{
  "best_metric": 0.6744453310966492,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.016511186328737718,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001651118632873772,
      "grad_norm": 0.6025562286376953,
      "learning_rate": 2e-05,
      "loss": 0.8633,
      "step": 1
    },
    {
      "epoch": 0.0001651118632873772,
      "eval_loss": 0.953804612159729,
      "eval_runtime": 831.0169,
      "eval_samples_per_second": 7.213,
      "eval_steps_per_second": 1.804,
      "step": 1
    },
    {
      "epoch": 0.0003302237265747544,
      "grad_norm": 0.6425795555114746,
      "learning_rate": 4e-05,
      "loss": 0.9543,
      "step": 2
    },
    {
      "epoch": 0.0004953355898621316,
      "grad_norm": 0.5645630955696106,
      "learning_rate": 6e-05,
      "loss": 0.8123,
      "step": 3
    },
    {
      "epoch": 0.0006604474531495088,
      "grad_norm": 0.5715195536613464,
      "learning_rate": 8e-05,
      "loss": 0.9324,
      "step": 4
    },
    {
      "epoch": 0.000825559316436886,
      "grad_norm": 0.5616925954818726,
      "learning_rate": 0.0001,
      "loss": 0.9792,
      "step": 5
    },
    {
      "epoch": 0.0009906711797242633,
      "grad_norm": 0.4393025040626526,
      "learning_rate": 0.00012,
      "loss": 0.8852,
      "step": 6
    },
    {
      "epoch": 0.0011557830430116403,
      "grad_norm": 0.4828271269798279,
      "learning_rate": 0.00014,
      "loss": 0.8654,
      "step": 7
    },
    {
      "epoch": 0.0013208949062990176,
      "grad_norm": 0.633884608745575,
      "learning_rate": 0.00016,
      "loss": 0.9406,
      "step": 8
    },
    {
      "epoch": 0.0014860067695863948,
      "grad_norm": 0.626456618309021,
      "learning_rate": 0.00018,
      "loss": 0.8317,
      "step": 9
    },
    {
      "epoch": 0.001651118632873772,
      "grad_norm": 0.4569125473499298,
      "learning_rate": 0.0002,
      "loss": 0.7754,
      "step": 10
    },
    {
      "epoch": 0.0018162304961611491,
      "grad_norm": 0.4024462103843689,
      "learning_rate": 0.00019999535665248002,
      "loss": 0.8435,
      "step": 11
    },
    {
      "epoch": 0.0019813423594485266,
      "grad_norm": 0.3451145887374878,
      "learning_rate": 0.0001999814270411335,
      "loss": 0.7137,
      "step": 12
    },
    {
      "epoch": 0.0021464542227359034,
      "grad_norm": 0.33148011565208435,
      "learning_rate": 0.000199958212459561,
      "loss": 0.7715,
      "step": 13
    },
    {
      "epoch": 0.0023115660860232807,
      "grad_norm": 0.34364211559295654,
      "learning_rate": 0.00019992571506363,
      "loss": 0.8241,
      "step": 14
    },
    {
      "epoch": 0.002476677949310658,
      "grad_norm": 0.32813310623168945,
      "learning_rate": 0.00019988393787127441,
      "loss": 0.7905,
      "step": 15
    },
    {
      "epoch": 0.002641789812598035,
      "grad_norm": 0.35355880856513977,
      "learning_rate": 0.0001998328847622148,
      "loss": 0.7944,
      "step": 16
    },
    {
      "epoch": 0.0028069016758854124,
      "grad_norm": 0.32826319336891174,
      "learning_rate": 0.00019977256047759765,
      "loss": 0.7636,
      "step": 17
    },
    {
      "epoch": 0.0029720135391727897,
      "grad_norm": 0.3257204294204712,
      "learning_rate": 0.00019970297061955533,
      "loss": 0.7244,
      "step": 18
    },
    {
      "epoch": 0.003137125402460167,
      "grad_norm": 0.3375376760959625,
      "learning_rate": 0.00019962412165068573,
      "loss": 0.714,
      "step": 19
    },
    {
      "epoch": 0.003302237265747544,
      "grad_norm": 0.3384173810482025,
      "learning_rate": 0.00019953602089345217,
      "loss": 0.7644,
      "step": 20
    },
    {
      "epoch": 0.003467349129034921,
      "grad_norm": 0.2862045466899872,
      "learning_rate": 0.0001994386765295032,
      "loss": 0.7,
      "step": 21
    },
    {
      "epoch": 0.0036324609923222982,
      "grad_norm": 0.3143760859966278,
      "learning_rate": 0.00019933209759891317,
      "loss": 0.7111,
      "step": 22
    },
    {
      "epoch": 0.0037975728556096755,
      "grad_norm": 0.2990686297416687,
      "learning_rate": 0.00019921629399934223,
      "loss": 0.6409,
      "step": 23
    },
    {
      "epoch": 0.003962684718897053,
      "grad_norm": 0.3404158055782318,
      "learning_rate": 0.00019909127648511755,
      "loss": 0.7219,
      "step": 24
    },
    {
      "epoch": 0.0041277965821844296,
      "grad_norm": 0.3198144733905792,
      "learning_rate": 0.0001989570566662345,
      "loss": 0.6811,
      "step": 25
    },
    {
      "epoch": 0.004292908445471807,
      "grad_norm": 0.3477422297000885,
      "learning_rate": 0.00019881364700727823,
      "loss": 0.7442,
      "step": 26
    },
    {
      "epoch": 0.004458020308759184,
      "grad_norm": 0.3631756007671356,
      "learning_rate": 0.0001986610608262665,
      "loss": 0.8221,
      "step": 27
    },
    {
      "epoch": 0.004623132172046561,
      "grad_norm": 0.32080984115600586,
      "learning_rate": 0.00019849931229341258,
      "loss": 0.6626,
      "step": 28
    },
    {
      "epoch": 0.0047882440353339386,
      "grad_norm": 0.3251453936100006,
      "learning_rate": 0.00019832841642980945,
      "loss": 0.7156,
      "step": 29
    },
    {
      "epoch": 0.004953355898621316,
      "grad_norm": 0.3476259112358093,
      "learning_rate": 0.00019814838910603481,
      "loss": 0.7087,
      "step": 30
    },
    {
      "epoch": 0.005118467761908693,
      "grad_norm": 0.2831595242023468,
      "learning_rate": 0.00019795924704067721,
      "loss": 0.5912,
      "step": 31
    },
    {
      "epoch": 0.00528357962519607,
      "grad_norm": 0.3411269783973694,
      "learning_rate": 0.00019776100779878345,
      "loss": 0.7125,
      "step": 32
    },
    {
      "epoch": 0.0054486914884834476,
      "grad_norm": 0.35447773337364197,
      "learning_rate": 0.00019755368979022732,
      "loss": 0.7567,
      "step": 33
    },
    {
      "epoch": 0.005613803351770825,
      "grad_norm": 0.32824215292930603,
      "learning_rate": 0.00019733731226800015,
      "loss": 0.7238,
      "step": 34
    },
    {
      "epoch": 0.005778915215058202,
      "grad_norm": 0.3237905204296112,
      "learning_rate": 0.00019711189532642243,
      "loss": 0.7055,
      "step": 35
    },
    {
      "epoch": 0.005944027078345579,
      "grad_norm": 0.3332991898059845,
      "learning_rate": 0.00019687745989927823,
      "loss": 0.7217,
      "step": 36
    },
    {
      "epoch": 0.006109138941632957,
      "grad_norm": 0.3003871738910675,
      "learning_rate": 0.00019663402775787066,
      "loss": 0.7078,
      "step": 37
    },
    {
      "epoch": 0.006274250804920334,
      "grad_norm": 0.31166723370552063,
      "learning_rate": 0.00019638162150900027,
      "loss": 0.674,
      "step": 38
    },
    {
      "epoch": 0.006439362668207711,
      "grad_norm": 0.31454190611839294,
      "learning_rate": 0.00019612026459286578,
      "loss": 0.631,
      "step": 39
    },
    {
      "epoch": 0.006604474531495088,
      "grad_norm": 0.2961897552013397,
      "learning_rate": 0.00019584998128088684,
      "loss": 0.6135,
      "step": 40
    },
    {
      "epoch": 0.006769586394782465,
      "grad_norm": 0.31604376435279846,
      "learning_rate": 0.0001955707966734505,
      "loss": 0.6517,
      "step": 41
    },
    {
      "epoch": 0.006934698258069842,
      "grad_norm": 0.3436253070831299,
      "learning_rate": 0.00019528273669757972,
      "loss": 0.7957,
      "step": 42
    },
    {
      "epoch": 0.007099810121357219,
      "grad_norm": 0.3258967399597168,
      "learning_rate": 0.0001949858281045261,
      "loss": 0.7068,
      "step": 43
    },
    {
      "epoch": 0.0072649219846445965,
      "grad_norm": 0.3063102066516876,
      "learning_rate": 0.00019468009846728513,
      "loss": 0.6734,
      "step": 44
    },
    {
      "epoch": 0.007430033847931974,
      "grad_norm": 0.32180124521255493,
      "learning_rate": 0.00019436557617803595,
      "loss": 0.7536,
      "step": 45
    },
    {
      "epoch": 0.007595145711219351,
      "grad_norm": 0.31712058186531067,
      "learning_rate": 0.00019404229044550433,
      "loss": 0.7201,
      "step": 46
    },
    {
      "epoch": 0.007760257574506728,
      "grad_norm": 0.2951134145259857,
      "learning_rate": 0.00019371027129225042,
      "loss": 0.62,
      "step": 47
    },
    {
      "epoch": 0.007925369437794106,
      "grad_norm": 0.30386847257614136,
      "learning_rate": 0.0001933695495518804,
      "loss": 0.6752,
      "step": 48
    },
    {
      "epoch": 0.008090481301081483,
      "grad_norm": 0.3203580677509308,
      "learning_rate": 0.00019302015686618326,
      "loss": 0.6805,
      "step": 49
    },
    {
      "epoch": 0.008255593164368859,
      "grad_norm": 0.2829570174217224,
      "learning_rate": 0.0001926621256821922,
      "loss": 0.5785,
      "step": 50
    },
    {
      "epoch": 0.008420705027656237,
      "grad_norm": 0.3065510094165802,
      "learning_rate": 0.00019229548924917146,
      "loss": 0.6573,
      "step": 51
    },
    {
      "epoch": 0.008585816890943614,
      "grad_norm": 0.36454063653945923,
      "learning_rate": 0.00019192028161552847,
      "loss": 0.7931,
      "step": 52
    },
    {
      "epoch": 0.008750928754230992,
      "grad_norm": 0.31599584221839905,
      "learning_rate": 0.0001915365376256519,
      "loss": 0.7019,
      "step": 53
    },
    {
      "epoch": 0.008916040617518368,
      "grad_norm": 0.3125596046447754,
      "learning_rate": 0.00019114429291667583,
      "loss": 0.6634,
      "step": 54
    },
    {
      "epoch": 0.009081152480805746,
      "grad_norm": 0.3362664580345154,
      "learning_rate": 0.00019074358391517023,
      "loss": 0.7445,
      "step": 55
    },
    {
      "epoch": 0.009246264344093123,
      "grad_norm": 0.3391803801059723,
      "learning_rate": 0.00019033444783375804,
      "loss": 0.7809,
      "step": 56
    },
    {
      "epoch": 0.0094113762073805,
      "grad_norm": 0.3022312819957733,
      "learning_rate": 0.00018991692266765947,
      "loss": 0.6743,
      "step": 57
    },
    {
      "epoch": 0.009576488070667877,
      "grad_norm": 0.30301007628440857,
      "learning_rate": 0.00018949104719116332,
      "loss": 0.6472,
      "step": 58
    },
    {
      "epoch": 0.009741599933955255,
      "grad_norm": 0.3142068386077881,
      "learning_rate": 0.00018905686095402647,
      "loss": 0.6656,
      "step": 59
    },
    {
      "epoch": 0.009906711797242632,
      "grad_norm": 0.2799323797225952,
      "learning_rate": 0.0001886144042778006,
      "loss": 0.6186,
      "step": 60
    },
    {
      "epoch": 0.01007182366053001,
      "grad_norm": 0.33195391297340393,
      "learning_rate": 0.00018816371825208789,
      "loss": 0.7365,
      "step": 61
    },
    {
      "epoch": 0.010236935523817386,
      "grad_norm": 0.2870056927204132,
      "learning_rate": 0.0001877048447307252,
      "loss": 0.6195,
      "step": 62
    },
    {
      "epoch": 0.010402047387104764,
      "grad_norm": 0.2942243218421936,
      "learning_rate": 0.00018723782632789701,
      "loss": 0.6346,
      "step": 63
    },
    {
      "epoch": 0.01056715925039214,
      "grad_norm": 0.36610937118530273,
      "learning_rate": 0.00018676270641417822,
      "loss": 0.7423,
      "step": 64
    },
    {
      "epoch": 0.010732271113679517,
      "grad_norm": 0.32092538475990295,
      "learning_rate": 0.0001862795291125063,
      "loss": 0.6371,
      "step": 65
    },
    {
      "epoch": 0.010897382976966895,
      "grad_norm": 0.2960004508495331,
      "learning_rate": 0.0001857883392940837,
      "loss": 0.5923,
      "step": 66
    },
    {
      "epoch": 0.011062494840254272,
      "grad_norm": 0.3343415856361389,
      "learning_rate": 0.000185289182574211,
      "loss": 0.6983,
      "step": 67
    },
    {
      "epoch": 0.01122760670354165,
      "grad_norm": 0.3269459903240204,
      "learning_rate": 0.0001847821053080505,
      "loss": 0.7298,
      "step": 68
    },
    {
      "epoch": 0.011392718566829026,
      "grad_norm": 0.29574498534202576,
      "learning_rate": 0.00018426715458632153,
      "loss": 0.6434,
      "step": 69
    },
    {
      "epoch": 0.011557830430116404,
      "grad_norm": 0.2938220202922821,
      "learning_rate": 0.00018374437823092724,
      "loss": 0.6383,
      "step": 70
    },
    {
      "epoch": 0.01172294229340378,
      "grad_norm": 0.3147146999835968,
      "learning_rate": 0.00018321382479051347,
      "loss": 0.6643,
      "step": 71
    },
    {
      "epoch": 0.011888054156691159,
      "grad_norm": 0.3595152497291565,
      "learning_rate": 0.00018267554353596025,
      "loss": 0.7867,
      "step": 72
    },
    {
      "epoch": 0.012053166019978535,
      "grad_norm": 0.32271626591682434,
      "learning_rate": 0.0001821295844558062,
      "loss": 0.6786,
      "step": 73
    },
    {
      "epoch": 0.012218277883265913,
      "grad_norm": 0.2905098795890808,
      "learning_rate": 0.0001815759982516061,
      "loss": 0.5966,
      "step": 74
    },
    {
      "epoch": 0.01238338974655329,
      "grad_norm": 0.3641018867492676,
      "learning_rate": 0.00018101483633322255,
      "loss": 0.7708,
      "step": 75
    },
    {
      "epoch": 0.012548501609840668,
      "grad_norm": 0.3200140595436096,
      "learning_rate": 0.00018044615081405153,
      "loss": 0.6035,
      "step": 76
    },
    {
      "epoch": 0.012713613473128044,
      "grad_norm": 0.3007895350456238,
      "learning_rate": 0.00017986999450618295,
      "loss": 0.6379,
      "step": 77
    },
    {
      "epoch": 0.012878725336415422,
      "grad_norm": 0.3379741907119751,
      "learning_rate": 0.00017928642091549613,
      "loss": 0.7315,
      "step": 78
    },
    {
      "epoch": 0.013043837199702799,
      "grad_norm": 0.2804384231567383,
      "learning_rate": 0.00017869548423669077,
      "loss": 0.5894,
      "step": 79
    },
    {
      "epoch": 0.013208949062990177,
      "grad_norm": 0.3281707465648651,
      "learning_rate": 0.00017809723934825405,
      "loss": 0.6707,
      "step": 80
    },
    {
      "epoch": 0.013374060926277553,
      "grad_norm": 0.28626206517219543,
      "learning_rate": 0.00017749174180736442,
      "loss": 0.5444,
      "step": 81
    },
    {
      "epoch": 0.01353917278956493,
      "grad_norm": 0.34358954429626465,
      "learning_rate": 0.00017687904784473188,
      "loss": 0.7219,
      "step": 82
    },
    {
      "epoch": 0.013704284652852308,
      "grad_norm": 0.33361655473709106,
      "learning_rate": 0.00017625921435937637,
      "loss": 0.663,
      "step": 83
    },
    {
      "epoch": 0.013869396516139684,
      "grad_norm": 0.38789382576942444,
      "learning_rate": 0.00017563229891334338,
      "loss": 0.7912,
      "step": 84
    },
    {
      "epoch": 0.014034508379427062,
      "grad_norm": 0.32810458540916443,
      "learning_rate": 0.00017499835972635856,
      "loss": 0.6905,
      "step": 85
    },
    {
      "epoch": 0.014199620242714438,
      "grad_norm": 0.3457249701023102,
      "learning_rate": 0.00017435745567042095,
      "loss": 0.6821,
      "step": 86
    },
    {
      "epoch": 0.014364732106001817,
      "grad_norm": 0.3237375020980835,
      "learning_rate": 0.00017370964626433567,
      "loss": 0.6797,
      "step": 87
    },
    {
      "epoch": 0.014529843969289193,
      "grad_norm": 0.3508392572402954,
      "learning_rate": 0.0001730549916681868,
      "loss": 0.6382,
      "step": 88
    },
    {
      "epoch": 0.014694955832576571,
      "grad_norm": 0.3452267348766327,
      "learning_rate": 0.00017239355267775018,
      "loss": 0.6762,
      "step": 89
    },
    {
      "epoch": 0.014860067695863947,
      "grad_norm": 0.318096399307251,
      "learning_rate": 0.0001717253907188477,
      "loss": 0.6225,
      "step": 90
    },
    {
      "epoch": 0.015025179559151326,
      "grad_norm": 0.32376089692115784,
      "learning_rate": 0.00017105056784164294,
      "loss": 0.6575,
      "step": 91
    },
    {
      "epoch": 0.015190291422438702,
      "grad_norm": 0.2974165678024292,
      "learning_rate": 0.00017036914671487852,
      "loss": 0.5908,
      "step": 92
    },
    {
      "epoch": 0.01535540328572608,
      "grad_norm": 0.2842133343219757,
      "learning_rate": 0.00016968119062005642,
      "loss": 0.5888,
      "step": 93
    },
    {
      "epoch": 0.015520515149013456,
      "grad_norm": 0.3510216474533081,
      "learning_rate": 0.00016898676344556118,
      "loss": 0.7047,
      "step": 94
    },
    {
      "epoch": 0.015685627012300835,
      "grad_norm": 0.33503997325897217,
      "learning_rate": 0.00016828592968072678,
      "loss": 0.6951,
      "step": 95
    },
    {
      "epoch": 0.015850738875588213,
      "grad_norm": 0.31613603234291077,
      "learning_rate": 0.00016757875440984768,
      "loss": 0.6436,
      "step": 96
    },
    {
      "epoch": 0.016015850738875587,
      "grad_norm": 0.41182562708854675,
      "learning_rate": 0.0001668653033061347,
      "loss": 0.5818,
      "step": 97
    },
    {
      "epoch": 0.016180962602162965,
      "grad_norm": 0.3742947280406952,
      "learning_rate": 0.00016614564262561608,
      "loss": 0.7527,
      "step": 98
    },
    {
      "epoch": 0.016346074465450344,
      "grad_norm": 0.3371233642101288,
      "learning_rate": 0.0001654198392009846,
      "loss": 0.6411,
      "step": 99
    },
    {
      "epoch": 0.016511186328737718,
      "grad_norm": 0.3669418692588806,
      "learning_rate": 0.0001646879604353908,
      "loss": 0.6869,
      "step": 100
    },
    {
      "epoch": 0.016511186328737718,
      "eval_loss": 0.6744453310966492,
      "eval_runtime": 833.756,
      "eval_samples_per_second": 7.189,
      "eval_steps_per_second": 1.798,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 336,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7337044009641574e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}