M7Bv01_SFT_50pct_QLORA_2H100 / trainer_state.json
Serega6678's picture
Model save
e96cfad verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9996554496382222,
"eval_steps": 500,
"global_step": 1088,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.8348623853211011e-06,
"loss": 1.166,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 9.174311926605506e-06,
"loss": 1.1533,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 1.834862385321101e-05,
"loss": 1.1332,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 2.7522935779816515e-05,
"loss": 1.1124,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 3.669724770642202e-05,
"loss": 1.0896,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.587155963302753e-05,
"loss": 1.0765,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 5.504587155963303e-05,
"loss": 1.0314,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 6.422018348623854e-05,
"loss": 1.0489,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 7.339449541284404e-05,
"loss": 1.0039,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 8.256880733944955e-05,
"loss": 0.9825,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 9.174311926605506e-05,
"loss": 0.9929,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 0.00010091743119266055,
"loss": 0.9923,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 0.00011009174311926606,
"loss": 1.0024,
"step": 60
},
{
"epoch": 0.06,
"learning_rate": 0.00011926605504587157,
"loss": 1.0202,
"step": 65
},
{
"epoch": 0.06,
"learning_rate": 0.00012844036697247707,
"loss": 1.0064,
"step": 70
},
{
"epoch": 0.07,
"learning_rate": 0.00013761467889908258,
"loss": 0.9896,
"step": 75
},
{
"epoch": 0.07,
"learning_rate": 0.0001467889908256881,
"loss": 0.9902,
"step": 80
},
{
"epoch": 0.08,
"learning_rate": 0.0001559633027522936,
"loss": 0.9856,
"step": 85
},
{
"epoch": 0.08,
"learning_rate": 0.0001651376146788991,
"loss": 0.9789,
"step": 90
},
{
"epoch": 0.09,
"learning_rate": 0.00017431192660550458,
"loss": 0.9845,
"step": 95
},
{
"epoch": 0.09,
"learning_rate": 0.00018348623853211012,
"loss": 0.9741,
"step": 100
},
{
"epoch": 0.1,
"learning_rate": 0.0001926605504587156,
"loss": 0.9714,
"step": 105
},
{
"epoch": 0.1,
"learning_rate": 0.00019999948512240548,
"loss": 1.0182,
"step": 110
},
{
"epoch": 0.11,
"learning_rate": 0.00019998146496329837,
"loss": 0.9622,
"step": 115
},
{
"epoch": 0.11,
"learning_rate": 0.00019993770622619782,
"loss": 0.9725,
"step": 120
},
{
"epoch": 0.11,
"learning_rate": 0.00019986822017606848,
"loss": 0.9853,
"step": 125
},
{
"epoch": 0.12,
"learning_rate": 0.00019977302470094708,
"loss": 0.981,
"step": 130
},
{
"epoch": 0.12,
"learning_rate": 0.00019965214430733754,
"loss": 0.9773,
"step": 135
},
{
"epoch": 0.13,
"learning_rate": 0.00019950561011390213,
"loss": 0.9749,
"step": 140
},
{
"epoch": 0.13,
"learning_rate": 0.00019933345984345037,
"loss": 0.988,
"step": 145
},
{
"epoch": 0.14,
"learning_rate": 0.00019913573781322818,
"loss": 0.9992,
"step": 150
},
{
"epoch": 0.14,
"learning_rate": 0.00019891249492350887,
"loss": 0.9706,
"step": 155
},
{
"epoch": 0.15,
"learning_rate": 0.00019866378864448985,
"loss": 0.9663,
"step": 160
},
{
"epoch": 0.15,
"learning_rate": 0.00019838968300149782,
"loss": 0.974,
"step": 165
},
{
"epoch": 0.16,
"learning_rate": 0.00019809024855850662,
"loss": 0.9755,
"step": 170
},
{
"epoch": 0.16,
"learning_rate": 0.00019776556239997146,
"loss": 0.9621,
"step": 175
},
{
"epoch": 0.17,
"learning_rate": 0.000197415708110985,
"loss": 0.9749,
"step": 180
},
{
"epoch": 0.17,
"learning_rate": 0.00019704077575575978,
"loss": 0.958,
"step": 185
},
{
"epoch": 0.17,
"learning_rate": 0.00019664086185444246,
"loss": 0.9863,
"step": 190
},
{
"epoch": 0.18,
"learning_rate": 0.0001962160693582665,
"loss": 1.0012,
"step": 195
},
{
"epoch": 0.18,
"learning_rate": 0.00019576650762304903,
"loss": 0.9802,
"step": 200
},
{
"epoch": 0.19,
"learning_rate": 0.00019529229238103883,
"loss": 0.9748,
"step": 205
},
{
"epoch": 0.19,
"learning_rate": 0.00019479354571112323,
"loss": 1.012,
"step": 210
},
{
"epoch": 0.2,
"learning_rate": 0.00019427039600740072,
"loss": 0.9702,
"step": 215
},
{
"epoch": 0.2,
"learning_rate": 0.00019372297794612817,
"loss": 0.9607,
"step": 220
},
{
"epoch": 0.21,
"learning_rate": 0.00019315143245105047,
"loss": 0.9543,
"step": 225
},
{
"epoch": 0.21,
"learning_rate": 0.00019255590665712214,
"loss": 0.9941,
"step": 230
},
{
"epoch": 0.22,
"learning_rate": 0.00019193655387262984,
"loss": 0.9915,
"step": 235
},
{
"epoch": 0.22,
"learning_rate": 0.00019129353353972581,
"loss": 0.98,
"step": 240
},
{
"epoch": 0.23,
"learning_rate": 0.00019062701119338185,
"loss": 0.9759,
"step": 245
},
{
"epoch": 0.23,
"learning_rate": 0.0001899371584187753,
"loss": 0.9784,
"step": 250
},
{
"epoch": 0.23,
"learning_rate": 0.00018922415280711716,
"loss": 0.9737,
"step": 255
},
{
"epoch": 0.24,
"learning_rate": 0.00018848817790993432,
"loss": 0.9737,
"step": 260
},
{
"epoch": 0.24,
"learning_rate": 0.00018772942319181696,
"loss": 0.9674,
"step": 265
},
{
"epoch": 0.25,
"learning_rate": 0.0001869480839816443,
"loss": 0.9572,
"step": 270
},
{
"epoch": 0.25,
"learning_rate": 0.0001861443614223002,
"loss": 0.9758,
"step": 275
},
{
"epoch": 0.26,
"learning_rate": 0.00018531846241889245,
"loss": 0.9611,
"step": 280
},
{
"epoch": 0.26,
"learning_rate": 0.0001844705995854882,
"loss": 0.9593,
"step": 285
},
{
"epoch": 0.27,
"learning_rate": 0.0001836009911903803,
"loss": 0.9847,
"step": 290
},
{
"epoch": 0.27,
"learning_rate": 0.00018270986109989744,
"loss": 0.9755,
"step": 295
},
{
"epoch": 0.28,
"learning_rate": 0.00018179743872077359,
"loss": 0.9491,
"step": 300
},
{
"epoch": 0.28,
"learning_rate": 0.000180863958941091,
"loss": 0.9872,
"step": 305
},
{
"epoch": 0.28,
"learning_rate": 0.00017990966206981224,
"loss": 0.9491,
"step": 310
},
{
"epoch": 0.29,
"learning_rate": 0.0001789347937749164,
"loss": 0.9579,
"step": 315
},
{
"epoch": 0.29,
"learning_rate": 0.00017793960502015613,
"loss": 0.9702,
"step": 320
},
{
"epoch": 0.3,
"learning_rate": 0.0001769243520004511,
"loss": 0.9749,
"step": 325
},
{
"epoch": 0.3,
"learning_rate": 0.0001758892960759348,
"loss": 0.9624,
"step": 330
},
{
"epoch": 0.31,
"learning_rate": 0.00017483470370467178,
"loss": 0.9547,
"step": 335
},
{
"epoch": 0.31,
"learning_rate": 0.00017376084637406222,
"loss": 0.9685,
"step": 340
},
{
"epoch": 0.32,
"learning_rate": 0.00017266800053095232,
"loss": 0.9455,
"step": 345
},
{
"epoch": 0.32,
"learning_rate": 0.0001715564475104673,
"loss": 0.9745,
"step": 350
},
{
"epoch": 0.33,
"learning_rate": 0.00017042647346358645,
"loss": 0.9906,
"step": 355
},
{
"epoch": 0.33,
"learning_rate": 0.00016927836928347826,
"loss": 0.9749,
"step": 360
},
{
"epoch": 0.34,
"learning_rate": 0.00016811243053061487,
"loss": 0.9674,
"step": 365
},
{
"epoch": 0.34,
"learning_rate": 0.00016692895735668476,
"loss": 0.9589,
"step": 370
},
{
"epoch": 0.34,
"learning_rate": 0.00016572825442732366,
"loss": 0.9703,
"step": 375
},
{
"epoch": 0.35,
"learning_rate": 0.0001645106308436836,
"loss": 0.9472,
"step": 380
},
{
"epoch": 0.35,
"learning_rate": 0.00016327640006285967,
"loss": 0.9647,
"step": 385
},
{
"epoch": 0.36,
"learning_rate": 0.00016202587981719584,
"loss": 0.9631,
"step": 390
},
{
"epoch": 0.36,
"learning_rate": 0.0001607593920324899,
"loss": 0.9784,
"step": 395
},
{
"epoch": 0.37,
"learning_rate": 0.00015947726274511908,
"loss": 0.9662,
"step": 400
},
{
"epoch": 0.37,
"learning_rate": 0.0001581798220181073,
"loss": 0.9433,
"step": 405
},
{
"epoch": 0.38,
"learning_rate": 0.00015686740385615586,
"loss": 0.9731,
"step": 410
},
{
"epoch": 0.38,
"learning_rate": 0.00015554034611965954,
"loss": 0.9593,
"step": 415
},
{
"epoch": 0.39,
"learning_rate": 0.00015419899043772994,
"loss": 0.9379,
"step": 420
},
{
"epoch": 0.39,
"learning_rate": 0.00015284368212024877,
"loss": 0.9453,
"step": 425
},
{
"epoch": 0.4,
"learning_rate": 0.00015147477006897337,
"loss": 0.9581,
"step": 430
},
{
"epoch": 0.4,
"learning_rate": 0.000150092606687718,
"loss": 0.9595,
"step": 435
},
{
"epoch": 0.4,
"learning_rate": 0.0001486975477916329,
"loss": 0.9726,
"step": 440
},
{
"epoch": 0.41,
"learning_rate": 0.00014728995251560596,
"loss": 0.9479,
"step": 445
},
{
"epoch": 0.41,
"learning_rate": 0.00014587018322180905,
"loss": 0.9698,
"step": 450
},
{
"epoch": 0.42,
"learning_rate": 0.00014443860540641406,
"loss": 0.9639,
"step": 455
},
{
"epoch": 0.42,
"learning_rate": 0.00014299558760550184,
"loss": 0.9803,
"step": 460
},
{
"epoch": 0.43,
"learning_rate": 0.00014154150130018866,
"loss": 0.9708,
"step": 465
},
{
"epoch": 0.43,
"learning_rate": 0.0001400767208209946,
"loss": 0.9624,
"step": 470
},
{
"epoch": 0.44,
"learning_rate": 0.0001386016232514784,
"loss": 0.9683,
"step": 475
},
{
"epoch": 0.44,
"learning_rate": 0.00013711658833116323,
"loss": 0.9472,
"step": 480
},
{
"epoch": 0.45,
"learning_rate": 0.00013562199835777934,
"loss": 0.9613,
"step": 485
},
{
"epoch": 0.45,
"learning_rate": 0.00013411823808884765,
"loss": 0.9535,
"step": 490
},
{
"epoch": 0.45,
"learning_rate": 0.00013260569464263036,
"loss": 0.9339,
"step": 495
},
{
"epoch": 0.46,
"learning_rate": 0.00013108475739847362,
"loss": 0.9634,
"step": 500
},
{
"epoch": 0.46,
"learning_rate": 0.00012955581789656843,
"loss": 0.9665,
"step": 505
},
{
"epoch": 0.47,
"learning_rate": 0.00012801926973715483,
"loss": 0.9415,
"step": 510
},
{
"epoch": 0.47,
"learning_rate": 0.0001264755084791963,
"loss": 0.9423,
"step": 515
},
{
"epoch": 0.48,
"learning_rate": 0.00012492493153854937,
"loss": 0.9653,
"step": 520
},
{
"epoch": 0.48,
"learning_rate": 0.0001233679380856557,
"loss": 0.9544,
"step": 525
},
{
"epoch": 0.49,
"learning_rate": 0.00012180492894278206,
"loss": 0.9639,
"step": 530
},
{
"epoch": 0.49,
"learning_rate": 0.00012023630648083528,
"loss": 0.9618,
"step": 535
},
{
"epoch": 0.5,
"learning_rate": 0.00011866247451577864,
"loss": 0.9411,
"step": 540
},
{
"epoch": 0.5,
"learning_rate": 0.00011708383820467595,
"loss": 0.9592,
"step": 545
},
{
"epoch": 0.51,
"learning_rate": 0.00011550080394139062,
"loss": 0.962,
"step": 550
},
{
"epoch": 0.51,
"learning_rate": 0.00011391377925196626,
"loss": 0.9857,
"step": 555
},
{
"epoch": 0.51,
"learning_rate": 0.00011232317268971585,
"loss": 0.9723,
"step": 560
},
{
"epoch": 0.52,
"learning_rate": 0.00011072939373004647,
"loss": 0.9561,
"step": 565
},
{
"epoch": 0.52,
"learning_rate": 0.00010913285266504636,
"loss": 0.9531,
"step": 570
},
{
"epoch": 0.53,
"learning_rate": 0.0001075339604978624,
"loss": 0.9512,
"step": 575
},
{
"epoch": 0.53,
"learning_rate": 0.0001059331288368938,
"loss": 0.959,
"step": 580
},
{
"epoch": 0.54,
"learning_rate": 0.0001043307697898305,
"loss": 0.9423,
"step": 585
},
{
"epoch": 0.54,
"learning_rate": 0.00010272729585756275,
"loss": 0.9656,
"step": 590
},
{
"epoch": 0.55,
"learning_rate": 0.00010112311982798959,
"loss": 0.9701,
"step": 595
},
{
"epoch": 0.55,
"learning_rate": 9.951865466975344e-05,
"loss": 0.9553,
"step": 600
},
{
"epoch": 0.56,
"learning_rate": 9.791431342592811e-05,
"loss": 0.9353,
"step": 605
},
{
"epoch": 0.56,
"learning_rate": 9.631050910768773e-05,
"loss": 0.9363,
"step": 610
},
{
"epoch": 0.57,
"learning_rate": 9.470765458798368e-05,
"loss": 0.9463,
"step": 615
},
{
"epoch": 0.57,
"learning_rate": 9.310616249525759e-05,
"loss": 0.9629,
"step": 620
},
{
"epoch": 0.57,
"learning_rate": 9.15064451072165e-05,
"loss": 0.9485,
"step": 625
},
{
"epoch": 0.58,
"learning_rate": 8.990891424469927e-05,
"loss": 0.9585,
"step": 630
},
{
"epoch": 0.58,
"learning_rate": 8.831398116565964e-05,
"loss": 0.9848,
"step": 635
},
{
"epoch": 0.59,
"learning_rate": 8.672205645929503e-05,
"loss": 0.9371,
"step": 640
},
{
"epoch": 0.59,
"learning_rate": 8.513354994034681e-05,
"loss": 0.9354,
"step": 645
},
{
"epoch": 0.6,
"learning_rate": 8.35488705436006e-05,
"loss": 0.9606,
"step": 650
},
{
"epoch": 0.6,
"learning_rate": 8.196842621861242e-05,
"loss": 0.9672,
"step": 655
},
{
"epoch": 0.61,
"learning_rate": 8.039262382468905e-05,
"loss": 0.9562,
"step": 660
},
{
"epoch": 0.61,
"learning_rate": 7.882186902614865e-05,
"loss": 0.9731,
"step": 665
},
{
"epoch": 0.62,
"learning_rate": 7.725656618788937e-05,
"loss": 0.9606,
"step": 670
},
{
"epoch": 0.62,
"learning_rate": 7.569711827129208e-05,
"loss": 0.9426,
"step": 675
},
{
"epoch": 0.62,
"learning_rate": 7.414392673048478e-05,
"loss": 0.9451,
"step": 680
},
{
"epoch": 0.63,
"learning_rate": 7.259739140899462e-05,
"loss": 0.95,
"step": 685
},
{
"epoch": 0.63,
"learning_rate": 7.105791043681519e-05,
"loss": 0.9636,
"step": 690
},
{
"epoch": 0.64,
"learning_rate": 6.952588012791405e-05,
"loss": 0.9472,
"step": 695
},
{
"epoch": 0.64,
"learning_rate": 6.80016948782086e-05,
"loss": 0.9516,
"step": 700
},
{
"epoch": 0.65,
"learning_rate": 6.648574706403522e-05,
"loss": 0.9558,
"step": 705
},
{
"epoch": 0.65,
"learning_rate": 6.497842694113842e-05,
"loss": 0.9741,
"step": 710
},
{
"epoch": 0.66,
"learning_rate": 6.348012254420606e-05,
"loss": 0.9626,
"step": 715
},
{
"epoch": 0.66,
"learning_rate": 6.199121958697604e-05,
"loss": 0.9499,
"step": 720
},
{
"epoch": 0.67,
"learning_rate": 6.051210136294089e-05,
"loss": 0.9557,
"step": 725
},
{
"epoch": 0.67,
"learning_rate": 5.904314864667497e-05,
"loss": 0.9562,
"step": 730
},
{
"epoch": 0.68,
"learning_rate": 5.758473959581061e-05,
"loss": 0.933,
"step": 735
},
{
"epoch": 0.68,
"learning_rate": 5.613724965368723e-05,
"loss": 0.9766,
"step": 740
},
{
"epoch": 0.68,
"learning_rate": 5.4701051452700245e-05,
"loss": 0.9381,
"step": 745
},
{
"epoch": 0.69,
"learning_rate": 5.327651471837242e-05,
"loss": 0.9397,
"step": 750
},
{
"epoch": 0.69,
"learning_rate": 5.1864006174174504e-05,
"loss": 0.9309,
"step": 755
},
{
"epoch": 0.7,
"learning_rate": 5.046388944711824e-05,
"loss": 0.9578,
"step": 760
},
{
"epoch": 0.7,
"learning_rate": 4.9076524974146507e-05,
"loss": 0.9472,
"step": 765
},
{
"epoch": 0.71,
"learning_rate": 4.7702269909344907e-05,
"loss": 0.9419,
"step": 770
},
{
"epoch": 0.71,
"learning_rate": 4.6341478031998265e-05,
"loss": 0.9791,
"step": 775
},
{
"epoch": 0.72,
"learning_rate": 4.4994499655515865e-05,
"loss": 0.9417,
"step": 780
},
{
"epoch": 0.72,
"learning_rate": 4.3661681537249455e-05,
"loss": 0.9433,
"step": 785
},
{
"epoch": 0.73,
"learning_rate": 4.234336678922569e-05,
"loss": 0.9308,
"step": 790
},
{
"epoch": 0.73,
"learning_rate": 4.103989478981827e-05,
"loss": 0.9556,
"step": 795
},
{
"epoch": 0.74,
"learning_rate": 3.975160109637992e-05,
"loss": 0.9535,
"step": 800
},
{
"epoch": 0.74,
"learning_rate": 3.847881735885918e-05,
"loss": 0.9496,
"step": 805
},
{
"epoch": 0.74,
"learning_rate": 3.722187123442249e-05,
"loss": 0.9417,
"step": 810
},
{
"epoch": 0.75,
"learning_rate": 3.598108630310399e-05,
"loss": 0.9336,
"step": 815
},
{
"epoch": 0.75,
"learning_rate": 3.475678198450555e-05,
"loss": 0.9492,
"step": 820
},
{
"epoch": 0.76,
"learning_rate": 3.354927345556723e-05,
"loss": 0.963,
"step": 825
},
{
"epoch": 0.76,
"learning_rate": 3.235887156943029e-05,
"loss": 0.9489,
"step": 830
},
{
"epoch": 0.77,
"learning_rate": 3.118588277541312e-05,
"loss": 0.9551,
"step": 835
},
{
"epoch": 0.77,
"learning_rate": 3.003060904012096e-05,
"loss": 0.9497,
"step": 840
},
{
"epoch": 0.78,
"learning_rate": 2.8893347769709476e-05,
"loss": 0.927,
"step": 845
},
{
"epoch": 0.78,
"learning_rate": 2.7774391733322713e-05,
"loss": 0.964,
"step": 850
},
{
"epoch": 0.79,
"learning_rate": 2.6674028987724163e-05,
"loss": 0.9524,
"step": 855
},
{
"epoch": 0.79,
"learning_rate": 2.559254280314156e-05,
"loss": 0.9519,
"step": 860
},
{
"epoch": 0.79,
"learning_rate": 2.4530211590343578e-05,
"loss": 0.96,
"step": 865
},
{
"epoch": 0.8,
"learning_rate": 2.3487308828967493e-05,
"loss": 0.9603,
"step": 870
},
{
"epoch": 0.8,
"learning_rate": 2.2464102997116475e-05,
"loss": 0.9513,
"step": 875
},
{
"epoch": 0.81,
"learning_rate": 2.1460857502244248e-05,
"loss": 0.9621,
"step": 880
},
{
"epoch": 0.81,
"learning_rate": 2.047783061334523e-05,
"loss": 0.9459,
"step": 885
},
{
"epoch": 0.82,
"learning_rate": 1.9515275394467446e-05,
"loss": 0.9421,
"step": 890
},
{
"epoch": 0.82,
"learning_rate": 1.8573439639565282e-05,
"loss": 0.9757,
"step": 895
},
{
"epoch": 0.83,
"learning_rate": 1.765256580870924e-05,
"loss": 0.9392,
"step": 900
},
{
"epoch": 0.83,
"learning_rate": 1.6752890965668266e-05,
"loss": 0.9413,
"step": 905
},
{
"epoch": 0.84,
"learning_rate": 1.587464671688187e-05,
"loss": 0.9638,
"step": 910
},
{
"epoch": 0.84,
"learning_rate": 1.501805915183685e-05,
"loss": 0.9464,
"step": 915
},
{
"epoch": 0.85,
"learning_rate": 1.4183348784864037e-05,
"loss": 0.9909,
"step": 920
},
{
"epoch": 0.85,
"learning_rate": 1.3370730498370831e-05,
"loss": 0.9639,
"step": 925
},
{
"epoch": 0.85,
"learning_rate": 1.258041348752308e-05,
"loss": 0.9478,
"step": 930
},
{
"epoch": 0.86,
"learning_rate": 1.1812601206391304e-05,
"loss": 0.9451,
"step": 935
},
{
"epoch": 0.86,
"learning_rate": 1.1067491315574797e-05,
"loss": 0.9606,
"step": 940
},
{
"epoch": 0.87,
"learning_rate": 1.0345275631317163e-05,
"loss": 0.95,
"step": 945
},
{
"epoch": 0.87,
"learning_rate": 9.64614007612633e-06,
"loss": 0.917,
"step": 950
},
{
"epoch": 0.88,
"learning_rate": 8.970264630912061e-06,
"loss": 0.9498,
"step": 955
},
{
"epoch": 0.88,
"learning_rate": 8.317823288652526e-06,
"loss": 0.9526,
"step": 960
},
{
"epoch": 0.89,
"learning_rate": 7.688984009603062e-06,
"loss": 0.9482,
"step": 965
},
{
"epoch": 0.89,
"learning_rate": 7.083908678057194e-06,
"loss": 0.9614,
"step": 970
},
{
"epoch": 0.9,
"learning_rate": 6.502753060672495e-06,
"loss": 0.948,
"step": 975
},
{
"epoch": 0.9,
"learning_rate": 5.945666766370861e-06,
"loss": 0.9497,
"step": 980
},
{
"epoch": 0.91,
"learning_rate": 5.412793207824252e-06,
"loss": 0.958,
"step": 985
},
{
"epoch": 0.91,
"learning_rate": 4.904269564535391e-06,
"loss": 0.9649,
"step": 990
},
{
"epoch": 0.91,
"learning_rate": 4.42022674752326e-06,
"loss": 0.9505,
"step": 995
},
{
"epoch": 0.92,
"learning_rate": 3.960789365622075e-06,
"loss": 0.9659,
"step": 1000
},
{
"epoch": 0.92,
"learning_rate": 3.526075693402986e-06,
"loss": 0.9486,
"step": 1005
},
{
"epoch": 0.93,
"learning_rate": 3.116197640726104e-06,
"loss": 0.9495,
"step": 1010
},
{
"epoch": 0.93,
"learning_rate": 2.7312607239311505e-06,
"loss": 0.9771,
"step": 1015
},
{
"epoch": 0.94,
"learning_rate": 2.3713640386741396e-06,
"loss": 0.938,
"step": 1020
},
{
"epoch": 0.94,
"learning_rate": 2.0366002344166745e-06,
"loss": 0.953,
"step": 1025
},
{
"epoch": 0.95,
"learning_rate": 1.7270554905750137e-06,
"loss": 0.976,
"step": 1030
},
{
"epoch": 0.95,
"learning_rate": 1.4428094943345294e-06,
"loss": 0.9734,
"step": 1035
},
{
"epoch": 0.96,
"learning_rate": 1.1839354201355513e-06,
"loss": 0.9538,
"step": 1040
},
{
"epoch": 0.96,
"learning_rate": 9.50499910835867e-07,
"loss": 0.998,
"step": 1045
},
{
"epoch": 0.96,
"learning_rate": 7.425630605545575e-07,
"loss": 0.9474,
"step": 1050
},
{
"epoch": 0.97,
"learning_rate": 5.60178399201805e-07,
"loss": 0.957,
"step": 1055
},
{
"epoch": 0.97,
"learning_rate": 4.0339287869847197e-07,
"loss": 0.9426,
"step": 1060
},
{
"epoch": 0.98,
"learning_rate": 2.7224686088910265e-07,
"loss": 0.9386,
"step": 1065
},
{
"epoch": 0.98,
"learning_rate": 1.6677410715149054e-07,
"loss": 0.954,
"step": 1070
},
{
"epoch": 0.99,
"learning_rate": 8.700176970527497e-08,
"loss": 0.9449,
"step": 1075
},
{
"epoch": 0.99,
"learning_rate": 3.29503846221213e-08,
"loss": 0.9593,
"step": 1080
},
{
"epoch": 1.0,
"learning_rate": 4.633866539005549e-09,
"loss": 0.9504,
"step": 1085
},
{
"epoch": 1.0,
"eval_loss": 0.9550448656082153,
"eval_runtime": 1441.354,
"eval_samples_per_second": 5.335,
"eval_steps_per_second": 0.667,
"step": 1088
},
{
"epoch": 1.0,
"step": 1088,
"total_flos": 6.120039388450652e+18,
"train_loss": 0.9663942014688954,
"train_runtime": 46060.5946,
"train_samples_per_second": 1.512,
"train_steps_per_second": 0.024
}
],
"logging_steps": 5,
"max_steps": 1088,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 6.120039388450652e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}