zephyr-7b-sft-qlora / trainer_state.json
yzzh's picture
Model save
88c69fc verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 2179,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 0.28782306759602416,
"learning_rate": 9.174311926605506e-07,
"loss": 1.1568,
"step": 1
},
{
"epoch": 0.0,
"grad_norm": 0.2765226643079522,
"learning_rate": 4.587155963302753e-06,
"loss": 1.1458,
"step": 5
},
{
"epoch": 0.0,
"grad_norm": 0.2707977544047907,
"learning_rate": 9.174311926605506e-06,
"loss": 1.1252,
"step": 10
},
{
"epoch": 0.01,
"grad_norm": 0.23184164475898333,
"learning_rate": 1.3761467889908258e-05,
"loss": 1.1309,
"step": 15
},
{
"epoch": 0.01,
"grad_norm": 0.207610763811708,
"learning_rate": 1.834862385321101e-05,
"loss": 1.1227,
"step": 20
},
{
"epoch": 0.01,
"grad_norm": 0.1816681264337633,
"learning_rate": 2.2935779816513765e-05,
"loss": 1.0656,
"step": 25
},
{
"epoch": 0.01,
"grad_norm": 0.1631492001334514,
"learning_rate": 2.7522935779816515e-05,
"loss": 1.0435,
"step": 30
},
{
"epoch": 0.02,
"grad_norm": 0.12091918318355398,
"learning_rate": 3.211009174311927e-05,
"loss": 1.0422,
"step": 35
},
{
"epoch": 0.02,
"grad_norm": 0.10894779898677374,
"learning_rate": 3.669724770642202e-05,
"loss": 1.0231,
"step": 40
},
{
"epoch": 0.02,
"grad_norm": 0.10540985367231842,
"learning_rate": 4.1284403669724776e-05,
"loss": 0.9966,
"step": 45
},
{
"epoch": 0.02,
"grad_norm": 0.09676232054101573,
"learning_rate": 4.587155963302753e-05,
"loss": 0.9798,
"step": 50
},
{
"epoch": 0.03,
"grad_norm": 0.11000697328127398,
"learning_rate": 5.0458715596330276e-05,
"loss": 1.0154,
"step": 55
},
{
"epoch": 0.03,
"grad_norm": 0.10373599911083506,
"learning_rate": 5.504587155963303e-05,
"loss": 0.9935,
"step": 60
},
{
"epoch": 0.03,
"grad_norm": 0.11059687218734753,
"learning_rate": 5.9633027522935784e-05,
"loss": 0.9899,
"step": 65
},
{
"epoch": 0.03,
"grad_norm": 0.11912414533134615,
"learning_rate": 6.422018348623854e-05,
"loss": 0.9856,
"step": 70
},
{
"epoch": 0.03,
"grad_norm": 0.1133131029182366,
"learning_rate": 6.880733944954129e-05,
"loss": 0.995,
"step": 75
},
{
"epoch": 0.04,
"grad_norm": 0.1285831542439206,
"learning_rate": 7.339449541284404e-05,
"loss": 0.9857,
"step": 80
},
{
"epoch": 0.04,
"grad_norm": 0.11413242308426012,
"learning_rate": 7.79816513761468e-05,
"loss": 0.9809,
"step": 85
},
{
"epoch": 0.04,
"grad_norm": 0.10876549432839086,
"learning_rate": 8.256880733944955e-05,
"loss": 0.9742,
"step": 90
},
{
"epoch": 0.04,
"grad_norm": 0.11916614500162052,
"learning_rate": 8.715596330275229e-05,
"loss": 0.9574,
"step": 95
},
{
"epoch": 0.05,
"grad_norm": 0.1370299381128718,
"learning_rate": 9.174311926605506e-05,
"loss": 0.9862,
"step": 100
},
{
"epoch": 0.05,
"grad_norm": 0.137870839924706,
"learning_rate": 9.63302752293578e-05,
"loss": 1.0027,
"step": 105
},
{
"epoch": 0.05,
"grad_norm": 0.12566416676044165,
"learning_rate": 0.00010091743119266055,
"loss": 0.9572,
"step": 110
},
{
"epoch": 0.05,
"grad_norm": 0.11452270864650357,
"learning_rate": 0.00010550458715596329,
"loss": 0.9547,
"step": 115
},
{
"epoch": 0.06,
"grad_norm": 0.11788556058363543,
"learning_rate": 0.00011009174311926606,
"loss": 1.0131,
"step": 120
},
{
"epoch": 0.06,
"grad_norm": 0.11618026116590524,
"learning_rate": 0.00011467889908256881,
"loss": 0.9948,
"step": 125
},
{
"epoch": 0.06,
"grad_norm": 0.11293458291689443,
"learning_rate": 0.00011926605504587157,
"loss": 0.983,
"step": 130
},
{
"epoch": 0.06,
"grad_norm": 0.11157978831839803,
"learning_rate": 0.00012385321100917432,
"loss": 0.9708,
"step": 135
},
{
"epoch": 0.06,
"grad_norm": 0.1084963251618998,
"learning_rate": 0.00012844036697247707,
"loss": 0.9696,
"step": 140
},
{
"epoch": 0.07,
"grad_norm": 0.12208924093427911,
"learning_rate": 0.00013302752293577983,
"loss": 0.9589,
"step": 145
},
{
"epoch": 0.07,
"grad_norm": 0.12400327121666536,
"learning_rate": 0.00013761467889908258,
"loss": 0.9743,
"step": 150
},
{
"epoch": 0.07,
"grad_norm": 0.11683640502206159,
"learning_rate": 0.0001422018348623853,
"loss": 0.9561,
"step": 155
},
{
"epoch": 0.07,
"grad_norm": 0.10367694083396438,
"learning_rate": 0.0001467889908256881,
"loss": 0.9666,
"step": 160
},
{
"epoch": 0.08,
"grad_norm": 0.12707530495236583,
"learning_rate": 0.00015137614678899084,
"loss": 0.9865,
"step": 165
},
{
"epoch": 0.08,
"grad_norm": 0.10632460411245542,
"learning_rate": 0.0001559633027522936,
"loss": 0.9674,
"step": 170
},
{
"epoch": 0.08,
"grad_norm": 0.10377606105203888,
"learning_rate": 0.00016055045871559632,
"loss": 0.9868,
"step": 175
},
{
"epoch": 0.08,
"grad_norm": 0.10127959187939727,
"learning_rate": 0.0001651376146788991,
"loss": 0.964,
"step": 180
},
{
"epoch": 0.08,
"grad_norm": 0.1067977777725574,
"learning_rate": 0.00016972477064220186,
"loss": 0.9818,
"step": 185
},
{
"epoch": 0.09,
"grad_norm": 0.10097509908529916,
"learning_rate": 0.00017431192660550458,
"loss": 0.985,
"step": 190
},
{
"epoch": 0.09,
"grad_norm": 0.08983732625855309,
"learning_rate": 0.00017889908256880734,
"loss": 0.986,
"step": 195
},
{
"epoch": 0.09,
"grad_norm": 0.09879437209533858,
"learning_rate": 0.00018348623853211012,
"loss": 0.9575,
"step": 200
},
{
"epoch": 0.09,
"grad_norm": 0.09503268529031307,
"learning_rate": 0.00018807339449541284,
"loss": 0.9652,
"step": 205
},
{
"epoch": 0.1,
"grad_norm": 0.09280130396940776,
"learning_rate": 0.0001926605504587156,
"loss": 0.9546,
"step": 210
},
{
"epoch": 0.1,
"grad_norm": 0.09653028292096948,
"learning_rate": 0.00019724770642201835,
"loss": 0.9683,
"step": 215
},
{
"epoch": 0.1,
"grad_norm": 0.09433817156644378,
"learning_rate": 0.00019999948669655127,
"loss": 0.9658,
"step": 220
},
{
"epoch": 0.1,
"grad_norm": 0.09147287152333045,
"learning_rate": 0.00019999371209327089,
"loss": 0.9637,
"step": 225
},
{
"epoch": 0.11,
"grad_norm": 0.09512038122974721,
"learning_rate": 0.00019998152162914806,
"loss": 0.9459,
"step": 230
},
{
"epoch": 0.11,
"grad_norm": 0.0941352545868701,
"learning_rate": 0.00019996291608635525,
"loss": 0.9798,
"step": 235
},
{
"epoch": 0.11,
"grad_norm": 0.10048319682038799,
"learning_rate": 0.00019993789665867314,
"loss": 0.9477,
"step": 240
},
{
"epoch": 0.11,
"grad_norm": 0.0870804299235567,
"learning_rate": 0.00019990646495141444,
"loss": 0.9727,
"step": 245
},
{
"epoch": 0.11,
"grad_norm": 0.0911867604696636,
"learning_rate": 0.0001998686229813205,
"loss": 0.994,
"step": 250
},
{
"epoch": 0.12,
"grad_norm": 0.0910776617883196,
"learning_rate": 0.00019982437317643217,
"loss": 0.967,
"step": 255
},
{
"epoch": 0.12,
"grad_norm": 0.09364688409217624,
"learning_rate": 0.0001997737183759338,
"loss": 0.9521,
"step": 260
},
{
"epoch": 0.12,
"grad_norm": 0.09254538330109398,
"learning_rate": 0.00019971666182997137,
"loss": 0.986,
"step": 265
},
{
"epoch": 0.12,
"grad_norm": 0.10322422823108995,
"learning_rate": 0.00019965320719944366,
"loss": 0.9541,
"step": 270
},
{
"epoch": 0.13,
"grad_norm": 0.09173096996766032,
"learning_rate": 0.00019958335855576738,
"loss": 0.9546,
"step": 275
},
{
"epoch": 0.13,
"grad_norm": 0.0893743167592582,
"learning_rate": 0.00019950712038061617,
"loss": 0.9576,
"step": 280
},
{
"epoch": 0.13,
"grad_norm": 0.09477317623808881,
"learning_rate": 0.00019942449756563279,
"loss": 0.9677,
"step": 285
},
{
"epoch": 0.13,
"grad_norm": 0.0938118134559368,
"learning_rate": 0.00019933549541211552,
"loss": 0.9365,
"step": 290
},
{
"epoch": 0.14,
"grad_norm": 0.08783897990789609,
"learning_rate": 0.00019924011963067765,
"loss": 0.9683,
"step": 295
},
{
"epoch": 0.14,
"grad_norm": 0.09119730775090834,
"learning_rate": 0.00019913837634088144,
"loss": 0.9482,
"step": 300
},
{
"epoch": 0.14,
"grad_norm": 0.0923867205609476,
"learning_rate": 0.00019903027207084523,
"loss": 0.9352,
"step": 305
},
{
"epoch": 0.14,
"grad_norm": 0.08608823546934513,
"learning_rate": 0.00019891581375682473,
"loss": 0.9416,
"step": 310
},
{
"epoch": 0.14,
"grad_norm": 0.08755150309465999,
"learning_rate": 0.00019879500874276786,
"loss": 0.9572,
"step": 315
},
{
"epoch": 0.15,
"grad_norm": 0.08859531100037746,
"learning_rate": 0.00019866786477984357,
"loss": 0.9583,
"step": 320
},
{
"epoch": 0.15,
"grad_norm": 0.08989870433700839,
"learning_rate": 0.0001985343900259446,
"loss": 0.9556,
"step": 325
},
{
"epoch": 0.15,
"grad_norm": 0.08858019305307584,
"learning_rate": 0.0001983945930451639,
"loss": 0.9396,
"step": 330
},
{
"epoch": 0.15,
"grad_norm": 0.09002132618468012,
"learning_rate": 0.0001982484828072452,
"loss": 0.9484,
"step": 335
},
{
"epoch": 0.16,
"grad_norm": 0.09371174635475092,
"learning_rate": 0.00019809606868700756,
"loss": 0.9783,
"step": 340
},
{
"epoch": 0.16,
"grad_norm": 0.08957560235407128,
"learning_rate": 0.00019793736046374373,
"loss": 0.9705,
"step": 345
},
{
"epoch": 0.16,
"grad_norm": 0.09036101764586872,
"learning_rate": 0.0001977723683205928,
"loss": 0.9621,
"step": 350
},
{
"epoch": 0.16,
"grad_norm": 0.08511370022873634,
"learning_rate": 0.00019760110284388667,
"loss": 0.9496,
"step": 355
},
{
"epoch": 0.17,
"grad_norm": 0.08897578619547024,
"learning_rate": 0.00019742357502247103,
"loss": 0.956,
"step": 360
},
{
"epoch": 0.17,
"grad_norm": 0.08600773035072362,
"learning_rate": 0.00019723979624700004,
"loss": 0.9696,
"step": 365
},
{
"epoch": 0.17,
"grad_norm": 0.09055825979523356,
"learning_rate": 0.0001970497783092057,
"loss": 0.9367,
"step": 370
},
{
"epoch": 0.17,
"grad_norm": 0.0932727351645862,
"learning_rate": 0.00019685353340114103,
"loss": 0.9744,
"step": 375
},
{
"epoch": 0.17,
"grad_norm": 0.0854363406688081,
"learning_rate": 0.00019665107411439805,
"loss": 0.9484,
"step": 380
},
{
"epoch": 0.18,
"grad_norm": 0.09005207643389745,
"learning_rate": 0.00019644241343929966,
"loss": 0.9677,
"step": 385
},
{
"epoch": 0.18,
"grad_norm": 0.08649622389550082,
"learning_rate": 0.00019622756476406626,
"loss": 0.9712,
"step": 390
},
{
"epoch": 0.18,
"grad_norm": 0.09439150706615457,
"learning_rate": 0.00019600654187395663,
"loss": 0.9683,
"step": 395
},
{
"epoch": 0.18,
"grad_norm": 0.09297365586336294,
"learning_rate": 0.00019577935895038361,
"loss": 0.9597,
"step": 400
},
{
"epoch": 0.19,
"grad_norm": 0.08529999606035547,
"learning_rate": 0.00019554603057000397,
"loss": 0.955,
"step": 405
},
{
"epoch": 0.19,
"grad_norm": 0.09078999187809153,
"learning_rate": 0.0001953065717037832,
"loss": 0.982,
"step": 410
},
{
"epoch": 0.19,
"grad_norm": 0.08821581975562078,
"learning_rate": 0.00019506099771603513,
"loss": 0.9413,
"step": 415
},
{
"epoch": 0.19,
"grad_norm": 0.09158552500876148,
"learning_rate": 0.00019480932436343582,
"loss": 0.948,
"step": 420
},
{
"epoch": 0.2,
"grad_norm": 0.08959534367059374,
"learning_rate": 0.00019455156779401265,
"loss": 0.9427,
"step": 425
},
{
"epoch": 0.2,
"grad_norm": 0.08425686082734027,
"learning_rate": 0.00019428774454610843,
"loss": 0.9687,
"step": 430
},
{
"epoch": 0.2,
"grad_norm": 0.09345564412190348,
"learning_rate": 0.00019401787154731993,
"loss": 0.9518,
"step": 435
},
{
"epoch": 0.2,
"grad_norm": 0.09078358962410667,
"learning_rate": 0.0001937419661134121,
"loss": 0.9188,
"step": 440
},
{
"epoch": 0.2,
"grad_norm": 0.08705601046979651,
"learning_rate": 0.00019346004594720669,
"loss": 0.9368,
"step": 445
},
{
"epoch": 0.21,
"grad_norm": 0.08422228533676696,
"learning_rate": 0.0001931721291374467,
"loss": 0.9464,
"step": 450
},
{
"epoch": 0.21,
"grad_norm": 0.08632474019571335,
"learning_rate": 0.00019287823415763553,
"loss": 0.9729,
"step": 455
},
{
"epoch": 0.21,
"grad_norm": 0.08755073393921248,
"learning_rate": 0.00019257837986485187,
"loss": 0.9544,
"step": 460
},
{
"epoch": 0.21,
"grad_norm": 0.08687000103849005,
"learning_rate": 0.0001922725854985396,
"loss": 0.9545,
"step": 465
},
{
"epoch": 0.22,
"grad_norm": 0.09216723149978304,
"learning_rate": 0.0001919608706792735,
"loss": 0.9597,
"step": 470
},
{
"epoch": 0.22,
"grad_norm": 0.0923192619958272,
"learning_rate": 0.00019164325540750016,
"loss": 0.9633,
"step": 475
},
{
"epoch": 0.22,
"grad_norm": 0.08732884649919875,
"learning_rate": 0.00019131976006225488,
"loss": 0.9693,
"step": 480
},
{
"epoch": 0.22,
"grad_norm": 0.08589978089749792,
"learning_rate": 0.00019099040539985394,
"loss": 0.9493,
"step": 485
},
{
"epoch": 0.22,
"grad_norm": 0.08762407567201845,
"learning_rate": 0.00019065521255256298,
"loss": 0.9664,
"step": 490
},
{
"epoch": 0.23,
"grad_norm": 0.09213229196529499,
"learning_rate": 0.00019031420302724096,
"loss": 0.9778,
"step": 495
},
{
"epoch": 0.23,
"grad_norm": 0.08592356697919659,
"learning_rate": 0.00018996739870396026,
"loss": 0.9572,
"step": 500
},
{
"epoch": 0.23,
"grad_norm": 0.10623494849251007,
"learning_rate": 0.00018961482183460282,
"loss": 0.964,
"step": 505
},
{
"epoch": 0.23,
"grad_norm": 0.08704350244157279,
"learning_rate": 0.00018925649504143244,
"loss": 0.9524,
"step": 510
},
{
"epoch": 0.24,
"grad_norm": 0.0897677422263576,
"learning_rate": 0.0001888924413156432,
"loss": 0.9496,
"step": 515
},
{
"epoch": 0.24,
"grad_norm": 0.08827247508424733,
"learning_rate": 0.0001885226840158843,
"loss": 0.9358,
"step": 520
},
{
"epoch": 0.24,
"grad_norm": 0.08453360810699566,
"learning_rate": 0.00018814724686676133,
"loss": 0.9374,
"step": 525
},
{
"epoch": 0.24,
"grad_norm": 0.09448297684027758,
"learning_rate": 0.00018776615395731398,
"loss": 0.958,
"step": 530
},
{
"epoch": 0.25,
"grad_norm": 0.08600018025356833,
"learning_rate": 0.0001873794297394706,
"loss": 0.9618,
"step": 535
},
{
"epoch": 0.25,
"grad_norm": 0.08675234848801924,
"learning_rate": 0.00018698709902647902,
"loss": 0.9438,
"step": 540
},
{
"epoch": 0.25,
"grad_norm": 0.09061001820394972,
"learning_rate": 0.00018658918699131468,
"loss": 0.9687,
"step": 545
},
{
"epoch": 0.25,
"grad_norm": 0.0918295658678201,
"learning_rate": 0.00018618571916506545,
"loss": 0.9472,
"step": 550
},
{
"epoch": 0.25,
"grad_norm": 0.08596947713972145,
"learning_rate": 0.00018577672143529336,
"loss": 0.9516,
"step": 555
},
{
"epoch": 0.26,
"grad_norm": 0.09019003738558351,
"learning_rate": 0.00018536222004437368,
"loss": 0.9487,
"step": 560
},
{
"epoch": 0.26,
"grad_norm": 0.0847736196421309,
"learning_rate": 0.0001849422415878112,
"loss": 0.9314,
"step": 565
},
{
"epoch": 0.26,
"grad_norm": 0.08712414636411857,
"learning_rate": 0.00018451681301253362,
"loss": 0.9562,
"step": 570
},
{
"epoch": 0.26,
"grad_norm": 0.09276684050446858,
"learning_rate": 0.00018408596161516267,
"loss": 0.94,
"step": 575
},
{
"epoch": 0.27,
"grad_norm": 0.08820606105057767,
"learning_rate": 0.00018364971504026273,
"loss": 0.9546,
"step": 580
},
{
"epoch": 0.27,
"grad_norm": 0.08793901876987452,
"learning_rate": 0.00018320810127856705,
"loss": 0.9556,
"step": 585
},
{
"epoch": 0.27,
"grad_norm": 0.08756027329406087,
"learning_rate": 0.00018276114866518168,
"loss": 0.9647,
"step": 590
},
{
"epoch": 0.27,
"grad_norm": 0.08612057766614822,
"learning_rate": 0.00018230888587776755,
"loss": 0.9348,
"step": 595
},
{
"epoch": 0.28,
"grad_norm": 0.08825824481464735,
"learning_rate": 0.00018185134193470043,
"loss": 0.9621,
"step": 600
},
{
"epoch": 0.28,
"grad_norm": 0.08855957551515957,
"learning_rate": 0.00018138854619320893,
"loss": 0.951,
"step": 605
},
{
"epoch": 0.28,
"grad_norm": 0.09202042855847319,
"learning_rate": 0.00018092052834749094,
"loss": 0.9524,
"step": 610
},
{
"epoch": 0.28,
"grad_norm": 0.0882422487809607,
"learning_rate": 0.0001804473184268084,
"loss": 0.9344,
"step": 615
},
{
"epoch": 0.28,
"grad_norm": 0.09188481277352664,
"learning_rate": 0.0001799689467935604,
"loss": 0.9575,
"step": 620
},
{
"epoch": 0.29,
"grad_norm": 0.08761250216320178,
"learning_rate": 0.00017948544414133534,
"loss": 0.9353,
"step": 625
},
{
"epoch": 0.29,
"grad_norm": 0.09089274409603867,
"learning_rate": 0.00017899684149294117,
"loss": 0.964,
"step": 630
},
{
"epoch": 0.29,
"grad_norm": 0.08766747210542415,
"learning_rate": 0.00017850317019841514,
"loss": 0.9525,
"step": 635
},
{
"epoch": 0.29,
"grad_norm": 0.08930600295491815,
"learning_rate": 0.00017800446193301227,
"loss": 0.96,
"step": 640
},
{
"epoch": 0.3,
"grad_norm": 0.08853887368794433,
"learning_rate": 0.00017750074869517284,
"loss": 0.9694,
"step": 645
},
{
"epoch": 0.3,
"grad_norm": 0.08442533232702532,
"learning_rate": 0.00017699206280446953,
"loss": 0.9208,
"step": 650
},
{
"epoch": 0.3,
"grad_norm": 0.08683714377922135,
"learning_rate": 0.00017647843689953352,
"loss": 0.9661,
"step": 655
},
{
"epoch": 0.3,
"grad_norm": 0.08674144789262467,
"learning_rate": 0.00017595990393596026,
"loss": 0.9586,
"step": 660
},
{
"epoch": 0.31,
"grad_norm": 0.08859684741151846,
"learning_rate": 0.0001754364971841952,
"loss": 0.9581,
"step": 665
},
{
"epoch": 0.31,
"grad_norm": 0.08859618436822166,
"learning_rate": 0.0001749082502273988,
"loss": 0.9396,
"step": 670
},
{
"epoch": 0.31,
"grad_norm": 0.08662436024506778,
"learning_rate": 0.00017437519695929194,
"loss": 0.9478,
"step": 675
},
{
"epoch": 0.31,
"grad_norm": 0.08702673421879521,
"learning_rate": 0.0001738373715819811,
"loss": 0.9659,
"step": 680
},
{
"epoch": 0.31,
"grad_norm": 0.08834975009894457,
"learning_rate": 0.00017329480860376391,
"loss": 0.9801,
"step": 685
},
{
"epoch": 0.32,
"grad_norm": 0.08907394268442888,
"learning_rate": 0.00017274754283691504,
"loss": 0.9527,
"step": 690
},
{
"epoch": 0.32,
"grad_norm": 0.09231370364779791,
"learning_rate": 0.00017219560939545246,
"loss": 0.9588,
"step": 695
},
{
"epoch": 0.32,
"grad_norm": 0.09009781412735576,
"learning_rate": 0.00017163904369288445,
"loss": 0.9419,
"step": 700
},
{
"epoch": 0.32,
"grad_norm": 0.08650205473210101,
"learning_rate": 0.00017107788143993743,
"loss": 0.94,
"step": 705
},
{
"epoch": 0.33,
"grad_norm": 0.0919904852442932,
"learning_rate": 0.00017051215864226469,
"loss": 0.9506,
"step": 710
},
{
"epoch": 0.33,
"grad_norm": 0.08808529519659543,
"learning_rate": 0.0001699419115981361,
"loss": 0.957,
"step": 715
},
{
"epoch": 0.33,
"grad_norm": 0.09101444782991605,
"learning_rate": 0.00016936717689610903,
"loss": 0.9328,
"step": 720
},
{
"epoch": 0.33,
"grad_norm": 0.0865079634420763,
"learning_rate": 0.00016878799141268106,
"loss": 0.9421,
"step": 725
},
{
"epoch": 0.34,
"grad_norm": 0.0895608019365179,
"learning_rate": 0.00016820439230992343,
"loss": 0.9618,
"step": 730
},
{
"epoch": 0.34,
"grad_norm": 0.08619071121372446,
"learning_rate": 0.00016761641703309704,
"loss": 0.9265,
"step": 735
},
{
"epoch": 0.34,
"grad_norm": 0.0848234059929775,
"learning_rate": 0.00016702410330824962,
"loss": 0.9701,
"step": 740
},
{
"epoch": 0.34,
"grad_norm": 0.08582375402337497,
"learning_rate": 0.00016642748913979513,
"loss": 0.9484,
"step": 745
},
{
"epoch": 0.34,
"grad_norm": 0.09152872800299702,
"learning_rate": 0.00016582661280807552,
"loss": 0.9639,
"step": 750
},
{
"epoch": 0.35,
"grad_norm": 0.0877108383812197,
"learning_rate": 0.0001652215128669042,
"loss": 0.9787,
"step": 755
},
{
"epoch": 0.35,
"grad_norm": 0.08689501691870347,
"learning_rate": 0.00016461222814109268,
"loss": 0.9608,
"step": 760
},
{
"epoch": 0.35,
"grad_norm": 0.09332436047860204,
"learning_rate": 0.00016399879772395915,
"loss": 0.9432,
"step": 765
},
{
"epoch": 0.35,
"grad_norm": 0.08516705345764235,
"learning_rate": 0.00016338126097482057,
"loss": 0.9348,
"step": 770
},
{
"epoch": 0.36,
"grad_norm": 0.08726474252968008,
"learning_rate": 0.0001627596575164668,
"loss": 0.9709,
"step": 775
},
{
"epoch": 0.36,
"grad_norm": 0.08888011508247526,
"learning_rate": 0.0001621340272326185,
"loss": 0.956,
"step": 780
},
{
"epoch": 0.36,
"grad_norm": 0.09139409277427421,
"learning_rate": 0.00016150441026536823,
"loss": 0.9483,
"step": 785
},
{
"epoch": 0.36,
"grad_norm": 0.09042448727858429,
"learning_rate": 0.00016087084701260466,
"loss": 0.9526,
"step": 790
},
{
"epoch": 0.36,
"grad_norm": 0.08642751941422035,
"learning_rate": 0.00016023337812542048,
"loss": 0.9442,
"step": 795
},
{
"epoch": 0.37,
"grad_norm": 0.08584355244570809,
"learning_rate": 0.00015959204450550428,
"loss": 0.9492,
"step": 800
},
{
"epoch": 0.37,
"grad_norm": 0.08766167281479247,
"learning_rate": 0.00015894688730251614,
"loss": 0.9787,
"step": 805
},
{
"epoch": 0.37,
"grad_norm": 0.0883622912274688,
"learning_rate": 0.0001582979479114472,
"loss": 0.9466,
"step": 810
},
{
"epoch": 0.37,
"grad_norm": 0.09140030196293039,
"learning_rate": 0.000157645267969964,
"loss": 0.9495,
"step": 815
},
{
"epoch": 0.38,
"grad_norm": 0.08506975393435418,
"learning_rate": 0.0001569888893557365,
"loss": 0.9279,
"step": 820
},
{
"epoch": 0.38,
"grad_norm": 0.08519765362403448,
"learning_rate": 0.00015632885418375136,
"loss": 0.9509,
"step": 825
},
{
"epoch": 0.38,
"grad_norm": 0.08778850238010608,
"learning_rate": 0.00015566520480360957,
"loss": 0.9161,
"step": 830
},
{
"epoch": 0.38,
"grad_norm": 0.09158195757138242,
"learning_rate": 0.0001549979837968094,
"loss": 0.9245,
"step": 835
},
{
"epoch": 0.39,
"grad_norm": 0.08986630430709179,
"learning_rate": 0.00015432723397401405,
"loss": 0.9455,
"step": 840
},
{
"epoch": 0.39,
"grad_norm": 0.09336343830360828,
"learning_rate": 0.00015365299837230483,
"loss": 0.9584,
"step": 845
},
{
"epoch": 0.39,
"grad_norm": 0.08854767057712627,
"learning_rate": 0.00015297532025241992,
"loss": 0.9373,
"step": 850
},
{
"epoch": 0.39,
"grad_norm": 0.0861561244367331,
"learning_rate": 0.00015229424309597852,
"loss": 0.9337,
"step": 855
},
{
"epoch": 0.39,
"grad_norm": 0.09273027341749242,
"learning_rate": 0.00015160981060269107,
"loss": 0.9492,
"step": 860
},
{
"epoch": 0.4,
"grad_norm": 0.09378203137542973,
"learning_rate": 0.00015092206668755517,
"loss": 0.9463,
"step": 865
},
{
"epoch": 0.4,
"grad_norm": 0.0862644522566823,
"learning_rate": 0.00015023105547803806,
"loss": 0.9339,
"step": 870
},
{
"epoch": 0.4,
"grad_norm": 0.08790661308759892,
"learning_rate": 0.00014953682131124528,
"loss": 0.9474,
"step": 875
},
{
"epoch": 0.4,
"grad_norm": 0.08422068379445599,
"learning_rate": 0.0001488394087310757,
"loss": 0.932,
"step": 880
},
{
"epoch": 0.41,
"grad_norm": 0.08835895673531197,
"learning_rate": 0.00014813886248536375,
"loss": 0.9682,
"step": 885
},
{
"epoch": 0.41,
"grad_norm": 0.08812707061816671,
"learning_rate": 0.00014743522752300793,
"loss": 0.9494,
"step": 890
},
{
"epoch": 0.41,
"grad_norm": 0.08984312676721799,
"learning_rate": 0.00014672854899108718,
"loss": 0.968,
"step": 895
},
{
"epoch": 0.41,
"grad_norm": 0.08997766999205116,
"learning_rate": 0.00014601887223196372,
"loss": 0.9259,
"step": 900
},
{
"epoch": 0.42,
"grad_norm": 0.08554195694203166,
"learning_rate": 0.00014530624278037406,
"loss": 0.9325,
"step": 905
},
{
"epoch": 0.42,
"grad_norm": 0.08600975689157553,
"learning_rate": 0.0001445907063605072,
"loss": 0.9396,
"step": 910
},
{
"epoch": 0.42,
"grad_norm": 0.08549667691396576,
"learning_rate": 0.00014387230888307097,
"loss": 0.931,
"step": 915
},
{
"epoch": 0.42,
"grad_norm": 0.08633848719229598,
"learning_rate": 0.0001431510964423462,
"loss": 0.9736,
"step": 920
},
{
"epoch": 0.42,
"grad_norm": 0.08946502964232063,
"learning_rate": 0.0001424271153132291,
"loss": 0.9508,
"step": 925
},
{
"epoch": 0.43,
"grad_norm": 0.08644778095141836,
"learning_rate": 0.00014170041194826248,
"loss": 0.9291,
"step": 930
},
{
"epoch": 0.43,
"grad_norm": 0.08743477799274565,
"learning_rate": 0.0001409710329746547,
"loss": 0.9581,
"step": 935
},
{
"epoch": 0.43,
"grad_norm": 0.09102927350920745,
"learning_rate": 0.0001402390251912885,
"loss": 0.9641,
"step": 940
},
{
"epoch": 0.43,
"grad_norm": 0.08406401589929084,
"learning_rate": 0.00013950443556571778,
"loss": 0.928,
"step": 945
},
{
"epoch": 0.44,
"grad_norm": 0.08874042668156715,
"learning_rate": 0.0001387673112311545,
"loss": 0.911,
"step": 950
},
{
"epoch": 0.44,
"grad_norm": 0.0846652407845296,
"learning_rate": 0.00013802769948344405,
"loss": 0.93,
"step": 955
},
{
"epoch": 0.44,
"grad_norm": 0.08812982695434313,
"learning_rate": 0.00013728564777803088,
"loss": 0.9574,
"step": 960
},
{
"epoch": 0.44,
"grad_norm": 0.08779218610162595,
"learning_rate": 0.0001365412037269136,
"loss": 0.9263,
"step": 965
},
{
"epoch": 0.45,
"grad_norm": 0.08763397205182845,
"learning_rate": 0.00013579441509559004,
"loss": 0.9647,
"step": 970
},
{
"epoch": 0.45,
"grad_norm": 0.08771463604901869,
"learning_rate": 0.0001350453297999925,
"loss": 0.9422,
"step": 975
},
{
"epoch": 0.45,
"grad_norm": 0.09110171303652766,
"learning_rate": 0.00013429399590341324,
"loss": 0.947,
"step": 980
},
{
"epoch": 0.45,
"grad_norm": 0.0890607024116997,
"learning_rate": 0.00013354046161342085,
"loss": 0.9513,
"step": 985
},
{
"epoch": 0.45,
"grad_norm": 0.0859287161459074,
"learning_rate": 0.0001327847752787669,
"loss": 0.9706,
"step": 990
},
{
"epoch": 0.46,
"grad_norm": 0.09247919961374537,
"learning_rate": 0.00013202698538628376,
"loss": 0.9657,
"step": 995
},
{
"epoch": 0.46,
"grad_norm": 0.09027056948690071,
"learning_rate": 0.00013126714055777377,
"loss": 0.9527,
"step": 1000
},
{
"epoch": 0.46,
"grad_norm": 0.08674017096568151,
"learning_rate": 0.0001305052895468893,
"loss": 0.9519,
"step": 1005
},
{
"epoch": 0.46,
"grad_norm": 0.08650629459230609,
"learning_rate": 0.00012974148123600477,
"loss": 0.9395,
"step": 1010
},
{
"epoch": 0.47,
"grad_norm": 0.08523687321318427,
"learning_rate": 0.00012897576463307997,
"loss": 0.9433,
"step": 1015
},
{
"epoch": 0.47,
"grad_norm": 0.08649388719980053,
"learning_rate": 0.00012820818886851598,
"loss": 0.9212,
"step": 1020
},
{
"epoch": 0.47,
"grad_norm": 0.08632252078335054,
"learning_rate": 0.00012743880319200242,
"loss": 0.9677,
"step": 1025
},
{
"epoch": 0.47,
"grad_norm": 0.08776100128200802,
"learning_rate": 0.00012666765696935773,
"loss": 0.9469,
"step": 1030
},
{
"epoch": 0.47,
"grad_norm": 0.08935277960845327,
"learning_rate": 0.0001258947996793616,
"loss": 0.9354,
"step": 1035
},
{
"epoch": 0.48,
"grad_norm": 0.09034950318804204,
"learning_rate": 0.00012512028091058044,
"loss": 0.9541,
"step": 1040
},
{
"epoch": 0.48,
"grad_norm": 0.08871578654302656,
"learning_rate": 0.00012434415035818535,
"loss": 0.9435,
"step": 1045
},
{
"epoch": 0.48,
"grad_norm": 0.08906304568486471,
"learning_rate": 0.00012356645782076383,
"loss": 0.9673,
"step": 1050
},
{
"epoch": 0.48,
"grad_norm": 0.08552583500630938,
"learning_rate": 0.00012278725319712447,
"loss": 0.9545,
"step": 1055
},
{
"epoch": 0.49,
"grad_norm": 0.08555288016156151,
"learning_rate": 0.00012200658648309531,
"loss": 0.9552,
"step": 1060
},
{
"epoch": 0.49,
"grad_norm": 0.08664206961589904,
"learning_rate": 0.00012122450776831594,
"loss": 0.9463,
"step": 1065
},
{
"epoch": 0.49,
"grad_norm": 0.08904216070092703,
"learning_rate": 0.00012044106723302364,
"loss": 0.9489,
"step": 1070
},
{
"epoch": 0.49,
"grad_norm": 0.08709170070909589,
"learning_rate": 0.00011965631514483375,
"loss": 0.9475,
"step": 1075
},
{
"epoch": 0.5,
"grad_norm": 0.08790044008622408,
"learning_rate": 0.00011887030185551426,
"loss": 0.9446,
"step": 1080
},
{
"epoch": 0.5,
"grad_norm": 0.08658875670552062,
"learning_rate": 0.00011808307779775518,
"loss": 0.9411,
"step": 1085
},
{
"epoch": 0.5,
"grad_norm": 0.0977471754063036,
"learning_rate": 0.00011729469348193262,
"loss": 0.9255,
"step": 1090
},
{
"epoch": 0.5,
"grad_norm": 0.08804945539452566,
"learning_rate": 0.00011650519949286795,
"loss": 0.9802,
"step": 1095
},
{
"epoch": 0.5,
"grad_norm": 0.08581976314554501,
"learning_rate": 0.00011571464648658201,
"loss": 0.9383,
"step": 1100
},
{
"epoch": 0.51,
"grad_norm": 0.08839470223710093,
"learning_rate": 0.00011492308518704506,
"loss": 0.9441,
"step": 1105
},
{
"epoch": 0.51,
"grad_norm": 0.08941383297565787,
"learning_rate": 0.00011413056638292215,
"loss": 0.9515,
"step": 1110
},
{
"epoch": 0.51,
"grad_norm": 0.08584986185665876,
"learning_rate": 0.00011333714092431423,
"loss": 0.9309,
"step": 1115
},
{
"epoch": 0.51,
"grad_norm": 0.0865352790700451,
"learning_rate": 0.00011254285971949574,
"loss": 0.9335,
"step": 1120
},
{
"epoch": 0.52,
"grad_norm": 0.0863789933194355,
"learning_rate": 0.00011174777373164798,
"loss": 0.9487,
"step": 1125
},
{
"epoch": 0.52,
"grad_norm": 0.08729028323407131,
"learning_rate": 0.0001109519339755893,
"loss": 0.9381,
"step": 1130
},
{
"epoch": 0.52,
"grad_norm": 0.08674945320440842,
"learning_rate": 0.00011015539151450172,
"loss": 0.9398,
"step": 1135
},
{
"epoch": 0.52,
"grad_norm": 0.09452409408655012,
"learning_rate": 0.00010935819745665477,
"loss": 0.9709,
"step": 1140
},
{
"epoch": 0.53,
"grad_norm": 0.0862575634432857,
"learning_rate": 0.00010856040295212612,
"loss": 0.9306,
"step": 1145
},
{
"epoch": 0.53,
"grad_norm": 0.08968733351995441,
"learning_rate": 0.00010776205918951969,
"loss": 0.9573,
"step": 1150
},
{
"epoch": 0.53,
"grad_norm": 0.0901921037984152,
"learning_rate": 0.00010696321739268121,
"loss": 0.964,
"step": 1155
},
{
"epoch": 0.53,
"grad_norm": 0.08958751346326631,
"learning_rate": 0.00010616392881741166,
"loss": 0.9563,
"step": 1160
},
{
"epoch": 0.53,
"grad_norm": 0.08935150733851532,
"learning_rate": 0.00010536424474817847,
"loss": 0.9281,
"step": 1165
},
{
"epoch": 0.54,
"grad_norm": 0.08505482136944548,
"learning_rate": 0.00010456421649482502,
"loss": 0.9522,
"step": 1170
},
{
"epoch": 0.54,
"grad_norm": 0.08977467093508296,
"learning_rate": 0.0001037638953892784,
"loss": 0.9515,
"step": 1175
},
{
"epoch": 0.54,
"grad_norm": 0.09103794206490902,
"learning_rate": 0.00010296333278225599,
"loss": 0.9488,
"step": 1180
},
{
"epoch": 0.54,
"grad_norm": 0.08855592795266524,
"learning_rate": 0.00010216258003997043,
"loss": 0.9382,
"step": 1185
},
{
"epoch": 0.55,
"grad_norm": 0.08551252341505816,
"learning_rate": 0.00010136168854083402,
"loss": 0.9592,
"step": 1190
},
{
"epoch": 0.55,
"grad_norm": 0.08711479138102324,
"learning_rate": 0.00010056070967216198,
"loss": 0.959,
"step": 1195
},
{
"epoch": 0.55,
"grad_norm": 0.08549275625721742,
"learning_rate": 9.975969482687547e-05,
"loss": 0.9449,
"step": 1200
},
{
"epoch": 0.55,
"grad_norm": 0.08888803602947658,
"learning_rate": 9.8958695400204e-05,
"loss": 0.9287,
"step": 1205
},
{
"epoch": 0.56,
"grad_norm": 0.08689172899821032,
"learning_rate": 9.815776278638771e-05,
"loss": 0.94,
"step": 1210
},
{
"epoch": 0.56,
"grad_norm": 0.09137637622059057,
"learning_rate": 9.735694837537993e-05,
"loss": 0.967,
"step": 1215
},
{
"epoch": 0.56,
"grad_norm": 0.08486290429115295,
"learning_rate": 9.655630354954974e-05,
"loss": 0.9324,
"step": 1220
},
{
"epoch": 0.56,
"grad_norm": 0.08503393222349716,
"learning_rate": 9.57558796803852e-05,
"loss": 0.9494,
"step": 1225
},
{
"epoch": 0.56,
"grad_norm": 0.0873443558033662,
"learning_rate": 9.495572812519718e-05,
"loss": 0.9506,
"step": 1230
},
{
"epoch": 0.57,
"grad_norm": 0.09121014808349219,
"learning_rate": 9.415590022382419e-05,
"loss": 0.9252,
"step": 1235
},
{
"epoch": 0.57,
"grad_norm": 0.086584430175237,
"learning_rate": 9.33564472953383e-05,
"loss": 0.9439,
"step": 1240
},
{
"epoch": 0.57,
"grad_norm": 0.08692310082632433,
"learning_rate": 9.255742063475228e-05,
"loss": 0.9297,
"step": 1245
},
{
"epoch": 0.57,
"grad_norm": 0.08990215639751623,
"learning_rate": 9.175887150972841e-05,
"loss": 0.9629,
"step": 1250
},
{
"epoch": 0.58,
"grad_norm": 0.08963253963139663,
"learning_rate": 9.096085115728902e-05,
"loss": 0.9642,
"step": 1255
},
{
"epoch": 0.58,
"grad_norm": 0.09194536883220446,
"learning_rate": 9.016341078052908e-05,
"loss": 0.9308,
"step": 1260
},
{
"epoch": 0.58,
"grad_norm": 0.0911811600503115,
"learning_rate": 8.936660154533069e-05,
"loss": 0.952,
"step": 1265
},
{
"epoch": 0.58,
"grad_norm": 0.08845398994221279,
"learning_rate": 8.857047457708023e-05,
"loss": 0.9676,
"step": 1270
},
{
"epoch": 0.59,
"grad_norm": 0.08623567977555162,
"learning_rate": 8.777508095738818e-05,
"loss": 0.9277,
"step": 1275
},
{
"epoch": 0.59,
"grad_norm": 0.0857316423044204,
"learning_rate": 8.698047172081128e-05,
"loss": 0.9472,
"step": 1280
},
{
"epoch": 0.59,
"grad_norm": 0.09001530302196627,
"learning_rate": 8.618669785157825e-05,
"loss": 0.9304,
"step": 1285
},
{
"epoch": 0.59,
"grad_norm": 0.09938874508667282,
"learning_rate": 8.539381028031837e-05,
"loss": 0.9644,
"step": 1290
},
{
"epoch": 0.59,
"grad_norm": 0.08956519091936009,
"learning_rate": 8.460185988079379e-05,
"loss": 0.9244,
"step": 1295
},
{
"epoch": 0.6,
"grad_norm": 0.09301102302473901,
"learning_rate": 8.381089746663517e-05,
"loss": 0.9469,
"step": 1300
},
{
"epoch": 0.6,
"grad_norm": 0.08856088507182096,
"learning_rate": 8.302097378808146e-05,
"loss": 0.9421,
"step": 1305
},
{
"epoch": 0.6,
"grad_norm": 0.08829957085883325,
"learning_rate": 8.223213952872353e-05,
"loss": 0.9752,
"step": 1310
},
{
"epoch": 0.6,
"grad_norm": 0.09355532885262087,
"learning_rate": 8.144444530225236e-05,
"loss": 0.9201,
"step": 1315
},
{
"epoch": 0.61,
"grad_norm": 0.08851734452569436,
"learning_rate": 8.065794164921128e-05,
"loss": 0.9556,
"step": 1320
},
{
"epoch": 0.61,
"grad_norm": 0.08801571017475394,
"learning_rate": 7.987267903375332e-05,
"loss": 0.9679,
"step": 1325
},
{
"epoch": 0.61,
"grad_norm": 0.08789034709036309,
"learning_rate": 7.90887078404033e-05,
"loss": 0.9704,
"step": 1330
},
{
"epoch": 0.61,
"grad_norm": 0.08766717856159563,
"learning_rate": 7.830607837082493e-05,
"loss": 0.9537,
"step": 1335
},
{
"epoch": 0.61,
"grad_norm": 0.08796194617668124,
"learning_rate": 7.75248408405934e-05,
"loss": 0.9295,
"step": 1340
},
{
"epoch": 0.62,
"grad_norm": 0.08644181932736543,
"learning_rate": 7.674504537597336e-05,
"loss": 0.9106,
"step": 1345
},
{
"epoch": 0.62,
"grad_norm": 0.08730172492521628,
"learning_rate": 7.596674201070282e-05,
"loss": 0.9247,
"step": 1350
},
{
"epoch": 0.62,
"grad_norm": 0.08810264581282028,
"learning_rate": 7.518998068278266e-05,
"loss": 0.941,
"step": 1355
},
{
"epoch": 0.62,
"grad_norm": 0.08798895320349515,
"learning_rate": 7.441481123127257e-05,
"loss": 0.9242,
"step": 1360
},
{
"epoch": 0.63,
"grad_norm": 0.09819188555964814,
"learning_rate": 7.364128339309326e-05,
"loss": 0.9216,
"step": 1365
},
{
"epoch": 0.63,
"grad_norm": 0.08880903672413525,
"learning_rate": 7.28694467998352e-05,
"loss": 0.9386,
"step": 1370
},
{
"epoch": 0.63,
"grad_norm": 0.08594152206617324,
"learning_rate": 7.209935097457413e-05,
"loss": 0.9365,
"step": 1375
},
{
"epoch": 0.63,
"grad_norm": 0.08716534615610971,
"learning_rate": 7.133104532869342e-05,
"loss": 0.9823,
"step": 1380
},
{
"epoch": 0.64,
"grad_norm": 0.08772796875372083,
"learning_rate": 7.056457915871399e-05,
"loss": 0.9526,
"step": 1385
},
{
"epoch": 0.64,
"grad_norm": 0.10720913898902203,
"learning_rate": 6.980000164313093e-05,
"loss": 0.9445,
"step": 1390
},
{
"epoch": 0.64,
"grad_norm": 0.09018703484669713,
"learning_rate": 6.903736183925835e-05,
"loss": 0.9479,
"step": 1395
},
{
"epoch": 0.64,
"grad_norm": 0.08733086798681411,
"learning_rate": 6.827670868008171e-05,
"loss": 0.9194,
"step": 1400
},
{
"epoch": 0.64,
"grad_norm": 0.0863528369966269,
"learning_rate": 6.751809097111798e-05,
"loss": 0.9483,
"step": 1405
},
{
"epoch": 0.65,
"grad_norm": 0.08631912201267505,
"learning_rate": 6.676155738728438e-05,
"loss": 0.9455,
"step": 1410
},
{
"epoch": 0.65,
"grad_norm": 0.08609745370001315,
"learning_rate": 6.600715646977502e-05,
"loss": 0.9413,
"step": 1415
},
{
"epoch": 0.65,
"grad_norm": 0.08629402800348958,
"learning_rate": 6.525493662294668e-05,
"loss": 0.9609,
"step": 1420
},
{
"epoch": 0.65,
"grad_norm": 0.08751936032063028,
"learning_rate": 6.450494611121273e-05,
"loss": 0.914,
"step": 1425
},
{
"epoch": 0.66,
"grad_norm": 0.08745706909629332,
"learning_rate": 6.375723305594658e-05,
"loss": 0.9217,
"step": 1430
},
{
"epoch": 0.66,
"grad_norm": 0.08641611663046964,
"learning_rate": 6.301184543239398e-05,
"loss": 0.9189,
"step": 1435
},
{
"epoch": 0.66,
"grad_norm": 0.08722147871097277,
"learning_rate": 6.226883106659485e-05,
"loss": 0.9371,
"step": 1440
},
{
"epoch": 0.66,
"grad_norm": 0.0899356065834259,
"learning_rate": 6.152823763231463e-05,
"loss": 0.9558,
"step": 1445
},
{
"epoch": 0.67,
"grad_norm": 0.08955527969440581,
"learning_rate": 6.079011264798534e-05,
"loss": 0.9291,
"step": 1450
},
{
"epoch": 0.67,
"grad_norm": 0.08576837808957845,
"learning_rate": 6.005450347365687e-05,
"loss": 0.9274,
"step": 1455
},
{
"epoch": 0.67,
"grad_norm": 0.08645095620943792,
"learning_rate": 5.932145730795793e-05,
"loss": 0.9598,
"step": 1460
},
{
"epoch": 0.67,
"grad_norm": 0.0869911444874417,
"learning_rate": 5.8591021185067876e-05,
"loss": 0.9363,
"step": 1465
},
{
"epoch": 0.67,
"grad_norm": 0.0873524141173332,
"learning_rate": 5.786324197169887e-05,
"loss": 0.9422,
"step": 1470
},
{
"epoch": 0.68,
"grad_norm": 0.08911905819028881,
"learning_rate": 5.7138166364088705e-05,
"loss": 0.9087,
"step": 1475
},
{
"epoch": 0.68,
"grad_norm": 0.08693990530615593,
"learning_rate": 5.641584088500461e-05,
"loss": 0.9429,
"step": 1480
},
{
"epoch": 0.68,
"grad_norm": 0.08924602848888696,
"learning_rate": 5.569631188075841e-05,
"loss": 0.9371,
"step": 1485
},
{
"epoch": 0.68,
"grad_norm": 0.08914866066749584,
"learning_rate": 5.497962551823266e-05,
"loss": 0.9531,
"step": 1490
},
{
"epoch": 0.69,
"grad_norm": 0.08529396225999064,
"learning_rate": 5.4265827781918576e-05,
"loss": 0.9566,
"step": 1495
},
{
"epoch": 0.69,
"grad_norm": 0.08823829670606588,
"learning_rate": 5.355496447096533e-05,
"loss": 0.9364,
"step": 1500
},
{
"epoch": 0.69,
"grad_norm": 0.08772222657507125,
"learning_rate": 5.284708119624173e-05,
"loss": 0.9432,
"step": 1505
},
{
"epoch": 0.69,
"grad_norm": 0.08557062679793,
"learning_rate": 5.214222337740962e-05,
"loss": 0.9262,
"step": 1510
},
{
"epoch": 0.7,
"grad_norm": 0.08659945848240291,
"learning_rate": 5.144043624000944e-05,
"loss": 0.9345,
"step": 1515
},
{
"epoch": 0.7,
"grad_norm": 0.08848309633261352,
"learning_rate": 5.0741764812558724e-05,
"loss": 0.9383,
"step": 1520
},
{
"epoch": 0.7,
"grad_norm": 0.08846095794944839,
"learning_rate": 5.00462539236628e-05,
"loss": 0.9187,
"step": 1525
},
{
"epoch": 0.7,
"grad_norm": 0.08813900803993555,
"learning_rate": 4.935394819913849e-05,
"loss": 0.9312,
"step": 1530
},
{
"epoch": 0.7,
"grad_norm": 0.09209963741468702,
"learning_rate": 4.8664892059150723e-05,
"loss": 0.9598,
"step": 1535
},
{
"epoch": 0.71,
"grad_norm": 0.08771530518180069,
"learning_rate": 4.7979129715362626e-05,
"loss": 0.9474,
"step": 1540
},
{
"epoch": 0.71,
"grad_norm": 0.08792286254368877,
"learning_rate": 4.72967051680985e-05,
"loss": 0.957,
"step": 1545
},
{
"epoch": 0.71,
"grad_norm": 0.08941277401969798,
"learning_rate": 4.661766220352097e-05,
"loss": 0.9378,
"step": 1550
},
{
"epoch": 0.71,
"grad_norm": 0.09121672960781078,
"learning_rate": 4.5942044390821214e-05,
"loss": 0.9483,
"step": 1555
},
{
"epoch": 0.72,
"grad_norm": 0.08879176023561161,
"learning_rate": 4.526989507942374e-05,
"loss": 0.931,
"step": 1560
},
{
"epoch": 0.72,
"grad_norm": 0.0883812911577774,
"learning_rate": 4.460125739620479e-05,
"loss": 0.9406,
"step": 1565
},
{
"epoch": 0.72,
"grad_norm": 0.09091739732819643,
"learning_rate": 4.393617424272527e-05,
"loss": 0.943,
"step": 1570
},
{
"epoch": 0.72,
"grad_norm": 0.08712923953000383,
"learning_rate": 4.3274688292478106e-05,
"loss": 0.924,
"step": 1575
},
{
"epoch": 0.73,
"grad_norm": 0.08764495954523147,
"learning_rate": 4.261684198815003e-05,
"loss": 0.9421,
"step": 1580
},
{
"epoch": 0.73,
"grad_norm": 0.08942249793670395,
"learning_rate": 4.1962677538898645e-05,
"loss": 0.9285,
"step": 1585
},
{
"epoch": 0.73,
"grad_norm": 0.0912127042783993,
"learning_rate": 4.131223691764383e-05,
"loss": 0.9279,
"step": 1590
},
{
"epoch": 0.73,
"grad_norm": 0.08585042904329478,
"learning_rate": 4.0665561858374934e-05,
"loss": 0.9624,
"step": 1595
},
{
"epoch": 0.73,
"grad_norm": 0.0878958377245175,
"learning_rate": 4.0022693853472884e-05,
"loss": 0.9198,
"step": 1600
},
{
"epoch": 0.74,
"grad_norm": 0.09047554656699612,
"learning_rate": 3.938367415104793e-05,
"loss": 0.9482,
"step": 1605
},
{
"epoch": 0.74,
"grad_norm": 0.08814416840573022,
"learning_rate": 3.8748543752293e-05,
"loss": 0.9356,
"step": 1610
},
{
"epoch": 0.74,
"grad_norm": 0.08723692471240356,
"learning_rate": 3.8117343408853127e-05,
"loss": 0.9278,
"step": 1615
},
{
"epoch": 0.74,
"grad_norm": 0.08717485150452346,
"learning_rate": 3.7490113620210485e-05,
"loss": 0.9524,
"step": 1620
},
{
"epoch": 0.75,
"grad_norm": 0.08692486607533598,
"learning_rate": 3.686689463108608e-05,
"loss": 0.9643,
"step": 1625
},
{
"epoch": 0.75,
"grad_norm": 0.0884000414734674,
"learning_rate": 3.624772642885734e-05,
"loss": 0.9325,
"step": 1630
},
{
"epoch": 0.75,
"grad_norm": 0.08869428008386021,
"learning_rate": 3.563264874099258e-05,
"loss": 0.9287,
"step": 1635
},
{
"epoch": 0.75,
"grad_norm": 0.08820910205821329,
"learning_rate": 3.502170103250177e-05,
"loss": 0.9302,
"step": 1640
},
{
"epoch": 0.75,
"grad_norm": 0.08861971632371925,
"learning_rate": 3.441492250340461e-05,
"loss": 0.9585,
"step": 1645
},
{
"epoch": 0.76,
"grad_norm": 0.0894936060024211,
"learning_rate": 3.381235208621522e-05,
"loss": 0.9308,
"step": 1650
},
{
"epoch": 0.76,
"grad_norm": 0.08873703732670399,
"learning_rate": 3.3214028443444036e-05,
"loss": 0.9566,
"step": 1655
},
{
"epoch": 0.76,
"grad_norm": 0.08737818209354478,
"learning_rate": 3.2619989965117356e-05,
"loss": 0.9498,
"step": 1660
},
{
"epoch": 0.76,
"grad_norm": 0.08766867092475095,
"learning_rate": 3.2030274766313865e-05,
"loss": 0.967,
"step": 1665
},
{
"epoch": 0.77,
"grad_norm": 0.08557302682938876,
"learning_rate": 3.1444920684719394e-05,
"loss": 0.9263,
"step": 1670
},
{
"epoch": 0.77,
"grad_norm": 0.08700645088876224,
"learning_rate": 3.086396527819876e-05,
"loss": 0.9468,
"step": 1675
},
{
"epoch": 0.77,
"grad_norm": 0.08747938373180429,
"learning_rate": 3.028744582238633e-05,
"loss": 0.9313,
"step": 1680
},
{
"epoch": 0.77,
"grad_norm": 0.08729419364535573,
"learning_rate": 2.9715399308294e-05,
"loss": 0.9397,
"step": 1685
},
{
"epoch": 0.78,
"grad_norm": 0.08469658948344076,
"learning_rate": 2.914786243993808e-05,
"loss": 0.9289,
"step": 1690
},
{
"epoch": 0.78,
"grad_norm": 0.08761596719724722,
"learning_rate": 2.8584871631983888e-05,
"loss": 0.9445,
"step": 1695
},
{
"epoch": 0.78,
"grad_norm": 0.08867345772765582,
"learning_rate": 2.8026463007409664e-05,
"loss": 0.9411,
"step": 1700
},
{
"epoch": 0.78,
"grad_norm": 0.08862291602018178,
"learning_rate": 2.747267239518857e-05,
"loss": 0.9211,
"step": 1705
},
{
"epoch": 0.78,
"grad_norm": 0.0880959695459882,
"learning_rate": 2.6923535327989924e-05,
"loss": 0.9366,
"step": 1710
},
{
"epoch": 0.79,
"grad_norm": 0.08567801939104099,
"learning_rate": 2.637908703989924e-05,
"loss": 0.923,
"step": 1715
},
{
"epoch": 0.79,
"grad_norm": 0.08783102422275266,
"learning_rate": 2.5839362464157634e-05,
"loss": 0.9446,
"step": 1720
},
{
"epoch": 0.79,
"grad_norm": 0.08738566610637465,
"learning_rate": 2.5304396230920345e-05,
"loss": 0.9494,
"step": 1725
},
{
"epoch": 0.79,
"grad_norm": 0.08754716332558513,
"learning_rate": 2.477422266503473e-05,
"loss": 0.9261,
"step": 1730
},
{
"epoch": 0.8,
"grad_norm": 0.08938747413217578,
"learning_rate": 2.4248875783837987e-05,
"loss": 0.9522,
"step": 1735
},
{
"epoch": 0.8,
"grad_norm": 0.09156561613392297,
"learning_rate": 2.3728389294974475e-05,
"loss": 0.949,
"step": 1740
},
{
"epoch": 0.8,
"grad_norm": 0.09048390614208174,
"learning_rate": 2.3212796594232943e-05,
"loss": 0.9302,
"step": 1745
},
{
"epoch": 0.8,
"grad_norm": 0.08934599478933157,
"learning_rate": 2.2702130763403673e-05,
"loss": 0.9688,
"step": 1750
},
{
"epoch": 0.81,
"grad_norm": 0.08845439903331347,
"learning_rate": 2.2196424568156073e-05,
"loss": 0.9303,
"step": 1755
},
{
"epoch": 0.81,
"grad_norm": 0.08832857380862127,
"learning_rate": 2.1695710455936115e-05,
"loss": 0.9416,
"step": 1760
},
{
"epoch": 0.81,
"grad_norm": 0.08892222595846298,
"learning_rate": 2.1200020553884604e-05,
"loss": 0.9518,
"step": 1765
},
{
"epoch": 0.81,
"grad_norm": 0.08649233810401519,
"learning_rate": 2.070938666677573e-05,
"loss": 0.942,
"step": 1770
},
{
"epoch": 0.81,
"grad_norm": 0.0900743762289211,
"learning_rate": 2.0223840274976413e-05,
"loss": 0.9576,
"step": 1775
},
{
"epoch": 0.82,
"grad_norm": 0.08695584735679976,
"learning_rate": 1.974341253242635e-05,
"loss": 0.9542,
"step": 1780
},
{
"epoch": 0.82,
"grad_norm": 0.08744798511286825,
"learning_rate": 1.9268134264639272e-05,
"loss": 0.959,
"step": 1785
},
{
"epoch": 0.82,
"grad_norm": 0.08747274450074151,
"learning_rate": 1.879803596672497e-05,
"loss": 0.9173,
"step": 1790
},
{
"epoch": 0.82,
"grad_norm": 0.0918571830857398,
"learning_rate": 1.8333147801432614e-05,
"loss": 0.9476,
"step": 1795
},
{
"epoch": 0.83,
"grad_norm": 0.08982466572383123,
"learning_rate": 1.7873499597215604e-05,
"loss": 0.9323,
"step": 1800
},
{
"epoch": 0.83,
"grad_norm": 0.08759844398854984,
"learning_rate": 1.741912084631746e-05,
"loss": 0.97,
"step": 1805
},
{
"epoch": 0.83,
"grad_norm": 0.09055340730791506,
"learning_rate": 1.697004070287982e-05,
"loss": 0.939,
"step": 1810
},
{
"epoch": 0.83,
"grad_norm": 0.09056007317649489,
"learning_rate": 1.6526287981071475e-05,
"loss": 0.9629,
"step": 1815
},
{
"epoch": 0.84,
"grad_norm": 0.08589739963435682,
"learning_rate": 1.608789115323993e-05,
"loss": 0.9451,
"step": 1820
},
{
"epoch": 0.84,
"grad_norm": 0.08640941835070298,
"learning_rate": 1.5654878348084244e-05,
"loss": 0.9197,
"step": 1825
},
{
"epoch": 0.84,
"grad_norm": 0.08910530693806586,
"learning_rate": 1.5227277348850466e-05,
"loss": 0.9494,
"step": 1830
},
{
"epoch": 0.84,
"grad_norm": 0.08850326334733846,
"learning_rate": 1.4805115591548746e-05,
"loss": 0.9228,
"step": 1835
},
{
"epoch": 0.84,
"grad_norm": 0.08689898885121261,
"learning_rate": 1.4388420163193217e-05,
"loss": 0.9432,
"step": 1840
},
{
"epoch": 0.85,
"grad_norm": 0.08505242590609849,
"learning_rate": 1.3977217800063846e-05,
"loss": 0.9347,
"step": 1845
},
{
"epoch": 0.85,
"grad_norm": 0.09147654680555943,
"learning_rate": 1.3571534885991044e-05,
"loss": 0.9308,
"step": 1850
},
{
"epoch": 0.85,
"grad_norm": 0.09022868476385788,
"learning_rate": 1.3171397450662715e-05,
"loss": 0.948,
"step": 1855
},
{
"epoch": 0.85,
"grad_norm": 0.08685234829482098,
"learning_rate": 1.277683116795425e-05,
"loss": 0.92,
"step": 1860
},
{
"epoch": 0.86,
"grad_norm": 0.08814308202101184,
"learning_rate": 1.2387861354281194e-05,
"loss": 0.9362,
"step": 1865
},
{
"epoch": 0.86,
"grad_norm": 0.0851637412899579,
"learning_rate": 1.2004512966974745e-05,
"loss": 0.9366,
"step": 1870
},
{
"epoch": 0.86,
"grad_norm": 0.08894109019360302,
"learning_rate": 1.162681060268065e-05,
"loss": 0.9439,
"step": 1875
},
{
"epoch": 0.86,
"grad_norm": 0.08621574297233676,
"learning_rate": 1.1254778495780748e-05,
"loss": 0.917,
"step": 1880
},
{
"epoch": 0.87,
"grad_norm": 0.09245233519670913,
"learning_rate": 1.0888440516838373e-05,
"loss": 0.9506,
"step": 1885
},
{
"epoch": 0.87,
"grad_norm": 0.09044369763554148,
"learning_rate": 1.0527820171066372e-05,
"loss": 0.9303,
"step": 1890
},
{
"epoch": 0.87,
"grad_norm": 0.09008186958818373,
"learning_rate": 1.0172940596819259e-05,
"loss": 0.9411,
"step": 1895
},
{
"epoch": 0.87,
"grad_norm": 0.0904602032108916,
"learning_rate": 9.823824564108408e-06,
"loss": 0.94,
"step": 1900
},
{
"epoch": 0.87,
"grad_norm": 0.08715850828856053,
"learning_rate": 9.480494473141188e-06,
"loss": 0.9474,
"step": 1905
},
{
"epoch": 0.88,
"grad_norm": 0.08874174744461717,
"learning_rate": 9.142972352883594e-06,
"loss": 0.9604,
"step": 1910
},
{
"epoch": 0.88,
"grad_norm": 0.08626507990923932,
"learning_rate": 8.811279859646915e-06,
"loss": 0.9371,
"step": 1915
},
{
"epoch": 0.88,
"grad_norm": 0.08536401487047512,
"learning_rate": 8.485438275698154e-06,
"loss": 0.9478,
"step": 1920
},
{
"epoch": 0.88,
"grad_norm": 0.08762760613175481,
"learning_rate": 8.165468507894514e-06,
"loss": 0.9619,
"step": 1925
},
{
"epoch": 0.89,
"grad_norm": 0.08649803369527974,
"learning_rate": 7.851391086341952e-06,
"loss": 0.9213,
"step": 1930
},
{
"epoch": 0.89,
"grad_norm": 0.0863185912090572,
"learning_rate": 7.543226163077899e-06,
"loss": 0.9398,
"step": 1935
},
{
"epoch": 0.89,
"grad_norm": 0.08832161267172574,
"learning_rate": 7.240993510778305e-06,
"loss": 0.9355,
"step": 1940
},
{
"epoch": 0.89,
"grad_norm": 0.08872195570007042,
"learning_rate": 6.9447125214888835e-06,
"loss": 0.9484,
"step": 1945
},
{
"epoch": 0.89,
"grad_norm": 0.08537888004129789,
"learning_rate": 6.65440220538096e-06,
"loss": 0.937,
"step": 1950
},
{
"epoch": 0.9,
"grad_norm": 0.08646668763284765,
"learning_rate": 6.370081189531707e-06,
"loss": 0.9266,
"step": 1955
},
{
"epoch": 0.9,
"grad_norm": 0.09151612686918877,
"learning_rate": 6.091767716728924e-06,
"loss": 0.9529,
"step": 1960
},
{
"epoch": 0.9,
"grad_norm": 0.08625391503125818,
"learning_rate": 5.819479644300563e-06,
"loss": 0.9623,
"step": 1965
},
{
"epoch": 0.9,
"grad_norm": 0.09219046541541549,
"learning_rate": 5.553234442969013e-06,
"loss": 0.9421,
"step": 1970
},
{
"epoch": 0.91,
"grad_norm": 0.08774543131766023,
"learning_rate": 5.293049195730038e-06,
"loss": 0.9419,
"step": 1975
},
{
"epoch": 0.91,
"grad_norm": 0.08654274395119196,
"learning_rate": 5.038940596756747e-06,
"loss": 0.9575,
"step": 1980
},
{
"epoch": 0.91,
"grad_norm": 0.0876337850241222,
"learning_rate": 4.790924950328435e-06,
"loss": 0.9391,
"step": 1985
},
{
"epoch": 0.91,
"grad_norm": 0.08639018592656753,
"learning_rate": 4.5490181697844916e-06,
"loss": 0.9333,
"step": 1990
},
{
"epoch": 0.92,
"grad_norm": 0.0873104746399997,
"learning_rate": 4.313235776503244e-06,
"loss": 0.9793,
"step": 1995
},
{
"epoch": 0.92,
"grad_norm": 0.09228098479128997,
"learning_rate": 4.08359289890623e-06,
"loss": 0.9282,
"step": 2000
},
{
"epoch": 0.92,
"grad_norm": 0.08822164948945242,
"learning_rate": 3.860104271487397e-06,
"loss": 0.9332,
"step": 2005
},
{
"epoch": 0.92,
"grad_norm": 0.08678259126429717,
"learning_rate": 3.6427842338677352e-06,
"loss": 0.936,
"step": 2010
},
{
"epoch": 0.92,
"grad_norm": 0.0881737292442483,
"learning_rate": 3.4316467298752263e-06,
"loss": 0.9625,
"step": 2015
},
{
"epoch": 0.93,
"grad_norm": 0.09213889711272016,
"learning_rate": 3.226705306650113e-06,
"loss": 0.9649,
"step": 2020
},
{
"epoch": 0.93,
"grad_norm": 0.08904039321814257,
"learning_rate": 3.0279731137757948e-06,
"loss": 0.9177,
"step": 2025
},
{
"epoch": 0.93,
"grad_norm": 0.08671758256460199,
"learning_rate": 2.835462902434971e-06,
"loss": 0.9362,
"step": 2030
},
{
"epoch": 0.93,
"grad_norm": 0.08617851604946536,
"learning_rate": 2.649187024591604e-06,
"loss": 0.9233,
"step": 2035
},
{
"epoch": 0.94,
"grad_norm": 0.08788489883371325,
"learning_rate": 2.4691574321983215e-06,
"loss": 0.9627,
"step": 2040
},
{
"epoch": 0.94,
"grad_norm": 0.08882492486063351,
"learning_rate": 2.2953856764295624e-06,
"loss": 0.9539,
"step": 2045
},
{
"epoch": 0.94,
"grad_norm": 0.08894914791155306,
"learning_rate": 2.1278829069404484e-06,
"loss": 0.9547,
"step": 2050
},
{
"epoch": 0.94,
"grad_norm": 0.08942232005808806,
"learning_rate": 1.966659871151366e-06,
"loss": 0.9457,
"step": 2055
},
{
"epoch": 0.95,
"grad_norm": 0.0878596216919505,
"learning_rate": 1.811726913558387e-06,
"loss": 0.9401,
"step": 2060
},
{
"epoch": 0.95,
"grad_norm": 0.08624565992036248,
"learning_rate": 1.6630939750695519e-06,
"loss": 0.9283,
"step": 2065
},
{
"epoch": 0.95,
"grad_norm": 0.08751905040079597,
"learning_rate": 1.5207705923670157e-06,
"loss": 0.9361,
"step": 2070
},
{
"epoch": 0.95,
"grad_norm": 0.08655512741877175,
"learning_rate": 1.3847658972951483e-06,
"loss": 0.9351,
"step": 2075
},
{
"epoch": 0.95,
"grad_norm": 0.08957313404563644,
"learning_rate": 1.2550886162746467e-06,
"loss": 0.952,
"step": 2080
},
{
"epoch": 0.96,
"grad_norm": 0.08660110151814926,
"learning_rate": 1.1317470697425837e-06,
"loss": 0.952,
"step": 2085
},
{
"epoch": 0.96,
"grad_norm": 0.08972626387226099,
"learning_rate": 1.0147491716185676e-06,
"loss": 0.9009,
"step": 2090
},
{
"epoch": 0.96,
"grad_norm": 0.08970864022551972,
"learning_rate": 9.04102428796949e-07,
"loss": 0.9323,
"step": 2095
},
{
"epoch": 0.96,
"grad_norm": 0.08435882797271965,
"learning_rate": 7.99813940665195e-07,
"loss": 0.9112,
"step": 2100
},
{
"epoch": 0.97,
"grad_norm": 0.09018316452815832,
"learning_rate": 7.018903986483083e-07,
"loss": 0.9663,
"step": 2105
},
{
"epoch": 0.97,
"grad_norm": 0.08893420874426604,
"learning_rate": 6.103380857795604e-07,
"loss": 0.9607,
"step": 2110
},
{
"epoch": 0.97,
"grad_norm": 0.08572861346513169,
"learning_rate": 5.251628762972916e-07,
"loss": 0.9447,
"step": 2115
},
{
"epoch": 0.97,
"grad_norm": 0.08774975368376736,
"learning_rate": 4.463702352680787e-07,
"loss": 0.9385,
"step": 2120
},
{
"epoch": 0.98,
"grad_norm": 0.08689461932505746,
"learning_rate": 3.7396521823600537e-07,
"loss": 0.9274,
"step": 2125
},
{
"epoch": 0.98,
"grad_norm": 0.09004858281896364,
"learning_rate": 3.079524708983095e-07,
"loss": 0.913,
"step": 2130
},
{
"epoch": 0.98,
"grad_norm": 0.08569955277802684,
"learning_rate": 2.483362288073443e-07,
"loss": 0.9154,
"step": 2135
},
{
"epoch": 0.98,
"grad_norm": 0.0871518933503058,
"learning_rate": 1.9512031709874035e-07,
"loss": 0.9185,
"step": 2140
},
{
"epoch": 0.98,
"grad_norm": 0.08625979911743939,
"learning_rate": 1.4830815024606815e-07,
"loss": 0.9531,
"step": 2145
},
{
"epoch": 0.99,
"grad_norm": 0.08834947806834018,
"learning_rate": 1.0790273184164701e-07,
"loss": 0.9524,
"step": 2150
},
{
"epoch": 0.99,
"grad_norm": 0.09003565411089794,
"learning_rate": 7.390665440393241e-08,
"loss": 0.9328,
"step": 2155
},
{
"epoch": 0.99,
"grad_norm": 0.08858802189320047,
"learning_rate": 4.632209921107134e-08,
"loss": 0.9394,
"step": 2160
},
{
"epoch": 0.99,
"grad_norm": 0.08654302372571418,
"learning_rate": 2.5150836161058622e-08,
"loss": 0.9371,
"step": 2165
},
{
"epoch": 1.0,
"grad_norm": 0.08900054318893043,
"learning_rate": 1.03942236580723e-08,
"loss": 0.9539,
"step": 2170
},
{
"epoch": 1.0,
"grad_norm": 0.08775869737859891,
"learning_rate": 2.053208525365502e-09,
"loss": 0.9452,
"step": 2175
},
{
"epoch": 1.0,
"eval_loss": 0.9438490867614746,
"eval_runtime": 602.9143,
"eval_samples_per_second": 25.594,
"eval_steps_per_second": 0.401,
"step": 2179
},
{
"epoch": 1.0,
"step": 2179,
"total_flos": 3.4589037545127936e+16,
"train_loss": 0.951526911010322,
"train_runtime": 20629.7225,
"train_samples_per_second": 6.758,
"train_steps_per_second": 0.106
}
],
"logging_steps": 5,
"max_steps": 2179,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 3.4589037545127936e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}