{
  "best_metric": 0.7441057562828064,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.27238678924072185,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001361933946203609,
      "grad_norm": 1.359459400177002,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.0032,
      "step": 1
    },
    {
      "epoch": 0.001361933946203609,
      "eval_loss": 1.8361178636550903,
      "eval_runtime": 102.3534,
      "eval_samples_per_second": 12.086,
      "eval_steps_per_second": 6.048,
      "step": 1
    },
    {
      "epoch": 0.002723867892407218,
      "grad_norm": 1.3595656156539917,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.8715,
      "step": 2
    },
    {
      "epoch": 0.0040858018386108275,
      "grad_norm": 0.8516422510147095,
      "learning_rate": 1e-05,
      "loss": 0.985,
      "step": 3
    },
    {
      "epoch": 0.005447735784814436,
      "grad_norm": 1.3526928424835205,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.9778,
      "step": 4
    },
    {
      "epoch": 0.0068096697310180455,
      "grad_norm": 1.1126354932785034,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.9992,
      "step": 5
    },
    {
      "epoch": 0.008171603677221655,
      "grad_norm": 0.7547999620437622,
      "learning_rate": 2e-05,
      "loss": 1.0925,
      "step": 6
    },
    {
      "epoch": 0.009533537623425264,
      "grad_norm": 0.6296585202217102,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.9077,
      "step": 7
    },
    {
      "epoch": 0.010895471569628872,
      "grad_norm": 0.7324953079223633,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.0185,
      "step": 8
    },
    {
      "epoch": 0.012257405515832482,
      "grad_norm": 0.599586546421051,
      "learning_rate": 3e-05,
      "loss": 0.9358,
      "step": 9
    },
    {
      "epoch": 0.013619339462036091,
      "grad_norm": 0.4697187840938568,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.002,
      "step": 10
    },
    {
      "epoch": 0.0149812734082397,
      "grad_norm": 0.4674184024333954,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.9005,
      "step": 11
    },
    {
      "epoch": 0.01634320735444331,
      "grad_norm": 0.5633310675621033,
      "learning_rate": 4e-05,
      "loss": 0.9512,
      "step": 12
    },
    {
      "epoch": 0.017705141300646918,
      "grad_norm": 0.4497458338737488,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.9223,
      "step": 13
    },
    {
      "epoch": 0.01906707524685053,
      "grad_norm": 0.44553446769714355,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.9974,
      "step": 14
    },
    {
      "epoch": 0.020429009193054137,
      "grad_norm": 0.5649915933609009,
      "learning_rate": 5e-05,
      "loss": 0.9039,
      "step": 15
    },
    {
      "epoch": 0.021790943139257744,
      "grad_norm": 0.4939787685871124,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.8819,
      "step": 16
    },
    {
      "epoch": 0.023152877085461356,
      "grad_norm": 0.4850780665874481,
      "learning_rate": 5.666666666666667e-05,
      "loss": 0.9079,
      "step": 17
    },
    {
      "epoch": 0.024514811031664963,
      "grad_norm": 0.6583819389343262,
      "learning_rate": 6e-05,
      "loss": 0.9422,
      "step": 18
    },
    {
      "epoch": 0.025876744977868574,
      "grad_norm": 0.5175965428352356,
      "learning_rate": 6.333333333333333e-05,
      "loss": 0.7785,
      "step": 19
    },
    {
      "epoch": 0.027238678924072182,
      "grad_norm": 0.39870592951774597,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.8753,
      "step": 20
    },
    {
      "epoch": 0.028600612870275793,
      "grad_norm": 0.46424269676208496,
      "learning_rate": 7e-05,
      "loss": 0.8358,
      "step": 21
    },
    {
      "epoch": 0.0299625468164794,
      "grad_norm": 0.37857022881507874,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.7899,
      "step": 22
    },
    {
      "epoch": 0.03132448076268301,
      "grad_norm": 0.4620775878429413,
      "learning_rate": 7.666666666666667e-05,
      "loss": 0.794,
      "step": 23
    },
    {
      "epoch": 0.03268641470888662,
      "grad_norm": 0.43770840764045715,
      "learning_rate": 8e-05,
      "loss": 0.9161,
      "step": 24
    },
    {
      "epoch": 0.03404834865509023,
      "grad_norm": 0.3814782500267029,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.8271,
      "step": 25
    },
    {
      "epoch": 0.035410282601293835,
      "grad_norm": 0.37671318650245667,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.7861,
      "step": 26
    },
    {
      "epoch": 0.03677221654749745,
      "grad_norm": 0.4395905137062073,
      "learning_rate": 9e-05,
      "loss": 0.8465,
      "step": 27
    },
    {
      "epoch": 0.03813415049370106,
      "grad_norm": 0.4225689470767975,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.9939,
      "step": 28
    },
    {
      "epoch": 0.03949608443990466,
      "grad_norm": 0.4693770706653595,
      "learning_rate": 9.666666666666667e-05,
      "loss": 0.7881,
      "step": 29
    },
    {
      "epoch": 0.04085801838610827,
      "grad_norm": 0.5270646810531616,
      "learning_rate": 0.0001,
      "loss": 1.021,
      "step": 30
    },
    {
      "epoch": 0.042219952332311884,
      "grad_norm": 0.4941515028476715,
      "learning_rate": 9.999146252290264e-05,
      "loss": 0.8432,
      "step": 31
    },
    {
      "epoch": 0.04358188627851549,
      "grad_norm": 0.5971108675003052,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.8603,
      "step": 32
    },
    {
      "epoch": 0.0449438202247191,
      "grad_norm": 0.5028383135795593,
      "learning_rate": 9.99231801983717e-05,
      "loss": 0.8093,
      "step": 33
    },
    {
      "epoch": 0.04630575417092271,
      "grad_norm": 0.5662347078323364,
      "learning_rate": 9.986345866928941e-05,
      "loss": 0.8591,
      "step": 34
    },
    {
      "epoch": 0.04766768811712632,
      "grad_norm": 0.48115891218185425,
      "learning_rate": 9.978670881475172e-05,
      "loss": 1.076,
      "step": 35
    },
    {
      "epoch": 0.049029622063329927,
      "grad_norm": 0.46579429507255554,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.8445,
      "step": 36
    },
    {
      "epoch": 0.05039155600953354,
      "grad_norm": 0.4585355818271637,
      "learning_rate": 9.958223477553714e-05,
      "loss": 0.8441,
      "step": 37
    },
    {
      "epoch": 0.05175348995573715,
      "grad_norm": 0.5284808874130249,
      "learning_rate": 9.94545804185573e-05,
      "loss": 0.7553,
      "step": 38
    },
    {
      "epoch": 0.05311542390194075,
      "grad_norm": 0.5747087597846985,
      "learning_rate": 9.931003736767013e-05,
      "loss": 1.0747,
      "step": 39
    },
    {
      "epoch": 0.054477357848144364,
      "grad_norm": 0.5586481094360352,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.8998,
      "step": 40
    },
    {
      "epoch": 0.055839291794347976,
      "grad_norm": 0.46324145793914795,
      "learning_rate": 9.89704883800683e-05,
      "loss": 0.8412,
      "step": 41
    },
    {
      "epoch": 0.05720122574055159,
      "grad_norm": 0.5777992010116577,
      "learning_rate": 9.877559839902184e-05,
      "loss": 1.0007,
      "step": 42
    },
    {
      "epoch": 0.05856315968675519,
      "grad_norm": 0.5372388362884521,
      "learning_rate": 9.85640515958057e-05,
      "loss": 0.8075,
      "step": 43
    },
    {
      "epoch": 0.0599250936329588,
      "grad_norm": 0.5269652605056763,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.9494,
      "step": 44
    },
    {
      "epoch": 0.06128702757916241,
      "grad_norm": 0.5043860077857971,
      "learning_rate": 9.809128215864097e-05,
      "loss": 0.9655,
      "step": 45
    },
    {
      "epoch": 0.06264896152536602,
      "grad_norm": 0.560890257358551,
      "learning_rate": 9.783022097502204e-05,
      "loss": 1.0982,
      "step": 46
    },
    {
      "epoch": 0.06401089547156963,
      "grad_norm": 0.5604570508003235,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0527,
      "step": 47
    },
    {
      "epoch": 0.06537282941777324,
      "grad_norm": 0.684009313583374,
      "learning_rate": 9.725919140804099e-05,
      "loss": 1.1406,
      "step": 48
    },
    {
      "epoch": 0.06673476336397685,
      "grad_norm": 1.0995265245437622,
      "learning_rate": 9.694941803075283e-05,
      "loss": 1.3842,
      "step": 49
    },
    {
      "epoch": 0.06809669731018046,
      "grad_norm": 1.3429076671600342,
      "learning_rate": 9.662361147021779e-05,
      "loss": 1.2928,
      "step": 50
    },
    {
      "epoch": 0.06809669731018046,
      "eval_loss": 0.9619658589363098,
      "eval_runtime": 103.5333,
      "eval_samples_per_second": 11.948,
      "eval_steps_per_second": 5.979,
      "step": 50
    },
    {
      "epoch": 0.06945863125638406,
      "grad_norm": 0.5980075001716614,
      "learning_rate": 9.628188298907782e-05,
      "loss": 0.8406,
      "step": 51
    },
    {
      "epoch": 0.07082056520258767,
      "grad_norm": 0.3864894509315491,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.7524,
      "step": 52
    },
    {
      "epoch": 0.07218249914879128,
      "grad_norm": 0.3460322916507721,
      "learning_rate": 9.555113246230442e-05,
      "loss": 0.5977,
      "step": 53
    },
    {
      "epoch": 0.0735444330949949,
      "grad_norm": 0.34733179211616516,
      "learning_rate": 9.516235996730645e-05,
      "loss": 0.7982,
      "step": 54
    },
    {
      "epoch": 0.0749063670411985,
      "grad_norm": 0.31024450063705444,
      "learning_rate": 9.475816456775313e-05,
      "loss": 0.7509,
      "step": 55
    },
    {
      "epoch": 0.07626830098740212,
      "grad_norm": 0.2641952633857727,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.7111,
      "step": 56
    },
    {
      "epoch": 0.07763023493360573,
      "grad_norm": 0.21512354910373688,
      "learning_rate": 9.39040624041849e-05,
      "loss": 0.6776,
      "step": 57
    },
    {
      "epoch": 0.07899216887980932,
      "grad_norm": 0.23714327812194824,
      "learning_rate": 9.345444731527642e-05,
      "loss": 0.6766,
      "step": 58
    },
    {
      "epoch": 0.08035410282601294,
      "grad_norm": 0.2512352168560028,
      "learning_rate": 9.298999257241863e-05,
      "loss": 0.6887,
      "step": 59
    },
    {
      "epoch": 0.08171603677221655,
      "grad_norm": 0.238255575299263,
      "learning_rate": 9.251085678648072e-05,
      "loss": 0.6792,
      "step": 60
    },
    {
      "epoch": 0.08307797071842016,
      "grad_norm": 0.22919142246246338,
      "learning_rate": 9.201720358189464e-05,
      "loss": 0.6205,
      "step": 61
    },
    {
      "epoch": 0.08443990466462377,
      "grad_norm": 0.2486080378293991,
      "learning_rate": 9.150920154077754e-05,
      "loss": 0.6673,
      "step": 62
    },
    {
      "epoch": 0.08580183861082738,
      "grad_norm": 0.23667849600315094,
      "learning_rate": 9.098702414536107e-05,
      "loss": 0.7034,
      "step": 63
    },
    {
      "epoch": 0.08716377255703098,
      "grad_norm": 0.2587597072124481,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7128,
      "step": 64
    },
    {
      "epoch": 0.08852570650323459,
      "grad_norm": 0.2409951239824295,
      "learning_rate": 8.9900861364012e-05,
      "loss": 0.7189,
      "step": 65
    },
    {
      "epoch": 0.0898876404494382,
      "grad_norm": 0.27102091908454895,
      "learning_rate": 8.933724690167417e-05,
      "loss": 0.6919,
      "step": 66
    },
    {
      "epoch": 0.09124957439564181,
      "grad_norm": 0.2558993101119995,
      "learning_rate": 8.876019880555649e-05,
      "loss": 0.765,
      "step": 67
    },
    {
      "epoch": 0.09261150834184542,
      "grad_norm": 0.2672257423400879,
      "learning_rate": 8.816991413705516e-05,
      "loss": 0.7003,
      "step": 68
    },
    {
      "epoch": 0.09397344228804903,
      "grad_norm": 0.2692933976650238,
      "learning_rate": 8.756659447784368e-05,
      "loss": 0.708,
      "step": 69
    },
    {
      "epoch": 0.09533537623425264,
      "grad_norm": 0.27926138043403625,
      "learning_rate": 8.695044586103296e-05,
      "loss": 0.733,
      "step": 70
    },
    {
      "epoch": 0.09669731018045624,
      "grad_norm": 0.2771991193294525,
      "learning_rate": 8.632167870081121e-05,
      "loss": 0.7327,
      "step": 71
    },
    {
      "epoch": 0.09805924412665985,
      "grad_norm": 0.2985626757144928,
      "learning_rate": 8.568050772058762e-05,
      "loss": 0.8615,
      "step": 72
    },
    {
      "epoch": 0.09942117807286346,
      "grad_norm": 0.31558680534362793,
      "learning_rate": 8.502715187966455e-05,
      "loss": 0.7023,
      "step": 73
    },
    {
      "epoch": 0.10078311201906708,
      "grad_norm": 0.3178228437900543,
      "learning_rate": 8.436183429846313e-05,
      "loss": 0.6482,
      "step": 74
    },
    {
      "epoch": 0.10214504596527069,
      "grad_norm": 0.37531399726867676,
      "learning_rate": 8.368478218232787e-05,
      "loss": 0.7561,
      "step": 75
    },
    {
      "epoch": 0.1035069799114743,
      "grad_norm": 0.3327881693840027,
      "learning_rate": 8.299622674393614e-05,
      "loss": 0.7175,
      "step": 76
    },
    {
      "epoch": 0.10486891385767791,
      "grad_norm": 0.35700246691703796,
      "learning_rate": 8.229640312433937e-05,
      "loss": 0.8682,
      "step": 77
    },
    {
      "epoch": 0.1062308478038815,
      "grad_norm": 0.3885123133659363,
      "learning_rate": 8.158555031266254e-05,
      "loss": 0.7162,
      "step": 78
    },
    {
      "epoch": 0.10759278175008512,
      "grad_norm": 0.4296872317790985,
      "learning_rate": 8.086391106448965e-05,
      "loss": 0.7599,
      "step": 79
    },
    {
      "epoch": 0.10895471569628873,
      "grad_norm": 0.3776177167892456,
      "learning_rate": 8.013173181896283e-05,
      "loss": 0.7456,
      "step": 80
    },
    {
      "epoch": 0.11031664964249234,
      "grad_norm": 0.418770432472229,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8147,
      "step": 81
    },
    {
      "epoch": 0.11167858358869595,
      "grad_norm": 0.4962342381477356,
      "learning_rate": 7.863675700402526e-05,
      "loss": 0.8032,
      "step": 82
    },
    {
      "epoch": 0.11304051753489956,
      "grad_norm": 0.4492637515068054,
      "learning_rate": 7.787447196714427e-05,
      "loss": 0.8496,
      "step": 83
    },
    {
      "epoch": 0.11440245148110317,
      "grad_norm": 0.46460703015327454,
      "learning_rate": 7.710266782362247e-05,
      "loss": 0.8725,
      "step": 84
    },
    {
      "epoch": 0.11576438542730677,
      "grad_norm": 0.41849854588508606,
      "learning_rate": 7.63216081438678e-05,
      "loss": 0.6809,
      "step": 85
    },
    {
      "epoch": 0.11712631937351038,
      "grad_norm": 0.4125671684741974,
      "learning_rate": 7.553155965904535e-05,
      "loss": 0.6868,
      "step": 86
    },
    {
      "epoch": 0.118488253319714,
      "grad_norm": 0.53044193983078,
      "learning_rate": 7.473279216998895e-05,
      "loss": 0.8233,
      "step": 87
    },
    {
      "epoch": 0.1198501872659176,
      "grad_norm": 0.4882828891277313,
      "learning_rate": 7.392557845506432e-05,
      "loss": 0.7528,
      "step": 88
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.5197656154632568,
      "learning_rate": 7.311019417701566e-05,
      "loss": 0.6389,
      "step": 89
    },
    {
      "epoch": 0.12257405515832483,
      "grad_norm": 0.5164709687232971,
      "learning_rate": 7.228691778882693e-05,
      "loss": 0.7867,
      "step": 90
    },
    {
      "epoch": 0.12393598910452842,
      "grad_norm": 0.4505544602870941,
      "learning_rate": 7.145603043863045e-05,
      "loss": 0.8332,
      "step": 91
    },
    {
      "epoch": 0.12529792305073204,
      "grad_norm": 0.48305976390838623,
      "learning_rate": 7.061781587369519e-05,
      "loss": 0.7723,
      "step": 92
    },
    {
      "epoch": 0.12665985699693566,
      "grad_norm": 0.45914426445961,
      "learning_rate": 6.977256034352712e-05,
      "loss": 0.8264,
      "step": 93
    },
    {
      "epoch": 0.12802179094313926,
      "grad_norm": 0.4988130033016205,
      "learning_rate": 6.892055250211552e-05,
      "loss": 0.8078,
      "step": 94
    },
    {
      "epoch": 0.12938372488934285,
      "grad_norm": 0.48290184140205383,
      "learning_rate": 6.806208330935766e-05,
      "loss": 0.8155,
      "step": 95
    },
    {
      "epoch": 0.13074565883554648,
      "grad_norm": 0.49604806303977966,
      "learning_rate": 6.719744593169641e-05,
      "loss": 0.8617,
      "step": 96
    },
    {
      "epoch": 0.13210759278175008,
      "grad_norm": 0.5252610445022583,
      "learning_rate": 6.632693564200416e-05,
      "loss": 0.9714,
      "step": 97
    },
    {
      "epoch": 0.1334695267279537,
      "grad_norm": 0.6614923477172852,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0185,
      "step": 98
    },
    {
      "epoch": 0.1348314606741573,
      "grad_norm": 0.7504107356071472,
      "learning_rate": 6.456948734446624e-05,
      "loss": 0.9037,
      "step": 99
    },
    {
      "epoch": 0.13619339462036092,
      "grad_norm": 1.1629681587219238,
      "learning_rate": 6.368314950360415e-05,
      "loss": 1.1788,
      "step": 100
    },
    {
      "epoch": 0.13619339462036092,
      "eval_loss": 0.7944371700286865,
      "eval_runtime": 103.4461,
      "eval_samples_per_second": 11.958,
      "eval_steps_per_second": 5.984,
      "step": 100
    },
    {
      "epoch": 0.13755532856656452,
      "grad_norm": 0.2067456841468811,
      "learning_rate": 6.279213887972179e-05,
      "loss": 0.5961,
      "step": 101
    },
    {
      "epoch": 0.13891726251276812,
      "grad_norm": 0.21972322463989258,
      "learning_rate": 6.189675975213094e-05,
      "loss": 0.5196,
      "step": 102
    },
    {
      "epoch": 0.14027919645897174,
      "grad_norm": 0.22380179166793823,
      "learning_rate": 6.099731789198344e-05,
      "loss": 0.6496,
      "step": 103
    },
    {
      "epoch": 0.14164113040517534,
      "grad_norm": 0.23384810984134674,
      "learning_rate": 6.009412045785051e-05,
      "loss": 0.7285,
      "step": 104
    },
    {
      "epoch": 0.14300306435137897,
      "grad_norm": 0.25438612699508667,
      "learning_rate": 5.918747589082853e-05,
      "loss": 0.696,
      "step": 105
    },
    {
      "epoch": 0.14436499829758256,
      "grad_norm": 0.23733669519424438,
      "learning_rate": 5.82776938092065e-05,
      "loss": 0.7598,
      "step": 106
    },
    {
      "epoch": 0.1457269322437862,
      "grad_norm": 0.2382114678621292,
      "learning_rate": 5.736508490273188e-05,
      "loss": 0.6886,
      "step": 107
    },
    {
      "epoch": 0.1470888661899898,
      "grad_norm": 0.23478229343891144,
      "learning_rate": 5.644996082651017e-05,
      "loss": 0.6981,
      "step": 108
    },
    {
      "epoch": 0.14845080013619338,
      "grad_norm": 0.2193242460489273,
      "learning_rate": 5.553263409457504e-05,
      "loss": 0.6531,
      "step": 109
    },
    {
      "epoch": 0.149812734082397,
      "grad_norm": 0.3010532259941101,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 0.7956,
      "step": 110
    },
    {
      "epoch": 0.1511746680286006,
      "grad_norm": 0.27796250581741333,
      "learning_rate": 5.3692626373743706e-05,
      "loss": 0.7316,
      "step": 111
    },
    {
      "epoch": 0.15253660197480423,
      "grad_norm": 0.23366563022136688,
      "learning_rate": 5.27705737457985e-05,
      "loss": 0.7443,
      "step": 112
    },
    {
      "epoch": 0.15389853592100783,
      "grad_norm": 0.22676481306552887,
      "learning_rate": 5.184757496945726e-05,
      "loss": 0.6667,
      "step": 113
    },
    {
      "epoch": 0.15526046986721145,
      "grad_norm": 0.25168755650520325,
      "learning_rate": 5.092394524795649e-05,
      "loss": 0.6867,
      "step": 114
    },
    {
      "epoch": 0.15662240381341505,
      "grad_norm": 0.23510901629924774,
      "learning_rate": 5e-05,
      "loss": 0.7551,
      "step": 115
    },
    {
      "epoch": 0.15798433775961865,
      "grad_norm": 0.24297989904880524,
      "learning_rate": 4.907605475204352e-05,
      "loss": 0.723,
      "step": 116
    },
    {
      "epoch": 0.15934627170582227,
      "grad_norm": 0.2936830222606659,
      "learning_rate": 4.8152425030542766e-05,
      "loss": 0.7914,
      "step": 117
    },
    {
      "epoch": 0.16070820565202587,
      "grad_norm": 0.32800665497779846,
      "learning_rate": 4.72294262542015e-05,
      "loss": 0.713,
      "step": 118
    },
    {
      "epoch": 0.1620701395982295,
      "grad_norm": 0.285540372133255,
      "learning_rate": 4.6307373626256306e-05,
      "loss": 0.7493,
      "step": 119
    },
    {
      "epoch": 0.1634320735444331,
      "grad_norm": 0.32253602147102356,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 0.726,
      "step": 120
    },
    {
      "epoch": 0.1647940074906367,
      "grad_norm": 0.30640706419944763,
      "learning_rate": 4.446736590542497e-05,
      "loss": 0.7065,
      "step": 121
    },
    {
      "epoch": 0.16615594143684032,
      "grad_norm": 0.2831270396709442,
      "learning_rate": 4.3550039173489845e-05,
      "loss": 0.6869,
      "step": 122
    },
    {
      "epoch": 0.1675178753830439,
      "grad_norm": 0.31756505370140076,
      "learning_rate": 4.2634915097268115e-05,
      "loss": 0.7338,
      "step": 123
    },
    {
      "epoch": 0.16887980932924754,
      "grad_norm": 0.33590009808540344,
      "learning_rate": 4.1722306190793495e-05,
      "loss": 0.7718,
      "step": 124
    },
    {
      "epoch": 0.17024174327545114,
      "grad_norm": 0.31208398938179016,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 0.6202,
      "step": 125
    },
    {
      "epoch": 0.17160367722165476,
      "grad_norm": 0.3926757872104645,
      "learning_rate": 3.99058795421495e-05,
      "loss": 0.6732,
      "step": 126
    },
    {
      "epoch": 0.17296561116785836,
      "grad_norm": 0.37769249081611633,
      "learning_rate": 3.9002682108016585e-05,
      "loss": 0.7741,
      "step": 127
    },
    {
      "epoch": 0.17432754511406195,
      "grad_norm": 0.33026885986328125,
      "learning_rate": 3.8103240247869075e-05,
      "loss": 0.6891,
      "step": 128
    },
    {
      "epoch": 0.17568947906026558,
      "grad_norm": 0.36324840784072876,
      "learning_rate": 3.720786112027822e-05,
      "loss": 0.6293,
      "step": 129
    },
    {
      "epoch": 0.17705141300646918,
      "grad_norm": 0.4438748359680176,
      "learning_rate": 3.631685049639586e-05,
      "loss": 0.6637,
      "step": 130
    },
    {
      "epoch": 0.1784133469526728,
      "grad_norm": 0.437080979347229,
      "learning_rate": 3.543051265553377e-05,
      "loss": 0.8234,
      "step": 131
    },
    {
      "epoch": 0.1797752808988764,
      "grad_norm": 0.4293113350868225,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7818,
      "step": 132
    },
    {
      "epoch": 0.18113721484508002,
      "grad_norm": 0.4313202202320099,
      "learning_rate": 3.367306435799584e-05,
      "loss": 0.782,
      "step": 133
    },
    {
      "epoch": 0.18249914879128362,
      "grad_norm": 0.4160058796405792,
      "learning_rate": 3.2802554068303596e-05,
      "loss": 0.7241,
      "step": 134
    },
    {
      "epoch": 0.18386108273748722,
      "grad_norm": 0.416565865278244,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 0.7352,
      "step": 135
    },
    {
      "epoch": 0.18522301668369084,
      "grad_norm": 0.48462221026420593,
      "learning_rate": 3.107944749788449e-05,
      "loss": 0.8697,
      "step": 136
    },
    {
      "epoch": 0.18658495062989444,
      "grad_norm": 0.3931826651096344,
      "learning_rate": 3.0227439656472877e-05,
      "loss": 0.735,
      "step": 137
    },
    {
      "epoch": 0.18794688457609807,
      "grad_norm": 0.5121709108352661,
      "learning_rate": 2.9382184126304834e-05,
      "loss": 0.8023,
      "step": 138
    },
    {
      "epoch": 0.18930881852230166,
      "grad_norm": 0.4136485457420349,
      "learning_rate": 2.8543969561369556e-05,
      "loss": 0.7394,
      "step": 139
    },
    {
      "epoch": 0.1906707524685053,
      "grad_norm": 0.44947853684425354,
      "learning_rate": 2.771308221117309e-05,
      "loss": 0.751,
      "step": 140
    },
    {
      "epoch": 0.1920326864147089,
      "grad_norm": 0.46959882974624634,
      "learning_rate": 2.688980582298435e-05,
      "loss": 0.8248,
      "step": 141
    },
    {
      "epoch": 0.19339462036091248,
      "grad_norm": 0.47862911224365234,
      "learning_rate": 2.607442154493568e-05,
      "loss": 0.7799,
      "step": 142
    },
    {
      "epoch": 0.1947565543071161,
      "grad_norm": 0.4101274609565735,
      "learning_rate": 2.5267207830011068e-05,
      "loss": 0.7949,
      "step": 143
    },
    {
      "epoch": 0.1961184882533197,
      "grad_norm": 0.4547268748283386,
      "learning_rate": 2.446844034095466e-05,
      "loss": 0.8562,
      "step": 144
    },
    {
      "epoch": 0.19748042219952333,
      "grad_norm": 0.4429760277271271,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 0.7845,
      "step": 145
    },
    {
      "epoch": 0.19884235614572693,
      "grad_norm": 0.45933544635772705,
      "learning_rate": 2.2897332176377528e-05,
      "loss": 0.7277,
      "step": 146
    },
    {
      "epoch": 0.20020429009193055,
      "grad_norm": 0.4962371289730072,
      "learning_rate": 2.2125528032855724e-05,
      "loss": 0.7611,
      "step": 147
    },
    {
      "epoch": 0.20156622403813415,
      "grad_norm": 0.6105312705039978,
      "learning_rate": 2.136324299597474e-05,
      "loss": 0.9267,
      "step": 148
    },
    {
      "epoch": 0.20292815798433775,
      "grad_norm": 0.6516053676605225,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6398,
      "step": 149
    },
    {
      "epoch": 0.20429009193054137,
      "grad_norm": 1.3799935579299927,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 1.106,
      "step": 150
    },
    {
      "epoch": 0.20429009193054137,
      "eval_loss": 0.7522867918014526,
      "eval_runtime": 103.5151,
      "eval_samples_per_second": 11.95,
      "eval_steps_per_second": 5.98,
      "step": 150
    },
    {
      "epoch": 0.20565202587674497,
      "grad_norm": 0.17255501449108124,
      "learning_rate": 1.9136088935510362e-05,
      "loss": 0.6241,
      "step": 151
    },
    {
      "epoch": 0.2070139598229486,
      "grad_norm": 0.15434518456459045,
      "learning_rate": 1.8414449687337464e-05,
      "loss": 0.5175,
      "step": 152
    },
    {
      "epoch": 0.2083758937691522,
      "grad_norm": 0.16057954728603363,
      "learning_rate": 1.7703596875660645e-05,
      "loss": 0.5843,
      "step": 153
    },
    {
      "epoch": 0.20973782771535582,
      "grad_norm": 0.16260911524295807,
      "learning_rate": 1.700377325606388e-05,
      "loss": 0.6183,
      "step": 154
    },
    {
      "epoch": 0.21109976166155942,
      "grad_norm": 0.180234894156456,
      "learning_rate": 1.631521781767214e-05,
      "loss": 0.6693,
      "step": 155
    },
    {
      "epoch": 0.212461695607763,
      "grad_norm": 0.21156199276447296,
      "learning_rate": 1.5638165701536868e-05,
      "loss": 0.726,
      "step": 156
    },
    {
      "epoch": 0.21382362955396664,
      "grad_norm": 0.18673358857631683,
      "learning_rate": 1.4972848120335453e-05,
      "loss": 0.6639,
      "step": 157
    },
    {
      "epoch": 0.21518556350017023,
      "grad_norm": 0.19483909010887146,
      "learning_rate": 1.4319492279412388e-05,
      "loss": 0.6797,
      "step": 158
    },
    {
      "epoch": 0.21654749744637386,
      "grad_norm": 0.2238985300064087,
      "learning_rate": 1.3678321299188801e-05,
      "loss": 0.6316,
      "step": 159
    },
    {
      "epoch": 0.21790943139257746,
      "grad_norm": 0.22773568332195282,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 0.7293,
      "step": 160
    },
    {
      "epoch": 0.21927136533878108,
      "grad_norm": 0.22139477729797363,
      "learning_rate": 1.2433405522156332e-05,
      "loss": 0.5769,
      "step": 161
    },
    {
      "epoch": 0.22063329928498468,
      "grad_norm": 0.2327103167772293,
      "learning_rate": 1.183008586294485e-05,
      "loss": 0.7907,
      "step": 162
    },
    {
      "epoch": 0.22199523323118828,
      "grad_norm": 0.22104878723621368,
      "learning_rate": 1.1239801194443506e-05,
      "loss": 0.6322,
      "step": 163
    },
    {
      "epoch": 0.2233571671773919,
      "grad_norm": 0.2553716003894806,
      "learning_rate": 1.066275309832584e-05,
      "loss": 0.7341,
      "step": 164
    },
    {
      "epoch": 0.2247191011235955,
      "grad_norm": 0.2540958523750305,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 0.7212,
      "step": 165
    },
    {
      "epoch": 0.22608103506979912,
      "grad_norm": 0.24824371933937073,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7148,
      "step": 166
    },
    {
      "epoch": 0.22744296901600272,
      "grad_norm": 0.2560056447982788,
      "learning_rate": 9.012975854638949e-06,
      "loss": 0.8558,
      "step": 167
    },
    {
      "epoch": 0.22880490296220635,
      "grad_norm": 0.2578204274177551,
      "learning_rate": 8.490798459222476e-06,
      "loss": 0.7938,
      "step": 168
    },
    {
      "epoch": 0.23016683690840994,
      "grad_norm": 0.23950396478176117,
      "learning_rate": 7.982796418105371e-06,
      "loss": 0.7336,
      "step": 169
    },
    {
      "epoch": 0.23152877085461354,
      "grad_norm": 0.2819407880306244,
      "learning_rate": 7.489143213519301e-06,
      "loss": 0.8381,
      "step": 170
    },
    {
      "epoch": 0.23289070480081717,
      "grad_norm": 0.2772591710090637,
      "learning_rate": 7.010007427581378e-06,
      "loss": 0.6564,
      "step": 171
    },
    {
      "epoch": 0.23425263874702076,
      "grad_norm": 0.28909778594970703,
      "learning_rate": 6.5455526847235825e-06,
      "loss": 0.7016,
      "step": 172
    },
    {
      "epoch": 0.2356145726932244,
      "grad_norm": 0.2975641191005707,
      "learning_rate": 6.0959375958151045e-06,
      "loss": 0.7454,
      "step": 173
    },
    {
      "epoch": 0.236976506639428,
      "grad_norm": 0.3052116334438324,
      "learning_rate": 5.6613157039969055e-06,
      "loss": 0.7788,
      "step": 174
    },
    {
      "epoch": 0.23833844058563158,
      "grad_norm": 0.3118731677532196,
      "learning_rate": 5.241835432246889e-06,
      "loss": 0.68,
      "step": 175
    },
    {
      "epoch": 0.2397003745318352,
      "grad_norm": 0.35767170786857605,
      "learning_rate": 4.837640032693558e-06,
      "loss": 0.7429,
      "step": 176
    },
    {
      "epoch": 0.2410623084780388,
      "grad_norm": 0.361837238073349,
      "learning_rate": 4.448867537695578e-06,
      "loss": 0.8067,
      "step": 177
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.3700478971004486,
      "learning_rate": 4.075650712703849e-06,
      "loss": 0.7809,
      "step": 178
    },
    {
      "epoch": 0.24378617637044603,
      "grad_norm": 0.39388328790664673,
      "learning_rate": 3.71811701092219e-06,
      "loss": 0.6992,
      "step": 179
    },
    {
      "epoch": 0.24514811031664965,
      "grad_norm": 0.43889668583869934,
      "learning_rate": 3.376388529782215e-06,
      "loss": 0.8435,
      "step": 180
    },
    {
      "epoch": 0.24651004426285325,
      "grad_norm": 0.45104825496673584,
      "learning_rate": 3.0505819692471792e-06,
      "loss": 0.6705,
      "step": 181
    },
    {
      "epoch": 0.24787197820905685,
      "grad_norm": 0.4363878071308136,
      "learning_rate": 2.7408085919590264e-06,
      "loss": 0.7322,
      "step": 182
    },
    {
      "epoch": 0.24923391215526047,
      "grad_norm": 0.35879090428352356,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.722,
      "step": 183
    },
    {
      "epoch": 0.25059584610146407,
      "grad_norm": 0.43597957491874695,
      "learning_rate": 2.1697790249779636e-06,
      "loss": 0.7197,
      "step": 184
    },
    {
      "epoch": 0.25195778004766767,
      "grad_norm": 0.49777480959892273,
      "learning_rate": 1.908717841359048e-06,
      "loss": 0.827,
      "step": 185
    },
    {
      "epoch": 0.2533197139938713,
      "grad_norm": 0.41167500615119934,
      "learning_rate": 1.6640797865406288e-06,
      "loss": 0.6546,
      "step": 186
    },
    {
      "epoch": 0.2546816479400749,
      "grad_norm": 0.4394213557243347,
      "learning_rate": 1.4359484041943038e-06,
      "loss": 0.8141,
      "step": 187
    },
    {
      "epoch": 0.2560435818862785,
      "grad_norm": 0.556496798992157,
      "learning_rate": 1.2244016009781701e-06,
      "loss": 0.8927,
      "step": 188
    },
    {
      "epoch": 0.2574055158324821,
      "grad_norm": 0.5145028829574585,
      "learning_rate": 1.0295116199317057e-06,
      "loss": 0.7661,
      "step": 189
    },
    {
      "epoch": 0.2587674497786857,
      "grad_norm": 0.5240097045898438,
      "learning_rate": 8.513450158049108e-07,
      "loss": 0.7814,
      "step": 190
    },
    {
      "epoch": 0.26012938372488936,
      "grad_norm": 0.4952259063720703,
      "learning_rate": 6.899626323298713e-07,
      "loss": 0.76,
      "step": 191
    },
    {
      "epoch": 0.26149131767109296,
      "grad_norm": 0.44523516297340393,
      "learning_rate": 5.454195814427021e-07,
      "loss": 0.7334,
      "step": 192
    },
    {
      "epoch": 0.26285325161729656,
      "grad_norm": 0.5299931764602661,
      "learning_rate": 4.177652244628627e-07,
      "loss": 0.7903,
      "step": 193
    },
    {
      "epoch": 0.26421518556350015,
      "grad_norm": 0.4894885718822479,
      "learning_rate": 3.0704315523631953e-07,
      "loss": 0.7987,
      "step": 194
    },
    {
      "epoch": 0.26557711950970375,
      "grad_norm": 0.5092527270317078,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 0.7906,
      "step": 195
    },
    {
      "epoch": 0.2669390534559074,
      "grad_norm": 0.48224949836730957,
      "learning_rate": 1.3654133071059893e-07,
      "loss": 0.8502,
      "step": 196
    },
    {
      "epoch": 0.268300987402111,
      "grad_norm": 0.6226413249969482,
      "learning_rate": 7.681980162830282e-08,
      "loss": 0.9195,
      "step": 197
    },
    {
      "epoch": 0.2696629213483146,
      "grad_norm": 0.5972543954849243,
      "learning_rate": 3.4146992848854695e-08,
      "loss": 0.8265,
      "step": 198
    },
    {
      "epoch": 0.2710248552945182,
      "grad_norm": 0.6523533463478088,
      "learning_rate": 8.537477097364522e-09,
      "loss": 0.5512,
      "step": 199
    },
    {
      "epoch": 0.27238678924072185,
      "grad_norm": 1.3673629760742188,
      "learning_rate": 0.0,
      "loss": 1.0819,
      "step": 200
    },
    {
      "epoch": 0.27238678924072185,
      "eval_loss": 0.7441057562828064,
      "eval_runtime": 103.3871,
      "eval_samples_per_second": 11.965,
      "eval_steps_per_second": 5.987,
      "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": 5,
        "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": 2.8092898738176e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}