{
  "best_metric": 0.21310460567474365,
  "best_model_checkpoint": "../../models/baseline/btx/checkpoint-13692",
  "epoch": 1.0,
  "eval_steps": 3423,
  "global_step": 13692,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010005842827928718,
      "grad_norm": 2.8703060150146484,
      "learning_rate": 4.9987649590704944e-05,
      "loss": 0.7257,
      "step": 137
    },
    {
      "epoch": 0.020011685655857436,
      "grad_norm": 2.461472988128662,
      "learning_rate": 4.9950610565428546e-05,
      "loss": 0.6506,
      "step": 274
    },
    {
      "epoch": 0.03001752848378615,
      "grad_norm": 2.306278944015503,
      "learning_rate": 4.988891951994058e-05,
      "loss": 0.6267,
      "step": 411
    },
    {
      "epoch": 0.04002337131171487,
      "grad_norm": 2.7277510166168213,
      "learning_rate": 4.9802637407013966e-05,
      "loss": 0.5933,
      "step": 548
    },
    {
      "epoch": 0.05002921413964359,
      "grad_norm": 2.524292230606079,
      "learning_rate": 4.969184947620146e-05,
      "loss": 0.5853,
      "step": 685
    },
    {
      "epoch": 0.0600350569675723,
      "grad_norm": 2.5938446521759033,
      "learning_rate": 4.9556665189606316e-05,
      "loss": 0.5486,
      "step": 822
    },
    {
      "epoch": 0.07004089979550102,
      "grad_norm": 2.528536796569824,
      "learning_rate": 4.93972181137301e-05,
      "loss": 0.5527,
      "step": 959
    },
    {
      "epoch": 0.08004674262342974,
      "grad_norm": 2.1125128269195557,
      "learning_rate": 4.9213665787504655e-05,
      "loss": 0.5129,
      "step": 1096
    },
    {
      "epoch": 0.09005258545135846,
      "grad_norm": 2.1105308532714844,
      "learning_rate": 4.900618956663845e-05,
      "loss": 0.5193,
      "step": 1233
    },
    {
      "epoch": 0.10005842827928718,
      "grad_norm": 1.8278461694717407,
      "learning_rate": 4.877499444443122e-05,
      "loss": 0.5207,
      "step": 1370
    },
    {
      "epoch": 0.1100642711072159,
      "grad_norm": 4.437809944152832,
      "learning_rate": 4.852030884923388e-05,
      "loss": 0.4967,
      "step": 1507
    },
    {
      "epoch": 0.1200701139351446,
      "grad_norm": 2.0539824962615967,
      "learning_rate": 4.82423844187538e-05,
      "loss": 0.4825,
      "step": 1644
    },
    {
      "epoch": 0.13007595676307332,
      "grad_norm": 1.672153115272522,
      "learning_rate": 4.7941495751428536e-05,
      "loss": 0.4648,
      "step": 1781
    },
    {
      "epoch": 0.14008179959100203,
      "grad_norm": 1.9463084936141968,
      "learning_rate": 4.7617940135113606e-05,
      "loss": 0.4623,
      "step": 1918
    },
    {
      "epoch": 0.15008764241893077,
      "grad_norm": 1.61201810836792,
      "learning_rate": 4.7272037253352276e-05,
      "loss": 0.4406,
      "step": 2055
    },
    {
      "epoch": 0.16009348524685948,
      "grad_norm": 1.998997449874878,
      "learning_rate": 4.690412886951786e-05,
      "loss": 0.4563,
      "step": 2192
    },
    {
      "epoch": 0.1700993280747882,
      "grad_norm": 1.4533461332321167,
      "learning_rate": 4.651457848914021e-05,
      "loss": 0.4449,
      "step": 2329
    },
    {
      "epoch": 0.1801051709027169,
      "grad_norm": 1.3883270025253296,
      "learning_rate": 4.610377100075045e-05,
      "loss": 0.4186,
      "step": 2466
    },
    {
      "epoch": 0.19011101373064562,
      "grad_norm": 1.6303733587265015,
      "learning_rate": 4.5672112295598404e-05,
      "loss": 0.42,
      "step": 2603
    },
    {
      "epoch": 0.20011685655857436,
      "grad_norm": 2.2687270641326904,
      "learning_rate": 4.5220028866618837e-05,
      "loss": 0.4063,
      "step": 2740
    },
    {
      "epoch": 0.21012269938650308,
      "grad_norm": 1.6023283004760742,
      "learning_rate": 4.4747967387042424e-05,
      "loss": 0.4037,
      "step": 2877
    },
    {
      "epoch": 0.2201285422144318,
      "grad_norm": 1.6843392848968506,
      "learning_rate": 4.4256394269067967e-05,
      "loss": 0.3942,
      "step": 3014
    },
    {
      "epoch": 0.2301343850423605,
      "grad_norm": 1.3607641458511353,
      "learning_rate": 4.3745795203031904e-05,
      "loss": 0.3898,
      "step": 3151
    },
    {
      "epoch": 0.2401402278702892,
      "grad_norm": 1.3324497938156128,
      "learning_rate": 4.321667467753034e-05,
      "loss": 0.3937,
      "step": 3288
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.4498611092567444,
      "eval_runtime": 365.3631,
      "eval_samples_per_second": 31.58,
      "eval_steps_per_second": 7.896,
      "step": 3423
    },
    {
      "epoch": 0.2501460706982179,
      "grad_norm": 2.132169723510742,
      "learning_rate": 4.2669555480967783e-05,
      "loss": 0.3771,
      "step": 3425
    },
    {
      "epoch": 0.26015191352614664,
      "grad_norm": 1.718522071838379,
      "learning_rate": 4.210497818502509e-05,
      "loss": 0.3865,
      "step": 3562
    },
    {
      "epoch": 0.27015775635407535,
      "grad_norm": 1.6622902154922485,
      "learning_rate": 4.152350061055695e-05,
      "loss": 0.3621,
      "step": 3699
    },
    {
      "epoch": 0.28016359918200406,
      "grad_norm": 1.836055040359497,
      "learning_rate": 4.092569727644661e-05,
      "loss": 0.3764,
      "step": 3836
    },
    {
      "epoch": 0.29016944200993283,
      "grad_norm": 1.3349945545196533,
      "learning_rate": 4.031215883196239e-05,
      "loss": 0.3546,
      "step": 3973
    },
    {
      "epoch": 0.30017528483786154,
      "grad_norm": 1.3506925106048584,
      "learning_rate": 3.968349147317693e-05,
      "loss": 0.3551,
      "step": 4110
    },
    {
      "epoch": 0.31018112766579026,
      "grad_norm": 1.663672685623169,
      "learning_rate": 3.904031634402552e-05,
      "loss": 0.329,
      "step": 4247
    },
    {
      "epoch": 0.32018697049371897,
      "grad_norm": 1.5420622825622559,
      "learning_rate": 3.838326892259564e-05,
      "loss": 0.3477,
      "step": 4384
    },
    {
      "epoch": 0.3301928133216477,
      "grad_norm": 1.14065682888031,
      "learning_rate": 3.7712998393253786e-05,
      "loss": 0.3311,
      "step": 4521
    },
    {
      "epoch": 0.3401986561495764,
      "grad_norm": 2.2005677223205566,
      "learning_rate": 3.703016700522999e-05,
      "loss": 0.3329,
      "step": 4658
    },
    {
      "epoch": 0.3502044989775051,
      "grad_norm": 1.666883111000061,
      "learning_rate": 3.6335449418293985e-05,
      "loss": 0.3398,
      "step": 4795
    },
    {
      "epoch": 0.3602103418054338,
      "grad_norm": 1.7949641942977905,
      "learning_rate": 3.562953203616925e-05,
      "loss": 0.3155,
      "step": 4932
    },
    {
      "epoch": 0.37021618463336253,
      "grad_norm": 1.5265356302261353,
      "learning_rate": 3.491311232834357e-05,
      "loss": 0.3216,
      "step": 5069
    },
    {
      "epoch": 0.38022202746129125,
      "grad_norm": 1.8440781831741333,
      "learning_rate": 3.418689814094646e-05,
      "loss": 0.3154,
      "step": 5206
    },
    {
      "epoch": 0.39022787028921996,
      "grad_norm": 1.4105604887008667,
      "learning_rate": 3.345160699737394e-05,
      "loss": 0.3141,
      "step": 5343
    },
    {
      "epoch": 0.4002337131171487,
      "grad_norm": 1.1201190948486328,
      "learning_rate": 3.2707965389351925e-05,
      "loss": 0.303,
      "step": 5480
    },
    {
      "epoch": 0.41023955594507744,
      "grad_norm": 1.8358474969863892,
      "learning_rate": 3.195670805913866e-05,
      "loss": 0.3042,
      "step": 5617
    },
    {
      "epoch": 0.42024539877300615,
      "grad_norm": 1.7674305438995361,
      "learning_rate": 3.119857727357527e-05,
      "loss": 0.2908,
      "step": 5754
    },
    {
      "epoch": 0.43025124160093486,
      "grad_norm": 1.841166377067566,
      "learning_rate": 3.0434322090701827e-05,
      "loss": 0.2923,
      "step": 5891
    },
    {
      "epoch": 0.4402570844288636,
      "grad_norm": 1.6789052486419678,
      "learning_rate": 2.9664697619663472e-05,
      "loss": 0.2791,
      "step": 6028
    },
    {
      "epoch": 0.4502629272567923,
      "grad_norm": 1.2760952711105347,
      "learning_rate": 2.8890464274637876e-05,
      "loss": 0.2749,
      "step": 6165
    },
    {
      "epoch": 0.460268770084721,
      "grad_norm": 1.3617960214614868,
      "learning_rate": 2.8112387023521115e-05,
      "loss": 0.2715,
      "step": 6302
    },
    {
      "epoch": 0.4702746129126497,
      "grad_norm": 1.0967957973480225,
      "learning_rate": 2.733123463211434e-05,
      "loss": 0.2748,
      "step": 6439
    },
    {
      "epoch": 0.4802804557405784,
      "grad_norm": 0.9176567196846008,
      "learning_rate": 2.6547778904558018e-05,
      "loss": 0.2747,
      "step": 6576
    },
    {
      "epoch": 0.49028629856850714,
      "grad_norm": 0.9466305375099182,
      "learning_rate": 2.5762793920764124e-05,
      "loss": 0.2679,
      "step": 6713
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.31969591975212097,
      "eval_runtime": 364.3381,
      "eval_samples_per_second": 31.668,
      "eval_steps_per_second": 7.918,
      "step": 6846
    },
    {
      "epoch": 0.5002921413964359,
      "grad_norm": 1.4617935419082642,
      "learning_rate": 2.4977055271599893e-05,
      "loss": 0.2643,
      "step": 6850
    },
    {
      "epoch": 0.5102979842243646,
      "grad_norm": 1.6485743522644043,
      "learning_rate": 2.4191339292578617e-05,
      "loss": 0.2605,
      "step": 6987
    },
    {
      "epoch": 0.5203038270522933,
      "grad_norm": 1.0177462100982666,
      "learning_rate": 2.340642229681474e-05,
      "loss": 0.2597,
      "step": 7124
    },
    {
      "epoch": 0.530309669880222,
      "grad_norm": 1.5512287616729736,
      "learning_rate": 2.262307980800109e-05,
      "loss": 0.2427,
      "step": 7261
    },
    {
      "epoch": 0.5403155127081507,
      "grad_norm": 1.314630150794983,
      "learning_rate": 2.1842085794166068e-05,
      "loss": 0.239,
      "step": 7398
    },
    {
      "epoch": 0.5503213555360794,
      "grad_norm": 1.3187059164047241,
      "learning_rate": 2.1064211902967904e-05,
      "loss": 0.2287,
      "step": 7535
    },
    {
      "epoch": 0.5603271983640081,
      "grad_norm": 1.2602145671844482,
      "learning_rate": 2.02902266992815e-05,
      "loss": 0.2381,
      "step": 7672
    },
    {
      "epoch": 0.570333041191937,
      "grad_norm": 1.5069787502288818,
      "learning_rate": 1.9520894905831154e-05,
      "loss": 0.2324,
      "step": 7809
    },
    {
      "epoch": 0.5803388840198657,
      "grad_norm": 0.8896231651306152,
      "learning_rate": 1.8756976647619502e-05,
      "loss": 0.2292,
      "step": 7946
    },
    {
      "epoch": 0.5903447268477944,
      "grad_norm": 0.9988867044448853,
      "learning_rate": 1.7999226700899093e-05,
      "loss": 0.2203,
      "step": 8083
    },
    {
      "epoch": 0.6003505696757231,
      "grad_norm": 0.9557806253433228,
      "learning_rate": 1.7248393747428747e-05,
      "loss": 0.2149,
      "step": 8220
    },
    {
      "epoch": 0.6103564125036518,
      "grad_norm": 1.0728305578231812,
      "learning_rate": 1.6505219634751472e-05,
      "loss": 0.2218,
      "step": 8357
    },
    {
      "epoch": 0.6203622553315805,
      "grad_norm": 1.2526644468307495,
      "learning_rate": 1.5770438643224794e-05,
      "loss": 0.2266,
      "step": 8494
    },
    {
      "epoch": 0.6303680981595092,
      "grad_norm": 1.0386145114898682,
      "learning_rate": 1.5044776760527727e-05,
      "loss": 0.2163,
      "step": 8631
    },
    {
      "epoch": 0.6403739409874379,
      "grad_norm": 1.0314420461654663,
      "learning_rate": 1.4328950964361143e-05,
      "loss": 0.2114,
      "step": 8768
    },
    {
      "epoch": 0.6503797838153667,
      "grad_norm": 0.5962662100791931,
      "learning_rate": 1.3623668514050391e-05,
      "loss": 0.2049,
      "step": 8905
    },
    {
      "epoch": 0.6603856266432954,
      "grad_norm": 0.6801035404205322,
      "learning_rate": 1.2929626251749854e-05,
      "loss": 0.2085,
      "step": 9042
    },
    {
      "epoch": 0.6703914694712241,
      "grad_norm": 1.8030842542648315,
      "learning_rate": 1.2247509913940128e-05,
      "loss": 0.2045,
      "step": 9179
    },
    {
      "epoch": 0.6803973122991528,
      "grad_norm": 1.7659096717834473,
      "learning_rate": 1.1577993453897933e-05,
      "loss": 0.2069,
      "step": 9316
    },
    {
      "epoch": 0.6904031551270815,
      "grad_norm": 0.6933948397636414,
      "learning_rate": 1.0921738375808166e-05,
      "loss": 0.1892,
      "step": 9453
    },
    {
      "epoch": 0.7004089979550102,
      "grad_norm": 1.0741862058639526,
      "learning_rate": 1.0279393081176122e-05,
      "loss": 0.1893,
      "step": 9590
    },
    {
      "epoch": 0.7104148407829389,
      "grad_norm": 0.31156471371650696,
      "learning_rate": 9.651592228185622e-06,
      "loss": 0.1894,
      "step": 9727
    },
    {
      "epoch": 0.7204206836108676,
      "grad_norm": 1.0299690961837769,
      "learning_rate": 9.038956104635871e-06,
      "loss": 0.1844,
      "step": 9864
    },
    {
      "epoch": 0.7304265264387964,
      "grad_norm": 0.8893802165985107,
      "learning_rate": 8.442090015076842e-06,
      "loss": 0.1952,
      "step": 10001
    },
    {
      "epoch": 0.7404323692667251,
      "grad_norm": 1.3043843507766724,
      "learning_rate": 7.861583682748586e-06,
      "loss": 0.1804,
      "step": 10138
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.23675276339054108,
      "eval_runtime": 365.1866,
      "eval_samples_per_second": 31.595,
      "eval_steps_per_second": 7.9,
      "step": 10269
    },
    {
      "epoch": 0.7504382120946538,
      "grad_norm": 1.0938574075698853,
      "learning_rate": 7.298010666915303e-06,
      "loss": 0.1777,
      "step": 10275
    },
    {
      "epoch": 0.7604440549225825,
      "grad_norm": 0.9465618133544922,
      "learning_rate": 6.751927796170044e-06,
      "loss": 0.1902,
      "step": 10412
    },
    {
      "epoch": 0.7704498977505112,
      "grad_norm": 1.0503722429275513,
      "learning_rate": 6.2238746182698375e-06,
      "loss": 0.161,
      "step": 10549
    },
    {
      "epoch": 0.7804557405784399,
      "grad_norm": 1.2977089881896973,
      "learning_rate": 5.7143728670448095e-06,
      "loss": 0.1817,
      "step": 10686
    },
    {
      "epoch": 0.7904615834063686,
      "grad_norm": 0.7178501486778259,
      "learning_rate": 5.223925946908093e-06,
      "loss": 0.1715,
      "step": 10823
    },
    {
      "epoch": 0.8004674262342975,
      "grad_norm": 1.1066858768463135,
      "learning_rate": 4.7530184354757675e-06,
      "loss": 0.1795,
      "step": 10960
    },
    {
      "epoch": 0.8104732690622262,
      "grad_norm": 0.5346119999885559,
      "learning_rate": 4.30211560478837e-06,
      "loss": 0.1716,
      "step": 11097
    },
    {
      "epoch": 0.8204791118901549,
      "grad_norm": 1.6099894046783447,
      "learning_rate": 3.871662961606784e-06,
      "loss": 0.1758,
      "step": 11234
    },
    {
      "epoch": 0.8304849547180836,
      "grad_norm": 0.7507832050323486,
      "learning_rate": 3.4620858072370504e-06,
      "loss": 0.1706,
      "step": 11371
    },
    {
      "epoch": 0.8404907975460123,
      "grad_norm": 1.2874454259872437,
      "learning_rate": 3.073788817318707e-06,
      "loss": 0.1713,
      "step": 11508
    },
    {
      "epoch": 0.850496640373941,
      "grad_norm": 0.863970935344696,
      "learning_rate": 2.7071556419920514e-06,
      "loss": 0.1637,
      "step": 11645
    },
    {
      "epoch": 0.8605024832018697,
      "grad_norm": 0.841557502746582,
      "learning_rate": 2.3625485268391893e-06,
      "loss": 0.1544,
      "step": 11782
    },
    {
      "epoch": 0.8705083260297984,
      "grad_norm": 0.9113953113555908,
      "learning_rate": 2.040307954973572e-06,
      "loss": 0.1642,
      "step": 11919
    },
    {
      "epoch": 0.8805141688577272,
      "grad_norm": 1.1008964776992798,
      "learning_rate": 1.7407523106315244e-06,
      "loss": 0.1501,
      "step": 12056
    },
    {
      "epoch": 0.8905200116856559,
      "grad_norm": 0.7368434071540833,
      "learning_rate": 1.4641775645981849e-06,
      "loss": 0.1617,
      "step": 12193
    },
    {
      "epoch": 0.9005258545135846,
      "grad_norm": 0.8009047508239746,
      "learning_rate": 1.210856981778688e-06,
      "loss": 0.1498,
      "step": 12330
    },
    {
      "epoch": 0.9105316973415133,
      "grad_norm": 0.7741762399673462,
      "learning_rate": 9.810408512034908e-07,
      "loss": 0.1567,
      "step": 12467
    },
    {
      "epoch": 0.920537540169442,
      "grad_norm": 0.5345299243927002,
      "learning_rate": 7.749562387346088e-07,
      "loss": 0.1668,
      "step": 12604
    },
    {
      "epoch": 0.9305433829973707,
      "grad_norm": 0.8907518982887268,
      "learning_rate": 5.928067627171158e-07,
      "loss": 0.159,
      "step": 12741
    },
    {
      "epoch": 0.9405492258252994,
      "grad_norm": 1.0891618728637695,
      "learning_rate": 4.347723927975417e-07,
      "loss": 0.1615,
      "step": 12878
    },
    {
      "epoch": 0.9505550686532281,
      "grad_norm": 0.5715863108634949,
      "learning_rate": 3.01009272107991e-07,
      "loss": 0.1568,
      "step": 13015
    },
    {
      "epoch": 0.9605609114811569,
      "grad_norm": 0.8792664408683777,
      "learning_rate": 1.9164956299158322e-07,
      "loss": 0.1656,
      "step": 13152
    },
    {
      "epoch": 0.9705667543090856,
      "grad_norm": 1.4301509857177734,
      "learning_rate": 1.0680131642176183e-07,
      "loss": 0.1528,
      "step": 13289
    },
    {
      "epoch": 0.9805725971370143,
      "grad_norm": 0.6064629554748535,
      "learning_rate": 4.6548365244375446e-08,
      "loss": 0.1628,
      "step": 13426
    },
    {
      "epoch": 0.990578439964943,
      "grad_norm": 0.9063898921012878,
      "learning_rate": 1.0950241348084422e-08,
      "loss": 0.1529,
      "step": 13563
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.21310460567474365,
      "eval_runtime": 364.3533,
      "eval_samples_per_second": 31.667,
      "eval_steps_per_second": 7.918,
      "step": 13692
    },
    {
      "epoch": 1.0,
      "step": 13692,
      "total_flos": 2.405329205216464e+19,
      "train_loss": 0.29627383469211893,
      "train_runtime": 43035.7563,
      "train_samples_per_second": 2.545,
      "train_steps_per_second": 0.318
    }
  ],
  "logging_steps": 137,
  "max_steps": 13692,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3423,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.405329205216464e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}