{
  "best_metric": 0.07521108537912369,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.030108012494825184,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015054006247412592,
      "grad_norm": 0.13432709872722626,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.192,
      "step": 1
    },
    {
      "epoch": 0.00015054006247412592,
      "eval_loss": 0.2719675600528717,
      "eval_runtime": 5.8281,
      "eval_samples_per_second": 8.579,
      "eval_steps_per_second": 1.201,
      "step": 1
    },
    {
      "epoch": 0.00030108012494825184,
      "grad_norm": 0.13893114030361176,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.2357,
      "step": 2
    },
    {
      "epoch": 0.00045162018742237776,
      "grad_norm": 0.23538532853126526,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.2321,
      "step": 3
    },
    {
      "epoch": 0.0006021602498965037,
      "grad_norm": 0.12552545964717865,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.153,
      "step": 4
    },
    {
      "epoch": 0.0007527003123706296,
      "grad_norm": 0.12770973145961761,
      "learning_rate": 0.00015,
      "loss": 0.2248,
      "step": 5
    },
    {
      "epoch": 0.0009032403748447555,
      "grad_norm": 0.13605402410030365,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.201,
      "step": 6
    },
    {
      "epoch": 0.0010537804373188814,
      "grad_norm": 0.1637810617685318,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.2183,
      "step": 7
    },
    {
      "epoch": 0.0012043204997930074,
      "grad_norm": 0.12221050262451172,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.124,
      "step": 8
    },
    {
      "epoch": 0.0013548605622671333,
      "grad_norm": 0.1582375317811966,
      "learning_rate": 0.00027,
      "loss": 0.162,
      "step": 9
    },
    {
      "epoch": 0.0015054006247412592,
      "grad_norm": 0.13441474735736847,
      "learning_rate": 0.0003,
      "loss": 0.1341,
      "step": 10
    },
    {
      "epoch": 0.0016559406872153851,
      "grad_norm": 0.17374110221862793,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.2062,
      "step": 11
    },
    {
      "epoch": 0.001806480749689511,
      "grad_norm": 0.14382176101207733,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.1631,
      "step": 12
    },
    {
      "epoch": 0.001957020812163637,
      "grad_norm": 0.11867301911115646,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.1372,
      "step": 13
    },
    {
      "epoch": 0.002107560874637763,
      "grad_norm": 0.10297456383705139,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.1205,
      "step": 14
    },
    {
      "epoch": 0.002258100937111889,
      "grad_norm": 0.13378922641277313,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.173,
      "step": 15
    },
    {
      "epoch": 0.0024086409995860147,
      "grad_norm": 0.2846575081348419,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.2639,
      "step": 16
    },
    {
      "epoch": 0.0025591810620601407,
      "grad_norm": 0.21519090235233307,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.2581,
      "step": 17
    },
    {
      "epoch": 0.0027097211245342666,
      "grad_norm": 0.19943968951702118,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.2171,
      "step": 18
    },
    {
      "epoch": 0.0028602611870083925,
      "grad_norm": 0.20476272702217102,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.3608,
      "step": 19
    },
    {
      "epoch": 0.0030108012494825184,
      "grad_norm": 0.18420757353305817,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.2178,
      "step": 20
    },
    {
      "epoch": 0.0031613413119566443,
      "grad_norm": 0.1748962551355362,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.2517,
      "step": 21
    },
    {
      "epoch": 0.0033118813744307703,
      "grad_norm": 0.20323532819747925,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.2238,
      "step": 22
    },
    {
      "epoch": 0.003462421436904896,
      "grad_norm": 0.2342359721660614,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.2862,
      "step": 23
    },
    {
      "epoch": 0.003612961499379022,
      "grad_norm": 0.14597725868225098,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.1902,
      "step": 24
    },
    {
      "epoch": 0.003763501561853148,
      "grad_norm": 0.1760072559118271,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.2673,
      "step": 25
    },
    {
      "epoch": 0.003763501561853148,
      "eval_loss": 0.1731989085674286,
      "eval_runtime": 5.8861,
      "eval_samples_per_second": 8.495,
      "eval_steps_per_second": 1.189,
      "step": 25
    },
    {
      "epoch": 0.003914041624327274,
      "grad_norm": 0.16469714045524597,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.2375,
      "step": 26
    },
    {
      "epoch": 0.0040645816868014,
      "grad_norm": 0.1807279884815216,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.2787,
      "step": 27
    },
    {
      "epoch": 0.004215121749275526,
      "grad_norm": 0.1720961630344391,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.2626,
      "step": 28
    },
    {
      "epoch": 0.004365661811749652,
      "grad_norm": 0.17341332137584686,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.2325,
      "step": 29
    },
    {
      "epoch": 0.004516201874223778,
      "grad_norm": 0.16063857078552246,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.2144,
      "step": 30
    },
    {
      "epoch": 0.0046667419366979036,
      "grad_norm": 0.166489839553833,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.2199,
      "step": 31
    },
    {
      "epoch": 0.0048172819991720295,
      "grad_norm": 0.1735871136188507,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.2436,
      "step": 32
    },
    {
      "epoch": 0.004967822061646155,
      "grad_norm": 0.17148464918136597,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.2547,
      "step": 33
    },
    {
      "epoch": 0.005118362124120281,
      "grad_norm": 0.17381110787391663,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.2313,
      "step": 34
    },
    {
      "epoch": 0.005268902186594407,
      "grad_norm": 0.19464297592639923,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.2857,
      "step": 35
    },
    {
      "epoch": 0.005419442249068533,
      "grad_norm": 0.17032398283481598,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.2546,
      "step": 36
    },
    {
      "epoch": 0.005569982311542659,
      "grad_norm": 0.190896674990654,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.2831,
      "step": 37
    },
    {
      "epoch": 0.005720522374016785,
      "grad_norm": 0.24636401236057281,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.3094,
      "step": 38
    },
    {
      "epoch": 0.005871062436490911,
      "grad_norm": 0.17670078575611115,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.2858,
      "step": 39
    },
    {
      "epoch": 0.006021602498965037,
      "grad_norm": 0.23208720982074738,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.3023,
      "step": 40
    },
    {
      "epoch": 0.006172142561439163,
      "grad_norm": 0.22071202099323273,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.3636,
      "step": 41
    },
    {
      "epoch": 0.006322682623913289,
      "grad_norm": 0.19284580647945404,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.2341,
      "step": 42
    },
    {
      "epoch": 0.006473222686387415,
      "grad_norm": 0.20681974291801453,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.2126,
      "step": 43
    },
    {
      "epoch": 0.0066237627488615405,
      "grad_norm": 0.22657203674316406,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.2376,
      "step": 44
    },
    {
      "epoch": 0.0067743028113356665,
      "grad_norm": 0.2658374309539795,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.2796,
      "step": 45
    },
    {
      "epoch": 0.006924842873809792,
      "grad_norm": 0.19090871512889862,
      "learning_rate": 0.000274201324672203,
      "loss": 0.1877,
      "step": 46
    },
    {
      "epoch": 0.007075382936283918,
      "grad_norm": 0.2513241767883301,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.2573,
      "step": 47
    },
    {
      "epoch": 0.007225922998758044,
      "grad_norm": 0.29451292753219604,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.264,
      "step": 48
    },
    {
      "epoch": 0.00737646306123217,
      "grad_norm": 0.2619107663631439,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.2481,
      "step": 49
    },
    {
      "epoch": 0.007527003123706296,
      "grad_norm": 0.3190884590148926,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.2778,
      "step": 50
    },
    {
      "epoch": 0.007527003123706296,
      "eval_loss": 0.15092426538467407,
      "eval_runtime": 5.883,
      "eval_samples_per_second": 8.499,
      "eval_steps_per_second": 1.19,
      "step": 50
    },
    {
      "epoch": 0.007677543186180422,
      "grad_norm": 0.1401667445898056,
      "learning_rate": 0.0002668315918143169,
      "loss": 0.1223,
      "step": 51
    },
    {
      "epoch": 0.007828083248654548,
      "grad_norm": 0.13726787269115448,
      "learning_rate": 0.00026526016662852886,
      "loss": 0.1403,
      "step": 52
    },
    {
      "epoch": 0.007978623311128674,
      "grad_norm": 0.14362362027168274,
      "learning_rate": 0.00026365723046405023,
      "loss": 0.1686,
      "step": 53
    },
    {
      "epoch": 0.0081291633736028,
      "grad_norm": 0.1130962073802948,
      "learning_rate": 0.0002620232215476231,
      "loss": 0.1077,
      "step": 54
    },
    {
      "epoch": 0.008279703436076926,
      "grad_norm": 0.11369391530752182,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.1216,
      "step": 55
    },
    {
      "epoch": 0.008430243498551052,
      "grad_norm": 0.1306382417678833,
      "learning_rate": 0.00025866378071866334,
      "loss": 0.086,
      "step": 56
    },
    {
      "epoch": 0.008580783561025178,
      "grad_norm": 0.14394906163215637,
      "learning_rate": 0.00025693926724370956,
      "loss": 0.097,
      "step": 57
    },
    {
      "epoch": 0.008731323623499303,
      "grad_norm": 0.1420009285211563,
      "learning_rate": 0.00025518551764087326,
      "loss": 0.139,
      "step": 58
    },
    {
      "epoch": 0.00888186368597343,
      "grad_norm": 0.13858570158481598,
      "learning_rate": 0.00025340301136778483,
      "loss": 0.1434,
      "step": 59
    },
    {
      "epoch": 0.009032403748447555,
      "grad_norm": 0.11388222873210907,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.0768,
      "step": 60
    },
    {
      "epoch": 0.009182943810921681,
      "grad_norm": 0.11433927714824677,
      "learning_rate": 0.0002497536858170772,
      "loss": 0.0825,
      "step": 61
    },
    {
      "epoch": 0.009333483873395807,
      "grad_norm": 0.11547299474477768,
      "learning_rate": 0.00024788786422862526,
      "loss": 0.1096,
      "step": 62
    },
    {
      "epoch": 0.009484023935869933,
      "grad_norm": 0.12787331640720367,
      "learning_rate": 0.00024599528107549745,
      "loss": 0.117,
      "step": 63
    },
    {
      "epoch": 0.009634563998344059,
      "grad_norm": 0.10538256913423538,
      "learning_rate": 0.00024407645377103054,
      "loss": 0.07,
      "step": 64
    },
    {
      "epoch": 0.009785104060818185,
      "grad_norm": 0.1287563145160675,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.0919,
      "step": 65
    },
    {
      "epoch": 0.00993564412329231,
      "grad_norm": 0.11719094216823578,
      "learning_rate": 0.00024016217209245374,
      "loss": 0.0887,
      "step": 66
    },
    {
      "epoch": 0.010086184185766437,
      "grad_norm": 0.17247700691223145,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.1397,
      "step": 67
    },
    {
      "epoch": 0.010236724248240563,
      "grad_norm": 0.24622748792171478,
      "learning_rate": 0.0002361492994024415,
      "loss": 0.1682,
      "step": 68
    },
    {
      "epoch": 0.010387264310714689,
      "grad_norm": 0.2091142237186432,
      "learning_rate": 0.0002341072586027509,
      "loss": 0.1091,
      "step": 69
    },
    {
      "epoch": 0.010537804373188814,
      "grad_norm": 0.24608778953552246,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.2397,
      "step": 70
    },
    {
      "epoch": 0.01068834443566294,
      "grad_norm": 0.308851033449173,
      "learning_rate": 0.00022995475930919905,
      "loss": 0.1596,
      "step": 71
    },
    {
      "epoch": 0.010838884498137066,
      "grad_norm": 0.23022933304309845,
      "learning_rate": 0.00022784543606718227,
      "loss": 0.1739,
      "step": 72
    },
    {
      "epoch": 0.010989424560611192,
      "grad_norm": 0.1964433789253235,
      "learning_rate": 0.00022571483066022657,
      "loss": 0.1933,
      "step": 73
    },
    {
      "epoch": 0.011139964623085318,
      "grad_norm": 0.2195066511631012,
      "learning_rate": 0.0002235635255745762,
      "loss": 0.2146,
      "step": 74
    },
    {
      "epoch": 0.011290504685559444,
      "grad_norm": 0.21165235340595245,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.1528,
      "step": 75
    },
    {
      "epoch": 0.011290504685559444,
      "eval_loss": 0.12030501663684845,
      "eval_runtime": 5.8823,
      "eval_samples_per_second": 8.5,
      "eval_steps_per_second": 1.19,
      "step": 75
    },
    {
      "epoch": 0.01144104474803357,
      "grad_norm": 0.30299341678619385,
      "learning_rate": 0.00021920117444680317,
      "loss": 0.2136,
      "step": 76
    },
    {
      "epoch": 0.011591584810507696,
      "grad_norm": 0.2567080855369568,
      "learning_rate": 0.00021699132102792097,
      "loss": 0.1794,
      "step": 77
    },
    {
      "epoch": 0.011742124872981822,
      "grad_norm": 0.19719505310058594,
      "learning_rate": 0.0002147631528507739,
      "loss": 0.1988,
      "step": 78
    },
    {
      "epoch": 0.011892664935455948,
      "grad_norm": 0.22220024466514587,
      "learning_rate": 0.00021251727907429355,
      "loss": 0.1759,
      "step": 79
    },
    {
      "epoch": 0.012043204997930074,
      "grad_norm": 0.18353872001171112,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.1792,
      "step": 80
    },
    {
      "epoch": 0.0121937450604042,
      "grad_norm": 0.18121051788330078,
      "learning_rate": 0.0002079748753938678,
      "loss": 0.1299,
      "step": 81
    },
    {
      "epoch": 0.012344285122878326,
      "grad_norm": 0.2993931174278259,
      "learning_rate": 0.0002056795873377331,
      "loss": 0.1858,
      "step": 82
    },
    {
      "epoch": 0.012494825185352451,
      "grad_norm": 0.28290849924087524,
      "learning_rate": 0.00020336907703837748,
      "loss": 0.241,
      "step": 83
    },
    {
      "epoch": 0.012645365247826577,
      "grad_norm": 0.2094016671180725,
      "learning_rate": 0.00020104397616624645,
      "loss": 0.221,
      "step": 84
    },
    {
      "epoch": 0.012795905310300703,
      "grad_norm": 0.18955637514591217,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.1413,
      "step": 85
    },
    {
      "epoch": 0.01294644537277483,
      "grad_norm": 0.20471981167793274,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.2158,
      "step": 86
    },
    {
      "epoch": 0.013096985435248955,
      "grad_norm": 0.20053322613239288,
      "learning_rate": 0.0001939875056076697,
      "loss": 0.2066,
      "step": 87
    },
    {
      "epoch": 0.013247525497723081,
      "grad_norm": 0.2138388454914093,
      "learning_rate": 0.00019161043631427666,
      "loss": 0.228,
      "step": 88
    },
    {
      "epoch": 0.013398065560197207,
      "grad_norm": 0.2082088589668274,
      "learning_rate": 0.00018922199114307294,
      "loss": 0.1788,
      "step": 89
    },
    {
      "epoch": 0.013548605622671333,
      "grad_norm": 0.37482932209968567,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.1592,
      "step": 90
    },
    {
      "epoch": 0.013699145685145459,
      "grad_norm": 0.292537122964859,
      "learning_rate": 0.00018441358800701273,
      "loss": 0.2572,
      "step": 91
    },
    {
      "epoch": 0.013849685747619585,
      "grad_norm": 0.2552037239074707,
      "learning_rate": 0.00018199494461156203,
      "loss": 0.1872,
      "step": 92
    },
    {
      "epoch": 0.01400022581009371,
      "grad_norm": 0.2402886003255844,
      "learning_rate": 0.000179567554117722,
      "loss": 0.2123,
      "step": 93
    },
    {
      "epoch": 0.014150765872567837,
      "grad_norm": 0.24449338018894196,
      "learning_rate": 0.00017713208014981648,
      "loss": 0.2047,
      "step": 94
    },
    {
      "epoch": 0.014301305935041963,
      "grad_norm": 0.26285871863365173,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.2038,
      "step": 95
    },
    {
      "epoch": 0.014451845997516088,
      "grad_norm": 0.25671887397766113,
      "learning_rate": 0.00017223954715677627,
      "loss": 0.2015,
      "step": 96
    },
    {
      "epoch": 0.014602386059990214,
      "grad_norm": 0.2887267768383026,
      "learning_rate": 0.00016978382570131034,
      "loss": 0.1925,
      "step": 97
    },
    {
      "epoch": 0.01475292612246434,
      "grad_norm": 0.28670281171798706,
      "learning_rate": 0.00016732269554543794,
      "loss": 0.1805,
      "step": 98
    },
    {
      "epoch": 0.014903466184938466,
      "grad_norm": 0.3724100887775421,
      "learning_rate": 0.00016485682953756942,
      "loss": 0.2652,
      "step": 99
    },
    {
      "epoch": 0.015054006247412592,
      "grad_norm": 0.3608229458332062,
      "learning_rate": 0.00016238690182084986,
      "loss": 0.226,
      "step": 100
    },
    {
      "epoch": 0.015054006247412592,
      "eval_loss": 0.11629380285739899,
      "eval_runtime": 5.8921,
      "eval_samples_per_second": 8.486,
      "eval_steps_per_second": 1.188,
      "step": 100
    },
    {
      "epoch": 0.015204546309886718,
      "grad_norm": 0.14270652830600739,
      "learning_rate": 0.0001599135876488549,
      "loss": 0.0555,
      "step": 101
    },
    {
      "epoch": 0.015355086372360844,
      "grad_norm": 0.15754464268684387,
      "learning_rate": 0.00015743756320098332,
      "loss": 0.1004,
      "step": 102
    },
    {
      "epoch": 0.01550562643483497,
      "grad_norm": 0.16595377027988434,
      "learning_rate": 0.0001549595053975962,
      "loss": 0.0742,
      "step": 103
    },
    {
      "epoch": 0.015656166497309096,
      "grad_norm": 0.14158500730991364,
      "learning_rate": 0.00015248009171495378,
      "loss": 0.0879,
      "step": 104
    },
    {
      "epoch": 0.015806706559783223,
      "grad_norm": 0.14816971123218536,
      "learning_rate": 0.00015,
      "loss": 0.0947,
      "step": 105
    },
    {
      "epoch": 0.015957246622257348,
      "grad_norm": 0.11312155425548553,
      "learning_rate": 0.00014751990828504622,
      "loss": 0.0564,
      "step": 106
    },
    {
      "epoch": 0.016107786684731475,
      "grad_norm": 0.13716237246990204,
      "learning_rate": 0.00014504049460240375,
      "loss": 0.1012,
      "step": 107
    },
    {
      "epoch": 0.0162583267472056,
      "grad_norm": 0.11018291860818863,
      "learning_rate": 0.00014256243679901663,
      "loss": 0.054,
      "step": 108
    },
    {
      "epoch": 0.016408866809679727,
      "grad_norm": 0.14708121120929718,
      "learning_rate": 0.00014008641235114508,
      "loss": 0.0739,
      "step": 109
    },
    {
      "epoch": 0.01655940687215385,
      "grad_norm": 0.15850837528705597,
      "learning_rate": 0.00013761309817915014,
      "loss": 0.1001,
      "step": 110
    },
    {
      "epoch": 0.01670994693462798,
      "grad_norm": 0.1399727165699005,
      "learning_rate": 0.00013514317046243058,
      "loss": 0.0825,
      "step": 111
    },
    {
      "epoch": 0.016860486997102103,
      "grad_norm": 0.1393916755914688,
      "learning_rate": 0.00013267730445456208,
      "loss": 0.0936,
      "step": 112
    },
    {
      "epoch": 0.01701102705957623,
      "grad_norm": 0.1308310329914093,
      "learning_rate": 0.00013021617429868963,
      "loss": 0.0847,
      "step": 113
    },
    {
      "epoch": 0.017161567122050355,
      "grad_norm": 0.1415696144104004,
      "learning_rate": 0.00012776045284322368,
      "loss": 0.0944,
      "step": 114
    },
    {
      "epoch": 0.017312107184524483,
      "grad_norm": 0.11390219628810883,
      "learning_rate": 0.00012531081145788987,
      "loss": 0.0538,
      "step": 115
    },
    {
      "epoch": 0.017462647246998607,
      "grad_norm": 0.10866839438676834,
      "learning_rate": 0.00012286791985018355,
      "loss": 0.0647,
      "step": 116
    },
    {
      "epoch": 0.017613187309472735,
      "grad_norm": 0.31850966811180115,
      "learning_rate": 0.00012043244588227796,
      "loss": 0.1308,
      "step": 117
    },
    {
      "epoch": 0.01776372737194686,
      "grad_norm": 0.22462540864944458,
      "learning_rate": 0.00011800505538843798,
      "loss": 0.1285,
      "step": 118
    },
    {
      "epoch": 0.017914267434420986,
      "grad_norm": 0.33375418186187744,
      "learning_rate": 0.00011558641199298727,
      "loss": 0.1345,
      "step": 119
    },
    {
      "epoch": 0.01806480749689511,
      "grad_norm": 0.35804978013038635,
      "learning_rate": 0.00011317717692888012,
      "loss": 0.127,
      "step": 120
    },
    {
      "epoch": 0.018215347559369238,
      "grad_norm": 0.2238689512014389,
      "learning_rate": 0.00011077800885692702,
      "loss": 0.1408,
      "step": 121
    },
    {
      "epoch": 0.018365887621843362,
      "grad_norm": 0.17107348144054413,
      "learning_rate": 0.00010838956368572334,
      "loss": 0.1118,
      "step": 122
    },
    {
      "epoch": 0.01851642768431749,
      "grad_norm": 0.2386879324913025,
      "learning_rate": 0.0001060124943923303,
      "loss": 0.1541,
      "step": 123
    },
    {
      "epoch": 0.018666967746791614,
      "grad_norm": 0.21105018258094788,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.127,
      "step": 124
    },
    {
      "epoch": 0.018817507809265742,
      "grad_norm": 0.20090296864509583,
      "learning_rate": 0.00010129507961929748,
      "loss": 0.1236,
      "step": 125
    },
    {
      "epoch": 0.018817507809265742,
      "eval_loss": 0.10832758992910385,
      "eval_runtime": 5.8892,
      "eval_samples_per_second": 8.49,
      "eval_steps_per_second": 1.189,
      "step": 125
    },
    {
      "epoch": 0.018968047871739866,
      "grad_norm": 0.20435857772827148,
      "learning_rate": 9.895602383375353e-05,
      "loss": 0.184,
      "step": 126
    },
    {
      "epoch": 0.019118587934213994,
      "grad_norm": 0.2117018699645996,
      "learning_rate": 9.663092296162251e-05,
      "loss": 0.1317,
      "step": 127
    },
    {
      "epoch": 0.019269127996688118,
      "grad_norm": 0.2362200915813446,
      "learning_rate": 9.432041266226686e-05,
      "loss": 0.1534,
      "step": 128
    },
    {
      "epoch": 0.019419668059162246,
      "grad_norm": 0.23022405803203583,
      "learning_rate": 9.202512460613219e-05,
      "loss": 0.1322,
      "step": 129
    },
    {
      "epoch": 0.01957020812163637,
      "grad_norm": 0.2183733582496643,
      "learning_rate": 8.97456863020546e-05,
      "loss": 0.1846,
      "step": 130
    },
    {
      "epoch": 0.019720748184110497,
      "grad_norm": 0.23582717776298523,
      "learning_rate": 8.748272092570646e-05,
      "loss": 0.1702,
      "step": 131
    },
    {
      "epoch": 0.01987128824658462,
      "grad_norm": 0.20001551508903503,
      "learning_rate": 8.523684714922608e-05,
      "loss": 0.1551,
      "step": 132
    },
    {
      "epoch": 0.02002182830905875,
      "grad_norm": 0.21373708546161652,
      "learning_rate": 8.300867897207903e-05,
      "loss": 0.1552,
      "step": 133
    },
    {
      "epoch": 0.020172368371532873,
      "grad_norm": 0.2089868038892746,
      "learning_rate": 8.079882555319684e-05,
      "loss": 0.1589,
      "step": 134
    },
    {
      "epoch": 0.020322908434007,
      "grad_norm": 0.22662235796451569,
      "learning_rate": 7.860789104443896e-05,
      "loss": 0.2086,
      "step": 135
    },
    {
      "epoch": 0.020473448496481125,
      "grad_norm": 0.22787557542324066,
      "learning_rate": 7.643647442542382e-05,
      "loss": 0.1547,
      "step": 136
    },
    {
      "epoch": 0.020623988558955253,
      "grad_norm": 0.19957378506660461,
      "learning_rate": 7.428516933977347e-05,
      "loss": 0.1173,
      "step": 137
    },
    {
      "epoch": 0.020774528621429377,
      "grad_norm": 0.21787644922733307,
      "learning_rate": 7.215456393281776e-05,
      "loss": 0.1634,
      "step": 138
    },
    {
      "epoch": 0.020925068683903505,
      "grad_norm": 0.26152557134628296,
      "learning_rate": 7.004524069080096e-05,
      "loss": 0.1511,
      "step": 139
    },
    {
      "epoch": 0.02107560874637763,
      "grad_norm": 0.28347164392471313,
      "learning_rate": 6.795777628163599e-05,
      "loss": 0.1633,
      "step": 140
    },
    {
      "epoch": 0.021226148808851757,
      "grad_norm": 0.2593938410282135,
      "learning_rate": 6.58927413972491e-05,
      "loss": 0.1389,
      "step": 141
    },
    {
      "epoch": 0.02137668887132588,
      "grad_norm": 0.36443331837654114,
      "learning_rate": 6.385070059755846e-05,
      "loss": 0.1682,
      "step": 142
    },
    {
      "epoch": 0.02152722893380001,
      "grad_norm": 0.3305942714214325,
      "learning_rate": 6.183221215612904e-05,
      "loss": 0.189,
      "step": 143
    },
    {
      "epoch": 0.021677768996274133,
      "grad_norm": 0.2871330678462982,
      "learning_rate": 5.983782790754623e-05,
      "loss": 0.1544,
      "step": 144
    },
    {
      "epoch": 0.02182830905874826,
      "grad_norm": 0.3002281188964844,
      "learning_rate": 5.786809309654982e-05,
      "loss": 0.1697,
      "step": 145
    },
    {
      "epoch": 0.021978849121222385,
      "grad_norm": 0.2565898597240448,
      "learning_rate": 5.592354622896944e-05,
      "loss": 0.174,
      "step": 146
    },
    {
      "epoch": 0.022129389183696512,
      "grad_norm": 0.24160735309123993,
      "learning_rate": 5.40047189245025e-05,
      "loss": 0.1427,
      "step": 147
    },
    {
      "epoch": 0.022279929246170636,
      "grad_norm": 0.3103688061237335,
      "learning_rate": 5.211213577137469e-05,
      "loss": 0.1604,
      "step": 148
    },
    {
      "epoch": 0.022430469308644764,
      "grad_norm": 0.34485578536987305,
      "learning_rate": 5.024631418292274e-05,
      "loss": 0.1984,
      "step": 149
    },
    {
      "epoch": 0.022581009371118888,
      "grad_norm": 0.39101657271385193,
      "learning_rate": 4.840776425613886e-05,
      "loss": 0.1854,
      "step": 150
    },
    {
      "epoch": 0.022581009371118888,
      "eval_loss": 0.08700338006019592,
      "eval_runtime": 5.8922,
      "eval_samples_per_second": 8.486,
      "eval_steps_per_second": 1.188,
      "step": 150
    },
    {
      "epoch": 0.022731549433593016,
      "grad_norm": 0.15644125640392303,
      "learning_rate": 4.659698863221513e-05,
      "loss": 0.0615,
      "step": 151
    },
    {
      "epoch": 0.02288208949606714,
      "grad_norm": 0.13763482868671417,
      "learning_rate": 4.481448235912671e-05,
      "loss": 0.0345,
      "step": 152
    },
    {
      "epoch": 0.023032629558541268,
      "grad_norm": 0.1581212878227234,
      "learning_rate": 4.306073275629044e-05,
      "loss": 0.0534,
      "step": 153
    },
    {
      "epoch": 0.023183169621015392,
      "grad_norm": 0.14264962077140808,
      "learning_rate": 4.133621928133665e-05,
      "loss": 0.0723,
      "step": 154
    },
    {
      "epoch": 0.02333370968348952,
      "grad_norm": 0.15869100391864777,
      "learning_rate": 3.964141339903026e-05,
      "loss": 0.0649,
      "step": 155
    },
    {
      "epoch": 0.023484249745963644,
      "grad_norm": 0.13853639364242554,
      "learning_rate": 3.797677845237696e-05,
      "loss": 0.0582,
      "step": 156
    },
    {
      "epoch": 0.02363478980843777,
      "grad_norm": 0.16589723527431488,
      "learning_rate": 3.634276953594982e-05,
      "loss": 0.0942,
      "step": 157
    },
    {
      "epoch": 0.023785329870911896,
      "grad_norm": 0.12482775747776031,
      "learning_rate": 3.473983337147118e-05,
      "loss": 0.04,
      "step": 158
    },
    {
      "epoch": 0.023935869933386023,
      "grad_norm": 0.12084036320447922,
      "learning_rate": 3.316840818568315e-05,
      "loss": 0.0433,
      "step": 159
    },
    {
      "epoch": 0.024086409995860147,
      "grad_norm": 0.19188204407691956,
      "learning_rate": 3.162892359054098e-05,
      "loss": 0.0683,
      "step": 160
    },
    {
      "epoch": 0.024236950058334275,
      "grad_norm": 0.1759098321199417,
      "learning_rate": 3.0121800465761293e-05,
      "loss": 0.0658,
      "step": 161
    },
    {
      "epoch": 0.0243874901208084,
      "grad_norm": 0.11549676209688187,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.0428,
      "step": 162
    },
    {
      "epoch": 0.024538030183282527,
      "grad_norm": 0.1507856547832489,
      "learning_rate": 2.7206277796996144e-05,
      "loss": 0.0735,
      "step": 163
    },
    {
      "epoch": 0.02468857024575665,
      "grad_norm": 0.14003053307533264,
      "learning_rate": 2.5798675327796993e-05,
      "loss": 0.0741,
      "step": 164
    },
    {
      "epoch": 0.02483911030823078,
      "grad_norm": 0.12259425222873688,
      "learning_rate": 2.4425028260620715e-05,
      "loss": 0.0429,
      "step": 165
    },
    {
      "epoch": 0.024989650370704903,
      "grad_norm": 0.11335761100053787,
      "learning_rate": 2.3085712136859668e-05,
      "loss": 0.0405,
      "step": 166
    },
    {
      "epoch": 0.02514019043317903,
      "grad_norm": 0.30729901790618896,
      "learning_rate": 2.178109311216913e-05,
      "loss": 0.0947,
      "step": 167
    },
    {
      "epoch": 0.025290730495653155,
      "grad_norm": 0.21062178909778595,
      "learning_rate": 2.0511527856363912e-05,
      "loss": 0.0986,
      "step": 168
    },
    {
      "epoch": 0.025441270558127282,
      "grad_norm": 0.2791978418827057,
      "learning_rate": 1.927736345590839e-05,
      "loss": 0.1273,
      "step": 169
    },
    {
      "epoch": 0.025591810620601407,
      "grad_norm": 0.23478782176971436,
      "learning_rate": 1.8078937319026654e-05,
      "loss": 0.1027,
      "step": 170
    },
    {
      "epoch": 0.025742350683075534,
      "grad_norm": 0.20816297829151154,
      "learning_rate": 1.6916577083458228e-05,
      "loss": 0.074,
      "step": 171
    },
    {
      "epoch": 0.02589289074554966,
      "grad_norm": 0.2092941403388977,
      "learning_rate": 1.579060052688548e-05,
      "loss": 0.1411,
      "step": 172
    },
    {
      "epoch": 0.026043430808023786,
      "grad_norm": 0.2681998908519745,
      "learning_rate": 1.4701315480056164e-05,
      "loss": 0.1129,
      "step": 173
    },
    {
      "epoch": 0.02619397087049791,
      "grad_norm": 0.23058678209781647,
      "learning_rate": 1.3649019742625623e-05,
      "loss": 0.1003,
      "step": 174
    },
    {
      "epoch": 0.026344510932972038,
      "grad_norm": 0.2815040349960327,
      "learning_rate": 1.2634001001741373e-05,
      "loss": 0.1296,
      "step": 175
    },
    {
      "epoch": 0.026344510932972038,
      "eval_loss": 0.07823067903518677,
      "eval_runtime": 5.8874,
      "eval_samples_per_second": 8.493,
      "eval_steps_per_second": 1.189,
      "step": 175
    },
    {
      "epoch": 0.026495050995446162,
      "grad_norm": 0.1958063393831253,
      "learning_rate": 1.1656536753392287e-05,
      "loss": 0.0977,
      "step": 176
    },
    {
      "epoch": 0.02664559105792029,
      "grad_norm": 0.25271862745285034,
      "learning_rate": 1.0716894226543953e-05,
      "loss": 0.1516,
      "step": 177
    },
    {
      "epoch": 0.026796131120394414,
      "grad_norm": 0.2665039598941803,
      "learning_rate": 9.815330310080887e-06,
      "loss": 0.1355,
      "step": 178
    },
    {
      "epoch": 0.02694667118286854,
      "grad_norm": 0.1967024803161621,
      "learning_rate": 8.952091482575824e-06,
      "loss": 0.1041,
      "step": 179
    },
    {
      "epoch": 0.027097211245342666,
      "grad_norm": 0.22323350608348846,
      "learning_rate": 8.127413744904804e-06,
      "loss": 0.1508,
      "step": 180
    },
    {
      "epoch": 0.027247751307816793,
      "grad_norm": 0.26765817403793335,
      "learning_rate": 7.34152255572697e-06,
      "loss": 0.1542,
      "step": 181
    },
    {
      "epoch": 0.027398291370290918,
      "grad_norm": 0.22527235746383667,
      "learning_rate": 6.594632769846353e-06,
      "loss": 0.1327,
      "step": 182
    },
    {
      "epoch": 0.027548831432765045,
      "grad_norm": 0.19589683413505554,
      "learning_rate": 5.886948579472778e-06,
      "loss": 0.1088,
      "step": 183
    },
    {
      "epoch": 0.02769937149523917,
      "grad_norm": 0.7182509303092957,
      "learning_rate": 5.218663458397715e-06,
      "loss": 0.1013,
      "step": 184
    },
    {
      "epoch": 0.027849911557713297,
      "grad_norm": 0.2169928103685379,
      "learning_rate": 4.589960109100444e-06,
      "loss": 0.1138,
      "step": 185
    },
    {
      "epoch": 0.02800045162018742,
      "grad_norm": 0.6080103516578674,
      "learning_rate": 4.001010412799138e-06,
      "loss": 0.1358,
      "step": 186
    },
    {
      "epoch": 0.02815099168266155,
      "grad_norm": 0.2407759577035904,
      "learning_rate": 3.451975382460109e-06,
      "loss": 0.1595,
      "step": 187
    },
    {
      "epoch": 0.028301531745135673,
      "grad_norm": 0.3847437798976898,
      "learning_rate": 2.9430051187785962e-06,
      "loss": 0.1593,
      "step": 188
    },
    {
      "epoch": 0.0284520718076098,
      "grad_norm": 0.27828317880630493,
      "learning_rate": 2.4742387691426445e-06,
      "loss": 0.1293,
      "step": 189
    },
    {
      "epoch": 0.028602611870083925,
      "grad_norm": 0.2508259117603302,
      "learning_rate": 2.0458044895916513e-06,
      "loss": 0.1092,
      "step": 190
    },
    {
      "epoch": 0.028753151932558053,
      "grad_norm": 0.23639361560344696,
      "learning_rate": 1.6578194097797258e-06,
      "loss": 0.1025,
      "step": 191
    },
    {
      "epoch": 0.028903691995032177,
      "grad_norm": 0.2561388909816742,
      "learning_rate": 1.3103896009537207e-06,
      "loss": 0.1349,
      "step": 192
    },
    {
      "epoch": 0.029054232057506305,
      "grad_norm": 0.27320489287376404,
      "learning_rate": 1.0036100469542786e-06,
      "loss": 0.172,
      "step": 193
    },
    {
      "epoch": 0.02920477211998043,
      "grad_norm": 0.336984783411026,
      "learning_rate": 7.375646182482875e-07,
      "loss": 0.1359,
      "step": 194
    },
    {
      "epoch": 0.029355312182454556,
      "grad_norm": 0.4405703544616699,
      "learning_rate": 5.123260489995229e-07,
      "loss": 0.1344,
      "step": 195
    },
    {
      "epoch": 0.02950585224492868,
      "grad_norm": 0.7872334718704224,
      "learning_rate": 3.2795591718381975e-07,
      "loss": 0.1815,
      "step": 196
    },
    {
      "epoch": 0.029656392307402808,
      "grad_norm": 0.2895253300666809,
      "learning_rate": 1.8450462775428942e-07,
      "loss": 0.1195,
      "step": 197
    },
    {
      "epoch": 0.029806932369876932,
      "grad_norm": 0.6127339601516724,
      "learning_rate": 8.201139886109264e-08,
      "loss": 0.1486,
      "step": 198
    },
    {
      "epoch": 0.02995747243235106,
      "grad_norm": 0.3820211589336395,
      "learning_rate": 2.0504251129649374e-08,
      "loss": 0.1565,
      "step": 199
    },
    {
      "epoch": 0.030108012494825184,
      "grad_norm": 0.5019745230674744,
      "learning_rate": 0.0,
      "loss": 0.178,
      "step": 200
    },
    {
      "epoch": 0.030108012494825184,
      "eval_loss": 0.07521108537912369,
      "eval_runtime": 5.8896,
      "eval_samples_per_second": 8.49,
      "eval_steps_per_second": 1.189,
      "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": 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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.60219415052288e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}