100rab25's picture
End of training
af94381 verified
raw
history blame contribute delete
No virus
141 kB
{
"best_metric": 0.936588653351305,
"best_model_checkpoint": "hotel_images_classifier_jd_v4_convnext/checkpoint-5735",
"epoch": 4.996732737965585,
"eval_steps": 500,
"global_step": 5735,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.3554006968641113e-07,
"loss": 2.1295,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 8.710801393728223e-07,
"loss": 2.1513,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 1.3066202090592335e-06,
"loss": 2.1402,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 1.7421602787456445e-06,
"loss": 2.1123,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 2.177700348432056e-06,
"loss": 2.099,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 2.613240418118467e-06,
"loss": 2.0814,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 3.0487804878048782e-06,
"loss": 2.0632,
"step": 35
},
{
"epoch": 0.03,
"learning_rate": 3.484320557491289e-06,
"loss": 2.0355,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 3.9198606271777e-06,
"loss": 1.9951,
"step": 45
},
{
"epoch": 0.04,
"learning_rate": 4.355400696864112e-06,
"loss": 1.951,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 4.790940766550523e-06,
"loss": 1.9243,
"step": 55
},
{
"epoch": 0.05,
"learning_rate": 5.226480836236934e-06,
"loss": 1.8926,
"step": 60
},
{
"epoch": 0.06,
"learning_rate": 5.662020905923345e-06,
"loss": 1.8243,
"step": 65
},
{
"epoch": 0.06,
"learning_rate": 6.0975609756097564e-06,
"loss": 1.8075,
"step": 70
},
{
"epoch": 0.07,
"learning_rate": 6.533101045296168e-06,
"loss": 1.7203,
"step": 75
},
{
"epoch": 0.07,
"learning_rate": 6.968641114982578e-06,
"loss": 1.6883,
"step": 80
},
{
"epoch": 0.07,
"learning_rate": 7.4041811846689906e-06,
"loss": 1.5936,
"step": 85
},
{
"epoch": 0.08,
"learning_rate": 7.8397212543554e-06,
"loss": 1.5082,
"step": 90
},
{
"epoch": 0.08,
"learning_rate": 8.275261324041812e-06,
"loss": 1.3915,
"step": 95
},
{
"epoch": 0.09,
"learning_rate": 8.710801393728225e-06,
"loss": 1.272,
"step": 100
},
{
"epoch": 0.09,
"learning_rate": 9.146341463414634e-06,
"loss": 1.2218,
"step": 105
},
{
"epoch": 0.1,
"learning_rate": 9.581881533101046e-06,
"loss": 1.1056,
"step": 110
},
{
"epoch": 0.1,
"learning_rate": 1.0017421602787457e-05,
"loss": 1.009,
"step": 115
},
{
"epoch": 0.1,
"learning_rate": 1.0452961672473868e-05,
"loss": 0.9107,
"step": 120
},
{
"epoch": 0.11,
"learning_rate": 1.0888501742160279e-05,
"loss": 0.8491,
"step": 125
},
{
"epoch": 0.11,
"learning_rate": 1.132404181184669e-05,
"loss": 0.8039,
"step": 130
},
{
"epoch": 0.12,
"learning_rate": 1.1759581881533102e-05,
"loss": 0.6879,
"step": 135
},
{
"epoch": 0.12,
"learning_rate": 1.2195121951219513e-05,
"loss": 0.6804,
"step": 140
},
{
"epoch": 0.13,
"learning_rate": 1.2630662020905924e-05,
"loss": 0.6651,
"step": 145
},
{
"epoch": 0.13,
"learning_rate": 1.3066202090592336e-05,
"loss": 0.7246,
"step": 150
},
{
"epoch": 0.14,
"learning_rate": 1.3501742160278747e-05,
"loss": 0.5941,
"step": 155
},
{
"epoch": 0.14,
"learning_rate": 1.3937282229965156e-05,
"loss": 0.6366,
"step": 160
},
{
"epoch": 0.14,
"learning_rate": 1.437282229965157e-05,
"loss": 0.632,
"step": 165
},
{
"epoch": 0.15,
"learning_rate": 1.4808362369337981e-05,
"loss": 0.6272,
"step": 170
},
{
"epoch": 0.15,
"learning_rate": 1.524390243902439e-05,
"loss": 0.5831,
"step": 175
},
{
"epoch": 0.16,
"learning_rate": 1.56794425087108e-05,
"loss": 0.6105,
"step": 180
},
{
"epoch": 0.16,
"learning_rate": 1.6114982578397215e-05,
"loss": 0.6166,
"step": 185
},
{
"epoch": 0.17,
"learning_rate": 1.6550522648083624e-05,
"loss": 0.5731,
"step": 190
},
{
"epoch": 0.17,
"learning_rate": 1.6986062717770033e-05,
"loss": 0.5418,
"step": 195
},
{
"epoch": 0.17,
"learning_rate": 1.742160278745645e-05,
"loss": 0.4829,
"step": 200
},
{
"epoch": 0.18,
"learning_rate": 1.785714285714286e-05,
"loss": 0.5338,
"step": 205
},
{
"epoch": 0.18,
"learning_rate": 1.8292682926829268e-05,
"loss": 0.5265,
"step": 210
},
{
"epoch": 0.19,
"learning_rate": 1.872822299651568e-05,
"loss": 0.4572,
"step": 215
},
{
"epoch": 0.19,
"learning_rate": 1.9163763066202093e-05,
"loss": 0.5556,
"step": 220
},
{
"epoch": 0.2,
"learning_rate": 1.9599303135888502e-05,
"loss": 0.5239,
"step": 225
},
{
"epoch": 0.2,
"learning_rate": 2.0034843205574914e-05,
"loss": 0.4671,
"step": 230
},
{
"epoch": 0.2,
"learning_rate": 2.0470383275261327e-05,
"loss": 0.6027,
"step": 235
},
{
"epoch": 0.21,
"learning_rate": 2.0905923344947736e-05,
"loss": 0.462,
"step": 240
},
{
"epoch": 0.21,
"learning_rate": 2.134146341463415e-05,
"loss": 0.4752,
"step": 245
},
{
"epoch": 0.22,
"learning_rate": 2.1777003484320557e-05,
"loss": 0.4944,
"step": 250
},
{
"epoch": 0.22,
"learning_rate": 2.221254355400697e-05,
"loss": 0.4744,
"step": 255
},
{
"epoch": 0.23,
"learning_rate": 2.264808362369338e-05,
"loss": 0.4163,
"step": 260
},
{
"epoch": 0.23,
"learning_rate": 2.308362369337979e-05,
"loss": 0.5049,
"step": 265
},
{
"epoch": 0.24,
"learning_rate": 2.3519163763066204e-05,
"loss": 0.4613,
"step": 270
},
{
"epoch": 0.24,
"learning_rate": 2.3954703832752613e-05,
"loss": 0.4569,
"step": 275
},
{
"epoch": 0.24,
"learning_rate": 2.4390243902439026e-05,
"loss": 0.5183,
"step": 280
},
{
"epoch": 0.25,
"learning_rate": 2.4825783972125435e-05,
"loss": 0.4588,
"step": 285
},
{
"epoch": 0.25,
"learning_rate": 2.5261324041811847e-05,
"loss": 0.4504,
"step": 290
},
{
"epoch": 0.26,
"learning_rate": 2.569686411149826e-05,
"loss": 0.4407,
"step": 295
},
{
"epoch": 0.26,
"learning_rate": 2.6132404181184672e-05,
"loss": 0.433,
"step": 300
},
{
"epoch": 0.27,
"learning_rate": 2.6567944250871078e-05,
"loss": 0.4703,
"step": 305
},
{
"epoch": 0.27,
"learning_rate": 2.7003484320557494e-05,
"loss": 0.4817,
"step": 310
},
{
"epoch": 0.27,
"learning_rate": 2.7439024390243906e-05,
"loss": 0.4096,
"step": 315
},
{
"epoch": 0.28,
"learning_rate": 2.7874564459930312e-05,
"loss": 0.4442,
"step": 320
},
{
"epoch": 0.28,
"learning_rate": 2.8310104529616728e-05,
"loss": 0.4346,
"step": 325
},
{
"epoch": 0.29,
"learning_rate": 2.874564459930314e-05,
"loss": 0.3935,
"step": 330
},
{
"epoch": 0.29,
"learning_rate": 2.9181184668989546e-05,
"loss": 0.4138,
"step": 335
},
{
"epoch": 0.3,
"learning_rate": 2.9616724738675962e-05,
"loss": 0.5147,
"step": 340
},
{
"epoch": 0.3,
"learning_rate": 3.0052264808362368e-05,
"loss": 0.4364,
"step": 345
},
{
"epoch": 0.3,
"learning_rate": 3.048780487804878e-05,
"loss": 0.4994,
"step": 350
},
{
"epoch": 0.31,
"learning_rate": 3.092334494773519e-05,
"loss": 0.4408,
"step": 355
},
{
"epoch": 0.31,
"learning_rate": 3.13588850174216e-05,
"loss": 0.4428,
"step": 360
},
{
"epoch": 0.32,
"learning_rate": 3.179442508710802e-05,
"loss": 0.4494,
"step": 365
},
{
"epoch": 0.32,
"learning_rate": 3.222996515679443e-05,
"loss": 0.4916,
"step": 370
},
{
"epoch": 0.33,
"learning_rate": 3.2665505226480836e-05,
"loss": 0.3654,
"step": 375
},
{
"epoch": 0.33,
"learning_rate": 3.310104529616725e-05,
"loss": 0.4449,
"step": 380
},
{
"epoch": 0.34,
"learning_rate": 3.353658536585366e-05,
"loss": 0.4065,
"step": 385
},
{
"epoch": 0.34,
"learning_rate": 3.397212543554007e-05,
"loss": 0.4061,
"step": 390
},
{
"epoch": 0.34,
"learning_rate": 3.4407665505226486e-05,
"loss": 0.4105,
"step": 395
},
{
"epoch": 0.35,
"learning_rate": 3.48432055749129e-05,
"loss": 0.3599,
"step": 400
},
{
"epoch": 0.35,
"learning_rate": 3.5278745644599304e-05,
"loss": 0.4127,
"step": 405
},
{
"epoch": 0.36,
"learning_rate": 3.571428571428572e-05,
"loss": 0.3913,
"step": 410
},
{
"epoch": 0.36,
"learning_rate": 3.614982578397213e-05,
"loss": 0.4144,
"step": 415
},
{
"epoch": 0.37,
"learning_rate": 3.6585365853658535e-05,
"loss": 0.453,
"step": 420
},
{
"epoch": 0.37,
"learning_rate": 3.702090592334495e-05,
"loss": 0.4115,
"step": 425
},
{
"epoch": 0.37,
"learning_rate": 3.745644599303136e-05,
"loss": 0.3922,
"step": 430
},
{
"epoch": 0.38,
"learning_rate": 3.789198606271777e-05,
"loss": 0.4046,
"step": 435
},
{
"epoch": 0.38,
"learning_rate": 3.8327526132404185e-05,
"loss": 0.4329,
"step": 440
},
{
"epoch": 0.39,
"learning_rate": 3.876306620209059e-05,
"loss": 0.396,
"step": 445
},
{
"epoch": 0.39,
"learning_rate": 3.9198606271777003e-05,
"loss": 0.3752,
"step": 450
},
{
"epoch": 0.4,
"learning_rate": 3.9634146341463416e-05,
"loss": 0.4517,
"step": 455
},
{
"epoch": 0.4,
"learning_rate": 4.006968641114983e-05,
"loss": 0.4133,
"step": 460
},
{
"epoch": 0.41,
"learning_rate": 4.050522648083624e-05,
"loss": 0.4157,
"step": 465
},
{
"epoch": 0.41,
"learning_rate": 4.0940766550522653e-05,
"loss": 0.3896,
"step": 470
},
{
"epoch": 0.41,
"learning_rate": 4.137630662020906e-05,
"loss": 0.4439,
"step": 475
},
{
"epoch": 0.42,
"learning_rate": 4.181184668989547e-05,
"loss": 0.43,
"step": 480
},
{
"epoch": 0.42,
"learning_rate": 4.2247386759581884e-05,
"loss": 0.4353,
"step": 485
},
{
"epoch": 0.43,
"learning_rate": 4.26829268292683e-05,
"loss": 0.4139,
"step": 490
},
{
"epoch": 0.43,
"learning_rate": 4.311846689895471e-05,
"loss": 0.4046,
"step": 495
},
{
"epoch": 0.44,
"learning_rate": 4.3554006968641115e-05,
"loss": 0.3796,
"step": 500
},
{
"epoch": 0.44,
"learning_rate": 4.398954703832753e-05,
"loss": 0.3573,
"step": 505
},
{
"epoch": 0.44,
"learning_rate": 4.442508710801394e-05,
"loss": 0.3775,
"step": 510
},
{
"epoch": 0.45,
"learning_rate": 4.4860627177700346e-05,
"loss": 0.3842,
"step": 515
},
{
"epoch": 0.45,
"learning_rate": 4.529616724738676e-05,
"loss": 0.4263,
"step": 520
},
{
"epoch": 0.46,
"learning_rate": 4.573170731707318e-05,
"loss": 0.4224,
"step": 525
},
{
"epoch": 0.46,
"learning_rate": 4.616724738675958e-05,
"loss": 0.3573,
"step": 530
},
{
"epoch": 0.47,
"learning_rate": 4.6602787456445996e-05,
"loss": 0.3622,
"step": 535
},
{
"epoch": 0.47,
"learning_rate": 4.703832752613241e-05,
"loss": 0.395,
"step": 540
},
{
"epoch": 0.47,
"learning_rate": 4.7473867595818814e-05,
"loss": 0.4084,
"step": 545
},
{
"epoch": 0.48,
"learning_rate": 4.7909407665505226e-05,
"loss": 0.3787,
"step": 550
},
{
"epoch": 0.48,
"learning_rate": 4.8344947735191646e-05,
"loss": 0.3119,
"step": 555
},
{
"epoch": 0.49,
"learning_rate": 4.878048780487805e-05,
"loss": 0.3595,
"step": 560
},
{
"epoch": 0.49,
"learning_rate": 4.9216027874564464e-05,
"loss": 0.3358,
"step": 565
},
{
"epoch": 0.5,
"learning_rate": 4.965156794425087e-05,
"loss": 0.3784,
"step": 570
},
{
"epoch": 0.5,
"learning_rate": 4.9990311955047475e-05,
"loss": 0.3965,
"step": 575
},
{
"epoch": 0.51,
"learning_rate": 4.994187173028483e-05,
"loss": 0.4117,
"step": 580
},
{
"epoch": 0.51,
"learning_rate": 4.989343150552219e-05,
"loss": 0.3981,
"step": 585
},
{
"epoch": 0.51,
"learning_rate": 4.984499128075954e-05,
"loss": 0.4092,
"step": 590
},
{
"epoch": 0.52,
"learning_rate": 4.9796551055996904e-05,
"loss": 0.3796,
"step": 595
},
{
"epoch": 0.52,
"learning_rate": 4.974811083123426e-05,
"loss": 0.4506,
"step": 600
},
{
"epoch": 0.53,
"learning_rate": 4.969967060647162e-05,
"loss": 0.3155,
"step": 605
},
{
"epoch": 0.53,
"learning_rate": 4.965123038170897e-05,
"loss": 0.4018,
"step": 610
},
{
"epoch": 0.54,
"learning_rate": 4.960279015694633e-05,
"loss": 0.4199,
"step": 615
},
{
"epoch": 0.54,
"learning_rate": 4.955434993218369e-05,
"loss": 0.3539,
"step": 620
},
{
"epoch": 0.54,
"learning_rate": 4.950590970742104e-05,
"loss": 0.358,
"step": 625
},
{
"epoch": 0.55,
"learning_rate": 4.94574694826584e-05,
"loss": 0.3451,
"step": 630
},
{
"epoch": 0.55,
"learning_rate": 4.940902925789576e-05,
"loss": 0.4245,
"step": 635
},
{
"epoch": 0.56,
"learning_rate": 4.9360589033133116e-05,
"loss": 0.4185,
"step": 640
},
{
"epoch": 0.56,
"learning_rate": 4.931214880837047e-05,
"loss": 0.4084,
"step": 645
},
{
"epoch": 0.57,
"learning_rate": 4.926370858360783e-05,
"loss": 0.3606,
"step": 650
},
{
"epoch": 0.57,
"learning_rate": 4.921526835884519e-05,
"loss": 0.3947,
"step": 655
},
{
"epoch": 0.58,
"learning_rate": 4.9166828134082546e-05,
"loss": 0.4114,
"step": 660
},
{
"epoch": 0.58,
"learning_rate": 4.91183879093199e-05,
"loss": 0.4064,
"step": 665
},
{
"epoch": 0.58,
"learning_rate": 4.906994768455726e-05,
"loss": 0.306,
"step": 670
},
{
"epoch": 0.59,
"learning_rate": 4.9021507459794614e-05,
"loss": 0.3528,
"step": 675
},
{
"epoch": 0.59,
"learning_rate": 4.8973067235031975e-05,
"loss": 0.3498,
"step": 680
},
{
"epoch": 0.6,
"learning_rate": 4.892462701026933e-05,
"loss": 0.3181,
"step": 685
},
{
"epoch": 0.6,
"learning_rate": 4.887618678550669e-05,
"loss": 0.3641,
"step": 690
},
{
"epoch": 0.61,
"learning_rate": 4.8827746560744043e-05,
"loss": 0.3407,
"step": 695
},
{
"epoch": 0.61,
"learning_rate": 4.87793063359814e-05,
"loss": 0.386,
"step": 700
},
{
"epoch": 0.61,
"learning_rate": 4.873086611121876e-05,
"loss": 0.3508,
"step": 705
},
{
"epoch": 0.62,
"learning_rate": 4.868242588645612e-05,
"loss": 0.3948,
"step": 710
},
{
"epoch": 0.62,
"learning_rate": 4.863398566169347e-05,
"loss": 0.4081,
"step": 715
},
{
"epoch": 0.63,
"learning_rate": 4.858554543693083e-05,
"loss": 0.3175,
"step": 720
},
{
"epoch": 0.63,
"learning_rate": 4.853710521216819e-05,
"loss": 0.3874,
"step": 725
},
{
"epoch": 0.64,
"learning_rate": 4.848866498740555e-05,
"loss": 0.3429,
"step": 730
},
{
"epoch": 0.64,
"learning_rate": 4.84402247626429e-05,
"loss": 0.3081,
"step": 735
},
{
"epoch": 0.64,
"learning_rate": 4.8391784537880256e-05,
"loss": 0.4345,
"step": 740
},
{
"epoch": 0.65,
"learning_rate": 4.834334431311762e-05,
"loss": 0.3485,
"step": 745
},
{
"epoch": 0.65,
"learning_rate": 4.829490408835497e-05,
"loss": 0.3776,
"step": 750
},
{
"epoch": 0.66,
"learning_rate": 4.824646386359233e-05,
"loss": 0.3567,
"step": 755
},
{
"epoch": 0.66,
"learning_rate": 4.8198023638829685e-05,
"loss": 0.3871,
"step": 760
},
{
"epoch": 0.67,
"learning_rate": 4.8149583414067046e-05,
"loss": 0.4222,
"step": 765
},
{
"epoch": 0.67,
"learning_rate": 4.81011431893044e-05,
"loss": 0.3306,
"step": 770
},
{
"epoch": 0.68,
"learning_rate": 4.8052702964541754e-05,
"loss": 0.3361,
"step": 775
},
{
"epoch": 0.68,
"learning_rate": 4.8004262739779115e-05,
"loss": 0.3324,
"step": 780
},
{
"epoch": 0.68,
"learning_rate": 4.7955822515016475e-05,
"loss": 0.3567,
"step": 785
},
{
"epoch": 0.69,
"learning_rate": 4.790738229025383e-05,
"loss": 0.3536,
"step": 790
},
{
"epoch": 0.69,
"learning_rate": 4.785894206549118e-05,
"loss": 0.3765,
"step": 795
},
{
"epoch": 0.7,
"learning_rate": 4.7810501840728544e-05,
"loss": 0.281,
"step": 800
},
{
"epoch": 0.7,
"learning_rate": 4.7762061615965905e-05,
"loss": 0.4237,
"step": 805
},
{
"epoch": 0.71,
"learning_rate": 4.771362139120326e-05,
"loss": 0.2897,
"step": 810
},
{
"epoch": 0.71,
"learning_rate": 4.766518116644061e-05,
"loss": 0.3523,
"step": 815
},
{
"epoch": 0.71,
"learning_rate": 4.761674094167797e-05,
"loss": 0.3451,
"step": 820
},
{
"epoch": 0.72,
"learning_rate": 4.756830071691533e-05,
"loss": 0.3097,
"step": 825
},
{
"epoch": 0.72,
"learning_rate": 4.751986049215269e-05,
"loss": 0.3108,
"step": 830
},
{
"epoch": 0.73,
"learning_rate": 4.747142026739004e-05,
"loss": 0.3163,
"step": 835
},
{
"epoch": 0.73,
"learning_rate": 4.74229800426274e-05,
"loss": 0.3837,
"step": 840
},
{
"epoch": 0.74,
"learning_rate": 4.7374539817864756e-05,
"loss": 0.3176,
"step": 845
},
{
"epoch": 0.74,
"learning_rate": 4.732609959310211e-05,
"loss": 0.2989,
"step": 850
},
{
"epoch": 0.74,
"learning_rate": 4.727765936833947e-05,
"loss": 0.3573,
"step": 855
},
{
"epoch": 0.75,
"learning_rate": 4.722921914357683e-05,
"loss": 0.3808,
"step": 860
},
{
"epoch": 0.75,
"learning_rate": 4.7180778918814186e-05,
"loss": 0.3437,
"step": 865
},
{
"epoch": 0.76,
"learning_rate": 4.713233869405154e-05,
"loss": 0.29,
"step": 870
},
{
"epoch": 0.76,
"learning_rate": 4.70838984692889e-05,
"loss": 0.373,
"step": 875
},
{
"epoch": 0.77,
"learning_rate": 4.703545824452626e-05,
"loss": 0.3563,
"step": 880
},
{
"epoch": 0.77,
"learning_rate": 4.6987018019763615e-05,
"loss": 0.3566,
"step": 885
},
{
"epoch": 0.78,
"learning_rate": 4.693857779500097e-05,
"loss": 0.3402,
"step": 890
},
{
"epoch": 0.78,
"learning_rate": 4.689013757023833e-05,
"loss": 0.3522,
"step": 895
},
{
"epoch": 0.78,
"learning_rate": 4.684169734547569e-05,
"loss": 0.2922,
"step": 900
},
{
"epoch": 0.79,
"learning_rate": 4.6793257120713044e-05,
"loss": 0.3906,
"step": 905
},
{
"epoch": 0.79,
"learning_rate": 4.67448168959504e-05,
"loss": 0.2914,
"step": 910
},
{
"epoch": 0.8,
"learning_rate": 4.669637667118776e-05,
"loss": 0.3724,
"step": 915
},
{
"epoch": 0.8,
"learning_rate": 4.664793644642511e-05,
"loss": 0.3726,
"step": 920
},
{
"epoch": 0.81,
"learning_rate": 4.659949622166247e-05,
"loss": 0.3667,
"step": 925
},
{
"epoch": 0.81,
"learning_rate": 4.655105599689983e-05,
"loss": 0.3482,
"step": 930
},
{
"epoch": 0.81,
"learning_rate": 4.650261577213719e-05,
"loss": 0.3391,
"step": 935
},
{
"epoch": 0.82,
"learning_rate": 4.645417554737454e-05,
"loss": 0.3725,
"step": 940
},
{
"epoch": 0.82,
"learning_rate": 4.6405735322611896e-05,
"loss": 0.3568,
"step": 945
},
{
"epoch": 0.83,
"learning_rate": 4.635729509784926e-05,
"loss": 0.3503,
"step": 950
},
{
"epoch": 0.83,
"learning_rate": 4.630885487308662e-05,
"loss": 0.3252,
"step": 955
},
{
"epoch": 0.84,
"learning_rate": 4.626041464832397e-05,
"loss": 0.3632,
"step": 960
},
{
"epoch": 0.84,
"learning_rate": 4.6211974423561325e-05,
"loss": 0.4087,
"step": 965
},
{
"epoch": 0.85,
"learning_rate": 4.6163534198798686e-05,
"loss": 0.3375,
"step": 970
},
{
"epoch": 0.85,
"learning_rate": 4.611509397403605e-05,
"loss": 0.2587,
"step": 975
},
{
"epoch": 0.85,
"learning_rate": 4.60666537492734e-05,
"loss": 0.3476,
"step": 980
},
{
"epoch": 0.86,
"learning_rate": 4.6018213524510755e-05,
"loss": 0.355,
"step": 985
},
{
"epoch": 0.86,
"learning_rate": 4.5969773299748115e-05,
"loss": 0.3461,
"step": 990
},
{
"epoch": 0.87,
"learning_rate": 4.592133307498547e-05,
"loss": 0.3245,
"step": 995
},
{
"epoch": 0.87,
"learning_rate": 4.587289285022282e-05,
"loss": 0.3733,
"step": 1000
},
{
"epoch": 0.88,
"learning_rate": 4.5824452625460184e-05,
"loss": 0.3524,
"step": 1005
},
{
"epoch": 0.88,
"learning_rate": 4.5776012400697545e-05,
"loss": 0.39,
"step": 1010
},
{
"epoch": 0.88,
"learning_rate": 4.57275721759349e-05,
"loss": 0.3003,
"step": 1015
},
{
"epoch": 0.89,
"learning_rate": 4.567913195117225e-05,
"loss": 0.3461,
"step": 1020
},
{
"epoch": 0.89,
"learning_rate": 4.563069172640961e-05,
"loss": 0.3557,
"step": 1025
},
{
"epoch": 0.9,
"learning_rate": 4.5582251501646974e-05,
"loss": 0.3439,
"step": 1030
},
{
"epoch": 0.9,
"learning_rate": 4.553381127688433e-05,
"loss": 0.3439,
"step": 1035
},
{
"epoch": 0.91,
"learning_rate": 4.548537105212168e-05,
"loss": 0.368,
"step": 1040
},
{
"epoch": 0.91,
"learning_rate": 4.543693082735904e-05,
"loss": 0.3529,
"step": 1045
},
{
"epoch": 0.91,
"learning_rate": 4.53884906025964e-05,
"loss": 0.3132,
"step": 1050
},
{
"epoch": 0.92,
"learning_rate": 4.534005037783376e-05,
"loss": 0.3995,
"step": 1055
},
{
"epoch": 0.92,
"learning_rate": 4.529161015307111e-05,
"loss": 0.3206,
"step": 1060
},
{
"epoch": 0.93,
"learning_rate": 4.524316992830847e-05,
"loss": 0.3235,
"step": 1065
},
{
"epoch": 0.93,
"learning_rate": 4.5194729703545826e-05,
"loss": 0.295,
"step": 1070
},
{
"epoch": 0.94,
"learning_rate": 4.514628947878318e-05,
"loss": 0.32,
"step": 1075
},
{
"epoch": 0.94,
"learning_rate": 4.509784925402054e-05,
"loss": 0.3585,
"step": 1080
},
{
"epoch": 0.95,
"learning_rate": 4.50494090292579e-05,
"loss": 0.3468,
"step": 1085
},
{
"epoch": 0.95,
"learning_rate": 4.5000968804495255e-05,
"loss": 0.2956,
"step": 1090
},
{
"epoch": 0.95,
"learning_rate": 4.495252857973261e-05,
"loss": 0.3009,
"step": 1095
},
{
"epoch": 0.96,
"learning_rate": 4.490408835496997e-05,
"loss": 0.2903,
"step": 1100
},
{
"epoch": 0.96,
"learning_rate": 4.485564813020733e-05,
"loss": 0.3052,
"step": 1105
},
{
"epoch": 0.97,
"learning_rate": 4.4807207905444684e-05,
"loss": 0.3248,
"step": 1110
},
{
"epoch": 0.97,
"learning_rate": 4.475876768068204e-05,
"loss": 0.3175,
"step": 1115
},
{
"epoch": 0.98,
"learning_rate": 4.47103274559194e-05,
"loss": 0.3432,
"step": 1120
},
{
"epoch": 0.98,
"learning_rate": 4.466188723115676e-05,
"loss": 0.3474,
"step": 1125
},
{
"epoch": 0.98,
"learning_rate": 4.461344700639411e-05,
"loss": 0.2994,
"step": 1130
},
{
"epoch": 0.99,
"learning_rate": 4.456500678163147e-05,
"loss": 0.3588,
"step": 1135
},
{
"epoch": 0.99,
"learning_rate": 4.451656655686883e-05,
"loss": 0.2992,
"step": 1140
},
{
"epoch": 1.0,
"learning_rate": 4.446812633210619e-05,
"loss": 0.3471,
"step": 1145
},
{
"epoch": 1.0,
"eval_accuracy": 0.9215169709594413,
"eval_loss": 0.23573137819766998,
"eval_runtime": 35.5735,
"eval_samples_per_second": 458.824,
"eval_steps_per_second": 14.365,
"step": 1147
},
{
"epoch": 1.0,
"learning_rate": 4.4419686107343536e-05,
"loss": 0.3217,
"step": 1150
},
{
"epoch": 1.01,
"learning_rate": 4.43712458825809e-05,
"loss": 0.3659,
"step": 1155
},
{
"epoch": 1.01,
"learning_rate": 4.432280565781826e-05,
"loss": 0.3182,
"step": 1160
},
{
"epoch": 1.02,
"learning_rate": 4.427436543305561e-05,
"loss": 0.3008,
"step": 1165
},
{
"epoch": 1.02,
"learning_rate": 4.4225925208292965e-05,
"loss": 0.3799,
"step": 1170
},
{
"epoch": 1.02,
"learning_rate": 4.4177484983530326e-05,
"loss": 0.2918,
"step": 1175
},
{
"epoch": 1.03,
"learning_rate": 4.412904475876769e-05,
"loss": 0.3586,
"step": 1180
},
{
"epoch": 1.03,
"learning_rate": 4.408060453400504e-05,
"loss": 0.3247,
"step": 1185
},
{
"epoch": 1.04,
"learning_rate": 4.4032164309242395e-05,
"loss": 0.3698,
"step": 1190
},
{
"epoch": 1.04,
"learning_rate": 4.3983724084479755e-05,
"loss": 0.2486,
"step": 1195
},
{
"epoch": 1.05,
"learning_rate": 4.3935283859717116e-05,
"loss": 0.3384,
"step": 1200
},
{
"epoch": 1.05,
"learning_rate": 4.388684363495446e-05,
"loss": 0.3103,
"step": 1205
},
{
"epoch": 1.05,
"learning_rate": 4.3838403410191824e-05,
"loss": 0.3102,
"step": 1210
},
{
"epoch": 1.06,
"learning_rate": 4.3789963185429185e-05,
"loss": 0.2874,
"step": 1215
},
{
"epoch": 1.06,
"learning_rate": 4.3741522960666545e-05,
"loss": 0.3117,
"step": 1220
},
{
"epoch": 1.07,
"learning_rate": 4.369308273590389e-05,
"loss": 0.29,
"step": 1225
},
{
"epoch": 1.07,
"learning_rate": 4.364464251114125e-05,
"loss": 0.3126,
"step": 1230
},
{
"epoch": 1.08,
"learning_rate": 4.3596202286378614e-05,
"loss": 0.3032,
"step": 1235
},
{
"epoch": 1.08,
"learning_rate": 4.354776206161597e-05,
"loss": 0.2815,
"step": 1240
},
{
"epoch": 1.08,
"learning_rate": 4.349932183685332e-05,
"loss": 0.3402,
"step": 1245
},
{
"epoch": 1.09,
"learning_rate": 4.345088161209068e-05,
"loss": 0.3124,
"step": 1250
},
{
"epoch": 1.09,
"learning_rate": 4.340244138732804e-05,
"loss": 0.3668,
"step": 1255
},
{
"epoch": 1.1,
"learning_rate": 4.33540011625654e-05,
"loss": 0.3733,
"step": 1260
},
{
"epoch": 1.1,
"learning_rate": 4.330556093780275e-05,
"loss": 0.2975,
"step": 1265
},
{
"epoch": 1.11,
"learning_rate": 4.325712071304011e-05,
"loss": 0.2937,
"step": 1270
},
{
"epoch": 1.11,
"learning_rate": 4.320868048827747e-05,
"loss": 0.3099,
"step": 1275
},
{
"epoch": 1.12,
"learning_rate": 4.316024026351482e-05,
"loss": 0.2724,
"step": 1280
},
{
"epoch": 1.12,
"learning_rate": 4.311180003875218e-05,
"loss": 0.3753,
"step": 1285
},
{
"epoch": 1.12,
"learning_rate": 4.306335981398954e-05,
"loss": 0.2749,
"step": 1290
},
{
"epoch": 1.13,
"learning_rate": 4.30149195892269e-05,
"loss": 0.3306,
"step": 1295
},
{
"epoch": 1.13,
"learning_rate": 4.296647936446425e-05,
"loss": 0.3296,
"step": 1300
},
{
"epoch": 1.14,
"learning_rate": 4.291803913970161e-05,
"loss": 0.3038,
"step": 1305
},
{
"epoch": 1.14,
"learning_rate": 4.286959891493897e-05,
"loss": 0.3409,
"step": 1310
},
{
"epoch": 1.15,
"learning_rate": 4.2821158690176324e-05,
"loss": 0.3078,
"step": 1315
},
{
"epoch": 1.15,
"learning_rate": 4.277271846541368e-05,
"loss": 0.3256,
"step": 1320
},
{
"epoch": 1.15,
"learning_rate": 4.272427824065104e-05,
"loss": 0.3472,
"step": 1325
},
{
"epoch": 1.16,
"learning_rate": 4.26758380158884e-05,
"loss": 0.2428,
"step": 1330
},
{
"epoch": 1.16,
"learning_rate": 4.2627397791125754e-05,
"loss": 0.2921,
"step": 1335
},
{
"epoch": 1.17,
"learning_rate": 4.257895756636311e-05,
"loss": 0.2891,
"step": 1340
},
{
"epoch": 1.17,
"learning_rate": 4.253051734160047e-05,
"loss": 0.324,
"step": 1345
},
{
"epoch": 1.18,
"learning_rate": 4.248207711683783e-05,
"loss": 0.3255,
"step": 1350
},
{
"epoch": 1.18,
"learning_rate": 4.2433636892075176e-05,
"loss": 0.3342,
"step": 1355
},
{
"epoch": 1.18,
"learning_rate": 4.238519666731254e-05,
"loss": 0.3427,
"step": 1360
},
{
"epoch": 1.19,
"learning_rate": 4.23367564425499e-05,
"loss": 0.3312,
"step": 1365
},
{
"epoch": 1.19,
"learning_rate": 4.228831621778726e-05,
"loss": 0.3428,
"step": 1370
},
{
"epoch": 1.2,
"learning_rate": 4.2239875993024605e-05,
"loss": 0.2858,
"step": 1375
},
{
"epoch": 1.2,
"learning_rate": 4.2191435768261966e-05,
"loss": 0.3091,
"step": 1380
},
{
"epoch": 1.21,
"learning_rate": 4.214299554349933e-05,
"loss": 0.3313,
"step": 1385
},
{
"epoch": 1.21,
"learning_rate": 4.209455531873668e-05,
"loss": 0.2886,
"step": 1390
},
{
"epoch": 1.22,
"learning_rate": 4.2046115093974035e-05,
"loss": 0.3379,
"step": 1395
},
{
"epoch": 1.22,
"learning_rate": 4.1997674869211395e-05,
"loss": 0.3373,
"step": 1400
},
{
"epoch": 1.22,
"learning_rate": 4.1949234644448756e-05,
"loss": 0.3359,
"step": 1405
},
{
"epoch": 1.23,
"learning_rate": 4.190079441968611e-05,
"loss": 0.232,
"step": 1410
},
{
"epoch": 1.23,
"learning_rate": 4.1852354194923464e-05,
"loss": 0.3492,
"step": 1415
},
{
"epoch": 1.24,
"learning_rate": 4.1803913970160825e-05,
"loss": 0.2808,
"step": 1420
},
{
"epoch": 1.24,
"learning_rate": 4.1755473745398185e-05,
"loss": 0.2837,
"step": 1425
},
{
"epoch": 1.25,
"learning_rate": 4.170703352063553e-05,
"loss": 0.307,
"step": 1430
},
{
"epoch": 1.25,
"learning_rate": 4.165859329587289e-05,
"loss": 0.3164,
"step": 1435
},
{
"epoch": 1.25,
"learning_rate": 4.1610153071110254e-05,
"loss": 0.3468,
"step": 1440
},
{
"epoch": 1.26,
"learning_rate": 4.1561712846347615e-05,
"loss": 0.3014,
"step": 1445
},
{
"epoch": 1.26,
"learning_rate": 4.151327262158496e-05,
"loss": 0.2759,
"step": 1450
},
{
"epoch": 1.27,
"learning_rate": 4.146483239682232e-05,
"loss": 0.3596,
"step": 1455
},
{
"epoch": 1.27,
"learning_rate": 4.141639217205968e-05,
"loss": 0.3454,
"step": 1460
},
{
"epoch": 1.28,
"learning_rate": 4.136795194729704e-05,
"loss": 0.3659,
"step": 1465
},
{
"epoch": 1.28,
"learning_rate": 4.131951172253439e-05,
"loss": 0.3166,
"step": 1470
},
{
"epoch": 1.29,
"learning_rate": 4.127107149777175e-05,
"loss": 0.2987,
"step": 1475
},
{
"epoch": 1.29,
"learning_rate": 4.122263127300911e-05,
"loss": 0.3051,
"step": 1480
},
{
"epoch": 1.29,
"learning_rate": 4.1174191048246466e-05,
"loss": 0.3011,
"step": 1485
},
{
"epoch": 1.3,
"learning_rate": 4.112575082348382e-05,
"loss": 0.3414,
"step": 1490
},
{
"epoch": 1.3,
"learning_rate": 4.107731059872118e-05,
"loss": 0.3404,
"step": 1495
},
{
"epoch": 1.31,
"learning_rate": 4.102887037395854e-05,
"loss": 0.3364,
"step": 1500
},
{
"epoch": 1.31,
"learning_rate": 4.098043014919589e-05,
"loss": 0.2577,
"step": 1505
},
{
"epoch": 1.32,
"learning_rate": 4.093198992443325e-05,
"loss": 0.3557,
"step": 1510
},
{
"epoch": 1.32,
"learning_rate": 4.088354969967061e-05,
"loss": 0.3152,
"step": 1515
},
{
"epoch": 1.32,
"learning_rate": 4.083510947490797e-05,
"loss": 0.3028,
"step": 1520
},
{
"epoch": 1.33,
"learning_rate": 4.078666925014532e-05,
"loss": 0.2979,
"step": 1525
},
{
"epoch": 1.33,
"learning_rate": 4.073822902538268e-05,
"loss": 0.3361,
"step": 1530
},
{
"epoch": 1.34,
"learning_rate": 4.068978880062004e-05,
"loss": 0.3056,
"step": 1535
},
{
"epoch": 1.34,
"learning_rate": 4.0641348575857394e-05,
"loss": 0.2803,
"step": 1540
},
{
"epoch": 1.35,
"learning_rate": 4.059290835109475e-05,
"loss": 0.3051,
"step": 1545
},
{
"epoch": 1.35,
"learning_rate": 4.054446812633211e-05,
"loss": 0.2973,
"step": 1550
},
{
"epoch": 1.35,
"learning_rate": 4.049602790156947e-05,
"loss": 0.2844,
"step": 1555
},
{
"epoch": 1.36,
"learning_rate": 4.044758767680682e-05,
"loss": 0.302,
"step": 1560
},
{
"epoch": 1.36,
"learning_rate": 4.039914745204418e-05,
"loss": 0.2609,
"step": 1565
},
{
"epoch": 1.37,
"learning_rate": 4.035070722728154e-05,
"loss": 0.3128,
"step": 1570
},
{
"epoch": 1.37,
"learning_rate": 4.03022670025189e-05,
"loss": 0.3432,
"step": 1575
},
{
"epoch": 1.38,
"learning_rate": 4.0253826777756245e-05,
"loss": 0.269,
"step": 1580
},
{
"epoch": 1.38,
"learning_rate": 4.0205386552993606e-05,
"loss": 0.3291,
"step": 1585
},
{
"epoch": 1.39,
"learning_rate": 4.015694632823097e-05,
"loss": 0.3288,
"step": 1590
},
{
"epoch": 1.39,
"learning_rate": 4.010850610346832e-05,
"loss": 0.3705,
"step": 1595
},
{
"epoch": 1.39,
"learning_rate": 4.0060065878705675e-05,
"loss": 0.3727,
"step": 1600
},
{
"epoch": 1.4,
"learning_rate": 4.0011625653943035e-05,
"loss": 0.3162,
"step": 1605
},
{
"epoch": 1.4,
"learning_rate": 3.9963185429180396e-05,
"loss": 0.3219,
"step": 1610
},
{
"epoch": 1.41,
"learning_rate": 3.991474520441775e-05,
"loss": 0.2474,
"step": 1615
},
{
"epoch": 1.41,
"learning_rate": 3.9866304979655104e-05,
"loss": 0.2695,
"step": 1620
},
{
"epoch": 1.42,
"learning_rate": 3.9817864754892465e-05,
"loss": 0.3315,
"step": 1625
},
{
"epoch": 1.42,
"learning_rate": 3.9769424530129825e-05,
"loss": 0.3264,
"step": 1630
},
{
"epoch": 1.42,
"learning_rate": 3.972098430536718e-05,
"loss": 0.3045,
"step": 1635
},
{
"epoch": 1.43,
"learning_rate": 3.967254408060453e-05,
"loss": 0.3371,
"step": 1640
},
{
"epoch": 1.43,
"learning_rate": 3.9624103855841894e-05,
"loss": 0.2753,
"step": 1645
},
{
"epoch": 1.44,
"learning_rate": 3.9575663631079255e-05,
"loss": 0.2673,
"step": 1650
},
{
"epoch": 1.44,
"learning_rate": 3.95272234063166e-05,
"loss": 0.3277,
"step": 1655
},
{
"epoch": 1.45,
"learning_rate": 3.947878318155396e-05,
"loss": 0.2356,
"step": 1660
},
{
"epoch": 1.45,
"learning_rate": 3.943034295679132e-05,
"loss": 0.3103,
"step": 1665
},
{
"epoch": 1.46,
"learning_rate": 3.938190273202868e-05,
"loss": 0.3692,
"step": 1670
},
{
"epoch": 1.46,
"learning_rate": 3.933346250726603e-05,
"loss": 0.3367,
"step": 1675
},
{
"epoch": 1.46,
"learning_rate": 3.928502228250339e-05,
"loss": 0.3329,
"step": 1680
},
{
"epoch": 1.47,
"learning_rate": 3.923658205774075e-05,
"loss": 0.3214,
"step": 1685
},
{
"epoch": 1.47,
"learning_rate": 3.9188141832978106e-05,
"loss": 0.3232,
"step": 1690
},
{
"epoch": 1.48,
"learning_rate": 3.913970160821546e-05,
"loss": 0.255,
"step": 1695
},
{
"epoch": 1.48,
"learning_rate": 3.909126138345282e-05,
"loss": 0.2979,
"step": 1700
},
{
"epoch": 1.49,
"learning_rate": 3.904282115869018e-05,
"loss": 0.3084,
"step": 1705
},
{
"epoch": 1.49,
"learning_rate": 3.8994380933927536e-05,
"loss": 0.282,
"step": 1710
},
{
"epoch": 1.49,
"learning_rate": 3.894594070916489e-05,
"loss": 0.3428,
"step": 1715
},
{
"epoch": 1.5,
"learning_rate": 3.889750048440225e-05,
"loss": 0.2828,
"step": 1720
},
{
"epoch": 1.5,
"learning_rate": 3.884906025963961e-05,
"loss": 0.3064,
"step": 1725
},
{
"epoch": 1.51,
"learning_rate": 3.880062003487696e-05,
"loss": 0.3072,
"step": 1730
},
{
"epoch": 1.51,
"learning_rate": 3.875217981011432e-05,
"loss": 0.2837,
"step": 1735
},
{
"epoch": 1.52,
"learning_rate": 3.870373958535168e-05,
"loss": 0.326,
"step": 1740
},
{
"epoch": 1.52,
"learning_rate": 3.8655299360589034e-05,
"loss": 0.2989,
"step": 1745
},
{
"epoch": 1.52,
"learning_rate": 3.860685913582639e-05,
"loss": 0.2909,
"step": 1750
},
{
"epoch": 1.53,
"learning_rate": 3.855841891106375e-05,
"loss": 0.3057,
"step": 1755
},
{
"epoch": 1.53,
"learning_rate": 3.850997868630111e-05,
"loss": 0.3385,
"step": 1760
},
{
"epoch": 1.54,
"learning_rate": 3.846153846153846e-05,
"loss": 0.3401,
"step": 1765
},
{
"epoch": 1.54,
"learning_rate": 3.841309823677582e-05,
"loss": 0.371,
"step": 1770
},
{
"epoch": 1.55,
"learning_rate": 3.836465801201318e-05,
"loss": 0.3236,
"step": 1775
},
{
"epoch": 1.55,
"learning_rate": 3.831621778725054e-05,
"loss": 0.3186,
"step": 1780
},
{
"epoch": 1.56,
"learning_rate": 3.826777756248789e-05,
"loss": 0.3311,
"step": 1785
},
{
"epoch": 1.56,
"learning_rate": 3.8219337337725246e-05,
"loss": 0.2933,
"step": 1790
},
{
"epoch": 1.56,
"learning_rate": 3.817089711296261e-05,
"loss": 0.2791,
"step": 1795
},
{
"epoch": 1.57,
"learning_rate": 3.812245688819997e-05,
"loss": 0.3214,
"step": 1800
},
{
"epoch": 1.57,
"learning_rate": 3.8074016663437315e-05,
"loss": 0.3202,
"step": 1805
},
{
"epoch": 1.58,
"learning_rate": 3.8025576438674675e-05,
"loss": 0.3369,
"step": 1810
},
{
"epoch": 1.58,
"learning_rate": 3.7977136213912036e-05,
"loss": 0.3665,
"step": 1815
},
{
"epoch": 1.59,
"learning_rate": 3.792869598914939e-05,
"loss": 0.3038,
"step": 1820
},
{
"epoch": 1.59,
"learning_rate": 3.7880255764386744e-05,
"loss": 0.2905,
"step": 1825
},
{
"epoch": 1.59,
"learning_rate": 3.7831815539624105e-05,
"loss": 0.2688,
"step": 1830
},
{
"epoch": 1.6,
"learning_rate": 3.7783375314861465e-05,
"loss": 0.262,
"step": 1835
},
{
"epoch": 1.6,
"learning_rate": 3.773493509009882e-05,
"loss": 0.3512,
"step": 1840
},
{
"epoch": 1.61,
"learning_rate": 3.768649486533617e-05,
"loss": 0.2879,
"step": 1845
},
{
"epoch": 1.61,
"learning_rate": 3.7638054640573534e-05,
"loss": 0.2945,
"step": 1850
},
{
"epoch": 1.62,
"learning_rate": 3.7589614415810895e-05,
"loss": 0.3293,
"step": 1855
},
{
"epoch": 1.62,
"learning_rate": 3.754117419104825e-05,
"loss": 0.224,
"step": 1860
},
{
"epoch": 1.62,
"learning_rate": 3.74927339662856e-05,
"loss": 0.2565,
"step": 1865
},
{
"epoch": 1.63,
"learning_rate": 3.744429374152296e-05,
"loss": 0.2875,
"step": 1870
},
{
"epoch": 1.63,
"learning_rate": 3.7395853516760324e-05,
"loss": 0.3145,
"step": 1875
},
{
"epoch": 1.64,
"learning_rate": 3.734741329199768e-05,
"loss": 0.3431,
"step": 1880
},
{
"epoch": 1.64,
"learning_rate": 3.729897306723503e-05,
"loss": 0.3306,
"step": 1885
},
{
"epoch": 1.65,
"learning_rate": 3.725053284247239e-05,
"loss": 0.2567,
"step": 1890
},
{
"epoch": 1.65,
"learning_rate": 3.7202092617709746e-05,
"loss": 0.3239,
"step": 1895
},
{
"epoch": 1.66,
"learning_rate": 3.71536523929471e-05,
"loss": 0.2713,
"step": 1900
},
{
"epoch": 1.66,
"learning_rate": 3.710521216818446e-05,
"loss": 0.3105,
"step": 1905
},
{
"epoch": 1.66,
"learning_rate": 3.705677194342182e-05,
"loss": 0.2917,
"step": 1910
},
{
"epoch": 1.67,
"learning_rate": 3.7008331718659176e-05,
"loss": 0.3088,
"step": 1915
},
{
"epoch": 1.67,
"learning_rate": 3.695989149389653e-05,
"loss": 0.3254,
"step": 1920
},
{
"epoch": 1.68,
"learning_rate": 3.691145126913389e-05,
"loss": 0.2573,
"step": 1925
},
{
"epoch": 1.68,
"learning_rate": 3.686301104437125e-05,
"loss": 0.3028,
"step": 1930
},
{
"epoch": 1.69,
"learning_rate": 3.6814570819608605e-05,
"loss": 0.3148,
"step": 1935
},
{
"epoch": 1.69,
"learning_rate": 3.676613059484596e-05,
"loss": 0.2852,
"step": 1940
},
{
"epoch": 1.69,
"learning_rate": 3.671769037008332e-05,
"loss": 0.2979,
"step": 1945
},
{
"epoch": 1.7,
"learning_rate": 3.666925014532068e-05,
"loss": 0.2761,
"step": 1950
},
{
"epoch": 1.7,
"learning_rate": 3.6620809920558034e-05,
"loss": 0.2881,
"step": 1955
},
{
"epoch": 1.71,
"learning_rate": 3.657236969579539e-05,
"loss": 0.3342,
"step": 1960
},
{
"epoch": 1.71,
"learning_rate": 3.652392947103275e-05,
"loss": 0.3224,
"step": 1965
},
{
"epoch": 1.72,
"learning_rate": 3.64754892462701e-05,
"loss": 0.29,
"step": 1970
},
{
"epoch": 1.72,
"learning_rate": 3.642704902150746e-05,
"loss": 0.2791,
"step": 1975
},
{
"epoch": 1.73,
"learning_rate": 3.637860879674482e-05,
"loss": 0.2787,
"step": 1980
},
{
"epoch": 1.73,
"learning_rate": 3.633016857198218e-05,
"loss": 0.2408,
"step": 1985
},
{
"epoch": 1.73,
"learning_rate": 3.628172834721953e-05,
"loss": 0.3416,
"step": 1990
},
{
"epoch": 1.74,
"learning_rate": 3.6233288122456886e-05,
"loss": 0.2535,
"step": 1995
},
{
"epoch": 1.74,
"learning_rate": 3.618484789769425e-05,
"loss": 0.2952,
"step": 2000
},
{
"epoch": 1.75,
"learning_rate": 3.613640767293161e-05,
"loss": 0.276,
"step": 2005
},
{
"epoch": 1.75,
"learning_rate": 3.608796744816896e-05,
"loss": 0.3297,
"step": 2010
},
{
"epoch": 1.76,
"learning_rate": 3.6039527223406315e-05,
"loss": 0.2697,
"step": 2015
},
{
"epoch": 1.76,
"learning_rate": 3.5991086998643676e-05,
"loss": 0.2842,
"step": 2020
},
{
"epoch": 1.76,
"learning_rate": 3.594264677388104e-05,
"loss": 0.2624,
"step": 2025
},
{
"epoch": 1.77,
"learning_rate": 3.589420654911839e-05,
"loss": 0.2926,
"step": 2030
},
{
"epoch": 1.77,
"learning_rate": 3.5845766324355745e-05,
"loss": 0.256,
"step": 2035
},
{
"epoch": 1.78,
"learning_rate": 3.5797326099593105e-05,
"loss": 0.2721,
"step": 2040
},
{
"epoch": 1.78,
"learning_rate": 3.574888587483046e-05,
"loss": 0.2989,
"step": 2045
},
{
"epoch": 1.79,
"learning_rate": 3.570044565006781e-05,
"loss": 0.3026,
"step": 2050
},
{
"epoch": 1.79,
"learning_rate": 3.5652005425305174e-05,
"loss": 0.3311,
"step": 2055
},
{
"epoch": 1.79,
"learning_rate": 3.5603565200542535e-05,
"loss": 0.2946,
"step": 2060
},
{
"epoch": 1.8,
"learning_rate": 3.555512497577989e-05,
"loss": 0.2862,
"step": 2065
},
{
"epoch": 1.8,
"learning_rate": 3.550668475101724e-05,
"loss": 0.3143,
"step": 2070
},
{
"epoch": 1.81,
"learning_rate": 3.54582445262546e-05,
"loss": 0.2917,
"step": 2075
},
{
"epoch": 1.81,
"learning_rate": 3.5409804301491964e-05,
"loss": 0.2724,
"step": 2080
},
{
"epoch": 1.82,
"learning_rate": 3.536136407672932e-05,
"loss": 0.281,
"step": 2085
},
{
"epoch": 1.82,
"learning_rate": 3.531292385196667e-05,
"loss": 0.281,
"step": 2090
},
{
"epoch": 1.83,
"learning_rate": 3.526448362720403e-05,
"loss": 0.3207,
"step": 2095
},
{
"epoch": 1.83,
"learning_rate": 3.521604340244139e-05,
"loss": 0.285,
"step": 2100
},
{
"epoch": 1.83,
"learning_rate": 3.516760317767875e-05,
"loss": 0.2488,
"step": 2105
},
{
"epoch": 1.84,
"learning_rate": 3.51191629529161e-05,
"loss": 0.2862,
"step": 2110
},
{
"epoch": 1.84,
"learning_rate": 3.507072272815346e-05,
"loss": 0.3185,
"step": 2115
},
{
"epoch": 1.85,
"learning_rate": 3.5022282503390816e-05,
"loss": 0.267,
"step": 2120
},
{
"epoch": 1.85,
"learning_rate": 3.4973842278628176e-05,
"loss": 0.3251,
"step": 2125
},
{
"epoch": 1.86,
"learning_rate": 3.492540205386553e-05,
"loss": 0.3037,
"step": 2130
},
{
"epoch": 1.86,
"learning_rate": 3.487696182910289e-05,
"loss": 0.2641,
"step": 2135
},
{
"epoch": 1.86,
"learning_rate": 3.4828521604340245e-05,
"loss": 0.2865,
"step": 2140
},
{
"epoch": 1.87,
"learning_rate": 3.47800813795776e-05,
"loss": 0.287,
"step": 2145
},
{
"epoch": 1.87,
"learning_rate": 3.473164115481496e-05,
"loss": 0.2995,
"step": 2150
},
{
"epoch": 1.88,
"learning_rate": 3.468320093005232e-05,
"loss": 0.3447,
"step": 2155
},
{
"epoch": 1.88,
"learning_rate": 3.4634760705289674e-05,
"loss": 0.3023,
"step": 2160
},
{
"epoch": 1.89,
"learning_rate": 3.458632048052703e-05,
"loss": 0.2464,
"step": 2165
},
{
"epoch": 1.89,
"learning_rate": 3.453788025576439e-05,
"loss": 0.3194,
"step": 2170
},
{
"epoch": 1.9,
"learning_rate": 3.448944003100174e-05,
"loss": 0.2495,
"step": 2175
},
{
"epoch": 1.9,
"learning_rate": 3.4440999806239104e-05,
"loss": 0.3157,
"step": 2180
},
{
"epoch": 1.9,
"learning_rate": 3.439255958147646e-05,
"loss": 0.3145,
"step": 2185
},
{
"epoch": 1.91,
"learning_rate": 3.434411935671382e-05,
"loss": 0.3024,
"step": 2190
},
{
"epoch": 1.91,
"learning_rate": 3.429567913195117e-05,
"loss": 0.2898,
"step": 2195
},
{
"epoch": 1.92,
"learning_rate": 3.424723890718853e-05,
"loss": 0.3095,
"step": 2200
},
{
"epoch": 1.92,
"learning_rate": 3.419879868242589e-05,
"loss": 0.2975,
"step": 2205
},
{
"epoch": 1.93,
"learning_rate": 3.415035845766325e-05,
"loss": 0.2891,
"step": 2210
},
{
"epoch": 1.93,
"learning_rate": 3.41019182329006e-05,
"loss": 0.3322,
"step": 2215
},
{
"epoch": 1.93,
"learning_rate": 3.4053478008137955e-05,
"loss": 0.3134,
"step": 2220
},
{
"epoch": 1.94,
"learning_rate": 3.4005037783375316e-05,
"loss": 0.3105,
"step": 2225
},
{
"epoch": 1.94,
"learning_rate": 3.395659755861268e-05,
"loss": 0.2925,
"step": 2230
},
{
"epoch": 1.95,
"learning_rate": 3.390815733385003e-05,
"loss": 0.2837,
"step": 2235
},
{
"epoch": 1.95,
"learning_rate": 3.3859717109087385e-05,
"loss": 0.3237,
"step": 2240
},
{
"epoch": 1.96,
"learning_rate": 3.3811276884324745e-05,
"loss": 0.324,
"step": 2245
},
{
"epoch": 1.96,
"learning_rate": 3.37628366595621e-05,
"loss": 0.2523,
"step": 2250
},
{
"epoch": 1.96,
"learning_rate": 3.371439643479946e-05,
"loss": 0.3082,
"step": 2255
},
{
"epoch": 1.97,
"learning_rate": 3.3665956210036814e-05,
"loss": 0.26,
"step": 2260
},
{
"epoch": 1.97,
"learning_rate": 3.3617515985274175e-05,
"loss": 0.2905,
"step": 2265
},
{
"epoch": 1.98,
"learning_rate": 3.356907576051153e-05,
"loss": 0.3016,
"step": 2270
},
{
"epoch": 1.98,
"learning_rate": 3.352063553574889e-05,
"loss": 0.2906,
"step": 2275
},
{
"epoch": 1.99,
"learning_rate": 3.347219531098624e-05,
"loss": 0.3172,
"step": 2280
},
{
"epoch": 1.99,
"learning_rate": 3.3423755086223604e-05,
"loss": 0.2584,
"step": 2285
},
{
"epoch": 2.0,
"learning_rate": 3.337531486146096e-05,
"loss": 0.2902,
"step": 2290
},
{
"epoch": 2.0,
"learning_rate": 3.332687463669831e-05,
"loss": 0.2737,
"step": 2295
},
{
"epoch": 2.0,
"eval_accuracy": 0.9279500061267002,
"eval_loss": 0.21325047314167023,
"eval_runtime": 33.0726,
"eval_samples_per_second": 493.521,
"eval_steps_per_second": 15.451,
"step": 2295
},
{
"epoch": 2.0,
"learning_rate": 3.327843441193567e-05,
"loss": 0.2392,
"step": 2300
},
{
"epoch": 2.01,
"learning_rate": 3.322999418717303e-05,
"loss": 0.2823,
"step": 2305
},
{
"epoch": 2.01,
"learning_rate": 3.318155396241039e-05,
"loss": 0.243,
"step": 2310
},
{
"epoch": 2.02,
"learning_rate": 3.313311373764774e-05,
"loss": 0.2835,
"step": 2315
},
{
"epoch": 2.02,
"learning_rate": 3.30846735128851e-05,
"loss": 0.2637,
"step": 2320
},
{
"epoch": 2.03,
"learning_rate": 3.3036233288122456e-05,
"loss": 0.2774,
"step": 2325
},
{
"epoch": 2.03,
"learning_rate": 3.2987793063359816e-05,
"loss": 0.2641,
"step": 2330
},
{
"epoch": 2.03,
"learning_rate": 3.293935283859717e-05,
"loss": 0.2982,
"step": 2335
},
{
"epoch": 2.04,
"learning_rate": 3.289091261383453e-05,
"loss": 0.2386,
"step": 2340
},
{
"epoch": 2.04,
"learning_rate": 3.2842472389071885e-05,
"loss": 0.2492,
"step": 2345
},
{
"epoch": 2.05,
"learning_rate": 3.2794032164309246e-05,
"loss": 0.3039,
"step": 2350
},
{
"epoch": 2.05,
"learning_rate": 3.27455919395466e-05,
"loss": 0.2867,
"step": 2355
},
{
"epoch": 2.06,
"learning_rate": 3.269715171478396e-05,
"loss": 0.2728,
"step": 2360
},
{
"epoch": 2.06,
"learning_rate": 3.2648711490021314e-05,
"loss": 0.2753,
"step": 2365
},
{
"epoch": 2.06,
"learning_rate": 3.2600271265258675e-05,
"loss": 0.262,
"step": 2370
},
{
"epoch": 2.07,
"learning_rate": 3.255183104049603e-05,
"loss": 0.2956,
"step": 2375
},
{
"epoch": 2.07,
"learning_rate": 3.250339081573339e-05,
"loss": 0.2489,
"step": 2380
},
{
"epoch": 2.08,
"learning_rate": 3.2454950590970744e-05,
"loss": 0.3273,
"step": 2385
},
{
"epoch": 2.08,
"learning_rate": 3.24065103662081e-05,
"loss": 0.2949,
"step": 2390
},
{
"epoch": 2.09,
"learning_rate": 3.235807014144546e-05,
"loss": 0.2864,
"step": 2395
},
{
"epoch": 2.09,
"learning_rate": 3.230962991668281e-05,
"loss": 0.3368,
"step": 2400
},
{
"epoch": 2.1,
"learning_rate": 3.226118969192017e-05,
"loss": 0.2872,
"step": 2405
},
{
"epoch": 2.1,
"learning_rate": 3.221274946715753e-05,
"loss": 0.2777,
"step": 2410
},
{
"epoch": 2.1,
"learning_rate": 3.216430924239489e-05,
"loss": 0.2758,
"step": 2415
},
{
"epoch": 2.11,
"learning_rate": 3.211586901763224e-05,
"loss": 0.312,
"step": 2420
},
{
"epoch": 2.11,
"learning_rate": 3.20674287928696e-05,
"loss": 0.3046,
"step": 2425
},
{
"epoch": 2.12,
"learning_rate": 3.2018988568106956e-05,
"loss": 0.2585,
"step": 2430
},
{
"epoch": 2.12,
"learning_rate": 3.197054834334432e-05,
"loss": 0.2614,
"step": 2435
},
{
"epoch": 2.13,
"learning_rate": 3.192210811858167e-05,
"loss": 0.2884,
"step": 2440
},
{
"epoch": 2.13,
"learning_rate": 3.187366789381903e-05,
"loss": 0.3079,
"step": 2445
},
{
"epoch": 2.13,
"learning_rate": 3.1825227669056385e-05,
"loss": 0.2631,
"step": 2450
},
{
"epoch": 2.14,
"learning_rate": 3.1776787444293746e-05,
"loss": 0.2869,
"step": 2455
},
{
"epoch": 2.14,
"learning_rate": 3.17283472195311e-05,
"loss": 0.287,
"step": 2460
},
{
"epoch": 2.15,
"learning_rate": 3.1679906994768454e-05,
"loss": 0.2367,
"step": 2465
},
{
"epoch": 2.15,
"learning_rate": 3.1631466770005815e-05,
"loss": 0.275,
"step": 2470
},
{
"epoch": 2.16,
"learning_rate": 3.158302654524317e-05,
"loss": 0.2715,
"step": 2475
},
{
"epoch": 2.16,
"learning_rate": 3.153458632048053e-05,
"loss": 0.2347,
"step": 2480
},
{
"epoch": 2.17,
"learning_rate": 3.148614609571788e-05,
"loss": 0.2678,
"step": 2485
},
{
"epoch": 2.17,
"learning_rate": 3.1437705870955244e-05,
"loss": 0.2632,
"step": 2490
},
{
"epoch": 2.17,
"learning_rate": 3.13892656461926e-05,
"loss": 0.2905,
"step": 2495
},
{
"epoch": 2.18,
"learning_rate": 3.134082542142996e-05,
"loss": 0.3163,
"step": 2500
},
{
"epoch": 2.18,
"learning_rate": 3.129238519666731e-05,
"loss": 0.2399,
"step": 2505
},
{
"epoch": 2.19,
"learning_rate": 3.124394497190467e-05,
"loss": 0.2466,
"step": 2510
},
{
"epoch": 2.19,
"learning_rate": 3.119550474714203e-05,
"loss": 0.2397,
"step": 2515
},
{
"epoch": 2.2,
"learning_rate": 3.114706452237939e-05,
"loss": 0.2918,
"step": 2520
},
{
"epoch": 2.2,
"learning_rate": 3.109862429761674e-05,
"loss": 0.2539,
"step": 2525
},
{
"epoch": 2.2,
"learning_rate": 3.10501840728541e-05,
"loss": 0.2748,
"step": 2530
},
{
"epoch": 2.21,
"learning_rate": 3.1001743848091457e-05,
"loss": 0.3029,
"step": 2535
},
{
"epoch": 2.21,
"learning_rate": 3.095330362332882e-05,
"loss": 0.2715,
"step": 2540
},
{
"epoch": 2.22,
"learning_rate": 3.090486339856617e-05,
"loss": 0.3094,
"step": 2545
},
{
"epoch": 2.22,
"learning_rate": 3.0856423173803525e-05,
"loss": 0.2538,
"step": 2550
},
{
"epoch": 2.23,
"learning_rate": 3.0807982949040886e-05,
"loss": 0.2593,
"step": 2555
},
{
"epoch": 2.23,
"learning_rate": 3.075954272427824e-05,
"loss": 0.2512,
"step": 2560
},
{
"epoch": 2.23,
"learning_rate": 3.07111024995156e-05,
"loss": 0.3078,
"step": 2565
},
{
"epoch": 2.24,
"learning_rate": 3.0662662274752954e-05,
"loss": 0.2688,
"step": 2570
},
{
"epoch": 2.24,
"learning_rate": 3.0614222049990315e-05,
"loss": 0.2596,
"step": 2575
},
{
"epoch": 2.25,
"learning_rate": 3.056578182522767e-05,
"loss": 0.2409,
"step": 2580
},
{
"epoch": 2.25,
"learning_rate": 3.0517341600465026e-05,
"loss": 0.2896,
"step": 2585
},
{
"epoch": 2.26,
"learning_rate": 3.0468901375702387e-05,
"loss": 0.2954,
"step": 2590
},
{
"epoch": 2.26,
"learning_rate": 3.0420461150939744e-05,
"loss": 0.2402,
"step": 2595
},
{
"epoch": 2.27,
"learning_rate": 3.0372020926177098e-05,
"loss": 0.2952,
"step": 2600
},
{
"epoch": 2.27,
"learning_rate": 3.0323580701414456e-05,
"loss": 0.2588,
"step": 2605
},
{
"epoch": 2.27,
"learning_rate": 3.0275140476651813e-05,
"loss": 0.2592,
"step": 2610
},
{
"epoch": 2.28,
"learning_rate": 3.0226700251889174e-05,
"loss": 0.2324,
"step": 2615
},
{
"epoch": 2.28,
"learning_rate": 3.0178260027126528e-05,
"loss": 0.27,
"step": 2620
},
{
"epoch": 2.29,
"learning_rate": 3.0129819802363885e-05,
"loss": 0.2381,
"step": 2625
},
{
"epoch": 2.29,
"learning_rate": 3.0081379577601242e-05,
"loss": 0.2255,
"step": 2630
},
{
"epoch": 2.3,
"learning_rate": 3.0032939352838596e-05,
"loss": 0.3099,
"step": 2635
},
{
"epoch": 2.3,
"learning_rate": 2.9984499128075953e-05,
"loss": 0.2758,
"step": 2640
},
{
"epoch": 2.3,
"learning_rate": 2.9936058903313314e-05,
"loss": 0.2841,
"step": 2645
},
{
"epoch": 2.31,
"learning_rate": 2.988761867855067e-05,
"loss": 0.2702,
"step": 2650
},
{
"epoch": 2.31,
"learning_rate": 2.9839178453788025e-05,
"loss": 0.2386,
"step": 2655
},
{
"epoch": 2.32,
"learning_rate": 2.9790738229025383e-05,
"loss": 0.2571,
"step": 2660
},
{
"epoch": 2.32,
"learning_rate": 2.9742298004262743e-05,
"loss": 0.2844,
"step": 2665
},
{
"epoch": 2.33,
"learning_rate": 2.96938577795001e-05,
"loss": 0.338,
"step": 2670
},
{
"epoch": 2.33,
"learning_rate": 2.9645417554737455e-05,
"loss": 0.1878,
"step": 2675
},
{
"epoch": 2.34,
"learning_rate": 2.9596977329974812e-05,
"loss": 0.2119,
"step": 2680
},
{
"epoch": 2.34,
"learning_rate": 2.954853710521217e-05,
"loss": 0.24,
"step": 2685
},
{
"epoch": 2.34,
"learning_rate": 2.950009688044953e-05,
"loss": 0.2502,
"step": 2690
},
{
"epoch": 2.35,
"learning_rate": 2.945165665568688e-05,
"loss": 0.2378,
"step": 2695
},
{
"epoch": 2.35,
"learning_rate": 2.940321643092424e-05,
"loss": 0.2311,
"step": 2700
},
{
"epoch": 2.36,
"learning_rate": 2.93547762061616e-05,
"loss": 0.3013,
"step": 2705
},
{
"epoch": 2.36,
"learning_rate": 2.9306335981398953e-05,
"loss": 0.2377,
"step": 2710
},
{
"epoch": 2.37,
"learning_rate": 2.925789575663631e-05,
"loss": 0.2446,
"step": 2715
},
{
"epoch": 2.37,
"learning_rate": 2.920945553187367e-05,
"loss": 0.2943,
"step": 2720
},
{
"epoch": 2.37,
"learning_rate": 2.9161015307111028e-05,
"loss": 0.2121,
"step": 2725
},
{
"epoch": 2.38,
"learning_rate": 2.9112575082348382e-05,
"loss": 0.3064,
"step": 2730
},
{
"epoch": 2.38,
"learning_rate": 2.906413485758574e-05,
"loss": 0.3046,
"step": 2735
},
{
"epoch": 2.39,
"learning_rate": 2.90156946328231e-05,
"loss": 0.2876,
"step": 2740
},
{
"epoch": 2.39,
"learning_rate": 2.8967254408060457e-05,
"loss": 0.2875,
"step": 2745
},
{
"epoch": 2.4,
"learning_rate": 2.891881418329781e-05,
"loss": 0.2591,
"step": 2750
},
{
"epoch": 2.4,
"learning_rate": 2.887037395853517e-05,
"loss": 0.3035,
"step": 2755
},
{
"epoch": 2.4,
"learning_rate": 2.8821933733772526e-05,
"loss": 0.3093,
"step": 2760
},
{
"epoch": 2.41,
"learning_rate": 2.8773493509009887e-05,
"loss": 0.3047,
"step": 2765
},
{
"epoch": 2.41,
"learning_rate": 2.8725053284247237e-05,
"loss": 0.2584,
"step": 2770
},
{
"epoch": 2.42,
"learning_rate": 2.8676613059484598e-05,
"loss": 0.3159,
"step": 2775
},
{
"epoch": 2.42,
"learning_rate": 2.8628172834721955e-05,
"loss": 0.232,
"step": 2780
},
{
"epoch": 2.43,
"learning_rate": 2.8579732609959316e-05,
"loss": 0.2765,
"step": 2785
},
{
"epoch": 2.43,
"learning_rate": 2.8531292385196666e-05,
"loss": 0.2654,
"step": 2790
},
{
"epoch": 2.44,
"learning_rate": 2.8482852160434027e-05,
"loss": 0.2886,
"step": 2795
},
{
"epoch": 2.44,
"learning_rate": 2.8434411935671384e-05,
"loss": 0.2729,
"step": 2800
},
{
"epoch": 2.44,
"learning_rate": 2.838597171090874e-05,
"loss": 0.2581,
"step": 2805
},
{
"epoch": 2.45,
"learning_rate": 2.8337531486146096e-05,
"loss": 0.2444,
"step": 2810
},
{
"epoch": 2.45,
"learning_rate": 2.8289091261383456e-05,
"loss": 0.2744,
"step": 2815
},
{
"epoch": 2.46,
"learning_rate": 2.8240651036620814e-05,
"loss": 0.2381,
"step": 2820
},
{
"epoch": 2.46,
"learning_rate": 2.8192210811858168e-05,
"loss": 0.266,
"step": 2825
},
{
"epoch": 2.47,
"learning_rate": 2.8143770587095525e-05,
"loss": 0.2855,
"step": 2830
},
{
"epoch": 2.47,
"learning_rate": 2.8095330362332882e-05,
"loss": 0.2438,
"step": 2835
},
{
"epoch": 2.47,
"learning_rate": 2.8046890137570243e-05,
"loss": 0.2978,
"step": 2840
},
{
"epoch": 2.48,
"learning_rate": 2.7998449912807593e-05,
"loss": 0.3108,
"step": 2845
},
{
"epoch": 2.48,
"learning_rate": 2.7950009688044954e-05,
"loss": 0.2635,
"step": 2850
},
{
"epoch": 2.49,
"learning_rate": 2.790156946328231e-05,
"loss": 0.285,
"step": 2855
},
{
"epoch": 2.49,
"learning_rate": 2.7853129238519672e-05,
"loss": 0.2889,
"step": 2860
},
{
"epoch": 2.5,
"learning_rate": 2.7804689013757023e-05,
"loss": 0.2835,
"step": 2865
},
{
"epoch": 2.5,
"learning_rate": 2.7756248788994383e-05,
"loss": 0.26,
"step": 2870
},
{
"epoch": 2.5,
"learning_rate": 2.770780856423174e-05,
"loss": 0.3051,
"step": 2875
},
{
"epoch": 2.51,
"learning_rate": 2.7659368339469095e-05,
"loss": 0.302,
"step": 2880
},
{
"epoch": 2.51,
"learning_rate": 2.7610928114706452e-05,
"loss": 0.2117,
"step": 2885
},
{
"epoch": 2.52,
"learning_rate": 2.756248788994381e-05,
"loss": 0.2519,
"step": 2890
},
{
"epoch": 2.52,
"learning_rate": 2.751404766518117e-05,
"loss": 0.222,
"step": 2895
},
{
"epoch": 2.53,
"learning_rate": 2.7465607440418524e-05,
"loss": 0.2209,
"step": 2900
},
{
"epoch": 2.53,
"learning_rate": 2.741716721565588e-05,
"loss": 0.2685,
"step": 2905
},
{
"epoch": 2.54,
"learning_rate": 2.736872699089324e-05,
"loss": 0.2825,
"step": 2910
},
{
"epoch": 2.54,
"learning_rate": 2.73202867661306e-05,
"loss": 0.2712,
"step": 2915
},
{
"epoch": 2.54,
"learning_rate": 2.727184654136795e-05,
"loss": 0.2704,
"step": 2920
},
{
"epoch": 2.55,
"learning_rate": 2.722340631660531e-05,
"loss": 0.2521,
"step": 2925
},
{
"epoch": 2.55,
"learning_rate": 2.7174966091842668e-05,
"loss": 0.209,
"step": 2930
},
{
"epoch": 2.56,
"learning_rate": 2.712652586708003e-05,
"loss": 0.2917,
"step": 2935
},
{
"epoch": 2.56,
"learning_rate": 2.707808564231738e-05,
"loss": 0.2538,
"step": 2940
},
{
"epoch": 2.57,
"learning_rate": 2.702964541755474e-05,
"loss": 0.2544,
"step": 2945
},
{
"epoch": 2.57,
"learning_rate": 2.6981205192792097e-05,
"loss": 0.2455,
"step": 2950
},
{
"epoch": 2.57,
"learning_rate": 2.693276496802945e-05,
"loss": 0.2913,
"step": 2955
},
{
"epoch": 2.58,
"learning_rate": 2.688432474326681e-05,
"loss": 0.2502,
"step": 2960
},
{
"epoch": 2.58,
"learning_rate": 2.6835884518504166e-05,
"loss": 0.2838,
"step": 2965
},
{
"epoch": 2.59,
"learning_rate": 2.6787444293741527e-05,
"loss": 0.3126,
"step": 2970
},
{
"epoch": 2.59,
"learning_rate": 2.673900406897888e-05,
"loss": 0.2505,
"step": 2975
},
{
"epoch": 2.6,
"learning_rate": 2.6690563844216238e-05,
"loss": 0.2788,
"step": 2980
},
{
"epoch": 2.6,
"learning_rate": 2.6642123619453595e-05,
"loss": 0.2642,
"step": 2985
},
{
"epoch": 2.61,
"learning_rate": 2.6593683394690956e-05,
"loss": 0.2925,
"step": 2990
},
{
"epoch": 2.61,
"learning_rate": 2.6545243169928306e-05,
"loss": 0.2257,
"step": 2995
},
{
"epoch": 2.61,
"learning_rate": 2.6496802945165667e-05,
"loss": 0.2088,
"step": 3000
},
{
"epoch": 2.62,
"learning_rate": 2.6448362720403024e-05,
"loss": 0.1908,
"step": 3005
},
{
"epoch": 2.62,
"learning_rate": 2.6399922495640385e-05,
"loss": 0.2843,
"step": 3010
},
{
"epoch": 2.63,
"learning_rate": 2.6351482270877736e-05,
"loss": 0.2607,
"step": 3015
},
{
"epoch": 2.63,
"learning_rate": 2.6303042046115096e-05,
"loss": 0.2609,
"step": 3020
},
{
"epoch": 2.64,
"learning_rate": 2.6254601821352454e-05,
"loss": 0.2704,
"step": 3025
},
{
"epoch": 2.64,
"learning_rate": 2.620616159658981e-05,
"loss": 0.3238,
"step": 3030
},
{
"epoch": 2.64,
"learning_rate": 2.6157721371827165e-05,
"loss": 0.2911,
"step": 3035
},
{
"epoch": 2.65,
"learning_rate": 2.6109281147064522e-05,
"loss": 0.2851,
"step": 3040
},
{
"epoch": 2.65,
"learning_rate": 2.6060840922301883e-05,
"loss": 0.2804,
"step": 3045
},
{
"epoch": 2.66,
"learning_rate": 2.6012400697539237e-05,
"loss": 0.3157,
"step": 3050
},
{
"epoch": 2.66,
"learning_rate": 2.5963960472776594e-05,
"loss": 0.3432,
"step": 3055
},
{
"epoch": 2.67,
"learning_rate": 2.591552024801395e-05,
"loss": 0.2601,
"step": 3060
},
{
"epoch": 2.67,
"learning_rate": 2.5867080023251312e-05,
"loss": 0.275,
"step": 3065
},
{
"epoch": 2.67,
"learning_rate": 2.5818639798488663e-05,
"loss": 0.227,
"step": 3070
},
{
"epoch": 2.68,
"learning_rate": 2.5770199573726024e-05,
"loss": 0.2709,
"step": 3075
},
{
"epoch": 2.68,
"learning_rate": 2.572175934896338e-05,
"loss": 0.322,
"step": 3080
},
{
"epoch": 2.69,
"learning_rate": 2.5673319124200738e-05,
"loss": 0.308,
"step": 3085
},
{
"epoch": 2.69,
"learning_rate": 2.5624878899438092e-05,
"loss": 0.295,
"step": 3090
},
{
"epoch": 2.7,
"learning_rate": 2.5576438674675453e-05,
"loss": 0.2253,
"step": 3095
},
{
"epoch": 2.7,
"learning_rate": 2.552799844991281e-05,
"loss": 0.2835,
"step": 3100
},
{
"epoch": 2.71,
"learning_rate": 2.5479558225150167e-05,
"loss": 0.2677,
"step": 3105
},
{
"epoch": 2.71,
"learning_rate": 2.543111800038752e-05,
"loss": 0.249,
"step": 3110
},
{
"epoch": 2.71,
"learning_rate": 2.538267777562488e-05,
"loss": 0.3039,
"step": 3115
},
{
"epoch": 2.72,
"learning_rate": 2.533423755086224e-05,
"loss": 0.3151,
"step": 3120
},
{
"epoch": 2.72,
"learning_rate": 2.5285797326099593e-05,
"loss": 0.2402,
"step": 3125
},
{
"epoch": 2.73,
"learning_rate": 2.523735710133695e-05,
"loss": 0.2756,
"step": 3130
},
{
"epoch": 2.73,
"learning_rate": 2.5188916876574308e-05,
"loss": 0.2832,
"step": 3135
},
{
"epoch": 2.74,
"learning_rate": 2.514047665181167e-05,
"loss": 0.2324,
"step": 3140
},
{
"epoch": 2.74,
"learning_rate": 2.509203642704902e-05,
"loss": 0.2659,
"step": 3145
},
{
"epoch": 2.74,
"learning_rate": 2.504359620228638e-05,
"loss": 0.2668,
"step": 3150
},
{
"epoch": 2.75,
"learning_rate": 2.4995155977523737e-05,
"loss": 0.2376,
"step": 3155
},
{
"epoch": 2.75,
"learning_rate": 2.4946715752761095e-05,
"loss": 0.205,
"step": 3160
},
{
"epoch": 2.76,
"learning_rate": 2.4898275527998452e-05,
"loss": 0.2591,
"step": 3165
},
{
"epoch": 2.76,
"learning_rate": 2.484983530323581e-05,
"loss": 0.2501,
"step": 3170
},
{
"epoch": 2.77,
"learning_rate": 2.4801395078473167e-05,
"loss": 0.2742,
"step": 3175
},
{
"epoch": 2.77,
"learning_rate": 2.475295485371052e-05,
"loss": 0.3057,
"step": 3180
},
{
"epoch": 2.77,
"learning_rate": 2.470451462894788e-05,
"loss": 0.2713,
"step": 3185
},
{
"epoch": 2.78,
"learning_rate": 2.4656074404185235e-05,
"loss": 0.2654,
"step": 3190
},
{
"epoch": 2.78,
"learning_rate": 2.4607634179422596e-05,
"loss": 0.2561,
"step": 3195
},
{
"epoch": 2.79,
"learning_rate": 2.455919395465995e-05,
"loss": 0.2607,
"step": 3200
},
{
"epoch": 2.79,
"learning_rate": 2.4510753729897307e-05,
"loss": 0.2499,
"step": 3205
},
{
"epoch": 2.8,
"learning_rate": 2.4462313505134664e-05,
"loss": 0.2496,
"step": 3210
},
{
"epoch": 2.8,
"learning_rate": 2.4413873280372022e-05,
"loss": 0.2424,
"step": 3215
},
{
"epoch": 2.81,
"learning_rate": 2.436543305560938e-05,
"loss": 0.2322,
"step": 3220
},
{
"epoch": 2.81,
"learning_rate": 2.4316992830846736e-05,
"loss": 0.2577,
"step": 3225
},
{
"epoch": 2.81,
"learning_rate": 2.4268552606084094e-05,
"loss": 0.2591,
"step": 3230
},
{
"epoch": 2.82,
"learning_rate": 2.422011238132145e-05,
"loss": 0.2574,
"step": 3235
},
{
"epoch": 2.82,
"learning_rate": 2.417167215655881e-05,
"loss": 0.3172,
"step": 3240
},
{
"epoch": 2.83,
"learning_rate": 2.4123231931796166e-05,
"loss": 0.2887,
"step": 3245
},
{
"epoch": 2.83,
"learning_rate": 2.4074791707033523e-05,
"loss": 0.247,
"step": 3250
},
{
"epoch": 2.84,
"learning_rate": 2.4026351482270877e-05,
"loss": 0.2893,
"step": 3255
},
{
"epoch": 2.84,
"learning_rate": 2.3977911257508238e-05,
"loss": 0.2391,
"step": 3260
},
{
"epoch": 2.84,
"learning_rate": 2.392947103274559e-05,
"loss": 0.2743,
"step": 3265
},
{
"epoch": 2.85,
"learning_rate": 2.3881030807982952e-05,
"loss": 0.2385,
"step": 3270
},
{
"epoch": 2.85,
"learning_rate": 2.3832590583220306e-05,
"loss": 0.303,
"step": 3275
},
{
"epoch": 2.86,
"learning_rate": 2.3784150358457664e-05,
"loss": 0.271,
"step": 3280
},
{
"epoch": 2.86,
"learning_rate": 2.373571013369502e-05,
"loss": 0.2753,
"step": 3285
},
{
"epoch": 2.87,
"learning_rate": 2.3687269908932378e-05,
"loss": 0.2433,
"step": 3290
},
{
"epoch": 2.87,
"learning_rate": 2.3638829684169735e-05,
"loss": 0.202,
"step": 3295
},
{
"epoch": 2.88,
"learning_rate": 2.3590389459407093e-05,
"loss": 0.2825,
"step": 3300
},
{
"epoch": 2.88,
"learning_rate": 2.354194923464445e-05,
"loss": 0.3058,
"step": 3305
},
{
"epoch": 2.88,
"learning_rate": 2.3493509009881807e-05,
"loss": 0.28,
"step": 3310
},
{
"epoch": 2.89,
"learning_rate": 2.3445068785119165e-05,
"loss": 0.3542,
"step": 3315
},
{
"epoch": 2.89,
"learning_rate": 2.3396628560356522e-05,
"loss": 0.2888,
"step": 3320
},
{
"epoch": 2.9,
"learning_rate": 2.334818833559388e-05,
"loss": 0.254,
"step": 3325
},
{
"epoch": 2.9,
"learning_rate": 2.3299748110831233e-05,
"loss": 0.3272,
"step": 3330
},
{
"epoch": 2.91,
"learning_rate": 2.3251307886068594e-05,
"loss": 0.2412,
"step": 3335
},
{
"epoch": 2.91,
"learning_rate": 2.3202867661305948e-05,
"loss": 0.263,
"step": 3340
},
{
"epoch": 2.91,
"learning_rate": 2.315442743654331e-05,
"loss": 0.2462,
"step": 3345
},
{
"epoch": 2.92,
"learning_rate": 2.3105987211780663e-05,
"loss": 0.2673,
"step": 3350
},
{
"epoch": 2.92,
"learning_rate": 2.3057546987018023e-05,
"loss": 0.24,
"step": 3355
},
{
"epoch": 2.93,
"learning_rate": 2.3009106762255377e-05,
"loss": 0.2574,
"step": 3360
},
{
"epoch": 2.93,
"learning_rate": 2.2960666537492735e-05,
"loss": 0.2235,
"step": 3365
},
{
"epoch": 2.94,
"learning_rate": 2.2912226312730092e-05,
"loss": 0.2718,
"step": 3370
},
{
"epoch": 2.94,
"learning_rate": 2.286378608796745e-05,
"loss": 0.2465,
"step": 3375
},
{
"epoch": 2.94,
"learning_rate": 2.2815345863204807e-05,
"loss": 0.3352,
"step": 3380
},
{
"epoch": 2.95,
"learning_rate": 2.2766905638442164e-05,
"loss": 0.3209,
"step": 3385
},
{
"epoch": 2.95,
"learning_rate": 2.271846541367952e-05,
"loss": 0.2985,
"step": 3390
},
{
"epoch": 2.96,
"learning_rate": 2.267002518891688e-05,
"loss": 0.2459,
"step": 3395
},
{
"epoch": 2.96,
"learning_rate": 2.2621584964154236e-05,
"loss": 0.2722,
"step": 3400
},
{
"epoch": 2.97,
"learning_rate": 2.257314473939159e-05,
"loss": 0.27,
"step": 3405
},
{
"epoch": 2.97,
"learning_rate": 2.252470451462895e-05,
"loss": 0.2211,
"step": 3410
},
{
"epoch": 2.98,
"learning_rate": 2.2476264289866304e-05,
"loss": 0.2449,
"step": 3415
},
{
"epoch": 2.98,
"learning_rate": 2.2427824065103665e-05,
"loss": 0.271,
"step": 3420
},
{
"epoch": 2.98,
"learning_rate": 2.237938384034102e-05,
"loss": 0.2359,
"step": 3425
},
{
"epoch": 2.99,
"learning_rate": 2.233094361557838e-05,
"loss": 0.2508,
"step": 3430
},
{
"epoch": 2.99,
"learning_rate": 2.2282503390815734e-05,
"loss": 0.2641,
"step": 3435
},
{
"epoch": 3.0,
"learning_rate": 2.2234063166053094e-05,
"loss": 0.2743,
"step": 3440
},
{
"epoch": 3.0,
"eval_accuracy": 0.9354858473226321,
"eval_loss": 0.19344256818294525,
"eval_runtime": 32.9481,
"eval_samples_per_second": 495.385,
"eval_steps_per_second": 15.509,
"step": 3443
},
{
"epoch": 3.0,
"learning_rate": 2.218562294129045e-05,
"loss": 0.3024,
"step": 3445
},
{
"epoch": 3.01,
"learning_rate": 2.2137182716527806e-05,
"loss": 0.2083,
"step": 3450
},
{
"epoch": 3.01,
"learning_rate": 2.2088742491765163e-05,
"loss": 0.2759,
"step": 3455
},
{
"epoch": 3.01,
"learning_rate": 2.204030226700252e-05,
"loss": 0.2079,
"step": 3460
},
{
"epoch": 3.02,
"learning_rate": 2.1991862042239878e-05,
"loss": 0.2582,
"step": 3465
},
{
"epoch": 3.02,
"learning_rate": 2.194342181747723e-05,
"loss": 0.2363,
"step": 3470
},
{
"epoch": 3.03,
"learning_rate": 2.1894981592714592e-05,
"loss": 0.2461,
"step": 3475
},
{
"epoch": 3.03,
"learning_rate": 2.1846541367951946e-05,
"loss": 0.2833,
"step": 3480
},
{
"epoch": 3.04,
"learning_rate": 2.1798101143189307e-05,
"loss": 0.2147,
"step": 3485
},
{
"epoch": 3.04,
"learning_rate": 2.174966091842666e-05,
"loss": 0.3068,
"step": 3490
},
{
"epoch": 3.05,
"learning_rate": 2.170122069366402e-05,
"loss": 0.2794,
"step": 3495
},
{
"epoch": 3.05,
"learning_rate": 2.1652780468901376e-05,
"loss": 0.2412,
"step": 3500
},
{
"epoch": 3.05,
"learning_rate": 2.1604340244138736e-05,
"loss": 0.2643,
"step": 3505
},
{
"epoch": 3.06,
"learning_rate": 2.155590001937609e-05,
"loss": 0.2292,
"step": 3510
},
{
"epoch": 3.06,
"learning_rate": 2.150745979461345e-05,
"loss": 0.2301,
"step": 3515
},
{
"epoch": 3.07,
"learning_rate": 2.1459019569850805e-05,
"loss": 0.2631,
"step": 3520
},
{
"epoch": 3.07,
"learning_rate": 2.1410579345088162e-05,
"loss": 0.245,
"step": 3525
},
{
"epoch": 3.08,
"learning_rate": 2.136213912032552e-05,
"loss": 0.3059,
"step": 3530
},
{
"epoch": 3.08,
"learning_rate": 2.1313698895562877e-05,
"loss": 0.3249,
"step": 3535
},
{
"epoch": 3.08,
"learning_rate": 2.1265258670800234e-05,
"loss": 0.2494,
"step": 3540
},
{
"epoch": 3.09,
"learning_rate": 2.1216818446037588e-05,
"loss": 0.236,
"step": 3545
},
{
"epoch": 3.09,
"learning_rate": 2.116837822127495e-05,
"loss": 0.2538,
"step": 3550
},
{
"epoch": 3.1,
"learning_rate": 2.1119937996512303e-05,
"loss": 0.2535,
"step": 3555
},
{
"epoch": 3.1,
"learning_rate": 2.1071497771749663e-05,
"loss": 0.2569,
"step": 3560
},
{
"epoch": 3.11,
"learning_rate": 2.1023057546987017e-05,
"loss": 0.2719,
"step": 3565
},
{
"epoch": 3.11,
"learning_rate": 2.0974617322224378e-05,
"loss": 0.3165,
"step": 3570
},
{
"epoch": 3.11,
"learning_rate": 2.0926177097461732e-05,
"loss": 0.2562,
"step": 3575
},
{
"epoch": 3.12,
"learning_rate": 2.0877736872699093e-05,
"loss": 0.2455,
"step": 3580
},
{
"epoch": 3.12,
"learning_rate": 2.0829296647936447e-05,
"loss": 0.2502,
"step": 3585
},
{
"epoch": 3.13,
"learning_rate": 2.0780856423173807e-05,
"loss": 0.2613,
"step": 3590
},
{
"epoch": 3.13,
"learning_rate": 2.073241619841116e-05,
"loss": 0.223,
"step": 3595
},
{
"epoch": 3.14,
"learning_rate": 2.068397597364852e-05,
"loss": 0.2685,
"step": 3600
},
{
"epoch": 3.14,
"learning_rate": 2.0635535748885876e-05,
"loss": 0.2225,
"step": 3605
},
{
"epoch": 3.15,
"learning_rate": 2.0587095524123233e-05,
"loss": 0.3119,
"step": 3610
},
{
"epoch": 3.15,
"learning_rate": 2.053865529936059e-05,
"loss": 0.32,
"step": 3615
},
{
"epoch": 3.15,
"learning_rate": 2.0490215074597944e-05,
"loss": 0.2553,
"step": 3620
},
{
"epoch": 3.16,
"learning_rate": 2.0441774849835305e-05,
"loss": 0.3213,
"step": 3625
},
{
"epoch": 3.16,
"learning_rate": 2.039333462507266e-05,
"loss": 0.3333,
"step": 3630
},
{
"epoch": 3.17,
"learning_rate": 2.034489440031002e-05,
"loss": 0.2476,
"step": 3635
},
{
"epoch": 3.17,
"learning_rate": 2.0296454175547374e-05,
"loss": 0.2668,
"step": 3640
},
{
"epoch": 3.18,
"learning_rate": 2.0248013950784734e-05,
"loss": 0.274,
"step": 3645
},
{
"epoch": 3.18,
"learning_rate": 2.019957372602209e-05,
"loss": 0.213,
"step": 3650
},
{
"epoch": 3.18,
"learning_rate": 2.015113350125945e-05,
"loss": 0.2447,
"step": 3655
},
{
"epoch": 3.19,
"learning_rate": 2.0102693276496803e-05,
"loss": 0.2567,
"step": 3660
},
{
"epoch": 3.19,
"learning_rate": 2.005425305173416e-05,
"loss": 0.2418,
"step": 3665
},
{
"epoch": 3.2,
"learning_rate": 2.0005812826971518e-05,
"loss": 0.2832,
"step": 3670
},
{
"epoch": 3.2,
"learning_rate": 1.9957372602208875e-05,
"loss": 0.2576,
"step": 3675
},
{
"epoch": 3.21,
"learning_rate": 1.9908932377446232e-05,
"loss": 0.2643,
"step": 3680
},
{
"epoch": 3.21,
"learning_rate": 1.986049215268359e-05,
"loss": 0.2307,
"step": 3685
},
{
"epoch": 3.21,
"learning_rate": 1.9812051927920947e-05,
"loss": 0.2682,
"step": 3690
},
{
"epoch": 3.22,
"learning_rate": 1.97636117031583e-05,
"loss": 0.2294,
"step": 3695
},
{
"epoch": 3.22,
"learning_rate": 1.971517147839566e-05,
"loss": 0.1979,
"step": 3700
},
{
"epoch": 3.23,
"learning_rate": 1.9666731253633016e-05,
"loss": 0.2419,
"step": 3705
},
{
"epoch": 3.23,
"learning_rate": 1.9618291028870376e-05,
"loss": 0.2108,
"step": 3710
},
{
"epoch": 3.24,
"learning_rate": 1.956985080410773e-05,
"loss": 0.2921,
"step": 3715
},
{
"epoch": 3.24,
"learning_rate": 1.952141057934509e-05,
"loss": 0.2453,
"step": 3720
},
{
"epoch": 3.25,
"learning_rate": 1.9472970354582445e-05,
"loss": 0.27,
"step": 3725
},
{
"epoch": 3.25,
"learning_rate": 1.9424530129819806e-05,
"loss": 0.2463,
"step": 3730
},
{
"epoch": 3.25,
"learning_rate": 1.937608990505716e-05,
"loss": 0.2755,
"step": 3735
},
{
"epoch": 3.26,
"learning_rate": 1.9327649680294517e-05,
"loss": 0.2368,
"step": 3740
},
{
"epoch": 3.26,
"learning_rate": 1.9279209455531874e-05,
"loss": 0.2183,
"step": 3745
},
{
"epoch": 3.27,
"learning_rate": 1.923076923076923e-05,
"loss": 0.2578,
"step": 3750
},
{
"epoch": 3.27,
"learning_rate": 1.918232900600659e-05,
"loss": 0.2126,
"step": 3755
},
{
"epoch": 3.28,
"learning_rate": 1.9133888781243946e-05,
"loss": 0.2364,
"step": 3760
},
{
"epoch": 3.28,
"learning_rate": 1.9085448556481303e-05,
"loss": 0.2678,
"step": 3765
},
{
"epoch": 3.28,
"learning_rate": 1.9037008331718657e-05,
"loss": 0.3004,
"step": 3770
},
{
"epoch": 3.29,
"learning_rate": 1.8988568106956018e-05,
"loss": 0.2454,
"step": 3775
},
{
"epoch": 3.29,
"learning_rate": 1.8940127882193372e-05,
"loss": 0.2075,
"step": 3780
},
{
"epoch": 3.3,
"learning_rate": 1.8891687657430733e-05,
"loss": 0.277,
"step": 3785
},
{
"epoch": 3.3,
"learning_rate": 1.8843247432668087e-05,
"loss": 0.2028,
"step": 3790
},
{
"epoch": 3.31,
"learning_rate": 1.8794807207905447e-05,
"loss": 0.2516,
"step": 3795
},
{
"epoch": 3.31,
"learning_rate": 1.87463669831428e-05,
"loss": 0.2274,
"step": 3800
},
{
"epoch": 3.32,
"learning_rate": 1.8697926758380162e-05,
"loss": 0.2516,
"step": 3805
},
{
"epoch": 3.32,
"learning_rate": 1.8649486533617516e-05,
"loss": 0.2521,
"step": 3810
},
{
"epoch": 3.32,
"learning_rate": 1.8601046308854873e-05,
"loss": 0.2864,
"step": 3815
},
{
"epoch": 3.33,
"learning_rate": 1.855260608409223e-05,
"loss": 0.2158,
"step": 3820
},
{
"epoch": 3.33,
"learning_rate": 1.8504165859329588e-05,
"loss": 0.2666,
"step": 3825
},
{
"epoch": 3.34,
"learning_rate": 1.8455725634566945e-05,
"loss": 0.2723,
"step": 3830
},
{
"epoch": 3.34,
"learning_rate": 1.8407285409804303e-05,
"loss": 0.2239,
"step": 3835
},
{
"epoch": 3.35,
"learning_rate": 1.835884518504166e-05,
"loss": 0.2679,
"step": 3840
},
{
"epoch": 3.35,
"learning_rate": 1.8310404960279017e-05,
"loss": 0.2769,
"step": 3845
},
{
"epoch": 3.35,
"learning_rate": 1.8261964735516374e-05,
"loss": 0.2118,
"step": 3850
},
{
"epoch": 3.36,
"learning_rate": 1.821352451075373e-05,
"loss": 0.2198,
"step": 3855
},
{
"epoch": 3.36,
"learning_rate": 1.816508428599109e-05,
"loss": 0.2204,
"step": 3860
},
{
"epoch": 3.37,
"learning_rate": 1.8116644061228443e-05,
"loss": 0.256,
"step": 3865
},
{
"epoch": 3.37,
"learning_rate": 1.8068203836465804e-05,
"loss": 0.2367,
"step": 3870
},
{
"epoch": 3.38,
"learning_rate": 1.8019763611703158e-05,
"loss": 0.2814,
"step": 3875
},
{
"epoch": 3.38,
"learning_rate": 1.797132338694052e-05,
"loss": 0.2785,
"step": 3880
},
{
"epoch": 3.38,
"learning_rate": 1.7922883162177872e-05,
"loss": 0.2382,
"step": 3885
},
{
"epoch": 3.39,
"learning_rate": 1.787444293741523e-05,
"loss": 0.2369,
"step": 3890
},
{
"epoch": 3.39,
"learning_rate": 1.7826002712652587e-05,
"loss": 0.2418,
"step": 3895
},
{
"epoch": 3.4,
"learning_rate": 1.7777562487889944e-05,
"loss": 0.325,
"step": 3900
},
{
"epoch": 3.4,
"learning_rate": 1.77291222631273e-05,
"loss": 0.2449,
"step": 3905
},
{
"epoch": 3.41,
"learning_rate": 1.768068203836466e-05,
"loss": 0.2384,
"step": 3910
},
{
"epoch": 3.41,
"learning_rate": 1.7632241813602016e-05,
"loss": 0.2356,
"step": 3915
},
{
"epoch": 3.42,
"learning_rate": 1.7583801588839374e-05,
"loss": 0.2797,
"step": 3920
},
{
"epoch": 3.42,
"learning_rate": 1.753536136407673e-05,
"loss": 0.2874,
"step": 3925
},
{
"epoch": 3.42,
"learning_rate": 1.7486921139314088e-05,
"loss": 0.2378,
"step": 3930
},
{
"epoch": 3.43,
"learning_rate": 1.7438480914551446e-05,
"loss": 0.2272,
"step": 3935
},
{
"epoch": 3.43,
"learning_rate": 1.73900406897888e-05,
"loss": 0.2669,
"step": 3940
},
{
"epoch": 3.44,
"learning_rate": 1.734160046502616e-05,
"loss": 0.2174,
"step": 3945
},
{
"epoch": 3.44,
"learning_rate": 1.7293160240263514e-05,
"loss": 0.2557,
"step": 3950
},
{
"epoch": 3.45,
"learning_rate": 1.724472001550087e-05,
"loss": 0.2632,
"step": 3955
},
{
"epoch": 3.45,
"learning_rate": 1.719627979073823e-05,
"loss": 0.2637,
"step": 3960
},
{
"epoch": 3.45,
"learning_rate": 1.7147839565975586e-05,
"loss": 0.2624,
"step": 3965
},
{
"epoch": 3.46,
"learning_rate": 1.7099399341212943e-05,
"loss": 0.2656,
"step": 3970
},
{
"epoch": 3.46,
"learning_rate": 1.70509591164503e-05,
"loss": 0.1978,
"step": 3975
},
{
"epoch": 3.47,
"learning_rate": 1.7002518891687658e-05,
"loss": 0.2626,
"step": 3980
},
{
"epoch": 3.47,
"learning_rate": 1.6954078666925015e-05,
"loss": 0.2479,
"step": 3985
},
{
"epoch": 3.48,
"learning_rate": 1.6905638442162373e-05,
"loss": 0.2134,
"step": 3990
},
{
"epoch": 3.48,
"learning_rate": 1.685719821739973e-05,
"loss": 0.1868,
"step": 3995
},
{
"epoch": 3.49,
"learning_rate": 1.6808757992637087e-05,
"loss": 0.2816,
"step": 4000
},
{
"epoch": 3.49,
"learning_rate": 1.6760317767874445e-05,
"loss": 0.2529,
"step": 4005
},
{
"epoch": 3.49,
"learning_rate": 1.6711877543111802e-05,
"loss": 0.2192,
"step": 4010
},
{
"epoch": 3.5,
"learning_rate": 1.6663437318349156e-05,
"loss": 0.2448,
"step": 4015
},
{
"epoch": 3.5,
"learning_rate": 1.6614997093586517e-05,
"loss": 0.2717,
"step": 4020
},
{
"epoch": 3.51,
"learning_rate": 1.656655686882387e-05,
"loss": 0.2815,
"step": 4025
},
{
"epoch": 3.51,
"learning_rate": 1.6518116644061228e-05,
"loss": 0.2294,
"step": 4030
},
{
"epoch": 3.52,
"learning_rate": 1.6469676419298585e-05,
"loss": 0.2857,
"step": 4035
},
{
"epoch": 3.52,
"learning_rate": 1.6421236194535943e-05,
"loss": 0.2569,
"step": 4040
},
{
"epoch": 3.52,
"learning_rate": 1.63727959697733e-05,
"loss": 0.3037,
"step": 4045
},
{
"epoch": 3.53,
"learning_rate": 1.6324355745010657e-05,
"loss": 0.2302,
"step": 4050
},
{
"epoch": 3.53,
"learning_rate": 1.6275915520248014e-05,
"loss": 0.2339,
"step": 4055
},
{
"epoch": 3.54,
"learning_rate": 1.6227475295485372e-05,
"loss": 0.2724,
"step": 4060
},
{
"epoch": 3.54,
"learning_rate": 1.617903507072273e-05,
"loss": 0.2541,
"step": 4065
},
{
"epoch": 3.55,
"learning_rate": 1.6130594845960086e-05,
"loss": 0.2332,
"step": 4070
},
{
"epoch": 3.55,
"learning_rate": 1.6082154621197444e-05,
"loss": 0.1858,
"step": 4075
},
{
"epoch": 3.55,
"learning_rate": 1.60337143964348e-05,
"loss": 0.2229,
"step": 4080
},
{
"epoch": 3.56,
"learning_rate": 1.598527417167216e-05,
"loss": 0.281,
"step": 4085
},
{
"epoch": 3.56,
"learning_rate": 1.5936833946909516e-05,
"loss": 0.2181,
"step": 4090
},
{
"epoch": 3.57,
"learning_rate": 1.5888393722146873e-05,
"loss": 0.2212,
"step": 4095
},
{
"epoch": 3.57,
"learning_rate": 1.5839953497384227e-05,
"loss": 0.2396,
"step": 4100
},
{
"epoch": 3.58,
"learning_rate": 1.5791513272621584e-05,
"loss": 0.2062,
"step": 4105
},
{
"epoch": 3.58,
"learning_rate": 1.574307304785894e-05,
"loss": 0.2639,
"step": 4110
},
{
"epoch": 3.59,
"learning_rate": 1.56946328230963e-05,
"loss": 0.2742,
"step": 4115
},
{
"epoch": 3.59,
"learning_rate": 1.5646192598333656e-05,
"loss": 0.2067,
"step": 4120
},
{
"epoch": 3.59,
"learning_rate": 1.5597752373571014e-05,
"loss": 0.2269,
"step": 4125
},
{
"epoch": 3.6,
"learning_rate": 1.554931214880837e-05,
"loss": 0.2495,
"step": 4130
},
{
"epoch": 3.6,
"learning_rate": 1.5500871924045728e-05,
"loss": 0.2716,
"step": 4135
},
{
"epoch": 3.61,
"learning_rate": 1.5452431699283086e-05,
"loss": 0.2981,
"step": 4140
},
{
"epoch": 3.61,
"learning_rate": 1.5403991474520443e-05,
"loss": 0.2497,
"step": 4145
},
{
"epoch": 3.62,
"learning_rate": 1.53555512497578e-05,
"loss": 0.2611,
"step": 4150
},
{
"epoch": 3.62,
"learning_rate": 1.5307111024995158e-05,
"loss": 0.2029,
"step": 4155
},
{
"epoch": 3.62,
"learning_rate": 1.5258670800232513e-05,
"loss": 0.2313,
"step": 4160
},
{
"epoch": 3.63,
"learning_rate": 1.5210230575469872e-05,
"loss": 0.2331,
"step": 4165
},
{
"epoch": 3.63,
"learning_rate": 1.5161790350707228e-05,
"loss": 0.2249,
"step": 4170
},
{
"epoch": 3.64,
"learning_rate": 1.5113350125944587e-05,
"loss": 0.2626,
"step": 4175
},
{
"epoch": 3.64,
"learning_rate": 1.5064909901181942e-05,
"loss": 0.2732,
"step": 4180
},
{
"epoch": 3.65,
"learning_rate": 1.5016469676419298e-05,
"loss": 0.277,
"step": 4185
},
{
"epoch": 3.65,
"learning_rate": 1.4968029451656657e-05,
"loss": 0.2989,
"step": 4190
},
{
"epoch": 3.65,
"learning_rate": 1.4919589226894013e-05,
"loss": 0.2132,
"step": 4195
},
{
"epoch": 3.66,
"learning_rate": 1.4871149002131372e-05,
"loss": 0.2327,
"step": 4200
},
{
"epoch": 3.66,
"learning_rate": 1.4822708777368727e-05,
"loss": 0.2749,
"step": 4205
},
{
"epoch": 3.67,
"learning_rate": 1.4774268552606085e-05,
"loss": 0.2662,
"step": 4210
},
{
"epoch": 3.67,
"learning_rate": 1.472582832784344e-05,
"loss": 0.2445,
"step": 4215
},
{
"epoch": 3.68,
"learning_rate": 1.46773881030808e-05,
"loss": 0.2006,
"step": 4220
},
{
"epoch": 3.68,
"learning_rate": 1.4628947878318155e-05,
"loss": 0.2756,
"step": 4225
},
{
"epoch": 3.69,
"learning_rate": 1.4580507653555514e-05,
"loss": 0.2415,
"step": 4230
},
{
"epoch": 3.69,
"learning_rate": 1.453206742879287e-05,
"loss": 0.2374,
"step": 4235
},
{
"epoch": 3.69,
"learning_rate": 1.4483627204030229e-05,
"loss": 0.2086,
"step": 4240
},
{
"epoch": 3.7,
"learning_rate": 1.4435186979267584e-05,
"loss": 0.2363,
"step": 4245
},
{
"epoch": 3.7,
"learning_rate": 1.4386746754504943e-05,
"loss": 0.2488,
"step": 4250
},
{
"epoch": 3.71,
"learning_rate": 1.4338306529742299e-05,
"loss": 0.1849,
"step": 4255
},
{
"epoch": 3.71,
"learning_rate": 1.4289866304979658e-05,
"loss": 0.2258,
"step": 4260
},
{
"epoch": 3.72,
"learning_rate": 1.4241426080217014e-05,
"loss": 0.2473,
"step": 4265
},
{
"epoch": 3.72,
"learning_rate": 1.419298585545437e-05,
"loss": 0.2714,
"step": 4270
},
{
"epoch": 3.72,
"learning_rate": 1.4144545630691728e-05,
"loss": 0.2507,
"step": 4275
},
{
"epoch": 3.73,
"learning_rate": 1.4096105405929084e-05,
"loss": 0.2551,
"step": 4280
},
{
"epoch": 3.73,
"learning_rate": 1.4047665181166441e-05,
"loss": 0.2303,
"step": 4285
},
{
"epoch": 3.74,
"learning_rate": 1.3999224956403797e-05,
"loss": 0.2438,
"step": 4290
},
{
"epoch": 3.74,
"learning_rate": 1.3950784731641156e-05,
"loss": 0.2686,
"step": 4295
},
{
"epoch": 3.75,
"learning_rate": 1.3902344506878511e-05,
"loss": 0.2598,
"step": 4300
},
{
"epoch": 3.75,
"learning_rate": 1.385390428211587e-05,
"loss": 0.277,
"step": 4305
},
{
"epoch": 3.76,
"learning_rate": 1.3805464057353226e-05,
"loss": 0.2484,
"step": 4310
},
{
"epoch": 3.76,
"learning_rate": 1.3757023832590585e-05,
"loss": 0.2338,
"step": 4315
},
{
"epoch": 3.76,
"learning_rate": 1.370858360782794e-05,
"loss": 0.2003,
"step": 4320
},
{
"epoch": 3.77,
"learning_rate": 1.36601433830653e-05,
"loss": 0.2693,
"step": 4325
},
{
"epoch": 3.77,
"learning_rate": 1.3611703158302655e-05,
"loss": 0.1846,
"step": 4330
},
{
"epoch": 3.78,
"learning_rate": 1.3563262933540014e-05,
"loss": 0.2816,
"step": 4335
},
{
"epoch": 3.78,
"learning_rate": 1.351482270877737e-05,
"loss": 0.2407,
"step": 4340
},
{
"epoch": 3.79,
"learning_rate": 1.3466382484014726e-05,
"loss": 0.2064,
"step": 4345
},
{
"epoch": 3.79,
"learning_rate": 1.3417942259252083e-05,
"loss": 0.247,
"step": 4350
},
{
"epoch": 3.79,
"learning_rate": 1.336950203448944e-05,
"loss": 0.2141,
"step": 4355
},
{
"epoch": 3.8,
"learning_rate": 1.3321061809726798e-05,
"loss": 0.2234,
"step": 4360
},
{
"epoch": 3.8,
"learning_rate": 1.3272621584964153e-05,
"loss": 0.2442,
"step": 4365
},
{
"epoch": 3.81,
"learning_rate": 1.3224181360201512e-05,
"loss": 0.2605,
"step": 4370
},
{
"epoch": 3.81,
"learning_rate": 1.3175741135438868e-05,
"loss": 0.2615,
"step": 4375
},
{
"epoch": 3.82,
"learning_rate": 1.3127300910676227e-05,
"loss": 0.2375,
"step": 4380
},
{
"epoch": 3.82,
"learning_rate": 1.3078860685913582e-05,
"loss": 0.2877,
"step": 4385
},
{
"epoch": 3.82,
"learning_rate": 1.3030420461150941e-05,
"loss": 0.2611,
"step": 4390
},
{
"epoch": 3.83,
"learning_rate": 1.2981980236388297e-05,
"loss": 0.2661,
"step": 4395
},
{
"epoch": 3.83,
"learning_rate": 1.2933540011625656e-05,
"loss": 0.2197,
"step": 4400
},
{
"epoch": 3.84,
"learning_rate": 1.2885099786863012e-05,
"loss": 0.2708,
"step": 4405
},
{
"epoch": 3.84,
"learning_rate": 1.2836659562100369e-05,
"loss": 0.2373,
"step": 4410
},
{
"epoch": 3.85,
"learning_rate": 1.2788219337337726e-05,
"loss": 0.2355,
"step": 4415
},
{
"epoch": 3.85,
"learning_rate": 1.2739779112575084e-05,
"loss": 0.2711,
"step": 4420
},
{
"epoch": 3.86,
"learning_rate": 1.269133888781244e-05,
"loss": 0.2934,
"step": 4425
},
{
"epoch": 3.86,
"learning_rate": 1.2642898663049797e-05,
"loss": 0.2275,
"step": 4430
},
{
"epoch": 3.86,
"learning_rate": 1.2594458438287154e-05,
"loss": 0.2604,
"step": 4435
},
{
"epoch": 3.87,
"learning_rate": 1.254601821352451e-05,
"loss": 0.2189,
"step": 4440
},
{
"epoch": 3.87,
"learning_rate": 1.2497577988761869e-05,
"loss": 0.2325,
"step": 4445
},
{
"epoch": 3.88,
"learning_rate": 1.2449137763999226e-05,
"loss": 0.2539,
"step": 4450
},
{
"epoch": 3.88,
"learning_rate": 1.2400697539236583e-05,
"loss": 0.237,
"step": 4455
},
{
"epoch": 3.89,
"learning_rate": 1.235225731447394e-05,
"loss": 0.2687,
"step": 4460
},
{
"epoch": 3.89,
"learning_rate": 1.2303817089711298e-05,
"loss": 0.2067,
"step": 4465
},
{
"epoch": 3.89,
"learning_rate": 1.2255376864948654e-05,
"loss": 0.2191,
"step": 4470
},
{
"epoch": 3.9,
"learning_rate": 1.2206936640186011e-05,
"loss": 0.2455,
"step": 4475
},
{
"epoch": 3.9,
"learning_rate": 1.2158496415423368e-05,
"loss": 0.2558,
"step": 4480
},
{
"epoch": 3.91,
"learning_rate": 1.2110056190660726e-05,
"loss": 0.2222,
"step": 4485
},
{
"epoch": 3.91,
"learning_rate": 1.2061615965898083e-05,
"loss": 0.245,
"step": 4490
},
{
"epoch": 3.92,
"learning_rate": 1.2013175741135438e-05,
"loss": 0.2443,
"step": 4495
},
{
"epoch": 3.92,
"learning_rate": 1.1964735516372796e-05,
"loss": 0.2373,
"step": 4500
},
{
"epoch": 3.93,
"learning_rate": 1.1916295291610153e-05,
"loss": 0.2459,
"step": 4505
},
{
"epoch": 3.93,
"learning_rate": 1.186785506684751e-05,
"loss": 0.2378,
"step": 4510
},
{
"epoch": 3.93,
"learning_rate": 1.1819414842084868e-05,
"loss": 0.2445,
"step": 4515
},
{
"epoch": 3.94,
"learning_rate": 1.1770974617322225e-05,
"loss": 0.2292,
"step": 4520
},
{
"epoch": 3.94,
"learning_rate": 1.1722534392559582e-05,
"loss": 0.2242,
"step": 4525
},
{
"epoch": 3.95,
"learning_rate": 1.167409416779694e-05,
"loss": 0.2253,
"step": 4530
},
{
"epoch": 3.95,
"learning_rate": 1.1625653943034297e-05,
"loss": 0.2524,
"step": 4535
},
{
"epoch": 3.96,
"learning_rate": 1.1577213718271654e-05,
"loss": 0.2166,
"step": 4540
},
{
"epoch": 3.96,
"learning_rate": 1.1528773493509012e-05,
"loss": 0.219,
"step": 4545
},
{
"epoch": 3.96,
"learning_rate": 1.1480333268746367e-05,
"loss": 0.2463,
"step": 4550
},
{
"epoch": 3.97,
"learning_rate": 1.1431893043983725e-05,
"loss": 0.2433,
"step": 4555
},
{
"epoch": 3.97,
"learning_rate": 1.1383452819221082e-05,
"loss": 0.2808,
"step": 4560
},
{
"epoch": 3.98,
"learning_rate": 1.133501259445844e-05,
"loss": 0.2268,
"step": 4565
},
{
"epoch": 3.98,
"learning_rate": 1.1286572369695795e-05,
"loss": 0.2416,
"step": 4570
},
{
"epoch": 3.99,
"learning_rate": 1.1238132144933152e-05,
"loss": 0.2407,
"step": 4575
},
{
"epoch": 3.99,
"learning_rate": 1.118969192017051e-05,
"loss": 0.2301,
"step": 4580
},
{
"epoch": 3.99,
"learning_rate": 1.1141251695407867e-05,
"loss": 0.2137,
"step": 4585
},
{
"epoch": 4.0,
"learning_rate": 1.1092811470645224e-05,
"loss": 0.276,
"step": 4590
},
{
"epoch": 4.0,
"eval_accuracy": 0.9328513662541356,
"eval_loss": 0.1981973648071289,
"eval_runtime": 32.5781,
"eval_samples_per_second": 501.012,
"eval_steps_per_second": 15.685,
"step": 4591
},
{
"epoch": 4.0,
"learning_rate": 1.1044371245882582e-05,
"loss": 0.259,
"step": 4595
},
{
"epoch": 4.01,
"learning_rate": 1.0995931021119939e-05,
"loss": 0.2393,
"step": 4600
},
{
"epoch": 4.01,
"learning_rate": 1.0947490796357296e-05,
"loss": 0.2032,
"step": 4605
},
{
"epoch": 4.02,
"learning_rate": 1.0899050571594653e-05,
"loss": 0.2769,
"step": 4610
},
{
"epoch": 4.02,
"learning_rate": 1.085061034683201e-05,
"loss": 0.2219,
"step": 4615
},
{
"epoch": 4.03,
"learning_rate": 1.0802170122069368e-05,
"loss": 0.2302,
"step": 4620
},
{
"epoch": 4.03,
"learning_rate": 1.0753729897306725e-05,
"loss": 0.2641,
"step": 4625
},
{
"epoch": 4.03,
"learning_rate": 1.0705289672544081e-05,
"loss": 0.2522,
"step": 4630
},
{
"epoch": 4.04,
"learning_rate": 1.0656849447781438e-05,
"loss": 0.2489,
"step": 4635
},
{
"epoch": 4.04,
"learning_rate": 1.0608409223018794e-05,
"loss": 0.2271,
"step": 4640
},
{
"epoch": 4.05,
"learning_rate": 1.0559968998256151e-05,
"loss": 0.2463,
"step": 4645
},
{
"epoch": 4.05,
"learning_rate": 1.0511528773493509e-05,
"loss": 0.2225,
"step": 4650
},
{
"epoch": 4.06,
"learning_rate": 1.0463088548730866e-05,
"loss": 0.2203,
"step": 4655
},
{
"epoch": 4.06,
"learning_rate": 1.0414648323968223e-05,
"loss": 0.2425,
"step": 4660
},
{
"epoch": 4.06,
"learning_rate": 1.036620809920558e-05,
"loss": 0.2398,
"step": 4665
},
{
"epoch": 4.07,
"learning_rate": 1.0317767874442938e-05,
"loss": 0.2602,
"step": 4670
},
{
"epoch": 4.07,
"learning_rate": 1.0269327649680295e-05,
"loss": 0.2231,
"step": 4675
},
{
"epoch": 4.08,
"learning_rate": 1.0220887424917653e-05,
"loss": 0.2309,
"step": 4680
},
{
"epoch": 4.08,
"learning_rate": 1.017244720015501e-05,
"loss": 0.203,
"step": 4685
},
{
"epoch": 4.09,
"learning_rate": 1.0124006975392367e-05,
"loss": 0.2328,
"step": 4690
},
{
"epoch": 4.09,
"learning_rate": 1.0075566750629725e-05,
"loss": 0.246,
"step": 4695
},
{
"epoch": 4.09,
"learning_rate": 1.002712652586708e-05,
"loss": 0.2183,
"step": 4700
},
{
"epoch": 4.1,
"learning_rate": 9.978686301104437e-06,
"loss": 0.2706,
"step": 4705
},
{
"epoch": 4.1,
"learning_rate": 9.930246076341795e-06,
"loss": 0.2341,
"step": 4710
},
{
"epoch": 4.11,
"learning_rate": 9.88180585157915e-06,
"loss": 0.2424,
"step": 4715
},
{
"epoch": 4.11,
"learning_rate": 9.833365626816508e-06,
"loss": 0.2339,
"step": 4720
},
{
"epoch": 4.12,
"learning_rate": 9.784925402053865e-06,
"loss": 0.2488,
"step": 4725
},
{
"epoch": 4.12,
"learning_rate": 9.736485177291222e-06,
"loss": 0.2365,
"step": 4730
},
{
"epoch": 4.13,
"learning_rate": 9.68804495252858e-06,
"loss": 0.2708,
"step": 4735
},
{
"epoch": 4.13,
"learning_rate": 9.639604727765937e-06,
"loss": 0.2019,
"step": 4740
},
{
"epoch": 4.13,
"learning_rate": 9.591164503003294e-06,
"loss": 0.2367,
"step": 4745
},
{
"epoch": 4.14,
"learning_rate": 9.542724278240652e-06,
"loss": 0.2955,
"step": 4750
},
{
"epoch": 4.14,
"learning_rate": 9.494284053478009e-06,
"loss": 0.2416,
"step": 4755
},
{
"epoch": 4.15,
"learning_rate": 9.445843828715366e-06,
"loss": 0.2161,
"step": 4760
},
{
"epoch": 4.15,
"learning_rate": 9.397403603952724e-06,
"loss": 0.217,
"step": 4765
},
{
"epoch": 4.16,
"learning_rate": 9.348963379190081e-06,
"loss": 0.2444,
"step": 4770
},
{
"epoch": 4.16,
"learning_rate": 9.300523154427437e-06,
"loss": 0.2552,
"step": 4775
},
{
"epoch": 4.16,
"learning_rate": 9.252082929664794e-06,
"loss": 0.2619,
"step": 4780
},
{
"epoch": 4.17,
"learning_rate": 9.203642704902151e-06,
"loss": 0.2536,
"step": 4785
},
{
"epoch": 4.17,
"learning_rate": 9.155202480139509e-06,
"loss": 0.2801,
"step": 4790
},
{
"epoch": 4.18,
"learning_rate": 9.106762255376864e-06,
"loss": 0.2041,
"step": 4795
},
{
"epoch": 4.18,
"learning_rate": 9.058322030614222e-06,
"loss": 0.2553,
"step": 4800
},
{
"epoch": 4.19,
"learning_rate": 9.009881805851579e-06,
"loss": 0.2731,
"step": 4805
},
{
"epoch": 4.19,
"learning_rate": 8.961441581088936e-06,
"loss": 0.2556,
"step": 4810
},
{
"epoch": 4.2,
"learning_rate": 8.913001356326293e-06,
"loss": 0.2234,
"step": 4815
},
{
"epoch": 4.2,
"learning_rate": 8.86456113156365e-06,
"loss": 0.2173,
"step": 4820
},
{
"epoch": 4.2,
"learning_rate": 8.816120906801008e-06,
"loss": 0.1825,
"step": 4825
},
{
"epoch": 4.21,
"learning_rate": 8.767680682038365e-06,
"loss": 0.2473,
"step": 4830
},
{
"epoch": 4.21,
"learning_rate": 8.719240457275723e-06,
"loss": 0.2573,
"step": 4835
},
{
"epoch": 4.22,
"learning_rate": 8.67080023251308e-06,
"loss": 0.2639,
"step": 4840
},
{
"epoch": 4.22,
"learning_rate": 8.622360007750436e-06,
"loss": 0.2657,
"step": 4845
},
{
"epoch": 4.23,
"learning_rate": 8.573919782987793e-06,
"loss": 0.2369,
"step": 4850
},
{
"epoch": 4.23,
"learning_rate": 8.52547955822515e-06,
"loss": 0.2444,
"step": 4855
},
{
"epoch": 4.23,
"learning_rate": 8.477039333462508e-06,
"loss": 0.2526,
"step": 4860
},
{
"epoch": 4.24,
"learning_rate": 8.428599108699865e-06,
"loss": 0.2296,
"step": 4865
},
{
"epoch": 4.24,
"learning_rate": 8.380158883937222e-06,
"loss": 0.2737,
"step": 4870
},
{
"epoch": 4.25,
"learning_rate": 8.331718659174578e-06,
"loss": 0.2396,
"step": 4875
},
{
"epoch": 4.25,
"learning_rate": 8.283278434411935e-06,
"loss": 0.255,
"step": 4880
},
{
"epoch": 4.26,
"learning_rate": 8.234838209649293e-06,
"loss": 0.25,
"step": 4885
},
{
"epoch": 4.26,
"learning_rate": 8.18639798488665e-06,
"loss": 0.2356,
"step": 4890
},
{
"epoch": 4.26,
"learning_rate": 8.137957760124007e-06,
"loss": 0.2483,
"step": 4895
},
{
"epoch": 4.27,
"learning_rate": 8.089517535361365e-06,
"loss": 0.1909,
"step": 4900
},
{
"epoch": 4.27,
"learning_rate": 8.041077310598722e-06,
"loss": 0.2718,
"step": 4905
},
{
"epoch": 4.28,
"learning_rate": 7.99263708583608e-06,
"loss": 0.1832,
"step": 4910
},
{
"epoch": 4.28,
"learning_rate": 7.944196861073437e-06,
"loss": 0.202,
"step": 4915
},
{
"epoch": 4.29,
"learning_rate": 7.895756636310792e-06,
"loss": 0.1984,
"step": 4920
},
{
"epoch": 4.29,
"learning_rate": 7.84731641154815e-06,
"loss": 0.2228,
"step": 4925
},
{
"epoch": 4.3,
"learning_rate": 7.798876186785507e-06,
"loss": 0.2607,
"step": 4930
},
{
"epoch": 4.3,
"learning_rate": 7.750435962022864e-06,
"loss": 0.2531,
"step": 4935
},
{
"epoch": 4.3,
"learning_rate": 7.701995737260221e-06,
"loss": 0.2607,
"step": 4940
},
{
"epoch": 4.31,
"learning_rate": 7.653555512497579e-06,
"loss": 0.1789,
"step": 4945
},
{
"epoch": 4.31,
"learning_rate": 7.605115287734936e-06,
"loss": 0.2349,
"step": 4950
},
{
"epoch": 4.32,
"learning_rate": 7.556675062972293e-06,
"loss": 0.2391,
"step": 4955
},
{
"epoch": 4.32,
"learning_rate": 7.508234838209649e-06,
"loss": 0.2218,
"step": 4960
},
{
"epoch": 4.33,
"learning_rate": 7.459794613447006e-06,
"loss": 0.2189,
"step": 4965
},
{
"epoch": 4.33,
"learning_rate": 7.411354388684364e-06,
"loss": 0.2126,
"step": 4970
},
{
"epoch": 4.33,
"learning_rate": 7.36291416392172e-06,
"loss": 0.2859,
"step": 4975
},
{
"epoch": 4.34,
"learning_rate": 7.3144739391590775e-06,
"loss": 0.248,
"step": 4980
},
{
"epoch": 4.34,
"learning_rate": 7.266033714396435e-06,
"loss": 0.2377,
"step": 4985
},
{
"epoch": 4.35,
"learning_rate": 7.217593489633792e-06,
"loss": 0.2215,
"step": 4990
},
{
"epoch": 4.35,
"learning_rate": 7.1691532648711494e-06,
"loss": 0.2335,
"step": 4995
},
{
"epoch": 4.36,
"learning_rate": 7.120713040108507e-06,
"loss": 0.2288,
"step": 5000
},
{
"epoch": 4.36,
"learning_rate": 7.072272815345864e-06,
"loss": 0.2109,
"step": 5005
},
{
"epoch": 4.37,
"learning_rate": 7.0238325905832206e-06,
"loss": 0.2778,
"step": 5010
},
{
"epoch": 4.37,
"learning_rate": 6.975392365820578e-06,
"loss": 0.2011,
"step": 5015
},
{
"epoch": 4.37,
"learning_rate": 6.926952141057935e-06,
"loss": 0.2371,
"step": 5020
},
{
"epoch": 4.38,
"learning_rate": 6.8785119162952925e-06,
"loss": 0.2579,
"step": 5025
},
{
"epoch": 4.38,
"learning_rate": 6.83007169153265e-06,
"loss": 0.231,
"step": 5030
},
{
"epoch": 4.39,
"learning_rate": 6.781631466770007e-06,
"loss": 0.2492,
"step": 5035
},
{
"epoch": 4.39,
"learning_rate": 6.733191242007363e-06,
"loss": 0.2245,
"step": 5040
},
{
"epoch": 4.4,
"learning_rate": 6.68475101724472e-06,
"loss": 0.212,
"step": 5045
},
{
"epoch": 4.4,
"learning_rate": 6.636310792482077e-06,
"loss": 0.2368,
"step": 5050
},
{
"epoch": 4.4,
"learning_rate": 6.587870567719434e-06,
"loss": 0.2392,
"step": 5055
},
{
"epoch": 4.41,
"learning_rate": 6.539430342956791e-06,
"loss": 0.245,
"step": 5060
},
{
"epoch": 4.41,
"learning_rate": 6.4909901181941486e-06,
"loss": 0.237,
"step": 5065
},
{
"epoch": 4.42,
"learning_rate": 6.442549893431506e-06,
"loss": 0.2315,
"step": 5070
},
{
"epoch": 4.42,
"learning_rate": 6.394109668668863e-06,
"loss": 0.2275,
"step": 5075
},
{
"epoch": 4.43,
"learning_rate": 6.34566944390622e-06,
"loss": 0.2518,
"step": 5080
},
{
"epoch": 4.43,
"learning_rate": 6.297229219143577e-06,
"loss": 0.202,
"step": 5085
},
{
"epoch": 4.43,
"learning_rate": 6.248788994380934e-06,
"loss": 0.1873,
"step": 5090
},
{
"epoch": 4.44,
"learning_rate": 6.200348769618292e-06,
"loss": 0.2137,
"step": 5095
},
{
"epoch": 4.44,
"learning_rate": 6.151908544855649e-06,
"loss": 0.2415,
"step": 5100
},
{
"epoch": 4.45,
"learning_rate": 6.1034683200930054e-06,
"loss": 0.2454,
"step": 5105
},
{
"epoch": 4.45,
"learning_rate": 6.055028095330363e-06,
"loss": 0.2174,
"step": 5110
},
{
"epoch": 4.46,
"learning_rate": 6.006587870567719e-06,
"loss": 0.2009,
"step": 5115
},
{
"epoch": 4.46,
"learning_rate": 5.9581476458050766e-06,
"loss": 0.2038,
"step": 5120
},
{
"epoch": 4.47,
"learning_rate": 5.909707421042434e-06,
"loss": 0.2712,
"step": 5125
},
{
"epoch": 4.47,
"learning_rate": 5.861267196279791e-06,
"loss": 0.2162,
"step": 5130
},
{
"epoch": 4.47,
"learning_rate": 5.8128269715171485e-06,
"loss": 0.2107,
"step": 5135
},
{
"epoch": 4.48,
"learning_rate": 5.764386746754506e-06,
"loss": 0.2024,
"step": 5140
},
{
"epoch": 4.48,
"learning_rate": 5.715946521991862e-06,
"loss": 0.2117,
"step": 5145
},
{
"epoch": 4.49,
"learning_rate": 5.66750629722922e-06,
"loss": 0.2738,
"step": 5150
},
{
"epoch": 4.49,
"learning_rate": 5.619066072466576e-06,
"loss": 0.1896,
"step": 5155
},
{
"epoch": 4.5,
"learning_rate": 5.5706258477039334e-06,
"loss": 0.2247,
"step": 5160
},
{
"epoch": 4.5,
"learning_rate": 5.522185622941291e-06,
"loss": 0.2147,
"step": 5165
},
{
"epoch": 4.5,
"learning_rate": 5.473745398178648e-06,
"loss": 0.2535,
"step": 5170
},
{
"epoch": 4.51,
"learning_rate": 5.425305173416005e-06,
"loss": 0.2311,
"step": 5175
},
{
"epoch": 4.51,
"learning_rate": 5.376864948653363e-06,
"loss": 0.2176,
"step": 5180
},
{
"epoch": 4.52,
"learning_rate": 5.328424723890719e-06,
"loss": 0.223,
"step": 5185
},
{
"epoch": 4.52,
"learning_rate": 5.279984499128076e-06,
"loss": 0.2261,
"step": 5190
},
{
"epoch": 4.53,
"learning_rate": 5.231544274365433e-06,
"loss": 0.2274,
"step": 5195
},
{
"epoch": 4.53,
"learning_rate": 5.18310404960279e-06,
"loss": 0.2454,
"step": 5200
},
{
"epoch": 4.53,
"learning_rate": 5.134663824840148e-06,
"loss": 0.1954,
"step": 5205
},
{
"epoch": 4.54,
"learning_rate": 5.086223600077505e-06,
"loss": 0.235,
"step": 5210
},
{
"epoch": 4.54,
"learning_rate": 5.037783375314862e-06,
"loss": 0.211,
"step": 5215
},
{
"epoch": 4.55,
"learning_rate": 4.989343150552219e-06,
"loss": 0.2621,
"step": 5220
},
{
"epoch": 4.55,
"learning_rate": 4.940902925789575e-06,
"loss": 0.2052,
"step": 5225
},
{
"epoch": 4.56,
"learning_rate": 4.8924627010269325e-06,
"loss": 0.2374,
"step": 5230
},
{
"epoch": 4.56,
"learning_rate": 4.84402247626429e-06,
"loss": 0.2456,
"step": 5235
},
{
"epoch": 4.57,
"learning_rate": 4.795582251501647e-06,
"loss": 0.2255,
"step": 5240
},
{
"epoch": 4.57,
"learning_rate": 4.7471420267390045e-06,
"loss": 0.2346,
"step": 5245
},
{
"epoch": 4.57,
"learning_rate": 4.698701801976362e-06,
"loss": 0.2316,
"step": 5250
},
{
"epoch": 4.58,
"learning_rate": 4.650261577213718e-06,
"loss": 0.2274,
"step": 5255
},
{
"epoch": 4.58,
"learning_rate": 4.601821352451076e-06,
"loss": 0.2306,
"step": 5260
},
{
"epoch": 4.59,
"learning_rate": 4.553381127688432e-06,
"loss": 0.2307,
"step": 5265
},
{
"epoch": 4.59,
"learning_rate": 4.504940902925789e-06,
"loss": 0.2203,
"step": 5270
},
{
"epoch": 4.6,
"learning_rate": 4.456500678163147e-06,
"loss": 0.256,
"step": 5275
},
{
"epoch": 4.6,
"learning_rate": 4.408060453400504e-06,
"loss": 0.2345,
"step": 5280
},
{
"epoch": 4.6,
"learning_rate": 4.359620228637861e-06,
"loss": 0.1915,
"step": 5285
},
{
"epoch": 4.61,
"learning_rate": 4.311180003875218e-06,
"loss": 0.2929,
"step": 5290
},
{
"epoch": 4.61,
"learning_rate": 4.262739779112575e-06,
"loss": 0.2332,
"step": 5295
},
{
"epoch": 4.62,
"learning_rate": 4.2142995543499325e-06,
"loss": 0.2832,
"step": 5300
},
{
"epoch": 4.62,
"learning_rate": 4.165859329587289e-06,
"loss": 0.275,
"step": 5305
},
{
"epoch": 4.63,
"learning_rate": 4.117419104824646e-06,
"loss": 0.2151,
"step": 5310
},
{
"epoch": 4.63,
"learning_rate": 4.068978880062004e-06,
"loss": 0.2636,
"step": 5315
},
{
"epoch": 4.64,
"learning_rate": 4.020538655299361e-06,
"loss": 0.2243,
"step": 5320
},
{
"epoch": 4.64,
"learning_rate": 3.972098430536718e-06,
"loss": 0.2449,
"step": 5325
},
{
"epoch": 4.64,
"learning_rate": 3.923658205774075e-06,
"loss": 0.2025,
"step": 5330
},
{
"epoch": 4.65,
"learning_rate": 3.875217981011432e-06,
"loss": 0.2649,
"step": 5335
},
{
"epoch": 4.65,
"learning_rate": 3.826777756248789e-06,
"loss": 0.2332,
"step": 5340
},
{
"epoch": 4.66,
"learning_rate": 3.7783375314861467e-06,
"loss": 0.2352,
"step": 5345
},
{
"epoch": 4.66,
"learning_rate": 3.729897306723503e-06,
"loss": 0.2582,
"step": 5350
},
{
"epoch": 4.67,
"learning_rate": 3.68145708196086e-06,
"loss": 0.2151,
"step": 5355
},
{
"epoch": 4.67,
"learning_rate": 3.6330168571982174e-06,
"loss": 0.2044,
"step": 5360
},
{
"epoch": 4.67,
"learning_rate": 3.5845766324355747e-06,
"loss": 0.2433,
"step": 5365
},
{
"epoch": 4.68,
"learning_rate": 3.536136407672932e-06,
"loss": 0.1951,
"step": 5370
},
{
"epoch": 4.68,
"learning_rate": 3.487696182910289e-06,
"loss": 0.2756,
"step": 5375
},
{
"epoch": 4.69,
"learning_rate": 3.4392559581476463e-06,
"loss": 0.2865,
"step": 5380
},
{
"epoch": 4.69,
"learning_rate": 3.3908157333850036e-06,
"loss": 0.2148,
"step": 5385
},
{
"epoch": 4.7,
"learning_rate": 3.34237550862236e-06,
"loss": 0.2146,
"step": 5390
},
{
"epoch": 4.7,
"learning_rate": 3.293935283859717e-06,
"loss": 0.2075,
"step": 5395
},
{
"epoch": 4.7,
"learning_rate": 3.2454950590970743e-06,
"loss": 0.2403,
"step": 5400
},
{
"epoch": 4.71,
"learning_rate": 3.1970548343344316e-06,
"loss": 0.2394,
"step": 5405
},
{
"epoch": 4.71,
"learning_rate": 3.1486146095717885e-06,
"loss": 0.276,
"step": 5410
},
{
"epoch": 4.72,
"learning_rate": 3.100174384809146e-06,
"loss": 0.2727,
"step": 5415
},
{
"epoch": 4.72,
"learning_rate": 3.0517341600465027e-06,
"loss": 0.232,
"step": 5420
},
{
"epoch": 4.73,
"learning_rate": 3.0032939352838596e-06,
"loss": 0.2546,
"step": 5425
},
{
"epoch": 4.73,
"learning_rate": 2.954853710521217e-06,
"loss": 0.2274,
"step": 5430
},
{
"epoch": 4.74,
"learning_rate": 2.9064134857585743e-06,
"loss": 0.2036,
"step": 5435
},
{
"epoch": 4.74,
"learning_rate": 2.857973260995931e-06,
"loss": 0.2165,
"step": 5440
},
{
"epoch": 4.74,
"learning_rate": 2.809533036233288e-06,
"loss": 0.2413,
"step": 5445
},
{
"epoch": 4.75,
"learning_rate": 2.7610928114706454e-06,
"loss": 0.2182,
"step": 5450
},
{
"epoch": 4.75,
"learning_rate": 2.7126525867080027e-06,
"loss": 0.2114,
"step": 5455
},
{
"epoch": 4.76,
"learning_rate": 2.6642123619453596e-06,
"loss": 0.2239,
"step": 5460
},
{
"epoch": 4.76,
"learning_rate": 2.6157721371827165e-06,
"loss": 0.2688,
"step": 5465
},
{
"epoch": 4.77,
"learning_rate": 2.567331912420074e-06,
"loss": 0.2786,
"step": 5470
},
{
"epoch": 4.77,
"learning_rate": 2.518891687657431e-06,
"loss": 0.2299,
"step": 5475
},
{
"epoch": 4.77,
"learning_rate": 2.4704514628947876e-06,
"loss": 0.1905,
"step": 5480
},
{
"epoch": 4.78,
"learning_rate": 2.422011238132145e-06,
"loss": 0.2844,
"step": 5485
},
{
"epoch": 4.78,
"learning_rate": 2.3735710133695023e-06,
"loss": 0.2027,
"step": 5490
},
{
"epoch": 4.79,
"learning_rate": 2.325130788606859e-06,
"loss": 0.2105,
"step": 5495
},
{
"epoch": 4.79,
"learning_rate": 2.276690563844216e-06,
"loss": 0.2181,
"step": 5500
},
{
"epoch": 4.8,
"learning_rate": 2.2282503390815734e-06,
"loss": 0.2418,
"step": 5505
},
{
"epoch": 4.8,
"learning_rate": 2.1798101143189307e-06,
"loss": 0.2313,
"step": 5510
},
{
"epoch": 4.81,
"learning_rate": 2.1313698895562876e-06,
"loss": 0.222,
"step": 5515
},
{
"epoch": 4.81,
"learning_rate": 2.0829296647936445e-06,
"loss": 0.2446,
"step": 5520
},
{
"epoch": 4.81,
"learning_rate": 2.034489440031002e-06,
"loss": 0.1978,
"step": 5525
},
{
"epoch": 4.82,
"learning_rate": 1.986049215268359e-06,
"loss": 0.2033,
"step": 5530
},
{
"epoch": 4.82,
"learning_rate": 1.937608990505716e-06,
"loss": 0.2334,
"step": 5535
},
{
"epoch": 4.83,
"learning_rate": 1.8891687657430734e-06,
"loss": 0.196,
"step": 5540
},
{
"epoch": 4.83,
"learning_rate": 1.84072854098043e-06,
"loss": 0.2656,
"step": 5545
},
{
"epoch": 4.84,
"learning_rate": 1.7922883162177874e-06,
"loss": 0.2952,
"step": 5550
},
{
"epoch": 4.84,
"learning_rate": 1.7438480914551445e-06,
"loss": 0.198,
"step": 5555
},
{
"epoch": 4.84,
"learning_rate": 1.6954078666925018e-06,
"loss": 0.2646,
"step": 5560
},
{
"epoch": 4.85,
"learning_rate": 1.6469676419298585e-06,
"loss": 0.2238,
"step": 5565
},
{
"epoch": 4.85,
"learning_rate": 1.5985274171672158e-06,
"loss": 0.2172,
"step": 5570
},
{
"epoch": 4.86,
"learning_rate": 1.550087192404573e-06,
"loss": 0.2443,
"step": 5575
},
{
"epoch": 4.86,
"learning_rate": 1.5016469676419298e-06,
"loss": 0.2483,
"step": 5580
},
{
"epoch": 4.87,
"learning_rate": 1.4532067428792871e-06,
"loss": 0.2608,
"step": 5585
},
{
"epoch": 4.87,
"learning_rate": 1.404766518116644e-06,
"loss": 0.2074,
"step": 5590
},
{
"epoch": 4.87,
"learning_rate": 1.3563262933540013e-06,
"loss": 0.243,
"step": 5595
},
{
"epoch": 4.88,
"learning_rate": 1.3078860685913582e-06,
"loss": 0.2229,
"step": 5600
},
{
"epoch": 4.88,
"learning_rate": 1.2594458438287156e-06,
"loss": 0.1979,
"step": 5605
},
{
"epoch": 4.89,
"learning_rate": 1.2110056190660725e-06,
"loss": 0.2189,
"step": 5610
},
{
"epoch": 4.89,
"learning_rate": 1.1625653943034296e-06,
"loss": 0.2184,
"step": 5615
},
{
"epoch": 4.9,
"learning_rate": 1.1141251695407867e-06,
"loss": 0.2394,
"step": 5620
},
{
"epoch": 4.9,
"learning_rate": 1.0656849447781438e-06,
"loss": 0.1871,
"step": 5625
},
{
"epoch": 4.91,
"learning_rate": 1.017244720015501e-06,
"loss": 0.2337,
"step": 5630
},
{
"epoch": 4.91,
"learning_rate": 9.68804495252858e-07,
"loss": 0.2211,
"step": 5635
},
{
"epoch": 4.91,
"learning_rate": 9.20364270490215e-07,
"loss": 0.238,
"step": 5640
},
{
"epoch": 4.92,
"learning_rate": 8.719240457275722e-07,
"loss": 0.2422,
"step": 5645
},
{
"epoch": 4.92,
"learning_rate": 8.234838209649292e-07,
"loss": 0.2413,
"step": 5650
},
{
"epoch": 4.93,
"learning_rate": 7.750435962022865e-07,
"loss": 0.2388,
"step": 5655
},
{
"epoch": 4.93,
"learning_rate": 7.266033714396436e-07,
"loss": 0.2548,
"step": 5660
},
{
"epoch": 4.94,
"learning_rate": 6.781631466770007e-07,
"loss": 0.2092,
"step": 5665
},
{
"epoch": 4.94,
"learning_rate": 6.297229219143578e-07,
"loss": 0.2334,
"step": 5670
},
{
"epoch": 4.94,
"learning_rate": 5.812826971517148e-07,
"loss": 0.2486,
"step": 5675
},
{
"epoch": 4.95,
"learning_rate": 5.328424723890719e-07,
"loss": 0.1872,
"step": 5680
},
{
"epoch": 4.95,
"learning_rate": 4.84402247626429e-07,
"loss": 0.2143,
"step": 5685
},
{
"epoch": 4.96,
"learning_rate": 4.359620228637861e-07,
"loss": 0.2304,
"step": 5690
},
{
"epoch": 4.96,
"learning_rate": 3.8752179810114323e-07,
"loss": 0.1966,
"step": 5695
},
{
"epoch": 4.97,
"learning_rate": 3.3908157333850034e-07,
"loss": 0.2462,
"step": 5700
},
{
"epoch": 4.97,
"learning_rate": 2.906413485758574e-07,
"loss": 0.1794,
"step": 5705
},
{
"epoch": 4.97,
"learning_rate": 2.422011238132145e-07,
"loss": 0.2265,
"step": 5710
},
{
"epoch": 4.98,
"learning_rate": 1.9376089905057161e-07,
"loss": 0.1958,
"step": 5715
},
{
"epoch": 4.98,
"learning_rate": 1.453206742879287e-07,
"loss": 0.286,
"step": 5720
},
{
"epoch": 4.99,
"learning_rate": 9.688044952528581e-08,
"loss": 0.1954,
"step": 5725
},
{
"epoch": 4.99,
"learning_rate": 4.8440224762642903e-08,
"loss": 0.2226,
"step": 5730
},
{
"epoch": 5.0,
"learning_rate": 0.0,
"loss": 0.2324,
"step": 5735
},
{
"epoch": 5.0,
"eval_accuracy": 0.936588653351305,
"eval_loss": 0.19167460501194,
"eval_runtime": 33.2463,
"eval_samples_per_second": 490.942,
"eval_steps_per_second": 15.37,
"step": 5735
},
{
"epoch": 5.0,
"step": 5735,
"total_flos": 1.8247354653007872e+19,
"train_loss": 0.32012205235107943,
"train_runtime": 3716.3983,
"train_samples_per_second": 197.627,
"train_steps_per_second": 1.543
}
],
"logging_steps": 5,
"max_steps": 5735,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 1.8247354653007872e+19,
"trial_name": null,
"trial_params": null
}