eren23's picture
Upload folder using huggingface_hub
ea5b075 verified
raw history blame
No virus
43.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.96,
"eval_steps": 500,
"global_step": 1800,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.5e-06,
"loss": 1.3998,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 5e-06,
"loss": 1.3688,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 7.5e-06,
"loss": 1.4511,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 1.5508,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 1.25e-05,
"loss": 1.4908,
"step": 25
},
{
"epoch": 0.02,
"learning_rate": 1.5e-05,
"loss": 1.4012,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 1.75e-05,
"loss": 1.4774,
"step": 35
},
{
"epoch": 0.02,
"learning_rate": 2e-05,
"loss": 1.5198,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 2.25e-05,
"loss": 1.1156,
"step": 45
},
{
"epoch": 0.03,
"learning_rate": 2.5e-05,
"loss": 1.2655,
"step": 50
},
{
"epoch": 0.03,
"learning_rate": 2.7500000000000004e-05,
"loss": 1.2638,
"step": 55
},
{
"epoch": 0.03,
"learning_rate": 3e-05,
"loss": 1.4318,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 3.2500000000000004e-05,
"loss": 1.2045,
"step": 65
},
{
"epoch": 0.04,
"learning_rate": 3.5e-05,
"loss": 1.2026,
"step": 70
},
{
"epoch": 0.04,
"learning_rate": 3.7500000000000003e-05,
"loss": 1.2322,
"step": 75
},
{
"epoch": 0.04,
"learning_rate": 4e-05,
"loss": 0.9502,
"step": 80
},
{
"epoch": 0.05,
"learning_rate": 4.25e-05,
"loss": 0.9484,
"step": 85
},
{
"epoch": 0.05,
"learning_rate": 4.5e-05,
"loss": 0.9976,
"step": 90
},
{
"epoch": 0.05,
"learning_rate": 4.75e-05,
"loss": 0.9654,
"step": 95
},
{
"epoch": 0.05,
"learning_rate": 5e-05,
"loss": 0.9907,
"step": 100
},
{
"epoch": 0.06,
"learning_rate": 4.9999021073200754e-05,
"loss": 0.8228,
"step": 105
},
{
"epoch": 0.06,
"learning_rate": 4.999608436946682e-05,
"loss": 0.9102,
"step": 110
},
{
"epoch": 0.06,
"learning_rate": 4.9991190118783634e-05,
"loss": 0.8813,
"step": 115
},
{
"epoch": 0.06,
"learning_rate": 4.998433870444026e-05,
"loss": 1.0755,
"step": 120
},
{
"epoch": 0.07,
"learning_rate": 4.9975530662999344e-05,
"loss": 1.0611,
"step": 125
},
{
"epoch": 0.07,
"learning_rate": 4.99647666842551e-05,
"loss": 0.8125,
"step": 130
},
{
"epoch": 0.07,
"learning_rate": 4.995204761117933e-05,
"loss": 0.9662,
"step": 135
},
{
"epoch": 0.07,
"learning_rate": 4.9937374439855336e-05,
"loss": 1.1076,
"step": 140
},
{
"epoch": 0.08,
"learning_rate": 4.9920748319399966e-05,
"loss": 0.7678,
"step": 145
},
{
"epoch": 0.08,
"learning_rate": 4.990217055187362e-05,
"loss": 0.9845,
"step": 150
},
{
"epoch": 0.08,
"learning_rate": 4.9881642592178265e-05,
"loss": 0.8852,
"step": 155
},
{
"epoch": 0.09,
"learning_rate": 4.985916604794348e-05,
"loss": 1.1478,
"step": 160
},
{
"epoch": 0.09,
"learning_rate": 4.983474267940059e-05,
"loss": 0.8057,
"step": 165
},
{
"epoch": 0.09,
"learning_rate": 4.980837439924478e-05,
"loss": 0.9576,
"step": 170
},
{
"epoch": 0.09,
"learning_rate": 4.978006327248537e-05,
"loss": 0.9848,
"step": 175
},
{
"epoch": 0.1,
"learning_rate": 4.974981151628398e-05,
"loss": 0.866,
"step": 180
},
{
"epoch": 0.1,
"learning_rate": 4.9717621499781034e-05,
"loss": 0.8123,
"step": 185
},
{
"epoch": 0.1,
"learning_rate": 4.9683495743910094e-05,
"loss": 0.8428,
"step": 190
},
{
"epoch": 0.1,
"learning_rate": 4.9647436921200514e-05,
"loss": 0.8741,
"step": 195
},
{
"epoch": 0.11,
"learning_rate": 4.960944785556814e-05,
"loss": 1.0406,
"step": 200
},
{
"epoch": 0.11,
"learning_rate": 4.9569531522094126e-05,
"loss": 0.951,
"step": 205
},
{
"epoch": 0.11,
"learning_rate": 4.952769104679195e-05,
"loss": 0.8859,
"step": 210
},
{
"epoch": 0.11,
"learning_rate": 4.9483929706362616e-05,
"loss": 0.9462,
"step": 215
},
{
"epoch": 0.12,
"learning_rate": 4.943825092793806e-05,
"loss": 0.7735,
"step": 220
},
{
"epoch": 0.12,
"learning_rate": 4.9390658288812675e-05,
"loss": 1.0622,
"step": 225
},
{
"epoch": 0.12,
"learning_rate": 4.9341155516163275e-05,
"loss": 0.8898,
"step": 230
},
{
"epoch": 0.13,
"learning_rate": 4.928974648675711e-05,
"loss": 1.0837,
"step": 235
},
{
"epoch": 0.13,
"learning_rate": 4.923643522664833e-05,
"loss": 1.0851,
"step": 240
},
{
"epoch": 0.13,
"learning_rate": 4.91812259108626e-05,
"loss": 0.8921,
"step": 245
},
{
"epoch": 0.13,
"learning_rate": 4.9124122863070255e-05,
"loss": 1.1334,
"step": 250
},
{
"epoch": 0.14,
"learning_rate": 4.9065130555247574e-05,
"loss": 1.0134,
"step": 255
},
{
"epoch": 0.14,
"learning_rate": 4.900425360732667e-05,
"loss": 0.8632,
"step": 260
},
{
"epoch": 0.14,
"learning_rate": 4.894149678683358e-05,
"loss": 0.8454,
"step": 265
},
{
"epoch": 0.14,
"learning_rate": 4.887686500851499e-05,
"loss": 1.0354,
"step": 270
},
{
"epoch": 0.15,
"learning_rate": 4.881036333395329e-05,
"loss": 0.8201,
"step": 275
},
{
"epoch": 0.15,
"learning_rate": 4.874199697117019e-05,
"loss": 1.0308,
"step": 280
},
{
"epoch": 0.15,
"learning_rate": 4.8671771274218864e-05,
"loss": 0.8313,
"step": 285
},
{
"epoch": 0.15,
"learning_rate": 4.859969174276465e-05,
"loss": 0.9553,
"step": 290
},
{
"epoch": 0.16,
"learning_rate": 4.852576402165436e-05,
"loss": 0.6957,
"step": 295
},
{
"epoch": 0.16,
"learning_rate": 4.8449993900474187e-05,
"loss": 0.8249,
"step": 300
},
{
"epoch": 0.16,
"learning_rate": 4.83723873130963e-05,
"loss": 0.8603,
"step": 305
},
{
"epoch": 0.17,
"learning_rate": 4.8292950337214147e-05,
"loss": 1.0159,
"step": 310
},
{
"epoch": 0.17,
"learning_rate": 4.82116891938665e-05,
"loss": 0.8829,
"step": 315
},
{
"epoch": 0.17,
"learning_rate": 4.812861024695023e-05,
"loss": 0.8929,
"step": 320
},
{
"epoch": 0.17,
"learning_rate": 4.804372000272196e-05,
"loss": 0.8426,
"step": 325
},
{
"epoch": 0.18,
"learning_rate": 4.795702510928848e-05,
"loss": 0.9862,
"step": 330
},
{
"epoch": 0.18,
"learning_rate": 4.786853235608616e-05,
"loss": 0.7721,
"step": 335
},
{
"epoch": 0.18,
"learning_rate": 4.77782486733492e-05,
"loss": 0.8675,
"step": 340
},
{
"epoch": 0.18,
"learning_rate": 4.768618113156694e-05,
"loss": 0.9827,
"step": 345
},
{
"epoch": 0.19,
"learning_rate": 4.75923369409301e-05,
"loss": 0.985,
"step": 350
},
{
"epoch": 0.19,
"learning_rate": 4.7496723450766125e-05,
"loss": 0.8595,
"step": 355
},
{
"epoch": 0.19,
"learning_rate": 4.739934814896364e-05,
"loss": 0.7193,
"step": 360
},
{
"epoch": 0.19,
"learning_rate": 4.730021866138607e-05,
"loss": 0.8829,
"step": 365
},
{
"epoch": 0.2,
"learning_rate": 4.719934275127434e-05,
"loss": 1.029,
"step": 370
},
{
"epoch": 0.2,
"learning_rate": 4.7096728318639025e-05,
"loss": 0.9495,
"step": 375
},
{
"epoch": 0.2,
"learning_rate": 4.6992383399641564e-05,
"loss": 1.0201,
"step": 380
},
{
"epoch": 0.21,
"learning_rate": 4.688631616596496e-05,
"loss": 1.0748,
"step": 385
},
{
"epoch": 0.21,
"learning_rate": 4.6778534924173816e-05,
"loss": 0.8893,
"step": 390
},
{
"epoch": 0.21,
"learning_rate": 4.6669048115063816e-05,
"loss": 0.9947,
"step": 395
},
{
"epoch": 0.21,
"learning_rate": 4.6557864313000695e-05,
"loss": 0.8135,
"step": 400
},
{
"epoch": 0.22,
"learning_rate": 4.644499222524873e-05,
"loss": 0.6328,
"step": 405
},
{
"epoch": 0.22,
"learning_rate": 4.633044069128884e-05,
"loss": 0.8124,
"step": 410
},
{
"epoch": 0.22,
"learning_rate": 4.621421868212635e-05,
"loss": 0.7317,
"step": 415
},
{
"epoch": 0.22,
"learning_rate": 4.609633529958841e-05,
"loss": 0.9451,
"step": 420
},
{
"epoch": 0.23,
"learning_rate": 4.597679977561122e-05,
"loss": 0.7934,
"step": 425
},
{
"epoch": 0.23,
"learning_rate": 4.5855621471516997e-05,
"loss": 0.8032,
"step": 430
},
{
"epoch": 0.23,
"learning_rate": 4.57328098772809e-05,
"loss": 0.8991,
"step": 435
},
{
"epoch": 0.23,
"learning_rate": 4.560837461078779e-05,
"loss": 0.9042,
"step": 440
},
{
"epoch": 0.24,
"learning_rate": 4.548232541707904e-05,
"loss": 0.6863,
"step": 445
},
{
"epoch": 0.24,
"learning_rate": 4.535467216758936e-05,
"loss": 0.8636,
"step": 450
},
{
"epoch": 0.24,
"learning_rate": 4.522542485937369e-05,
"loss": 1.0166,
"step": 455
},
{
"epoch": 0.25,
"learning_rate": 4.5094593614324334e-05,
"loss": 0.8609,
"step": 460
},
{
"epoch": 0.25,
"learning_rate": 4.4962188678378254e-05,
"loss": 0.9181,
"step": 465
},
{
"epoch": 0.25,
"learning_rate": 4.482822042071466e-05,
"loss": 0.8425,
"step": 470
},
{
"epoch": 0.25,
"learning_rate": 4.469269933294296e-05,
"loss": 1.0779,
"step": 475
},
{
"epoch": 0.26,
"learning_rate": 4.455563602828113e-05,
"loss": 0.7981,
"step": 480
},
{
"epoch": 0.26,
"learning_rate": 4.441704124072455e-05,
"loss": 0.8449,
"step": 485
},
{
"epoch": 0.26,
"learning_rate": 4.427692582420536e-05,
"loss": 0.9613,
"step": 490
},
{
"epoch": 0.26,
"learning_rate": 4.413530075174245e-05,
"loss": 1.0064,
"step": 495
},
{
"epoch": 0.27,
"learning_rate": 4.3992177114582124e-05,
"loss": 0.8283,
"step": 500
},
{
"epoch": 0.27,
"learning_rate": 4.384756612132952e-05,
"loss": 0.7479,
"step": 505
},
{
"epoch": 0.27,
"learning_rate": 4.370147909707077e-05,
"loss": 0.9646,
"step": 510
},
{
"epoch": 0.27,
"learning_rate": 4.3553927482486125e-05,
"loss": 0.7828,
"step": 515
},
{
"epoch": 0.28,
"learning_rate": 4.340492283295397e-05,
"loss": 1.1004,
"step": 520
},
{
"epoch": 0.28,
"learning_rate": 4.325447681764586e-05,
"loss": 0.94,
"step": 525
},
{
"epoch": 0.28,
"learning_rate": 4.3102601218612704e-05,
"loss": 0.8336,
"step": 530
},
{
"epoch": 0.29,
"learning_rate": 4.2949307929862034e-05,
"loss": 0.8661,
"step": 535
},
{
"epoch": 0.29,
"learning_rate": 4.279460895642652e-05,
"loss": 0.776,
"step": 540
},
{
"epoch": 0.29,
"learning_rate": 4.263851641342383e-05,
"loss": 0.7592,
"step": 545
},
{
"epoch": 0.29,
"learning_rate": 4.2481042525107854e-05,
"loss": 0.8982,
"step": 550
},
{
"epoch": 0.3,
"learning_rate": 4.2322199623911354e-05,
"loss": 1.0055,
"step": 555
},
{
"epoch": 0.3,
"learning_rate": 4.216200014948014e-05,
"loss": 1.029,
"step": 560
},
{
"epoch": 0.3,
"learning_rate": 4.200045664769892e-05,
"loss": 0.7536,
"step": 565
},
{
"epoch": 0.3,
"learning_rate": 4.1837581769708755e-05,
"loss": 0.9696,
"step": 570
},
{
"epoch": 0.31,
"learning_rate": 4.167338827091627e-05,
"loss": 0.809,
"step": 575
},
{
"epoch": 0.31,
"learning_rate": 4.150788900999477e-05,
"loss": 0.6986,
"step": 580
},
{
"epoch": 0.31,
"learning_rate": 4.13410969478772e-05,
"loss": 0.9191,
"step": 585
},
{
"epoch": 0.31,
"learning_rate": 4.1173025146741115e-05,
"loss": 0.7988,
"step": 590
},
{
"epoch": 0.32,
"learning_rate": 4.100368676898574e-05,
"loss": 1.2793,
"step": 595
},
{
"epoch": 0.32,
"learning_rate": 4.083309507620118e-05,
"loss": 0.9876,
"step": 600
},
{
"epoch": 0.32,
"learning_rate": 4.066126342812979e-05,
"loss": 0.9145,
"step": 605
},
{
"epoch": 0.33,
"learning_rate": 4.048820528162002e-05,
"loss": 0.7188,
"step": 610
},
{
"epoch": 0.33,
"learning_rate": 4.031393418957246e-05,
"loss": 1.0917,
"step": 615
},
{
"epoch": 0.33,
"learning_rate": 4.0138463799878475e-05,
"loss": 0.7947,
"step": 620
},
{
"epoch": 0.33,
"learning_rate": 3.996180785435144e-05,
"loss": 1.035,
"step": 625
},
{
"epoch": 0.34,
"learning_rate": 3.9783980187650496e-05,
"loss": 0.9993,
"step": 630
},
{
"epoch": 0.34,
"learning_rate": 3.960499472619713e-05,
"loss": 0.8827,
"step": 635
},
{
"epoch": 0.34,
"learning_rate": 3.942486548708454e-05,
"loss": 1.008,
"step": 640
},
{
"epoch": 0.34,
"learning_rate": 3.924360657697987e-05,
"loss": 0.9294,
"step": 645
},
{
"epoch": 0.35,
"learning_rate": 3.906123219101952e-05,
"loss": 0.9193,
"step": 650
},
{
"epoch": 0.35,
"learning_rate": 3.887775661169738e-05,
"loss": 0.9623,
"step": 655
},
{
"epoch": 0.35,
"learning_rate": 3.8693194207746385e-05,
"loss": 0.9708,
"step": 660
},
{
"epoch": 0.35,
"learning_rate": 3.8507559433013216e-05,
"loss": 0.8962,
"step": 665
},
{
"epoch": 0.36,
"learning_rate": 3.832086682532633e-05,
"loss": 0.9749,
"step": 670
},
{
"epoch": 0.36,
"learning_rate": 3.813313100535747e-05,
"loss": 0.8436,
"step": 675
},
{
"epoch": 0.36,
"learning_rate": 3.7944366675476686e-05,
"loss": 1.119,
"step": 680
},
{
"epoch": 0.37,
"learning_rate": 3.775458861860086e-05,
"loss": 0.766,
"step": 685
},
{
"epoch": 0.37,
"learning_rate": 3.756381169703607e-05,
"loss": 0.8493,
"step": 690
},
{
"epoch": 0.37,
"learning_rate": 3.737205085131359e-05,
"loss": 0.943,
"step": 695
},
{
"epoch": 0.37,
"learning_rate": 3.7179321099019916e-05,
"loss": 0.8762,
"step": 700
},
{
"epoch": 0.38,
"learning_rate": 3.69856375336206e-05,
"loss": 0.8062,
"step": 705
},
{
"epoch": 0.38,
"learning_rate": 3.6791015323278264e-05,
"loss": 1.0253,
"step": 710
},
{
"epoch": 0.38,
"learning_rate": 3.65954697096647e-05,
"loss": 0.7868,
"step": 715
},
{
"epoch": 0.38,
"learning_rate": 3.639901600676725e-05,
"loss": 1.0347,
"step": 720
},
{
"epoch": 0.39,
"learning_rate": 3.6201669599689465e-05,
"loss": 0.9483,
"step": 725
},
{
"epoch": 0.39,
"learning_rate": 3.600344594344628e-05,
"loss": 1.087,
"step": 730
},
{
"epoch": 0.39,
"learning_rate": 3.580436056175365e-05,
"loss": 1.0731,
"step": 735
},
{
"epoch": 0.39,
"learning_rate": 3.560442904581281e-05,
"loss": 0.7429,
"step": 740
},
{
"epoch": 0.4,
"learning_rate": 3.5403667053089265e-05,
"loss": 0.9416,
"step": 745
},
{
"epoch": 0.4,
"learning_rate": 3.520209030608662e-05,
"loss": 0.9878,
"step": 750
},
{
"epoch": 0.4,
"learning_rate": 3.4999714591115266e-05,
"loss": 0.9712,
"step": 755
},
{
"epoch": 0.41,
"learning_rate": 3.479655575705606e-05,
"loss": 1.045,
"step": 760
},
{
"epoch": 0.41,
"learning_rate": 3.459262971411918e-05,
"loss": 0.9611,
"step": 765
},
{
"epoch": 0.41,
"learning_rate": 3.43879524325981e-05,
"loss": 1.0409,
"step": 770
},
{
"epoch": 0.41,
"learning_rate": 3.418253994161892e-05,
"loss": 0.9732,
"step": 775
},
{
"epoch": 0.42,
"learning_rate": 3.3976408327885015e-05,
"loss": 0.7373,
"step": 780
},
{
"epoch": 0.42,
"learning_rate": 3.3769573734417256e-05,
"loss": 0.9754,
"step": 785
},
{
"epoch": 0.42,
"learning_rate": 3.356205235928978e-05,
"loss": 0.7527,
"step": 790
},
{
"epoch": 0.42,
"learning_rate": 3.33538604543614e-05,
"loss": 0.9828,
"step": 795
},
{
"epoch": 0.43,
"learning_rate": 3.3145014324002944e-05,
"loss": 0.8507,
"step": 800
},
{
"epoch": 0.43,
"learning_rate": 3.293553032382032e-05,
"loss": 0.9479,
"step": 805
},
{
"epoch": 0.43,
"learning_rate": 3.272542485937369e-05,
"loss": 0.7149,
"step": 810
},
{
"epoch": 0.43,
"learning_rate": 3.251471438489262e-05,
"loss": 0.829,
"step": 815
},
{
"epoch": 0.44,
"learning_rate": 3.230341540198754e-05,
"loss": 0.8014,
"step": 820
},
{
"epoch": 0.44,
"learning_rate": 3.209154445835742e-05,
"loss": 0.8209,
"step": 825
},
{
"epoch": 0.44,
"learning_rate": 3.187911814649383e-05,
"loss": 0.8609,
"step": 830
},
{
"epoch": 0.45,
"learning_rate": 3.166615310238153e-05,
"loss": 0.8066,
"step": 835
},
{
"epoch": 0.45,
"learning_rate": 3.145266600419565e-05,
"loss": 0.9395,
"step": 840
},
{
"epoch": 0.45,
"learning_rate": 3.1238673570995524e-05,
"loss": 0.7853,
"step": 845
},
{
"epoch": 0.45,
"learning_rate": 3.102419256141536e-05,
"loss": 0.9172,
"step": 850
},
{
"epoch": 0.46,
"learning_rate": 3.0809239772351824e-05,
"loss": 1.2131,
"step": 855
},
{
"epoch": 0.46,
"learning_rate": 3.059383203764857e-05,
"loss": 0.9192,
"step": 860
},
{
"epoch": 0.46,
"learning_rate": 3.0377986226777945e-05,
"loss": 0.9534,
"step": 865
},
{
"epoch": 0.46,
"learning_rate": 3.016171924351985e-05,
"loss": 0.7594,
"step": 870
},
{
"epoch": 0.47,
"learning_rate": 2.9945048024637935e-05,
"loss": 0.8499,
"step": 875
},
{
"epoch": 0.47,
"learning_rate": 2.9727989538553232e-05,
"loss": 0.9014,
"step": 880
},
{
"epoch": 0.47,
"learning_rate": 2.9510560784015257e-05,
"loss": 0.7373,
"step": 885
},
{
"epoch": 0.47,
"learning_rate": 2.9292778788770797e-05,
"loss": 1.1039,
"step": 890
},
{
"epoch": 0.48,
"learning_rate": 2.907466060823037e-05,
"loss": 0.7907,
"step": 895
},
{
"epoch": 0.48,
"learning_rate": 2.885622332413256e-05,
"loss": 0.942,
"step": 900
},
{
"epoch": 0.48,
"learning_rate": 2.863748404320628e-05,
"loss": 0.6486,
"step": 905
},
{
"epoch": 0.49,
"learning_rate": 2.8418459895831068e-05,
"loss": 1.0279,
"step": 910
},
{
"epoch": 0.49,
"learning_rate": 2.819916803469551e-05,
"loss": 0.9169,
"step": 915
},
{
"epoch": 0.49,
"learning_rate": 2.7979625633454004e-05,
"loss": 0.9556,
"step": 920
},
{
"epoch": 0.49,
"learning_rate": 2.775984988538175e-05,
"loss": 0.8916,
"step": 925
},
{
"epoch": 0.5,
"learning_rate": 2.7539858002028314e-05,
"loss": 0.7564,
"step": 930
},
{
"epoch": 0.5,
"learning_rate": 2.7319667211869725e-05,
"loss": 0.8854,
"step": 935
},
{
"epoch": 0.5,
"learning_rate": 2.709929475895921e-05,
"loss": 1.0735,
"step": 940
},
{
"epoch": 0.5,
"learning_rate": 2.6878757901576773e-05,
"loss": 1.0539,
"step": 945
},
{
"epoch": 0.51,
"learning_rate": 2.6658073910877603e-05,
"loss": 0.7653,
"step": 950
},
{
"epoch": 0.51,
"learning_rate": 2.6437260069539503e-05,
"loss": 0.9273,
"step": 955
},
{
"epoch": 0.51,
"learning_rate": 2.6216333670409453e-05,
"loss": 0.7204,
"step": 960
},
{
"epoch": 0.51,
"learning_rate": 2.5995312015149253e-05,
"loss": 1.182,
"step": 965
},
{
"epoch": 0.52,
"learning_rate": 2.5774212412880634e-05,
"loss": 0.699,
"step": 970
},
{
"epoch": 0.52,
"learning_rate": 2.555305217882967e-05,
"loss": 1.0156,
"step": 975
},
{
"epoch": 0.52,
"learning_rate": 2.5331848632970772e-05,
"loss": 1.144,
"step": 980
},
{
"epoch": 0.53,
"learning_rate": 2.5110619098670263e-05,
"loss": 0.7747,
"step": 985
},
{
"epoch": 0.53,
"learning_rate": 2.488938090132974e-05,
"loss": 0.9474,
"step": 990
},
{
"epoch": 0.53,
"learning_rate": 2.4668151367029234e-05,
"loss": 0.9307,
"step": 995
},
{
"epoch": 0.53,
"learning_rate": 2.444694782117033e-05,
"loss": 1.002,
"step": 1000
},
{
"epoch": 0.54,
"learning_rate": 2.422578758711937e-05,
"loss": 0.8443,
"step": 1005
},
{
"epoch": 0.54,
"learning_rate": 2.4004687984850753e-05,
"loss": 1.1606,
"step": 1010
},
{
"epoch": 0.54,
"learning_rate": 2.3783666329590553e-05,
"loss": 0.875,
"step": 1015
},
{
"epoch": 0.54,
"learning_rate": 2.35627399304605e-05,
"loss": 0.873,
"step": 1020
},
{
"epoch": 0.55,
"learning_rate": 2.334192608912241e-05,
"loss": 0.9557,
"step": 1025
},
{
"epoch": 0.55,
"learning_rate": 2.3121242098423233e-05,
"loss": 0.7154,
"step": 1030
},
{
"epoch": 0.55,
"learning_rate": 2.2900705241040792e-05,
"loss": 0.8942,
"step": 1035
},
{
"epoch": 0.55,
"learning_rate": 2.268033278813028e-05,
"loss": 0.9301,
"step": 1040
},
{
"epoch": 0.56,
"learning_rate": 2.2460141997971692e-05,
"loss": 1.0188,
"step": 1045
},
{
"epoch": 0.56,
"learning_rate": 2.224015011461826e-05,
"loss": 0.8915,
"step": 1050
},
{
"epoch": 0.56,
"learning_rate": 2.2020374366546006e-05,
"loss": 0.7145,
"step": 1055
},
{
"epoch": 0.57,
"learning_rate": 2.1800831965304498e-05,
"loss": 0.8901,
"step": 1060
},
{
"epoch": 0.57,
"learning_rate": 2.158154010416894e-05,
"loss": 0.798,
"step": 1065
},
{
"epoch": 0.57,
"learning_rate": 2.1362515956793715e-05,
"loss": 0.8913,
"step": 1070
},
{
"epoch": 0.57,
"learning_rate": 2.114377667586744e-05,
"loss": 0.881,
"step": 1075
},
{
"epoch": 0.58,
"learning_rate": 2.0925339391769632e-05,
"loss": 0.8176,
"step": 1080
},
{
"epoch": 0.58,
"learning_rate": 2.0707221211229205e-05,
"loss": 0.9179,
"step": 1085
},
{
"epoch": 0.58,
"learning_rate": 2.0489439215984742e-05,
"loss": 0.8757,
"step": 1090
},
{
"epoch": 0.58,
"learning_rate": 2.027201046144677e-05,
"loss": 0.8905,
"step": 1095
},
{
"epoch": 0.59,
"learning_rate": 2.0054951975362067e-05,
"loss": 0.9235,
"step": 1100
},
{
"epoch": 0.59,
"learning_rate": 1.9838280756480156e-05,
"loss": 0.9577,
"step": 1105
},
{
"epoch": 0.59,
"learning_rate": 1.962201377322206e-05,
"loss": 0.9302,
"step": 1110
},
{
"epoch": 0.59,
"learning_rate": 1.9406167962351435e-05,
"loss": 0.8898,
"step": 1115
},
{
"epoch": 0.6,
"learning_rate": 1.9190760227648182e-05,
"loss": 1.1963,
"step": 1120
},
{
"epoch": 0.6,
"learning_rate": 1.8975807438584642e-05,
"loss": 0.9905,
"step": 1125
},
{
"epoch": 0.6,
"learning_rate": 1.8761326429004482e-05,
"loss": 0.9767,
"step": 1130
},
{
"epoch": 0.61,
"learning_rate": 1.8547333995804352e-05,
"loss": 0.9304,
"step": 1135
},
{
"epoch": 0.61,
"learning_rate": 1.8333846897618473e-05,
"loss": 0.8,
"step": 1140
},
{
"epoch": 0.61,
"learning_rate": 1.812088185350618e-05,
"loss": 0.7821,
"step": 1145
},
{
"epoch": 0.61,
"learning_rate": 1.7908455541642584e-05,
"loss": 1.0053,
"step": 1150
},
{
"epoch": 0.62,
"learning_rate": 1.7696584598012463e-05,
"loss": 1.0378,
"step": 1155
},
{
"epoch": 0.62,
"learning_rate": 1.7485285615107387e-05,
"loss": 0.7936,
"step": 1160
},
{
"epoch": 0.62,
"learning_rate": 1.7274575140626318e-05,
"loss": 0.7954,
"step": 1165
},
{
"epoch": 0.62,
"learning_rate": 1.706446967617968e-05,
"loss": 0.9855,
"step": 1170
},
{
"epoch": 0.63,
"learning_rate": 1.6854985675997066e-05,
"loss": 1.0846,
"step": 1175
},
{
"epoch": 0.63,
"learning_rate": 1.664613954563861e-05,
"loss": 0.8494,
"step": 1180
},
{
"epoch": 0.63,
"learning_rate": 1.643794764071024e-05,
"loss": 0.837,
"step": 1185
},
{
"epoch": 0.63,
"learning_rate": 1.623042626558275e-05,
"loss": 0.8491,
"step": 1190
},
{
"epoch": 0.64,
"learning_rate": 1.602359167211499e-05,
"loss": 1.0021,
"step": 1195
},
{
"epoch": 0.64,
"learning_rate": 1.5817460058381088e-05,
"loss": 0.8144,
"step": 1200
},
{
"epoch": 0.64,
"learning_rate": 1.5612047567401904e-05,
"loss": 0.8625,
"step": 1205
},
{
"epoch": 0.65,
"learning_rate": 1.540737028588082e-05,
"loss": 1.0831,
"step": 1210
},
{
"epoch": 0.65,
"learning_rate": 1.520344424294394e-05,
"loss": 0.668,
"step": 1215
},
{
"epoch": 0.65,
"learning_rate": 1.5000285408884735e-05,
"loss": 0.7774,
"step": 1220
},
{
"epoch": 0.65,
"learning_rate": 1.4797909693913376e-05,
"loss": 1.0238,
"step": 1225
},
{
"epoch": 0.66,
"learning_rate": 1.4596332946910738e-05,
"loss": 1.1004,
"step": 1230
},
{
"epoch": 0.66,
"learning_rate": 1.4395570954187199e-05,
"loss": 0.8647,
"step": 1235
},
{
"epoch": 0.66,
"learning_rate": 1.4195639438246355e-05,
"loss": 0.794,
"step": 1240
},
{
"epoch": 0.66,
"learning_rate": 1.3996554056553723e-05,
"loss": 0.8817,
"step": 1245
},
{
"epoch": 0.67,
"learning_rate": 1.3798330400310539e-05,
"loss": 0.7758,
"step": 1250
},
{
"epoch": 0.67,
"learning_rate": 1.3600983993232758e-05,
"loss": 1.1403,
"step": 1255
},
{
"epoch": 0.67,
"learning_rate": 1.3404530290335304e-05,
"loss": 0.8733,
"step": 1260
},
{
"epoch": 0.67,
"learning_rate": 1.3208984676721741e-05,
"loss": 0.8425,
"step": 1265
},
{
"epoch": 0.68,
"learning_rate": 1.3014362466379407e-05,
"loss": 0.8829,
"step": 1270
},
{
"epoch": 0.68,
"learning_rate": 1.2820678900980093e-05,
"loss": 0.8972,
"step": 1275
},
{
"epoch": 0.68,
"learning_rate": 1.262794914868642e-05,
"loss": 0.6963,
"step": 1280
},
{
"epoch": 0.69,
"learning_rate": 1.2436188302963944e-05,
"loss": 0.7988,
"step": 1285
},
{
"epoch": 0.69,
"learning_rate": 1.224541138139915e-05,
"loss": 1.1047,
"step": 1290
},
{
"epoch": 0.69,
"learning_rate": 1.2055633324523324e-05,
"loss": 0.9825,
"step": 1295
},
{
"epoch": 0.69,
"learning_rate": 1.1866868994642535e-05,
"loss": 0.7205,
"step": 1300
},
{
"epoch": 0.7,
"learning_rate": 1.1679133174673684e-05,
"loss": 0.6994,
"step": 1305
},
{
"epoch": 0.7,
"learning_rate": 1.1492440566986795e-05,
"loss": 0.7823,
"step": 1310
},
{
"epoch": 0.7,
"learning_rate": 1.1306805792253614e-05,
"loss": 0.9258,
"step": 1315
},
{
"epoch": 0.7,
"learning_rate": 1.1122243388302621e-05,
"loss": 0.7392,
"step": 1320
},
{
"epoch": 0.71,
"learning_rate": 1.0938767808980486e-05,
"loss": 0.693,
"step": 1325
},
{
"epoch": 0.71,
"learning_rate": 1.0756393423020128e-05,
"loss": 0.9524,
"step": 1330
},
{
"epoch": 0.71,
"learning_rate": 1.0575134512915463e-05,
"loss": 0.9227,
"step": 1335
},
{
"epoch": 0.71,
"learning_rate": 1.0395005273802872e-05,
"loss": 0.9156,
"step": 1340
},
{
"epoch": 0.72,
"learning_rate": 1.0216019812349508e-05,
"loss": 0.7696,
"step": 1345
},
{
"epoch": 0.72,
"learning_rate": 1.0038192145648567e-05,
"loss": 0.8188,
"step": 1350
},
{
"epoch": 0.72,
"learning_rate": 9.861536200121534e-06,
"loss": 1.1761,
"step": 1355
},
{
"epoch": 0.73,
"learning_rate": 9.686065810427547e-06,
"loss": 1.0429,
"step": 1360
},
{
"epoch": 0.73,
"learning_rate": 9.511794718379977e-06,
"loss": 0.9353,
"step": 1365
},
{
"epoch": 0.73,
"learning_rate": 9.338736571870204e-06,
"loss": 1.0411,
"step": 1370
},
{
"epoch": 0.73,
"learning_rate": 9.166904923798821e-06,
"loss": 0.8242,
"step": 1375
},
{
"epoch": 0.74,
"learning_rate": 8.996313231014256e-06,
"loss": 0.977,
"step": 1380
},
{
"epoch": 0.74,
"learning_rate": 8.826974853258884e-06,
"loss": 0.8923,
"step": 1385
},
{
"epoch": 0.74,
"learning_rate": 8.658903052122798e-06,
"loss": 0.859,
"step": 1390
},
{
"epoch": 0.74,
"learning_rate": 8.492110990005228e-06,
"loss": 0.9146,
"step": 1395
},
{
"epoch": 0.75,
"learning_rate": 8.32661172908373e-06,
"loss": 0.848,
"step": 1400
},
{
"epoch": 0.75,
"learning_rate": 8.162418230291249e-06,
"loss": 1.0004,
"step": 1405
},
{
"epoch": 0.75,
"learning_rate": 7.99954335230108e-06,
"loss": 0.9763,
"step": 1410
},
{
"epoch": 0.75,
"learning_rate": 7.837999850519868e-06,
"loss": 0.8771,
"step": 1415
},
{
"epoch": 0.76,
"learning_rate": 7.677800376088656e-06,
"loss": 0.766,
"step": 1420
},
{
"epoch": 0.76,
"learning_rate": 7.518957474892149e-06,
"loss": 0.8326,
"step": 1425
},
{
"epoch": 0.76,
"learning_rate": 7.3614835865761765e-06,
"loss": 1.0521,
"step": 1430
},
{
"epoch": 0.77,
"learning_rate": 7.20539104357349e-06,
"loss": 0.7602,
"step": 1435
},
{
"epoch": 0.77,
"learning_rate": 7.0506920701379735e-06,
"loss": 1.0047,
"step": 1440
},
{
"epoch": 0.77,
"learning_rate": 6.897398781387299e-06,
"loss": 0.9478,
"step": 1445
},
{
"epoch": 0.77,
"learning_rate": 6.745523182354147e-06,
"loss": 0.8251,
"step": 1450
},
{
"epoch": 0.78,
"learning_rate": 6.59507716704604e-06,
"loss": 0.9253,
"step": 1455
},
{
"epoch": 0.78,
"learning_rate": 6.446072517513879e-06,
"loss": 0.7583,
"step": 1460
},
{
"epoch": 0.78,
"learning_rate": 6.298520902929234e-06,
"loss": 1.1714,
"step": 1465
},
{
"epoch": 0.78,
"learning_rate": 6.152433878670486e-06,
"loss": 0.8578,
"step": 1470
},
{
"epoch": 0.79,
"learning_rate": 6.007822885417882e-06,
"loss": 0.9193,
"step": 1475
},
{
"epoch": 0.79,
"learning_rate": 5.864699248257563e-06,
"loss": 0.8938,
"step": 1480
},
{
"epoch": 0.79,
"learning_rate": 5.7230741757946485e-06,
"loss": 0.9434,
"step": 1485
},
{
"epoch": 0.79,
"learning_rate": 5.582958759275456e-06,
"loss": 0.8449,
"step": 1490
},
{
"epoch": 0.8,
"learning_rate": 5.444363971718874e-06,
"loss": 0.9795,
"step": 1495
},
{
"epoch": 0.8,
"learning_rate": 5.307300667057049e-06,
"loss": 0.8855,
"step": 1500
},
{
"epoch": 0.8,
"learning_rate": 5.171779579285352e-06,
"loss": 0.8158,
"step": 1505
},
{
"epoch": 0.81,
"learning_rate": 5.0378113216217495e-06,
"loss": 0.8632,
"step": 1510
},
{
"epoch": 0.81,
"learning_rate": 4.9054063856756674e-06,
"loss": 1.0902,
"step": 1515
},
{
"epoch": 0.81,
"learning_rate": 4.7745751406263165e-06,
"loss": 0.7169,
"step": 1520
},
{
"epoch": 0.81,
"learning_rate": 4.645327832410648e-06,
"loss": 0.8929,
"step": 1525
},
{
"epoch": 0.82,
"learning_rate": 4.5176745829209614e-06,
"loss": 1.1013,
"step": 1530
},
{
"epoch": 0.82,
"learning_rate": 4.391625389212214e-06,
"loss": 1.049,
"step": 1535
},
{
"epoch": 0.82,
"learning_rate": 4.2671901227191055e-06,
"loss": 0.9125,
"step": 1540
},
{
"epoch": 0.82,
"learning_rate": 4.144378528483009e-06,
"loss": 0.919,
"step": 1545
},
{
"epoch": 0.83,
"learning_rate": 4.023200224388787e-06,
"loss": 0.9128,
"step": 1550
},
{
"epoch": 0.83,
"learning_rate": 3.903664700411588e-06,
"loss": 0.8124,
"step": 1555
},
{
"epoch": 0.83,
"learning_rate": 3.785781317873652e-06,
"loss": 0.6316,
"step": 1560
},
{
"epoch": 0.83,
"learning_rate": 3.6695593087111623e-06,
"loss": 0.8769,
"step": 1565
},
{
"epoch": 0.84,
"learning_rate": 3.5550077747512732e-06,
"loss": 0.9873,
"step": 1570
},
{
"epoch": 0.84,
"learning_rate": 3.4421356869993037e-06,
"loss": 0.8763,
"step": 1575
},
{
"epoch": 0.84,
"learning_rate": 3.3309518849361814e-06,
"loss": 1.015,
"step": 1580
},
{
"epoch": 0.85,
"learning_rate": 3.2214650758261854e-06,
"loss": 0.8868,
"step": 1585
},
{
"epoch": 0.85,
"learning_rate": 3.1136838340350417e-06,
"loss": 0.8198,
"step": 1590
},
{
"epoch": 0.85,
"learning_rate": 3.007616600358437e-06,
"loss": 0.9481,
"step": 1595
},
{
"epoch": 0.85,
"learning_rate": 2.9032716813609723e-06,
"loss": 0.8791,
"step": 1600
},
{
"epoch": 0.86,
"learning_rate": 2.800657248725658e-06,
"loss": 0.7747,
"step": 1605
},
{
"epoch": 0.86,
"learning_rate": 2.699781338613938e-06,
"loss": 0.7336,
"step": 1610
},
{
"epoch": 0.86,
"learning_rate": 2.600651851036362e-06,
"loss": 0.9263,
"step": 1615
},
{
"epoch": 0.86,
"learning_rate": 2.503276549233882e-06,
"loss": 0.9969,
"step": 1620
},
{
"epoch": 0.87,
"learning_rate": 2.4076630590699062e-06,
"loss": 0.788,
"step": 1625
},
{
"epoch": 0.87,
"learning_rate": 2.3138188684330596e-06,
"loss": 1.0097,
"step": 1630
},
{
"epoch": 0.87,
"learning_rate": 2.2217513266508007e-06,
"loss": 1.0821,
"step": 1635
},
{
"epoch": 0.87,
"learning_rate": 2.131467643913848e-06,
"loss": 1.0141,
"step": 1640
},
{
"epoch": 0.88,
"learning_rate": 2.042974890711524e-06,
"loss": 0.8745,
"step": 1645
},
{
"epoch": 0.88,
"learning_rate": 1.956279997278043e-06,
"loss": 0.963,
"step": 1650
},
{
"epoch": 0.88,
"learning_rate": 1.8713897530497653e-06,
"loss": 0.9889,
"step": 1655
},
{
"epoch": 0.89,
"learning_rate": 1.7883108061335001e-06,
"loss": 0.7698,
"step": 1660
},
{
"epoch": 0.89,
"learning_rate": 1.7070496627858563e-06,
"loss": 0.8428,
"step": 1665
},
{
"epoch": 0.89,
"learning_rate": 1.6276126869037038e-06,
"loss": 0.9162,
"step": 1670
},
{
"epoch": 0.89,
"learning_rate": 1.5500060995258137e-06,
"loss": 1.1577,
"step": 1675
},
{
"epoch": 0.9,
"learning_rate": 1.4742359783456367e-06,
"loss": 1.0998,
"step": 1680
},
{
"epoch": 0.9,
"learning_rate": 1.400308257235347e-06,
"loss": 0.8622,
"step": 1685
},
{
"epoch": 0.9,
"learning_rate": 1.3282287257811416e-06,
"loss": 0.943,
"step": 1690
},
{
"epoch": 0.9,
"learning_rate": 1.2580030288298183e-06,
"loss": 0.9814,
"step": 1695
},
{
"epoch": 0.91,
"learning_rate": 1.1896366660467173e-06,
"loss": 0.7347,
"step": 1700
},
{
"epoch": 0.91,
"learning_rate": 1.1231349914850143e-06,
"loss": 0.8488,
"step": 1705
},
{
"epoch": 0.91,
"learning_rate": 1.0585032131664257e-06,
"loss": 1.0964,
"step": 1710
},
{
"epoch": 0.91,
"learning_rate": 9.957463926733385e-07,
"loss": 0.9621,
"step": 1715
},
{
"epoch": 0.92,
"learning_rate": 9.348694447524259e-07,
"loss": 0.7326,
"step": 1720
},
{
"epoch": 0.92,
"learning_rate": 8.758771369297536e-07,
"loss": 0.9444,
"step": 1725
},
{
"epoch": 0.92,
"learning_rate": 8.18774089137403e-07,
"loss": 0.754,
"step": 1730
},
{
"epoch": 0.93,
"learning_rate": 7.635647733516827e-07,
"loss": 0.8082,
"step": 1735
},
{
"epoch": 0.93,
"learning_rate": 7.10253513242895e-07,
"loss": 0.8634,
"step": 1740
},
{
"epoch": 0.93,
"learning_rate": 6.588444838367347e-07,
"loss": 0.6584,
"step": 1745
},
{
"epoch": 0.93,
"learning_rate": 6.093417111873306e-07,
"loss": 0.9802,
"step": 1750
},
{
"epoch": 0.94,
"learning_rate": 5.617490720619511e-07,
"loss": 0.9283,
"step": 1755
},
{
"epoch": 0.94,
"learning_rate": 5.160702936373802e-07,
"loss": 0.6214,
"step": 1760
},
{
"epoch": 0.94,
"learning_rate": 4.7230895320805044e-07,
"loss": 1.0153,
"step": 1765
},
{
"epoch": 0.94,
"learning_rate": 4.3046847790587653e-07,
"loss": 0.8742,
"step": 1770
},
{
"epoch": 0.95,
"learning_rate": 3.905521444318605e-07,
"loss": 1.1606,
"step": 1775
},
{
"epoch": 0.95,
"learning_rate": 3.5256307879948933e-07,
"loss": 0.7276,
"step": 1780
},
{
"epoch": 0.95,
"learning_rate": 3.1650425608991397e-07,
"loss": 1.0695,
"step": 1785
},
{
"epoch": 0.95,
"learning_rate": 2.823785002189716e-07,
"loss": 0.9512,
"step": 1790
},
{
"epoch": 0.96,
"learning_rate": 2.5018848371601844e-07,
"loss": 1.0723,
"step": 1795
},
{
"epoch": 0.96,
"learning_rate": 2.1993672751463579e-07,
"loss": 0.8787,
"step": 1800
}
],
"logging_steps": 5,
"max_steps": 1875,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 200,
"total_flos": 1.672777000943616e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}