{
  "best_metric": 10.301692008972168,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.015877662609593085,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015877662609593086,
      "grad_norm": 0.07810629904270172,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 10.3764,
      "step": 1
    },
    {
      "epoch": 0.00015877662609593086,
      "eval_loss": 10.363986015319824,
      "eval_runtime": 0.0965,
      "eval_samples_per_second": 518.162,
      "eval_steps_per_second": 72.543,
      "step": 1
    },
    {
      "epoch": 0.00031755325219186173,
      "grad_norm": 0.061406999826431274,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 10.3633,
      "step": 2
    },
    {
      "epoch": 0.00047632987828779254,
      "grad_norm": 0.05004843696951866,
      "learning_rate": 8.999999999999999e-05,
      "loss": 10.3681,
      "step": 3
    },
    {
      "epoch": 0.0006351065043837235,
      "grad_norm": 0.05747171863913536,
      "learning_rate": 0.00011999999999999999,
      "loss": 10.3682,
      "step": 4
    },
    {
      "epoch": 0.0007938831304796542,
      "grad_norm": 0.05080826207995415,
      "learning_rate": 0.00015,
      "loss": 10.3647,
      "step": 5
    },
    {
      "epoch": 0.0009526597565755851,
      "grad_norm": 0.046676479279994965,
      "learning_rate": 0.00017999999999999998,
      "loss": 10.3577,
      "step": 6
    },
    {
      "epoch": 0.001111436382671516,
      "grad_norm": 0.046294715255498886,
      "learning_rate": 0.00020999999999999998,
      "loss": 10.366,
      "step": 7
    },
    {
      "epoch": 0.001270213008767447,
      "grad_norm": 0.04639292135834694,
      "learning_rate": 0.00023999999999999998,
      "loss": 10.3691,
      "step": 8
    },
    {
      "epoch": 0.0014289896348633777,
      "grad_norm": 0.04217684268951416,
      "learning_rate": 0.00027,
      "loss": 10.3534,
      "step": 9
    },
    {
      "epoch": 0.0015877662609593084,
      "grad_norm": 0.04545888677239418,
      "learning_rate": 0.0003,
      "loss": 10.3577,
      "step": 10
    },
    {
      "epoch": 0.0017465428870552394,
      "grad_norm": 0.045676153153181076,
      "learning_rate": 0.0002999794957488703,
      "loss": 10.3567,
      "step": 11
    },
    {
      "epoch": 0.0019053195131511701,
      "grad_norm": 0.044181909412145615,
      "learning_rate": 0.0002999179886011389,
      "loss": 10.3612,
      "step": 12
    },
    {
      "epoch": 0.002064096139247101,
      "grad_norm": 0.04575149342417717,
      "learning_rate": 0.0002998154953722457,
      "loss": 10.3539,
      "step": 13
    },
    {
      "epoch": 0.002222872765343032,
      "grad_norm": 0.04331066459417343,
      "learning_rate": 0.00029967204408281613,
      "loss": 10.357,
      "step": 14
    },
    {
      "epoch": 0.002381649391438963,
      "grad_norm": 0.04593302682042122,
      "learning_rate": 0.00029948767395100045,
      "loss": 10.3536,
      "step": 15
    },
    {
      "epoch": 0.002540426017534894,
      "grad_norm": 0.046111367642879486,
      "learning_rate": 0.0002992624353817517,
      "loss": 10.3586,
      "step": 16
    },
    {
      "epoch": 0.0026992026436308244,
      "grad_norm": 0.05106338486075401,
      "learning_rate": 0.0002989963899530457,
      "loss": 10.3551,
      "step": 17
    },
    {
      "epoch": 0.0028579792697267553,
      "grad_norm": 0.052090976387262344,
      "learning_rate": 0.00029868961039904624,
      "loss": 10.3548,
      "step": 18
    },
    {
      "epoch": 0.0030167558958226863,
      "grad_norm": 0.04916371405124664,
      "learning_rate": 0.00029834218059022024,
      "loss": 10.3536,
      "step": 19
    },
    {
      "epoch": 0.003175532521918617,
      "grad_norm": 0.05516723915934563,
      "learning_rate": 0.00029795419551040833,
      "loss": 10.3551,
      "step": 20
    },
    {
      "epoch": 0.003334309148014548,
      "grad_norm": 0.053350552916526794,
      "learning_rate": 0.00029752576123085736,
      "loss": 10.3571,
      "step": 21
    },
    {
      "epoch": 0.003493085774110479,
      "grad_norm": 0.05715618655085564,
      "learning_rate": 0.0002970569948812214,
      "loss": 10.3542,
      "step": 22
    },
    {
      "epoch": 0.0036518624002064098,
      "grad_norm": 0.06765611469745636,
      "learning_rate": 0.0002965480246175399,
      "loss": 10.349,
      "step": 23
    },
    {
      "epoch": 0.0038106390263023403,
      "grad_norm": 0.06198740378022194,
      "learning_rate": 0.0002959989895872009,
      "loss": 10.3561,
      "step": 24
    },
    {
      "epoch": 0.003969415652398271,
      "grad_norm": 0.05947557091712952,
      "learning_rate": 0.0002954100398908995,
      "loss": 10.3525,
      "step": 25
    },
    {
      "epoch": 0.003969415652398271,
      "eval_loss": 10.353515625,
      "eval_runtime": 0.0934,
      "eval_samples_per_second": 535.238,
      "eval_steps_per_second": 74.933,
      "step": 25
    },
    {
      "epoch": 0.004128192278494202,
      "grad_norm": 0.071525439620018,
      "learning_rate": 0.0002947813365416023,
      "loss": 10.3526,
      "step": 26
    },
    {
      "epoch": 0.004286968904590133,
      "grad_norm": 0.07154348492622375,
      "learning_rate": 0.0002941130514205272,
      "loss": 10.3504,
      "step": 27
    },
    {
      "epoch": 0.004445745530686064,
      "grad_norm": 0.06603620201349258,
      "learning_rate": 0.0002934053672301536,
      "loss": 10.3462,
      "step": 28
    },
    {
      "epoch": 0.004604522156781995,
      "grad_norm": 0.07479649782180786,
      "learning_rate": 0.00029265847744427303,
      "loss": 10.3493,
      "step": 29
    },
    {
      "epoch": 0.004763298782877926,
      "grad_norm": 0.0767395943403244,
      "learning_rate": 0.00029187258625509513,
      "loss": 10.349,
      "step": 30
    },
    {
      "epoch": 0.004922075408973856,
      "grad_norm": 0.07685164362192154,
      "learning_rate": 0.00029104790851742417,
      "loss": 10.3495,
      "step": 31
    },
    {
      "epoch": 0.005080852035069788,
      "grad_norm": 0.08169625699520111,
      "learning_rate": 0.0002901846696899191,
      "loss": 10.3573,
      "step": 32
    },
    {
      "epoch": 0.005239628661165718,
      "grad_norm": 0.07723478972911835,
      "learning_rate": 0.00028928310577345606,
      "loss": 10.3489,
      "step": 33
    },
    {
      "epoch": 0.005398405287261649,
      "grad_norm": 0.0714058205485344,
      "learning_rate": 0.0002883434632466077,
      "loss": 10.344,
      "step": 34
    },
    {
      "epoch": 0.00555718191335758,
      "grad_norm": 0.07186929881572723,
      "learning_rate": 0.00028736599899825856,
      "loss": 10.3461,
      "step": 35
    },
    {
      "epoch": 0.005715958539453511,
      "grad_norm": 0.07883802056312561,
      "learning_rate": 0.00028635098025737434,
      "loss": 10.3465,
      "step": 36
    },
    {
      "epoch": 0.005874735165549441,
      "grad_norm": 0.07939917594194412,
      "learning_rate": 0.00028529868451994384,
      "loss": 10.3391,
      "step": 37
    },
    {
      "epoch": 0.006033511791645373,
      "grad_norm": 0.07693421095609665,
      "learning_rate": 0.0002842093994731145,
      "loss": 10.3466,
      "step": 38
    },
    {
      "epoch": 0.006192288417741303,
      "grad_norm": 0.08108057081699371,
      "learning_rate": 0.00028308342291654174,
      "loss": 10.3399,
      "step": 39
    },
    {
      "epoch": 0.006351065043837234,
      "grad_norm": 0.07625582814216614,
      "learning_rate": 0.00028192106268097334,
      "loss": 10.3424,
      "step": 40
    },
    {
      "epoch": 0.006509841669933165,
      "grad_norm": 0.08772553503513336,
      "learning_rate": 0.00028072263654409154,
      "loss": 10.3357,
      "step": 41
    },
    {
      "epoch": 0.006668618296029096,
      "grad_norm": 0.09969928115606308,
      "learning_rate": 0.0002794884721436361,
      "loss": 10.3313,
      "step": 42
    },
    {
      "epoch": 0.006827394922125027,
      "grad_norm": 0.10627187043428421,
      "learning_rate": 0.00027821890688783083,
      "loss": 10.334,
      "step": 43
    },
    {
      "epoch": 0.006986171548220958,
      "grad_norm": 0.11822281032800674,
      "learning_rate": 0.0002769142878631403,
      "loss": 10.3403,
      "step": 44
    },
    {
      "epoch": 0.007144948174316888,
      "grad_norm": 0.13020247220993042,
      "learning_rate": 0.00027557497173937923,
      "loss": 10.3354,
      "step": 45
    },
    {
      "epoch": 0.0073037248004128195,
      "grad_norm": 0.153047114610672,
      "learning_rate": 0.000274201324672203,
      "loss": 10.3254,
      "step": 46
    },
    {
      "epoch": 0.00746250142650875,
      "grad_norm": 0.18278735876083374,
      "learning_rate": 0.00027279372220300385,
      "loss": 10.3353,
      "step": 47
    },
    {
      "epoch": 0.007621278052604681,
      "grad_norm": 0.2163456678390503,
      "learning_rate": 0.0002713525491562421,
      "loss": 10.3213,
      "step": 48
    },
    {
      "epoch": 0.007780054678700612,
      "grad_norm": 0.16671767830848694,
      "learning_rate": 0.00026987819953423867,
      "loss": 10.3174,
      "step": 49
    },
    {
      "epoch": 0.007938831304796543,
      "grad_norm": 0.22391104698181152,
      "learning_rate": 0.00026837107640945905,
      "loss": 10.3147,
      "step": 50
    },
    {
      "epoch": 0.007938831304796543,
      "eval_loss": 10.32917594909668,
      "eval_runtime": 0.0932,
      "eval_samples_per_second": 536.364,
      "eval_steps_per_second": 75.091,
      "step": 50
    },
    {
      "epoch": 0.008097607930892474,
      "grad_norm": 0.1727171391248703,
      "learning_rate": 0.0002668315918143169,
      "loss": 10.3255,
      "step": 51
    },
    {
      "epoch": 0.008256384556988404,
      "grad_norm": 0.1261977106332779,
      "learning_rate": 0.00026526016662852886,
      "loss": 10.3373,
      "step": 52
    },
    {
      "epoch": 0.008415161183084335,
      "grad_norm": 0.19324587285518646,
      "learning_rate": 0.00026365723046405023,
      "loss": 10.3299,
      "step": 53
    },
    {
      "epoch": 0.008573937809180266,
      "grad_norm": 0.16581648588180542,
      "learning_rate": 0.0002620232215476231,
      "loss": 10.3303,
      "step": 54
    },
    {
      "epoch": 0.008732714435276196,
      "grad_norm": 0.16929411888122559,
      "learning_rate": 0.0002603585866009697,
      "loss": 10.3314,
      "step": 55
    },
    {
      "epoch": 0.008891491061372127,
      "grad_norm": 0.14727461338043213,
      "learning_rate": 0.00025866378071866334,
      "loss": 10.3248,
      "step": 56
    },
    {
      "epoch": 0.009050267687468059,
      "grad_norm": 0.1087571531534195,
      "learning_rate": 0.00025693926724370956,
      "loss": 10.325,
      "step": 57
    },
    {
      "epoch": 0.00920904431356399,
      "grad_norm": 0.09721245616674423,
      "learning_rate": 0.00025518551764087326,
      "loss": 10.3173,
      "step": 58
    },
    {
      "epoch": 0.00936782093965992,
      "grad_norm": 0.08206453919410706,
      "learning_rate": 0.00025340301136778483,
      "loss": 10.3209,
      "step": 59
    },
    {
      "epoch": 0.009526597565755851,
      "grad_norm": 0.09024045616388321,
      "learning_rate": 0.00025159223574386114,
      "loss": 10.3219,
      "step": 60
    },
    {
      "epoch": 0.009685374191851783,
      "grad_norm": 0.07984571903944016,
      "learning_rate": 0.0002497536858170772,
      "loss": 10.3224,
      "step": 61
    },
    {
      "epoch": 0.009844150817947712,
      "grad_norm": 0.11346311867237091,
      "learning_rate": 0.00024788786422862526,
      "loss": 10.3194,
      "step": 62
    },
    {
      "epoch": 0.010002927444043644,
      "grad_norm": 0.10196421295404434,
      "learning_rate": 0.00024599528107549745,
      "loss": 10.3233,
      "step": 63
    },
    {
      "epoch": 0.010161704070139575,
      "grad_norm": 0.11686540395021439,
      "learning_rate": 0.00024407645377103054,
      "loss": 10.3199,
      "step": 64
    },
    {
      "epoch": 0.010320480696235505,
      "grad_norm": 0.10796058177947998,
      "learning_rate": 0.00024213190690345018,
      "loss": 10.3213,
      "step": 65
    },
    {
      "epoch": 0.010479257322331436,
      "grad_norm": 0.10543781518936157,
      "learning_rate": 0.00024016217209245374,
      "loss": 10.3191,
      "step": 66
    },
    {
      "epoch": 0.010638033948427368,
      "grad_norm": 0.1500771939754486,
      "learning_rate": 0.00023816778784387094,
      "loss": 10.3217,
      "step": 67
    },
    {
      "epoch": 0.010796810574523297,
      "grad_norm": 0.13386686146259308,
      "learning_rate": 0.0002361492994024415,
      "loss": 10.3224,
      "step": 68
    },
    {
      "epoch": 0.010955587200619229,
      "grad_norm": 0.17342054843902588,
      "learning_rate": 0.0002341072586027509,
      "loss": 10.3188,
      "step": 69
    },
    {
      "epoch": 0.01111436382671516,
      "grad_norm": 0.1327526718378067,
      "learning_rate": 0.00023204222371836405,
      "loss": 10.3154,
      "step": 70
    },
    {
      "epoch": 0.01127314045281109,
      "grad_norm": 0.15230214595794678,
      "learning_rate": 0.00022995475930919905,
      "loss": 10.3179,
      "step": 71
    },
    {
      "epoch": 0.011431917078907021,
      "grad_norm": 0.1093672513961792,
      "learning_rate": 0.00022784543606718227,
      "loss": 10.3217,
      "step": 72
    },
    {
      "epoch": 0.011590693705002953,
      "grad_norm": 0.10216083377599716,
      "learning_rate": 0.00022571483066022657,
      "loss": 10.321,
      "step": 73
    },
    {
      "epoch": 0.011749470331098882,
      "grad_norm": 0.11733946949243546,
      "learning_rate": 0.0002235635255745762,
      "loss": 10.3107,
      "step": 74
    },
    {
      "epoch": 0.011908246957194814,
      "grad_norm": 0.1087634265422821,
      "learning_rate": 0.00022139210895556104,
      "loss": 10.3107,
      "step": 75
    },
    {
      "epoch": 0.011908246957194814,
      "eval_loss": 10.310944557189941,
      "eval_runtime": 0.0928,
      "eval_samples_per_second": 538.899,
      "eval_steps_per_second": 75.446,
      "step": 75
    },
    {
      "epoch": 0.012067023583290745,
      "grad_norm": 0.09749813377857208,
      "learning_rate": 0.00021920117444680317,
      "loss": 10.3223,
      "step": 76
    },
    {
      "epoch": 0.012225800209386675,
      "grad_norm": 0.08614695817232132,
      "learning_rate": 0.00021699132102792097,
      "loss": 10.3191,
      "step": 77
    },
    {
      "epoch": 0.012384576835482606,
      "grad_norm": 0.10386686772108078,
      "learning_rate": 0.0002147631528507739,
      "loss": 10.3194,
      "step": 78
    },
    {
      "epoch": 0.012543353461578538,
      "grad_norm": 0.09013906866312027,
      "learning_rate": 0.00021251727907429355,
      "loss": 10.3176,
      "step": 79
    },
    {
      "epoch": 0.012702130087674467,
      "grad_norm": 0.12356393784284592,
      "learning_rate": 0.0002102543136979454,
      "loss": 10.3124,
      "step": 80
    },
    {
      "epoch": 0.012860906713770399,
      "grad_norm": 0.11175656318664551,
      "learning_rate": 0.0002079748753938678,
      "loss": 10.313,
      "step": 81
    },
    {
      "epoch": 0.01301968333986633,
      "grad_norm": 0.10210341215133667,
      "learning_rate": 0.0002056795873377331,
      "loss": 10.3088,
      "step": 82
    },
    {
      "epoch": 0.013178459965962262,
      "grad_norm": 0.11279959231615067,
      "learning_rate": 0.00020336907703837748,
      "loss": 10.3101,
      "step": 83
    },
    {
      "epoch": 0.013337236592058191,
      "grad_norm": 0.09707577526569366,
      "learning_rate": 0.00020104397616624645,
      "loss": 10.3137,
      "step": 84
    },
    {
      "epoch": 0.013496013218154123,
      "grad_norm": 0.0997617170214653,
      "learning_rate": 0.00019870492038070252,
      "loss": 10.3163,
      "step": 85
    },
    {
      "epoch": 0.013654789844250054,
      "grad_norm": 0.12623490393161774,
      "learning_rate": 0.0001963525491562421,
      "loss": 10.3136,
      "step": 86
    },
    {
      "epoch": 0.013813566470345984,
      "grad_norm": 0.10603071749210358,
      "learning_rate": 0.0001939875056076697,
      "loss": 10.308,
      "step": 87
    },
    {
      "epoch": 0.013972343096441915,
      "grad_norm": 0.10383056104183197,
      "learning_rate": 0.00019161043631427666,
      "loss": 10.3122,
      "step": 88
    },
    {
      "epoch": 0.014131119722537847,
      "grad_norm": 0.11057064682245255,
      "learning_rate": 0.00018922199114307294,
      "loss": 10.317,
      "step": 89
    },
    {
      "epoch": 0.014289896348633776,
      "grad_norm": 0.1066858321428299,
      "learning_rate": 0.00018682282307111987,
      "loss": 10.3097,
      "step": 90
    },
    {
      "epoch": 0.014448672974729708,
      "grad_norm": 0.08680516481399536,
      "learning_rate": 0.00018441358800701273,
      "loss": 10.3105,
      "step": 91
    },
    {
      "epoch": 0.014607449600825639,
      "grad_norm": 0.10082846879959106,
      "learning_rate": 0.00018199494461156203,
      "loss": 10.3076,
      "step": 92
    },
    {
      "epoch": 0.014766226226921569,
      "grad_norm": 0.11305494606494904,
      "learning_rate": 0.000179567554117722,
      "loss": 10.3123,
      "step": 93
    },
    {
      "epoch": 0.0149250028530175,
      "grad_norm": 0.09946515411138535,
      "learning_rate": 0.00017713208014981648,
      "loss": 10.2971,
      "step": 94
    },
    {
      "epoch": 0.015083779479113432,
      "grad_norm": 0.11427634954452515,
      "learning_rate": 0.00017468918854211007,
      "loss": 10.3018,
      "step": 95
    },
    {
      "epoch": 0.015242556105209361,
      "grad_norm": 0.11798146367073059,
      "learning_rate": 0.00017223954715677627,
      "loss": 10.3051,
      "step": 96
    },
    {
      "epoch": 0.015401332731305293,
      "grad_norm": 0.13001081347465515,
      "learning_rate": 0.00016978382570131034,
      "loss": 10.2983,
      "step": 97
    },
    {
      "epoch": 0.015560109357401224,
      "grad_norm": 0.11518680304288864,
      "learning_rate": 0.00016732269554543794,
      "loss": 10.3018,
      "step": 98
    },
    {
      "epoch": 0.015718885983497154,
      "grad_norm": 0.15253396332263947,
      "learning_rate": 0.00016485682953756942,
      "loss": 10.2871,
      "step": 99
    },
    {
      "epoch": 0.015877662609593085,
      "grad_norm": 0.20822547376155853,
      "learning_rate": 0.00016238690182084986,
      "loss": 10.288,
      "step": 100
    },
    {
      "epoch": 0.015877662609593085,
      "eval_loss": 10.301692008972168,
      "eval_runtime": 0.0933,
      "eval_samples_per_second": 535.978,
      "eval_steps_per_second": 75.037,
      "step": 100
    }
  ],
  "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": 1,
        "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": 11114269900800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}