Transformers
PyTorch
Graphcore
bert
Generated from Trainer
Inference Endpoints
bert-large-uncased / trainer_state.json
sergiopperez's picture
Update BERT large uncased checkpoint after running phase 1 (SL 128) and phase 2 (SL 512)
387585b
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.035964035964036,
"global_step": 2038,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.417624521072796e-05,
"loss": 3.9478,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.00010835249042145592,
"loss": 3.4956,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 0.00016252873563218388,
"loss": 3.5834,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 0.00021670498084291185,
"loss": 3.6582,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 0.00027088122605363983,
"loss": 3.6931,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 0.00032505747126436777,
"loss": 3.5358,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 0.00037923371647509576,
"loss": 3.4064,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 0.0004334099616858237,
"loss": 3.6459,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 0.00048758620689655173,
"loss": 3.537,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 0.0005417624521072797,
"loss": 3.5901,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 0.0005959386973180077,
"loss": 3.354,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 0.0006501149425287355,
"loss": 3.5718,
"step": 60
},
{
"epoch": 0.06,
"learning_rate": 0.0007042911877394635,
"loss": 3.4404,
"step": 65
},
{
"epoch": 0.07,
"learning_rate": 0.0007584674329501915,
"loss": 3.6794,
"step": 70
},
{
"epoch": 0.07,
"learning_rate": 0.0008126436781609194,
"loss": 3.4177,
"step": 75
},
{
"epoch": 0.08,
"learning_rate": 0.0008668199233716474,
"loss": 3.318,
"step": 80
},
{
"epoch": 0.08,
"learning_rate": 0.0009209961685823754,
"loss": 3.2787,
"step": 85
},
{
"epoch": 0.09,
"learning_rate": 0.0009751724137931035,
"loss": 3.4573,
"step": 90
},
{
"epoch": 0.09,
"learning_rate": 0.0010293486590038313,
"loss": 3.5262,
"step": 95
},
{
"epoch": 0.1,
"learning_rate": 0.0010835249042145593,
"loss": 3.5019,
"step": 100
},
{
"epoch": 0.1,
"learning_rate": 0.0011377011494252873,
"loss": 3.4242,
"step": 105
},
{
"epoch": 0.11,
"learning_rate": 0.0011918773946360153,
"loss": 3.321,
"step": 110
},
{
"epoch": 0.11,
"learning_rate": 0.0012460536398467433,
"loss": 3.2642,
"step": 115
},
{
"epoch": 0.12,
"learning_rate": 0.001300229885057471,
"loss": 3.4654,
"step": 120
},
{
"epoch": 0.12,
"learning_rate": 0.001354406130268199,
"loss": 3.5731,
"step": 125
},
{
"epoch": 0.13,
"learning_rate": 0.001408582375478927,
"loss": 3.5807,
"step": 130
},
{
"epoch": 0.13,
"learning_rate": 0.0014627586206896553,
"loss": 3.3095,
"step": 135
},
{
"epoch": 0.14,
"learning_rate": 0.001516934865900383,
"loss": 3.2068,
"step": 140
},
{
"epoch": 0.14,
"learning_rate": 0.001571111111111111,
"loss": 3.3576,
"step": 145
},
{
"epoch": 0.15,
"learning_rate": 0.0016252873563218388,
"loss": 3.1022,
"step": 150
},
{
"epoch": 0.15,
"learning_rate": 0.001679463601532567,
"loss": 3.3052,
"step": 155
},
{
"epoch": 0.16,
"learning_rate": 0.0017336398467432948,
"loss": 3.1333,
"step": 160
},
{
"epoch": 0.16,
"learning_rate": 0.001787816091954023,
"loss": 3.1107,
"step": 165
},
{
"epoch": 0.17,
"learning_rate": 0.0018419923371647507,
"loss": 3.2723,
"step": 170
},
{
"epoch": 0.17,
"learning_rate": 0.0018961685823754787,
"loss": 3.0396,
"step": 175
},
{
"epoch": 0.18,
"learning_rate": 0.001950344827586207,
"loss": 3.1269,
"step": 180
},
{
"epoch": 0.18,
"learning_rate": 0.0020045210727969347,
"loss": 3.4973,
"step": 185
},
{
"epoch": 0.19,
"learning_rate": 0.0020586973180076627,
"loss": 3.2676,
"step": 190
},
{
"epoch": 0.19,
"learning_rate": 0.0021128735632183907,
"loss": 2.7068,
"step": 195
},
{
"epoch": 0.2,
"learning_rate": 0.0021670498084291187,
"loss": 3.0751,
"step": 200
},
{
"epoch": 0.2,
"learning_rate": 0.0022212260536398467,
"loss": 3.0416,
"step": 205
},
{
"epoch": 0.21,
"learning_rate": 0.0022754022988505746,
"loss": 3.1006,
"step": 210
},
{
"epoch": 0.21,
"learning_rate": 0.002329578544061302,
"loss": 2.8475,
"step": 215
},
{
"epoch": 0.22,
"learning_rate": 0.0023837547892720306,
"loss": 3.1305,
"step": 220
},
{
"epoch": 0.22,
"learning_rate": 0.002437931034482758,
"loss": 3.0844,
"step": 225
},
{
"epoch": 0.23,
"learning_rate": 0.0024921072796934866,
"loss": 2.8136,
"step": 230
},
{
"epoch": 0.23,
"learning_rate": 0.0025462835249042146,
"loss": 2.9123,
"step": 235
},
{
"epoch": 0.24,
"learning_rate": 0.002600459770114942,
"loss": 3.0378,
"step": 240
},
{
"epoch": 0.24,
"learning_rate": 0.0026546360153256706,
"loss": 2.6106,
"step": 245
},
{
"epoch": 0.25,
"learning_rate": 0.002708812260536398,
"loss": 2.7494,
"step": 250
},
{
"epoch": 0.25,
"learning_rate": 0.002762988505747126,
"loss": 2.8047,
"step": 255
},
{
"epoch": 0.26,
"learning_rate": 0.002817164750957854,
"loss": 2.4465,
"step": 260
},
{
"epoch": 0.26,
"learning_rate": 0.002821634214969049,
"loss": 2.6294,
"step": 265
},
{
"epoch": 0.27,
"learning_rate": 0.00281367698368036,
"loss": 2.7954,
"step": 270
},
{
"epoch": 0.27,
"learning_rate": 0.002805719752391671,
"loss": 2.3837,
"step": 275
},
{
"epoch": 0.28,
"learning_rate": 0.0027977625211029825,
"loss": 2.0739,
"step": 280
},
{
"epoch": 0.28,
"learning_rate": 0.0027898052898142935,
"loss": 2.08,
"step": 285
},
{
"epoch": 0.29,
"learning_rate": 0.002781848058525605,
"loss": 2.2492,
"step": 290
},
{
"epoch": 0.29,
"learning_rate": 0.002773890827236916,
"loss": 1.9265,
"step": 295
},
{
"epoch": 0.3,
"learning_rate": 0.002765933595948227,
"loss": 1.9779,
"step": 300
},
{
"epoch": 0.3,
"learning_rate": 0.0027579763646595383,
"loss": 1.8238,
"step": 305
},
{
"epoch": 0.31,
"learning_rate": 0.0027500191333708493,
"loss": 1.6509,
"step": 310
},
{
"epoch": 0.31,
"learning_rate": 0.0027420619020821608,
"loss": 1.5633,
"step": 315
},
{
"epoch": 0.32,
"learning_rate": 0.0027341046707934718,
"loss": 1.5235,
"step": 320
},
{
"epoch": 0.32,
"learning_rate": 0.002726147439504783,
"loss": 1.4549,
"step": 325
},
{
"epoch": 0.33,
"learning_rate": 0.002718190208216094,
"loss": 1.4057,
"step": 330
},
{
"epoch": 0.33,
"learning_rate": 0.0027102329769274056,
"loss": 1.4699,
"step": 335
},
{
"epoch": 0.34,
"learning_rate": 0.002702275745638717,
"loss": 1.3995,
"step": 340
},
{
"epoch": 0.34,
"learning_rate": 0.002694318514350028,
"loss": 1.2831,
"step": 345
},
{
"epoch": 0.35,
"learning_rate": 0.002686361283061339,
"loss": 1.4057,
"step": 350
},
{
"epoch": 0.35,
"learning_rate": 0.0026784040517726505,
"loss": 1.3694,
"step": 355
},
{
"epoch": 0.36,
"learning_rate": 0.0026704468204839615,
"loss": 1.3262,
"step": 360
},
{
"epoch": 0.36,
"learning_rate": 0.002662489589195273,
"loss": 1.3559,
"step": 365
},
{
"epoch": 0.37,
"learning_rate": 0.002654532357906584,
"loss": 1.3316,
"step": 370
},
{
"epoch": 0.37,
"learning_rate": 0.002646575126617895,
"loss": 1.4259,
"step": 375
},
{
"epoch": 0.38,
"learning_rate": 0.0026386178953292064,
"loss": 1.3915,
"step": 380
},
{
"epoch": 0.38,
"learning_rate": 0.0026306606640405174,
"loss": 1.3454,
"step": 385
},
{
"epoch": 0.39,
"learning_rate": 0.002622703432751829,
"loss": 1.4387,
"step": 390
},
{
"epoch": 0.39,
"learning_rate": 0.00261474620146314,
"loss": 1.3051,
"step": 395
},
{
"epoch": 0.4,
"learning_rate": 0.002606788970174451,
"loss": 1.4805,
"step": 400
},
{
"epoch": 0.4,
"learning_rate": 0.0025988317388857623,
"loss": 1.4211,
"step": 405
},
{
"epoch": 0.41,
"learning_rate": 0.0025908745075970733,
"loss": 1.3394,
"step": 410
},
{
"epoch": 0.41,
"learning_rate": 0.0025829172763083847,
"loss": 1.4346,
"step": 415
},
{
"epoch": 0.42,
"learning_rate": 0.002574960045019696,
"loss": 1.4137,
"step": 420
},
{
"epoch": 0.42,
"learning_rate": 0.002567002813731007,
"loss": 1.407,
"step": 425
},
{
"epoch": 0.43,
"learning_rate": 0.0025590455824423186,
"loss": 1.4121,
"step": 430
},
{
"epoch": 0.43,
"learning_rate": 0.0025510883511536296,
"loss": 1.3267,
"step": 435
},
{
"epoch": 0.44,
"learning_rate": 0.002543131119864941,
"loss": 1.4152,
"step": 440
},
{
"epoch": 0.44,
"learning_rate": 0.002535173888576252,
"loss": 1.3324,
"step": 445
},
{
"epoch": 0.45,
"learning_rate": 0.002527216657287563,
"loss": 1.3688,
"step": 450
},
{
"epoch": 0.45,
"learning_rate": 0.0025192594259988745,
"loss": 1.4605,
"step": 455
},
{
"epoch": 0.46,
"learning_rate": 0.0025113021947101855,
"loss": 1.3467,
"step": 460
},
{
"epoch": 0.46,
"learning_rate": 0.002503344963421497,
"loss": 1.3955,
"step": 465
},
{
"epoch": 0.47,
"learning_rate": 0.002495387732132808,
"loss": 1.3075,
"step": 470
},
{
"epoch": 0.47,
"learning_rate": 0.002487430500844119,
"loss": 1.4311,
"step": 475
},
{
"epoch": 0.48,
"learning_rate": 0.0024794732695554303,
"loss": 1.454,
"step": 480
},
{
"epoch": 0.48,
"learning_rate": 0.0024715160382667413,
"loss": 1.422,
"step": 485
},
{
"epoch": 0.49,
"learning_rate": 0.0024635588069780528,
"loss": 1.2557,
"step": 490
},
{
"epoch": 0.49,
"learning_rate": 0.0024556015756893638,
"loss": 1.3965,
"step": 495
},
{
"epoch": 0.5,
"learning_rate": 0.002447644344400675,
"loss": 1.3865,
"step": 500
},
{
"epoch": 0.5,
"learning_rate": 0.002439687113111986,
"loss": 1.3908,
"step": 505
},
{
"epoch": 0.51,
"learning_rate": 0.0024317298818232976,
"loss": 1.349,
"step": 510
},
{
"epoch": 0.51,
"learning_rate": 0.0024237726505346086,
"loss": 1.2927,
"step": 515
},
{
"epoch": 0.52,
"learning_rate": 0.00241581541924592,
"loss": 1.3646,
"step": 520
},
{
"epoch": 0.52,
"learning_rate": 0.002407858187957231,
"loss": 1.3899,
"step": 525
},
{
"epoch": 0.53,
"learning_rate": 0.0023999009566685425,
"loss": 1.3826,
"step": 530
},
{
"epoch": 0.53,
"learning_rate": 0.0023919437253798535,
"loss": 1.3454,
"step": 535
},
{
"epoch": 0.54,
"learning_rate": 0.002383986494091165,
"loss": 1.2858,
"step": 540
},
{
"epoch": 0.54,
"learning_rate": 0.002376029262802476,
"loss": 1.3471,
"step": 545
},
{
"epoch": 0.55,
"learning_rate": 0.002368072031513787,
"loss": 1.3412,
"step": 550
},
{
"epoch": 0.55,
"learning_rate": 0.0023601148002250984,
"loss": 1.4073,
"step": 555
},
{
"epoch": 0.56,
"learning_rate": 0.0023521575689364094,
"loss": 1.4214,
"step": 560
},
{
"epoch": 0.56,
"learning_rate": 0.002344200337647721,
"loss": 1.3379,
"step": 565
},
{
"epoch": 0.57,
"learning_rate": 0.002336243106359032,
"loss": 1.4228,
"step": 570
},
{
"epoch": 0.57,
"learning_rate": 0.002328285875070343,
"loss": 1.433,
"step": 575
},
{
"epoch": 0.58,
"learning_rate": 0.0023203286437816543,
"loss": 1.3152,
"step": 580
},
{
"epoch": 0.58,
"learning_rate": 0.0023123714124929653,
"loss": 1.3381,
"step": 585
},
{
"epoch": 0.59,
"learning_rate": 0.0023044141812042767,
"loss": 1.3229,
"step": 590
},
{
"epoch": 0.59,
"learning_rate": 0.0022964569499155877,
"loss": 1.331,
"step": 595
},
{
"epoch": 0.6,
"learning_rate": 0.002288499718626899,
"loss": 1.3322,
"step": 600
},
{
"epoch": 0.6,
"learning_rate": 0.0022805424873382106,
"loss": 1.284,
"step": 605
},
{
"epoch": 0.61,
"learning_rate": 0.0022725852560495216,
"loss": 1.4003,
"step": 610
},
{
"epoch": 0.61,
"learning_rate": 0.002264628024760833,
"loss": 1.2798,
"step": 615
},
{
"epoch": 0.62,
"learning_rate": 0.002256670793472144,
"loss": 1.3699,
"step": 620
},
{
"epoch": 0.62,
"learning_rate": 0.002248713562183455,
"loss": 1.2648,
"step": 625
},
{
"epoch": 0.63,
"learning_rate": 0.0022407563308947664,
"loss": 1.2905,
"step": 630
},
{
"epoch": 0.63,
"learning_rate": 0.0022327990996060774,
"loss": 1.3432,
"step": 635
},
{
"epoch": 0.64,
"learning_rate": 0.002224841868317389,
"loss": 1.3604,
"step": 640
},
{
"epoch": 0.64,
"learning_rate": 0.0022168846370287,
"loss": 1.3513,
"step": 645
},
{
"epoch": 0.65,
"learning_rate": 0.002208927405740011,
"loss": 1.3222,
"step": 650
},
{
"epoch": 0.65,
"learning_rate": 0.0022009701744513223,
"loss": 1.4611,
"step": 655
},
{
"epoch": 0.66,
"learning_rate": 0.0021930129431626333,
"loss": 1.3717,
"step": 660
},
{
"epoch": 0.66,
"learning_rate": 0.0021850557118739448,
"loss": 1.3321,
"step": 665
},
{
"epoch": 0.67,
"learning_rate": 0.0021770984805852558,
"loss": 1.242,
"step": 670
},
{
"epoch": 0.67,
"learning_rate": 0.0021691412492965668,
"loss": 1.3239,
"step": 675
},
{
"epoch": 0.68,
"learning_rate": 0.002161184018007878,
"loss": 1.3978,
"step": 680
},
{
"epoch": 0.68,
"learning_rate": 0.0021532267867191896,
"loss": 1.3098,
"step": 685
},
{
"epoch": 0.69,
"learning_rate": 0.0021452695554305006,
"loss": 1.3272,
"step": 690
},
{
"epoch": 0.69,
"learning_rate": 0.002137312324141812,
"loss": 1.3465,
"step": 695
},
{
"epoch": 0.7,
"learning_rate": 0.002129355092853123,
"loss": 1.3863,
"step": 700
},
{
"epoch": 0.7,
"learning_rate": 0.0021213978615644345,
"loss": 1.2466,
"step": 705
},
{
"epoch": 0.71,
"learning_rate": 0.0021134406302757455,
"loss": 1.2819,
"step": 710
},
{
"epoch": 0.71,
"learning_rate": 0.002105483398987057,
"loss": 1.2984,
"step": 715
},
{
"epoch": 0.72,
"learning_rate": 0.002097526167698368,
"loss": 1.3937,
"step": 720
},
{
"epoch": 0.72,
"learning_rate": 0.002089568936409679,
"loss": 1.3559,
"step": 725
},
{
"epoch": 0.73,
"learning_rate": 0.0020816117051209904,
"loss": 1.3167,
"step": 730
},
{
"epoch": 0.73,
"learning_rate": 0.0020736544738323014,
"loss": 1.312,
"step": 735
},
{
"epoch": 0.74,
"learning_rate": 0.002065697242543613,
"loss": 1.4823,
"step": 740
},
{
"epoch": 0.74,
"learning_rate": 0.002057740011254924,
"loss": 1.3505,
"step": 745
},
{
"epoch": 0.75,
"learning_rate": 0.002049782779966235,
"loss": 1.3069,
"step": 750
},
{
"epoch": 0.75,
"learning_rate": 0.0020418255486775463,
"loss": 1.2876,
"step": 755
},
{
"epoch": 0.76,
"learning_rate": 0.0020338683173888573,
"loss": 1.3353,
"step": 760
},
{
"epoch": 0.76,
"learning_rate": 0.0020259110861001687,
"loss": 1.3717,
"step": 765
},
{
"epoch": 0.77,
"learning_rate": 0.0020179538548114797,
"loss": 1.3586,
"step": 770
},
{
"epoch": 0.77,
"learning_rate": 0.002009996623522791,
"loss": 1.3533,
"step": 775
},
{
"epoch": 0.78,
"learning_rate": 0.002002039392234102,
"loss": 1.237,
"step": 780
},
{
"epoch": 0.78,
"learning_rate": 0.0019940821609454136,
"loss": 1.2833,
"step": 785
},
{
"epoch": 0.79,
"learning_rate": 0.001986124929656725,
"loss": 1.3615,
"step": 790
},
{
"epoch": 0.79,
"learning_rate": 0.001978167698368036,
"loss": 1.461,
"step": 795
},
{
"epoch": 0.8,
"learning_rate": 0.001970210467079347,
"loss": 1.3725,
"step": 800
},
{
"epoch": 0.8,
"learning_rate": 0.0019622532357906584,
"loss": 1.2839,
"step": 805
},
{
"epoch": 0.81,
"learning_rate": 0.0019542960045019694,
"loss": 1.2933,
"step": 810
},
{
"epoch": 0.81,
"learning_rate": 0.0019463387732132809,
"loss": 1.2416,
"step": 815
},
{
"epoch": 0.82,
"learning_rate": 0.0019383815419245919,
"loss": 1.3515,
"step": 820
},
{
"epoch": 0.82,
"learning_rate": 0.0019304243106359029,
"loss": 1.2728,
"step": 825
},
{
"epoch": 0.83,
"learning_rate": 0.0019224670793472143,
"loss": 1.2913,
"step": 830
},
{
"epoch": 0.83,
"learning_rate": 0.0019145098480585253,
"loss": 1.2836,
"step": 835
},
{
"epoch": 0.84,
"learning_rate": 0.0019065526167698368,
"loss": 1.3717,
"step": 840
},
{
"epoch": 0.84,
"learning_rate": 0.0018985953854811478,
"loss": 1.2558,
"step": 845
},
{
"epoch": 0.85,
"learning_rate": 0.001890638154192459,
"loss": 1.3507,
"step": 850
},
{
"epoch": 0.85,
"learning_rate": 0.0018826809229037704,
"loss": 1.3441,
"step": 855
},
{
"epoch": 0.86,
"learning_rate": 0.0018747236916150814,
"loss": 1.307,
"step": 860
},
{
"epoch": 0.86,
"learning_rate": 0.0018667664603263928,
"loss": 1.3997,
"step": 865
},
{
"epoch": 0.87,
"learning_rate": 0.0018588092290377038,
"loss": 1.3367,
"step": 870
},
{
"epoch": 0.87,
"learning_rate": 0.0018508519977490148,
"loss": 1.3763,
"step": 875
},
{
"epoch": 0.88,
"learning_rate": 0.0018428947664603263,
"loss": 1.4019,
"step": 880
},
{
"epoch": 0.88,
"learning_rate": 0.0018349375351716373,
"loss": 1.1833,
"step": 885
},
{
"epoch": 0.89,
"learning_rate": 0.0018269803038829487,
"loss": 1.3296,
"step": 890
},
{
"epoch": 0.89,
"learning_rate": 0.00181902307259426,
"loss": 1.3258,
"step": 895
},
{
"epoch": 0.9,
"learning_rate": 0.001811065841305571,
"loss": 1.3643,
"step": 900
},
{
"epoch": 0.9,
"learning_rate": 0.0018031086100168824,
"loss": 1.3896,
"step": 905
},
{
"epoch": 0.91,
"learning_rate": 0.0017951513787281934,
"loss": 1.3775,
"step": 910
},
{
"epoch": 0.91,
"learning_rate": 0.0017871941474395048,
"loss": 1.3878,
"step": 915
},
{
"epoch": 0.92,
"learning_rate": 0.0017792369161508158,
"loss": 1.339,
"step": 920
},
{
"epoch": 0.92,
"learning_rate": 0.0017712796848621268,
"loss": 1.3225,
"step": 925
},
{
"epoch": 0.93,
"learning_rate": 0.0017633224535734382,
"loss": 1.2899,
"step": 930
},
{
"epoch": 0.93,
"learning_rate": 0.0017553652222847495,
"loss": 1.3449,
"step": 935
},
{
"epoch": 0.94,
"learning_rate": 0.0017474079909960607,
"loss": 1.3988,
"step": 940
},
{
"epoch": 0.94,
"learning_rate": 0.001739450759707372,
"loss": 1.2508,
"step": 945
},
{
"epoch": 0.95,
"learning_rate": 0.001731493528418683,
"loss": 1.2946,
"step": 950
},
{
"epoch": 0.95,
"learning_rate": 0.0017235362971299943,
"loss": 1.2393,
"step": 955
},
{
"epoch": 0.96,
"learning_rate": 0.0017155790658413053,
"loss": 1.3437,
"step": 960
},
{
"epoch": 0.96,
"learning_rate": 0.0017076218345526168,
"loss": 1.2589,
"step": 965
},
{
"epoch": 0.97,
"learning_rate": 0.0016996646032639278,
"loss": 1.3129,
"step": 970
},
{
"epoch": 0.97,
"learning_rate": 0.001691707371975239,
"loss": 1.3064,
"step": 975
},
{
"epoch": 0.98,
"learning_rate": 0.0016837501406865502,
"loss": 1.3121,
"step": 980
},
{
"epoch": 0.98,
"learning_rate": 0.0016757929093978614,
"loss": 1.316,
"step": 985
},
{
"epoch": 0.99,
"learning_rate": 0.0016678356781091727,
"loss": 1.3004,
"step": 990
},
{
"epoch": 0.99,
"learning_rate": 0.0016598784468204839,
"loss": 1.3423,
"step": 995
},
{
"epoch": 1.0,
"learning_rate": 0.0016519212155317949,
"loss": 1.2852,
"step": 1000
},
{
"epoch": 1.0,
"learning_rate": 0.0016439639842431063,
"loss": 1.3119,
"step": 1005
},
{
"epoch": 1.01,
"learning_rate": 0.0016360067529544173,
"loss": 1.2672,
"step": 1010
},
{
"epoch": 1.01,
"learning_rate": 0.0016280495216657287,
"loss": 1.2331,
"step": 1015
},
{
"epoch": 1.02,
"learning_rate": 0.0016200922903770397,
"loss": 1.2987,
"step": 1020
},
{
"epoch": 1.02,
"learning_rate": 0.001612135059088351,
"loss": 1.3455,
"step": 1025
},
{
"epoch": 1.03,
"learning_rate": 0.0016041778277996622,
"loss": 1.2899,
"step": 1030
},
{
"epoch": 1.03,
"learning_rate": 0.0015962205965109734,
"loss": 1.2729,
"step": 1035
},
{
"epoch": 1.04,
"learning_rate": 0.0015882633652222848,
"loss": 1.2688,
"step": 1040
},
{
"epoch": 1.04,
"learning_rate": 0.0015803061339335958,
"loss": 1.2367,
"step": 1045
},
{
"epoch": 1.05,
"learning_rate": 0.0015723489026449068,
"loss": 1.302,
"step": 1050
},
{
"epoch": 1.05,
"learning_rate": 0.0015643916713562183,
"loss": 1.3786,
"step": 1055
},
{
"epoch": 1.06,
"learning_rate": 0.0015564344400675293,
"loss": 1.2653,
"step": 1060
},
{
"epoch": 1.06,
"learning_rate": 0.0015484772087788407,
"loss": 1.2689,
"step": 1065
},
{
"epoch": 1.07,
"learning_rate": 0.0015405199774901517,
"loss": 1.2673,
"step": 1070
},
{
"epoch": 1.07,
"learning_rate": 0.001532562746201463,
"loss": 1.261,
"step": 1075
},
{
"epoch": 1.08,
"learning_rate": 0.0015246055149127744,
"loss": 1.1957,
"step": 1080
},
{
"epoch": 1.08,
"learning_rate": 0.0015166482836240854,
"loss": 1.4158,
"step": 1085
},
{
"epoch": 1.09,
"learning_rate": 0.0015086910523353968,
"loss": 1.1961,
"step": 1090
},
{
"epoch": 1.09,
"learning_rate": 0.0015007338210467078,
"loss": 1.3019,
"step": 1095
},
{
"epoch": 1.1,
"learning_rate": 0.0014927765897580188,
"loss": 1.2551,
"step": 1100
},
{
"epoch": 1.1,
"learning_rate": 0.0014848193584693302,
"loss": 1.2763,
"step": 1105
},
{
"epoch": 1.11,
"learning_rate": 0.0014768621271806412,
"loss": 1.2999,
"step": 1110
},
{
"epoch": 1.11,
"learning_rate": 0.0014689048958919527,
"loss": 1.2929,
"step": 1115
},
{
"epoch": 1.12,
"learning_rate": 0.001460947664603264,
"loss": 1.2321,
"step": 1120
},
{
"epoch": 1.12,
"learning_rate": 0.001452990433314575,
"loss": 1.3635,
"step": 1125
},
{
"epoch": 1.13,
"learning_rate": 0.0014450332020258863,
"loss": 1.2883,
"step": 1130
},
{
"epoch": 1.13,
"learning_rate": 0.0014370759707371973,
"loss": 1.3663,
"step": 1135
},
{
"epoch": 1.14,
"learning_rate": 0.0014291187394485088,
"loss": 1.268,
"step": 1140
},
{
"epoch": 1.14,
"learning_rate": 0.0014211615081598198,
"loss": 1.2976,
"step": 1145
},
{
"epoch": 1.15,
"learning_rate": 0.001413204276871131,
"loss": 1.3624,
"step": 1150
},
{
"epoch": 1.15,
"learning_rate": 0.0014052470455824422,
"loss": 1.3659,
"step": 1155
},
{
"epoch": 1.16,
"learning_rate": 0.0013972898142937534,
"loss": 1.2711,
"step": 1160
},
{
"epoch": 1.16,
"learning_rate": 0.0013893325830050646,
"loss": 1.2882,
"step": 1165
},
{
"epoch": 1.17,
"learning_rate": 0.0013813753517163759,
"loss": 1.321,
"step": 1170
},
{
"epoch": 1.17,
"learning_rate": 0.001373418120427687,
"loss": 1.3505,
"step": 1175
},
{
"epoch": 1.18,
"learning_rate": 0.0013654608891389983,
"loss": 1.2967,
"step": 1180
},
{
"epoch": 1.18,
"learning_rate": 0.0013575036578503093,
"loss": 1.2868,
"step": 1185
},
{
"epoch": 1.19,
"learning_rate": 0.0013495464265616205,
"loss": 1.2786,
"step": 1190
},
{
"epoch": 1.19,
"learning_rate": 0.0013415891952729317,
"loss": 1.2839,
"step": 1195
},
{
"epoch": 1.2,
"learning_rate": 0.001333631963984243,
"loss": 1.309,
"step": 1200
},
{
"epoch": 1.2,
"learning_rate": 0.0013256747326955542,
"loss": 1.3182,
"step": 1205
},
{
"epoch": 1.21,
"learning_rate": 0.0013177175014068654,
"loss": 1.3086,
"step": 1210
},
{
"epoch": 1.21,
"learning_rate": 0.0013097602701181766,
"loss": 1.189,
"step": 1215
},
{
"epoch": 1.22,
"learning_rate": 0.0013018030388294878,
"loss": 1.3253,
"step": 1220
},
{
"epoch": 1.22,
"learning_rate": 0.001293845807540799,
"loss": 1.2408,
"step": 1225
},
{
"epoch": 1.23,
"learning_rate": 0.0012858885762521103,
"loss": 1.3168,
"step": 1230
},
{
"epoch": 1.23,
"learning_rate": 0.0012779313449634215,
"loss": 1.2883,
"step": 1235
},
{
"epoch": 1.24,
"learning_rate": 0.0012699741136747325,
"loss": 1.3386,
"step": 1240
},
{
"epoch": 1.24,
"learning_rate": 0.0012620168823860437,
"loss": 1.4053,
"step": 1245
},
{
"epoch": 1.25,
"learning_rate": 0.001254059651097355,
"loss": 1.2768,
"step": 1250
},
{
"epoch": 1.25,
"learning_rate": 0.0012461024198086661,
"loss": 1.2946,
"step": 1255
},
{
"epoch": 1.26,
"learning_rate": 0.0012381451885199776,
"loss": 1.1944,
"step": 1260
},
{
"epoch": 1.26,
"learning_rate": 0.0012301879572312886,
"loss": 1.1929,
"step": 1265
},
{
"epoch": 1.27,
"learning_rate": 0.0012222307259425998,
"loss": 1.3793,
"step": 1270
},
{
"epoch": 1.27,
"learning_rate": 0.001214273494653911,
"loss": 1.2986,
"step": 1275
},
{
"epoch": 1.28,
"learning_rate": 0.0012063162633652222,
"loss": 1.3376,
"step": 1280
},
{
"epoch": 1.28,
"learning_rate": 0.0011983590320765335,
"loss": 1.2406,
"step": 1285
},
{
"epoch": 1.29,
"learning_rate": 0.0011904018007878445,
"loss": 1.3542,
"step": 1290
},
{
"epoch": 1.29,
"learning_rate": 0.0011824445694991557,
"loss": 1.3042,
"step": 1295
},
{
"epoch": 1.3,
"learning_rate": 0.001174487338210467,
"loss": 1.3189,
"step": 1300
},
{
"epoch": 1.3,
"learning_rate": 0.0011665301069217783,
"loss": 1.2538,
"step": 1305
},
{
"epoch": 1.31,
"learning_rate": 0.0011585728756330895,
"loss": 1.3152,
"step": 1310
},
{
"epoch": 1.31,
"learning_rate": 0.0011506156443444005,
"loss": 1.2528,
"step": 1315
},
{
"epoch": 1.32,
"learning_rate": 0.0011426584130557118,
"loss": 1.2752,
"step": 1320
},
{
"epoch": 1.32,
"learning_rate": 0.001134701181767023,
"loss": 1.3363,
"step": 1325
},
{
"epoch": 1.33,
"learning_rate": 0.0011267439504783342,
"loss": 1.2964,
"step": 1330
},
{
"epoch": 1.33,
"learning_rate": 0.0011187867191896454,
"loss": 1.2031,
"step": 1335
},
{
"epoch": 1.34,
"learning_rate": 0.0011108294879009564,
"loss": 1.3499,
"step": 1340
},
{
"epoch": 1.34,
"learning_rate": 0.0011028722566122679,
"loss": 1.2842,
"step": 1345
},
{
"epoch": 1.35,
"learning_rate": 0.001094915025323579,
"loss": 1.2108,
"step": 1350
},
{
"epoch": 1.35,
"learning_rate": 0.0010869577940348903,
"loss": 1.3822,
"step": 1355
},
{
"epoch": 1.36,
"learning_rate": 0.0010790005627462015,
"loss": 1.303,
"step": 1360
},
{
"epoch": 1.36,
"learning_rate": 0.0010710433314575125,
"loss": 1.25,
"step": 1365
},
{
"epoch": 1.37,
"learning_rate": 0.0010630861001688237,
"loss": 1.2506,
"step": 1370
},
{
"epoch": 1.37,
"learning_rate": 0.001055128868880135,
"loss": 1.3144,
"step": 1375
},
{
"epoch": 1.38,
"learning_rate": 0.0010471716375914462,
"loss": 1.3205,
"step": 1380
},
{
"epoch": 1.38,
"learning_rate": 0.0010392144063027574,
"loss": 1.1656,
"step": 1385
},
{
"epoch": 1.39,
"learning_rate": 0.0010312571750140686,
"loss": 1.2727,
"step": 1390
},
{
"epoch": 1.39,
"learning_rate": 0.0010232999437253798,
"loss": 1.2887,
"step": 1395
},
{
"epoch": 1.4,
"learning_rate": 0.001015342712436691,
"loss": 1.2759,
"step": 1400
},
{
"epoch": 1.4,
"learning_rate": 0.0010073854811480023,
"loss": 1.2698,
"step": 1405
},
{
"epoch": 1.41,
"learning_rate": 0.0009994282498593135,
"loss": 1.3167,
"step": 1410
},
{
"epoch": 1.41,
"learning_rate": 0.0009914710185706245,
"loss": 1.2659,
"step": 1415
},
{
"epoch": 1.42,
"learning_rate": 0.0009835137872819357,
"loss": 1.2209,
"step": 1420
},
{
"epoch": 1.42,
"learning_rate": 0.000975556555993247,
"loss": 1.2778,
"step": 1425
},
{
"epoch": 1.43,
"learning_rate": 0.0009675993247045582,
"loss": 1.2276,
"step": 1430
},
{
"epoch": 1.43,
"learning_rate": 0.0009596420934158695,
"loss": 1.2704,
"step": 1435
},
{
"epoch": 1.44,
"learning_rate": 0.0009516848621271805,
"loss": 1.2859,
"step": 1440
},
{
"epoch": 1.44,
"learning_rate": 0.0009437276308384918,
"loss": 1.3544,
"step": 1445
},
{
"epoch": 1.45,
"learning_rate": 0.000935770399549803,
"loss": 1.2112,
"step": 1450
},
{
"epoch": 1.45,
"learning_rate": 0.0009278131682611142,
"loss": 1.2632,
"step": 1455
},
{
"epoch": 1.46,
"learning_rate": 0.0009198559369724254,
"loss": 1.2354,
"step": 1460
},
{
"epoch": 1.46,
"learning_rate": 0.0009118987056837366,
"loss": 1.2159,
"step": 1465
},
{
"epoch": 1.47,
"learning_rate": 0.0009039414743950478,
"loss": 1.2772,
"step": 1470
},
{
"epoch": 1.47,
"learning_rate": 0.000895984243106359,
"loss": 1.2689,
"step": 1475
},
{
"epoch": 1.48,
"learning_rate": 0.0008880270118176702,
"loss": 1.2522,
"step": 1480
},
{
"epoch": 1.48,
"learning_rate": 0.0008800697805289814,
"loss": 1.2642,
"step": 1485
},
{
"epoch": 1.49,
"learning_rate": 0.0008721125492402925,
"loss": 1.3123,
"step": 1490
},
{
"epoch": 1.49,
"learning_rate": 0.0008641553179516038,
"loss": 1.2526,
"step": 1495
},
{
"epoch": 1.5,
"learning_rate": 0.000856198086662915,
"loss": 1.3556,
"step": 1500
},
{
"epoch": 1.5,
"learning_rate": 0.0008482408553742262,
"loss": 1.1951,
"step": 1505
},
{
"epoch": 1.51,
"learning_rate": 0.0008402836240855374,
"loss": 1.3322,
"step": 1510
},
{
"epoch": 1.51,
"learning_rate": 0.0008323263927968485,
"loss": 1.2582,
"step": 1515
},
{
"epoch": 1.52,
"learning_rate": 0.0008243691615081597,
"loss": 1.3049,
"step": 1520
},
{
"epoch": 1.52,
"learning_rate": 0.000816411930219471,
"loss": 1.1639,
"step": 1525
},
{
"epoch": 1.53,
"learning_rate": 0.0008084546989307822,
"loss": 1.2385,
"step": 1530
},
{
"epoch": 1.53,
"learning_rate": 0.0008004974676420934,
"loss": 1.268,
"step": 1535
},
{
"epoch": 1.54,
"learning_rate": 0.0007925402363534045,
"loss": 1.2466,
"step": 1540
},
{
"epoch": 1.54,
"learning_rate": 0.0007845830050647157,
"loss": 1.2585,
"step": 1545
},
{
"epoch": 1.55,
"learning_rate": 0.000776625773776027,
"loss": 1.2781,
"step": 1550
},
{
"epoch": 1.55,
"learning_rate": 0.0007686685424873382,
"loss": 1.19,
"step": 1555
},
{
"epoch": 1.56,
"learning_rate": 0.0007607113111986494,
"loss": 1.2718,
"step": 1560
},
{
"epoch": 1.56,
"learning_rate": 0.0007527540799099605,
"loss": 1.2066,
"step": 1565
},
{
"epoch": 1.57,
"learning_rate": 0.0007447968486212717,
"loss": 1.2605,
"step": 1570
},
{
"epoch": 1.57,
"learning_rate": 0.0007368396173325829,
"loss": 1.2403,
"step": 1575
},
{
"epoch": 1.58,
"learning_rate": 0.0007288823860438941,
"loss": 1.3096,
"step": 1580
},
{
"epoch": 1.58,
"learning_rate": 0.0007209251547552054,
"loss": 1.152,
"step": 1585
},
{
"epoch": 1.59,
"learning_rate": 0.0007129679234665165,
"loss": 1.282,
"step": 1590
},
{
"epoch": 1.59,
"learning_rate": 0.0007050106921778277,
"loss": 1.2004,
"step": 1595
},
{
"epoch": 1.6,
"learning_rate": 0.0006970534608891389,
"loss": 1.2049,
"step": 1600
},
{
"epoch": 1.6,
"learning_rate": 0.0006890962296004501,
"loss": 1.1815,
"step": 1605
},
{
"epoch": 1.61,
"learning_rate": 0.0006811389983117614,
"loss": 1.1898,
"step": 1610
},
{
"epoch": 1.61,
"learning_rate": 0.0006731817670230726,
"loss": 1.244,
"step": 1615
},
{
"epoch": 1.62,
"learning_rate": 0.0006652245357343837,
"loss": 1.2229,
"step": 1620
},
{
"epoch": 1.62,
"learning_rate": 0.0006572673044456949,
"loss": 1.2084,
"step": 1625
},
{
"epoch": 1.63,
"learning_rate": 0.0006493100731570061,
"loss": 1.3129,
"step": 1630
},
{
"epoch": 1.63,
"learning_rate": 0.0006413528418683173,
"loss": 1.3901,
"step": 1635
},
{
"epoch": 1.64,
"learning_rate": 0.0006333956105796286,
"loss": 1.2896,
"step": 1640
},
{
"epoch": 1.64,
"learning_rate": 0.0006254383792909397,
"loss": 1.2866,
"step": 1645
},
{
"epoch": 1.65,
"learning_rate": 0.0006174811480022509,
"loss": 1.3251,
"step": 1650
},
{
"epoch": 1.65,
"learning_rate": 0.0006095239167135622,
"loss": 1.1864,
"step": 1655
},
{
"epoch": 1.66,
"learning_rate": 0.0006015666854248733,
"loss": 1.2127,
"step": 1660
},
{
"epoch": 1.66,
"learning_rate": 0.0005936094541361845,
"loss": 1.2944,
"step": 1665
},
{
"epoch": 1.67,
"learning_rate": 0.0005856522228474956,
"loss": 1.3106,
"step": 1670
},
{
"epoch": 1.67,
"learning_rate": 0.000577694991558807,
"loss": 1.3614,
"step": 1675
},
{
"epoch": 1.68,
"learning_rate": 0.0005697377602701182,
"loss": 1.2786,
"step": 1680
},
{
"epoch": 1.68,
"learning_rate": 0.0005617805289814293,
"loss": 1.2758,
"step": 1685
},
{
"epoch": 1.69,
"learning_rate": 0.0005538232976927405,
"loss": 1.31,
"step": 1690
},
{
"epoch": 1.69,
"learning_rate": 0.0005458660664040517,
"loss": 1.2246,
"step": 1695
},
{
"epoch": 1.7,
"learning_rate": 0.000537908835115363,
"loss": 1.2295,
"step": 1700
},
{
"epoch": 1.7,
"learning_rate": 0.0005299516038266742,
"loss": 1.2822,
"step": 1705
},
{
"epoch": 1.71,
"learning_rate": 0.0005219943725379853,
"loss": 1.2582,
"step": 1710
},
{
"epoch": 1.71,
"learning_rate": 0.0005140371412492965,
"loss": 1.1898,
"step": 1715
},
{
"epoch": 1.72,
"learning_rate": 0.0005060799099606077,
"loss": 1.2697,
"step": 1720
},
{
"epoch": 1.72,
"learning_rate": 0.0004981226786719189,
"loss": 1.2696,
"step": 1725
},
{
"epoch": 1.73,
"learning_rate": 0.0004901654473832302,
"loss": 1.2383,
"step": 1730
},
{
"epoch": 1.73,
"learning_rate": 0.0004822082160945413,
"loss": 1.2665,
"step": 1735
},
{
"epoch": 1.74,
"learning_rate": 0.00047425098480585254,
"loss": 1.3193,
"step": 1740
},
{
"epoch": 1.74,
"learning_rate": 0.0004662937535171637,
"loss": 1.2431,
"step": 1745
},
{
"epoch": 1.75,
"learning_rate": 0.0004583365222284749,
"loss": 1.2243,
"step": 1750
},
{
"epoch": 1.75,
"learning_rate": 0.00045037929093978614,
"loss": 1.2323,
"step": 1755
},
{
"epoch": 1.76,
"learning_rate": 0.0004424220596510973,
"loss": 1.3318,
"step": 1760
},
{
"epoch": 1.76,
"learning_rate": 0.0004344648283624085,
"loss": 1.2339,
"step": 1765
},
{
"epoch": 1.77,
"learning_rate": 0.0004265075970737197,
"loss": 1.3316,
"step": 1770
},
{
"epoch": 1.77,
"learning_rate": 0.0004185503657850309,
"loss": 1.2981,
"step": 1775
},
{
"epoch": 1.78,
"learning_rate": 0.00041059313449634213,
"loss": 1.1703,
"step": 1780
},
{
"epoch": 1.78,
"learning_rate": 0.0004026359032076533,
"loss": 1.2283,
"step": 1785
},
{
"epoch": 1.79,
"learning_rate": 0.0003946786719189645,
"loss": 1.2554,
"step": 1790
},
{
"epoch": 1.79,
"learning_rate": 0.00038672144063027573,
"loss": 1.3264,
"step": 1795
},
{
"epoch": 1.8,
"learning_rate": 0.0003787642093415869,
"loss": 1.2297,
"step": 1800
},
{
"epoch": 1.8,
"learning_rate": 0.0003708069780528981,
"loss": 1.3238,
"step": 1805
},
{
"epoch": 1.81,
"learning_rate": 0.0003628497467642093,
"loss": 1.2793,
"step": 1810
},
{
"epoch": 1.81,
"learning_rate": 0.0003548925154755205,
"loss": 1.2891,
"step": 1815
},
{
"epoch": 1.82,
"learning_rate": 0.0003469352841868317,
"loss": 1.2713,
"step": 1820
},
{
"epoch": 1.82,
"learning_rate": 0.0003389780528981429,
"loss": 1.218,
"step": 1825
},
{
"epoch": 1.83,
"learning_rate": 0.0003310208216094541,
"loss": 1.29,
"step": 1830
},
{
"epoch": 1.83,
"learning_rate": 0.0003230635903207653,
"loss": 1.2781,
"step": 1835
},
{
"epoch": 1.84,
"learning_rate": 0.00031510635903207653,
"loss": 1.2553,
"step": 1840
},
{
"epoch": 1.84,
"learning_rate": 0.0003071491277433877,
"loss": 1.3065,
"step": 1845
},
{
"epoch": 1.85,
"learning_rate": 0.0002991918964546989,
"loss": 1.2249,
"step": 1850
},
{
"epoch": 1.85,
"learning_rate": 0.0002912346651660101,
"loss": 1.1943,
"step": 1855
},
{
"epoch": 1.86,
"learning_rate": 0.0002832774338773213,
"loss": 1.3517,
"step": 1860
},
{
"epoch": 1.86,
"learning_rate": 0.0002753202025886325,
"loss": 1.2667,
"step": 1865
},
{
"epoch": 1.87,
"learning_rate": 0.0002673629712999437,
"loss": 1.2597,
"step": 1870
},
{
"epoch": 1.87,
"learning_rate": 0.0002594057400112549,
"loss": 1.2336,
"step": 1875
},
{
"epoch": 1.88,
"learning_rate": 0.0002514485087225661,
"loss": 1.1898,
"step": 1880
},
{
"epoch": 1.88,
"learning_rate": 0.0002434912774338773,
"loss": 1.1498,
"step": 1885
},
{
"epoch": 1.89,
"learning_rate": 0.0002355340461451885,
"loss": 1.2345,
"step": 1890
},
{
"epoch": 1.89,
"learning_rate": 0.0002275768148564997,
"loss": 1.2426,
"step": 1895
},
{
"epoch": 1.9,
"learning_rate": 0.00021961958356781088,
"loss": 1.256,
"step": 1900
},
{
"epoch": 1.9,
"learning_rate": 0.00021166235227912213,
"loss": 1.2133,
"step": 1905
},
{
"epoch": 1.91,
"learning_rate": 0.00020370512099043332,
"loss": 1.1982,
"step": 1910
},
{
"epoch": 1.91,
"learning_rate": 0.0001957478897017445,
"loss": 1.2487,
"step": 1915
},
{
"epoch": 1.92,
"learning_rate": 0.0001877906584130557,
"loss": 1.3181,
"step": 1920
},
{
"epoch": 1.92,
"learning_rate": 0.0001798334271243669,
"loss": 1.2821,
"step": 1925
},
{
"epoch": 1.93,
"learning_rate": 0.00017187619583567808,
"loss": 1.2304,
"step": 1930
},
{
"epoch": 1.93,
"learning_rate": 0.0001639189645469893,
"loss": 1.2659,
"step": 1935
},
{
"epoch": 1.94,
"learning_rate": 0.0001559617332583005,
"loss": 1.2992,
"step": 1940
},
{
"epoch": 1.94,
"learning_rate": 0.00014800450196961168,
"loss": 1.2244,
"step": 1945
},
{
"epoch": 1.95,
"learning_rate": 0.0001400472706809229,
"loss": 1.2843,
"step": 1950
},
{
"epoch": 1.95,
"learning_rate": 0.0001320900393922341,
"loss": 1.3562,
"step": 1955
},
{
"epoch": 1.96,
"learning_rate": 0.0001241328081035453,
"loss": 1.2034,
"step": 1960
},
{
"epoch": 1.96,
"learning_rate": 0.00011617557681485649,
"loss": 1.1652,
"step": 1965
},
{
"epoch": 1.97,
"learning_rate": 0.00010821834552616768,
"loss": 1.3189,
"step": 1970
},
{
"epoch": 1.97,
"learning_rate": 0.00010026111423747889,
"loss": 1.2199,
"step": 1975
},
{
"epoch": 1.98,
"learning_rate": 9.230388294879008e-05,
"loss": 1.2195,
"step": 1980
},
{
"epoch": 1.98,
"learning_rate": 8.434665166010128e-05,
"loss": 1.2418,
"step": 1985
},
{
"epoch": 1.99,
"learning_rate": 7.638942037141249e-05,
"loss": 1.2555,
"step": 1990
},
{
"epoch": 1.99,
"learning_rate": 6.843218908272369e-05,
"loss": 1.3079,
"step": 1995
},
{
"epoch": 2.0,
"learning_rate": 6.047495779403489e-05,
"loss": 1.2959,
"step": 2000
},
{
"epoch": 2.0,
"learning_rate": 5.251772650534609e-05,
"loss": 1.3329,
"step": 2005
},
{
"epoch": 2.01,
"learning_rate": 4.456049521665728e-05,
"loss": 1.2211,
"step": 2010
},
{
"epoch": 2.01,
"learning_rate": 3.660326392796848e-05,
"loss": 1.1615,
"step": 2015
},
{
"epoch": 2.02,
"learning_rate": 2.8646032639279683e-05,
"loss": 1.1695,
"step": 2020
},
{
"epoch": 2.02,
"learning_rate": 2.068880135059088e-05,
"loss": 1.1895,
"step": 2025
},
{
"epoch": 2.03,
"learning_rate": 1.2731570061902082e-05,
"loss": 1.2908,
"step": 2030
},
{
"epoch": 2.03,
"learning_rate": 4.7743387732132805e-06,
"loss": 1.2253,
"step": 2035
},
{
"epoch": 2.04,
"step": 2038,
"total_flos": 2.5582587482196332e+23,
"train_loss": 0.02294661615032911,
"train_runtime": 3034.1773,
"train_samples_per_second": 11004.826,
"train_steps_per_second": 0.672
}
],
"max_steps": 2038,
"num_train_epochs": 3,
"total_flos": 2.5582587482196332e+23,
"trial_name": null,
"trial_params": null
}