tanlq's picture
End of training
b180bca
{
"best_metric": 0.9875,
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-cifar10/checkpoint-4686",
"epoch": 2.99968,
"global_step": 4686,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1.066098081023454e-06,
"loss": 2.3047,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 2.132196162046908e-06,
"loss": 2.3074,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 3.198294243070363e-06,
"loss": 2.2927,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.264392324093816e-06,
"loss": 2.2861,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 5.330490405117271e-06,
"loss": 2.2798,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 6.396588486140726e-06,
"loss": 2.2716,
"step": 60
},
{
"epoch": 0.04,
"learning_rate": 7.4626865671641785e-06,
"loss": 2.2492,
"step": 70
},
{
"epoch": 0.05,
"learning_rate": 8.528784648187633e-06,
"loss": 2.2232,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 9.594882729211089e-06,
"loss": 2.2032,
"step": 90
},
{
"epoch": 0.06,
"learning_rate": 1.0660980810234541e-05,
"loss": 2.1674,
"step": 100
},
{
"epoch": 0.07,
"learning_rate": 1.1727078891257996e-05,
"loss": 2.1286,
"step": 110
},
{
"epoch": 0.08,
"learning_rate": 1.2793176972281452e-05,
"loss": 2.0904,
"step": 120
},
{
"epoch": 0.08,
"learning_rate": 1.3859275053304904e-05,
"loss": 2.0274,
"step": 130
},
{
"epoch": 0.09,
"learning_rate": 1.4925373134328357e-05,
"loss": 1.9892,
"step": 140
},
{
"epoch": 0.1,
"learning_rate": 1.5991471215351813e-05,
"loss": 1.9114,
"step": 150
},
{
"epoch": 0.1,
"learning_rate": 1.7057569296375266e-05,
"loss": 1.8492,
"step": 160
},
{
"epoch": 0.11,
"learning_rate": 1.812366737739872e-05,
"loss": 1.7891,
"step": 170
},
{
"epoch": 0.12,
"learning_rate": 1.9189765458422178e-05,
"loss": 1.6913,
"step": 180
},
{
"epoch": 0.12,
"learning_rate": 2.025586353944563e-05,
"loss": 1.5952,
"step": 190
},
{
"epoch": 0.13,
"learning_rate": 2.1321961620469083e-05,
"loss": 1.5431,
"step": 200
},
{
"epoch": 0.13,
"learning_rate": 2.238805970149254e-05,
"loss": 1.4303,
"step": 210
},
{
"epoch": 0.14,
"learning_rate": 2.345415778251599e-05,
"loss": 1.3897,
"step": 220
},
{
"epoch": 0.15,
"learning_rate": 2.4520255863539444e-05,
"loss": 1.2901,
"step": 230
},
{
"epoch": 0.15,
"learning_rate": 2.5586353944562904e-05,
"loss": 1.2243,
"step": 240
},
{
"epoch": 0.16,
"learning_rate": 2.6652452025586356e-05,
"loss": 1.1776,
"step": 250
},
{
"epoch": 0.17,
"learning_rate": 2.771855010660981e-05,
"loss": 1.137,
"step": 260
},
{
"epoch": 0.17,
"learning_rate": 2.878464818763326e-05,
"loss": 1.1444,
"step": 270
},
{
"epoch": 0.18,
"learning_rate": 2.9850746268656714e-05,
"loss": 1.0676,
"step": 280
},
{
"epoch": 0.19,
"learning_rate": 3.0916844349680173e-05,
"loss": 1.0014,
"step": 290
},
{
"epoch": 0.19,
"learning_rate": 3.1982942430703626e-05,
"loss": 0.9586,
"step": 300
},
{
"epoch": 0.2,
"learning_rate": 3.304904051172708e-05,
"loss": 0.9382,
"step": 310
},
{
"epoch": 0.2,
"learning_rate": 3.411513859275053e-05,
"loss": 0.9358,
"step": 320
},
{
"epoch": 0.21,
"learning_rate": 3.518123667377399e-05,
"loss": 0.9262,
"step": 330
},
{
"epoch": 0.22,
"learning_rate": 3.624733475479744e-05,
"loss": 0.844,
"step": 340
},
{
"epoch": 0.22,
"learning_rate": 3.73134328358209e-05,
"loss": 0.8245,
"step": 350
},
{
"epoch": 0.23,
"learning_rate": 3.8379530916844355e-05,
"loss": 0.8027,
"step": 360
},
{
"epoch": 0.24,
"learning_rate": 3.944562899786781e-05,
"loss": 0.7783,
"step": 370
},
{
"epoch": 0.24,
"learning_rate": 4.051172707889126e-05,
"loss": 0.7367,
"step": 380
},
{
"epoch": 0.25,
"learning_rate": 4.157782515991471e-05,
"loss": 0.7316,
"step": 390
},
{
"epoch": 0.26,
"learning_rate": 4.2643923240938166e-05,
"loss": 0.7364,
"step": 400
},
{
"epoch": 0.26,
"learning_rate": 4.3710021321961625e-05,
"loss": 0.7266,
"step": 410
},
{
"epoch": 0.27,
"learning_rate": 4.477611940298508e-05,
"loss": 0.7036,
"step": 420
},
{
"epoch": 0.28,
"learning_rate": 4.584221748400853e-05,
"loss": 0.7039,
"step": 430
},
{
"epoch": 0.28,
"learning_rate": 4.690831556503198e-05,
"loss": 0.6398,
"step": 440
},
{
"epoch": 0.29,
"learning_rate": 4.7974413646055436e-05,
"loss": 0.6432,
"step": 450
},
{
"epoch": 0.29,
"learning_rate": 4.904051172707889e-05,
"loss": 0.5952,
"step": 460
},
{
"epoch": 0.3,
"learning_rate": 4.9988143229784203e-05,
"loss": 0.586,
"step": 470
},
{
"epoch": 0.31,
"learning_rate": 4.9869575527626275e-05,
"loss": 0.5641,
"step": 480
},
{
"epoch": 0.31,
"learning_rate": 4.975100782546834e-05,
"loss": 0.6042,
"step": 490
},
{
"epoch": 0.32,
"learning_rate": 4.963244012331041e-05,
"loss": 0.5384,
"step": 500
},
{
"epoch": 0.33,
"learning_rate": 4.9513872421152476e-05,
"loss": 0.5275,
"step": 510
},
{
"epoch": 0.33,
"learning_rate": 4.939530471899455e-05,
"loss": 0.5853,
"step": 520
},
{
"epoch": 0.34,
"learning_rate": 4.927673701683661e-05,
"loss": 0.6605,
"step": 530
},
{
"epoch": 0.35,
"learning_rate": 4.9158169314678684e-05,
"loss": 0.6153,
"step": 540
},
{
"epoch": 0.35,
"learning_rate": 4.903960161252075e-05,
"loss": 0.5895,
"step": 550
},
{
"epoch": 0.36,
"learning_rate": 4.892103391036282e-05,
"loss": 0.54,
"step": 560
},
{
"epoch": 0.36,
"learning_rate": 4.8802466208204886e-05,
"loss": 0.5053,
"step": 570
},
{
"epoch": 0.37,
"learning_rate": 4.868389850604696e-05,
"loss": 0.4973,
"step": 580
},
{
"epoch": 0.38,
"learning_rate": 4.856533080388903e-05,
"loss": 0.5406,
"step": 590
},
{
"epoch": 0.38,
"learning_rate": 4.8446763101731094e-05,
"loss": 0.4995,
"step": 600
},
{
"epoch": 0.39,
"learning_rate": 4.832819539957316e-05,
"loss": 0.445,
"step": 610
},
{
"epoch": 0.4,
"learning_rate": 4.820962769741523e-05,
"loss": 0.503,
"step": 620
},
{
"epoch": 0.4,
"learning_rate": 4.8091059995257295e-05,
"loss": 0.4842,
"step": 630
},
{
"epoch": 0.41,
"learning_rate": 4.7972492293099366e-05,
"loss": 0.4961,
"step": 640
},
{
"epoch": 0.42,
"learning_rate": 4.785392459094143e-05,
"loss": 0.5153,
"step": 650
},
{
"epoch": 0.42,
"learning_rate": 4.77353568887835e-05,
"loss": 0.4224,
"step": 660
},
{
"epoch": 0.43,
"learning_rate": 4.761678918662557e-05,
"loss": 0.5129,
"step": 670
},
{
"epoch": 0.44,
"learning_rate": 4.749822148446763e-05,
"loss": 0.4767,
"step": 680
},
{
"epoch": 0.44,
"learning_rate": 4.7379653782309704e-05,
"loss": 0.4884,
"step": 690
},
{
"epoch": 0.45,
"learning_rate": 4.726108608015177e-05,
"loss": 0.5008,
"step": 700
},
{
"epoch": 0.45,
"learning_rate": 4.714251837799384e-05,
"loss": 0.4454,
"step": 710
},
{
"epoch": 0.46,
"learning_rate": 4.7023950675835905e-05,
"loss": 0.4604,
"step": 720
},
{
"epoch": 0.47,
"learning_rate": 4.690538297367798e-05,
"loss": 0.5052,
"step": 730
},
{
"epoch": 0.47,
"learning_rate": 4.678681527152004e-05,
"loss": 0.5529,
"step": 740
},
{
"epoch": 0.48,
"learning_rate": 4.6668247569362107e-05,
"loss": 0.4555,
"step": 750
},
{
"epoch": 0.49,
"learning_rate": 4.654967986720418e-05,
"loss": 0.4728,
"step": 760
},
{
"epoch": 0.49,
"learning_rate": 4.643111216504624e-05,
"loss": 0.4299,
"step": 770
},
{
"epoch": 0.5,
"learning_rate": 4.6312544462888315e-05,
"loss": 0.4924,
"step": 780
},
{
"epoch": 0.51,
"learning_rate": 4.619397676073038e-05,
"loss": 0.4357,
"step": 790
},
{
"epoch": 0.51,
"learning_rate": 4.607540905857245e-05,
"loss": 0.3772,
"step": 800
},
{
"epoch": 0.52,
"learning_rate": 4.5956841356414516e-05,
"loss": 0.3952,
"step": 810
},
{
"epoch": 0.52,
"learning_rate": 4.583827365425658e-05,
"loss": 0.5014,
"step": 820
},
{
"epoch": 0.53,
"learning_rate": 4.571970595209865e-05,
"loss": 0.4596,
"step": 830
},
{
"epoch": 0.54,
"learning_rate": 4.560113824994072e-05,
"loss": 0.3872,
"step": 840
},
{
"epoch": 0.54,
"learning_rate": 4.548257054778279e-05,
"loss": 0.3455,
"step": 850
},
{
"epoch": 0.55,
"learning_rate": 4.5364002845624853e-05,
"loss": 0.3995,
"step": 860
},
{
"epoch": 0.56,
"learning_rate": 4.5245435143466925e-05,
"loss": 0.419,
"step": 870
},
{
"epoch": 0.56,
"learning_rate": 4.512686744130899e-05,
"loss": 0.3945,
"step": 880
},
{
"epoch": 0.57,
"learning_rate": 4.5008299739151055e-05,
"loss": 0.4771,
"step": 890
},
{
"epoch": 0.58,
"learning_rate": 4.4889732036993126e-05,
"loss": 0.4154,
"step": 900
},
{
"epoch": 0.58,
"learning_rate": 4.477116433483519e-05,
"loss": 0.4645,
"step": 910
},
{
"epoch": 0.59,
"learning_rate": 4.465259663267726e-05,
"loss": 0.4333,
"step": 920
},
{
"epoch": 0.6,
"learning_rate": 4.453402893051933e-05,
"loss": 0.4068,
"step": 930
},
{
"epoch": 0.6,
"learning_rate": 4.44154612283614e-05,
"loss": 0.4505,
"step": 940
},
{
"epoch": 0.61,
"learning_rate": 4.4296893526203464e-05,
"loss": 0.4101,
"step": 950
},
{
"epoch": 0.61,
"learning_rate": 4.417832582404553e-05,
"loss": 0.3332,
"step": 960
},
{
"epoch": 0.62,
"learning_rate": 4.40597581218876e-05,
"loss": 0.362,
"step": 970
},
{
"epoch": 0.63,
"learning_rate": 4.3941190419729665e-05,
"loss": 0.4307,
"step": 980
},
{
"epoch": 0.63,
"learning_rate": 4.382262271757174e-05,
"loss": 0.4096,
"step": 990
},
{
"epoch": 0.64,
"learning_rate": 4.37040550154138e-05,
"loss": 0.4387,
"step": 1000
},
{
"epoch": 0.65,
"learning_rate": 4.358548731325587e-05,
"loss": 0.4004,
"step": 1010
},
{
"epoch": 0.65,
"learning_rate": 4.346691961109794e-05,
"loss": 0.3721,
"step": 1020
},
{
"epoch": 0.66,
"learning_rate": 4.334835190894e-05,
"loss": 0.4278,
"step": 1030
},
{
"epoch": 0.67,
"learning_rate": 4.3229784206782074e-05,
"loss": 0.3304,
"step": 1040
},
{
"epoch": 0.67,
"learning_rate": 4.311121650462414e-05,
"loss": 0.3647,
"step": 1050
},
{
"epoch": 0.68,
"learning_rate": 4.299264880246621e-05,
"loss": 0.4029,
"step": 1060
},
{
"epoch": 0.68,
"learning_rate": 4.2874081100308276e-05,
"loss": 0.3775,
"step": 1070
},
{
"epoch": 0.69,
"learning_rate": 4.275551339815035e-05,
"loss": 0.4088,
"step": 1080
},
{
"epoch": 0.7,
"learning_rate": 4.263694569599241e-05,
"loss": 0.3043,
"step": 1090
},
{
"epoch": 0.7,
"learning_rate": 4.251837799383448e-05,
"loss": 0.4541,
"step": 1100
},
{
"epoch": 0.71,
"learning_rate": 4.239981029167655e-05,
"loss": 0.3975,
"step": 1110
},
{
"epoch": 0.72,
"learning_rate": 4.228124258951861e-05,
"loss": 0.4155,
"step": 1120
},
{
"epoch": 0.72,
"learning_rate": 4.2162674887360685e-05,
"loss": 0.3831,
"step": 1130
},
{
"epoch": 0.73,
"learning_rate": 4.204410718520275e-05,
"loss": 0.4689,
"step": 1140
},
{
"epoch": 0.74,
"learning_rate": 4.192553948304482e-05,
"loss": 0.3641,
"step": 1150
},
{
"epoch": 0.74,
"learning_rate": 4.1806971780886886e-05,
"loss": 0.3748,
"step": 1160
},
{
"epoch": 0.75,
"learning_rate": 4.168840407872895e-05,
"loss": 0.4045,
"step": 1170
},
{
"epoch": 0.76,
"learning_rate": 4.156983637657102e-05,
"loss": 0.3324,
"step": 1180
},
{
"epoch": 0.76,
"learning_rate": 4.145126867441309e-05,
"loss": 0.4005,
"step": 1190
},
{
"epoch": 0.77,
"learning_rate": 4.133270097225516e-05,
"loss": 0.3305,
"step": 1200
},
{
"epoch": 0.77,
"learning_rate": 4.121413327009723e-05,
"loss": 0.2942,
"step": 1210
},
{
"epoch": 0.78,
"learning_rate": 4.1095565567939295e-05,
"loss": 0.397,
"step": 1220
},
{
"epoch": 0.79,
"learning_rate": 4.097699786578137e-05,
"loss": 0.3656,
"step": 1230
},
{
"epoch": 0.79,
"learning_rate": 4.085843016362343e-05,
"loss": 0.3399,
"step": 1240
},
{
"epoch": 0.8,
"learning_rate": 4.07398624614655e-05,
"loss": 0.4376,
"step": 1250
},
{
"epoch": 0.81,
"learning_rate": 4.062129475930757e-05,
"loss": 0.3958,
"step": 1260
},
{
"epoch": 0.81,
"learning_rate": 4.050272705714964e-05,
"loss": 0.3063,
"step": 1270
},
{
"epoch": 0.82,
"learning_rate": 4.0384159354991705e-05,
"loss": 0.3652,
"step": 1280
},
{
"epoch": 0.83,
"learning_rate": 4.026559165283377e-05,
"loss": 0.3659,
"step": 1290
},
{
"epoch": 0.83,
"learning_rate": 4.014702395067584e-05,
"loss": 0.3644,
"step": 1300
},
{
"epoch": 0.84,
"learning_rate": 4.0028456248517906e-05,
"loss": 0.3597,
"step": 1310
},
{
"epoch": 0.84,
"learning_rate": 3.990988854635998e-05,
"loss": 0.3046,
"step": 1320
},
{
"epoch": 0.85,
"learning_rate": 3.979132084420204e-05,
"loss": 0.2584,
"step": 1330
},
{
"epoch": 0.86,
"learning_rate": 3.9672753142044114e-05,
"loss": 0.4337,
"step": 1340
},
{
"epoch": 0.86,
"learning_rate": 3.955418543988618e-05,
"loss": 0.3598,
"step": 1350
},
{
"epoch": 0.87,
"learning_rate": 3.9435617737728243e-05,
"loss": 0.3817,
"step": 1360
},
{
"epoch": 0.88,
"learning_rate": 3.9317050035570315e-05,
"loss": 0.3243,
"step": 1370
},
{
"epoch": 0.88,
"learning_rate": 3.919848233341238e-05,
"loss": 0.4476,
"step": 1380
},
{
"epoch": 0.89,
"learning_rate": 3.907991463125445e-05,
"loss": 0.3555,
"step": 1390
},
{
"epoch": 0.9,
"learning_rate": 3.8961346929096516e-05,
"loss": 0.2918,
"step": 1400
},
{
"epoch": 0.9,
"learning_rate": 3.884277922693859e-05,
"loss": 0.3575,
"step": 1410
},
{
"epoch": 0.91,
"learning_rate": 3.872421152478065e-05,
"loss": 0.327,
"step": 1420
},
{
"epoch": 0.92,
"learning_rate": 3.860564382262272e-05,
"loss": 0.3016,
"step": 1430
},
{
"epoch": 0.92,
"learning_rate": 3.848707612046479e-05,
"loss": 0.2876,
"step": 1440
},
{
"epoch": 0.93,
"learning_rate": 3.8368508418306854e-05,
"loss": 0.312,
"step": 1450
},
{
"epoch": 0.93,
"learning_rate": 3.8249940716148926e-05,
"loss": 0.356,
"step": 1460
},
{
"epoch": 0.94,
"learning_rate": 3.813137301399099e-05,
"loss": 0.3757,
"step": 1470
},
{
"epoch": 0.95,
"learning_rate": 3.801280531183306e-05,
"loss": 0.3686,
"step": 1480
},
{
"epoch": 0.95,
"learning_rate": 3.789423760967513e-05,
"loss": 0.3574,
"step": 1490
},
{
"epoch": 0.96,
"learning_rate": 3.777566990751719e-05,
"loss": 0.3462,
"step": 1500
},
{
"epoch": 0.97,
"learning_rate": 3.765710220535926e-05,
"loss": 0.3756,
"step": 1510
},
{
"epoch": 0.97,
"learning_rate": 3.753853450320133e-05,
"loss": 0.3462,
"step": 1520
},
{
"epoch": 0.98,
"learning_rate": 3.74199668010434e-05,
"loss": 0.301,
"step": 1530
},
{
"epoch": 0.99,
"learning_rate": 3.7301399098885464e-05,
"loss": 0.2796,
"step": 1540
},
{
"epoch": 0.99,
"learning_rate": 3.7182831396727536e-05,
"loss": 0.396,
"step": 1550
},
{
"epoch": 1.0,
"learning_rate": 3.70642636945696e-05,
"loss": 0.3118,
"step": 1560
},
{
"epoch": 1.0,
"eval_accuracy": 0.9778,
"eval_loss": 0.11352841556072235,
"eval_runtime": 795.9024,
"eval_samples_per_second": 12.564,
"eval_steps_per_second": 1.571,
"step": 1562
},
{
"epoch": 1.01,
"learning_rate": 3.6945695992411666e-05,
"loss": 0.3787,
"step": 1570
},
{
"epoch": 1.01,
"learning_rate": 3.682712829025374e-05,
"loss": 0.3559,
"step": 1580
},
{
"epoch": 1.02,
"learning_rate": 3.67085605880958e-05,
"loss": 0.354,
"step": 1590
},
{
"epoch": 1.02,
"learning_rate": 3.6589992885937874e-05,
"loss": 0.3028,
"step": 1600
},
{
"epoch": 1.03,
"learning_rate": 3.647142518377994e-05,
"loss": 0.3173,
"step": 1610
},
{
"epoch": 1.04,
"learning_rate": 3.635285748162201e-05,
"loss": 0.3481,
"step": 1620
},
{
"epoch": 1.04,
"learning_rate": 3.6234289779464075e-05,
"loss": 0.294,
"step": 1630
},
{
"epoch": 1.05,
"learning_rate": 3.611572207730614e-05,
"loss": 0.2834,
"step": 1640
},
{
"epoch": 1.06,
"learning_rate": 3.599715437514821e-05,
"loss": 0.3062,
"step": 1650
},
{
"epoch": 1.06,
"learning_rate": 3.5878586672990276e-05,
"loss": 0.279,
"step": 1660
},
{
"epoch": 1.07,
"learning_rate": 3.576001897083235e-05,
"loss": 0.2972,
"step": 1670
},
{
"epoch": 1.08,
"learning_rate": 3.564145126867441e-05,
"loss": 0.2582,
"step": 1680
},
{
"epoch": 1.08,
"learning_rate": 3.5522883566516484e-05,
"loss": 0.2836,
"step": 1690
},
{
"epoch": 1.09,
"learning_rate": 3.540431586435855e-05,
"loss": 0.3459,
"step": 1700
},
{
"epoch": 1.09,
"learning_rate": 3.5285748162200614e-05,
"loss": 0.3492,
"step": 1710
},
{
"epoch": 1.1,
"learning_rate": 3.5167180460042685e-05,
"loss": 0.3747,
"step": 1720
},
{
"epoch": 1.11,
"learning_rate": 3.504861275788475e-05,
"loss": 0.3482,
"step": 1730
},
{
"epoch": 1.11,
"learning_rate": 3.493004505572682e-05,
"loss": 0.3396,
"step": 1740
},
{
"epoch": 1.12,
"learning_rate": 3.481147735356889e-05,
"loss": 0.2672,
"step": 1750
},
{
"epoch": 1.13,
"learning_rate": 3.469290965141096e-05,
"loss": 0.2904,
"step": 1760
},
{
"epoch": 1.13,
"learning_rate": 3.457434194925302e-05,
"loss": 0.4062,
"step": 1770
},
{
"epoch": 1.14,
"learning_rate": 3.445577424709509e-05,
"loss": 0.3078,
"step": 1780
},
{
"epoch": 1.15,
"learning_rate": 3.433720654493716e-05,
"loss": 0.3316,
"step": 1790
},
{
"epoch": 1.15,
"learning_rate": 3.4218638842779224e-05,
"loss": 0.3346,
"step": 1800
},
{
"epoch": 1.16,
"learning_rate": 3.4100071140621296e-05,
"loss": 0.2539,
"step": 1810
},
{
"epoch": 1.17,
"learning_rate": 3.398150343846336e-05,
"loss": 0.3525,
"step": 1820
},
{
"epoch": 1.17,
"learning_rate": 3.386293573630543e-05,
"loss": 0.3179,
"step": 1830
},
{
"epoch": 1.18,
"learning_rate": 3.37443680341475e-05,
"loss": 0.2437,
"step": 1840
},
{
"epoch": 1.18,
"learning_rate": 3.362580033198957e-05,
"loss": 0.2792,
"step": 1850
},
{
"epoch": 1.19,
"learning_rate": 3.3507232629831634e-05,
"loss": 0.2653,
"step": 1860
},
{
"epoch": 1.2,
"learning_rate": 3.3388664927673705e-05,
"loss": 0.3883,
"step": 1870
},
{
"epoch": 1.2,
"learning_rate": 3.327009722551577e-05,
"loss": 0.3113,
"step": 1880
},
{
"epoch": 1.21,
"learning_rate": 3.315152952335784e-05,
"loss": 0.2777,
"step": 1890
},
{
"epoch": 1.22,
"learning_rate": 3.3032961821199906e-05,
"loss": 0.2625,
"step": 1900
},
{
"epoch": 1.22,
"learning_rate": 3.291439411904198e-05,
"loss": 0.3033,
"step": 1910
},
{
"epoch": 1.23,
"learning_rate": 3.279582641688404e-05,
"loss": 0.3028,
"step": 1920
},
{
"epoch": 1.24,
"learning_rate": 3.2677258714726114e-05,
"loss": 0.3201,
"step": 1930
},
{
"epoch": 1.24,
"learning_rate": 3.255869101256818e-05,
"loss": 0.2813,
"step": 1940
},
{
"epoch": 1.25,
"learning_rate": 3.244012331041025e-05,
"loss": 0.1829,
"step": 1950
},
{
"epoch": 1.25,
"learning_rate": 3.2321555608252316e-05,
"loss": 0.3424,
"step": 1960
},
{
"epoch": 1.26,
"learning_rate": 3.220298790609439e-05,
"loss": 0.2576,
"step": 1970
},
{
"epoch": 1.27,
"learning_rate": 3.208442020393645e-05,
"loss": 0.2928,
"step": 1980
},
{
"epoch": 1.27,
"learning_rate": 3.196585250177852e-05,
"loss": 0.312,
"step": 1990
},
{
"epoch": 1.28,
"learning_rate": 3.184728479962059e-05,
"loss": 0.3058,
"step": 2000
},
{
"epoch": 1.29,
"learning_rate": 3.172871709746265e-05,
"loss": 0.2928,
"step": 2010
},
{
"epoch": 1.29,
"learning_rate": 3.1610149395304725e-05,
"loss": 0.2554,
"step": 2020
},
{
"epoch": 1.3,
"learning_rate": 3.149158169314679e-05,
"loss": 0.2874,
"step": 2030
},
{
"epoch": 1.31,
"learning_rate": 3.137301399098886e-05,
"loss": 0.2791,
"step": 2040
},
{
"epoch": 1.31,
"learning_rate": 3.1254446288830926e-05,
"loss": 0.3548,
"step": 2050
},
{
"epoch": 1.32,
"learning_rate": 3.113587858667299e-05,
"loss": 0.2915,
"step": 2060
},
{
"epoch": 1.33,
"learning_rate": 3.101731088451506e-05,
"loss": 0.221,
"step": 2070
},
{
"epoch": 1.33,
"learning_rate": 3.089874318235713e-05,
"loss": 0.2891,
"step": 2080
},
{
"epoch": 1.34,
"learning_rate": 3.07801754801992e-05,
"loss": 0.2505,
"step": 2090
},
{
"epoch": 1.34,
"learning_rate": 3.0661607778041264e-05,
"loss": 0.2632,
"step": 2100
},
{
"epoch": 1.35,
"learning_rate": 3.0543040075883335e-05,
"loss": 0.2336,
"step": 2110
},
{
"epoch": 1.36,
"learning_rate": 3.04244723737254e-05,
"loss": 0.265,
"step": 2120
},
{
"epoch": 1.36,
"learning_rate": 3.0305904671567465e-05,
"loss": 0.3128,
"step": 2130
},
{
"epoch": 1.37,
"learning_rate": 3.0187336969409537e-05,
"loss": 0.3218,
"step": 2140
},
{
"epoch": 1.38,
"learning_rate": 3.00687692672516e-05,
"loss": 0.2648,
"step": 2150
},
{
"epoch": 1.38,
"learning_rate": 2.9950201565093673e-05,
"loss": 0.3387,
"step": 2160
},
{
"epoch": 1.39,
"learning_rate": 2.9831633862935738e-05,
"loss": 0.2822,
"step": 2170
},
{
"epoch": 1.4,
"learning_rate": 2.971306616077781e-05,
"loss": 0.2359,
"step": 2180
},
{
"epoch": 1.4,
"learning_rate": 2.9594498458619874e-05,
"loss": 0.2544,
"step": 2190
},
{
"epoch": 1.41,
"learning_rate": 2.947593075646194e-05,
"loss": 0.3222,
"step": 2200
},
{
"epoch": 1.41,
"learning_rate": 2.935736305430401e-05,
"loss": 0.3221,
"step": 2210
},
{
"epoch": 1.42,
"learning_rate": 2.9238795352146075e-05,
"loss": 0.2123,
"step": 2220
},
{
"epoch": 1.43,
"learning_rate": 2.9120227649988147e-05,
"loss": 0.3861,
"step": 2230
},
{
"epoch": 1.43,
"learning_rate": 2.9001659947830212e-05,
"loss": 0.2087,
"step": 2240
},
{
"epoch": 1.44,
"learning_rate": 2.8883092245672283e-05,
"loss": 0.3096,
"step": 2250
},
{
"epoch": 1.45,
"learning_rate": 2.8764524543514348e-05,
"loss": 0.3355,
"step": 2260
},
{
"epoch": 1.45,
"learning_rate": 2.8645956841356413e-05,
"loss": 0.2005,
"step": 2270
},
{
"epoch": 1.46,
"learning_rate": 2.8527389139198485e-05,
"loss": 0.3197,
"step": 2280
},
{
"epoch": 1.47,
"learning_rate": 2.840882143704055e-05,
"loss": 0.2659,
"step": 2290
},
{
"epoch": 1.47,
"learning_rate": 2.829025373488262e-05,
"loss": 0.2898,
"step": 2300
},
{
"epoch": 1.48,
"learning_rate": 2.8171686032724686e-05,
"loss": 0.3266,
"step": 2310
},
{
"epoch": 1.49,
"learning_rate": 2.805311833056675e-05,
"loss": 0.2504,
"step": 2320
},
{
"epoch": 1.49,
"learning_rate": 2.7934550628408822e-05,
"loss": 0.1921,
"step": 2330
},
{
"epoch": 1.5,
"learning_rate": 2.7815982926250887e-05,
"loss": 0.2172,
"step": 2340
},
{
"epoch": 1.5,
"learning_rate": 2.769741522409296e-05,
"loss": 0.2125,
"step": 2350
},
{
"epoch": 1.51,
"learning_rate": 2.7578847521935024e-05,
"loss": 0.2438,
"step": 2360
},
{
"epoch": 1.52,
"learning_rate": 2.7460279819777095e-05,
"loss": 0.2219,
"step": 2370
},
{
"epoch": 1.52,
"learning_rate": 2.734171211761916e-05,
"loss": 0.3002,
"step": 2380
},
{
"epoch": 1.53,
"learning_rate": 2.7223144415461228e-05,
"loss": 0.2161,
"step": 2390
},
{
"epoch": 1.54,
"learning_rate": 2.7104576713303296e-05,
"loss": 0.3084,
"step": 2400
},
{
"epoch": 1.54,
"learning_rate": 2.6986009011145365e-05,
"loss": 0.3025,
"step": 2410
},
{
"epoch": 1.55,
"learning_rate": 2.6867441308987433e-05,
"loss": 0.3288,
"step": 2420
},
{
"epoch": 1.56,
"learning_rate": 2.67488736068295e-05,
"loss": 0.2618,
"step": 2430
},
{
"epoch": 1.56,
"learning_rate": 2.663030590467157e-05,
"loss": 0.2627,
"step": 2440
},
{
"epoch": 1.57,
"learning_rate": 2.6511738202513637e-05,
"loss": 0.1764,
"step": 2450
},
{
"epoch": 1.57,
"learning_rate": 2.6393170500355702e-05,
"loss": 0.3657,
"step": 2460
},
{
"epoch": 1.58,
"learning_rate": 2.6274602798197774e-05,
"loss": 0.2533,
"step": 2470
},
{
"epoch": 1.59,
"learning_rate": 2.615603509603984e-05,
"loss": 0.2534,
"step": 2480
},
{
"epoch": 1.59,
"learning_rate": 2.603746739388191e-05,
"loss": 0.2104,
"step": 2490
},
{
"epoch": 1.6,
"learning_rate": 2.5918899691723975e-05,
"loss": 0.2663,
"step": 2500
},
{
"epoch": 1.61,
"learning_rate": 2.5800331989566047e-05,
"loss": 0.237,
"step": 2510
},
{
"epoch": 1.61,
"learning_rate": 2.568176428740811e-05,
"loss": 0.2769,
"step": 2520
},
{
"epoch": 1.62,
"learning_rate": 2.5563196585250176e-05,
"loss": 0.2478,
"step": 2530
},
{
"epoch": 1.63,
"learning_rate": 2.5444628883092248e-05,
"loss": 0.2914,
"step": 2540
},
{
"epoch": 1.63,
"learning_rate": 2.5326061180934313e-05,
"loss": 0.2729,
"step": 2550
},
{
"epoch": 1.64,
"learning_rate": 2.5207493478776384e-05,
"loss": 0.2714,
"step": 2560
},
{
"epoch": 1.65,
"learning_rate": 2.508892577661845e-05,
"loss": 0.2168,
"step": 2570
},
{
"epoch": 1.65,
"learning_rate": 2.4970358074460517e-05,
"loss": 0.2612,
"step": 2580
},
{
"epoch": 1.66,
"learning_rate": 2.4851790372302586e-05,
"loss": 0.2308,
"step": 2590
},
{
"epoch": 1.66,
"learning_rate": 2.4733222670144654e-05,
"loss": 0.2405,
"step": 2600
},
{
"epoch": 1.67,
"learning_rate": 2.4614654967986722e-05,
"loss": 0.335,
"step": 2610
},
{
"epoch": 1.68,
"learning_rate": 2.449608726582879e-05,
"loss": 0.2793,
"step": 2620
},
{
"epoch": 1.68,
"learning_rate": 2.4377519563670855e-05,
"loss": 0.3362,
"step": 2630
},
{
"epoch": 1.69,
"learning_rate": 2.4258951861512923e-05,
"loss": 0.2275,
"step": 2640
},
{
"epoch": 1.7,
"learning_rate": 2.414038415935499e-05,
"loss": 0.3178,
"step": 2650
},
{
"epoch": 1.7,
"learning_rate": 2.402181645719706e-05,
"loss": 0.2352,
"step": 2660
},
{
"epoch": 1.71,
"learning_rate": 2.3903248755039128e-05,
"loss": 0.3398,
"step": 2670
},
{
"epoch": 1.72,
"learning_rate": 2.3784681052881196e-05,
"loss": 0.2568,
"step": 2680
},
{
"epoch": 1.72,
"learning_rate": 2.3666113350723264e-05,
"loss": 0.2928,
"step": 2690
},
{
"epoch": 1.73,
"learning_rate": 2.354754564856533e-05,
"loss": 0.211,
"step": 2700
},
{
"epoch": 1.73,
"learning_rate": 2.3428977946407397e-05,
"loss": 0.2666,
"step": 2710
},
{
"epoch": 1.74,
"learning_rate": 2.3310410244249466e-05,
"loss": 0.2174,
"step": 2720
},
{
"epoch": 1.75,
"learning_rate": 2.3191842542091534e-05,
"loss": 0.2172,
"step": 2730
},
{
"epoch": 1.75,
"learning_rate": 2.3073274839933602e-05,
"loss": 0.2173,
"step": 2740
},
{
"epoch": 1.76,
"learning_rate": 2.295470713777567e-05,
"loss": 0.2972,
"step": 2750
},
{
"epoch": 1.77,
"learning_rate": 2.283613943561774e-05,
"loss": 0.2733,
"step": 2760
},
{
"epoch": 1.77,
"learning_rate": 2.2717571733459807e-05,
"loss": 0.2385,
"step": 2770
},
{
"epoch": 1.78,
"learning_rate": 2.2599004031301875e-05,
"loss": 0.2272,
"step": 2780
},
{
"epoch": 1.79,
"learning_rate": 2.2480436329143943e-05,
"loss": 0.2721,
"step": 2790
},
{
"epoch": 1.79,
"learning_rate": 2.236186862698601e-05,
"loss": 0.3015,
"step": 2800
},
{
"epoch": 1.8,
"learning_rate": 2.224330092482808e-05,
"loss": 0.2605,
"step": 2810
},
{
"epoch": 1.81,
"learning_rate": 2.2124733222670148e-05,
"loss": 0.2269,
"step": 2820
},
{
"epoch": 1.81,
"learning_rate": 2.2006165520512216e-05,
"loss": 0.2565,
"step": 2830
},
{
"epoch": 1.82,
"learning_rate": 2.188759781835428e-05,
"loss": 0.1987,
"step": 2840
},
{
"epoch": 1.82,
"learning_rate": 2.176903011619635e-05,
"loss": 0.2089,
"step": 2850
},
{
"epoch": 1.83,
"learning_rate": 2.1650462414038417e-05,
"loss": 0.2291,
"step": 2860
},
{
"epoch": 1.84,
"learning_rate": 2.1531894711880485e-05,
"loss": 0.202,
"step": 2870
},
{
"epoch": 1.84,
"learning_rate": 2.1413327009722553e-05,
"loss": 0.1743,
"step": 2880
},
{
"epoch": 1.85,
"learning_rate": 2.129475930756462e-05,
"loss": 0.2867,
"step": 2890
},
{
"epoch": 1.86,
"learning_rate": 2.117619160540669e-05,
"loss": 0.3186,
"step": 2900
},
{
"epoch": 1.86,
"learning_rate": 2.1057623903248755e-05,
"loss": 0.1718,
"step": 2910
},
{
"epoch": 1.87,
"learning_rate": 2.0939056201090823e-05,
"loss": 0.2629,
"step": 2920
},
{
"epoch": 1.88,
"learning_rate": 2.082048849893289e-05,
"loss": 0.2223,
"step": 2930
},
{
"epoch": 1.88,
"learning_rate": 2.070192079677496e-05,
"loss": 0.1843,
"step": 2940
},
{
"epoch": 1.89,
"learning_rate": 2.0583353094617028e-05,
"loss": 0.2813,
"step": 2950
},
{
"epoch": 1.89,
"learning_rate": 2.0464785392459096e-05,
"loss": 0.28,
"step": 2960
},
{
"epoch": 1.9,
"learning_rate": 2.0346217690301164e-05,
"loss": 0.2057,
"step": 2970
},
{
"epoch": 1.91,
"learning_rate": 2.022764998814323e-05,
"loss": 0.3016,
"step": 2980
},
{
"epoch": 1.91,
"learning_rate": 2.0109082285985297e-05,
"loss": 0.2579,
"step": 2990
},
{
"epoch": 1.92,
"learning_rate": 1.9990514583827365e-05,
"loss": 0.2419,
"step": 3000
},
{
"epoch": 1.93,
"learning_rate": 1.9871946881669433e-05,
"loss": 0.2841,
"step": 3010
},
{
"epoch": 1.93,
"learning_rate": 1.97533791795115e-05,
"loss": 0.227,
"step": 3020
},
{
"epoch": 1.94,
"learning_rate": 1.963481147735357e-05,
"loss": 0.2019,
"step": 3030
},
{
"epoch": 1.95,
"learning_rate": 1.9516243775195638e-05,
"loss": 0.296,
"step": 3040
},
{
"epoch": 1.95,
"learning_rate": 1.9397676073037703e-05,
"loss": 0.2055,
"step": 3050
},
{
"epoch": 1.96,
"learning_rate": 1.927910837087977e-05,
"loss": 0.2495,
"step": 3060
},
{
"epoch": 1.97,
"learning_rate": 1.916054066872184e-05,
"loss": 0.1625,
"step": 3070
},
{
"epoch": 1.97,
"learning_rate": 1.9041972966563907e-05,
"loss": 0.2483,
"step": 3080
},
{
"epoch": 1.98,
"learning_rate": 1.8923405264405976e-05,
"loss": 0.2782,
"step": 3090
},
{
"epoch": 1.98,
"learning_rate": 1.8804837562248044e-05,
"loss": 0.2128,
"step": 3100
},
{
"epoch": 1.99,
"learning_rate": 1.8686269860090112e-05,
"loss": 0.1631,
"step": 3110
},
{
"epoch": 2.0,
"learning_rate": 1.856770215793218e-05,
"loss": 0.2717,
"step": 3120
},
{
"epoch": 2.0,
"eval_accuracy": 0.9867,
"eval_loss": 0.06189415976405144,
"eval_runtime": 794.0573,
"eval_samples_per_second": 12.594,
"eval_steps_per_second": 1.574,
"step": 3124
},
{
"epoch": 2.0,
"learning_rate": 1.844913445577425e-05,
"loss": 0.2339,
"step": 3130
},
{
"epoch": 2.01,
"learning_rate": 1.8330566753616317e-05,
"loss": 0.2318,
"step": 3140
},
{
"epoch": 2.02,
"learning_rate": 1.8211999051458385e-05,
"loss": 0.2117,
"step": 3150
},
{
"epoch": 2.02,
"learning_rate": 1.8093431349300453e-05,
"loss": 0.2235,
"step": 3160
},
{
"epoch": 2.03,
"learning_rate": 1.797486364714252e-05,
"loss": 0.2447,
"step": 3170
},
{
"epoch": 2.04,
"learning_rate": 1.7856295944984586e-05,
"loss": 0.2343,
"step": 3180
},
{
"epoch": 2.04,
"learning_rate": 1.7737728242826654e-05,
"loss": 0.2205,
"step": 3190
},
{
"epoch": 2.05,
"learning_rate": 1.7619160540668723e-05,
"loss": 0.245,
"step": 3200
},
{
"epoch": 2.06,
"learning_rate": 1.750059283851079e-05,
"loss": 0.1824,
"step": 3210
},
{
"epoch": 2.06,
"learning_rate": 1.738202513635286e-05,
"loss": 0.1872,
"step": 3220
},
{
"epoch": 2.07,
"learning_rate": 1.7263457434194927e-05,
"loss": 0.201,
"step": 3230
},
{
"epoch": 2.07,
"learning_rate": 1.7144889732036995e-05,
"loss": 0.1929,
"step": 3240
},
{
"epoch": 2.08,
"learning_rate": 1.702632202987906e-05,
"loss": 0.1707,
"step": 3250
},
{
"epoch": 2.09,
"learning_rate": 1.690775432772113e-05,
"loss": 0.26,
"step": 3260
},
{
"epoch": 2.09,
"learning_rate": 1.6789186625563197e-05,
"loss": 0.2135,
"step": 3270
},
{
"epoch": 2.1,
"learning_rate": 1.6670618923405265e-05,
"loss": 0.2477,
"step": 3280
},
{
"epoch": 2.11,
"learning_rate": 1.6552051221247333e-05,
"loss": 0.3029,
"step": 3290
},
{
"epoch": 2.11,
"learning_rate": 1.64334835190894e-05,
"loss": 0.2445,
"step": 3300
},
{
"epoch": 2.12,
"learning_rate": 1.631491581693147e-05,
"loss": 0.2268,
"step": 3310
},
{
"epoch": 2.13,
"learning_rate": 1.6196348114773534e-05,
"loss": 0.3133,
"step": 3320
},
{
"epoch": 2.13,
"learning_rate": 1.6077780412615603e-05,
"loss": 0.2255,
"step": 3330
},
{
"epoch": 2.14,
"learning_rate": 1.595921271045767e-05,
"loss": 0.2406,
"step": 3340
},
{
"epoch": 2.14,
"learning_rate": 1.584064500829974e-05,
"loss": 0.1899,
"step": 3350
},
{
"epoch": 2.15,
"learning_rate": 1.5722077306141807e-05,
"loss": 0.2539,
"step": 3360
},
{
"epoch": 2.16,
"learning_rate": 1.5603509603983875e-05,
"loss": 0.2009,
"step": 3370
},
{
"epoch": 2.16,
"learning_rate": 1.5484941901825944e-05,
"loss": 0.2638,
"step": 3380
},
{
"epoch": 2.17,
"learning_rate": 1.536637419966801e-05,
"loss": 0.1588,
"step": 3390
},
{
"epoch": 2.18,
"learning_rate": 1.5247806497510078e-05,
"loss": 0.2059,
"step": 3400
},
{
"epoch": 2.18,
"learning_rate": 1.5129238795352146e-05,
"loss": 0.1815,
"step": 3410
},
{
"epoch": 2.19,
"learning_rate": 1.5010671093194215e-05,
"loss": 0.2102,
"step": 3420
},
{
"epoch": 2.2,
"learning_rate": 1.4892103391036283e-05,
"loss": 0.3203,
"step": 3430
},
{
"epoch": 2.2,
"learning_rate": 1.4773535688878351e-05,
"loss": 0.17,
"step": 3440
},
{
"epoch": 2.21,
"learning_rate": 1.465496798672042e-05,
"loss": 0.2176,
"step": 3450
},
{
"epoch": 2.22,
"learning_rate": 1.4536400284562484e-05,
"loss": 0.1528,
"step": 3460
},
{
"epoch": 2.22,
"learning_rate": 1.4417832582404552e-05,
"loss": 0.1842,
"step": 3470
},
{
"epoch": 2.23,
"learning_rate": 1.429926488024662e-05,
"loss": 0.1791,
"step": 3480
},
{
"epoch": 2.23,
"learning_rate": 1.4180697178088689e-05,
"loss": 0.2646,
"step": 3490
},
{
"epoch": 2.24,
"learning_rate": 1.4062129475930757e-05,
"loss": 0.3129,
"step": 3500
},
{
"epoch": 2.25,
"learning_rate": 1.3943561773772825e-05,
"loss": 0.1282,
"step": 3510
},
{
"epoch": 2.25,
"learning_rate": 1.3824994071614893e-05,
"loss": 0.1876,
"step": 3520
},
{
"epoch": 2.26,
"learning_rate": 1.370642636945696e-05,
"loss": 0.2883,
"step": 3530
},
{
"epoch": 2.27,
"learning_rate": 1.3587858667299028e-05,
"loss": 0.2572,
"step": 3540
},
{
"epoch": 2.27,
"learning_rate": 1.3469290965141096e-05,
"loss": 0.2848,
"step": 3550
},
{
"epoch": 2.28,
"learning_rate": 1.3350723262983165e-05,
"loss": 0.1814,
"step": 3560
},
{
"epoch": 2.29,
"learning_rate": 1.3232155560825233e-05,
"loss": 0.1811,
"step": 3570
},
{
"epoch": 2.29,
"learning_rate": 1.3113587858667301e-05,
"loss": 0.1992,
"step": 3580
},
{
"epoch": 2.3,
"learning_rate": 1.2995020156509369e-05,
"loss": 0.2808,
"step": 3590
},
{
"epoch": 2.3,
"learning_rate": 1.2876452454351434e-05,
"loss": 0.2771,
"step": 3600
},
{
"epoch": 2.31,
"learning_rate": 1.2757884752193502e-05,
"loss": 0.1892,
"step": 3610
},
{
"epoch": 2.32,
"learning_rate": 1.263931705003557e-05,
"loss": 0.1927,
"step": 3620
},
{
"epoch": 2.32,
"learning_rate": 1.2520749347877639e-05,
"loss": 0.2016,
"step": 3630
},
{
"epoch": 2.33,
"learning_rate": 1.2402181645719707e-05,
"loss": 0.2299,
"step": 3640
},
{
"epoch": 2.34,
"learning_rate": 1.2283613943561773e-05,
"loss": 0.1871,
"step": 3650
},
{
"epoch": 2.34,
"learning_rate": 1.2165046241403842e-05,
"loss": 0.1911,
"step": 3660
},
{
"epoch": 2.35,
"learning_rate": 1.204647853924591e-05,
"loss": 0.2504,
"step": 3670
},
{
"epoch": 2.36,
"learning_rate": 1.1927910837087978e-05,
"loss": 0.1751,
"step": 3680
},
{
"epoch": 2.36,
"learning_rate": 1.1809343134930046e-05,
"loss": 0.1574,
"step": 3690
},
{
"epoch": 2.37,
"learning_rate": 1.1690775432772114e-05,
"loss": 0.1423,
"step": 3700
},
{
"epoch": 2.38,
"learning_rate": 1.1572207730614183e-05,
"loss": 0.1892,
"step": 3710
},
{
"epoch": 2.38,
"learning_rate": 1.1453640028456249e-05,
"loss": 0.2249,
"step": 3720
},
{
"epoch": 2.39,
"learning_rate": 1.1335072326298317e-05,
"loss": 0.2122,
"step": 3730
},
{
"epoch": 2.39,
"learning_rate": 1.1216504624140385e-05,
"loss": 0.2073,
"step": 3740
},
{
"epoch": 2.4,
"learning_rate": 1.1097936921982452e-05,
"loss": 0.2123,
"step": 3750
},
{
"epoch": 2.41,
"learning_rate": 1.097936921982452e-05,
"loss": 0.1781,
"step": 3760
},
{
"epoch": 2.41,
"learning_rate": 1.0860801517666588e-05,
"loss": 0.224,
"step": 3770
},
{
"epoch": 2.42,
"learning_rate": 1.0742233815508657e-05,
"loss": 0.188,
"step": 3780
},
{
"epoch": 2.43,
"learning_rate": 1.0623666113350723e-05,
"loss": 0.2385,
"step": 3790
},
{
"epoch": 2.43,
"learning_rate": 1.0505098411192791e-05,
"loss": 0.2363,
"step": 3800
},
{
"epoch": 2.44,
"learning_rate": 1.038653070903486e-05,
"loss": 0.1909,
"step": 3810
},
{
"epoch": 2.45,
"learning_rate": 1.0267963006876926e-05,
"loss": 0.2612,
"step": 3820
},
{
"epoch": 2.45,
"learning_rate": 1.0149395304718994e-05,
"loss": 0.2269,
"step": 3830
},
{
"epoch": 2.46,
"learning_rate": 1.0030827602561062e-05,
"loss": 0.2408,
"step": 3840
},
{
"epoch": 2.46,
"learning_rate": 9.91225990040313e-06,
"loss": 0.229,
"step": 3850
},
{
"epoch": 2.47,
"learning_rate": 9.793692198245199e-06,
"loss": 0.2482,
"step": 3860
},
{
"epoch": 2.48,
"learning_rate": 9.675124496087267e-06,
"loss": 0.1652,
"step": 3870
},
{
"epoch": 2.48,
"learning_rate": 9.556556793929335e-06,
"loss": 0.1671,
"step": 3880
},
{
"epoch": 2.49,
"learning_rate": 9.437989091771402e-06,
"loss": 0.1846,
"step": 3890
},
{
"epoch": 2.5,
"learning_rate": 9.31942138961347e-06,
"loss": 0.1745,
"step": 3900
},
{
"epoch": 2.5,
"learning_rate": 9.200853687455538e-06,
"loss": 0.2112,
"step": 3910
},
{
"epoch": 2.51,
"learning_rate": 9.082285985297605e-06,
"loss": 0.2274,
"step": 3920
},
{
"epoch": 2.52,
"learning_rate": 8.963718283139673e-06,
"loss": 0.2371,
"step": 3930
},
{
"epoch": 2.52,
"learning_rate": 8.845150580981741e-06,
"loss": 0.2615,
"step": 3940
},
{
"epoch": 2.53,
"learning_rate": 8.72658287882381e-06,
"loss": 0.2454,
"step": 3950
},
{
"epoch": 2.54,
"learning_rate": 8.608015176665876e-06,
"loss": 0.1898,
"step": 3960
},
{
"epoch": 2.54,
"learning_rate": 8.489447474507944e-06,
"loss": 0.207,
"step": 3970
},
{
"epoch": 2.55,
"learning_rate": 8.370879772350012e-06,
"loss": 0.2036,
"step": 3980
},
{
"epoch": 2.55,
"learning_rate": 8.252312070192079e-06,
"loss": 0.2158,
"step": 3990
},
{
"epoch": 2.56,
"learning_rate": 8.133744368034147e-06,
"loss": 0.1839,
"step": 4000
},
{
"epoch": 2.57,
"learning_rate": 8.015176665876215e-06,
"loss": 0.2519,
"step": 4010
},
{
"epoch": 2.57,
"learning_rate": 7.896608963718283e-06,
"loss": 0.1437,
"step": 4020
},
{
"epoch": 2.58,
"learning_rate": 7.778041261560352e-06,
"loss": 0.2306,
"step": 4030
},
{
"epoch": 2.59,
"learning_rate": 7.65947355940242e-06,
"loss": 0.2353,
"step": 4040
},
{
"epoch": 2.59,
"learning_rate": 7.540905857244487e-06,
"loss": 0.2149,
"step": 4050
},
{
"epoch": 2.6,
"learning_rate": 7.422338155086555e-06,
"loss": 0.2845,
"step": 4060
},
{
"epoch": 2.61,
"learning_rate": 7.303770452928623e-06,
"loss": 0.1821,
"step": 4070
},
{
"epoch": 2.61,
"learning_rate": 7.185202750770691e-06,
"loss": 0.2109,
"step": 4080
},
{
"epoch": 2.62,
"learning_rate": 7.066635048612759e-06,
"loss": 0.2036,
"step": 4090
},
{
"epoch": 2.62,
"learning_rate": 6.948067346454826e-06,
"loss": 0.2048,
"step": 4100
},
{
"epoch": 2.63,
"learning_rate": 6.829499644296894e-06,
"loss": 0.2418,
"step": 4110
},
{
"epoch": 2.64,
"learning_rate": 6.710931942138962e-06,
"loss": 0.1733,
"step": 4120
},
{
"epoch": 2.64,
"learning_rate": 6.592364239981029e-06,
"loss": 0.1938,
"step": 4130
},
{
"epoch": 2.65,
"learning_rate": 6.473796537823097e-06,
"loss": 0.1931,
"step": 4140
},
{
"epoch": 2.66,
"learning_rate": 6.355228835665165e-06,
"loss": 0.1563,
"step": 4150
},
{
"epoch": 2.66,
"learning_rate": 6.236661133507233e-06,
"loss": 0.2386,
"step": 4160
},
{
"epoch": 2.67,
"learning_rate": 6.118093431349301e-06,
"loss": 0.1682,
"step": 4170
},
{
"epoch": 2.68,
"learning_rate": 5.999525729191369e-06,
"loss": 0.1493,
"step": 4180
},
{
"epoch": 2.68,
"learning_rate": 5.880958027033436e-06,
"loss": 0.1525,
"step": 4190
},
{
"epoch": 2.69,
"learning_rate": 5.762390324875504e-06,
"loss": 0.1471,
"step": 4200
},
{
"epoch": 2.7,
"learning_rate": 5.643822622717572e-06,
"loss": 0.1232,
"step": 4210
},
{
"epoch": 2.7,
"learning_rate": 5.525254920559639e-06,
"loss": 0.1545,
"step": 4220
},
{
"epoch": 2.71,
"learning_rate": 5.406687218401707e-06,
"loss": 0.1835,
"step": 4230
},
{
"epoch": 2.71,
"learning_rate": 5.2881195162437755e-06,
"loss": 0.2369,
"step": 4240
},
{
"epoch": 2.72,
"learning_rate": 5.169551814085844e-06,
"loss": 0.1412,
"step": 4250
},
{
"epoch": 2.73,
"learning_rate": 5.050984111927911e-06,
"loss": 0.1897,
"step": 4260
},
{
"epoch": 2.73,
"learning_rate": 4.932416409769979e-06,
"loss": 0.1865,
"step": 4270
},
{
"epoch": 2.74,
"learning_rate": 4.813848707612047e-06,
"loss": 0.1815,
"step": 4280
},
{
"epoch": 2.75,
"learning_rate": 4.695281005454114e-06,
"loss": 0.2102,
"step": 4290
},
{
"epoch": 2.75,
"learning_rate": 4.576713303296182e-06,
"loss": 0.1086,
"step": 4300
},
{
"epoch": 2.76,
"learning_rate": 4.45814560113825e-06,
"loss": 0.117,
"step": 4310
},
{
"epoch": 2.77,
"learning_rate": 4.339577898980318e-06,
"loss": 0.2686,
"step": 4320
},
{
"epoch": 2.77,
"learning_rate": 4.221010196822386e-06,
"loss": 0.2048,
"step": 4330
},
{
"epoch": 2.78,
"learning_rate": 4.102442494664454e-06,
"loss": 0.2178,
"step": 4340
},
{
"epoch": 2.78,
"learning_rate": 3.983874792506522e-06,
"loss": 0.2273,
"step": 4350
},
{
"epoch": 2.79,
"learning_rate": 3.865307090348589e-06,
"loss": 0.1873,
"step": 4360
},
{
"epoch": 2.8,
"learning_rate": 3.746739388190657e-06,
"loss": 0.2187,
"step": 4370
},
{
"epoch": 2.8,
"learning_rate": 3.6281716860327245e-06,
"loss": 0.2283,
"step": 4380
},
{
"epoch": 2.81,
"learning_rate": 3.5096039838747927e-06,
"loss": 0.2117,
"step": 4390
},
{
"epoch": 2.82,
"learning_rate": 3.3910362817168605e-06,
"loss": 0.1951,
"step": 4400
},
{
"epoch": 2.82,
"learning_rate": 3.272468579558928e-06,
"loss": 0.1994,
"step": 4410
},
{
"epoch": 2.83,
"learning_rate": 3.153900877400996e-06,
"loss": 0.1735,
"step": 4420
},
{
"epoch": 2.84,
"learning_rate": 3.0353331752430643e-06,
"loss": 0.2796,
"step": 4430
},
{
"epoch": 2.84,
"learning_rate": 2.9167654730851317e-06,
"loss": 0.1308,
"step": 4440
},
{
"epoch": 2.85,
"learning_rate": 2.7981977709271994e-06,
"loss": 0.2232,
"step": 4450
},
{
"epoch": 2.86,
"learning_rate": 2.6796300687692672e-06,
"loss": 0.2338,
"step": 4460
},
{
"epoch": 2.86,
"learning_rate": 2.5610623666113354e-06,
"loss": 0.2609,
"step": 4470
},
{
"epoch": 2.87,
"learning_rate": 2.4424946644534032e-06,
"loss": 0.1971,
"step": 4480
},
{
"epoch": 2.87,
"learning_rate": 2.323926962295471e-06,
"loss": 0.1864,
"step": 4490
},
{
"epoch": 2.88,
"learning_rate": 2.2053592601375384e-06,
"loss": 0.1813,
"step": 4500
},
{
"epoch": 2.89,
"learning_rate": 2.0867915579796066e-06,
"loss": 0.2013,
"step": 4510
},
{
"epoch": 2.89,
"learning_rate": 1.9682238558216744e-06,
"loss": 0.1666,
"step": 4520
},
{
"epoch": 2.9,
"learning_rate": 1.8496561536637421e-06,
"loss": 0.2143,
"step": 4530
},
{
"epoch": 2.91,
"learning_rate": 1.73108845150581e-06,
"loss": 0.1793,
"step": 4540
},
{
"epoch": 2.91,
"learning_rate": 1.612520749347878e-06,
"loss": 0.1433,
"step": 4550
},
{
"epoch": 2.92,
"learning_rate": 1.4939530471899455e-06,
"loss": 0.1603,
"step": 4560
},
{
"epoch": 2.93,
"learning_rate": 1.3753853450320135e-06,
"loss": 0.136,
"step": 4570
},
{
"epoch": 2.93,
"learning_rate": 1.256817642874081e-06,
"loss": 0.1805,
"step": 4580
},
{
"epoch": 2.94,
"learning_rate": 1.138249940716149e-06,
"loss": 0.2584,
"step": 4590
},
{
"epoch": 2.94,
"learning_rate": 1.0196822385582168e-06,
"loss": 0.1895,
"step": 4600
},
{
"epoch": 2.95,
"learning_rate": 9.011145364002845e-07,
"loss": 0.2353,
"step": 4610
},
{
"epoch": 2.96,
"learning_rate": 7.825468342423524e-07,
"loss": 0.1917,
"step": 4620
},
{
"epoch": 2.96,
"learning_rate": 6.639791320844202e-07,
"loss": 0.1414,
"step": 4630
},
{
"epoch": 2.97,
"learning_rate": 5.454114299264881e-07,
"loss": 0.2053,
"step": 4640
},
{
"epoch": 2.98,
"learning_rate": 4.2684372776855587e-07,
"loss": 0.1612,
"step": 4650
},
{
"epoch": 2.98,
"learning_rate": 3.082760256106237e-07,
"loss": 0.2274,
"step": 4660
},
{
"epoch": 2.99,
"learning_rate": 1.8970832345269152e-07,
"loss": 0.2354,
"step": 4670
},
{
"epoch": 3.0,
"learning_rate": 7.114062129475932e-08,
"loss": 0.1964,
"step": 4680
},
{
"epoch": 3.0,
"eval_accuracy": 0.9875,
"eval_loss": 0.0503208190202713,
"eval_runtime": 861.4693,
"eval_samples_per_second": 11.608,
"eval_steps_per_second": 1.451,
"step": 4686
},
{
"epoch": 3.0,
"step": 4686,
"total_flos": 1.1623391924884734e+19,
"train_loss": 0.39782794105462216,
"train_runtime": 35181.3105,
"train_samples_per_second": 4.264,
"train_steps_per_second": 0.133
}
],
"max_steps": 4686,
"num_train_epochs": 3,
"total_flos": 1.1623391924884734e+19,
"trial_name": null,
"trial_params": null
}