Gokulapriyan's picture
End of training
3429590
{
"best_metric": 0.970766863713661,
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-og-dataset-10e/checkpoint-3276",
"epoch": 5.998628257887518,
"global_step": 3276,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1.5243902439024391e-06,
"loss": 1.3931,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 3.0487804878048782e-06,
"loss": 1.3553,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 4.573170731707317e-06,
"loss": 1.2902,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 6.0975609756097564e-06,
"loss": 1.159,
"step": 40
},
{
"epoch": 0.09,
"learning_rate": 7.621951219512195e-06,
"loss": 1.0435,
"step": 50
},
{
"epoch": 0.11,
"learning_rate": 9.146341463414634e-06,
"loss": 0.9505,
"step": 60
},
{
"epoch": 0.13,
"learning_rate": 1.0670731707317074e-05,
"loss": 0.8701,
"step": 70
},
{
"epoch": 0.15,
"learning_rate": 1.2195121951219513e-05,
"loss": 0.8029,
"step": 80
},
{
"epoch": 0.16,
"learning_rate": 1.3719512195121953e-05,
"loss": 0.7768,
"step": 90
},
{
"epoch": 0.18,
"learning_rate": 1.524390243902439e-05,
"loss": 0.769,
"step": 100
},
{
"epoch": 0.2,
"learning_rate": 1.676829268292683e-05,
"loss": 0.7661,
"step": 110
},
{
"epoch": 0.22,
"learning_rate": 1.8292682926829268e-05,
"loss": 0.7545,
"step": 120
},
{
"epoch": 0.24,
"learning_rate": 1.9817073170731708e-05,
"loss": 0.7431,
"step": 130
},
{
"epoch": 0.26,
"learning_rate": 2.134146341463415e-05,
"loss": 0.7103,
"step": 140
},
{
"epoch": 0.27,
"learning_rate": 2.286585365853659e-05,
"loss": 0.7522,
"step": 150
},
{
"epoch": 0.29,
"learning_rate": 2.4390243902439026e-05,
"loss": 0.7387,
"step": 160
},
{
"epoch": 0.31,
"learning_rate": 2.5914634146341466e-05,
"loss": 0.7177,
"step": 170
},
{
"epoch": 0.33,
"learning_rate": 2.7439024390243906e-05,
"loss": 0.6914,
"step": 180
},
{
"epoch": 0.35,
"learning_rate": 2.896341463414634e-05,
"loss": 0.6901,
"step": 190
},
{
"epoch": 0.37,
"learning_rate": 3.048780487804878e-05,
"loss": 0.712,
"step": 200
},
{
"epoch": 0.38,
"learning_rate": 3.201219512195122e-05,
"loss": 0.6809,
"step": 210
},
{
"epoch": 0.4,
"learning_rate": 3.353658536585366e-05,
"loss": 0.6893,
"step": 220
},
{
"epoch": 0.42,
"learning_rate": 3.5060975609756095e-05,
"loss": 0.6855,
"step": 230
},
{
"epoch": 0.44,
"learning_rate": 3.6585365853658535e-05,
"loss": 0.6507,
"step": 240
},
{
"epoch": 0.46,
"learning_rate": 3.8109756097560976e-05,
"loss": 0.6663,
"step": 250
},
{
"epoch": 0.48,
"learning_rate": 3.9634146341463416e-05,
"loss": 0.6314,
"step": 260
},
{
"epoch": 0.49,
"learning_rate": 4.1158536585365856e-05,
"loss": 0.6499,
"step": 270
},
{
"epoch": 0.51,
"learning_rate": 4.26829268292683e-05,
"loss": 0.6157,
"step": 280
},
{
"epoch": 0.53,
"learning_rate": 4.420731707317074e-05,
"loss": 0.6448,
"step": 290
},
{
"epoch": 0.55,
"learning_rate": 4.573170731707318e-05,
"loss": 0.626,
"step": 300
},
{
"epoch": 0.57,
"learning_rate": 4.725609756097561e-05,
"loss": 0.6497,
"step": 310
},
{
"epoch": 0.59,
"learning_rate": 4.878048780487805e-05,
"loss": 0.6293,
"step": 320
},
{
"epoch": 0.6,
"learning_rate": 4.996607869742198e-05,
"loss": 0.6415,
"step": 330
},
{
"epoch": 0.62,
"learning_rate": 4.979647218453189e-05,
"loss": 0.6102,
"step": 340
},
{
"epoch": 0.64,
"learning_rate": 4.9626865671641794e-05,
"loss": 0.6512,
"step": 350
},
{
"epoch": 0.66,
"learning_rate": 4.94572591587517e-05,
"loss": 0.6064,
"step": 360
},
{
"epoch": 0.68,
"learning_rate": 4.928765264586161e-05,
"loss": 0.5877,
"step": 370
},
{
"epoch": 0.7,
"learning_rate": 4.911804613297151e-05,
"loss": 0.5821,
"step": 380
},
{
"epoch": 0.71,
"learning_rate": 4.894843962008141e-05,
"loss": 0.5949,
"step": 390
},
{
"epoch": 0.73,
"learning_rate": 4.877883310719132e-05,
"loss": 0.5962,
"step": 400
},
{
"epoch": 0.75,
"learning_rate": 4.860922659430122e-05,
"loss": 0.5869,
"step": 410
},
{
"epoch": 0.77,
"learning_rate": 4.843962008141113e-05,
"loss": 0.5715,
"step": 420
},
{
"epoch": 0.79,
"learning_rate": 4.827001356852103e-05,
"loss": 0.5813,
"step": 430
},
{
"epoch": 0.8,
"learning_rate": 4.810040705563094e-05,
"loss": 0.5453,
"step": 440
},
{
"epoch": 0.82,
"learning_rate": 4.7930800542740845e-05,
"loss": 0.5238,
"step": 450
},
{
"epoch": 0.84,
"learning_rate": 4.7761194029850745e-05,
"loss": 0.5694,
"step": 460
},
{
"epoch": 0.86,
"learning_rate": 4.759158751696066e-05,
"loss": 0.5582,
"step": 470
},
{
"epoch": 0.88,
"learning_rate": 4.742198100407056e-05,
"loss": 0.539,
"step": 480
},
{
"epoch": 0.9,
"learning_rate": 4.7252374491180465e-05,
"loss": 0.6055,
"step": 490
},
{
"epoch": 0.91,
"learning_rate": 4.708276797829037e-05,
"loss": 0.5623,
"step": 500
},
{
"epoch": 0.93,
"learning_rate": 4.691316146540027e-05,
"loss": 0.5771,
"step": 510
},
{
"epoch": 0.95,
"learning_rate": 4.674355495251018e-05,
"loss": 0.5273,
"step": 520
},
{
"epoch": 0.97,
"learning_rate": 4.6573948439620084e-05,
"loss": 0.5157,
"step": 530
},
{
"epoch": 0.99,
"learning_rate": 4.640434192672999e-05,
"loss": 0.5433,
"step": 540
},
{
"epoch": 1.0,
"eval_accuracy": 0.8537533403514455,
"eval_loss": 0.36576539278030396,
"eval_runtime": 206.4632,
"eval_samples_per_second": 59.812,
"eval_steps_per_second": 1.87,
"step": 546
},
{
"epoch": 1.01,
"learning_rate": 4.623473541383989e-05,
"loss": 0.5664,
"step": 550
},
{
"epoch": 1.03,
"learning_rate": 4.60651289009498e-05,
"loss": 0.5373,
"step": 560
},
{
"epoch": 1.04,
"learning_rate": 4.58955223880597e-05,
"loss": 0.4839,
"step": 570
},
{
"epoch": 1.06,
"learning_rate": 4.57259158751696e-05,
"loss": 0.5462,
"step": 580
},
{
"epoch": 1.08,
"learning_rate": 4.5556309362279516e-05,
"loss": 0.4843,
"step": 590
},
{
"epoch": 1.1,
"learning_rate": 4.5386702849389416e-05,
"loss": 0.4725,
"step": 600
},
{
"epoch": 1.12,
"learning_rate": 4.521709633649933e-05,
"loss": 0.51,
"step": 610
},
{
"epoch": 1.14,
"learning_rate": 4.504748982360923e-05,
"loss": 0.5125,
"step": 620
},
{
"epoch": 1.15,
"learning_rate": 4.4877883310719135e-05,
"loss": 0.4948,
"step": 630
},
{
"epoch": 1.17,
"learning_rate": 4.470827679782904e-05,
"loss": 0.5021,
"step": 640
},
{
"epoch": 1.19,
"learning_rate": 4.453867028493894e-05,
"loss": 0.5344,
"step": 650
},
{
"epoch": 1.21,
"learning_rate": 4.436906377204885e-05,
"loss": 0.4832,
"step": 660
},
{
"epoch": 1.23,
"learning_rate": 4.4199457259158754e-05,
"loss": 0.4625,
"step": 670
},
{
"epoch": 1.25,
"learning_rate": 4.402985074626866e-05,
"loss": 0.4824,
"step": 680
},
{
"epoch": 1.26,
"learning_rate": 4.386024423337856e-05,
"loss": 0.4513,
"step": 690
},
{
"epoch": 1.28,
"learning_rate": 4.369063772048847e-05,
"loss": 0.4382,
"step": 700
},
{
"epoch": 1.3,
"learning_rate": 4.3521031207598374e-05,
"loss": 0.4615,
"step": 710
},
{
"epoch": 1.32,
"learning_rate": 4.335142469470828e-05,
"loss": 0.4568,
"step": 720
},
{
"epoch": 1.34,
"learning_rate": 4.318181818181819e-05,
"loss": 0.4518,
"step": 730
},
{
"epoch": 1.35,
"learning_rate": 4.3012211668928086e-05,
"loss": 0.4651,
"step": 740
},
{
"epoch": 1.37,
"learning_rate": 4.284260515603799e-05,
"loss": 0.4494,
"step": 750
},
{
"epoch": 1.39,
"learning_rate": 4.26729986431479e-05,
"loss": 0.4458,
"step": 760
},
{
"epoch": 1.41,
"learning_rate": 4.25033921302578e-05,
"loss": 0.427,
"step": 770
},
{
"epoch": 1.43,
"learning_rate": 4.233378561736771e-05,
"loss": 0.4564,
"step": 780
},
{
"epoch": 1.45,
"learning_rate": 4.216417910447761e-05,
"loss": 0.3992,
"step": 790
},
{
"epoch": 1.46,
"learning_rate": 4.199457259158752e-05,
"loss": 0.4369,
"step": 800
},
{
"epoch": 1.48,
"learning_rate": 4.1824966078697425e-05,
"loss": 0.4514,
"step": 810
},
{
"epoch": 1.5,
"learning_rate": 4.1655359565807325e-05,
"loss": 0.4554,
"step": 820
},
{
"epoch": 1.52,
"learning_rate": 4.148575305291724e-05,
"loss": 0.4295,
"step": 830
},
{
"epoch": 1.54,
"learning_rate": 4.131614654002714e-05,
"loss": 0.3885,
"step": 840
},
{
"epoch": 1.56,
"learning_rate": 4.1146540027137044e-05,
"loss": 0.3984,
"step": 850
},
{
"epoch": 1.57,
"learning_rate": 4.097693351424695e-05,
"loss": 0.4286,
"step": 860
},
{
"epoch": 1.59,
"learning_rate": 4.080732700135686e-05,
"loss": 0.3896,
"step": 870
},
{
"epoch": 1.61,
"learning_rate": 4.063772048846676e-05,
"loss": 0.4155,
"step": 880
},
{
"epoch": 1.63,
"learning_rate": 4.0468113975576664e-05,
"loss": 0.4385,
"step": 890
},
{
"epoch": 1.65,
"learning_rate": 4.029850746268657e-05,
"loss": 0.4015,
"step": 900
},
{
"epoch": 1.67,
"learning_rate": 4.012890094979647e-05,
"loss": 0.4346,
"step": 910
},
{
"epoch": 1.68,
"learning_rate": 3.995929443690638e-05,
"loss": 0.4322,
"step": 920
},
{
"epoch": 1.7,
"learning_rate": 3.978968792401628e-05,
"loss": 0.4195,
"step": 930
},
{
"epoch": 1.72,
"learning_rate": 3.962008141112619e-05,
"loss": 0.4291,
"step": 940
},
{
"epoch": 1.74,
"learning_rate": 3.9450474898236096e-05,
"loss": 0.3944,
"step": 950
},
{
"epoch": 1.76,
"learning_rate": 3.9280868385345995e-05,
"loss": 0.419,
"step": 960
},
{
"epoch": 1.78,
"learning_rate": 3.911126187245591e-05,
"loss": 0.4262,
"step": 970
},
{
"epoch": 1.79,
"learning_rate": 3.894165535956581e-05,
"loss": 0.3908,
"step": 980
},
{
"epoch": 1.81,
"learning_rate": 3.8772048846675715e-05,
"loss": 0.3874,
"step": 990
},
{
"epoch": 1.83,
"learning_rate": 3.860244233378562e-05,
"loss": 0.4107,
"step": 1000
},
{
"epoch": 1.85,
"learning_rate": 3.843283582089552e-05,
"loss": 0.4068,
"step": 1010
},
{
"epoch": 1.87,
"learning_rate": 3.826322930800543e-05,
"loss": 0.4207,
"step": 1020
},
{
"epoch": 1.89,
"learning_rate": 3.8093622795115334e-05,
"loss": 0.3736,
"step": 1030
},
{
"epoch": 1.9,
"learning_rate": 3.792401628222524e-05,
"loss": 0.3588,
"step": 1040
},
{
"epoch": 1.92,
"learning_rate": 3.775440976933514e-05,
"loss": 0.3974,
"step": 1050
},
{
"epoch": 1.94,
"learning_rate": 3.7584803256445054e-05,
"loss": 0.448,
"step": 1060
},
{
"epoch": 1.96,
"learning_rate": 3.741519674355495e-05,
"loss": 0.4074,
"step": 1070
},
{
"epoch": 1.98,
"learning_rate": 3.724559023066486e-05,
"loss": 0.3548,
"step": 1080
},
{
"epoch": 1.99,
"learning_rate": 3.7075983717774766e-05,
"loss": 0.366,
"step": 1090
},
{
"epoch": 2.0,
"eval_accuracy": 0.91545874159851,
"eval_loss": 0.21362212300300598,
"eval_runtime": 203.5259,
"eval_samples_per_second": 60.675,
"eval_steps_per_second": 1.897,
"step": 1092
},
{
"epoch": 2.01,
"learning_rate": 3.6906377204884666e-05,
"loss": 0.4042,
"step": 1100
},
{
"epoch": 2.03,
"learning_rate": 3.673677069199458e-05,
"loss": 0.3562,
"step": 1110
},
{
"epoch": 2.05,
"learning_rate": 3.656716417910448e-05,
"loss": 0.3795,
"step": 1120
},
{
"epoch": 2.07,
"learning_rate": 3.6397557666214386e-05,
"loss": 0.3778,
"step": 1130
},
{
"epoch": 2.09,
"learning_rate": 3.622795115332429e-05,
"loss": 0.3401,
"step": 1140
},
{
"epoch": 2.11,
"learning_rate": 3.605834464043419e-05,
"loss": 0.3334,
"step": 1150
},
{
"epoch": 2.12,
"learning_rate": 3.58887381275441e-05,
"loss": 0.3529,
"step": 1160
},
{
"epoch": 2.14,
"learning_rate": 3.5719131614654005e-05,
"loss": 0.3724,
"step": 1170
},
{
"epoch": 2.16,
"learning_rate": 3.554952510176391e-05,
"loss": 0.3719,
"step": 1180
},
{
"epoch": 2.18,
"learning_rate": 3.537991858887382e-05,
"loss": 0.3561,
"step": 1190
},
{
"epoch": 2.2,
"learning_rate": 3.521031207598372e-05,
"loss": 0.3711,
"step": 1200
},
{
"epoch": 2.22,
"learning_rate": 3.5040705563093624e-05,
"loss": 0.3743,
"step": 1210
},
{
"epoch": 2.23,
"learning_rate": 3.487109905020353e-05,
"loss": 0.3608,
"step": 1220
},
{
"epoch": 2.25,
"learning_rate": 3.470149253731344e-05,
"loss": 0.3561,
"step": 1230
},
{
"epoch": 2.27,
"learning_rate": 3.453188602442334e-05,
"loss": 0.3773,
"step": 1240
},
{
"epoch": 2.29,
"learning_rate": 3.436227951153324e-05,
"loss": 0.3753,
"step": 1250
},
{
"epoch": 2.31,
"learning_rate": 3.419267299864315e-05,
"loss": 0.3408,
"step": 1260
},
{
"epoch": 2.33,
"learning_rate": 3.402306648575305e-05,
"loss": 0.3511,
"step": 1270
},
{
"epoch": 2.34,
"learning_rate": 3.385345997286296e-05,
"loss": 0.3459,
"step": 1280
},
{
"epoch": 2.36,
"learning_rate": 3.368385345997286e-05,
"loss": 0.3422,
"step": 1290
},
{
"epoch": 2.38,
"learning_rate": 3.351424694708277e-05,
"loss": 0.3094,
"step": 1300
},
{
"epoch": 2.4,
"learning_rate": 3.3344640434192675e-05,
"loss": 0.3451,
"step": 1310
},
{
"epoch": 2.42,
"learning_rate": 3.3175033921302575e-05,
"loss": 0.3368,
"step": 1320
},
{
"epoch": 2.44,
"learning_rate": 3.300542740841249e-05,
"loss": 0.3197,
"step": 1330
},
{
"epoch": 2.45,
"learning_rate": 3.283582089552239e-05,
"loss": 0.3501,
"step": 1340
},
{
"epoch": 2.47,
"learning_rate": 3.2666214382632295e-05,
"loss": 0.3403,
"step": 1350
},
{
"epoch": 2.49,
"learning_rate": 3.24966078697422e-05,
"loss": 0.3609,
"step": 1360
},
{
"epoch": 2.51,
"learning_rate": 3.232700135685211e-05,
"loss": 0.3305,
"step": 1370
},
{
"epoch": 2.53,
"learning_rate": 3.215739484396201e-05,
"loss": 0.3445,
"step": 1380
},
{
"epoch": 2.55,
"learning_rate": 3.1987788331071914e-05,
"loss": 0.3352,
"step": 1390
},
{
"epoch": 2.56,
"learning_rate": 3.181818181818182e-05,
"loss": 0.3215,
"step": 1400
},
{
"epoch": 2.58,
"learning_rate": 3.164857530529172e-05,
"loss": 0.3233,
"step": 1410
},
{
"epoch": 2.6,
"learning_rate": 3.147896879240163e-05,
"loss": 0.3439,
"step": 1420
},
{
"epoch": 2.62,
"learning_rate": 3.130936227951153e-05,
"loss": 0.3357,
"step": 1430
},
{
"epoch": 2.64,
"learning_rate": 3.113975576662144e-05,
"loss": 0.3139,
"step": 1440
},
{
"epoch": 2.65,
"learning_rate": 3.0970149253731346e-05,
"loss": 0.3227,
"step": 1450
},
{
"epoch": 2.67,
"learning_rate": 3.0800542740841246e-05,
"loss": 0.2932,
"step": 1460
},
{
"epoch": 2.69,
"learning_rate": 3.063093622795116e-05,
"loss": 0.2985,
"step": 1470
},
{
"epoch": 2.71,
"learning_rate": 3.046132971506106e-05,
"loss": 0.3389,
"step": 1480
},
{
"epoch": 2.73,
"learning_rate": 3.0291723202170962e-05,
"loss": 0.3213,
"step": 1490
},
{
"epoch": 2.75,
"learning_rate": 3.0122116689280872e-05,
"loss": 0.312,
"step": 1500
},
{
"epoch": 2.76,
"learning_rate": 2.9952510176390775e-05,
"loss": 0.312,
"step": 1510
},
{
"epoch": 2.78,
"learning_rate": 2.9782903663500678e-05,
"loss": 0.2871,
"step": 1520
},
{
"epoch": 2.8,
"learning_rate": 2.9613297150610584e-05,
"loss": 0.3308,
"step": 1530
},
{
"epoch": 2.82,
"learning_rate": 2.9443690637720488e-05,
"loss": 0.28,
"step": 1540
},
{
"epoch": 2.84,
"learning_rate": 2.9274084124830397e-05,
"loss": 0.288,
"step": 1550
},
{
"epoch": 2.86,
"learning_rate": 2.91044776119403e-05,
"loss": 0.3126,
"step": 1560
},
{
"epoch": 2.87,
"learning_rate": 2.8934871099050204e-05,
"loss": 0.2924,
"step": 1570
},
{
"epoch": 2.89,
"learning_rate": 2.8765264586160114e-05,
"loss": 0.2895,
"step": 1580
},
{
"epoch": 2.91,
"learning_rate": 2.8595658073270017e-05,
"loss": 0.2773,
"step": 1590
},
{
"epoch": 2.93,
"learning_rate": 2.842605156037992e-05,
"loss": 0.287,
"step": 1600
},
{
"epoch": 2.95,
"learning_rate": 2.8256445047489826e-05,
"loss": 0.3182,
"step": 1610
},
{
"epoch": 2.97,
"learning_rate": 2.808683853459973e-05,
"loss": 0.3315,
"step": 1620
},
{
"epoch": 2.98,
"learning_rate": 2.7917232021709632e-05,
"loss": 0.3109,
"step": 1630
},
{
"epoch": 3.0,
"eval_accuracy": 0.9499554619807272,
"eval_loss": 0.1381101757287979,
"eval_runtime": 200.9359,
"eval_samples_per_second": 61.457,
"eval_steps_per_second": 1.921,
"step": 1638
},
{
"epoch": 3.0,
"learning_rate": 2.7747625508819542e-05,
"loss": 0.3194,
"step": 1640
},
{
"epoch": 3.02,
"learning_rate": 2.7578018995929445e-05,
"loss": 0.2683,
"step": 1650
},
{
"epoch": 3.04,
"learning_rate": 2.740841248303935e-05,
"loss": 0.2782,
"step": 1660
},
{
"epoch": 3.06,
"learning_rate": 2.7238805970149255e-05,
"loss": 0.3173,
"step": 1670
},
{
"epoch": 3.08,
"learning_rate": 2.7069199457259158e-05,
"loss": 0.2727,
"step": 1680
},
{
"epoch": 3.1,
"learning_rate": 2.6899592944369068e-05,
"loss": 0.3061,
"step": 1690
},
{
"epoch": 3.11,
"learning_rate": 2.672998643147897e-05,
"loss": 0.3275,
"step": 1700
},
{
"epoch": 3.13,
"learning_rate": 2.6560379918588874e-05,
"loss": 0.2705,
"step": 1710
},
{
"epoch": 3.15,
"learning_rate": 2.639077340569878e-05,
"loss": 0.2868,
"step": 1720
},
{
"epoch": 3.17,
"learning_rate": 2.6221166892808684e-05,
"loss": 0.3137,
"step": 1730
},
{
"epoch": 3.19,
"learning_rate": 2.6051560379918587e-05,
"loss": 0.3149,
"step": 1740
},
{
"epoch": 3.2,
"learning_rate": 2.5881953867028497e-05,
"loss": 0.2753,
"step": 1750
},
{
"epoch": 3.22,
"learning_rate": 2.57123473541384e-05,
"loss": 0.2677,
"step": 1760
},
{
"epoch": 3.24,
"learning_rate": 2.5542740841248303e-05,
"loss": 0.2966,
"step": 1770
},
{
"epoch": 3.26,
"learning_rate": 2.537313432835821e-05,
"loss": 0.3174,
"step": 1780
},
{
"epoch": 3.28,
"learning_rate": 2.5203527815468113e-05,
"loss": 0.2945,
"step": 1790
},
{
"epoch": 3.3,
"learning_rate": 2.5033921302578023e-05,
"loss": 0.2543,
"step": 1800
},
{
"epoch": 3.31,
"learning_rate": 2.4864314789687926e-05,
"loss": 0.294,
"step": 1810
},
{
"epoch": 3.33,
"learning_rate": 2.469470827679783e-05,
"loss": 0.2789,
"step": 1820
},
{
"epoch": 3.35,
"learning_rate": 2.4525101763907735e-05,
"loss": 0.2879,
"step": 1830
},
{
"epoch": 3.37,
"learning_rate": 2.4355495251017642e-05,
"loss": 0.2986,
"step": 1840
},
{
"epoch": 3.39,
"learning_rate": 2.4185888738127545e-05,
"loss": 0.2901,
"step": 1850
},
{
"epoch": 3.41,
"learning_rate": 2.4016282225237448e-05,
"loss": 0.2698,
"step": 1860
},
{
"epoch": 3.42,
"learning_rate": 2.3846675712347355e-05,
"loss": 0.2611,
"step": 1870
},
{
"epoch": 3.44,
"learning_rate": 2.367706919945726e-05,
"loss": 0.2883,
"step": 1880
},
{
"epoch": 3.46,
"learning_rate": 2.3507462686567168e-05,
"loss": 0.2847,
"step": 1890
},
{
"epoch": 3.48,
"learning_rate": 2.333785617367707e-05,
"loss": 0.2719,
"step": 1900
},
{
"epoch": 3.5,
"learning_rate": 2.3168249660786974e-05,
"loss": 0.2584,
"step": 1910
},
{
"epoch": 3.52,
"learning_rate": 2.299864314789688e-05,
"loss": 0.2926,
"step": 1920
},
{
"epoch": 3.53,
"learning_rate": 2.2829036635006783e-05,
"loss": 0.2668,
"step": 1930
},
{
"epoch": 3.55,
"learning_rate": 2.265943012211669e-05,
"loss": 0.2912,
"step": 1940
},
{
"epoch": 3.57,
"learning_rate": 2.2489823609226596e-05,
"loss": 0.2745,
"step": 1950
},
{
"epoch": 3.59,
"learning_rate": 2.2320217096336503e-05,
"loss": 0.2759,
"step": 1960
},
{
"epoch": 3.61,
"learning_rate": 2.2150610583446406e-05,
"loss": 0.2509,
"step": 1970
},
{
"epoch": 3.63,
"learning_rate": 2.198100407055631e-05,
"loss": 0.2616,
"step": 1980
},
{
"epoch": 3.64,
"learning_rate": 2.1811397557666216e-05,
"loss": 0.2628,
"step": 1990
},
{
"epoch": 3.66,
"learning_rate": 2.164179104477612e-05,
"loss": 0.2723,
"step": 2000
},
{
"epoch": 3.68,
"learning_rate": 2.1472184531886025e-05,
"loss": 0.2682,
"step": 2010
},
{
"epoch": 3.7,
"learning_rate": 2.130257801899593e-05,
"loss": 0.2729,
"step": 2020
},
{
"epoch": 3.72,
"learning_rate": 2.1132971506105835e-05,
"loss": 0.2861,
"step": 2030
},
{
"epoch": 3.74,
"learning_rate": 2.0963364993215738e-05,
"loss": 0.2803,
"step": 2040
},
{
"epoch": 3.75,
"learning_rate": 2.0793758480325644e-05,
"loss": 0.2415,
"step": 2050
},
{
"epoch": 3.77,
"learning_rate": 2.062415196743555e-05,
"loss": 0.2758,
"step": 2060
},
{
"epoch": 3.79,
"learning_rate": 2.0454545454545457e-05,
"loss": 0.2663,
"step": 2070
},
{
"epoch": 3.81,
"learning_rate": 2.028493894165536e-05,
"loss": 0.2573,
"step": 2080
},
{
"epoch": 3.83,
"learning_rate": 2.0115332428765267e-05,
"loss": 0.2521,
"step": 2090
},
{
"epoch": 3.84,
"learning_rate": 1.994572591587517e-05,
"loss": 0.2567,
"step": 2100
},
{
"epoch": 3.86,
"learning_rate": 1.9776119402985073e-05,
"loss": 0.2569,
"step": 2110
},
{
"epoch": 3.88,
"learning_rate": 1.960651289009498e-05,
"loss": 0.2751,
"step": 2120
},
{
"epoch": 3.9,
"learning_rate": 1.9436906377204886e-05,
"loss": 0.2775,
"step": 2130
},
{
"epoch": 3.92,
"learning_rate": 1.9267299864314793e-05,
"loss": 0.2763,
"step": 2140
},
{
"epoch": 3.94,
"learning_rate": 1.9097693351424696e-05,
"loss": 0.2484,
"step": 2150
},
{
"epoch": 3.95,
"learning_rate": 1.89280868385346e-05,
"loss": 0.2656,
"step": 2160
},
{
"epoch": 3.97,
"learning_rate": 1.8758480325644505e-05,
"loss": 0.2511,
"step": 2170
},
{
"epoch": 3.99,
"learning_rate": 1.858887381275441e-05,
"loss": 0.2501,
"step": 2180
},
{
"epoch": 4.0,
"eval_accuracy": 0.960401651955624,
"eval_loss": 0.10579904168844223,
"eval_runtime": 193.2913,
"eval_samples_per_second": 63.888,
"eval_steps_per_second": 1.997,
"step": 2184
},
{
"epoch": 4.01,
"learning_rate": 1.8419267299864315e-05,
"loss": 0.2779,
"step": 2190
},
{
"epoch": 4.03,
"learning_rate": 1.824966078697422e-05,
"loss": 0.2631,
"step": 2200
},
{
"epoch": 4.05,
"learning_rate": 1.8080054274084128e-05,
"loss": 0.2414,
"step": 2210
},
{
"epoch": 4.07,
"learning_rate": 1.791044776119403e-05,
"loss": 0.2583,
"step": 2220
},
{
"epoch": 4.08,
"learning_rate": 1.7740841248303934e-05,
"loss": 0.2574,
"step": 2230
},
{
"epoch": 4.1,
"learning_rate": 1.757123473541384e-05,
"loss": 0.2367,
"step": 2240
},
{
"epoch": 4.12,
"learning_rate": 1.7401628222523747e-05,
"loss": 0.2543,
"step": 2250
},
{
"epoch": 4.14,
"learning_rate": 1.723202170963365e-05,
"loss": 0.2456,
"step": 2260
},
{
"epoch": 4.16,
"learning_rate": 1.7062415196743557e-05,
"loss": 0.2262,
"step": 2270
},
{
"epoch": 4.18,
"learning_rate": 1.689280868385346e-05,
"loss": 0.2708,
"step": 2280
},
{
"epoch": 4.19,
"learning_rate": 1.6723202170963363e-05,
"loss": 0.2369,
"step": 2290
},
{
"epoch": 4.21,
"learning_rate": 1.655359565807327e-05,
"loss": 0.2347,
"step": 2300
},
{
"epoch": 4.23,
"learning_rate": 1.6383989145183176e-05,
"loss": 0.2741,
"step": 2310
},
{
"epoch": 4.25,
"learning_rate": 1.6214382632293083e-05,
"loss": 0.2422,
"step": 2320
},
{
"epoch": 4.27,
"learning_rate": 1.6044776119402986e-05,
"loss": 0.2374,
"step": 2330
},
{
"epoch": 4.29,
"learning_rate": 1.5875169606512892e-05,
"loss": 0.2174,
"step": 2340
},
{
"epoch": 4.3,
"learning_rate": 1.5705563093622795e-05,
"loss": 0.2402,
"step": 2350
},
{
"epoch": 4.32,
"learning_rate": 1.55359565807327e-05,
"loss": 0.243,
"step": 2360
},
{
"epoch": 4.34,
"learning_rate": 1.5366350067842605e-05,
"loss": 0.2101,
"step": 2370
},
{
"epoch": 4.36,
"learning_rate": 1.5196743554952511e-05,
"loss": 0.2542,
"step": 2380
},
{
"epoch": 4.38,
"learning_rate": 1.5027137042062416e-05,
"loss": 0.2415,
"step": 2390
},
{
"epoch": 4.4,
"learning_rate": 1.485753052917232e-05,
"loss": 0.2782,
"step": 2400
},
{
"epoch": 4.41,
"learning_rate": 1.4687924016282226e-05,
"loss": 0.2511,
"step": 2410
},
{
"epoch": 4.43,
"learning_rate": 1.4518317503392132e-05,
"loss": 0.2237,
"step": 2420
},
{
"epoch": 4.45,
"learning_rate": 1.4348710990502037e-05,
"loss": 0.2022,
"step": 2430
},
{
"epoch": 4.47,
"learning_rate": 1.417910447761194e-05,
"loss": 0.2466,
"step": 2440
},
{
"epoch": 4.49,
"learning_rate": 1.4009497964721847e-05,
"loss": 0.2598,
"step": 2450
},
{
"epoch": 4.5,
"learning_rate": 1.3839891451831751e-05,
"loss": 0.2306,
"step": 2460
},
{
"epoch": 4.52,
"learning_rate": 1.3670284938941655e-05,
"loss": 0.2475,
"step": 2470
},
{
"epoch": 4.54,
"learning_rate": 1.3500678426051561e-05,
"loss": 0.251,
"step": 2480
},
{
"epoch": 4.56,
"learning_rate": 1.3331071913161466e-05,
"loss": 0.2393,
"step": 2490
},
{
"epoch": 4.58,
"learning_rate": 1.3161465400271372e-05,
"loss": 0.2473,
"step": 2500
},
{
"epoch": 4.6,
"learning_rate": 1.2991858887381275e-05,
"loss": 0.2213,
"step": 2510
},
{
"epoch": 4.61,
"learning_rate": 1.282225237449118e-05,
"loss": 0.2219,
"step": 2520
},
{
"epoch": 4.63,
"learning_rate": 1.2652645861601087e-05,
"loss": 0.2249,
"step": 2530
},
{
"epoch": 4.65,
"learning_rate": 1.2483039348710992e-05,
"loss": 0.2294,
"step": 2540
},
{
"epoch": 4.67,
"learning_rate": 1.2313432835820896e-05,
"loss": 0.2228,
"step": 2550
},
{
"epoch": 4.69,
"learning_rate": 1.2143826322930801e-05,
"loss": 0.2439,
"step": 2560
},
{
"epoch": 4.71,
"learning_rate": 1.1974219810040706e-05,
"loss": 0.2505,
"step": 2570
},
{
"epoch": 4.72,
"learning_rate": 1.180461329715061e-05,
"loss": 0.2392,
"step": 2580
},
{
"epoch": 4.74,
"learning_rate": 1.1635006784260516e-05,
"loss": 0.2259,
"step": 2590
},
{
"epoch": 4.76,
"learning_rate": 1.1465400271370422e-05,
"loss": 0.2321,
"step": 2600
},
{
"epoch": 4.78,
"learning_rate": 1.1295793758480327e-05,
"loss": 0.2398,
"step": 2610
},
{
"epoch": 4.8,
"learning_rate": 1.112618724559023e-05,
"loss": 0.2343,
"step": 2620
},
{
"epoch": 4.82,
"learning_rate": 1.0956580732700137e-05,
"loss": 0.2345,
"step": 2630
},
{
"epoch": 4.83,
"learning_rate": 1.0786974219810041e-05,
"loss": 0.2171,
"step": 2640
},
{
"epoch": 4.85,
"learning_rate": 1.0617367706919946e-05,
"loss": 0.2562,
"step": 2650
},
{
"epoch": 4.87,
"learning_rate": 1.0447761194029851e-05,
"loss": 0.2568,
"step": 2660
},
{
"epoch": 4.89,
"learning_rate": 1.0278154681139757e-05,
"loss": 0.237,
"step": 2670
},
{
"epoch": 4.91,
"learning_rate": 1.010854816824966e-05,
"loss": 0.2186,
"step": 2680
},
{
"epoch": 4.93,
"learning_rate": 9.938941655359567e-06,
"loss": 0.2153,
"step": 2690
},
{
"epoch": 4.94,
"learning_rate": 9.769335142469472e-06,
"loss": 0.245,
"step": 2700
},
{
"epoch": 4.96,
"learning_rate": 9.599728629579375e-06,
"loss": 0.2082,
"step": 2710
},
{
"epoch": 4.98,
"learning_rate": 9.430122116689281e-06,
"loss": 0.2204,
"step": 2720
},
{
"epoch": 5.0,
"learning_rate": 9.260515603799186e-06,
"loss": 0.2515,
"step": 2730
},
{
"epoch": 5.0,
"eval_accuracy": 0.9646934974491862,
"eval_loss": 0.09361910074949265,
"eval_runtime": 192.1061,
"eval_samples_per_second": 64.282,
"eval_steps_per_second": 2.009,
"step": 2730
},
{
"epoch": 5.02,
"learning_rate": 9.090909090909091e-06,
"loss": 0.2526,
"step": 2740
},
{
"epoch": 5.04,
"learning_rate": 8.921302578018996e-06,
"loss": 0.2186,
"step": 2750
},
{
"epoch": 5.05,
"learning_rate": 8.751696065128902e-06,
"loss": 0.1975,
"step": 2760
},
{
"epoch": 5.07,
"learning_rate": 8.582089552238805e-06,
"loss": 0.2112,
"step": 2770
},
{
"epoch": 5.09,
"learning_rate": 8.412483039348712e-06,
"loss": 0.2201,
"step": 2780
},
{
"epoch": 5.11,
"learning_rate": 8.242876526458617e-06,
"loss": 0.2211,
"step": 2790
},
{
"epoch": 5.13,
"learning_rate": 8.073270013568522e-06,
"loss": 0.219,
"step": 2800
},
{
"epoch": 5.15,
"learning_rate": 7.903663500678426e-06,
"loss": 0.2276,
"step": 2810
},
{
"epoch": 5.16,
"learning_rate": 7.734056987788331e-06,
"loss": 0.2526,
"step": 2820
},
{
"epoch": 5.18,
"learning_rate": 7.564450474898237e-06,
"loss": 0.2447,
"step": 2830
},
{
"epoch": 5.2,
"learning_rate": 7.394843962008141e-06,
"loss": 0.2137,
"step": 2840
},
{
"epoch": 5.22,
"learning_rate": 7.225237449118047e-06,
"loss": 0.2136,
"step": 2850
},
{
"epoch": 5.24,
"learning_rate": 7.055630936227951e-06,
"loss": 0.2202,
"step": 2860
},
{
"epoch": 5.26,
"learning_rate": 6.886024423337857e-06,
"loss": 0.2092,
"step": 2870
},
{
"epoch": 5.27,
"learning_rate": 6.716417910447762e-06,
"loss": 0.2123,
"step": 2880
},
{
"epoch": 5.29,
"learning_rate": 6.546811397557666e-06,
"loss": 0.2178,
"step": 2890
},
{
"epoch": 5.31,
"learning_rate": 6.377204884667571e-06,
"loss": 0.2256,
"step": 2900
},
{
"epoch": 5.33,
"learning_rate": 6.207598371777477e-06,
"loss": 0.2012,
"step": 2910
},
{
"epoch": 5.35,
"learning_rate": 6.037991858887382e-06,
"loss": 0.2207,
"step": 2920
},
{
"epoch": 5.37,
"learning_rate": 5.8683853459972865e-06,
"loss": 0.1934,
"step": 2930
},
{
"epoch": 5.38,
"learning_rate": 5.698778833107191e-06,
"loss": 0.2171,
"step": 2940
},
{
"epoch": 5.4,
"learning_rate": 5.529172320217096e-06,
"loss": 0.2466,
"step": 2950
},
{
"epoch": 5.42,
"learning_rate": 5.359565807327002e-06,
"loss": 0.2171,
"step": 2960
},
{
"epoch": 5.44,
"learning_rate": 5.189959294436907e-06,
"loss": 0.2168,
"step": 2970
},
{
"epoch": 5.46,
"learning_rate": 5.020352781546811e-06,
"loss": 0.2126,
"step": 2980
},
{
"epoch": 5.48,
"learning_rate": 4.850746268656717e-06,
"loss": 0.2281,
"step": 2990
},
{
"epoch": 5.49,
"learning_rate": 4.681139755766622e-06,
"loss": 0.2291,
"step": 3000
},
{
"epoch": 5.51,
"learning_rate": 4.511533242876527e-06,
"loss": 0.2216,
"step": 3010
},
{
"epoch": 5.53,
"learning_rate": 4.3419267299864315e-06,
"loss": 0.198,
"step": 3020
},
{
"epoch": 5.55,
"learning_rate": 4.172320217096336e-06,
"loss": 0.2399,
"step": 3030
},
{
"epoch": 5.57,
"learning_rate": 4.002713704206242e-06,
"loss": 0.2471,
"step": 3040
},
{
"epoch": 5.59,
"learning_rate": 3.833107191316147e-06,
"loss": 0.2129,
"step": 3050
},
{
"epoch": 5.6,
"learning_rate": 3.6635006784260515e-06,
"loss": 0.2262,
"step": 3060
},
{
"epoch": 5.62,
"learning_rate": 3.4938941655359567e-06,
"loss": 0.2002,
"step": 3070
},
{
"epoch": 5.64,
"learning_rate": 3.324287652645862e-06,
"loss": 0.1986,
"step": 3080
},
{
"epoch": 5.66,
"learning_rate": 3.154681139755767e-06,
"loss": 0.2048,
"step": 3090
},
{
"epoch": 5.68,
"learning_rate": 2.9850746268656716e-06,
"loss": 0.2116,
"step": 3100
},
{
"epoch": 5.7,
"learning_rate": 2.815468113975577e-06,
"loss": 0.1974,
"step": 3110
},
{
"epoch": 5.71,
"learning_rate": 2.645861601085482e-06,
"loss": 0.2218,
"step": 3120
},
{
"epoch": 5.73,
"learning_rate": 2.476255088195387e-06,
"loss": 0.2084,
"step": 3130
},
{
"epoch": 5.75,
"learning_rate": 2.3066485753052916e-06,
"loss": 0.2171,
"step": 3140
},
{
"epoch": 5.77,
"learning_rate": 2.137042062415197e-06,
"loss": 0.2172,
"step": 3150
},
{
"epoch": 5.79,
"learning_rate": 1.967435549525102e-06,
"loss": 0.2268,
"step": 3160
},
{
"epoch": 5.8,
"learning_rate": 1.797829036635007e-06,
"loss": 0.2147,
"step": 3170
},
{
"epoch": 5.82,
"learning_rate": 1.6282225237449117e-06,
"loss": 0.2129,
"step": 3180
},
{
"epoch": 5.84,
"learning_rate": 1.458616010854817e-06,
"loss": 0.2081,
"step": 3190
},
{
"epoch": 5.86,
"learning_rate": 1.289009497964722e-06,
"loss": 0.224,
"step": 3200
},
{
"epoch": 5.88,
"learning_rate": 1.119402985074627e-06,
"loss": 0.2074,
"step": 3210
},
{
"epoch": 5.9,
"learning_rate": 9.49796472184532e-07,
"loss": 0.2075,
"step": 3220
},
{
"epoch": 5.91,
"learning_rate": 7.80189959294437e-07,
"loss": 0.1981,
"step": 3230
},
{
"epoch": 5.93,
"learning_rate": 6.10583446404342e-07,
"loss": 0.2124,
"step": 3240
},
{
"epoch": 5.95,
"learning_rate": 4.4097693351424695e-07,
"loss": 0.2035,
"step": 3250
},
{
"epoch": 5.97,
"learning_rate": 2.7137042062415197e-07,
"loss": 0.2317,
"step": 3260
},
{
"epoch": 5.99,
"learning_rate": 1.0176390773405698e-07,
"loss": 0.2311,
"step": 3270
},
{
"epoch": 6.0,
"eval_accuracy": 0.970766863713661,
"eval_loss": 0.07644093036651611,
"eval_runtime": 190.1522,
"eval_samples_per_second": 64.943,
"eval_steps_per_second": 2.03,
"step": 3276
},
{
"epoch": 6.0,
"step": 3276,
"total_flos": 1.3656980870969426e+19,
"train_loss": 0.3689301585976457,
"train_runtime": 12770.7006,
"train_samples_per_second": 32.875,
"train_steps_per_second": 0.257
}
],
"max_steps": 3276,
"num_train_epochs": 6,
"total_flos": 1.3656980870969426e+19,
"trial_name": null,
"trial_params": null
}