Transformers
PyTorch
Graphcore
English
groupbert
Generated from Trainer
Inference Endpoints
groupbert-base-uncased / trainer_state.json
Ivan Chelombiev
End of training
f91459b
raw
history blame
49.5 kB
{
"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": 0.0013736056394868903,
"loss": 1.4723,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.0019425717247145285,
"loss": 1.568,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 0.0023791547571544325,
"loss": 1.2706,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 0.0027472112789737805,
"loss": 1.3258,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 0.003071475584169756,
"loss": 1.2558,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 0.0033646329245522657,
"loss": 0.8074,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 0.0036342189215581556,
"loss": 1.4713,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 0.003885143449429057,
"loss": 1.2681,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 0.004120816918460671,
"loss": 1.2291,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 0.004343722427630694,
"loss": 1.306,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 0.004555734516094203,
"loss": 1.1953,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 0.004758309514308865,
"loss": 1.2176,
"step": 60
},
{
"epoch": 0.06,
"learning_rate": 0.0049526055654364855,
"loss": 1.2338,
"step": 65
},
{
"epoch": 0.07,
"learning_rate": 0.005139561687500467,
"loss": 1.381,
"step": 70
},
{
"epoch": 0.07,
"learning_rate": 0.005319951765989316,
"loss": 1.5546,
"step": 75
},
{
"epoch": 0.08,
"learning_rate": 0.005494422557947561,
"loss": 1.5126,
"step": 80
},
{
"epoch": 0.08,
"learning_rate": 0.005663521139548541,
"loss": 1.5132,
"step": 85
},
{
"epoch": 0.09,
"learning_rate": 0.005827715174143585,
"loss": 1.2736,
"step": 90
},
{
"epoch": 0.09,
"learning_rate": 0.005987408170800916,
"loss": 1.1807,
"step": 95
},
{
"epoch": 0.1,
"learning_rate": 0.006142951168339512,
"loss": 1.392,
"step": 100
},
{
"epoch": 0.1,
"learning_rate": 0.0062946518179668965,
"loss": 1.4068,
"step": 105
},
{
"epoch": 0.11,
"learning_rate": 0.0064427815392316505,
"loss": 1.2436,
"step": 110
},
{
"epoch": 0.11,
"learning_rate": 0.0065875812264513545,
"loss": 1.6382,
"step": 115
},
{
"epoch": 0.12,
"learning_rate": 0.006729265849104531,
"loss": 1.5855,
"step": 120
},
{
"epoch": 0.12,
"learning_rate": 0.006868028197434452,
"loss": 1.8619,
"step": 125
},
{
"epoch": 0.13,
"learning_rate": 0.007004041959724749,
"loss": 1.4162,
"step": 130
},
{
"epoch": 0.13,
"learning_rate": 0.007137464271463298,
"loss": 1.397,
"step": 135
},
{
"epoch": 0.14,
"learning_rate": 0.007268437843116311,
"loss": 1.376,
"step": 140
},
{
"epoch": 0.14,
"learning_rate": 0.0073970927486462865,
"loss": 1.5437,
"step": 145
},
{
"epoch": 0.15,
"learning_rate": 0.007523547938632788,
"loss": 1.8505,
"step": 150
},
{
"epoch": 0.15,
"learning_rate": 0.0076479125281174514,
"loss": 1.3138,
"step": 155
},
{
"epoch": 0.16,
"learning_rate": 0.007770286898858114,
"loss": 1.6157,
"step": 160
},
{
"epoch": 0.16,
"learning_rate": 0.00789076364767037,
"loss": 1.4061,
"step": 165
},
{
"epoch": 0.17,
"learning_rate": 0.008009428406336274,
"loss": 1.4829,
"step": 170
},
{
"epoch": 0.17,
"learning_rate": 0.008126360553720012,
"loss": 1.3897,
"step": 175
},
{
"epoch": 0.18,
"learning_rate": 0.008241633836921341,
"loss": 1.3801,
"step": 180
},
{
"epoch": 0.18,
"learning_rate": 0.008355316915277182,
"loss": 1.6133,
"step": 185
},
{
"epoch": 0.19,
"learning_rate": 0.008467473838610143,
"loss": 1.6826,
"step": 190
},
{
"epoch": 0.19,
"learning_rate": 0.008578164469184382,
"loss": 1.6101,
"step": 195
},
{
"epoch": 0.2,
"learning_rate": 0.008687444855261389,
"loss": 1.7164,
"step": 200
},
{
"epoch": 0.2,
"learning_rate": 0.008795367562872955,
"loss": 1.6603,
"step": 205
},
{
"epoch": 0.21,
"learning_rate": 0.008901981971385245,
"loss": 1.3604,
"step": 210
},
{
"epoch": 0.21,
"learning_rate": 0.009007334537569819,
"loss": 1.5517,
"step": 215
},
{
"epoch": 0.22,
"learning_rate": 0.009111469032188405,
"loss": 1.6048,
"step": 220
},
{
"epoch": 0.22,
"learning_rate": 0.009214426752509268,
"loss": 1.6281,
"step": 225
},
{
"epoch": 0.23,
"learning_rate": 0.009316246713681893,
"loss": 2.1204,
"step": 230
},
{
"epoch": 0.23,
"learning_rate": 0.009416965821485117,
"loss": 1.6439,
"step": 235
},
{
"epoch": 0.24,
"learning_rate": 0.00951661902861773,
"loss": 1.6982,
"step": 240
},
{
"epoch": 0.24,
"learning_rate": 0.009615239476408233,
"loss": 1.857,
"step": 245
},
{
"epoch": 0.25,
"learning_rate": 0.009712858623572643,
"loss": 1.5612,
"step": 250
},
{
"epoch": 0.25,
"learning_rate": 0.009809506363438459,
"loss": 1.4843,
"step": 255
},
{
"epoch": 0.26,
"learning_rate": 0.009905211130872971,
"loss": 1.81,
"step": 260
},
{
"epoch": 0.26,
"learning_rate": 0.01,
"loss": 1.5551,
"step": 265
},
{
"epoch": 0.27,
"learning_rate": 0.009971799492385787,
"loss": 1.8817,
"step": 270
},
{
"epoch": 0.27,
"learning_rate": 0.009943598984771575,
"loss": 1.7807,
"step": 275
},
{
"epoch": 0.28,
"learning_rate": 0.009915398477157361,
"loss": 1.7788,
"step": 280
},
{
"epoch": 0.28,
"learning_rate": 0.009887197969543148,
"loss": 1.9268,
"step": 285
},
{
"epoch": 0.29,
"learning_rate": 0.009858997461928934,
"loss": 1.767,
"step": 290
},
{
"epoch": 0.29,
"learning_rate": 0.00983079695431472,
"loss": 2.0681,
"step": 295
},
{
"epoch": 0.3,
"learning_rate": 0.009802596446700508,
"loss": 1.8078,
"step": 300
},
{
"epoch": 0.3,
"learning_rate": 0.009774395939086295,
"loss": 1.5819,
"step": 305
},
{
"epoch": 0.31,
"learning_rate": 0.009746195431472081,
"loss": 1.3608,
"step": 310
},
{
"epoch": 0.31,
"learning_rate": 0.00971799492385787,
"loss": 1.4035,
"step": 315
},
{
"epoch": 0.32,
"learning_rate": 0.009689794416243654,
"loss": 1.7838,
"step": 320
},
{
"epoch": 0.32,
"learning_rate": 0.009661593908629442,
"loss": 1.462,
"step": 325
},
{
"epoch": 0.33,
"learning_rate": 0.009633393401015228,
"loss": 1.8537,
"step": 330
},
{
"epoch": 0.33,
"learning_rate": 0.009605192893401015,
"loss": 1.6035,
"step": 335
},
{
"epoch": 0.34,
"learning_rate": 0.009576992385786803,
"loss": 1.7534,
"step": 340
},
{
"epoch": 0.34,
"learning_rate": 0.00954879187817259,
"loss": 1.5117,
"step": 345
},
{
"epoch": 0.35,
"learning_rate": 0.009520591370558376,
"loss": 1.6606,
"step": 350
},
{
"epoch": 0.35,
"learning_rate": 0.009492390862944162,
"loss": 2.2899,
"step": 355
},
{
"epoch": 0.36,
"learning_rate": 0.009464190355329949,
"loss": 1.6254,
"step": 360
},
{
"epoch": 0.36,
"learning_rate": 0.009435989847715737,
"loss": 1.7699,
"step": 365
},
{
"epoch": 0.37,
"learning_rate": 0.009407789340101523,
"loss": 1.5836,
"step": 370
},
{
"epoch": 0.37,
"learning_rate": 0.00937958883248731,
"loss": 1.9447,
"step": 375
},
{
"epoch": 0.38,
"learning_rate": 0.009351388324873098,
"loss": 1.7334,
"step": 380
},
{
"epoch": 0.38,
"learning_rate": 0.009323187817258882,
"loss": 1.5246,
"step": 385
},
{
"epoch": 0.39,
"learning_rate": 0.00929498730964467,
"loss": 1.7258,
"step": 390
},
{
"epoch": 0.39,
"learning_rate": 0.009266786802030457,
"loss": 1.6757,
"step": 395
},
{
"epoch": 0.4,
"learning_rate": 0.009238586294416243,
"loss": 1.7912,
"step": 400
},
{
"epoch": 0.4,
"learning_rate": 0.009210385786802031,
"loss": 1.8435,
"step": 405
},
{
"epoch": 0.41,
"learning_rate": 0.009182185279187818,
"loss": 2.0267,
"step": 410
},
{
"epoch": 0.41,
"learning_rate": 0.009153984771573604,
"loss": 1.6059,
"step": 415
},
{
"epoch": 0.42,
"learning_rate": 0.00912578426395939,
"loss": 1.7753,
"step": 420
},
{
"epoch": 0.42,
"learning_rate": 0.009097583756345177,
"loss": 1.988,
"step": 425
},
{
"epoch": 0.43,
"learning_rate": 0.009069383248730965,
"loss": 1.5201,
"step": 430
},
{
"epoch": 0.43,
"learning_rate": 0.009041182741116751,
"loss": 1.397,
"step": 435
},
{
"epoch": 0.44,
"learning_rate": 0.009012982233502538,
"loss": 1.7266,
"step": 440
},
{
"epoch": 0.44,
"learning_rate": 0.008984781725888326,
"loss": 1.6747,
"step": 445
},
{
"epoch": 0.45,
"learning_rate": 0.008956581218274112,
"loss": 1.5811,
"step": 450
},
{
"epoch": 0.45,
"learning_rate": 0.008928380710659899,
"loss": 1.4325,
"step": 455
},
{
"epoch": 0.46,
"learning_rate": 0.008900180203045685,
"loss": 1.9487,
"step": 460
},
{
"epoch": 0.46,
"learning_rate": 0.008871979695431471,
"loss": 1.4969,
"step": 465
},
{
"epoch": 0.47,
"learning_rate": 0.00884377918781726,
"loss": 1.6207,
"step": 470
},
{
"epoch": 0.47,
"learning_rate": 0.008815578680203046,
"loss": 1.9026,
"step": 475
},
{
"epoch": 0.48,
"learning_rate": 0.008787378172588832,
"loss": 1.6797,
"step": 480
},
{
"epoch": 0.48,
"learning_rate": 0.00875917766497462,
"loss": 1.5079,
"step": 485
},
{
"epoch": 0.49,
"learning_rate": 0.008730977157360405,
"loss": 1.5912,
"step": 490
},
{
"epoch": 0.49,
"learning_rate": 0.008702776649746193,
"loss": 1.706,
"step": 495
},
{
"epoch": 0.5,
"learning_rate": 0.00867457614213198,
"loss": 1.6559,
"step": 500
},
{
"epoch": 0.5,
"learning_rate": 0.008646375634517766,
"loss": 1.6109,
"step": 505
},
{
"epoch": 0.51,
"learning_rate": 0.008618175126903554,
"loss": 1.9024,
"step": 510
},
{
"epoch": 0.51,
"learning_rate": 0.00858997461928934,
"loss": 1.4508,
"step": 515
},
{
"epoch": 0.52,
"learning_rate": 0.008561774111675127,
"loss": 1.7011,
"step": 520
},
{
"epoch": 0.52,
"learning_rate": 0.008533573604060913,
"loss": 1.4233,
"step": 525
},
{
"epoch": 0.53,
"learning_rate": 0.0085053730964467,
"loss": 1.5886,
"step": 530
},
{
"epoch": 0.53,
"learning_rate": 0.008477172588832488,
"loss": 1.6088,
"step": 535
},
{
"epoch": 0.54,
"learning_rate": 0.008448972081218274,
"loss": 2.3507,
"step": 540
},
{
"epoch": 0.54,
"learning_rate": 0.00842077157360406,
"loss": 1.457,
"step": 545
},
{
"epoch": 0.55,
"learning_rate": 0.008392571065989849,
"loss": 1.7145,
"step": 550
},
{
"epoch": 0.55,
"learning_rate": 0.008364370558375635,
"loss": 1.6431,
"step": 555
},
{
"epoch": 0.56,
"learning_rate": 0.008336170050761421,
"loss": 1.6156,
"step": 560
},
{
"epoch": 0.56,
"learning_rate": 0.008307969543147208,
"loss": 1.4988,
"step": 565
},
{
"epoch": 0.57,
"learning_rate": 0.008279769035532994,
"loss": 1.6655,
"step": 570
},
{
"epoch": 0.57,
"learning_rate": 0.008251568527918782,
"loss": 1.3964,
"step": 575
},
{
"epoch": 0.58,
"learning_rate": 0.008223368020304569,
"loss": 1.5442,
"step": 580
},
{
"epoch": 0.58,
"learning_rate": 0.008195167512690355,
"loss": 1.576,
"step": 585
},
{
"epoch": 0.59,
"learning_rate": 0.008166967005076143,
"loss": 1.6838,
"step": 590
},
{
"epoch": 0.59,
"learning_rate": 0.008138766497461928,
"loss": 1.5472,
"step": 595
},
{
"epoch": 0.6,
"learning_rate": 0.008110565989847716,
"loss": 1.6603,
"step": 600
},
{
"epoch": 0.6,
"learning_rate": 0.008082365482233502,
"loss": 1.8896,
"step": 605
},
{
"epoch": 0.61,
"learning_rate": 0.008054164974619289,
"loss": 1.3879,
"step": 610
},
{
"epoch": 0.61,
"learning_rate": 0.008025964467005077,
"loss": 1.7506,
"step": 615
},
{
"epoch": 0.62,
"learning_rate": 0.007997763959390863,
"loss": 1.6107,
"step": 620
},
{
"epoch": 0.62,
"learning_rate": 0.00796956345177665,
"loss": 1.6015,
"step": 625
},
{
"epoch": 0.63,
"learning_rate": 0.007941362944162436,
"loss": 1.4905,
"step": 630
},
{
"epoch": 0.63,
"learning_rate": 0.007913162436548223,
"loss": 1.7908,
"step": 635
},
{
"epoch": 0.64,
"learning_rate": 0.00788496192893401,
"loss": 1.5734,
"step": 640
},
{
"epoch": 0.64,
"learning_rate": 0.007856761421319797,
"loss": 1.4382,
"step": 645
},
{
"epoch": 0.65,
"learning_rate": 0.007828560913705583,
"loss": 1.5483,
"step": 650
},
{
"epoch": 0.65,
"learning_rate": 0.00780036040609137,
"loss": 1.4697,
"step": 655
},
{
"epoch": 0.66,
"learning_rate": 0.007772159898477159,
"loss": 1.5878,
"step": 660
},
{
"epoch": 0.66,
"learning_rate": 0.007743959390862944,
"loss": 1.9756,
"step": 665
},
{
"epoch": 0.67,
"learning_rate": 0.007715758883248732,
"loss": 1.6656,
"step": 670
},
{
"epoch": 0.67,
"learning_rate": 0.007687558375634519,
"loss": 1.6744,
"step": 675
},
{
"epoch": 0.68,
"learning_rate": 0.007659357868020306,
"loss": 1.762,
"step": 680
},
{
"epoch": 0.68,
"learning_rate": 0.0076311573604060925,
"loss": 1.6982,
"step": 685
},
{
"epoch": 0.69,
"learning_rate": 0.007602956852791878,
"loss": 1.4908,
"step": 690
},
{
"epoch": 0.69,
"learning_rate": 0.007574756345177666,
"loss": 1.6065,
"step": 695
},
{
"epoch": 0.7,
"learning_rate": 0.0075465558375634526,
"loss": 1.2293,
"step": 700
},
{
"epoch": 0.7,
"learning_rate": 0.007518355329949239,
"loss": 1.6052,
"step": 705
},
{
"epoch": 0.71,
"learning_rate": 0.007490154822335025,
"loss": 1.3118,
"step": 710
},
{
"epoch": 0.71,
"learning_rate": 0.0074619543147208135,
"loss": 1.1742,
"step": 715
},
{
"epoch": 0.72,
"learning_rate": 0.0074337538071066,
"loss": 1.632,
"step": 720
},
{
"epoch": 0.72,
"learning_rate": 0.007405553299492385,
"loss": 1.6181,
"step": 725
},
{
"epoch": 0.73,
"learning_rate": 0.007377352791878174,
"loss": 1.6726,
"step": 730
},
{
"epoch": 0.73,
"learning_rate": 0.00734915228426396,
"loss": 1.5759,
"step": 735
},
{
"epoch": 0.74,
"learning_rate": 0.007320951776649747,
"loss": 1.3197,
"step": 740
},
{
"epoch": 0.74,
"learning_rate": 0.0072927512690355335,
"loss": 1.8665,
"step": 745
},
{
"epoch": 0.75,
"learning_rate": 0.007264550761421322,
"loss": 1.1938,
"step": 750
},
{
"epoch": 0.75,
"learning_rate": 0.007236350253807108,
"loss": 1.2782,
"step": 755
},
{
"epoch": 0.76,
"learning_rate": 0.0072081497461928936,
"loss": 1.6276,
"step": 760
},
{
"epoch": 0.76,
"learning_rate": 0.007179949238578682,
"loss": 1.5382,
"step": 765
},
{
"epoch": 0.77,
"learning_rate": 0.007151748730964467,
"loss": 1.5528,
"step": 770
},
{
"epoch": 0.77,
"learning_rate": 0.0071235482233502545,
"loss": 1.663,
"step": 775
},
{
"epoch": 0.78,
"learning_rate": 0.007095347715736042,
"loss": 1.5098,
"step": 780
},
{
"epoch": 0.78,
"learning_rate": 0.007067147208121828,
"loss": 1.781,
"step": 785
},
{
"epoch": 0.79,
"learning_rate": 0.007038946700507615,
"loss": 1.3787,
"step": 790
},
{
"epoch": 0.79,
"learning_rate": 0.007010746192893401,
"loss": 2.1853,
"step": 795
},
{
"epoch": 0.8,
"learning_rate": 0.006982545685279189,
"loss": 1.6639,
"step": 800
},
{
"epoch": 0.8,
"learning_rate": 0.006954345177664975,
"loss": 1.7152,
"step": 805
},
{
"epoch": 0.81,
"learning_rate": 0.006926144670050761,
"loss": 1.8148,
"step": 810
},
{
"epoch": 0.81,
"learning_rate": 0.006897944162436549,
"loss": 1.6564,
"step": 815
},
{
"epoch": 0.82,
"learning_rate": 0.0068697436548223354,
"loss": 1.3046,
"step": 820
},
{
"epoch": 0.82,
"learning_rate": 0.006841543147208123,
"loss": 1.3462,
"step": 825
},
{
"epoch": 0.83,
"learning_rate": 0.006813342639593909,
"loss": 1.4969,
"step": 830
},
{
"epoch": 0.83,
"learning_rate": 0.006785142131979697,
"loss": 1.7367,
"step": 835
},
{
"epoch": 0.84,
"learning_rate": 0.006756941624365483,
"loss": 1.5385,
"step": 840
},
{
"epoch": 0.84,
"learning_rate": 0.00672874111675127,
"loss": 1.5918,
"step": 845
},
{
"epoch": 0.85,
"learning_rate": 0.006700540609137057,
"loss": 1.4092,
"step": 850
},
{
"epoch": 0.85,
"learning_rate": 0.006672340101522844,
"loss": 1.6609,
"step": 855
},
{
"epoch": 0.86,
"learning_rate": 0.006644139593908631,
"loss": 1.6529,
"step": 860
},
{
"epoch": 0.86,
"learning_rate": 0.006615939086294417,
"loss": 2.0543,
"step": 865
},
{
"epoch": 0.87,
"learning_rate": 0.0065877385786802046,
"loss": 1.7507,
"step": 870
},
{
"epoch": 0.87,
"learning_rate": 0.00655953807106599,
"loss": 1.3364,
"step": 875
},
{
"epoch": 0.88,
"learning_rate": 0.0065313375634517765,
"loss": 1.5436,
"step": 880
},
{
"epoch": 0.88,
"learning_rate": 0.006503137055837565,
"loss": 1.5808,
"step": 885
},
{
"epoch": 0.89,
"learning_rate": 0.00647493654822335,
"loss": 1.1435,
"step": 890
},
{
"epoch": 0.89,
"learning_rate": 0.006446736040609138,
"loss": 1.7857,
"step": 895
},
{
"epoch": 0.9,
"learning_rate": 0.006418535532994924,
"loss": 1.506,
"step": 900
},
{
"epoch": 0.9,
"learning_rate": 0.006390335025380713,
"loss": 1.5276,
"step": 905
},
{
"epoch": 0.91,
"learning_rate": 0.006362134517766498,
"loss": 1.7656,
"step": 910
},
{
"epoch": 0.91,
"learning_rate": 0.006333934010152285,
"loss": 1.2465,
"step": 915
},
{
"epoch": 0.92,
"learning_rate": 0.006305733502538073,
"loss": 1.1414,
"step": 920
},
{
"epoch": 0.92,
"learning_rate": 0.006277532994923858,
"loss": 1.7263,
"step": 925
},
{
"epoch": 0.93,
"learning_rate": 0.0062493324873096456,
"loss": 1.6158,
"step": 930
},
{
"epoch": 0.93,
"learning_rate": 0.006221131979695433,
"loss": 1.3896,
"step": 935
},
{
"epoch": 0.94,
"learning_rate": 0.00619293147208122,
"loss": 1.8046,
"step": 940
},
{
"epoch": 0.94,
"learning_rate": 0.006164730964467006,
"loss": 1.6806,
"step": 945
},
{
"epoch": 0.95,
"learning_rate": 0.006136530456852793,
"loss": 1.7003,
"step": 950
},
{
"epoch": 0.95,
"learning_rate": 0.006108329949238579,
"loss": 1.4235,
"step": 955
},
{
"epoch": 0.96,
"learning_rate": 0.006080129441624366,
"loss": 1.5528,
"step": 960
},
{
"epoch": 0.96,
"learning_rate": 0.006051928934010154,
"loss": 1.6251,
"step": 965
},
{
"epoch": 0.97,
"learning_rate": 0.006023728426395939,
"loss": 1.7944,
"step": 970
},
{
"epoch": 0.97,
"learning_rate": 0.0059955279187817265,
"loss": 1.6361,
"step": 975
},
{
"epoch": 0.98,
"learning_rate": 0.005967327411167512,
"loss": 1.6142,
"step": 980
},
{
"epoch": 0.98,
"learning_rate": 0.0059391269035533,
"loss": 1.6014,
"step": 985
},
{
"epoch": 0.99,
"learning_rate": 0.005910926395939088,
"loss": 1.5756,
"step": 990
},
{
"epoch": 0.99,
"learning_rate": 0.005882725888324872,
"loss": 1.2877,
"step": 995
},
{
"epoch": 1.0,
"learning_rate": 0.005854525380710661,
"loss": 1.6494,
"step": 1000
},
{
"epoch": 1.0,
"learning_rate": 0.005826324873096447,
"loss": 1.4704,
"step": 1005
},
{
"epoch": 1.01,
"learning_rate": 0.005798124365482234,
"loss": 1.3735,
"step": 1010
},
{
"epoch": 1.01,
"learning_rate": 0.005769923857868021,
"loss": 1.3836,
"step": 1015
},
{
"epoch": 1.02,
"learning_rate": 0.005741723350253808,
"loss": 1.4496,
"step": 1020
},
{
"epoch": 1.02,
"learning_rate": 0.005713522842639595,
"loss": 1.4613,
"step": 1025
},
{
"epoch": 1.03,
"learning_rate": 0.00568532233502538,
"loss": 1.4161,
"step": 1030
},
{
"epoch": 1.03,
"learning_rate": 0.0056571218274111676,
"loss": 1.592,
"step": 1035
},
{
"epoch": 1.04,
"learning_rate": 0.005628921319796955,
"loss": 1.585,
"step": 1040
},
{
"epoch": 1.04,
"learning_rate": 0.005600720812182741,
"loss": 1.2444,
"step": 1045
},
{
"epoch": 1.05,
"learning_rate": 0.005572520304568528,
"loss": 1.3218,
"step": 1050
},
{
"epoch": 1.05,
"learning_rate": 0.005544319796954316,
"loss": 1.4106,
"step": 1055
},
{
"epoch": 1.06,
"learning_rate": 0.005516119289340102,
"loss": 1.6454,
"step": 1060
},
{
"epoch": 1.06,
"learning_rate": 0.005487918781725888,
"loss": 1.4884,
"step": 1065
},
{
"epoch": 1.07,
"learning_rate": 0.005459718274111677,
"loss": 1.387,
"step": 1070
},
{
"epoch": 1.07,
"learning_rate": 0.005431517766497462,
"loss": 1.5909,
"step": 1075
},
{
"epoch": 1.08,
"learning_rate": 0.005403317258883249,
"loss": 1.2899,
"step": 1080
},
{
"epoch": 1.08,
"learning_rate": 0.005375116751269036,
"loss": 1.2528,
"step": 1085
},
{
"epoch": 1.09,
"learning_rate": 0.005346916243654824,
"loss": 1.3185,
"step": 1090
},
{
"epoch": 1.09,
"learning_rate": 0.00531871573604061,
"loss": 1.751,
"step": 1095
},
{
"epoch": 1.1,
"learning_rate": 0.005290515228426396,
"loss": 1.2762,
"step": 1100
},
{
"epoch": 1.1,
"learning_rate": 0.005262314720812184,
"loss": 1.4006,
"step": 1105
},
{
"epoch": 1.11,
"learning_rate": 0.0052341142131979695,
"loss": 1.3565,
"step": 1110
},
{
"epoch": 1.11,
"learning_rate": 0.005205913705583757,
"loss": 1.7962,
"step": 1115
},
{
"epoch": 1.12,
"learning_rate": 0.005177713197969543,
"loss": 1.3809,
"step": 1120
},
{
"epoch": 1.12,
"learning_rate": 0.00514951269035533,
"loss": 1.6438,
"step": 1125
},
{
"epoch": 1.13,
"learning_rate": 0.005121312182741118,
"loss": 1.4397,
"step": 1130
},
{
"epoch": 1.13,
"learning_rate": 0.005093111675126903,
"loss": 1.8387,
"step": 1135
},
{
"epoch": 1.14,
"learning_rate": 0.005064911167512691,
"loss": 1.4722,
"step": 1140
},
{
"epoch": 1.14,
"learning_rate": 0.005036710659898478,
"loss": 1.6683,
"step": 1145
},
{
"epoch": 1.15,
"learning_rate": 0.005008510152284263,
"loss": 1.3579,
"step": 1150
},
{
"epoch": 1.15,
"learning_rate": 0.004980309644670051,
"loss": 1.4072,
"step": 1155
},
{
"epoch": 1.16,
"learning_rate": 0.004952109137055839,
"loss": 1.4808,
"step": 1160
},
{
"epoch": 1.16,
"learning_rate": 0.004923908629441625,
"loss": 1.37,
"step": 1165
},
{
"epoch": 1.17,
"learning_rate": 0.004895708121827412,
"loss": 1.4239,
"step": 1170
},
{
"epoch": 1.17,
"learning_rate": 0.004867507614213198,
"loss": 1.6803,
"step": 1175
},
{
"epoch": 1.18,
"learning_rate": 0.004839307106598985,
"loss": 1.3899,
"step": 1180
},
{
"epoch": 1.18,
"learning_rate": 0.004811106598984772,
"loss": 1.209,
"step": 1185
},
{
"epoch": 1.19,
"learning_rate": 0.004782906091370559,
"loss": 1.3444,
"step": 1190
},
{
"epoch": 1.19,
"learning_rate": 0.004754705583756346,
"loss": 1.5994,
"step": 1195
},
{
"epoch": 1.2,
"learning_rate": 0.004726505076142133,
"loss": 1.7138,
"step": 1200
},
{
"epoch": 1.2,
"learning_rate": 0.0046983045685279196,
"loss": 1.6732,
"step": 1205
},
{
"epoch": 1.21,
"learning_rate": 0.004670104060913706,
"loss": 1.6533,
"step": 1210
},
{
"epoch": 1.21,
"learning_rate": 0.004641903553299492,
"loss": 1.4821,
"step": 1215
},
{
"epoch": 1.22,
"learning_rate": 0.00461370304568528,
"loss": 1.9074,
"step": 1220
},
{
"epoch": 1.22,
"learning_rate": 0.004585502538071067,
"loss": 1.6595,
"step": 1225
},
{
"epoch": 1.23,
"learning_rate": 0.004557302030456853,
"loss": 1.5424,
"step": 1230
},
{
"epoch": 1.23,
"learning_rate": 0.0045291015228426405,
"loss": 1.669,
"step": 1235
},
{
"epoch": 1.24,
"learning_rate": 0.004500901015228428,
"loss": 1.7157,
"step": 1240
},
{
"epoch": 1.24,
"learning_rate": 0.004472700507614213,
"loss": 1.3508,
"step": 1245
},
{
"epoch": 1.25,
"learning_rate": 0.0044445000000000005,
"loss": 1.6086,
"step": 1250
},
{
"epoch": 1.25,
"learning_rate": 0.004416299492385787,
"loss": 2.1126,
"step": 1255
},
{
"epoch": 1.26,
"learning_rate": 0.004388098984771574,
"loss": 1.2235,
"step": 1260
},
{
"epoch": 1.26,
"learning_rate": 0.0043598984771573614,
"loss": 1.3403,
"step": 1265
},
{
"epoch": 1.27,
"learning_rate": 0.004331697969543148,
"loss": 1.4274,
"step": 1270
},
{
"epoch": 1.27,
"learning_rate": 0.004303497461928934,
"loss": 1.4858,
"step": 1275
},
{
"epoch": 1.28,
"learning_rate": 0.0042752969543147215,
"loss": 1.4251,
"step": 1280
},
{
"epoch": 1.28,
"learning_rate": 0.004247096446700508,
"loss": 1.2581,
"step": 1285
},
{
"epoch": 1.29,
"learning_rate": 0.004218895939086295,
"loss": 1.3023,
"step": 1290
},
{
"epoch": 1.29,
"learning_rate": 0.0041906954314720815,
"loss": 1.2824,
"step": 1295
},
{
"epoch": 1.3,
"learning_rate": 0.004162494923857869,
"loss": 1.6138,
"step": 1300
},
{
"epoch": 1.3,
"learning_rate": 0.004134294416243656,
"loss": 1.6641,
"step": 1305
},
{
"epoch": 1.31,
"learning_rate": 0.0041060939086294415,
"loss": 1.2635,
"step": 1310
},
{
"epoch": 1.31,
"learning_rate": 0.004077893401015229,
"loss": 1.5835,
"step": 1315
},
{
"epoch": 1.32,
"learning_rate": 0.004049692893401016,
"loss": 1.6182,
"step": 1320
},
{
"epoch": 1.32,
"learning_rate": 0.0040214923857868025,
"loss": 1.2402,
"step": 1325
},
{
"epoch": 1.33,
"learning_rate": 0.00399329187817259,
"loss": 1.6024,
"step": 1330
},
{
"epoch": 1.33,
"learning_rate": 0.003965091370558376,
"loss": 1.3873,
"step": 1335
},
{
"epoch": 1.34,
"learning_rate": 0.003936890862944163,
"loss": 1.5199,
"step": 1340
},
{
"epoch": 1.34,
"learning_rate": 0.00390869035532995,
"loss": 1.3065,
"step": 1345
},
{
"epoch": 1.35,
"learning_rate": 0.0038804898477157357,
"loss": 1.3709,
"step": 1350
},
{
"epoch": 1.35,
"learning_rate": 0.003852289340101523,
"loss": 1.5692,
"step": 1355
},
{
"epoch": 1.36,
"learning_rate": 0.0038240888324873098,
"loss": 1.2774,
"step": 1360
},
{
"epoch": 1.36,
"learning_rate": 0.003795888324873097,
"loss": 1.3966,
"step": 1365
},
{
"epoch": 1.37,
"learning_rate": 0.0037676878172588843,
"loss": 1.0405,
"step": 1370
},
{
"epoch": 1.37,
"learning_rate": 0.0037394873096446707,
"loss": 1.6305,
"step": 1375
},
{
"epoch": 1.38,
"learning_rate": 0.003711286802030457,
"loss": 1.3404,
"step": 1380
},
{
"epoch": 1.38,
"learning_rate": 0.0036830862944162435,
"loss": 1.5225,
"step": 1385
},
{
"epoch": 1.39,
"learning_rate": 0.0036548857868020303,
"loss": 1.4402,
"step": 1390
},
{
"epoch": 1.39,
"learning_rate": 0.0036266852791878175,
"loss": 1.8302,
"step": 1395
},
{
"epoch": 1.4,
"learning_rate": 0.003598484771573604,
"loss": 1.1884,
"step": 1400
},
{
"epoch": 1.4,
"learning_rate": 0.003570284263959391,
"loss": 1.6533,
"step": 1405
},
{
"epoch": 1.41,
"learning_rate": 0.0035420837563451785,
"loss": 1.449,
"step": 1410
},
{
"epoch": 1.41,
"learning_rate": 0.003513883248730964,
"loss": 1.4537,
"step": 1415
},
{
"epoch": 1.42,
"learning_rate": 0.0034856827411167512,
"loss": 1.4386,
"step": 1420
},
{
"epoch": 1.42,
"learning_rate": 0.003457482233502538,
"loss": 1.3043,
"step": 1425
},
{
"epoch": 1.43,
"learning_rate": 0.0034292817258883244,
"loss": 1.5577,
"step": 1430
},
{
"epoch": 1.43,
"learning_rate": 0.0034010812182741117,
"loss": 1.6184,
"step": 1435
},
{
"epoch": 1.44,
"learning_rate": 0.003372880710659899,
"loss": 1.2835,
"step": 1440
},
{
"epoch": 1.44,
"learning_rate": 0.0033446802030456858,
"loss": 1.4659,
"step": 1445
},
{
"epoch": 1.45,
"learning_rate": 0.0033164796954314717,
"loss": 1.1781,
"step": 1450
},
{
"epoch": 1.45,
"learning_rate": 0.0032882791878172586,
"loss": 1.4166,
"step": 1455
},
{
"epoch": 1.46,
"learning_rate": 0.003260078680203046,
"loss": 1.3821,
"step": 1460
},
{
"epoch": 1.46,
"learning_rate": 0.0032318781725888326,
"loss": 1.417,
"step": 1465
},
{
"epoch": 1.47,
"learning_rate": 0.0032036776649746195,
"loss": 1.0738,
"step": 1470
},
{
"epoch": 1.47,
"learning_rate": 0.0031754771573604067,
"loss": 1.2626,
"step": 1475
},
{
"epoch": 1.48,
"learning_rate": 0.0031472766497461935,
"loss": 1.4132,
"step": 1480
},
{
"epoch": 1.48,
"learning_rate": 0.0031190761421319795,
"loss": 1.3976,
"step": 1485
},
{
"epoch": 1.49,
"learning_rate": 0.0030908756345177663,
"loss": 1.1655,
"step": 1490
},
{
"epoch": 1.49,
"learning_rate": 0.003062675126903553,
"loss": 1.6067,
"step": 1495
},
{
"epoch": 1.5,
"learning_rate": 0.0030344746192893404,
"loss": 1.2399,
"step": 1500
},
{
"epoch": 1.5,
"learning_rate": 0.0030062741116751272,
"loss": 1.3499,
"step": 1505
},
{
"epoch": 1.51,
"learning_rate": 0.002978073604060914,
"loss": 1.2958,
"step": 1510
},
{
"epoch": 1.51,
"learning_rate": 0.0029498730964467,
"loss": 0.9839,
"step": 1515
},
{
"epoch": 1.52,
"learning_rate": 0.002921672588832487,
"loss": 1.423,
"step": 1520
},
{
"epoch": 1.52,
"learning_rate": 0.002893472081218274,
"loss": 1.4083,
"step": 1525
},
{
"epoch": 1.53,
"learning_rate": 0.002865271573604061,
"loss": 1.552,
"step": 1530
},
{
"epoch": 1.53,
"learning_rate": 0.002837071065989848,
"loss": 1.1468,
"step": 1535
},
{
"epoch": 1.54,
"learning_rate": 0.002808870558375635,
"loss": 1.1524,
"step": 1540
},
{
"epoch": 1.54,
"learning_rate": 0.002780670050761422,
"loss": 1.7909,
"step": 1545
},
{
"epoch": 1.55,
"learning_rate": 0.0027524695431472078,
"loss": 1.2374,
"step": 1550
},
{
"epoch": 1.55,
"learning_rate": 0.0027242690355329946,
"loss": 1.5076,
"step": 1555
},
{
"epoch": 1.56,
"learning_rate": 0.0026960685279187814,
"loss": 1.2157,
"step": 1560
},
{
"epoch": 1.56,
"learning_rate": 0.0026678680203045687,
"loss": 1.4255,
"step": 1565
},
{
"epoch": 1.57,
"learning_rate": 0.002639667512690356,
"loss": 1.1614,
"step": 1570
},
{
"epoch": 1.57,
"learning_rate": 0.0026114670050761423,
"loss": 1.2836,
"step": 1575
},
{
"epoch": 1.58,
"learning_rate": 0.0025832664974619296,
"loss": 0.9739,
"step": 1580
},
{
"epoch": 1.58,
"learning_rate": 0.002555065989847715,
"loss": 1.445,
"step": 1585
},
{
"epoch": 1.59,
"learning_rate": 0.0025268654822335024,
"loss": 1.3724,
"step": 1590
},
{
"epoch": 1.59,
"learning_rate": 0.002498664974619289,
"loss": 1.1985,
"step": 1595
},
{
"epoch": 1.6,
"learning_rate": 0.002470464467005076,
"loss": 1.5102,
"step": 1600
},
{
"epoch": 1.6,
"learning_rate": 0.0024422639593908633,
"loss": 1.4111,
"step": 1605
},
{
"epoch": 1.61,
"learning_rate": 0.00241406345177665,
"loss": 1.4832,
"step": 1610
},
{
"epoch": 1.61,
"learning_rate": 0.002385862944162437,
"loss": 1.7259,
"step": 1615
},
{
"epoch": 1.62,
"learning_rate": 0.002357662436548223,
"loss": 1.4051,
"step": 1620
},
{
"epoch": 1.62,
"learning_rate": 0.0023294619289340097,
"loss": 1.1585,
"step": 1625
},
{
"epoch": 1.63,
"learning_rate": 0.002301261421319797,
"loss": 1.4892,
"step": 1630
},
{
"epoch": 1.63,
"learning_rate": 0.0022730609137055838,
"loss": 1.2785,
"step": 1635
},
{
"epoch": 1.64,
"learning_rate": 0.0022448604060913706,
"loss": 1.4697,
"step": 1640
},
{
"epoch": 1.64,
"learning_rate": 0.002216659898477158,
"loss": 1.5335,
"step": 1645
},
{
"epoch": 1.65,
"learning_rate": 0.0021884593908629447,
"loss": 1.6132,
"step": 1650
},
{
"epoch": 1.65,
"learning_rate": 0.0021602588832487306,
"loss": 1.2333,
"step": 1655
},
{
"epoch": 1.66,
"learning_rate": 0.0021320583756345175,
"loss": 1.7243,
"step": 1660
},
{
"epoch": 1.66,
"learning_rate": 0.0021038578680203043,
"loss": 1.5654,
"step": 1665
},
{
"epoch": 1.67,
"learning_rate": 0.0020756573604060915,
"loss": 1.3233,
"step": 1670
},
{
"epoch": 1.67,
"learning_rate": 0.0020474568527918784,
"loss": 1.2538,
"step": 1675
},
{
"epoch": 1.68,
"learning_rate": 0.002019256345177665,
"loss": 1.5129,
"step": 1680
},
{
"epoch": 1.68,
"learning_rate": 0.0019910558375634524,
"loss": 1.2342,
"step": 1685
},
{
"epoch": 1.69,
"learning_rate": 0.001962855329949238,
"loss": 1.2484,
"step": 1690
},
{
"epoch": 1.69,
"learning_rate": 0.0019346548223350254,
"loss": 1.6045,
"step": 1695
},
{
"epoch": 1.7,
"learning_rate": 0.0019064543147208123,
"loss": 1.2544,
"step": 1700
},
{
"epoch": 1.7,
"learning_rate": 0.0018782538071065993,
"loss": 1.1989,
"step": 1705
},
{
"epoch": 1.71,
"learning_rate": 0.0018500532994923861,
"loss": 1.3844,
"step": 1710
},
{
"epoch": 1.71,
"learning_rate": 0.0018218527918781732,
"loss": 1.2898,
"step": 1715
},
{
"epoch": 1.72,
"learning_rate": 0.0017936522842639591,
"loss": 1.176,
"step": 1720
},
{
"epoch": 1.72,
"learning_rate": 0.001765451776649746,
"loss": 1.3886,
"step": 1725
},
{
"epoch": 1.73,
"learning_rate": 0.001737251269035533,
"loss": 1.4818,
"step": 1730
},
{
"epoch": 1.73,
"learning_rate": 0.00170905076142132,
"loss": 1.4334,
"step": 1735
},
{
"epoch": 1.74,
"learning_rate": 0.0016808502538071069,
"loss": 1.3581,
"step": 1740
},
{
"epoch": 1.74,
"learning_rate": 0.0016526497461928939,
"loss": 1.287,
"step": 1745
},
{
"epoch": 1.75,
"learning_rate": 0.0016244492385786807,
"loss": 1.4921,
"step": 1750
},
{
"epoch": 1.75,
"learning_rate": 0.0015962487309644667,
"loss": 1.6024,
"step": 1755
},
{
"epoch": 1.76,
"learning_rate": 0.001568048223350254,
"loss": 1.3267,
"step": 1760
},
{
"epoch": 1.76,
"learning_rate": 0.0015398477157360405,
"loss": 1.3324,
"step": 1765
},
{
"epoch": 1.77,
"learning_rate": 0.0015116472081218278,
"loss": 1.4282,
"step": 1770
},
{
"epoch": 1.77,
"learning_rate": 0.0014834467005076146,
"loss": 1.4165,
"step": 1775
},
{
"epoch": 1.78,
"learning_rate": 0.0014552461928934012,
"loss": 1.5209,
"step": 1780
},
{
"epoch": 1.78,
"learning_rate": 0.0014270456852791885,
"loss": 1.5915,
"step": 1785
},
{
"epoch": 1.79,
"learning_rate": 0.001398845177664974,
"loss": 1.5822,
"step": 1790
},
{
"epoch": 1.79,
"learning_rate": 0.0013706446700507613,
"loss": 1.4356,
"step": 1795
},
{
"epoch": 1.8,
"learning_rate": 0.0013424441624365483,
"loss": 1.3999,
"step": 1800
},
{
"epoch": 1.8,
"learning_rate": 0.0013142436548223351,
"loss": 1.3192,
"step": 1805
},
{
"epoch": 1.81,
"learning_rate": 0.0012860431472081222,
"loss": 0.9928,
"step": 1810
},
{
"epoch": 1.81,
"learning_rate": 0.0012578426395939092,
"loss": 1.7191,
"step": 1815
},
{
"epoch": 1.82,
"learning_rate": 0.001229642131979696,
"loss": 1.2173,
"step": 1820
},
{
"epoch": 1.82,
"learning_rate": 0.001201441624365482,
"loss": 1.1303,
"step": 1825
},
{
"epoch": 1.83,
"learning_rate": 0.0011732411167512688,
"loss": 1.649,
"step": 1830
},
{
"epoch": 1.83,
"learning_rate": 0.0011450406091370558,
"loss": 1.5897,
"step": 1835
},
{
"epoch": 1.84,
"learning_rate": 0.0011168401015228429,
"loss": 1.163,
"step": 1840
},
{
"epoch": 1.84,
"learning_rate": 0.0010886395939086297,
"loss": 1.1745,
"step": 1845
},
{
"epoch": 1.85,
"learning_rate": 0.0010604390862944168,
"loss": 1.2499,
"step": 1850
},
{
"epoch": 1.85,
"learning_rate": 0.0010322385786802038,
"loss": 1.1123,
"step": 1855
},
{
"epoch": 1.86,
"learning_rate": 0.0010040380710659895,
"loss": 1.6267,
"step": 1860
},
{
"epoch": 1.86,
"learning_rate": 0.0009758375634517764,
"loss": 1.7138,
"step": 1865
},
{
"epoch": 1.87,
"learning_rate": 0.0009476370558375634,
"loss": 1.0705,
"step": 1870
},
{
"epoch": 1.87,
"learning_rate": 0.0009194365482233503,
"loss": 1.5925,
"step": 1875
},
{
"epoch": 1.88,
"learning_rate": 0.0008912360406091373,
"loss": 1.2733,
"step": 1880
},
{
"epoch": 1.88,
"learning_rate": 0.0008630355329949242,
"loss": 1.5511,
"step": 1885
},
{
"epoch": 1.89,
"learning_rate": 0.0008348350253807112,
"loss": 1.3351,
"step": 1890
},
{
"epoch": 1.89,
"learning_rate": 0.000806634517766497,
"loss": 1.1094,
"step": 1895
},
{
"epoch": 1.9,
"learning_rate": 0.000778434010152284,
"loss": 1.1718,
"step": 1900
},
{
"epoch": 1.9,
"learning_rate": 0.0007502335025380709,
"loss": 1.2751,
"step": 1905
},
{
"epoch": 1.91,
"learning_rate": 0.000722032994923858,
"loss": 0.9808,
"step": 1910
},
{
"epoch": 1.91,
"learning_rate": 0.0006938324873096449,
"loss": 1.5196,
"step": 1915
},
{
"epoch": 1.92,
"learning_rate": 0.0006656319796954318,
"loss": 1.1567,
"step": 1920
},
{
"epoch": 1.92,
"learning_rate": 0.0006374314720812188,
"loss": 1.2295,
"step": 1925
},
{
"epoch": 1.93,
"learning_rate": 0.0006092309644670046,
"loss": 1.3395,
"step": 1930
},
{
"epoch": 1.93,
"learning_rate": 0.0005810304568527917,
"loss": 1.2176,
"step": 1935
},
{
"epoch": 1.94,
"learning_rate": 0.0005528299492385786,
"loss": 1.2218,
"step": 1940
},
{
"epoch": 1.94,
"learning_rate": 0.0005246294416243655,
"loss": 1.1824,
"step": 1945
},
{
"epoch": 1.95,
"learning_rate": 0.0004964289340101526,
"loss": 1.4026,
"step": 1950
},
{
"epoch": 1.95,
"learning_rate": 0.0004682284263959396,
"loss": 1.391,
"step": 1955
},
{
"epoch": 1.96,
"learning_rate": 0.0004400279187817254,
"loss": 1.5254,
"step": 1960
},
{
"epoch": 1.96,
"learning_rate": 0.0004118274111675124,
"loss": 1.2331,
"step": 1965
},
{
"epoch": 1.97,
"learning_rate": 0.0003836269035532993,
"loss": 1.2529,
"step": 1970
},
{
"epoch": 1.97,
"learning_rate": 0.00035542639593908625,
"loss": 1.0726,
"step": 1975
},
{
"epoch": 1.98,
"learning_rate": 0.00032722588832487324,
"loss": 1.2203,
"step": 1980
},
{
"epoch": 1.98,
"learning_rate": 0.0002990253807106602,
"loss": 1.2456,
"step": 1985
},
{
"epoch": 1.99,
"learning_rate": 0.00027082487309644716,
"loss": 1.3003,
"step": 1990
},
{
"epoch": 1.99,
"learning_rate": 0.00024262436548223298,
"loss": 1.299,
"step": 1995
},
{
"epoch": 2.0,
"learning_rate": 0.00021442385786802,
"loss": 1.488,
"step": 2000
},
{
"epoch": 2.0,
"learning_rate": 0.00018622335025380695,
"loss": 937.4512,
"step": 2005
},
{
"epoch": 2.01,
"learning_rate": 0.00015802284263959394,
"loss": 924.4408,
"step": 2010
},
{
"epoch": 2.01,
"learning_rate": 0.00012982233502538087,
"loss": 903.1811,
"step": 2015
},
{
"epoch": 2.02,
"learning_rate": 0.00010162182741116783,
"loss": 868.8327,
"step": 2020
},
{
"epoch": 2.02,
"learning_rate": 7.342131979695479e-05,
"loss": 833.6856,
"step": 2025
},
{
"epoch": 2.03,
"learning_rate": 4.522081218274065e-05,
"loss": 816.0007,
"step": 2030
},
{
"epoch": 2.03,
"learning_rate": 1.70203045685276e-05,
"loss": 795.98,
"step": 2035
},
{
"epoch": 2.04,
"step": 2038,
"total_flos": 2.2810681001063887e+23,
"train_loss": 16.08543400488377,
"train_runtime": 323733.6046,
"train_samples_per_second": 103.142,
"train_steps_per_second": 0.006
},
{
"epoch": 2.04,
"step": 2038,
"total_flos": 2.2810681001063887e+23,
"train_loss": 0.0,
"train_runtime": 3248433.7519,
"train_samples_per_second": 0.005,
"train_steps_per_second": 0.0
}
],
"max_steps": 1,
"num_train_epochs": 1,
"start_time": 1663027920.2259,
"total_flos": 2.2810681001063887e+23,
"trial_name": null,
"trial_params": null
}