ZMC2019's picture
Training in progress, step 1650, checkpoint
d6770d5 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.537744641192917,
"eval_steps": 500,
"global_step": 1650,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004659832246039142,
"grad_norm": 55.709484937361424,
"learning_rate": 7.763975155279503e-07,
"loss": 11.0694,
"step": 5
},
{
"epoch": 0.009319664492078284,
"grad_norm": 57.1398137451701,
"learning_rate": 1.5527950310559006e-06,
"loss": 10.8846,
"step": 10
},
{
"epoch": 0.013979496738117428,
"grad_norm": 97.98047478379912,
"learning_rate": 2.329192546583851e-06,
"loss": 9.4413,
"step": 15
},
{
"epoch": 0.01863932898415657,
"grad_norm": 32.76887701215898,
"learning_rate": 3.1055900621118013e-06,
"loss": 3.214,
"step": 20
},
{
"epoch": 0.023299161230195712,
"grad_norm": 3.315394944010228,
"learning_rate": 3.881987577639752e-06,
"loss": 1.346,
"step": 25
},
{
"epoch": 0.027958993476234855,
"grad_norm": 1.29231664681427,
"learning_rate": 4.658385093167702e-06,
"loss": 1.006,
"step": 30
},
{
"epoch": 0.032618825722273995,
"grad_norm": 0.8629586527731651,
"learning_rate": 5.4347826086956525e-06,
"loss": 0.8411,
"step": 35
},
{
"epoch": 0.03727865796831314,
"grad_norm": 0.6212648141101664,
"learning_rate": 6.2111801242236025e-06,
"loss": 0.7754,
"step": 40
},
{
"epoch": 0.04193849021435228,
"grad_norm": 0.46040470834395936,
"learning_rate": 6.9875776397515525e-06,
"loss": 0.7136,
"step": 45
},
{
"epoch": 0.046598322460391424,
"grad_norm": 0.42693871288027446,
"learning_rate": 7.763975155279503e-06,
"loss": 0.6831,
"step": 50
},
{
"epoch": 0.05125815470643057,
"grad_norm": 0.44192720551532577,
"learning_rate": 8.540372670807453e-06,
"loss": 0.646,
"step": 55
},
{
"epoch": 0.05591798695246971,
"grad_norm": 0.31222059058105195,
"learning_rate": 9.316770186335403e-06,
"loss": 0.6088,
"step": 60
},
{
"epoch": 0.06057781919850885,
"grad_norm": 0.30027349299916717,
"learning_rate": 1.0093167701863353e-05,
"loss": 0.5932,
"step": 65
},
{
"epoch": 0.06523765144454799,
"grad_norm": 0.3320480978786744,
"learning_rate": 1.0869565217391305e-05,
"loss": 0.5892,
"step": 70
},
{
"epoch": 0.06989748369058714,
"grad_norm": 0.3001101299512147,
"learning_rate": 1.1645962732919255e-05,
"loss": 0.5713,
"step": 75
},
{
"epoch": 0.07455731593662628,
"grad_norm": 0.30892715626333545,
"learning_rate": 1.2422360248447205e-05,
"loss": 0.5619,
"step": 80
},
{
"epoch": 0.07921714818266543,
"grad_norm": 0.3319072685834915,
"learning_rate": 1.3198757763975155e-05,
"loss": 0.5525,
"step": 85
},
{
"epoch": 0.08387698042870456,
"grad_norm": 0.29047402255141175,
"learning_rate": 1.3975155279503105e-05,
"loss": 0.5628,
"step": 90
},
{
"epoch": 0.08853681267474371,
"grad_norm": 0.25922715271689156,
"learning_rate": 1.4751552795031057e-05,
"loss": 0.5443,
"step": 95
},
{
"epoch": 0.09319664492078285,
"grad_norm": 0.31531185304643106,
"learning_rate": 1.5527950310559007e-05,
"loss": 0.5296,
"step": 100
},
{
"epoch": 0.097856477166822,
"grad_norm": 0.3013647908850556,
"learning_rate": 1.630434782608696e-05,
"loss": 0.5243,
"step": 105
},
{
"epoch": 0.10251630941286113,
"grad_norm": 0.3047350591065195,
"learning_rate": 1.7080745341614907e-05,
"loss": 0.5261,
"step": 110
},
{
"epoch": 0.10717614165890028,
"grad_norm": 0.30780196150291267,
"learning_rate": 1.785714285714286e-05,
"loss": 0.5231,
"step": 115
},
{
"epoch": 0.11183597390493942,
"grad_norm": 0.3804666896095633,
"learning_rate": 1.8633540372670807e-05,
"loss": 0.5098,
"step": 120
},
{
"epoch": 0.11649580615097857,
"grad_norm": 0.2868238329098672,
"learning_rate": 1.940993788819876e-05,
"loss": 0.5057,
"step": 125
},
{
"epoch": 0.1211556383970177,
"grad_norm": 0.32341698454060924,
"learning_rate": 2.0186335403726707e-05,
"loss": 0.5114,
"step": 130
},
{
"epoch": 0.12581547064305684,
"grad_norm": 0.4221000244611152,
"learning_rate": 2.096273291925466e-05,
"loss": 0.5106,
"step": 135
},
{
"epoch": 0.13047530288909598,
"grad_norm": 0.47197386491626697,
"learning_rate": 2.173913043478261e-05,
"loss": 0.4951,
"step": 140
},
{
"epoch": 0.13513513513513514,
"grad_norm": 0.3721540533945164,
"learning_rate": 2.2515527950310562e-05,
"loss": 0.522,
"step": 145
},
{
"epoch": 0.13979496738117428,
"grad_norm": 0.4388944569421825,
"learning_rate": 2.329192546583851e-05,
"loss": 0.4959,
"step": 150
},
{
"epoch": 0.14445479962721341,
"grad_norm": 0.4622898334441083,
"learning_rate": 2.4068322981366462e-05,
"loss": 0.5041,
"step": 155
},
{
"epoch": 0.14911463187325255,
"grad_norm": 0.49630920093444675,
"learning_rate": 2.484472049689441e-05,
"loss": 0.4849,
"step": 160
},
{
"epoch": 0.15377446411929171,
"grad_norm": 0.46849210325540636,
"learning_rate": 2.5621118012422362e-05,
"loss": 0.4961,
"step": 165
},
{
"epoch": 0.15843429636533085,
"grad_norm": 0.4082563546888238,
"learning_rate": 2.639751552795031e-05,
"loss": 0.4719,
"step": 170
},
{
"epoch": 0.16309412861137,
"grad_norm": 0.4549138940471945,
"learning_rate": 2.7173913043478262e-05,
"loss": 0.4852,
"step": 175
},
{
"epoch": 0.16775396085740912,
"grad_norm": 0.41032309538662626,
"learning_rate": 2.795031055900621e-05,
"loss": 0.478,
"step": 180
},
{
"epoch": 0.1724137931034483,
"grad_norm": 0.36866874054662224,
"learning_rate": 2.8726708074534165e-05,
"loss": 0.481,
"step": 185
},
{
"epoch": 0.17707362534948742,
"grad_norm": 0.36280659725390446,
"learning_rate": 2.9503105590062114e-05,
"loss": 0.4908,
"step": 190
},
{
"epoch": 0.18173345759552656,
"grad_norm": 0.4446282244198985,
"learning_rate": 3.0279503105590062e-05,
"loss": 0.4802,
"step": 195
},
{
"epoch": 0.1863932898415657,
"grad_norm": 0.4818264381472692,
"learning_rate": 3.1055900621118014e-05,
"loss": 0.4818,
"step": 200
},
{
"epoch": 0.19105312208760486,
"grad_norm": 0.5191372230429591,
"learning_rate": 3.183229813664597e-05,
"loss": 0.4708,
"step": 205
},
{
"epoch": 0.195712954333644,
"grad_norm": 0.5690145277815086,
"learning_rate": 3.260869565217392e-05,
"loss": 0.4848,
"step": 210
},
{
"epoch": 0.20037278657968313,
"grad_norm": 0.41006685540485915,
"learning_rate": 3.3385093167701865e-05,
"loss": 0.467,
"step": 215
},
{
"epoch": 0.20503261882572227,
"grad_norm": 0.47272355547942274,
"learning_rate": 3.4161490683229814e-05,
"loss": 0.4716,
"step": 220
},
{
"epoch": 0.2096924510717614,
"grad_norm": 0.5135260711958035,
"learning_rate": 3.493788819875777e-05,
"loss": 0.4536,
"step": 225
},
{
"epoch": 0.21435228331780057,
"grad_norm": 0.5124408748792798,
"learning_rate": 3.571428571428572e-05,
"loss": 0.467,
"step": 230
},
{
"epoch": 0.2190121155638397,
"grad_norm": 0.4205466417850958,
"learning_rate": 3.6490683229813665e-05,
"loss": 0.4647,
"step": 235
},
{
"epoch": 0.22367194780987884,
"grad_norm": 0.6251611138936444,
"learning_rate": 3.7267080745341614e-05,
"loss": 0.4624,
"step": 240
},
{
"epoch": 0.22833178005591798,
"grad_norm": 0.5610747747609784,
"learning_rate": 3.804347826086957e-05,
"loss": 0.4676,
"step": 245
},
{
"epoch": 0.23299161230195714,
"grad_norm": 0.4692752738735764,
"learning_rate": 3.881987577639752e-05,
"loss": 0.4592,
"step": 250
},
{
"epoch": 0.23765144454799628,
"grad_norm": 0.5435654364057863,
"learning_rate": 3.9596273291925465e-05,
"loss": 0.4679,
"step": 255
},
{
"epoch": 0.2423112767940354,
"grad_norm": 0.5264727485653637,
"learning_rate": 4.0372670807453414e-05,
"loss": 0.463,
"step": 260
},
{
"epoch": 0.24697110904007455,
"grad_norm": 0.5096976732033014,
"learning_rate": 4.114906832298137e-05,
"loss": 0.4613,
"step": 265
},
{
"epoch": 0.2516309412861137,
"grad_norm": 0.4649125930738299,
"learning_rate": 4.192546583850932e-05,
"loss": 0.4594,
"step": 270
},
{
"epoch": 0.25629077353215285,
"grad_norm": 0.5173502447936299,
"learning_rate": 4.270186335403727e-05,
"loss": 0.4652,
"step": 275
},
{
"epoch": 0.26095060577819196,
"grad_norm": 0.3868002746815184,
"learning_rate": 4.347826086956522e-05,
"loss": 0.4572,
"step": 280
},
{
"epoch": 0.2656104380242311,
"grad_norm": 0.5001940885551612,
"learning_rate": 4.425465838509317e-05,
"loss": 0.4613,
"step": 285
},
{
"epoch": 0.2702702702702703,
"grad_norm": 0.6213239402228385,
"learning_rate": 4.5031055900621124e-05,
"loss": 0.4633,
"step": 290
},
{
"epoch": 0.2749301025163094,
"grad_norm": 0.6125652570862165,
"learning_rate": 4.580745341614907e-05,
"loss": 0.4673,
"step": 295
},
{
"epoch": 0.27958993476234856,
"grad_norm": 0.7479197761570839,
"learning_rate": 4.658385093167702e-05,
"loss": 0.4693,
"step": 300
},
{
"epoch": 0.2842497670083877,
"grad_norm": 0.5483826450591869,
"learning_rate": 4.736024844720497e-05,
"loss": 0.4579,
"step": 305
},
{
"epoch": 0.28890959925442683,
"grad_norm": 0.6644586513259841,
"learning_rate": 4.8136645962732924e-05,
"loss": 0.45,
"step": 310
},
{
"epoch": 0.293569431500466,
"grad_norm": 0.8188490252541196,
"learning_rate": 4.891304347826087e-05,
"loss": 0.459,
"step": 315
},
{
"epoch": 0.2982292637465051,
"grad_norm": 1.034709523419619,
"learning_rate": 4.968944099378882e-05,
"loss": 0.4441,
"step": 320
},
{
"epoch": 0.30288909599254427,
"grad_norm": 0.759919110757548,
"learning_rate": 4.994822229892993e-05,
"loss": 0.4415,
"step": 325
},
{
"epoch": 0.30754892823858343,
"grad_norm": 0.6470711913841568,
"learning_rate": 4.986192613047981e-05,
"loss": 0.4519,
"step": 330
},
{
"epoch": 0.31220876048462254,
"grad_norm": 0.8153464642106912,
"learning_rate": 4.977562996202969e-05,
"loss": 0.4527,
"step": 335
},
{
"epoch": 0.3168685927306617,
"grad_norm": 0.4698984383111023,
"learning_rate": 4.968933379357957e-05,
"loss": 0.4532,
"step": 340
},
{
"epoch": 0.32152842497670087,
"grad_norm": 0.4756319068347418,
"learning_rate": 4.9603037625129445e-05,
"loss": 0.4479,
"step": 345
},
{
"epoch": 0.32618825722274,
"grad_norm": 0.35969300915800667,
"learning_rate": 4.951674145667933e-05,
"loss": 0.4613,
"step": 350
},
{
"epoch": 0.33084808946877914,
"grad_norm": 0.5175115868112082,
"learning_rate": 4.94304452882292e-05,
"loss": 0.4473,
"step": 355
},
{
"epoch": 0.33550792171481825,
"grad_norm": 0.46094013566363407,
"learning_rate": 4.934414911977908e-05,
"loss": 0.445,
"step": 360
},
{
"epoch": 0.3401677539608574,
"grad_norm": 0.4104764392290741,
"learning_rate": 4.9257852951328965e-05,
"loss": 0.4415,
"step": 365
},
{
"epoch": 0.3448275862068966,
"grad_norm": 0.40096213441032663,
"learning_rate": 4.917155678287884e-05,
"loss": 0.4546,
"step": 370
},
{
"epoch": 0.3494874184529357,
"grad_norm": 0.4645867033422015,
"learning_rate": 4.908526061442872e-05,
"loss": 0.4408,
"step": 375
},
{
"epoch": 0.35414725069897485,
"grad_norm": 0.4400737008116359,
"learning_rate": 4.89989644459786e-05,
"loss": 0.4557,
"step": 380
},
{
"epoch": 0.35880708294501396,
"grad_norm": 0.4260635316927096,
"learning_rate": 4.891266827752848e-05,
"loss": 0.4575,
"step": 385
},
{
"epoch": 0.3634669151910531,
"grad_norm": 0.5323727061907297,
"learning_rate": 4.882637210907836e-05,
"loss": 0.4417,
"step": 390
},
{
"epoch": 0.3681267474370923,
"grad_norm": 0.5836242210222355,
"learning_rate": 4.874007594062824e-05,
"loss": 0.4481,
"step": 395
},
{
"epoch": 0.3727865796831314,
"grad_norm": 0.4273563357499149,
"learning_rate": 4.865377977217811e-05,
"loss": 0.4327,
"step": 400
},
{
"epoch": 0.37744641192917056,
"grad_norm": 0.3953667888190435,
"learning_rate": 4.8567483603728e-05,
"loss": 0.4512,
"step": 405
},
{
"epoch": 0.3821062441752097,
"grad_norm": 0.41871105603942904,
"learning_rate": 4.8481187435277875e-05,
"loss": 0.4471,
"step": 410
},
{
"epoch": 0.38676607642124883,
"grad_norm": 0.5437922609735028,
"learning_rate": 4.839489126682776e-05,
"loss": 0.4338,
"step": 415
},
{
"epoch": 0.391425908667288,
"grad_norm": 0.5564237695130677,
"learning_rate": 4.830859509837763e-05,
"loss": 0.4521,
"step": 420
},
{
"epoch": 0.3960857409133271,
"grad_norm": 0.34206255911684263,
"learning_rate": 4.822229892992751e-05,
"loss": 0.4495,
"step": 425
},
{
"epoch": 0.40074557315936626,
"grad_norm": 0.4019378807561449,
"learning_rate": 4.8136002761477395e-05,
"loss": 0.4365,
"step": 430
},
{
"epoch": 0.40540540540540543,
"grad_norm": 0.5440015382583567,
"learning_rate": 4.804970659302727e-05,
"loss": 0.4499,
"step": 435
},
{
"epoch": 0.41006523765144454,
"grad_norm": 0.5537615079643711,
"learning_rate": 4.796341042457715e-05,
"loss": 0.4438,
"step": 440
},
{
"epoch": 0.4147250698974837,
"grad_norm": 0.586960808161654,
"learning_rate": 4.787711425612703e-05,
"loss": 0.4386,
"step": 445
},
{
"epoch": 0.4193849021435228,
"grad_norm": 0.5072343488418793,
"learning_rate": 4.779081808767691e-05,
"loss": 0.4292,
"step": 450
},
{
"epoch": 0.424044734389562,
"grad_norm": 0.48278977249280486,
"learning_rate": 4.770452191922679e-05,
"loss": 0.4362,
"step": 455
},
{
"epoch": 0.42870456663560114,
"grad_norm": 0.39818179591075503,
"learning_rate": 4.761822575077667e-05,
"loss": 0.4329,
"step": 460
},
{
"epoch": 0.43336439888164024,
"grad_norm": 0.48993775783018667,
"learning_rate": 4.753192958232654e-05,
"loss": 0.4299,
"step": 465
},
{
"epoch": 0.4380242311276794,
"grad_norm": 0.41171920657337485,
"learning_rate": 4.744563341387643e-05,
"loss": 0.4428,
"step": 470
},
{
"epoch": 0.4426840633737186,
"grad_norm": 0.4400559670696649,
"learning_rate": 4.7359337245426306e-05,
"loss": 0.432,
"step": 475
},
{
"epoch": 0.4473438956197577,
"grad_norm": 0.4686484619433322,
"learning_rate": 4.7273041076976184e-05,
"loss": 0.4441,
"step": 480
},
{
"epoch": 0.45200372786579684,
"grad_norm": 0.4455986109270811,
"learning_rate": 4.718674490852606e-05,
"loss": 0.4368,
"step": 485
},
{
"epoch": 0.45666356011183595,
"grad_norm": 0.4366809315888367,
"learning_rate": 4.710044874007594e-05,
"loss": 0.4312,
"step": 490
},
{
"epoch": 0.4613233923578751,
"grad_norm": 0.4587131719176713,
"learning_rate": 4.7014152571625826e-05,
"loss": 0.4369,
"step": 495
},
{
"epoch": 0.4659832246039143,
"grad_norm": 0.5269402211397143,
"learning_rate": 4.6927856403175704e-05,
"loss": 0.44,
"step": 500
},
{
"epoch": 0.4706430568499534,
"grad_norm": 0.387320399512531,
"learning_rate": 4.684156023472558e-05,
"loss": 0.4266,
"step": 505
},
{
"epoch": 0.47530288909599255,
"grad_norm": 0.4446811703899567,
"learning_rate": 4.675526406627546e-05,
"loss": 0.435,
"step": 510
},
{
"epoch": 0.47996272134203166,
"grad_norm": 0.6228000644001809,
"learning_rate": 4.666896789782534e-05,
"loss": 0.433,
"step": 515
},
{
"epoch": 0.4846225535880708,
"grad_norm": 0.5372584652001571,
"learning_rate": 4.658267172937522e-05,
"loss": 0.4368,
"step": 520
},
{
"epoch": 0.48928238583411,
"grad_norm": 0.4279339582606534,
"learning_rate": 4.64963755609251e-05,
"loss": 0.4358,
"step": 525
},
{
"epoch": 0.4939422180801491,
"grad_norm": 0.5212302132415493,
"learning_rate": 4.641007939247497e-05,
"loss": 0.4327,
"step": 530
},
{
"epoch": 0.49860205032618826,
"grad_norm": 0.38993326302525777,
"learning_rate": 4.632378322402486e-05,
"loss": 0.4329,
"step": 535
},
{
"epoch": 0.5032618825722274,
"grad_norm": 0.3927986683558084,
"learning_rate": 4.6237487055574736e-05,
"loss": 0.4228,
"step": 540
},
{
"epoch": 0.5079217148182665,
"grad_norm": 0.48245624377171165,
"learning_rate": 4.6151190887124615e-05,
"loss": 0.4292,
"step": 545
},
{
"epoch": 0.5125815470643057,
"grad_norm": 0.4417482867433448,
"learning_rate": 4.606489471867449e-05,
"loss": 0.4293,
"step": 550
},
{
"epoch": 0.5172413793103449,
"grad_norm": 0.34875514025764925,
"learning_rate": 4.597859855022437e-05,
"loss": 0.4236,
"step": 555
},
{
"epoch": 0.5219012115563839,
"grad_norm": 0.4108051872320117,
"learning_rate": 4.589230238177425e-05,
"loss": 0.4445,
"step": 560
},
{
"epoch": 0.5265610438024231,
"grad_norm": 0.44712854316017836,
"learning_rate": 4.5806006213324134e-05,
"loss": 0.422,
"step": 565
},
{
"epoch": 0.5312208760484622,
"grad_norm": 0.5074461667448572,
"learning_rate": 4.5719710044874006e-05,
"loss": 0.4218,
"step": 570
},
{
"epoch": 0.5358807082945014,
"grad_norm": 0.40474852553762236,
"learning_rate": 4.563341387642389e-05,
"loss": 0.428,
"step": 575
},
{
"epoch": 0.5405405405405406,
"grad_norm": 0.35760028403552246,
"learning_rate": 4.554711770797377e-05,
"loss": 0.4281,
"step": 580
},
{
"epoch": 0.5452003727865797,
"grad_norm": 0.43397068927843285,
"learning_rate": 4.546082153952365e-05,
"loss": 0.4251,
"step": 585
},
{
"epoch": 0.5498602050326188,
"grad_norm": 0.39007262792966735,
"learning_rate": 4.5374525371073526e-05,
"loss": 0.4213,
"step": 590
},
{
"epoch": 0.554520037278658,
"grad_norm": 0.36154265093260674,
"learning_rate": 4.5288229202623404e-05,
"loss": 0.4236,
"step": 595
},
{
"epoch": 0.5591798695246971,
"grad_norm": 0.40445512036092346,
"learning_rate": 4.520193303417328e-05,
"loss": 0.4237,
"step": 600
},
{
"epoch": 0.5638397017707363,
"grad_norm": 0.3575679279572506,
"learning_rate": 4.511563686572317e-05,
"loss": 0.4226,
"step": 605
},
{
"epoch": 0.5684995340167754,
"grad_norm": 0.42859866287384585,
"learning_rate": 4.5029340697273045e-05,
"loss": 0.4337,
"step": 610
},
{
"epoch": 0.5731593662628145,
"grad_norm": 0.3398059428883966,
"learning_rate": 4.4943044528822923e-05,
"loss": 0.4202,
"step": 615
},
{
"epoch": 0.5778191985088537,
"grad_norm": 0.4329692306704453,
"learning_rate": 4.48567483603728e-05,
"loss": 0.4172,
"step": 620
},
{
"epoch": 0.5824790307548928,
"grad_norm": 0.3697726336264495,
"learning_rate": 4.477045219192268e-05,
"loss": 0.439,
"step": 625
},
{
"epoch": 0.587138863000932,
"grad_norm": 0.36623031936246386,
"learning_rate": 4.4684156023472565e-05,
"loss": 0.4295,
"step": 630
},
{
"epoch": 0.5917986952469712,
"grad_norm": 0.474742638876247,
"learning_rate": 4.4597859855022436e-05,
"loss": 0.4341,
"step": 635
},
{
"epoch": 0.5964585274930102,
"grad_norm": 0.48429407467593777,
"learning_rate": 4.4511563686572315e-05,
"loss": 0.4248,
"step": 640
},
{
"epoch": 0.6011183597390494,
"grad_norm": 0.42926923766107844,
"learning_rate": 4.44252675181222e-05,
"loss": 0.4246,
"step": 645
},
{
"epoch": 0.6057781919850885,
"grad_norm": 0.41759175987652447,
"learning_rate": 4.433897134967208e-05,
"loss": 0.4333,
"step": 650
},
{
"epoch": 0.6104380242311277,
"grad_norm": 0.40591710297089845,
"learning_rate": 4.4252675181221956e-05,
"loss": 0.4308,
"step": 655
},
{
"epoch": 0.6150978564771669,
"grad_norm": 0.34151741261761837,
"learning_rate": 4.4166379012771834e-05,
"loss": 0.4127,
"step": 660
},
{
"epoch": 0.6197576887232059,
"grad_norm": 0.4739000530318965,
"learning_rate": 4.408008284432171e-05,
"loss": 0.4134,
"step": 665
},
{
"epoch": 0.6244175209692451,
"grad_norm": 0.40594442187572644,
"learning_rate": 4.39937866758716e-05,
"loss": 0.4119,
"step": 670
},
{
"epoch": 0.6290773532152842,
"grad_norm": 0.38741906022032196,
"learning_rate": 4.3907490507421476e-05,
"loss": 0.4205,
"step": 675
},
{
"epoch": 0.6337371854613234,
"grad_norm": 0.40827486654087697,
"learning_rate": 4.382119433897135e-05,
"loss": 0.4235,
"step": 680
},
{
"epoch": 0.6383970177073626,
"grad_norm": 0.4472633880572486,
"learning_rate": 4.373489817052123e-05,
"loss": 0.4332,
"step": 685
},
{
"epoch": 0.6430568499534017,
"grad_norm": 0.4294679057605266,
"learning_rate": 4.364860200207111e-05,
"loss": 0.4153,
"step": 690
},
{
"epoch": 0.6477166821994408,
"grad_norm": 0.40635265146514193,
"learning_rate": 4.356230583362099e-05,
"loss": 0.4207,
"step": 695
},
{
"epoch": 0.65237651444548,
"grad_norm": 0.3677110047703502,
"learning_rate": 4.347600966517087e-05,
"loss": 0.429,
"step": 700
},
{
"epoch": 0.6570363466915191,
"grad_norm": 0.39912181862304363,
"learning_rate": 4.3389713496720745e-05,
"loss": 0.4225,
"step": 705
},
{
"epoch": 0.6616961789375583,
"grad_norm": 0.4706777419313193,
"learning_rate": 4.330341732827063e-05,
"loss": 0.4231,
"step": 710
},
{
"epoch": 0.6663560111835974,
"grad_norm": 0.3960054145843989,
"learning_rate": 4.321712115982051e-05,
"loss": 0.4115,
"step": 715
},
{
"epoch": 0.6710158434296365,
"grad_norm": 0.3796810889210068,
"learning_rate": 4.3130824991370387e-05,
"loss": 0.4219,
"step": 720
},
{
"epoch": 0.6756756756756757,
"grad_norm": 0.3231682922426093,
"learning_rate": 4.3044528822920265e-05,
"loss": 0.4207,
"step": 725
},
{
"epoch": 0.6803355079217148,
"grad_norm": 0.4338919098644665,
"learning_rate": 4.295823265447014e-05,
"loss": 0.4156,
"step": 730
},
{
"epoch": 0.684995340167754,
"grad_norm": 0.3769886966857475,
"learning_rate": 4.287193648602002e-05,
"loss": 0.4195,
"step": 735
},
{
"epoch": 0.6896551724137931,
"grad_norm": 0.3380840539678925,
"learning_rate": 4.27856403175699e-05,
"loss": 0.413,
"step": 740
},
{
"epoch": 0.6943150046598322,
"grad_norm": 0.36717339806709604,
"learning_rate": 4.269934414911978e-05,
"loss": 0.4089,
"step": 745
},
{
"epoch": 0.6989748369058714,
"grad_norm": 0.4168652698432254,
"learning_rate": 4.261304798066966e-05,
"loss": 0.4136,
"step": 750
},
{
"epoch": 0.7036346691519105,
"grad_norm": 0.3690477723388078,
"learning_rate": 4.252675181221954e-05,
"loss": 0.416,
"step": 755
},
{
"epoch": 0.7082945013979497,
"grad_norm": 0.4242455380044557,
"learning_rate": 4.244045564376942e-05,
"loss": 0.4191,
"step": 760
},
{
"epoch": 0.7129543336439889,
"grad_norm": 0.3735978801523571,
"learning_rate": 4.23541594753193e-05,
"loss": 0.4031,
"step": 765
},
{
"epoch": 0.7176141658900279,
"grad_norm": 0.3541170842431973,
"learning_rate": 4.2267863306869176e-05,
"loss": 0.4125,
"step": 770
},
{
"epoch": 0.7222739981360671,
"grad_norm": 0.3904517316938196,
"learning_rate": 4.2181567138419054e-05,
"loss": 0.425,
"step": 775
},
{
"epoch": 0.7269338303821062,
"grad_norm": 0.3553979878523653,
"learning_rate": 4.209527096996894e-05,
"loss": 0.4095,
"step": 780
},
{
"epoch": 0.7315936626281454,
"grad_norm": 0.3993958111614743,
"learning_rate": 4.200897480151881e-05,
"loss": 0.4168,
"step": 785
},
{
"epoch": 0.7362534948741846,
"grad_norm": 0.4854725144908592,
"learning_rate": 4.1922678633068695e-05,
"loss": 0.4201,
"step": 790
},
{
"epoch": 0.7409133271202236,
"grad_norm": 0.4093466282869362,
"learning_rate": 4.1836382464618573e-05,
"loss": 0.4144,
"step": 795
},
{
"epoch": 0.7455731593662628,
"grad_norm": 0.3802224792673468,
"learning_rate": 4.175008629616845e-05,
"loss": 0.4126,
"step": 800
},
{
"epoch": 0.750232991612302,
"grad_norm": 0.36566042296095735,
"learning_rate": 4.166379012771833e-05,
"loss": 0.4124,
"step": 805
},
{
"epoch": 0.7548928238583411,
"grad_norm": 0.33821479986680525,
"learning_rate": 4.157749395926821e-05,
"loss": 0.4307,
"step": 810
},
{
"epoch": 0.7595526561043803,
"grad_norm": 0.3717989938649144,
"learning_rate": 4.1491197790818086e-05,
"loss": 0.405,
"step": 815
},
{
"epoch": 0.7642124883504194,
"grad_norm": 0.5365115867656194,
"learning_rate": 4.140490162236797e-05,
"loss": 0.4203,
"step": 820
},
{
"epoch": 0.7688723205964585,
"grad_norm": 0.40471466095870456,
"learning_rate": 4.131860545391785e-05,
"loss": 0.4124,
"step": 825
},
{
"epoch": 0.7735321528424977,
"grad_norm": 0.38714529094413536,
"learning_rate": 4.123230928546773e-05,
"loss": 0.4073,
"step": 830
},
{
"epoch": 0.7781919850885368,
"grad_norm": 0.3949031763600824,
"learning_rate": 4.1146013117017606e-05,
"loss": 0.4143,
"step": 835
},
{
"epoch": 0.782851817334576,
"grad_norm": 0.4352023815662388,
"learning_rate": 4.1059716948567484e-05,
"loss": 0.4174,
"step": 840
},
{
"epoch": 0.7875116495806151,
"grad_norm": 0.4358406385453878,
"learning_rate": 4.097342078011737e-05,
"loss": 0.4254,
"step": 845
},
{
"epoch": 0.7921714818266542,
"grad_norm": 0.38366190649635135,
"learning_rate": 4.088712461166724e-05,
"loss": 0.4151,
"step": 850
},
{
"epoch": 0.7968313140726934,
"grad_norm": 0.5018848204235326,
"learning_rate": 4.080082844321712e-05,
"loss": 0.4171,
"step": 855
},
{
"epoch": 0.8014911463187325,
"grad_norm": 0.3758022403546901,
"learning_rate": 4.0714532274767004e-05,
"loss": 0.4241,
"step": 860
},
{
"epoch": 0.8061509785647717,
"grad_norm": 0.3562876865702164,
"learning_rate": 4.062823610631688e-05,
"loss": 0.405,
"step": 865
},
{
"epoch": 0.8108108108108109,
"grad_norm": 0.32964459523802225,
"learning_rate": 4.054193993786676e-05,
"loss": 0.4195,
"step": 870
},
{
"epoch": 0.8154706430568499,
"grad_norm": 0.3902217678069233,
"learning_rate": 4.045564376941664e-05,
"loss": 0.415,
"step": 875
},
{
"epoch": 0.8201304753028891,
"grad_norm": 0.6740352106087266,
"learning_rate": 4.036934760096652e-05,
"loss": 0.4065,
"step": 880
},
{
"epoch": 0.8247903075489282,
"grad_norm": 0.433837350976653,
"learning_rate": 4.02830514325164e-05,
"loss": 0.4206,
"step": 885
},
{
"epoch": 0.8294501397949674,
"grad_norm": 0.44183852945895624,
"learning_rate": 4.019675526406628e-05,
"loss": 0.4072,
"step": 890
},
{
"epoch": 0.8341099720410066,
"grad_norm": 0.34981947402981967,
"learning_rate": 4.011045909561615e-05,
"loss": 0.4267,
"step": 895
},
{
"epoch": 0.8387698042870456,
"grad_norm": 0.3704822813418764,
"learning_rate": 4.0024162927166037e-05,
"loss": 0.4093,
"step": 900
},
{
"epoch": 0.8434296365330848,
"grad_norm": 0.3440227445259439,
"learning_rate": 3.9937866758715915e-05,
"loss": 0.4109,
"step": 905
},
{
"epoch": 0.848089468779124,
"grad_norm": 0.46842513834829896,
"learning_rate": 3.98515705902658e-05,
"loss": 0.4169,
"step": 910
},
{
"epoch": 0.8527493010251631,
"grad_norm": 0.5632219425437093,
"learning_rate": 3.976527442181567e-05,
"loss": 0.4096,
"step": 915
},
{
"epoch": 0.8574091332712023,
"grad_norm": 0.4099216183303217,
"learning_rate": 3.967897825336555e-05,
"loss": 0.4162,
"step": 920
},
{
"epoch": 0.8620689655172413,
"grad_norm": 0.3475937062948154,
"learning_rate": 3.9592682084915434e-05,
"loss": 0.403,
"step": 925
},
{
"epoch": 0.8667287977632805,
"grad_norm": 0.4832320578936911,
"learning_rate": 3.950638591646531e-05,
"loss": 0.4025,
"step": 930
},
{
"epoch": 0.8713886300093197,
"grad_norm": 0.361390732321457,
"learning_rate": 3.942008974801519e-05,
"loss": 0.414,
"step": 935
},
{
"epoch": 0.8760484622553588,
"grad_norm": 0.2938396873991374,
"learning_rate": 3.933379357956507e-05,
"loss": 0.4096,
"step": 940
},
{
"epoch": 0.880708294501398,
"grad_norm": 0.4195411837550818,
"learning_rate": 3.924749741111495e-05,
"loss": 0.4119,
"step": 945
},
{
"epoch": 0.8853681267474371,
"grad_norm": 0.48658637807442856,
"learning_rate": 3.916120124266483e-05,
"loss": 0.4197,
"step": 950
},
{
"epoch": 0.8900279589934762,
"grad_norm": 0.4260894598328252,
"learning_rate": 3.9074905074214704e-05,
"loss": 0.4187,
"step": 955
},
{
"epoch": 0.8946877912395154,
"grad_norm": 0.34451778618434714,
"learning_rate": 3.898860890576458e-05,
"loss": 0.4138,
"step": 960
},
{
"epoch": 0.8993476234855545,
"grad_norm": 0.4365094696793227,
"learning_rate": 3.890231273731447e-05,
"loss": 0.4055,
"step": 965
},
{
"epoch": 0.9040074557315937,
"grad_norm": 0.3248156521748473,
"learning_rate": 3.8816016568864345e-05,
"loss": 0.4033,
"step": 970
},
{
"epoch": 0.9086672879776329,
"grad_norm": 0.32381986617162706,
"learning_rate": 3.8729720400414224e-05,
"loss": 0.4222,
"step": 975
},
{
"epoch": 0.9133271202236719,
"grad_norm": 0.400448857756024,
"learning_rate": 3.86434242319641e-05,
"loss": 0.4093,
"step": 980
},
{
"epoch": 0.9179869524697111,
"grad_norm": 0.5091133203813641,
"learning_rate": 3.855712806351398e-05,
"loss": 0.4124,
"step": 985
},
{
"epoch": 0.9226467847157502,
"grad_norm": 0.43202295251303324,
"learning_rate": 3.8470831895063865e-05,
"loss": 0.4088,
"step": 990
},
{
"epoch": 0.9273066169617894,
"grad_norm": 0.364710789588561,
"learning_rate": 3.838453572661374e-05,
"loss": 0.4046,
"step": 995
},
{
"epoch": 0.9319664492078286,
"grad_norm": 0.4716388737566944,
"learning_rate": 3.8298239558163615e-05,
"loss": 0.4075,
"step": 1000
},
{
"epoch": 0.9366262814538676,
"grad_norm": 0.6143023930914768,
"learning_rate": 3.82119433897135e-05,
"loss": 0.4151,
"step": 1005
},
{
"epoch": 0.9412861136999068,
"grad_norm": 0.4045209641384314,
"learning_rate": 3.812564722126338e-05,
"loss": 0.4061,
"step": 1010
},
{
"epoch": 0.9459459459459459,
"grad_norm": 0.4374289349183326,
"learning_rate": 3.8039351052813256e-05,
"loss": 0.4149,
"step": 1015
},
{
"epoch": 0.9506057781919851,
"grad_norm": 0.4186126910891237,
"learning_rate": 3.7953054884363134e-05,
"loss": 0.4082,
"step": 1020
},
{
"epoch": 0.9552656104380243,
"grad_norm": 0.3724784755826059,
"learning_rate": 3.786675871591301e-05,
"loss": 0.4116,
"step": 1025
},
{
"epoch": 0.9599254426840633,
"grad_norm": 0.3162214191511966,
"learning_rate": 3.77804625474629e-05,
"loss": 0.4165,
"step": 1030
},
{
"epoch": 0.9645852749301025,
"grad_norm": 0.44560720068567894,
"learning_rate": 3.7694166379012776e-05,
"loss": 0.4086,
"step": 1035
},
{
"epoch": 0.9692451071761417,
"grad_norm": 0.3715493465051349,
"learning_rate": 3.7607870210562654e-05,
"loss": 0.406,
"step": 1040
},
{
"epoch": 0.9739049394221808,
"grad_norm": 0.2864953938663117,
"learning_rate": 3.752157404211253e-05,
"loss": 0.3984,
"step": 1045
},
{
"epoch": 0.97856477166822,
"grad_norm": 0.4430521911068819,
"learning_rate": 3.743527787366241e-05,
"loss": 0.428,
"step": 1050
},
{
"epoch": 0.983224603914259,
"grad_norm": 0.39380676782546514,
"learning_rate": 3.734898170521229e-05,
"loss": 0.4058,
"step": 1055
},
{
"epoch": 0.9878844361602982,
"grad_norm": 0.45421105453517185,
"learning_rate": 3.7262685536762174e-05,
"loss": 0.4048,
"step": 1060
},
{
"epoch": 0.9925442684063374,
"grad_norm": 0.3188847720393995,
"learning_rate": 3.7176389368312045e-05,
"loss": 0.4088,
"step": 1065
},
{
"epoch": 0.9972041006523765,
"grad_norm": 0.3979525304245011,
"learning_rate": 3.709009319986193e-05,
"loss": 0.409,
"step": 1070
},
{
"epoch": 1.0018639328984156,
"grad_norm": 0.364266540801231,
"learning_rate": 3.700379703141181e-05,
"loss": 0.3739,
"step": 1075
},
{
"epoch": 1.0065237651444547,
"grad_norm": 0.30445308416956596,
"learning_rate": 3.6917500862961687e-05,
"loss": 0.3498,
"step": 1080
},
{
"epoch": 1.011183597390494,
"grad_norm": 0.4080914841436169,
"learning_rate": 3.6831204694511565e-05,
"loss": 0.3564,
"step": 1085
},
{
"epoch": 1.015843429636533,
"grad_norm": 0.3649554671829125,
"learning_rate": 3.674490852606144e-05,
"loss": 0.3637,
"step": 1090
},
{
"epoch": 1.0205032618825722,
"grad_norm": 0.3163559100974115,
"learning_rate": 3.665861235761132e-05,
"loss": 0.349,
"step": 1095
},
{
"epoch": 1.0251630941286114,
"grad_norm": 0.36263837002354715,
"learning_rate": 3.6572316189161206e-05,
"loss": 0.3403,
"step": 1100
},
{
"epoch": 1.0298229263746506,
"grad_norm": 0.3092678358686789,
"learning_rate": 3.6486020020711085e-05,
"loss": 0.3465,
"step": 1105
},
{
"epoch": 1.0344827586206897,
"grad_norm": 0.3141892800399063,
"learning_rate": 3.639972385226096e-05,
"loss": 0.347,
"step": 1110
},
{
"epoch": 1.0391425908667289,
"grad_norm": 0.31295163640755363,
"learning_rate": 3.631342768381084e-05,
"loss": 0.3471,
"step": 1115
},
{
"epoch": 1.0438024231127678,
"grad_norm": 0.3401750953887306,
"learning_rate": 3.622713151536072e-05,
"loss": 0.3473,
"step": 1120
},
{
"epoch": 1.048462255358807,
"grad_norm": 0.31195615894221534,
"learning_rate": 3.6140835346910604e-05,
"loss": 0.3507,
"step": 1125
},
{
"epoch": 1.0531220876048462,
"grad_norm": 0.32979807481995643,
"learning_rate": 3.6054539178460476e-05,
"loss": 0.347,
"step": 1130
},
{
"epoch": 1.0577819198508853,
"grad_norm": 0.3759497094197671,
"learning_rate": 3.5968243010010354e-05,
"loss": 0.3635,
"step": 1135
},
{
"epoch": 1.0624417520969245,
"grad_norm": 0.3276972337838372,
"learning_rate": 3.588194684156024e-05,
"loss": 0.3546,
"step": 1140
},
{
"epoch": 1.0671015843429636,
"grad_norm": 0.3248203280892395,
"learning_rate": 3.579565067311012e-05,
"loss": 0.3461,
"step": 1145
},
{
"epoch": 1.0717614165890028,
"grad_norm": 0.3049982165023373,
"learning_rate": 3.5709354504659995e-05,
"loss": 0.3425,
"step": 1150
},
{
"epoch": 1.076421248835042,
"grad_norm": 0.3359497674452099,
"learning_rate": 3.5623058336209874e-05,
"loss": 0.3535,
"step": 1155
},
{
"epoch": 1.0810810810810811,
"grad_norm": 0.3158582105691738,
"learning_rate": 3.553676216775975e-05,
"loss": 0.3448,
"step": 1160
},
{
"epoch": 1.0857409133271203,
"grad_norm": 0.29574757335640145,
"learning_rate": 3.545046599930964e-05,
"loss": 0.3565,
"step": 1165
},
{
"epoch": 1.0904007455731595,
"grad_norm": 0.31108264753865356,
"learning_rate": 3.536416983085951e-05,
"loss": 0.3583,
"step": 1170
},
{
"epoch": 1.0950605778191984,
"grad_norm": 0.36037209266568915,
"learning_rate": 3.5277873662409386e-05,
"loss": 0.3448,
"step": 1175
},
{
"epoch": 1.0997204100652376,
"grad_norm": 0.3618383231487912,
"learning_rate": 3.519157749395927e-05,
"loss": 0.3507,
"step": 1180
},
{
"epoch": 1.1043802423112767,
"grad_norm": 0.4175780783750628,
"learning_rate": 3.510528132550915e-05,
"loss": 0.3479,
"step": 1185
},
{
"epoch": 1.109040074557316,
"grad_norm": 0.3599957546238691,
"learning_rate": 3.501898515705903e-05,
"loss": 0.3503,
"step": 1190
},
{
"epoch": 1.113699906803355,
"grad_norm": 0.3501599765642264,
"learning_rate": 3.4932688988608906e-05,
"loss": 0.3612,
"step": 1195
},
{
"epoch": 1.1183597390493942,
"grad_norm": 0.5599389993107197,
"learning_rate": 3.4846392820158784e-05,
"loss": 0.3512,
"step": 1200
},
{
"epoch": 1.1230195712954334,
"grad_norm": 0.39235842650287267,
"learning_rate": 3.476009665170867e-05,
"loss": 0.3503,
"step": 1205
},
{
"epoch": 1.1276794035414726,
"grad_norm": 0.35965537290287625,
"learning_rate": 3.467380048325855e-05,
"loss": 0.3505,
"step": 1210
},
{
"epoch": 1.1323392357875117,
"grad_norm": 0.3147552390929704,
"learning_rate": 3.458750431480842e-05,
"loss": 0.3556,
"step": 1215
},
{
"epoch": 1.1369990680335509,
"grad_norm": 0.35667525578447856,
"learning_rate": 3.4501208146358304e-05,
"loss": 0.3551,
"step": 1220
},
{
"epoch": 1.14165890027959,
"grad_norm": 0.3143522174903333,
"learning_rate": 3.441491197790818e-05,
"loss": 0.3506,
"step": 1225
},
{
"epoch": 1.146318732525629,
"grad_norm": 0.2953129277848881,
"learning_rate": 3.432861580945806e-05,
"loss": 0.3519,
"step": 1230
},
{
"epoch": 1.1509785647716682,
"grad_norm": 0.3201828959982261,
"learning_rate": 3.424231964100794e-05,
"loss": 0.351,
"step": 1235
},
{
"epoch": 1.1556383970177073,
"grad_norm": 0.35805902539565565,
"learning_rate": 3.415602347255782e-05,
"loss": 0.3496,
"step": 1240
},
{
"epoch": 1.1602982292637465,
"grad_norm": 0.2844778506189992,
"learning_rate": 3.40697273041077e-05,
"loss": 0.3567,
"step": 1245
},
{
"epoch": 1.1649580615097856,
"grad_norm": 0.3932646163355652,
"learning_rate": 3.398343113565758e-05,
"loss": 0.3508,
"step": 1250
},
{
"epoch": 1.1696178937558248,
"grad_norm": 0.27258390887519407,
"learning_rate": 3.389713496720746e-05,
"loss": 0.3296,
"step": 1255
},
{
"epoch": 1.174277726001864,
"grad_norm": 0.2775303977010617,
"learning_rate": 3.381083879875734e-05,
"loss": 0.3491,
"step": 1260
},
{
"epoch": 1.1789375582479031,
"grad_norm": 0.3028564721433078,
"learning_rate": 3.3724542630307215e-05,
"loss": 0.3456,
"step": 1265
},
{
"epoch": 1.1835973904939423,
"grad_norm": 0.32923905528364905,
"learning_rate": 3.363824646185709e-05,
"loss": 0.3555,
"step": 1270
},
{
"epoch": 1.1882572227399812,
"grad_norm": 0.2760919775973278,
"learning_rate": 3.355195029340698e-05,
"loss": 0.3489,
"step": 1275
},
{
"epoch": 1.1929170549860204,
"grad_norm": 0.3155488629032025,
"learning_rate": 3.346565412495685e-05,
"loss": 0.3597,
"step": 1280
},
{
"epoch": 1.1975768872320596,
"grad_norm": 0.34778125198320686,
"learning_rate": 3.3379357956506735e-05,
"loss": 0.3605,
"step": 1285
},
{
"epoch": 1.2022367194780987,
"grad_norm": 0.3591989412785019,
"learning_rate": 3.329306178805661e-05,
"loss": 0.3439,
"step": 1290
},
{
"epoch": 1.206896551724138,
"grad_norm": 0.338584951279966,
"learning_rate": 3.320676561960649e-05,
"loss": 0.3486,
"step": 1295
},
{
"epoch": 1.211556383970177,
"grad_norm": 0.44502827017418983,
"learning_rate": 3.312046945115637e-05,
"loss": 0.3574,
"step": 1300
},
{
"epoch": 1.2162162162162162,
"grad_norm": 0.37848494564678853,
"learning_rate": 3.303417328270625e-05,
"loss": 0.3554,
"step": 1305
},
{
"epoch": 1.2208760484622554,
"grad_norm": 0.2991926203877817,
"learning_rate": 3.2947877114256126e-05,
"loss": 0.3448,
"step": 1310
},
{
"epoch": 1.2255358807082946,
"grad_norm": 0.33851023261699276,
"learning_rate": 3.286158094580601e-05,
"loss": 0.3648,
"step": 1315
},
{
"epoch": 1.2301957129543337,
"grad_norm": 0.27617927948407645,
"learning_rate": 3.277528477735589e-05,
"loss": 0.3505,
"step": 1320
},
{
"epoch": 1.2348555452003729,
"grad_norm": 0.31943221432421715,
"learning_rate": 3.268898860890577e-05,
"loss": 0.3575,
"step": 1325
},
{
"epoch": 1.2395153774464118,
"grad_norm": 0.36090830340862545,
"learning_rate": 3.2602692440455645e-05,
"loss": 0.3459,
"step": 1330
},
{
"epoch": 1.244175209692451,
"grad_norm": 0.2869837155345359,
"learning_rate": 3.2516396272005524e-05,
"loss": 0.3483,
"step": 1335
},
{
"epoch": 1.2488350419384902,
"grad_norm": 0.4574789609384581,
"learning_rate": 3.243010010355541e-05,
"loss": 0.3537,
"step": 1340
},
{
"epoch": 1.2534948741845293,
"grad_norm": 0.34435517087930184,
"learning_rate": 3.234380393510528e-05,
"loss": 0.3412,
"step": 1345
},
{
"epoch": 1.2581547064305685,
"grad_norm": 0.28787047833310464,
"learning_rate": 3.225750776665516e-05,
"loss": 0.3481,
"step": 1350
},
{
"epoch": 1.2628145386766076,
"grad_norm": 0.28433333546839407,
"learning_rate": 3.217121159820504e-05,
"loss": 0.3581,
"step": 1355
},
{
"epoch": 1.2674743709226468,
"grad_norm": 0.2837264128964714,
"learning_rate": 3.208491542975492e-05,
"loss": 0.3475,
"step": 1360
},
{
"epoch": 1.272134203168686,
"grad_norm": 0.2783632546885593,
"learning_rate": 3.19986192613048e-05,
"loss": 0.3528,
"step": 1365
},
{
"epoch": 1.2767940354147251,
"grad_norm": 0.32499690495431244,
"learning_rate": 3.191232309285468e-05,
"loss": 0.352,
"step": 1370
},
{
"epoch": 1.281453867660764,
"grad_norm": 0.3177042804556951,
"learning_rate": 3.1826026924404556e-05,
"loss": 0.3416,
"step": 1375
},
{
"epoch": 1.2861136999068035,
"grad_norm": 0.3082833632499775,
"learning_rate": 3.173973075595444e-05,
"loss": 0.3561,
"step": 1380
},
{
"epoch": 1.2907735321528424,
"grad_norm": 0.3192882141973088,
"learning_rate": 3.165343458750431e-05,
"loss": 0.358,
"step": 1385
},
{
"epoch": 1.2954333643988816,
"grad_norm": 0.35083440823453566,
"learning_rate": 3.156713841905419e-05,
"loss": 0.3482,
"step": 1390
},
{
"epoch": 1.3000931966449207,
"grad_norm": 0.3028496199107332,
"learning_rate": 3.1480842250604076e-05,
"loss": 0.3524,
"step": 1395
},
{
"epoch": 1.30475302889096,
"grad_norm": 0.40238805661277516,
"learning_rate": 3.1394546082153954e-05,
"loss": 0.3465,
"step": 1400
},
{
"epoch": 1.309412861136999,
"grad_norm": 0.38264937163405993,
"learning_rate": 3.130824991370383e-05,
"loss": 0.3572,
"step": 1405
},
{
"epoch": 1.3140726933830382,
"grad_norm": 0.3476478264061866,
"learning_rate": 3.122195374525371e-05,
"loss": 0.3452,
"step": 1410
},
{
"epoch": 1.3187325256290774,
"grad_norm": 0.29460741785810235,
"learning_rate": 3.113565757680359e-05,
"loss": 0.3528,
"step": 1415
},
{
"epoch": 1.3233923578751166,
"grad_norm": 0.3105487189575632,
"learning_rate": 3.1049361408353474e-05,
"loss": 0.3403,
"step": 1420
},
{
"epoch": 1.3280521901211557,
"grad_norm": 0.24970556065463576,
"learning_rate": 3.096306523990335e-05,
"loss": 0.3481,
"step": 1425
},
{
"epoch": 1.3327120223671947,
"grad_norm": 0.26478763592488186,
"learning_rate": 3.0876769071453223e-05,
"loss": 0.3567,
"step": 1430
},
{
"epoch": 1.337371854613234,
"grad_norm": 0.3166787826392816,
"learning_rate": 3.079047290300311e-05,
"loss": 0.3549,
"step": 1435
},
{
"epoch": 1.342031686859273,
"grad_norm": 0.3370862593924141,
"learning_rate": 3.070417673455299e-05,
"loss": 0.3532,
"step": 1440
},
{
"epoch": 1.3466915191053122,
"grad_norm": 0.28943779202148834,
"learning_rate": 3.061788056610287e-05,
"loss": 0.3578,
"step": 1445
},
{
"epoch": 1.3513513513513513,
"grad_norm": 0.3305096681079534,
"learning_rate": 3.053158439765274e-05,
"loss": 0.3434,
"step": 1450
},
{
"epoch": 1.3560111835973905,
"grad_norm": 0.30770425179734145,
"learning_rate": 3.0445288229202625e-05,
"loss": 0.3513,
"step": 1455
},
{
"epoch": 1.3606710158434296,
"grad_norm": 0.29217231918736536,
"learning_rate": 3.0358992060752506e-05,
"loss": 0.357,
"step": 1460
},
{
"epoch": 1.3653308480894688,
"grad_norm": 0.30497087668658185,
"learning_rate": 3.027269589230238e-05,
"loss": 0.3512,
"step": 1465
},
{
"epoch": 1.369990680335508,
"grad_norm": 0.3169652144095064,
"learning_rate": 3.018639972385226e-05,
"loss": 0.3485,
"step": 1470
},
{
"epoch": 1.3746505125815471,
"grad_norm": 0.33878452557048316,
"learning_rate": 3.010010355540214e-05,
"loss": 0.3501,
"step": 1475
},
{
"epoch": 1.3793103448275863,
"grad_norm": 0.25128935811284947,
"learning_rate": 3.001380738695202e-05,
"loss": 0.3342,
"step": 1480
},
{
"epoch": 1.3839701770736252,
"grad_norm": 0.2807928725658594,
"learning_rate": 2.99275112185019e-05,
"loss": 0.3515,
"step": 1485
},
{
"epoch": 1.3886300093196646,
"grad_norm": 0.32627986332317066,
"learning_rate": 2.984121505005178e-05,
"loss": 0.3564,
"step": 1490
},
{
"epoch": 1.3932898415657036,
"grad_norm": 0.34700278304006454,
"learning_rate": 2.9754918881601657e-05,
"loss": 0.3647,
"step": 1495
},
{
"epoch": 1.3979496738117427,
"grad_norm": 0.33291240407016004,
"learning_rate": 2.966862271315154e-05,
"loss": 0.3608,
"step": 1500
},
{
"epoch": 1.402609506057782,
"grad_norm": 0.36233550445620966,
"learning_rate": 2.9582326544701417e-05,
"loss": 0.3576,
"step": 1505
},
{
"epoch": 1.407269338303821,
"grad_norm": 0.299037421676663,
"learning_rate": 2.9496030376251292e-05,
"loss": 0.35,
"step": 1510
},
{
"epoch": 1.4119291705498602,
"grad_norm": 0.2779558872885985,
"learning_rate": 2.9409734207801177e-05,
"loss": 0.3536,
"step": 1515
},
{
"epoch": 1.4165890027958994,
"grad_norm": 0.300917823810139,
"learning_rate": 2.9323438039351052e-05,
"loss": 0.3527,
"step": 1520
},
{
"epoch": 1.4212488350419386,
"grad_norm": 0.2914307296082574,
"learning_rate": 2.9237141870900937e-05,
"loss": 0.3487,
"step": 1525
},
{
"epoch": 1.4259086672879777,
"grad_norm": 0.2856071431198464,
"learning_rate": 2.9150845702450812e-05,
"loss": 0.3476,
"step": 1530
},
{
"epoch": 1.4305684995340169,
"grad_norm": 0.3129750830236417,
"learning_rate": 2.906454953400069e-05,
"loss": 0.3524,
"step": 1535
},
{
"epoch": 1.4352283317800558,
"grad_norm": 0.3179106281194418,
"learning_rate": 2.897825336555057e-05,
"loss": 0.3485,
"step": 1540
},
{
"epoch": 1.439888164026095,
"grad_norm": 0.38784207287547934,
"learning_rate": 2.889195719710045e-05,
"loss": 0.349,
"step": 1545
},
{
"epoch": 1.4445479962721341,
"grad_norm": 0.3753888528298807,
"learning_rate": 2.8805661028650328e-05,
"loss": 0.3451,
"step": 1550
},
{
"epoch": 1.4492078285181733,
"grad_norm": 0.41321946201235715,
"learning_rate": 2.871936486020021e-05,
"loss": 0.3426,
"step": 1555
},
{
"epoch": 1.4538676607642125,
"grad_norm": 0.3200312045653147,
"learning_rate": 2.8633068691750088e-05,
"loss": 0.3453,
"step": 1560
},
{
"epoch": 1.4585274930102516,
"grad_norm": 0.3307103194113536,
"learning_rate": 2.854677252329997e-05,
"loss": 0.3476,
"step": 1565
},
{
"epoch": 1.4631873252562908,
"grad_norm": 0.30755068927447626,
"learning_rate": 2.8460476354849848e-05,
"loss": 0.3546,
"step": 1570
},
{
"epoch": 1.46784715750233,
"grad_norm": 0.3595240127776032,
"learning_rate": 2.8374180186399723e-05,
"loss": 0.3546,
"step": 1575
},
{
"epoch": 1.4725069897483691,
"grad_norm": 0.3689101626664539,
"learning_rate": 2.8287884017949608e-05,
"loss": 0.3557,
"step": 1580
},
{
"epoch": 1.477166821994408,
"grad_norm": 0.3583075317481452,
"learning_rate": 2.8201587849499482e-05,
"loss": 0.3487,
"step": 1585
},
{
"epoch": 1.4818266542404475,
"grad_norm": 0.35602642963014874,
"learning_rate": 2.811529168104936e-05,
"loss": 0.3591,
"step": 1590
},
{
"epoch": 1.4864864864864864,
"grad_norm": 0.315787516045647,
"learning_rate": 2.8028995512599242e-05,
"loss": 0.3499,
"step": 1595
},
{
"epoch": 1.4911463187325256,
"grad_norm": 0.3590015577504981,
"learning_rate": 2.794269934414912e-05,
"loss": 0.3512,
"step": 1600
},
{
"epoch": 1.4958061509785647,
"grad_norm": 0.3122273467939273,
"learning_rate": 2.7856403175699002e-05,
"loss": 0.3557,
"step": 1605
},
{
"epoch": 1.500465983224604,
"grad_norm": 0.3542977601514441,
"learning_rate": 2.777010700724888e-05,
"loss": 0.3508,
"step": 1610
},
{
"epoch": 1.505125815470643,
"grad_norm": 0.3391938107105768,
"learning_rate": 2.768381083879876e-05,
"loss": 0.3458,
"step": 1615
},
{
"epoch": 1.5097856477166822,
"grad_norm": 0.2960461404701141,
"learning_rate": 2.759751467034864e-05,
"loss": 0.351,
"step": 1620
},
{
"epoch": 1.5144454799627214,
"grad_norm": 0.27438908752786395,
"learning_rate": 2.751121850189852e-05,
"loss": 0.3428,
"step": 1625
},
{
"epoch": 1.5191053122087603,
"grad_norm": 0.28849482254982545,
"learning_rate": 2.7424922333448393e-05,
"loss": 0.3366,
"step": 1630
},
{
"epoch": 1.5237651444547997,
"grad_norm": 0.3049772048163229,
"learning_rate": 2.7338626164998278e-05,
"loss": 0.3433,
"step": 1635
},
{
"epoch": 1.5284249767008387,
"grad_norm": 0.3325604613028116,
"learning_rate": 2.7252329996548153e-05,
"loss": 0.3463,
"step": 1640
},
{
"epoch": 1.533084808946878,
"grad_norm": 0.27987089540936305,
"learning_rate": 2.7166033828098038e-05,
"loss": 0.3614,
"step": 1645
},
{
"epoch": 1.537744641192917,
"grad_norm": 0.3045635963851511,
"learning_rate": 2.7079737659647913e-05,
"loss": 0.3505,
"step": 1650
}
],
"logging_steps": 5,
"max_steps": 3219,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 550,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.412450714289963e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}