-07,
"loss": 0.089,
"step": 13120
},
{
"epoch": 5.95,
"learning_rate": 4.199210548416898e-07,
"loss": 0.1332,
"step": 13130
},
{
"epoch": 5.96,
"learning_rate": 3.779289493575208e-07,
"loss": 0.1109,
"step": 13140
},
{
"epoch": 5.96,
"learning_rate": 3.359368438733518e-07,
"loss": 0.1233,
"step": 13150
},
{
"epoch": 5.97,
"learning_rate": 2.9394473838918287e-07,
"loss": 0.0943,
"step": 13160
},
{
"epoch": 5.97,
"learning_rate": 2.519526329050139e-07,
"loss": 0.1025,
"step": 13170
},
{
"epoch": 5.98,
"learning_rate": 2.099605274208449e-07,
"loss": 0.1167,
"step": 13180
},
{
"epoch": 5.98,
"learning_rate": 1.679684219366759e-07,
"loss": 0.1099,
"step": 13190
},
{
"epoch": 5.99,
"learning_rate": 1.2597631645250694e-07,
"loss": 0.1193,
"step": 13200
},
{
"epoch": 5.99,
"learning_rate": 8.398421096833795e-08,
"loss": 0.0606,
"step": 13210
},
{
"epoch": 6.0,
"learning_rate": 4.1992105484168976e-08,
"loss": 0.103,
"step": 13220
},
{
"epoch": 6.0,
"learning_rate": 0.0,
"loss": 0.143,
"step": 13230
},
{
"epoch": 6.0,
"eval_accuracy": 0.9785714285714285,
"eval_loss": 0.05712663382291794,
"eval_runtime": 454.6499,
"eval_samples_per_second": 25.866,
"eval_steps_per_second": 3.233,
"step": 13230
},
{
"epoch": 6.0,
"step": 13230,
"total_flos": 1.0638750731886305e+19,
"train_loss": 0.268089122246903,
"train_runtime": 51321.3842,
"train_samples_per_second": 8.249,
"train_steps_per_second": 0.258
}
],
"max_steps": 13230,
"num_train_epochs": 6,
"total_flos": 1.0638750731886305e+19,
"trial_name": null,
"trial_params": null
}