zephyr-danube2-sft-qlora / trainer_state.json
Ritvik19's picture
Upload 13 files
879fd07 verified
raw
history blame
37.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9995621747712183,
"eval_steps": 500,
"global_step": 1088,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0009187152341647227,
"grad_norm": 0.12890625,
"learning_rate": 1.8348623853211011e-06,
"loss": 1.1775,
"step": 1
},
{
"epoch": 0.004593576170823614,
"grad_norm": 0.1240234375,
"learning_rate": 9.174311926605506e-06,
"loss": 1.1877,
"step": 5
},
{
"epoch": 0.009187152341647228,
"grad_norm": 0.1298828125,
"learning_rate": 1.834862385321101e-05,
"loss": 1.1744,
"step": 10
},
{
"epoch": 0.01378072851247084,
"grad_norm": 0.11865234375,
"learning_rate": 2.7522935779816515e-05,
"loss": 1.1666,
"step": 15
},
{
"epoch": 0.018374304683294457,
"grad_norm": 0.0947265625,
"learning_rate": 3.669724770642202e-05,
"loss": 1.1771,
"step": 20
},
{
"epoch": 0.02296788085411807,
"grad_norm": 0.083984375,
"learning_rate": 4.587155963302753e-05,
"loss": 1.1437,
"step": 25
},
{
"epoch": 0.02756145702494168,
"grad_norm": 0.07080078125,
"learning_rate": 5.504587155963303e-05,
"loss": 1.1373,
"step": 30
},
{
"epoch": 0.0321550331957653,
"grad_norm": 0.0517578125,
"learning_rate": 6.422018348623854e-05,
"loss": 1.0934,
"step": 35
},
{
"epoch": 0.036748609366588914,
"grad_norm": 0.0439453125,
"learning_rate": 7.339449541284404e-05,
"loss": 1.0912,
"step": 40
},
{
"epoch": 0.04134218553741253,
"grad_norm": 0.041748046875,
"learning_rate": 8.256880733944955e-05,
"loss": 1.1026,
"step": 45
},
{
"epoch": 0.04593576170823614,
"grad_norm": 0.0380859375,
"learning_rate": 9.174311926605506e-05,
"loss": 1.0824,
"step": 50
},
{
"epoch": 0.05052933787905975,
"grad_norm": 0.03369140625,
"learning_rate": 0.00010091743119266055,
"loss": 1.1075,
"step": 55
},
{
"epoch": 0.05512291404988336,
"grad_norm": 0.034423828125,
"learning_rate": 0.00011009174311926606,
"loss": 1.1073,
"step": 60
},
{
"epoch": 0.05971649022070698,
"grad_norm": 0.0322265625,
"learning_rate": 0.00011926605504587157,
"loss": 1.0848,
"step": 65
},
{
"epoch": 0.0643100663915306,
"grad_norm": 0.0294189453125,
"learning_rate": 0.00012844036697247707,
"loss": 1.072,
"step": 70
},
{
"epoch": 0.0689036425623542,
"grad_norm": 0.0311279296875,
"learning_rate": 0.00013761467889908258,
"loss": 1.0763,
"step": 75
},
{
"epoch": 0.07349721873317783,
"grad_norm": 0.0294189453125,
"learning_rate": 0.0001467889908256881,
"loss": 1.0737,
"step": 80
},
{
"epoch": 0.07809079490400143,
"grad_norm": 0.0308837890625,
"learning_rate": 0.0001559633027522936,
"loss": 1.0564,
"step": 85
},
{
"epoch": 0.08268437107482506,
"grad_norm": 0.030517578125,
"learning_rate": 0.0001651376146788991,
"loss": 1.0754,
"step": 90
},
{
"epoch": 0.08727794724564866,
"grad_norm": 0.0296630859375,
"learning_rate": 0.00017431192660550458,
"loss": 1.0635,
"step": 95
},
{
"epoch": 0.09187152341647228,
"grad_norm": 0.02978515625,
"learning_rate": 0.00018348623853211012,
"loss": 1.0757,
"step": 100
},
{
"epoch": 0.09646509958729589,
"grad_norm": 0.0299072265625,
"learning_rate": 0.0001926605504587156,
"loss": 1.0715,
"step": 105
},
{
"epoch": 0.1010586757581195,
"grad_norm": 0.0301513671875,
"learning_rate": 0.00019999948512240548,
"loss": 1.0733,
"step": 110
},
{
"epoch": 0.10565225192894312,
"grad_norm": 0.0289306640625,
"learning_rate": 0.00019998146496329837,
"loss": 1.0891,
"step": 115
},
{
"epoch": 0.11024582809976673,
"grad_norm": 0.03125,
"learning_rate": 0.00019993770622619782,
"loss": 1.0702,
"step": 120
},
{
"epoch": 0.11483940427059035,
"grad_norm": 0.033447265625,
"learning_rate": 0.00019986822017606848,
"loss": 1.0861,
"step": 125
},
{
"epoch": 0.11943298044141396,
"grad_norm": 0.0294189453125,
"learning_rate": 0.00019977302470094708,
"loss": 1.0615,
"step": 130
},
{
"epoch": 0.12402655661223758,
"grad_norm": 0.0296630859375,
"learning_rate": 0.00019965214430733754,
"loss": 1.0673,
"step": 135
},
{
"epoch": 0.1286201327830612,
"grad_norm": 0.031982421875,
"learning_rate": 0.00019950561011390213,
"loss": 1.0648,
"step": 140
},
{
"epoch": 0.1332137089538848,
"grad_norm": 0.031494140625,
"learning_rate": 0.00019933345984345037,
"loss": 1.0685,
"step": 145
},
{
"epoch": 0.1378072851247084,
"grad_norm": 0.0301513671875,
"learning_rate": 0.00019913573781322818,
"loss": 1.0663,
"step": 150
},
{
"epoch": 0.14240086129553203,
"grad_norm": 0.0291748046875,
"learning_rate": 0.00019891249492350887,
"loss": 1.079,
"step": 155
},
{
"epoch": 0.14699443746635565,
"grad_norm": 0.03076171875,
"learning_rate": 0.00019866378864448985,
"loss": 1.0959,
"step": 160
},
{
"epoch": 0.15158801363717925,
"grad_norm": 0.030029296875,
"learning_rate": 0.00019838968300149782,
"loss": 1.0805,
"step": 165
},
{
"epoch": 0.15618158980800287,
"grad_norm": 0.0302734375,
"learning_rate": 0.00019809024855850662,
"loss": 1.0644,
"step": 170
},
{
"epoch": 0.1607751659788265,
"grad_norm": 0.02978515625,
"learning_rate": 0.00019776556239997146,
"loss": 1.0657,
"step": 175
},
{
"epoch": 0.1653687421496501,
"grad_norm": 0.0289306640625,
"learning_rate": 0.000197415708110985,
"loss": 1.0559,
"step": 180
},
{
"epoch": 0.1699623183204737,
"grad_norm": 0.02978515625,
"learning_rate": 0.00019704077575575978,
"loss": 1.0507,
"step": 185
},
{
"epoch": 0.17455589449129733,
"grad_norm": 0.031005859375,
"learning_rate": 0.00019664086185444246,
"loss": 1.1005,
"step": 190
},
{
"epoch": 0.17914947066212095,
"grad_norm": 0.02978515625,
"learning_rate": 0.0001962160693582665,
"loss": 1.0795,
"step": 195
},
{
"epoch": 0.18374304683294457,
"grad_norm": 0.0291748046875,
"learning_rate": 0.00019576650762304903,
"loss": 1.0786,
"step": 200
},
{
"epoch": 0.18833662300376816,
"grad_norm": 0.0284423828125,
"learning_rate": 0.00019529229238103883,
"loss": 1.0602,
"step": 205
},
{
"epoch": 0.19293019917459178,
"grad_norm": 0.0301513671875,
"learning_rate": 0.00019479354571112323,
"loss": 1.072,
"step": 210
},
{
"epoch": 0.1975237753454154,
"grad_norm": 0.0286865234375,
"learning_rate": 0.00019427039600740072,
"loss": 1.0903,
"step": 215
},
{
"epoch": 0.202117351516239,
"grad_norm": 0.03076171875,
"learning_rate": 0.00019372297794612817,
"loss": 1.0734,
"step": 220
},
{
"epoch": 0.20671092768706262,
"grad_norm": 0.029541015625,
"learning_rate": 0.00019315143245105047,
"loss": 1.0638,
"step": 225
},
{
"epoch": 0.21130450385788624,
"grad_norm": 0.0302734375,
"learning_rate": 0.00019255590665712214,
"loss": 1.0663,
"step": 230
},
{
"epoch": 0.21589808002870986,
"grad_norm": 0.029052734375,
"learning_rate": 0.00019193655387262984,
"loss": 1.0778,
"step": 235
},
{
"epoch": 0.22049165619953345,
"grad_norm": 0.02978515625,
"learning_rate": 0.00019129353353972581,
"loss": 1.0732,
"step": 240
},
{
"epoch": 0.22508523237035707,
"grad_norm": 0.029052734375,
"learning_rate": 0.00019062701119338185,
"loss": 1.0463,
"step": 245
},
{
"epoch": 0.2296788085411807,
"grad_norm": 0.030517578125,
"learning_rate": 0.0001899371584187753,
"loss": 1.0674,
"step": 250
},
{
"epoch": 0.23427238471200432,
"grad_norm": 0.0294189453125,
"learning_rate": 0.00018922415280711716,
"loss": 1.0611,
"step": 255
},
{
"epoch": 0.2388659608828279,
"grad_norm": 0.0291748046875,
"learning_rate": 0.00018848817790993432,
"loss": 1.0603,
"step": 260
},
{
"epoch": 0.24345953705365153,
"grad_norm": 0.0299072265625,
"learning_rate": 0.00018772942319181696,
"loss": 1.0497,
"step": 265
},
{
"epoch": 0.24805311322447515,
"grad_norm": 0.0311279296875,
"learning_rate": 0.0001869480839816443,
"loss": 1.056,
"step": 270
},
{
"epoch": 0.2526466893952988,
"grad_norm": 0.029541015625,
"learning_rate": 0.0001861443614223002,
"loss": 1.0677,
"step": 275
},
{
"epoch": 0.2572402655661224,
"grad_norm": 0.0301513671875,
"learning_rate": 0.00018531846241889245,
"loss": 1.0646,
"step": 280
},
{
"epoch": 0.261833841736946,
"grad_norm": 0.030029296875,
"learning_rate": 0.0001844705995854882,
"loss": 1.0962,
"step": 285
},
{
"epoch": 0.2664274179077696,
"grad_norm": 0.0296630859375,
"learning_rate": 0.0001836009911903803,
"loss": 1.0587,
"step": 290
},
{
"epoch": 0.2710209940785932,
"grad_norm": 0.0299072265625,
"learning_rate": 0.00018270986109989744,
"loss": 1.0724,
"step": 295
},
{
"epoch": 0.2756145702494168,
"grad_norm": 0.0299072265625,
"learning_rate": 0.00018179743872077359,
"loss": 1.0816,
"step": 300
},
{
"epoch": 0.28020814642024044,
"grad_norm": 0.030029296875,
"learning_rate": 0.000180863958941091,
"loss": 1.0654,
"step": 305
},
{
"epoch": 0.28480172259106407,
"grad_norm": 0.032470703125,
"learning_rate": 0.00017990966206981224,
"loss": 1.0828,
"step": 310
},
{
"epoch": 0.2893952987618877,
"grad_norm": 0.02978515625,
"learning_rate": 0.0001789347937749164,
"loss": 1.0492,
"step": 315
},
{
"epoch": 0.2939888749327113,
"grad_norm": 0.0294189453125,
"learning_rate": 0.00017793960502015613,
"loss": 1.0845,
"step": 320
},
{
"epoch": 0.2985824511035349,
"grad_norm": 0.0294189453125,
"learning_rate": 0.0001769243520004511,
"loss": 1.0536,
"step": 325
},
{
"epoch": 0.3031760272743585,
"grad_norm": 0.030029296875,
"learning_rate": 0.0001758892960759348,
"loss": 1.0649,
"step": 330
},
{
"epoch": 0.3077696034451821,
"grad_norm": 0.031005859375,
"learning_rate": 0.00017483470370467178,
"loss": 1.064,
"step": 335
},
{
"epoch": 0.31236317961600574,
"grad_norm": 0.0296630859375,
"learning_rate": 0.00017376084637406222,
"loss": 1.0584,
"step": 340
},
{
"epoch": 0.31695675578682936,
"grad_norm": 0.02978515625,
"learning_rate": 0.00017266800053095232,
"loss": 1.0616,
"step": 345
},
{
"epoch": 0.321550331957653,
"grad_norm": 0.030029296875,
"learning_rate": 0.0001715564475104673,
"loss": 1.0868,
"step": 350
},
{
"epoch": 0.3261439081284766,
"grad_norm": 0.030517578125,
"learning_rate": 0.00017042647346358645,
"loss": 1.0808,
"step": 355
},
{
"epoch": 0.3307374842993002,
"grad_norm": 0.0294189453125,
"learning_rate": 0.00016927836928347826,
"loss": 1.0739,
"step": 360
},
{
"epoch": 0.3353310604701238,
"grad_norm": 0.030517578125,
"learning_rate": 0.00016811243053061487,
"loss": 1.078,
"step": 365
},
{
"epoch": 0.3399246366409474,
"grad_norm": 0.030517578125,
"learning_rate": 0.00016692895735668476,
"loss": 1.0578,
"step": 370
},
{
"epoch": 0.34451821281177103,
"grad_norm": 0.0308837890625,
"learning_rate": 0.00016572825442732366,
"loss": 1.0535,
"step": 375
},
{
"epoch": 0.34911178898259465,
"grad_norm": 0.03125,
"learning_rate": 0.0001645106308436836,
"loss": 1.0668,
"step": 380
},
{
"epoch": 0.35370536515341827,
"grad_norm": 0.031494140625,
"learning_rate": 0.00016327640006285967,
"loss": 1.05,
"step": 385
},
{
"epoch": 0.3582989413242419,
"grad_norm": 0.031494140625,
"learning_rate": 0.00016202587981719584,
"loss": 1.066,
"step": 390
},
{
"epoch": 0.3628925174950655,
"grad_norm": 0.030517578125,
"learning_rate": 0.0001607593920324899,
"loss": 1.0622,
"step": 395
},
{
"epoch": 0.36748609366588914,
"grad_norm": 0.031982421875,
"learning_rate": 0.00015947726274511908,
"loss": 1.0666,
"step": 400
},
{
"epoch": 0.3720796698367127,
"grad_norm": 0.031494140625,
"learning_rate": 0.0001581798220181073,
"loss": 1.0531,
"step": 405
},
{
"epoch": 0.3766732460075363,
"grad_norm": 0.0311279296875,
"learning_rate": 0.00015686740385615586,
"loss": 1.0829,
"step": 410
},
{
"epoch": 0.38126682217835994,
"grad_norm": 0.030517578125,
"learning_rate": 0.00015554034611965954,
"loss": 1.0592,
"step": 415
},
{
"epoch": 0.38586039834918356,
"grad_norm": 0.031494140625,
"learning_rate": 0.00015419899043772994,
"loss": 1.05,
"step": 420
},
{
"epoch": 0.3904539745200072,
"grad_norm": 0.030029296875,
"learning_rate": 0.00015284368212024877,
"loss": 1.0732,
"step": 425
},
{
"epoch": 0.3950475506908308,
"grad_norm": 0.031494140625,
"learning_rate": 0.00015147477006897337,
"loss": 1.0728,
"step": 430
},
{
"epoch": 0.3996411268616544,
"grad_norm": 0.030029296875,
"learning_rate": 0.000150092606687718,
"loss": 1.0481,
"step": 435
},
{
"epoch": 0.404234703032478,
"grad_norm": 0.03173828125,
"learning_rate": 0.0001486975477916329,
"loss": 1.0781,
"step": 440
},
{
"epoch": 0.4088282792033016,
"grad_norm": 0.03125,
"learning_rate": 0.00014728995251560596,
"loss": 1.0703,
"step": 445
},
{
"epoch": 0.41342185537412524,
"grad_norm": 0.0322265625,
"learning_rate": 0.00014587018322180905,
"loss": 1.0554,
"step": 450
},
{
"epoch": 0.41801543154494886,
"grad_norm": 0.03076171875,
"learning_rate": 0.00014443860540641406,
"loss": 1.0626,
"step": 455
},
{
"epoch": 0.4226090077157725,
"grad_norm": 0.033203125,
"learning_rate": 0.00014299558760550184,
"loss": 1.0918,
"step": 460
},
{
"epoch": 0.4272025838865961,
"grad_norm": 0.0302734375,
"learning_rate": 0.00014154150130018866,
"loss": 1.0488,
"step": 465
},
{
"epoch": 0.4317961600574197,
"grad_norm": 0.031494140625,
"learning_rate": 0.0001400767208209946,
"loss": 1.0599,
"step": 470
},
{
"epoch": 0.43638973622824334,
"grad_norm": 0.0308837890625,
"learning_rate": 0.0001386016232514784,
"loss": 1.0669,
"step": 475
},
{
"epoch": 0.4409833123990669,
"grad_norm": 0.0311279296875,
"learning_rate": 0.00013711658833116323,
"loss": 1.0721,
"step": 480
},
{
"epoch": 0.44557688856989053,
"grad_norm": 0.03173828125,
"learning_rate": 0.00013562199835777934,
"loss": 1.0829,
"step": 485
},
{
"epoch": 0.45017046474071415,
"grad_norm": 0.03125,
"learning_rate": 0.00013411823808884765,
"loss": 1.0611,
"step": 490
},
{
"epoch": 0.45476404091153777,
"grad_norm": 0.031494140625,
"learning_rate": 0.00013260569464263036,
"loss": 1.0547,
"step": 495
},
{
"epoch": 0.4593576170823614,
"grad_norm": 0.032958984375,
"learning_rate": 0.00013108475739847362,
"loss": 1.0635,
"step": 500
},
{
"epoch": 0.463951193253185,
"grad_norm": 0.0302734375,
"learning_rate": 0.00012955581789656843,
"loss": 1.0746,
"step": 505
},
{
"epoch": 0.46854476942400863,
"grad_norm": 0.03125,
"learning_rate": 0.00012801926973715483,
"loss": 1.0665,
"step": 510
},
{
"epoch": 0.4731383455948322,
"grad_norm": 0.03125,
"learning_rate": 0.0001264755084791963,
"loss": 1.0547,
"step": 515
},
{
"epoch": 0.4777319217656558,
"grad_norm": 0.03271484375,
"learning_rate": 0.00012492493153854937,
"loss": 1.0508,
"step": 520
},
{
"epoch": 0.48232549793647944,
"grad_norm": 0.03173828125,
"learning_rate": 0.0001233679380856557,
"loss": 1.082,
"step": 525
},
{
"epoch": 0.48691907410730306,
"grad_norm": 0.03173828125,
"learning_rate": 0.00012180492894278206,
"loss": 1.0656,
"step": 530
},
{
"epoch": 0.4915126502781267,
"grad_norm": 0.032958984375,
"learning_rate": 0.00012023630648083528,
"loss": 1.0703,
"step": 535
},
{
"epoch": 0.4961062264489503,
"grad_norm": 0.031982421875,
"learning_rate": 0.00011866247451577864,
"loss": 1.0685,
"step": 540
},
{
"epoch": 0.5006998026197739,
"grad_norm": 0.0306396484375,
"learning_rate": 0.00011708383820467595,
"loss": 1.0568,
"step": 545
},
{
"epoch": 0.5052933787905975,
"grad_norm": 0.0322265625,
"learning_rate": 0.00011550080394139062,
"loss": 1.0405,
"step": 550
},
{
"epoch": 0.5098869549614211,
"grad_norm": 0.033203125,
"learning_rate": 0.00011391377925196626,
"loss": 1.0654,
"step": 555
},
{
"epoch": 0.5144805311322448,
"grad_norm": 0.031005859375,
"learning_rate": 0.00011232317268971585,
"loss": 1.0578,
"step": 560
},
{
"epoch": 0.5190741073030684,
"grad_norm": 0.03125,
"learning_rate": 0.00011072939373004647,
"loss": 1.0581,
"step": 565
},
{
"epoch": 0.523667683473892,
"grad_norm": 0.031005859375,
"learning_rate": 0.00010913285266504636,
"loss": 1.0464,
"step": 570
},
{
"epoch": 0.5282612596447156,
"grad_norm": 0.0308837890625,
"learning_rate": 0.0001075339604978624,
"loss": 1.0744,
"step": 575
},
{
"epoch": 0.5328548358155392,
"grad_norm": 0.0308837890625,
"learning_rate": 0.0001059331288368938,
"loss": 1.0675,
"step": 580
},
{
"epoch": 0.5374484119863628,
"grad_norm": 0.031982421875,
"learning_rate": 0.0001043307697898305,
"loss": 1.0682,
"step": 585
},
{
"epoch": 0.5420419881571864,
"grad_norm": 0.032470703125,
"learning_rate": 0.00010272729585756275,
"loss": 1.0577,
"step": 590
},
{
"epoch": 0.5466355643280101,
"grad_norm": 0.0311279296875,
"learning_rate": 0.00010112311982798959,
"loss": 1.0535,
"step": 595
},
{
"epoch": 0.5512291404988336,
"grad_norm": 0.0306396484375,
"learning_rate": 9.951865466975344e-05,
"loss": 1.0713,
"step": 600
},
{
"epoch": 0.5558227166696573,
"grad_norm": 0.0311279296875,
"learning_rate": 9.791431342592811e-05,
"loss": 1.0532,
"step": 605
},
{
"epoch": 0.5604162928404809,
"grad_norm": 0.0311279296875,
"learning_rate": 9.631050910768773e-05,
"loss": 1.0807,
"step": 610
},
{
"epoch": 0.5650098690113045,
"grad_norm": 0.031005859375,
"learning_rate": 9.470765458798368e-05,
"loss": 1.0504,
"step": 615
},
{
"epoch": 0.5696034451821281,
"grad_norm": 0.032470703125,
"learning_rate": 9.310616249525759e-05,
"loss": 1.0507,
"step": 620
},
{
"epoch": 0.5741970213529517,
"grad_norm": 0.0308837890625,
"learning_rate": 9.15064451072165e-05,
"loss": 1.0434,
"step": 625
},
{
"epoch": 0.5787905975237754,
"grad_norm": 0.031005859375,
"learning_rate": 8.990891424469927e-05,
"loss": 1.0744,
"step": 630
},
{
"epoch": 0.5833841736945989,
"grad_norm": 0.03173828125,
"learning_rate": 8.831398116565964e-05,
"loss": 1.0792,
"step": 635
},
{
"epoch": 0.5879777498654226,
"grad_norm": 0.03173828125,
"learning_rate": 8.672205645929503e-05,
"loss": 1.0723,
"step": 640
},
{
"epoch": 0.5925713260362462,
"grad_norm": 0.031982421875,
"learning_rate": 8.513354994034681e-05,
"loss": 1.0627,
"step": 645
},
{
"epoch": 0.5971649022070697,
"grad_norm": 0.031982421875,
"learning_rate": 8.35488705436006e-05,
"loss": 1.0844,
"step": 650
},
{
"epoch": 0.6017584783778934,
"grad_norm": 0.031982421875,
"learning_rate": 8.196842621861242e-05,
"loss": 1.0566,
"step": 655
},
{
"epoch": 0.606352054548717,
"grad_norm": 0.03173828125,
"learning_rate": 8.039262382468905e-05,
"loss": 1.0697,
"step": 660
},
{
"epoch": 0.6109456307195407,
"grad_norm": 0.03271484375,
"learning_rate": 7.882186902614865e-05,
"loss": 1.0719,
"step": 665
},
{
"epoch": 0.6155392068903642,
"grad_norm": 0.032470703125,
"learning_rate": 7.725656618788937e-05,
"loss": 1.0519,
"step": 670
},
{
"epoch": 0.6201327830611879,
"grad_norm": 0.03271484375,
"learning_rate": 7.569711827129208e-05,
"loss": 1.0508,
"step": 675
},
{
"epoch": 0.6247263592320115,
"grad_norm": 0.031982421875,
"learning_rate": 7.414392673048478e-05,
"loss": 1.0631,
"step": 680
},
{
"epoch": 0.6293199354028352,
"grad_norm": 0.031494140625,
"learning_rate": 7.259739140899462e-05,
"loss": 1.0702,
"step": 685
},
{
"epoch": 0.6339135115736587,
"grad_norm": 0.031494140625,
"learning_rate": 7.105791043681519e-05,
"loss": 1.0642,
"step": 690
},
{
"epoch": 0.6385070877444823,
"grad_norm": 0.031494140625,
"learning_rate": 6.952588012791405e-05,
"loss": 1.0585,
"step": 695
},
{
"epoch": 0.643100663915306,
"grad_norm": 0.03125,
"learning_rate": 6.80016948782086e-05,
"loss": 1.0691,
"step": 700
},
{
"epoch": 0.6476942400861295,
"grad_norm": 0.031494140625,
"learning_rate": 6.648574706403522e-05,
"loss": 1.0614,
"step": 705
},
{
"epoch": 0.6522878162569532,
"grad_norm": 0.031982421875,
"learning_rate": 6.497842694113842e-05,
"loss": 1.0649,
"step": 710
},
{
"epoch": 0.6568813924277768,
"grad_norm": 0.03173828125,
"learning_rate": 6.348012254420606e-05,
"loss": 1.07,
"step": 715
},
{
"epoch": 0.6614749685986004,
"grad_norm": 0.0308837890625,
"learning_rate": 6.199121958697604e-05,
"loss": 1.0709,
"step": 720
},
{
"epoch": 0.666068544769424,
"grad_norm": 0.03466796875,
"learning_rate": 6.051210136294089e-05,
"loss": 1.063,
"step": 725
},
{
"epoch": 0.6706621209402476,
"grad_norm": 0.03173828125,
"learning_rate": 5.904314864667497e-05,
"loss": 1.0622,
"step": 730
},
{
"epoch": 0.6752556971110713,
"grad_norm": 0.031005859375,
"learning_rate": 5.758473959581061e-05,
"loss": 1.0558,
"step": 735
},
{
"epoch": 0.6798492732818948,
"grad_norm": 0.03125,
"learning_rate": 5.613724965368723e-05,
"loss": 1.0724,
"step": 740
},
{
"epoch": 0.6844428494527185,
"grad_norm": 0.031982421875,
"learning_rate": 5.4701051452700245e-05,
"loss": 1.0675,
"step": 745
},
{
"epoch": 0.6890364256235421,
"grad_norm": 0.0322265625,
"learning_rate": 5.327651471837242e-05,
"loss": 1.079,
"step": 750
},
{
"epoch": 0.6936300017943657,
"grad_norm": 0.03173828125,
"learning_rate": 5.1864006174174504e-05,
"loss": 1.0626,
"step": 755
},
{
"epoch": 0.6982235779651893,
"grad_norm": 0.033447265625,
"learning_rate": 5.046388944711824e-05,
"loss": 1.0637,
"step": 760
},
{
"epoch": 0.7028171541360129,
"grad_norm": 0.0322265625,
"learning_rate": 4.9076524974146507e-05,
"loss": 1.0565,
"step": 765
},
{
"epoch": 0.7074107303068365,
"grad_norm": 0.031494140625,
"learning_rate": 4.7702269909344907e-05,
"loss": 1.068,
"step": 770
},
{
"epoch": 0.7120043064776601,
"grad_norm": 0.031494140625,
"learning_rate": 4.6341478031998265e-05,
"loss": 1.0632,
"step": 775
},
{
"epoch": 0.7165978826484838,
"grad_norm": 0.0322265625,
"learning_rate": 4.4994499655515865e-05,
"loss": 1.0809,
"step": 780
},
{
"epoch": 0.7211914588193074,
"grad_norm": 0.03173828125,
"learning_rate": 4.3661681537249455e-05,
"loss": 1.0694,
"step": 785
},
{
"epoch": 0.725785034990131,
"grad_norm": 0.03271484375,
"learning_rate": 4.234336678922569e-05,
"loss": 1.06,
"step": 790
},
{
"epoch": 0.7303786111609546,
"grad_norm": 0.03173828125,
"learning_rate": 4.103989478981827e-05,
"loss": 1.0498,
"step": 795
},
{
"epoch": 0.7349721873317783,
"grad_norm": 0.0322265625,
"learning_rate": 3.975160109637992e-05,
"loss": 1.0527,
"step": 800
},
{
"epoch": 0.7395657635026018,
"grad_norm": 0.033447265625,
"learning_rate": 3.847881735885918e-05,
"loss": 1.0593,
"step": 805
},
{
"epoch": 0.7441593396734254,
"grad_norm": 0.031982421875,
"learning_rate": 3.722187123442249e-05,
"loss": 1.0568,
"step": 810
},
{
"epoch": 0.7487529158442491,
"grad_norm": 0.0322265625,
"learning_rate": 3.598108630310399e-05,
"loss": 1.0651,
"step": 815
},
{
"epoch": 0.7533464920150726,
"grad_norm": 0.031494140625,
"learning_rate": 3.475678198450555e-05,
"loss": 1.0451,
"step": 820
},
{
"epoch": 0.7579400681858963,
"grad_norm": 0.032470703125,
"learning_rate": 3.354927345556723e-05,
"loss": 1.0591,
"step": 825
},
{
"epoch": 0.7625336443567199,
"grad_norm": 0.03173828125,
"learning_rate": 3.235887156943029e-05,
"loss": 1.0519,
"step": 830
},
{
"epoch": 0.7671272205275436,
"grad_norm": 0.031982421875,
"learning_rate": 3.118588277541312e-05,
"loss": 1.0833,
"step": 835
},
{
"epoch": 0.7717207966983671,
"grad_norm": 0.03271484375,
"learning_rate": 3.003060904012096e-05,
"loss": 1.0543,
"step": 840
},
{
"epoch": 0.7763143728691907,
"grad_norm": 0.031982421875,
"learning_rate": 2.8893347769709476e-05,
"loss": 1.0755,
"step": 845
},
{
"epoch": 0.7809079490400144,
"grad_norm": 0.03271484375,
"learning_rate": 2.7774391733322713e-05,
"loss": 1.0682,
"step": 850
},
{
"epoch": 0.7855015252108379,
"grad_norm": 0.03173828125,
"learning_rate": 2.6674028987724163e-05,
"loss": 1.064,
"step": 855
},
{
"epoch": 0.7900951013816616,
"grad_norm": 0.031494140625,
"learning_rate": 2.559254280314156e-05,
"loss": 1.0648,
"step": 860
},
{
"epoch": 0.7946886775524852,
"grad_norm": 0.031982421875,
"learning_rate": 2.4530211590343578e-05,
"loss": 1.0699,
"step": 865
},
{
"epoch": 0.7992822537233089,
"grad_norm": 0.03173828125,
"learning_rate": 2.3487308828967493e-05,
"loss": 1.0647,
"step": 870
},
{
"epoch": 0.8038758298941324,
"grad_norm": 0.031982421875,
"learning_rate": 2.2464102997116475e-05,
"loss": 1.0636,
"step": 875
},
{
"epoch": 0.808469406064956,
"grad_norm": 0.03125,
"learning_rate": 2.1460857502244248e-05,
"loss": 1.0793,
"step": 880
},
{
"epoch": 0.8130629822357797,
"grad_norm": 0.03125,
"learning_rate": 2.047783061334523e-05,
"loss": 1.0501,
"step": 885
},
{
"epoch": 0.8176565584066032,
"grad_norm": 0.031494140625,
"learning_rate": 1.9515275394467446e-05,
"loss": 1.0553,
"step": 890
},
{
"epoch": 0.8222501345774269,
"grad_norm": 0.03173828125,
"learning_rate": 1.8573439639565282e-05,
"loss": 1.059,
"step": 895
},
{
"epoch": 0.8268437107482505,
"grad_norm": 0.031494140625,
"learning_rate": 1.765256580870924e-05,
"loss": 1.0653,
"step": 900
},
{
"epoch": 0.8314372869190741,
"grad_norm": 0.0322265625,
"learning_rate": 1.6752890965668266e-05,
"loss": 1.0616,
"step": 905
},
{
"epoch": 0.8360308630898977,
"grad_norm": 0.031982421875,
"learning_rate": 1.587464671688187e-05,
"loss": 1.0612,
"step": 910
},
{
"epoch": 0.8406244392607214,
"grad_norm": 0.031982421875,
"learning_rate": 1.501805915183685e-05,
"loss": 1.0723,
"step": 915
},
{
"epoch": 0.845218015431545,
"grad_norm": 0.031982421875,
"learning_rate": 1.4183348784864037e-05,
"loss": 1.0664,
"step": 920
},
{
"epoch": 0.8498115916023685,
"grad_norm": 0.03125,
"learning_rate": 1.3370730498370831e-05,
"loss": 1.0693,
"step": 925
},
{
"epoch": 0.8544051677731922,
"grad_norm": 0.03173828125,
"learning_rate": 1.258041348752308e-05,
"loss": 1.0715,
"step": 930
},
{
"epoch": 0.8589987439440158,
"grad_norm": 0.031982421875,
"learning_rate": 1.1812601206391304e-05,
"loss": 1.0755,
"step": 935
},
{
"epoch": 0.8635923201148394,
"grad_norm": 0.03125,
"learning_rate": 1.1067491315574797e-05,
"loss": 1.0522,
"step": 940
},
{
"epoch": 0.868185896285663,
"grad_norm": 0.03173828125,
"learning_rate": 1.0345275631317163e-05,
"loss": 1.0495,
"step": 945
},
{
"epoch": 0.8727794724564867,
"grad_norm": 0.03173828125,
"learning_rate": 9.64614007612633e-06,
"loss": 1.0637,
"step": 950
},
{
"epoch": 0.8773730486273102,
"grad_norm": 0.031494140625,
"learning_rate": 8.970264630912061e-06,
"loss": 1.064,
"step": 955
},
{
"epoch": 0.8819666247981338,
"grad_norm": 0.031494140625,
"learning_rate": 8.317823288652526e-06,
"loss": 1.0457,
"step": 960
},
{
"epoch": 0.8865602009689575,
"grad_norm": 0.03173828125,
"learning_rate": 7.688984009603062e-06,
"loss": 1.0633,
"step": 965
},
{
"epoch": 0.8911537771397811,
"grad_norm": 0.0322265625,
"learning_rate": 7.083908678057194e-06,
"loss": 1.0677,
"step": 970
},
{
"epoch": 0.8957473533106047,
"grad_norm": 0.03125,
"learning_rate": 6.502753060672495e-06,
"loss": 1.0482,
"step": 975
},
{
"epoch": 0.9003409294814283,
"grad_norm": 0.0322265625,
"learning_rate": 5.945666766370861e-06,
"loss": 1.0749,
"step": 980
},
{
"epoch": 0.904934505652252,
"grad_norm": 0.03173828125,
"learning_rate": 5.412793207824252e-06,
"loss": 1.0588,
"step": 985
},
{
"epoch": 0.9095280818230755,
"grad_norm": 0.031494140625,
"learning_rate": 4.904269564535391e-06,
"loss": 1.0575,
"step": 990
},
{
"epoch": 0.9141216579938991,
"grad_norm": 0.03173828125,
"learning_rate": 4.42022674752326e-06,
"loss": 1.0554,
"step": 995
},
{
"epoch": 0.9187152341647228,
"grad_norm": 0.03271484375,
"learning_rate": 3.960789365622075e-06,
"loss": 1.0504,
"step": 1000
},
{
"epoch": 0.9233088103355463,
"grad_norm": 0.031494140625,
"learning_rate": 3.526075693402986e-06,
"loss": 1.064,
"step": 1005
},
{
"epoch": 0.92790238650637,
"grad_norm": 0.031494140625,
"learning_rate": 3.116197640726104e-06,
"loss": 1.0566,
"step": 1010
},
{
"epoch": 0.9324959626771936,
"grad_norm": 0.03173828125,
"learning_rate": 2.7312607239311505e-06,
"loss": 1.0623,
"step": 1015
},
{
"epoch": 0.9370895388480173,
"grad_norm": 0.032958984375,
"learning_rate": 2.3713640386741396e-06,
"loss": 1.0708,
"step": 1020
},
{
"epoch": 0.9416831150188408,
"grad_norm": 0.032470703125,
"learning_rate": 2.0366002344166745e-06,
"loss": 1.0646,
"step": 1025
},
{
"epoch": 0.9462766911896644,
"grad_norm": 0.03173828125,
"learning_rate": 1.7270554905750137e-06,
"loss": 1.0753,
"step": 1030
},
{
"epoch": 0.9508702673604881,
"grad_norm": 0.031494140625,
"learning_rate": 1.4428094943345294e-06,
"loss": 1.0618,
"step": 1035
},
{
"epoch": 0.9554638435313116,
"grad_norm": 0.03173828125,
"learning_rate": 1.1839354201355513e-06,
"loss": 1.0533,
"step": 1040
},
{
"epoch": 0.9600574197021353,
"grad_norm": 0.03125,
"learning_rate": 9.50499910835867e-07,
"loss": 1.0471,
"step": 1045
},
{
"epoch": 0.9646509958729589,
"grad_norm": 0.03173828125,
"learning_rate": 7.425630605545575e-07,
"loss": 1.0564,
"step": 1050
},
{
"epoch": 0.9692445720437826,
"grad_norm": 0.0322265625,
"learning_rate": 5.60178399201805e-07,
"loss": 1.0793,
"step": 1055
},
{
"epoch": 0.9738381482146061,
"grad_norm": 0.03173828125,
"learning_rate": 4.0339287869847197e-07,
"loss": 1.0729,
"step": 1060
},
{
"epoch": 0.9784317243854298,
"grad_norm": 0.031982421875,
"learning_rate": 2.7224686088910265e-07,
"loss": 1.0542,
"step": 1065
},
{
"epoch": 0.9830253005562534,
"grad_norm": 0.03173828125,
"learning_rate": 1.6677410715149054e-07,
"loss": 1.0532,
"step": 1070
},
{
"epoch": 0.9876188767270769,
"grad_norm": 0.031982421875,
"learning_rate": 8.700176970527497e-08,
"loss": 1.0724,
"step": 1075
},
{
"epoch": 0.9922124528979006,
"grad_norm": 0.0322265625,
"learning_rate": 3.29503846221213e-08,
"loss": 1.0617,
"step": 1080
},
{
"epoch": 0.9968060290687242,
"grad_norm": 0.031494140625,
"learning_rate": 4.633866539005549e-09,
"loss": 1.0546,
"step": 1085
},
{
"epoch": 0.9995621747712183,
"eval_loss": 1.0676658153533936,
"eval_runtime": 1909.6941,
"eval_samples_per_second": 8.075,
"eval_steps_per_second": 8.075,
"step": 1088
},
{
"epoch": 0.9995621747712183,
"step": 1088,
"total_flos": 3.023110834516656e+18,
"train_loss": 0.22257287449696483,
"train_runtime": 15104.5697,
"train_samples_per_second": 9.224,
"train_steps_per_second": 0.072
}
],
"logging_steps": 5,
"max_steps": 1088,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 20,
"total_flos": 3.023110834516656e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}