{
  "best_metric": 0.1986456662416458,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.0170593879944557,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.52969399722785e-05,
      "grad_norm": 0.5174692273139954,
      "learning_rate": 7e-06,
      "loss": 0.4162,
      "step": 1
    },
    {
      "epoch": 8.52969399722785e-05,
      "eval_loss": 0.710103452205658,
      "eval_runtime": 1534.395,
      "eval_samples_per_second": 12.868,
      "eval_steps_per_second": 3.218,
      "step": 1
    },
    {
      "epoch": 0.000170593879944557,
      "grad_norm": 0.6568453311920166,
      "learning_rate": 1.4e-05,
      "loss": 0.5157,
      "step": 2
    },
    {
      "epoch": 0.0002558908199168355,
      "grad_norm": 0.6513026356697083,
      "learning_rate": 2.1e-05,
      "loss": 0.5028,
      "step": 3
    },
    {
      "epoch": 0.000341187759889114,
      "grad_norm": 0.7913713455200195,
      "learning_rate": 2.8e-05,
      "loss": 0.5238,
      "step": 4
    },
    {
      "epoch": 0.00042648469986139245,
      "grad_norm": 0.6908019185066223,
      "learning_rate": 3.5e-05,
      "loss": 0.5048,
      "step": 5
    },
    {
      "epoch": 0.000511781639833671,
      "grad_norm": 0.6483615040779114,
      "learning_rate": 4.2e-05,
      "loss": 0.4301,
      "step": 6
    },
    {
      "epoch": 0.0005970785798059495,
      "grad_norm": 0.5787661075592041,
      "learning_rate": 4.899999999999999e-05,
      "loss": 0.4285,
      "step": 7
    },
    {
      "epoch": 0.000682375519778228,
      "grad_norm": 0.5178965330123901,
      "learning_rate": 5.6e-05,
      "loss": 0.3377,
      "step": 8
    },
    {
      "epoch": 0.0007676724597505065,
      "grad_norm": 0.455504447221756,
      "learning_rate": 6.3e-05,
      "loss": 0.2739,
      "step": 9
    },
    {
      "epoch": 0.0008529693997227849,
      "grad_norm": 0.40463095903396606,
      "learning_rate": 7e-05,
      "loss": 0.282,
      "step": 10
    },
    {
      "epoch": 0.0009382663396950634,
      "grad_norm": 0.5918212532997131,
      "learning_rate": 6.999521567473641e-05,
      "loss": 0.3131,
      "step": 11
    },
    {
      "epoch": 0.001023563279667342,
      "grad_norm": 0.5272678136825562,
      "learning_rate": 6.998086400693241e-05,
      "loss": 0.2757,
      "step": 12
    },
    {
      "epoch": 0.0011088602196396204,
      "grad_norm": 0.42902687191963196,
      "learning_rate": 6.995694892019065e-05,
      "loss": 0.2488,
      "step": 13
    },
    {
      "epoch": 0.001194157159611899,
      "grad_norm": 0.38537320494651794,
      "learning_rate": 6.99234769526571e-05,
      "loss": 0.2657,
      "step": 14
    },
    {
      "epoch": 0.0012794540995841775,
      "grad_norm": 0.3521060645580292,
      "learning_rate": 6.988045725523343e-05,
      "loss": 0.2967,
      "step": 15
    },
    {
      "epoch": 0.001364751039556456,
      "grad_norm": 0.3419083058834076,
      "learning_rate": 6.982790158907539e-05,
      "loss": 0.2869,
      "step": 16
    },
    {
      "epoch": 0.0014500479795287345,
      "grad_norm": 0.34917929768562317,
      "learning_rate": 6.976582432237733e-05,
      "loss": 0.2659,
      "step": 17
    },
    {
      "epoch": 0.001535344919501013,
      "grad_norm": 0.3363621234893799,
      "learning_rate": 6.969424242644413e-05,
      "loss": 0.247,
      "step": 18
    },
    {
      "epoch": 0.0016206418594732915,
      "grad_norm": 0.3077584207057953,
      "learning_rate": 6.961317547105138e-05,
      "loss": 0.2371,
      "step": 19
    },
    {
      "epoch": 0.0017059387994455698,
      "grad_norm": 0.31226736307144165,
      "learning_rate": 6.952264561909527e-05,
      "loss": 0.2337,
      "step": 20
    },
    {
      "epoch": 0.0017912357394178483,
      "grad_norm": 0.3040497899055481,
      "learning_rate": 6.942267762053337e-05,
      "loss": 0.2523,
      "step": 21
    },
    {
      "epoch": 0.0018765326793901268,
      "grad_norm": 0.30742520093917847,
      "learning_rate": 6.931329880561832e-05,
      "loss": 0.2285,
      "step": 22
    },
    {
      "epoch": 0.0019618296193624056,
      "grad_norm": 0.2825202941894531,
      "learning_rate": 6.919453907742597e-05,
      "loss": 0.2264,
      "step": 23
    },
    {
      "epoch": 0.002047126559334684,
      "grad_norm": 0.345242977142334,
      "learning_rate": 6.90664309036802e-05,
      "loss": 0.24,
      "step": 24
    },
    {
      "epoch": 0.0021324234993069626,
      "grad_norm": 0.4534529149532318,
      "learning_rate": 6.892900930787656e-05,
      "loss": 0.2635,
      "step": 25
    },
    {
      "epoch": 0.002217720439279241,
      "grad_norm": 0.334157258272171,
      "learning_rate": 6.87823118597072e-05,
      "loss": 0.2447,
      "step": 26
    },
    {
      "epoch": 0.002303017379251519,
      "grad_norm": 0.33431321382522583,
      "learning_rate": 6.862637866478969e-05,
      "loss": 0.2619,
      "step": 27
    },
    {
      "epoch": 0.002388314319223798,
      "grad_norm": 0.3746112883090973,
      "learning_rate": 6.846125235370252e-05,
      "loss": 0.2231,
      "step": 28
    },
    {
      "epoch": 0.002473611259196076,
      "grad_norm": 0.37363436818122864,
      "learning_rate": 6.828697807033038e-05,
      "loss": 0.2586,
      "step": 29
    },
    {
      "epoch": 0.002558908199168355,
      "grad_norm": 0.34933286905288696,
      "learning_rate": 6.81036034595222e-05,
      "loss": 0.2214,
      "step": 30
    },
    {
      "epoch": 0.002644205139140633,
      "grad_norm": 0.37522244453430176,
      "learning_rate": 6.791117865406564e-05,
      "loss": 0.212,
      "step": 31
    },
    {
      "epoch": 0.002729502079112912,
      "grad_norm": 0.37254416942596436,
      "learning_rate": 6.770975626098112e-05,
      "loss": 0.2475,
      "step": 32
    },
    {
      "epoch": 0.0028147990190851902,
      "grad_norm": 0.3565993010997772,
      "learning_rate": 6.749939134713974e-05,
      "loss": 0.2455,
      "step": 33
    },
    {
      "epoch": 0.002900095959057469,
      "grad_norm": 0.3483193814754486,
      "learning_rate": 6.728014142420846e-05,
      "loss": 0.2144,
      "step": 34
    },
    {
      "epoch": 0.0029853928990297473,
      "grad_norm": 0.38728171586990356,
      "learning_rate": 6.7052066432927e-05,
      "loss": 0.2233,
      "step": 35
    },
    {
      "epoch": 0.003070689839002026,
      "grad_norm": 0.408767431974411,
      "learning_rate": 6.681522872672069e-05,
      "loss": 0.2704,
      "step": 36
    },
    {
      "epoch": 0.0031559867789743043,
      "grad_norm": 0.3622119128704071,
      "learning_rate": 6.656969305465356e-05,
      "loss": 0.2226,
      "step": 37
    },
    {
      "epoch": 0.003241283718946583,
      "grad_norm": 0.3725903034210205,
      "learning_rate": 6.631552654372672e-05,
      "loss": 0.2206,
      "step": 38
    },
    {
      "epoch": 0.0033265806589188613,
      "grad_norm": 0.4931883215904236,
      "learning_rate": 6.60527986805264e-05,
      "loss": 0.2307,
      "step": 39
    },
    {
      "epoch": 0.0034118775988911396,
      "grad_norm": 0.44529104232788086,
      "learning_rate": 6.578158129222711e-05,
      "loss": 0.2383,
      "step": 40
    },
    {
      "epoch": 0.0034971745388634183,
      "grad_norm": 0.4084993302822113,
      "learning_rate": 6.550194852695469e-05,
      "loss": 0.235,
      "step": 41
    },
    {
      "epoch": 0.0035824714788356966,
      "grad_norm": 0.38800936937332153,
      "learning_rate": 6.521397683351509e-05,
      "loss": 0.2028,
      "step": 42
    },
    {
      "epoch": 0.0036677684188079753,
      "grad_norm": 0.4139971435070038,
      "learning_rate": 6.491774494049386e-05,
      "loss": 0.2358,
      "step": 43
    },
    {
      "epoch": 0.0037530653587802536,
      "grad_norm": 0.3838896155357361,
      "learning_rate": 6.461333383473272e-05,
      "loss": 0.2247,
      "step": 44
    },
    {
      "epoch": 0.0038383622987525324,
      "grad_norm": 0.4303966462612152,
      "learning_rate": 6.430082673918849e-05,
      "loss": 0.2599,
      "step": 45
    },
    {
      "epoch": 0.003923659238724811,
      "grad_norm": 0.35368064045906067,
      "learning_rate": 6.398030909018069e-05,
      "loss": 0.1827,
      "step": 46
    },
    {
      "epoch": 0.004008956178697089,
      "grad_norm": 0.4158652722835541,
      "learning_rate": 6.365186851403423e-05,
      "loss": 0.2126,
      "step": 47
    },
    {
      "epoch": 0.004094253118669368,
      "grad_norm": 0.4407242238521576,
      "learning_rate": 6.331559480312315e-05,
      "loss": 0.2477,
      "step": 48
    },
    {
      "epoch": 0.004179550058641646,
      "grad_norm": 0.5331549048423767,
      "learning_rate": 6.297157989132236e-05,
      "loss": 0.2642,
      "step": 49
    },
    {
      "epoch": 0.004264846998613925,
      "grad_norm": 0.560575544834137,
      "learning_rate": 6.261991782887377e-05,
      "loss": 0.2882,
      "step": 50
    },
    {
      "epoch": 0.004264846998613925,
      "eval_loss": 0.23865659534931183,
      "eval_runtime": 1541.2194,
      "eval_samples_per_second": 12.811,
      "eval_steps_per_second": 3.203,
      "step": 50
    },
    {
      "epoch": 0.0043501439385862034,
      "grad_norm": 0.33888059854507446,
      "learning_rate": 6.226070475667393e-05,
      "loss": 0.2974,
      "step": 51
    },
    {
      "epoch": 0.004435440878558482,
      "grad_norm": 0.34790778160095215,
      "learning_rate": 6.189403887999006e-05,
      "loss": 0.2458,
      "step": 52
    },
    {
      "epoch": 0.00452073781853076,
      "grad_norm": 0.3222178816795349,
      "learning_rate": 6.152002044161171e-05,
      "loss": 0.2258,
      "step": 53
    },
    {
      "epoch": 0.004606034758503038,
      "grad_norm": 0.2968549132347107,
      "learning_rate": 6.113875169444539e-05,
      "loss": 0.1849,
      "step": 54
    },
    {
      "epoch": 0.0046913316984753175,
      "grad_norm": 0.24279001355171204,
      "learning_rate": 6.0750336873559605e-05,
      "loss": 0.1772,
      "step": 55
    },
    {
      "epoch": 0.004776628638447596,
      "grad_norm": 0.22238604724407196,
      "learning_rate": 6.035488216768811e-05,
      "loss": 0.1755,
      "step": 56
    },
    {
      "epoch": 0.004861925578419874,
      "grad_norm": 0.2165011465549469,
      "learning_rate": 5.9952495690198894e-05,
      "loss": 0.1886,
      "step": 57
    },
    {
      "epoch": 0.004947222518392152,
      "grad_norm": 0.2520563304424286,
      "learning_rate": 5.954328744953709e-05,
      "loss": 0.1931,
      "step": 58
    },
    {
      "epoch": 0.0050325194583644315,
      "grad_norm": 0.2695819139480591,
      "learning_rate": 5.91273693191498e-05,
      "loss": 0.2196,
      "step": 59
    },
    {
      "epoch": 0.00511781639833671,
      "grad_norm": 0.2671445310115814,
      "learning_rate": 5.870485500690094e-05,
      "loss": 0.1952,
      "step": 60
    },
    {
      "epoch": 0.005203113338308988,
      "grad_norm": 0.2837413549423218,
      "learning_rate": 5.827586002398468e-05,
      "loss": 0.2103,
      "step": 61
    },
    {
      "epoch": 0.005288410278281266,
      "grad_norm": 0.24383383989334106,
      "learning_rate": 5.784050165334589e-05,
      "loss": 0.2176,
      "step": 62
    },
    {
      "epoch": 0.005373707218253546,
      "grad_norm": 0.24169886112213135,
      "learning_rate": 5.739889891761608e-05,
      "loss": 0.1862,
      "step": 63
    },
    {
      "epoch": 0.005459004158225824,
      "grad_norm": 0.23239196836948395,
      "learning_rate": 5.6951172546573794e-05,
      "loss": 0.1808,
      "step": 64
    },
    {
      "epoch": 0.005544301098198102,
      "grad_norm": 0.25222256779670715,
      "learning_rate": 5.6497444944138376e-05,
      "loss": 0.1963,
      "step": 65
    },
    {
      "epoch": 0.0056295980381703805,
      "grad_norm": 0.24847331643104553,
      "learning_rate": 5.603784015490587e-05,
      "loss": 0.2005,
      "step": 66
    },
    {
      "epoch": 0.005714894978142659,
      "grad_norm": 0.2550618052482605,
      "learning_rate": 5.557248383023655e-05,
      "loss": 0.2092,
      "step": 67
    },
    {
      "epoch": 0.005800191918114938,
      "grad_norm": 0.28103408217430115,
      "learning_rate": 5.510150319390302e-05,
      "loss": 0.2264,
      "step": 68
    },
    {
      "epoch": 0.005885488858087216,
      "grad_norm": 0.24416524171829224,
      "learning_rate": 5.4625027007308546e-05,
      "loss": 0.2022,
      "step": 69
    },
    {
      "epoch": 0.0059707857980594945,
      "grad_norm": 0.2345932126045227,
      "learning_rate": 5.414318553428494e-05,
      "loss": 0.1686,
      "step": 70
    },
    {
      "epoch": 0.006056082738031773,
      "grad_norm": 0.3526822328567505,
      "learning_rate": 5.3656110505479776e-05,
      "loss": 0.2058,
      "step": 71
    },
    {
      "epoch": 0.006141379678004052,
      "grad_norm": 0.25678718090057373,
      "learning_rate": 5.316393508234253e-05,
      "loss": 0.2026,
      "step": 72
    },
    {
      "epoch": 0.00622667661797633,
      "grad_norm": 0.281432181596756,
      "learning_rate": 5.266679382071953e-05,
      "loss": 0.2062,
      "step": 73
    },
    {
      "epoch": 0.0063119735579486086,
      "grad_norm": 0.24451790750026703,
      "learning_rate": 5.216482263406778e-05,
      "loss": 0.185,
      "step": 74
    },
    {
      "epoch": 0.006397270497920887,
      "grad_norm": 0.27670735120773315,
      "learning_rate": 5.1658158756297576e-05,
      "loss": 0.2115,
      "step": 75
    },
    {
      "epoch": 0.006482567437893166,
      "grad_norm": 0.27316904067993164,
      "learning_rate": 5.114694070425407e-05,
      "loss": 0.1944,
      "step": 76
    },
    {
      "epoch": 0.006567864377865444,
      "grad_norm": 0.2967571020126343,
      "learning_rate": 5.063130823984823e-05,
      "loss": 0.2172,
      "step": 77
    },
    {
      "epoch": 0.006653161317837723,
      "grad_norm": 0.2783087193965912,
      "learning_rate": 5.011140233184724e-05,
      "loss": 0.2118,
      "step": 78
    },
    {
      "epoch": 0.006738458257810001,
      "grad_norm": 0.2984948754310608,
      "learning_rate": 4.958736511733516e-05,
      "loss": 0.2273,
      "step": 79
    },
    {
      "epoch": 0.006823755197782279,
      "grad_norm": 0.2862406373023987,
      "learning_rate": 4.905933986285393e-05,
      "loss": 0.2165,
      "step": 80
    },
    {
      "epoch": 0.006909052137754558,
      "grad_norm": 0.2812900245189667,
      "learning_rate": 4.8527470925235824e-05,
      "loss": 0.1909,
      "step": 81
    },
    {
      "epoch": 0.006994349077726837,
      "grad_norm": 0.2917400598526001,
      "learning_rate": 4.799190371213772e-05,
      "loss": 0.2062,
      "step": 82
    },
    {
      "epoch": 0.007079646017699115,
      "grad_norm": 0.33554038405418396,
      "learning_rate": 4.745278464228808e-05,
      "loss": 0.2179,
      "step": 83
    },
    {
      "epoch": 0.007164942957671393,
      "grad_norm": 0.2989683747291565,
      "learning_rate": 4.69102611054575e-05,
      "loss": 0.1884,
      "step": 84
    },
    {
      "epoch": 0.007250239897643672,
      "grad_norm": 0.3299173414707184,
      "learning_rate": 4.6364481422163926e-05,
      "loss": 0.2275,
      "step": 85
    },
    {
      "epoch": 0.007335536837615951,
      "grad_norm": 0.34388697147369385,
      "learning_rate": 4.581559480312316e-05,
      "loss": 0.2307,
      "step": 86
    },
    {
      "epoch": 0.007420833777588229,
      "grad_norm": 0.3142262101173401,
      "learning_rate": 4.526375130845627e-05,
      "loss": 0.2082,
      "step": 87
    },
    {
      "epoch": 0.007506130717560507,
      "grad_norm": 0.35896992683410645,
      "learning_rate": 4.4709101806664554e-05,
      "loss": 0.1963,
      "step": 88
    },
    {
      "epoch": 0.007591427657532786,
      "grad_norm": 0.3397196829319,
      "learning_rate": 4.4151797933383685e-05,
      "loss": 0.2238,
      "step": 89
    },
    {
      "epoch": 0.007676724597505065,
      "grad_norm": 0.32939013838768005,
      "learning_rate": 4.359199204992797e-05,
      "loss": 0.2067,
      "step": 90
    },
    {
      "epoch": 0.007762021537477343,
      "grad_norm": 0.32344064116477966,
      "learning_rate": 4.30298372016363e-05,
      "loss": 0.2042,
      "step": 91
    },
    {
      "epoch": 0.007847318477449622,
      "grad_norm": 0.3592457175254822,
      "learning_rate": 4.246548707603114e-05,
      "loss": 0.2127,
      "step": 92
    },
    {
      "epoch": 0.0079326154174219,
      "grad_norm": 0.37003716826438904,
      "learning_rate": 4.1899095960801805e-05,
      "loss": 0.2292,
      "step": 93
    },
    {
      "epoch": 0.008017912357394179,
      "grad_norm": 0.3626440465450287,
      "learning_rate": 4.133081870162385e-05,
      "loss": 0.2211,
      "step": 94
    },
    {
      "epoch": 0.008103209297366456,
      "grad_norm": 0.36774942278862,
      "learning_rate": 4.076081065982569e-05,
      "loss": 0.2323,
      "step": 95
    },
    {
      "epoch": 0.008188506237338735,
      "grad_norm": 0.4029773473739624,
      "learning_rate": 4.018922766991447e-05,
      "loss": 0.2268,
      "step": 96
    },
    {
      "epoch": 0.008273803177311015,
      "grad_norm": 0.38385075330734253,
      "learning_rate": 3.961622599697241e-05,
      "loss": 0.2087,
      "step": 97
    },
    {
      "epoch": 0.008359100117283292,
      "grad_norm": 0.401379257440567,
      "learning_rate": 3.9041962293935516e-05,
      "loss": 0.2294,
      "step": 98
    },
    {
      "epoch": 0.008444397057255571,
      "grad_norm": 0.4526772201061249,
      "learning_rate": 3.84665935587662e-05,
      "loss": 0.2367,
      "step": 99
    },
    {
      "epoch": 0.00852969399722785,
      "grad_norm": 0.5280042290687561,
      "learning_rate": 3.7890277091531636e-05,
      "loss": 0.2509,
      "step": 100
    },
    {
      "epoch": 0.00852969399722785,
      "eval_loss": 0.21555276215076447,
      "eval_runtime": 1540.6118,
      "eval_samples_per_second": 12.816,
      "eval_steps_per_second": 3.205,
      "step": 100
    },
    {
      "epoch": 0.008614990937200128,
      "grad_norm": 0.22140806913375854,
      "learning_rate": 3.7313170451399475e-05,
      "loss": 0.2659,
      "step": 101
    },
    {
      "epoch": 0.008700287877172407,
      "grad_norm": 0.22919246554374695,
      "learning_rate": 3.673543141356278e-05,
      "loss": 0.2334,
      "step": 102
    },
    {
      "epoch": 0.008785584817144684,
      "grad_norm": 0.25748583674430847,
      "learning_rate": 3.6157217926105783e-05,
      "loss": 0.2202,
      "step": 103
    },
    {
      "epoch": 0.008870881757116963,
      "grad_norm": 0.24456602334976196,
      "learning_rate": 3.557868806682255e-05,
      "loss": 0.1962,
      "step": 104
    },
    {
      "epoch": 0.008956178697089243,
      "grad_norm": 0.23318764567375183,
      "learning_rate": 3.5e-05,
      "loss": 0.214,
      "step": 105
    },
    {
      "epoch": 0.00904147563706152,
      "grad_norm": 0.2334156632423401,
      "learning_rate": 3.442131193317745e-05,
      "loss": 0.2272,
      "step": 106
    },
    {
      "epoch": 0.0091267725770338,
      "grad_norm": 0.24065986275672913,
      "learning_rate": 3.384278207389421e-05,
      "loss": 0.1977,
      "step": 107
    },
    {
      "epoch": 0.009212069517006077,
      "grad_norm": 0.22004655003547668,
      "learning_rate": 3.3264568586437216e-05,
      "loss": 0.1991,
      "step": 108
    },
    {
      "epoch": 0.009297366456978356,
      "grad_norm": 0.2243257761001587,
      "learning_rate": 3.268682954860052e-05,
      "loss": 0.195,
      "step": 109
    },
    {
      "epoch": 0.009382663396950635,
      "grad_norm": 0.21268798410892487,
      "learning_rate": 3.210972290846837e-05,
      "loss": 0.195,
      "step": 110
    },
    {
      "epoch": 0.009467960336922912,
      "grad_norm": 0.23587660491466522,
      "learning_rate": 3.15334064412338e-05,
      "loss": 0.1994,
      "step": 111
    },
    {
      "epoch": 0.009553257276895192,
      "grad_norm": 0.2422051876783371,
      "learning_rate": 3.0958037706064485e-05,
      "loss": 0.1827,
      "step": 112
    },
    {
      "epoch": 0.00963855421686747,
      "grad_norm": 0.21840524673461914,
      "learning_rate": 3.038377400302758e-05,
      "loss": 0.1977,
      "step": 113
    },
    {
      "epoch": 0.009723851156839748,
      "grad_norm": 0.254047691822052,
      "learning_rate": 2.9810772330085524e-05,
      "loss": 0.1778,
      "step": 114
    },
    {
      "epoch": 0.009809148096812027,
      "grad_norm": 0.22765785455703735,
      "learning_rate": 2.9239189340174306e-05,
      "loss": 0.1646,
      "step": 115
    },
    {
      "epoch": 0.009894445036784305,
      "grad_norm": 0.2421681433916092,
      "learning_rate": 2.8669181298376163e-05,
      "loss": 0.2025,
      "step": 116
    },
    {
      "epoch": 0.009979741976756584,
      "grad_norm": 0.24907107651233673,
      "learning_rate": 2.8100904039198193e-05,
      "loss": 0.1941,
      "step": 117
    },
    {
      "epoch": 0.010065038916728863,
      "grad_norm": 0.23539845645427704,
      "learning_rate": 2.7534512923968863e-05,
      "loss": 0.1877,
      "step": 118
    },
    {
      "epoch": 0.01015033585670114,
      "grad_norm": 0.25767600536346436,
      "learning_rate": 2.6970162798363695e-05,
      "loss": 0.1983,
      "step": 119
    },
    {
      "epoch": 0.01023563279667342,
      "grad_norm": 0.2530064284801483,
      "learning_rate": 2.640800795007203e-05,
      "loss": 0.2016,
      "step": 120
    },
    {
      "epoch": 0.010320929736645697,
      "grad_norm": 0.265044629573822,
      "learning_rate": 2.5848202066616305e-05,
      "loss": 0.2135,
      "step": 121
    },
    {
      "epoch": 0.010406226676617976,
      "grad_norm": 0.25507453083992004,
      "learning_rate": 2.5290898193335446e-05,
      "loss": 0.2192,
      "step": 122
    },
    {
      "epoch": 0.010491523616590255,
      "grad_norm": 0.29793521761894226,
      "learning_rate": 2.4736248691543736e-05,
      "loss": 0.2357,
      "step": 123
    },
    {
      "epoch": 0.010576820556562533,
      "grad_norm": 0.2676340937614441,
      "learning_rate": 2.4184405196876842e-05,
      "loss": 0.2124,
      "step": 124
    },
    {
      "epoch": 0.010662117496534812,
      "grad_norm": 0.2631836235523224,
      "learning_rate": 2.363551857783608e-05,
      "loss": 0.2224,
      "step": 125
    },
    {
      "epoch": 0.010747414436507091,
      "grad_norm": 0.2812511920928955,
      "learning_rate": 2.308973889454249e-05,
      "loss": 0.2223,
      "step": 126
    },
    {
      "epoch": 0.010832711376479369,
      "grad_norm": 0.3007054328918457,
      "learning_rate": 2.2547215357711918e-05,
      "loss": 0.2035,
      "step": 127
    },
    {
      "epoch": 0.010918008316451648,
      "grad_norm": 0.24782508611679077,
      "learning_rate": 2.2008096287862266e-05,
      "loss": 0.182,
      "step": 128
    },
    {
      "epoch": 0.011003305256423925,
      "grad_norm": 0.2732129991054535,
      "learning_rate": 2.1472529074764177e-05,
      "loss": 0.1939,
      "step": 129
    },
    {
      "epoch": 0.011088602196396204,
      "grad_norm": 0.2680470645427704,
      "learning_rate": 2.0940660137146074e-05,
      "loss": 0.1916,
      "step": 130
    },
    {
      "epoch": 0.011173899136368484,
      "grad_norm": 0.2935539484024048,
      "learning_rate": 2.041263488266484e-05,
      "loss": 0.2008,
      "step": 131
    },
    {
      "epoch": 0.011259196076340761,
      "grad_norm": 0.288349986076355,
      "learning_rate": 1.988859766815275e-05,
      "loss": 0.1879,
      "step": 132
    },
    {
      "epoch": 0.01134449301631304,
      "grad_norm": 0.2973138391971588,
      "learning_rate": 1.9368691760151773e-05,
      "loss": 0.1942,
      "step": 133
    },
    {
      "epoch": 0.011429789956285318,
      "grad_norm": 0.2820628881454468,
      "learning_rate": 1.885305929574593e-05,
      "loss": 0.2074,
      "step": 134
    },
    {
      "epoch": 0.011515086896257597,
      "grad_norm": 0.37588265538215637,
      "learning_rate": 1.8341841243702424e-05,
      "loss": 0.2227,
      "step": 135
    },
    {
      "epoch": 0.011600383836229876,
      "grad_norm": 0.342728853225708,
      "learning_rate": 1.7835177365932225e-05,
      "loss": 0.2429,
      "step": 136
    },
    {
      "epoch": 0.011685680776202153,
      "grad_norm": 0.2969904839992523,
      "learning_rate": 1.7333206179280478e-05,
      "loss": 0.2049,
      "step": 137
    },
    {
      "epoch": 0.011770977716174432,
      "grad_norm": 0.33506619930267334,
      "learning_rate": 1.6836064917657478e-05,
      "loss": 0.2123,
      "step": 138
    },
    {
      "epoch": 0.011856274656146712,
      "grad_norm": 0.3339824676513672,
      "learning_rate": 1.6343889494520224e-05,
      "loss": 0.2506,
      "step": 139
    },
    {
      "epoch": 0.011941571596118989,
      "grad_norm": 0.31456679105758667,
      "learning_rate": 1.5856814465715064e-05,
      "loss": 0.2129,
      "step": 140
    },
    {
      "epoch": 0.012026868536091268,
      "grad_norm": 0.314937561750412,
      "learning_rate": 1.5374972992691458e-05,
      "loss": 0.1843,
      "step": 141
    },
    {
      "epoch": 0.012112165476063546,
      "grad_norm": 0.33343854546546936,
      "learning_rate": 1.4898496806096974e-05,
      "loss": 0.2068,
      "step": 142
    },
    {
      "epoch": 0.012197462416035825,
      "grad_norm": 0.3435650169849396,
      "learning_rate": 1.4427516169763444e-05,
      "loss": 0.2059,
      "step": 143
    },
    {
      "epoch": 0.012282759356008104,
      "grad_norm": 0.3483867049217224,
      "learning_rate": 1.396215984509412e-05,
      "loss": 0.2137,
      "step": 144
    },
    {
      "epoch": 0.012368056295980381,
      "grad_norm": 0.3761361837387085,
      "learning_rate": 1.3502555055861625e-05,
      "loss": 0.241,
      "step": 145
    },
    {
      "epoch": 0.01245335323595266,
      "grad_norm": 0.34961044788360596,
      "learning_rate": 1.3048827453426203e-05,
      "loss": 0.1923,
      "step": 146
    },
    {
      "epoch": 0.012538650175924938,
      "grad_norm": 0.3708224594593048,
      "learning_rate": 1.2601101082383917e-05,
      "loss": 0.2059,
      "step": 147
    },
    {
      "epoch": 0.012623947115897217,
      "grad_norm": 0.4034970700740814,
      "learning_rate": 1.2159498346654094e-05,
      "loss": 0.2139,
      "step": 148
    },
    {
      "epoch": 0.012709244055869496,
      "grad_norm": 0.4172138571739197,
      "learning_rate": 1.1724139976015306e-05,
      "loss": 0.2386,
      "step": 149
    },
    {
      "epoch": 0.012794540995841774,
      "grad_norm": 0.5822272896766663,
      "learning_rate": 1.1295144993099068e-05,
      "loss": 0.2607,
      "step": 150
    },
    {
      "epoch": 0.012794540995841774,
      "eval_loss": 0.20139965415000916,
      "eval_runtime": 1542.9021,
      "eval_samples_per_second": 12.797,
      "eval_steps_per_second": 3.2,
      "step": 150
    },
    {
      "epoch": 0.012879837935814053,
      "grad_norm": 0.19455158710479736,
      "learning_rate": 1.0872630680850196e-05,
      "loss": 0.2643,
      "step": 151
    },
    {
      "epoch": 0.012965134875786332,
      "grad_norm": 0.21238583326339722,
      "learning_rate": 1.0456712550462898e-05,
      "loss": 0.224,
      "step": 152
    },
    {
      "epoch": 0.01305043181575861,
      "grad_norm": 0.21164029836654663,
      "learning_rate": 1.0047504309801104e-05,
      "loss": 0.1908,
      "step": 153
    },
    {
      "epoch": 0.013135728755730889,
      "grad_norm": 0.20678101480007172,
      "learning_rate": 9.645117832311886e-06,
      "loss": 0.1827,
      "step": 154
    },
    {
      "epoch": 0.013221025695703166,
      "grad_norm": 0.20742088556289673,
      "learning_rate": 9.249663126440394e-06,
      "loss": 0.1675,
      "step": 155
    },
    {
      "epoch": 0.013306322635675445,
      "grad_norm": 0.1990153044462204,
      "learning_rate": 8.861248305554624e-06,
      "loss": 0.1552,
      "step": 156
    },
    {
      "epoch": 0.013391619575647724,
      "grad_norm": 0.2046077400445938,
      "learning_rate": 8.47997955838829e-06,
      "loss": 0.1596,
      "step": 157
    },
    {
      "epoch": 0.013476916515620002,
      "grad_norm": 0.22314919531345367,
      "learning_rate": 8.10596112000994e-06,
      "loss": 0.1903,
      "step": 158
    },
    {
      "epoch": 0.013562213455592281,
      "grad_norm": 0.23533815145492554,
      "learning_rate": 7.739295243326067e-06,
      "loss": 0.1707,
      "step": 159
    },
    {
      "epoch": 0.013647510395564558,
      "grad_norm": 0.23708821833133698,
      "learning_rate": 7.380082171126228e-06,
      "loss": 0.2003,
      "step": 160
    },
    {
      "epoch": 0.013732807335536838,
      "grad_norm": 0.24074110388755798,
      "learning_rate": 7.028420108677635e-06,
      "loss": 0.2098,
      "step": 161
    },
    {
      "epoch": 0.013818104275509117,
      "grad_norm": 0.2700691521167755,
      "learning_rate": 6.684405196876842e-06,
      "loss": 0.1846,
      "step": 162
    },
    {
      "epoch": 0.013903401215481394,
      "grad_norm": 0.24084365367889404,
      "learning_rate": 6.3481314859657675e-06,
      "loss": 0.1893,
      "step": 163
    },
    {
      "epoch": 0.013988698155453673,
      "grad_norm": 0.21697106957435608,
      "learning_rate": 6.019690909819298e-06,
      "loss": 0.1614,
      "step": 164
    },
    {
      "epoch": 0.01407399509542595,
      "grad_norm": 0.2759890556335449,
      "learning_rate": 5.6991732608115e-06,
      "loss": 0.2348,
      "step": 165
    },
    {
      "epoch": 0.01415929203539823,
      "grad_norm": 0.24391219019889832,
      "learning_rate": 5.386666165267256e-06,
      "loss": 0.1728,
      "step": 166
    },
    {
      "epoch": 0.014244588975370509,
      "grad_norm": 0.27125006914138794,
      "learning_rate": 5.08225505950613e-06,
      "loss": 0.1815,
      "step": 167
    },
    {
      "epoch": 0.014329885915342786,
      "grad_norm": 0.23501136898994446,
      "learning_rate": 4.786023166484913e-06,
      "loss": 0.1871,
      "step": 168
    },
    {
      "epoch": 0.014415182855315066,
      "grad_norm": 0.2554644048213959,
      "learning_rate": 4.498051473045291e-06,
      "loss": 0.1787,
      "step": 169
    },
    {
      "epoch": 0.014500479795287345,
      "grad_norm": 0.28374356031417847,
      "learning_rate": 4.218418707772886e-06,
      "loss": 0.2205,
      "step": 170
    },
    {
      "epoch": 0.014585776735259622,
      "grad_norm": 0.24838587641716003,
      "learning_rate": 3.947201319473587e-06,
      "loss": 0.1756,
      "step": 171
    },
    {
      "epoch": 0.014671073675231901,
      "grad_norm": 0.286033034324646,
      "learning_rate": 3.684473456273278e-06,
      "loss": 0.2002,
      "step": 172
    },
    {
      "epoch": 0.014756370615204179,
      "grad_norm": 0.27238067984580994,
      "learning_rate": 3.4303069453464383e-06,
      "loss": 0.1992,
      "step": 173
    },
    {
      "epoch": 0.014841667555176458,
      "grad_norm": 0.27960264682769775,
      "learning_rate": 3.184771273279312e-06,
      "loss": 0.2169,
      "step": 174
    },
    {
      "epoch": 0.014926964495148737,
      "grad_norm": 0.2696877121925354,
      "learning_rate": 2.947933567072987e-06,
      "loss": 0.167,
      "step": 175
    },
    {
      "epoch": 0.015012261435121015,
      "grad_norm": 0.2834438383579254,
      "learning_rate": 2.719858575791534e-06,
      "loss": 0.2182,
      "step": 176
    },
    {
      "epoch": 0.015097558375093294,
      "grad_norm": 0.2892184853553772,
      "learning_rate": 2.500608652860256e-06,
      "loss": 0.2139,
      "step": 177
    },
    {
      "epoch": 0.015182855315065571,
      "grad_norm": 0.2734169065952301,
      "learning_rate": 2.2902437390188737e-06,
      "loss": 0.2139,
      "step": 178
    },
    {
      "epoch": 0.01526815225503785,
      "grad_norm": 0.2813917100429535,
      "learning_rate": 2.0888213459343587e-06,
      "loss": 0.2036,
      "step": 179
    },
    {
      "epoch": 0.01535344919501013,
      "grad_norm": 0.31374284625053406,
      "learning_rate": 1.8963965404777875e-06,
      "loss": 0.2091,
      "step": 180
    },
    {
      "epoch": 0.015438746134982407,
      "grad_norm": 0.28282588720321655,
      "learning_rate": 1.7130219296696263e-06,
      "loss": 0.2073,
      "step": 181
    },
    {
      "epoch": 0.015524043074954686,
      "grad_norm": 0.2769049108028412,
      "learning_rate": 1.5387476462974824e-06,
      "loss": 0.199,
      "step": 182
    },
    {
      "epoch": 0.015609340014926965,
      "grad_norm": 0.3395721912384033,
      "learning_rate": 1.3736213352103147e-06,
      "loss": 0.2555,
      "step": 183
    },
    {
      "epoch": 0.015694636954899244,
      "grad_norm": 0.25511637330055237,
      "learning_rate": 1.2176881402928002e-06,
      "loss": 0.1637,
      "step": 184
    },
    {
      "epoch": 0.01577993389487152,
      "grad_norm": 0.26766902208328247,
      "learning_rate": 1.0709906921234367e-06,
      "loss": 0.1751,
      "step": 185
    },
    {
      "epoch": 0.0158652308348438,
      "grad_norm": 0.3374779224395752,
      "learning_rate": 9.33569096319799e-07,
      "loss": 0.2028,
      "step": 186
    },
    {
      "epoch": 0.01595052777481608,
      "grad_norm": 0.3081513047218323,
      "learning_rate": 8.054609225740255e-07,
      "loss": 0.1899,
      "step": 187
    },
    {
      "epoch": 0.016035824714788358,
      "grad_norm": 0.3581075668334961,
      "learning_rate": 6.867011943816724e-07,
      "loss": 0.2002,
      "step": 188
    },
    {
      "epoch": 0.016121121654760637,
      "grad_norm": 0.308506041765213,
      "learning_rate": 5.77322379466617e-07,
      "loss": 0.2009,
      "step": 189
    },
    {
      "epoch": 0.016206418594732912,
      "grad_norm": 0.31448206305503845,
      "learning_rate": 4.773543809047186e-07,
      "loss": 0.1867,
      "step": 190
    },
    {
      "epoch": 0.01629171553470519,
      "grad_norm": 0.3072265386581421,
      "learning_rate": 3.868245289486027e-07,
      "loss": 0.1947,
      "step": 191
    },
    {
      "epoch": 0.01637701247467747,
      "grad_norm": 0.3579135835170746,
      "learning_rate": 3.0575757355586817e-07,
      "loss": 0.1925,
      "step": 192
    },
    {
      "epoch": 0.01646230941464975,
      "grad_norm": 0.31911733746528625,
      "learning_rate": 2.3417567762266497e-07,
      "loss": 0.2053,
      "step": 193
    },
    {
      "epoch": 0.01654760635462203,
      "grad_norm": 0.40067747235298157,
      "learning_rate": 1.7209841092460043e-07,
      "loss": 0.2594,
      "step": 194
    },
    {
      "epoch": 0.016632903294594305,
      "grad_norm": 0.3914952874183655,
      "learning_rate": 1.1954274476655534e-07,
      "loss": 0.2225,
      "step": 195
    },
    {
      "epoch": 0.016718200234566584,
      "grad_norm": 0.37973523139953613,
      "learning_rate": 7.652304734289127e-08,
      "loss": 0.1855,
      "step": 196
    },
    {
      "epoch": 0.016803497174538863,
      "grad_norm": 0.35993579030036926,
      "learning_rate": 4.30510798093342e-08,
      "loss": 0.2147,
      "step": 197
    },
    {
      "epoch": 0.016888794114511142,
      "grad_norm": 0.42936384677886963,
      "learning_rate": 1.9135993067588284e-08,
      "loss": 0.2288,
      "step": 198
    },
    {
      "epoch": 0.01697409105448342,
      "grad_norm": 0.43449467420578003,
      "learning_rate": 4.784325263584854e-09,
      "loss": 0.2641,
      "step": 199
    },
    {
      "epoch": 0.0170593879944557,
      "grad_norm": 0.4845728576183319,
      "learning_rate": 0.0,
      "loss": 0.2361,
      "step": 200
    },
    {
      "epoch": 0.0170593879944557,
      "eval_loss": 0.1986456662416458,
      "eval_runtime": 1543.4483,
      "eval_samples_per_second": 12.793,
      "eval_steps_per_second": 3.199,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0321122932791706e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}