{
  "best_metric": 6.889637470245361,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.05577244841048522,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005577244841048522,
      "grad_norm": 1.3554329872131348,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 6.8919,
      "step": 1
    },
    {
      "epoch": 0.0005577244841048522,
      "eval_loss": 6.896846771240234,
      "eval_runtime": 1.1728,
      "eval_samples_per_second": 643.737,
      "eval_steps_per_second": 81.0,
      "step": 1
    },
    {
      "epoch": 0.0011154489682097045,
      "grad_norm": 1.2054715156555176,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 6.8914,
      "step": 2
    },
    {
      "epoch": 0.0016731734523145567,
      "grad_norm": 1.172521948814392,
      "learning_rate": 5.000000000000001e-07,
      "loss": 6.8961,
      "step": 3
    },
    {
      "epoch": 0.002230897936419409,
      "grad_norm": 1.3185895681381226,
      "learning_rate": 6.666666666666667e-07,
      "loss": 6.8916,
      "step": 4
    },
    {
      "epoch": 0.002788622420524261,
      "grad_norm": 1.3175787925720215,
      "learning_rate": 8.333333333333333e-07,
      "loss": 6.8673,
      "step": 5
    },
    {
      "epoch": 0.0033463469046291134,
      "grad_norm": 1.266465425491333,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 6.9026,
      "step": 6
    },
    {
      "epoch": 0.0039040713887339654,
      "grad_norm": 1.2903831005096436,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 6.9088,
      "step": 7
    },
    {
      "epoch": 0.004461795872838818,
      "grad_norm": 1.183057188987732,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 6.9319,
      "step": 8
    },
    {
      "epoch": 0.0050195203569436695,
      "grad_norm": 1.2220574617385864,
      "learning_rate": 1.5e-06,
      "loss": 6.9068,
      "step": 9
    },
    {
      "epoch": 0.005577244841048522,
      "grad_norm": 1.307094931602478,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 6.9001,
      "step": 10
    },
    {
      "epoch": 0.006134969325153374,
      "grad_norm": 1.2071970701217651,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 6.9041,
      "step": 11
    },
    {
      "epoch": 0.006692693809258227,
      "grad_norm": 1.1765486001968384,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 6.9127,
      "step": 12
    },
    {
      "epoch": 0.007250418293363078,
      "grad_norm": 1.1002272367477417,
      "learning_rate": 2.166666666666667e-06,
      "loss": 6.9324,
      "step": 13
    },
    {
      "epoch": 0.007808142777467931,
      "grad_norm": 1.2149229049682617,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 6.8805,
      "step": 14
    },
    {
      "epoch": 0.008365867261572783,
      "grad_norm": 1.232237696647644,
      "learning_rate": 2.5e-06,
      "loss": 6.9344,
      "step": 15
    },
    {
      "epoch": 0.008923591745677636,
      "grad_norm": 1.1563347578048706,
      "learning_rate": 2.666666666666667e-06,
      "loss": 6.8986,
      "step": 16
    },
    {
      "epoch": 0.009481316229782488,
      "grad_norm": 1.2460788488388062,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 6.9116,
      "step": 17
    },
    {
      "epoch": 0.010039040713887339,
      "grad_norm": 1.180173397064209,
      "learning_rate": 3e-06,
      "loss": 6.9119,
      "step": 18
    },
    {
      "epoch": 0.010596765197992191,
      "grad_norm": 1.2515779733657837,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 6.9471,
      "step": 19
    },
    {
      "epoch": 0.011154489682097044,
      "grad_norm": 1.133918046951294,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 6.9301,
      "step": 20
    },
    {
      "epoch": 0.011712214166201896,
      "grad_norm": 1.1963660717010498,
      "learning_rate": 3.5e-06,
      "loss": 6.9094,
      "step": 21
    },
    {
      "epoch": 0.012269938650306749,
      "grad_norm": 1.3270220756530762,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 6.8549,
      "step": 22
    },
    {
      "epoch": 0.012827663134411601,
      "grad_norm": 1.4715845584869385,
      "learning_rate": 3.833333333333334e-06,
      "loss": 6.9374,
      "step": 23
    },
    {
      "epoch": 0.013385387618516454,
      "grad_norm": 1.323679804801941,
      "learning_rate": 4.000000000000001e-06,
      "loss": 6.8936,
      "step": 24
    },
    {
      "epoch": 0.013943112102621304,
      "grad_norm": 1.0861523151397705,
      "learning_rate": 4.166666666666667e-06,
      "loss": 6.8981,
      "step": 25
    },
    {
      "epoch": 0.014500836586726157,
      "grad_norm": 1.2198395729064941,
      "learning_rate": 4.333333333333334e-06,
      "loss": 6.908,
      "step": 26
    },
    {
      "epoch": 0.01505856107083101,
      "grad_norm": 1.326386570930481,
      "learning_rate": 4.5e-06,
      "loss": 6.8783,
      "step": 27
    },
    {
      "epoch": 0.015616285554935862,
      "grad_norm": 1.2358511686325073,
      "learning_rate": 4.666666666666667e-06,
      "loss": 6.8833,
      "step": 28
    },
    {
      "epoch": 0.016174010039040714,
      "grad_norm": 1.0934771299362183,
      "learning_rate": 4.833333333333333e-06,
      "loss": 6.8939,
      "step": 29
    },
    {
      "epoch": 0.016731734523145567,
      "grad_norm": 1.1865074634552002,
      "learning_rate": 5e-06,
      "loss": 6.8829,
      "step": 30
    },
    {
      "epoch": 0.01728945900725042,
      "grad_norm": 1.1520872116088867,
      "learning_rate": 4.997482666353287e-06,
      "loss": 6.8988,
      "step": 31
    },
    {
      "epoch": 0.01784718349135527,
      "grad_norm": 1.1283820867538452,
      "learning_rate": 4.989935734988098e-06,
      "loss": 6.8907,
      "step": 32
    },
    {
      "epoch": 0.018404907975460124,
      "grad_norm": 1.151915431022644,
      "learning_rate": 4.977374404419838e-06,
      "loss": 6.8797,
      "step": 33
    },
    {
      "epoch": 0.018962632459564976,
      "grad_norm": 1.461426019668579,
      "learning_rate": 4.959823971496575e-06,
      "loss": 6.862,
      "step": 34
    },
    {
      "epoch": 0.019520356943669825,
      "grad_norm": 1.144579529762268,
      "learning_rate": 4.937319780454559e-06,
      "loss": 6.8864,
      "step": 35
    },
    {
      "epoch": 0.020078081427774678,
      "grad_norm": 1.2476716041564941,
      "learning_rate": 4.909907151739634e-06,
      "loss": 6.8603,
      "step": 36
    },
    {
      "epoch": 0.02063580591187953,
      "grad_norm": 1.1065360307693481,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 6.9067,
      "step": 37
    },
    {
      "epoch": 0.021193530395984383,
      "grad_norm": 1.202126145362854,
      "learning_rate": 4.8405871765993435e-06,
      "loss": 6.8714,
      "step": 38
    },
    {
      "epoch": 0.021751254880089235,
      "grad_norm": 1.2402465343475342,
      "learning_rate": 4.7988194313786275e-06,
      "loss": 6.8746,
      "step": 39
    },
    {
      "epoch": 0.022308979364194088,
      "grad_norm": 1.1461961269378662,
      "learning_rate": 4.752422169756048e-06,
      "loss": 6.8697,
      "step": 40
    },
    {
      "epoch": 0.02286670384829894,
      "grad_norm": 1.0722788572311401,
      "learning_rate": 4.701488829641845e-06,
      "loss": 6.9187,
      "step": 41
    },
    {
      "epoch": 0.023424428332403793,
      "grad_norm": 1.1811214685440063,
      "learning_rate": 4.646121984004666e-06,
      "loss": 6.8951,
      "step": 42
    },
    {
      "epoch": 0.023982152816508645,
      "grad_norm": 1.223608374595642,
      "learning_rate": 4.586433134303257e-06,
      "loss": 6.8677,
      "step": 43
    },
    {
      "epoch": 0.024539877300613498,
      "grad_norm": 1.1935073137283325,
      "learning_rate": 4.522542485937369e-06,
      "loss": 6.8941,
      "step": 44
    },
    {
      "epoch": 0.02509760178471835,
      "grad_norm": 1.3408180475234985,
      "learning_rate": 4.454578706170075e-06,
      "loss": 6.8736,
      "step": 45
    },
    {
      "epoch": 0.025655326268823202,
      "grad_norm": 1.1312620639801025,
      "learning_rate": 4.382678665009028e-06,
      "loss": 6.9068,
      "step": 46
    },
    {
      "epoch": 0.026213050752928055,
      "grad_norm": 1.2290675640106201,
      "learning_rate": 4.3069871595684795e-06,
      "loss": 6.89,
      "step": 47
    },
    {
      "epoch": 0.026770775237032907,
      "grad_norm": 1.1970597505569458,
      "learning_rate": 4.227656622467162e-06,
      "loss": 6.8816,
      "step": 48
    },
    {
      "epoch": 0.027328499721137756,
      "grad_norm": 1.205733060836792,
      "learning_rate": 4.144846814849282e-06,
      "loss": 6.8779,
      "step": 49
    },
    {
      "epoch": 0.02788622420524261,
      "grad_norm": 1.2369530200958252,
      "learning_rate": 4.058724504646834e-06,
      "loss": 6.8724,
      "step": 50
    },
    {
      "epoch": 0.02788622420524261,
      "eval_loss": 6.892075061798096,
      "eval_runtime": 0.7691,
      "eval_samples_per_second": 981.686,
      "eval_steps_per_second": 123.523,
      "step": 50
    },
    {
      "epoch": 0.02844394868934746,
      "grad_norm": 1.3323776721954346,
      "learning_rate": 3.969463130731183e-06,
      "loss": 6.9062,
      "step": 51
    },
    {
      "epoch": 0.029001673173452314,
      "grad_norm": 1.254181981086731,
      "learning_rate": 3.8772424536302565e-06,
      "loss": 6.9008,
      "step": 52
    },
    {
      "epoch": 0.029559397657557166,
      "grad_norm": 1.3206740617752075,
      "learning_rate": 3.782248193514766e-06,
      "loss": 6.9099,
      "step": 53
    },
    {
      "epoch": 0.03011712214166202,
      "grad_norm": 1.2332712411880493,
      "learning_rate": 3.684671656182497e-06,
      "loss": 6.8927,
      "step": 54
    },
    {
      "epoch": 0.03067484662576687,
      "grad_norm": 1.178006649017334,
      "learning_rate": 3.5847093477938955e-06,
      "loss": 6.9219,
      "step": 55
    },
    {
      "epoch": 0.031232571109871723,
      "grad_norm": 1.13715660572052,
      "learning_rate": 3.4825625791348093e-06,
      "loss": 6.9068,
      "step": 56
    },
    {
      "epoch": 0.03179029559397657,
      "grad_norm": 1.5851024389266968,
      "learning_rate": 3.3784370602033572e-06,
      "loss": 6.8539,
      "step": 57
    },
    {
      "epoch": 0.03234802007808143,
      "grad_norm": 1.1820706129074097,
      "learning_rate": 3.272542485937369e-06,
      "loss": 6.875,
      "step": 58
    },
    {
      "epoch": 0.03290574456218628,
      "grad_norm": 1.1604312658309937,
      "learning_rate": 3.165092113916688e-06,
      "loss": 6.8862,
      "step": 59
    },
    {
      "epoch": 0.03346346904629113,
      "grad_norm": 1.1780774593353271,
      "learning_rate": 3.056302334890786e-06,
      "loss": 6.8984,
      "step": 60
    },
    {
      "epoch": 0.03402119353039598,
      "grad_norm": 1.1557505130767822,
      "learning_rate": 2.946392236996592e-06,
      "loss": 6.8954,
      "step": 61
    },
    {
      "epoch": 0.03457891801450084,
      "grad_norm": 1.1038789749145508,
      "learning_rate": 2.835583164544139e-06,
      "loss": 6.9242,
      "step": 62
    },
    {
      "epoch": 0.03513664249860569,
      "grad_norm": 1.0958284139633179,
      "learning_rate": 2.724098272258584e-06,
      "loss": 6.8882,
      "step": 63
    },
    {
      "epoch": 0.03569436698271054,
      "grad_norm": 1.1988102197647095,
      "learning_rate": 2.6121620758762877e-06,
      "loss": 6.8943,
      "step": 64
    },
    {
      "epoch": 0.03625209146681539,
      "grad_norm": 1.1466842889785767,
      "learning_rate": 2.5e-06,
      "loss": 6.909,
      "step": 65
    },
    {
      "epoch": 0.03680981595092025,
      "grad_norm": 1.2120569944381714,
      "learning_rate": 2.3878379241237136e-06,
      "loss": 6.8626,
      "step": 66
    },
    {
      "epoch": 0.0373675404350251,
      "grad_norm": 1.3618991374969482,
      "learning_rate": 2.2759017277414165e-06,
      "loss": 6.8536,
      "step": 67
    },
    {
      "epoch": 0.03792526491912995,
      "grad_norm": 1.167353868484497,
      "learning_rate": 2.1644168354558623e-06,
      "loss": 6.8796,
      "step": 68
    },
    {
      "epoch": 0.0384829894032348,
      "grad_norm": 1.0730359554290771,
      "learning_rate": 2.053607763003409e-06,
      "loss": 6.8989,
      "step": 69
    },
    {
      "epoch": 0.03904071388733965,
      "grad_norm": 1.1657218933105469,
      "learning_rate": 1.9436976651092143e-06,
      "loss": 6.8913,
      "step": 70
    },
    {
      "epoch": 0.03959843837144451,
      "grad_norm": 1.233559489250183,
      "learning_rate": 1.8349078860833125e-06,
      "loss": 6.8623,
      "step": 71
    },
    {
      "epoch": 0.040156162855549356,
      "grad_norm": 1.4005221128463745,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 6.8556,
      "step": 72
    },
    {
      "epoch": 0.04071388733965421,
      "grad_norm": 1.0714030265808105,
      "learning_rate": 1.6215629397966432e-06,
      "loss": 6.9189,
      "step": 73
    },
    {
      "epoch": 0.04127161182375906,
      "grad_norm": 1.1474922895431519,
      "learning_rate": 1.5174374208651913e-06,
      "loss": 6.8716,
      "step": 74
    },
    {
      "epoch": 0.04182933630786392,
      "grad_norm": 1.104048728942871,
      "learning_rate": 1.415290652206105e-06,
      "loss": 6.8646,
      "step": 75
    },
    {
      "epoch": 0.042387060791968766,
      "grad_norm": 1.1361018419265747,
      "learning_rate": 1.3153283438175036e-06,
      "loss": 6.8972,
      "step": 76
    },
    {
      "epoch": 0.04294478527607362,
      "grad_norm": 1.131973385810852,
      "learning_rate": 1.217751806485235e-06,
      "loss": 6.9103,
      "step": 77
    },
    {
      "epoch": 0.04350250976017847,
      "grad_norm": 1.4930802583694458,
      "learning_rate": 1.122757546369744e-06,
      "loss": 6.858,
      "step": 78
    },
    {
      "epoch": 0.044060234244283326,
      "grad_norm": 1.213676929473877,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 6.871,
      "step": 79
    },
    {
      "epoch": 0.044617958728388175,
      "grad_norm": 1.1692030429840088,
      "learning_rate": 9.412754953531664e-07,
      "loss": 6.8811,
      "step": 80
    },
    {
      "epoch": 0.04517568321249303,
      "grad_norm": 1.1697320938110352,
      "learning_rate": 8.551531851507186e-07,
      "loss": 6.8768,
      "step": 81
    },
    {
      "epoch": 0.04573340769659788,
      "grad_norm": 1.1767263412475586,
      "learning_rate": 7.723433775328385e-07,
      "loss": 6.8627,
      "step": 82
    },
    {
      "epoch": 0.046291132180702736,
      "grad_norm": 1.1124926805496216,
      "learning_rate": 6.930128404315214e-07,
      "loss": 6.8774,
      "step": 83
    },
    {
      "epoch": 0.046848856664807585,
      "grad_norm": 1.352464199066162,
      "learning_rate": 6.17321334990973e-07,
      "loss": 6.8597,
      "step": 84
    },
    {
      "epoch": 0.047406581148912434,
      "grad_norm": 1.3012317419052124,
      "learning_rate": 5.454212938299256e-07,
      "loss": 6.8635,
      "step": 85
    },
    {
      "epoch": 0.04796430563301729,
      "grad_norm": 1.2052788734436035,
      "learning_rate": 4.774575140626317e-07,
      "loss": 6.8514,
      "step": 86
    },
    {
      "epoch": 0.04852203011712214,
      "grad_norm": 1.200753927230835,
      "learning_rate": 4.1356686569674344e-07,
      "loss": 6.8585,
      "step": 87
    },
    {
      "epoch": 0.049079754601226995,
      "grad_norm": 1.3905110359191895,
      "learning_rate": 3.538780159953348e-07,
      "loss": 6.8852,
      "step": 88
    },
    {
      "epoch": 0.049637479085331844,
      "grad_norm": 1.1501882076263428,
      "learning_rate": 2.98511170358155e-07,
      "loss": 6.87,
      "step": 89
    },
    {
      "epoch": 0.0501952035694367,
      "grad_norm": 1.4343775510787964,
      "learning_rate": 2.4757783024395244e-07,
      "loss": 6.8603,
      "step": 90
    },
    {
      "epoch": 0.05075292805354155,
      "grad_norm": 1.1068586111068726,
      "learning_rate": 2.0118056862137358e-07,
      "loss": 6.9276,
      "step": 91
    },
    {
      "epoch": 0.051310652537646405,
      "grad_norm": 1.2128379344940186,
      "learning_rate": 1.59412823400657e-07,
      "loss": 6.891,
      "step": 92
    },
    {
      "epoch": 0.051868377021751254,
      "grad_norm": 1.271918535232544,
      "learning_rate": 1.223587092621162e-07,
      "loss": 6.8973,
      "step": 93
    },
    {
      "epoch": 0.05242610150585611,
      "grad_norm": 1.1704728603363037,
      "learning_rate": 9.00928482603669e-08,
      "loss": 6.8768,
      "step": 94
    },
    {
      "epoch": 0.05298382598996096,
      "grad_norm": 1.1624881029129028,
      "learning_rate": 6.268021954544095e-08,
      "loss": 6.8773,
      "step": 95
    },
    {
      "epoch": 0.053541550474065815,
      "grad_norm": 1.1013178825378418,
      "learning_rate": 4.017602850342584e-08,
      "loss": 6.8871,
      "step": 96
    },
    {
      "epoch": 0.054099274958170664,
      "grad_norm": 1.1644474267959595,
      "learning_rate": 2.262559558016325e-08,
      "loss": 6.9111,
      "step": 97
    },
    {
      "epoch": 0.05465699944227551,
      "grad_norm": 1.0760912895202637,
      "learning_rate": 1.006426501190233e-08,
      "loss": 6.8965,
      "step": 98
    },
    {
      "epoch": 0.05521472392638037,
      "grad_norm": 1.120246171951294,
      "learning_rate": 2.5173336467135266e-09,
      "loss": 6.8703,
      "step": 99
    },
    {
      "epoch": 0.05577244841048522,
      "grad_norm": 1.1762772798538208,
      "learning_rate": 0.0,
      "loss": 6.8797,
      "step": 100
    },
    {
      "epoch": 0.05577244841048522,
      "eval_loss": 6.889637470245361,
      "eval_runtime": 0.787,
      "eval_samples_per_second": 959.313,
      "eval_steps_per_second": 120.708,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 263666073600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}