{
  "best_metric": 2.242912530899048,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.07110479068527242,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003555239534263621,
      "grad_norm": 5.148736953735352,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 10.6832,
      "step": 1
    },
    {
      "epoch": 0.0003555239534263621,
      "eval_loss": 4.129520893096924,
      "eval_runtime": 3.3586,
      "eval_samples_per_second": 14.887,
      "eval_steps_per_second": 2.084,
      "step": 1
    },
    {
      "epoch": 0.0007110479068527242,
      "grad_norm": 9.437398910522461,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 13.3188,
      "step": 2
    },
    {
      "epoch": 0.0010665718602790863,
      "grad_norm": 11.877067565917969,
      "learning_rate": 8.999999999999999e-05,
      "loss": 13.3741,
      "step": 3
    },
    {
      "epoch": 0.0014220958137054485,
      "grad_norm": 10.118707656860352,
      "learning_rate": 0.00011999999999999999,
      "loss": 15.4794,
      "step": 4
    },
    {
      "epoch": 0.0017776197671318106,
      "grad_norm": 10.598353385925293,
      "learning_rate": 0.00015,
      "loss": 14.2279,
      "step": 5
    },
    {
      "epoch": 0.0021331437205581727,
      "grad_norm": 10.02908706665039,
      "learning_rate": 0.00017999999999999998,
      "loss": 14.693,
      "step": 6
    },
    {
      "epoch": 0.002488667673984535,
      "grad_norm": 9.211532592773438,
      "learning_rate": 0.00020999999999999998,
      "loss": 13.2508,
      "step": 7
    },
    {
      "epoch": 0.002844191627410897,
      "grad_norm": 7.770359039306641,
      "learning_rate": 0.00023999999999999998,
      "loss": 11.5868,
      "step": 8
    },
    {
      "epoch": 0.003199715580837259,
      "grad_norm": 7.963329315185547,
      "learning_rate": 0.00027,
      "loss": 11.9802,
      "step": 9
    },
    {
      "epoch": 0.003555239534263621,
      "grad_norm": 7.712958335876465,
      "learning_rate": 0.0003,
      "loss": 11.9173,
      "step": 10
    },
    {
      "epoch": 0.003910763487689983,
      "grad_norm": 9.166488647460938,
      "learning_rate": 0.0002999794957488703,
      "loss": 10.7235,
      "step": 11
    },
    {
      "epoch": 0.004266287441116345,
      "grad_norm": 7.82598352432251,
      "learning_rate": 0.0002999179886011389,
      "loss": 11.9476,
      "step": 12
    },
    {
      "epoch": 0.0046218113945427075,
      "grad_norm": 6.442850589752197,
      "learning_rate": 0.0002998154953722457,
      "loss": 11.8718,
      "step": 13
    },
    {
      "epoch": 0.00497733534796907,
      "grad_norm": 6.2762250900268555,
      "learning_rate": 0.00029967204408281613,
      "loss": 11.2581,
      "step": 14
    },
    {
      "epoch": 0.005332859301395432,
      "grad_norm": 6.239474296569824,
      "learning_rate": 0.00029948767395100045,
      "loss": 11.5523,
      "step": 15
    },
    {
      "epoch": 0.005688383254821794,
      "grad_norm": 6.828975200653076,
      "learning_rate": 0.0002992624353817517,
      "loss": 10.8527,
      "step": 16
    },
    {
      "epoch": 0.006043907208248156,
      "grad_norm": 5.866279125213623,
      "learning_rate": 0.0002989963899530457,
      "loss": 10.2987,
      "step": 17
    },
    {
      "epoch": 0.006399431161674518,
      "grad_norm": 6.213174819946289,
      "learning_rate": 0.00029868961039904624,
      "loss": 11.1893,
      "step": 18
    },
    {
      "epoch": 0.00675495511510088,
      "grad_norm": 6.3075947761535645,
      "learning_rate": 0.00029834218059022024,
      "loss": 11.7585,
      "step": 19
    },
    {
      "epoch": 0.007110479068527242,
      "grad_norm": 5.69662618637085,
      "learning_rate": 0.00029795419551040833,
      "loss": 10.9056,
      "step": 20
    },
    {
      "epoch": 0.0074660030219536044,
      "grad_norm": 5.039904594421387,
      "learning_rate": 0.00029752576123085736,
      "loss": 10.9972,
      "step": 21
    },
    {
      "epoch": 0.007821526975379967,
      "grad_norm": 7.389419078826904,
      "learning_rate": 0.0002970569948812214,
      "loss": 10.7294,
      "step": 22
    },
    {
      "epoch": 0.008177050928806329,
      "grad_norm": 5.38754940032959,
      "learning_rate": 0.0002965480246175399,
      "loss": 11.4038,
      "step": 23
    },
    {
      "epoch": 0.00853257488223269,
      "grad_norm": 4.84633207321167,
      "learning_rate": 0.0002959989895872009,
      "loss": 11.3331,
      "step": 24
    },
    {
      "epoch": 0.008888098835659053,
      "grad_norm": 8.040166854858398,
      "learning_rate": 0.0002954100398908995,
      "loss": 9.1027,
      "step": 25
    },
    {
      "epoch": 0.008888098835659053,
      "eval_loss": 2.6589479446411133,
      "eval_runtime": 3.4083,
      "eval_samples_per_second": 14.67,
      "eval_steps_per_second": 2.054,
      "step": 25
    },
    {
      "epoch": 0.009243622789085415,
      "grad_norm": 6.918544292449951,
      "learning_rate": 0.0002947813365416023,
      "loss": 8.9439,
      "step": 26
    },
    {
      "epoch": 0.009599146742511777,
      "grad_norm": 7.847255229949951,
      "learning_rate": 0.0002941130514205272,
      "loss": 11.8663,
      "step": 27
    },
    {
      "epoch": 0.00995467069593814,
      "grad_norm": 7.098354816436768,
      "learning_rate": 0.0002934053672301536,
      "loss": 10.7316,
      "step": 28
    },
    {
      "epoch": 0.010310194649364501,
      "grad_norm": 6.682184219360352,
      "learning_rate": 0.00029265847744427303,
      "loss": 11.5576,
      "step": 29
    },
    {
      "epoch": 0.010665718602790863,
      "grad_norm": 6.960466384887695,
      "learning_rate": 0.00029187258625509513,
      "loss": 12.3166,
      "step": 30
    },
    {
      "epoch": 0.011021242556217226,
      "grad_norm": 5.996150493621826,
      "learning_rate": 0.00029104790851742417,
      "loss": 10.4602,
      "step": 31
    },
    {
      "epoch": 0.011376766509643588,
      "grad_norm": 4.758652687072754,
      "learning_rate": 0.0002901846696899191,
      "loss": 10.4963,
      "step": 32
    },
    {
      "epoch": 0.01173229046306995,
      "grad_norm": 7.130350112915039,
      "learning_rate": 0.00028928310577345606,
      "loss": 10.7115,
      "step": 33
    },
    {
      "epoch": 0.012087814416496312,
      "grad_norm": 6.909444332122803,
      "learning_rate": 0.0002883434632466077,
      "loss": 11.7185,
      "step": 34
    },
    {
      "epoch": 0.012443338369922674,
      "grad_norm": 5.900872230529785,
      "learning_rate": 0.00028736599899825856,
      "loss": 11.569,
      "step": 35
    },
    {
      "epoch": 0.012798862323349036,
      "grad_norm": 6.807727336883545,
      "learning_rate": 0.00028635098025737434,
      "loss": 11.2401,
      "step": 36
    },
    {
      "epoch": 0.013154386276775398,
      "grad_norm": 5.605060577392578,
      "learning_rate": 0.00028529868451994384,
      "loss": 10.745,
      "step": 37
    },
    {
      "epoch": 0.01350991023020176,
      "grad_norm": 6.011505126953125,
      "learning_rate": 0.0002842093994731145,
      "loss": 11.2352,
      "step": 38
    },
    {
      "epoch": 0.013865434183628123,
      "grad_norm": 5.524464130401611,
      "learning_rate": 0.00028308342291654174,
      "loss": 11.7443,
      "step": 39
    },
    {
      "epoch": 0.014220958137054485,
      "grad_norm": 6.286143779754639,
      "learning_rate": 0.00028192106268097334,
      "loss": 11.7776,
      "step": 40
    },
    {
      "epoch": 0.014576482090480847,
      "grad_norm": 6.927269458770752,
      "learning_rate": 0.00028072263654409154,
      "loss": 11.5985,
      "step": 41
    },
    {
      "epoch": 0.014932006043907209,
      "grad_norm": 6.525967121124268,
      "learning_rate": 0.0002794884721436361,
      "loss": 10.8744,
      "step": 42
    },
    {
      "epoch": 0.015287529997333571,
      "grad_norm": 8.965846061706543,
      "learning_rate": 0.00027821890688783083,
      "loss": 11.2533,
      "step": 43
    },
    {
      "epoch": 0.015643053950759933,
      "grad_norm": 5.708492755889893,
      "learning_rate": 0.0002769142878631403,
      "loss": 11.8151,
      "step": 44
    },
    {
      "epoch": 0.015998577904186295,
      "grad_norm": 6.520906925201416,
      "learning_rate": 0.00027557497173937923,
      "loss": 12.0673,
      "step": 45
    },
    {
      "epoch": 0.016354101857612657,
      "grad_norm": 6.278893947601318,
      "learning_rate": 0.000274201324672203,
      "loss": 11.4272,
      "step": 46
    },
    {
      "epoch": 0.01670962581103902,
      "grad_norm": 6.297929763793945,
      "learning_rate": 0.00027279372220300385,
      "loss": 12.42,
      "step": 47
    },
    {
      "epoch": 0.01706514976446538,
      "grad_norm": 6.474391460418701,
      "learning_rate": 0.0002713525491562421,
      "loss": 12.3248,
      "step": 48
    },
    {
      "epoch": 0.017420673717891744,
      "grad_norm": 7.879404067993164,
      "learning_rate": 0.00026987819953423867,
      "loss": 11.704,
      "step": 49
    },
    {
      "epoch": 0.017776197671318106,
      "grad_norm": 11.09743595123291,
      "learning_rate": 0.00026837107640945905,
      "loss": 11.4028,
      "step": 50
    },
    {
      "epoch": 0.017776197671318106,
      "eval_loss": 2.671022653579712,
      "eval_runtime": 3.4117,
      "eval_samples_per_second": 14.655,
      "eval_steps_per_second": 2.052,
      "step": 50
    },
    {
      "epoch": 0.018131721624744468,
      "grad_norm": 7.684964179992676,
      "learning_rate": 0.0002668315918143169,
      "loss": 9.6814,
      "step": 51
    },
    {
      "epoch": 0.01848724557817083,
      "grad_norm": 8.576638221740723,
      "learning_rate": 0.00026526016662852886,
      "loss": 9.9166,
      "step": 52
    },
    {
      "epoch": 0.018842769531597192,
      "grad_norm": 6.030575275421143,
      "learning_rate": 0.00026365723046405023,
      "loss": 9.4847,
      "step": 53
    },
    {
      "epoch": 0.019198293485023554,
      "grad_norm": 5.481552600860596,
      "learning_rate": 0.0002620232215476231,
      "loss": 10.3622,
      "step": 54
    },
    {
      "epoch": 0.019553817438449916,
      "grad_norm": 6.241498947143555,
      "learning_rate": 0.0002603585866009697,
      "loss": 10.2548,
      "step": 55
    },
    {
      "epoch": 0.01990934139187628,
      "grad_norm": 6.387746334075928,
      "learning_rate": 0.00025866378071866334,
      "loss": 11.7413,
      "step": 56
    },
    {
      "epoch": 0.02026486534530264,
      "grad_norm": 5.217421054840088,
      "learning_rate": 0.00025693926724370956,
      "loss": 10.0964,
      "step": 57
    },
    {
      "epoch": 0.020620389298729003,
      "grad_norm": 5.437652587890625,
      "learning_rate": 0.00025518551764087326,
      "loss": 10.6227,
      "step": 58
    },
    {
      "epoch": 0.020975913252155365,
      "grad_norm": 5.892682075500488,
      "learning_rate": 0.00025340301136778483,
      "loss": 10.518,
      "step": 59
    },
    {
      "epoch": 0.021331437205581727,
      "grad_norm": 5.065958499908447,
      "learning_rate": 0.00025159223574386114,
      "loss": 10.1033,
      "step": 60
    },
    {
      "epoch": 0.02168696115900809,
      "grad_norm": 4.1559953689575195,
      "learning_rate": 0.0002497536858170772,
      "loss": 10.8079,
      "step": 61
    },
    {
      "epoch": 0.02204248511243445,
      "grad_norm": 4.143509387969971,
      "learning_rate": 0.00024788786422862526,
      "loss": 10.3888,
      "step": 62
    },
    {
      "epoch": 0.022398009065860813,
      "grad_norm": 4.2139363288879395,
      "learning_rate": 0.00024599528107549745,
      "loss": 10.6368,
      "step": 63
    },
    {
      "epoch": 0.022753533019287175,
      "grad_norm": 4.801663398742676,
      "learning_rate": 0.00024407645377103054,
      "loss": 9.8445,
      "step": 64
    },
    {
      "epoch": 0.023109056972713538,
      "grad_norm": 5.6707024574279785,
      "learning_rate": 0.00024213190690345018,
      "loss": 9.8583,
      "step": 65
    },
    {
      "epoch": 0.0234645809261399,
      "grad_norm": 4.797868728637695,
      "learning_rate": 0.00024016217209245374,
      "loss": 10.7598,
      "step": 66
    },
    {
      "epoch": 0.023820104879566262,
      "grad_norm": 4.8325371742248535,
      "learning_rate": 0.00023816778784387094,
      "loss": 9.2898,
      "step": 67
    },
    {
      "epoch": 0.024175628832992624,
      "grad_norm": 4.890848159790039,
      "learning_rate": 0.0002361492994024415,
      "loss": 10.3457,
      "step": 68
    },
    {
      "epoch": 0.024531152786418986,
      "grad_norm": 7.144769191741943,
      "learning_rate": 0.0002341072586027509,
      "loss": 9.929,
      "step": 69
    },
    {
      "epoch": 0.024886676739845348,
      "grad_norm": 5.622339248657227,
      "learning_rate": 0.00023204222371836405,
      "loss": 9.5537,
      "step": 70
    },
    {
      "epoch": 0.02524220069327171,
      "grad_norm": 8.047707557678223,
      "learning_rate": 0.00022995475930919905,
      "loss": 10.8773,
      "step": 71
    },
    {
      "epoch": 0.025597724646698072,
      "grad_norm": 5.305599689483643,
      "learning_rate": 0.00022784543606718227,
      "loss": 10.2004,
      "step": 72
    },
    {
      "epoch": 0.025953248600124434,
      "grad_norm": 5.336524963378906,
      "learning_rate": 0.00022571483066022657,
      "loss": 9.5412,
      "step": 73
    },
    {
      "epoch": 0.026308772553550797,
      "grad_norm": 5.118494987487793,
      "learning_rate": 0.0002235635255745762,
      "loss": 9.6813,
      "step": 74
    },
    {
      "epoch": 0.02666429650697716,
      "grad_norm": 4.906371116638184,
      "learning_rate": 0.00022139210895556104,
      "loss": 10.4721,
      "step": 75
    },
    {
      "epoch": 0.02666429650697716,
      "eval_loss": 2.505891799926758,
      "eval_runtime": 3.4096,
      "eval_samples_per_second": 14.665,
      "eval_steps_per_second": 2.053,
      "step": 75
    },
    {
      "epoch": 0.02701982046040352,
      "grad_norm": 4.981451511383057,
      "learning_rate": 0.00021920117444680317,
      "loss": 8.8563,
      "step": 76
    },
    {
      "epoch": 0.027375344413829883,
      "grad_norm": 4.70904016494751,
      "learning_rate": 0.00021699132102792097,
      "loss": 10.5626,
      "step": 77
    },
    {
      "epoch": 0.027730868367256245,
      "grad_norm": 5.6545233726501465,
      "learning_rate": 0.0002147631528507739,
      "loss": 11.0533,
      "step": 78
    },
    {
      "epoch": 0.028086392320682607,
      "grad_norm": 5.137275218963623,
      "learning_rate": 0.00021251727907429355,
      "loss": 10.8668,
      "step": 79
    },
    {
      "epoch": 0.02844191627410897,
      "grad_norm": 5.4811553955078125,
      "learning_rate": 0.0002102543136979454,
      "loss": 10.9318,
      "step": 80
    },
    {
      "epoch": 0.02879744022753533,
      "grad_norm": 5.466274261474609,
      "learning_rate": 0.0002079748753938678,
      "loss": 10.401,
      "step": 81
    },
    {
      "epoch": 0.029152964180961694,
      "grad_norm": 5.636516094207764,
      "learning_rate": 0.0002056795873377331,
      "loss": 10.0704,
      "step": 82
    },
    {
      "epoch": 0.029508488134388056,
      "grad_norm": 5.315571308135986,
      "learning_rate": 0.00020336907703837748,
      "loss": 11.0001,
      "step": 83
    },
    {
      "epoch": 0.029864012087814418,
      "grad_norm": 6.53507661819458,
      "learning_rate": 0.00020104397616624645,
      "loss": 11.992,
      "step": 84
    },
    {
      "epoch": 0.03021953604124078,
      "grad_norm": 5.709775924682617,
      "learning_rate": 0.00019870492038070252,
      "loss": 10.4158,
      "step": 85
    },
    {
      "epoch": 0.030575059994667142,
      "grad_norm": 5.086690425872803,
      "learning_rate": 0.0001963525491562421,
      "loss": 10.1491,
      "step": 86
    },
    {
      "epoch": 0.030930583948093504,
      "grad_norm": 5.827716827392578,
      "learning_rate": 0.0001939875056076697,
      "loss": 11.3729,
      "step": 87
    },
    {
      "epoch": 0.031286107901519866,
      "grad_norm": 5.376121520996094,
      "learning_rate": 0.00019161043631427666,
      "loss": 10.2509,
      "step": 88
    },
    {
      "epoch": 0.03164163185494623,
      "grad_norm": 5.2902445793151855,
      "learning_rate": 0.00018922199114307294,
      "loss": 9.9306,
      "step": 89
    },
    {
      "epoch": 0.03199715580837259,
      "grad_norm": 6.116251468658447,
      "learning_rate": 0.00018682282307111987,
      "loss": 11.4962,
      "step": 90
    },
    {
      "epoch": 0.03235267976179895,
      "grad_norm": 5.817269325256348,
      "learning_rate": 0.00018441358800701273,
      "loss": 10.5293,
      "step": 91
    },
    {
      "epoch": 0.032708203715225315,
      "grad_norm": 5.698713779449463,
      "learning_rate": 0.00018199494461156203,
      "loss": 9.9072,
      "step": 92
    },
    {
      "epoch": 0.03306372766865168,
      "grad_norm": 7.766204357147217,
      "learning_rate": 0.000179567554117722,
      "loss": 10.4333,
      "step": 93
    },
    {
      "epoch": 0.03341925162207804,
      "grad_norm": 6.0432939529418945,
      "learning_rate": 0.00017713208014981648,
      "loss": 11.2163,
      "step": 94
    },
    {
      "epoch": 0.0337747755755044,
      "grad_norm": 6.411512851715088,
      "learning_rate": 0.00017468918854211007,
      "loss": 11.3715,
      "step": 95
    },
    {
      "epoch": 0.03413029952893076,
      "grad_norm": 6.964004039764404,
      "learning_rate": 0.00017223954715677627,
      "loss": 10.0495,
      "step": 96
    },
    {
      "epoch": 0.034485823482357125,
      "grad_norm": 5.977689743041992,
      "learning_rate": 0.00016978382570131034,
      "loss": 10.9753,
      "step": 97
    },
    {
      "epoch": 0.03484134743578349,
      "grad_norm": 6.7813825607299805,
      "learning_rate": 0.00016732269554543794,
      "loss": 9.5063,
      "step": 98
    },
    {
      "epoch": 0.03519687138920985,
      "grad_norm": 6.9034318923950195,
      "learning_rate": 0.00016485682953756942,
      "loss": 10.1179,
      "step": 99
    },
    {
      "epoch": 0.03555239534263621,
      "grad_norm": 10.123339653015137,
      "learning_rate": 0.00016238690182084986,
      "loss": 9.7543,
      "step": 100
    },
    {
      "epoch": 0.03555239534263621,
      "eval_loss": 2.6253039836883545,
      "eval_runtime": 3.4096,
      "eval_samples_per_second": 14.665,
      "eval_steps_per_second": 2.053,
      "step": 100
    },
    {
      "epoch": 0.035907919296062574,
      "grad_norm": 8.50604248046875,
      "learning_rate": 0.0001599135876488549,
      "loss": 10.522,
      "step": 101
    },
    {
      "epoch": 0.036263443249488936,
      "grad_norm": 10.837066650390625,
      "learning_rate": 0.00015743756320098332,
      "loss": 8.8138,
      "step": 102
    },
    {
      "epoch": 0.0366189672029153,
      "grad_norm": 6.720249176025391,
      "learning_rate": 0.0001549595053975962,
      "loss": 7.2665,
      "step": 103
    },
    {
      "epoch": 0.03697449115634166,
      "grad_norm": 6.120709419250488,
      "learning_rate": 0.00015248009171495378,
      "loss": 10.0905,
      "step": 104
    },
    {
      "epoch": 0.03733001510976802,
      "grad_norm": 5.360714912414551,
      "learning_rate": 0.00015,
      "loss": 10.3304,
      "step": 105
    },
    {
      "epoch": 0.037685539063194384,
      "grad_norm": 6.324580669403076,
      "learning_rate": 0.00014751990828504622,
      "loss": 11.3479,
      "step": 106
    },
    {
      "epoch": 0.038041063016620746,
      "grad_norm": 5.683630466461182,
      "learning_rate": 0.00014504049460240375,
      "loss": 10.5964,
      "step": 107
    },
    {
      "epoch": 0.03839658697004711,
      "grad_norm": 4.51971435546875,
      "learning_rate": 0.00014256243679901663,
      "loss": 9.617,
      "step": 108
    },
    {
      "epoch": 0.03875211092347347,
      "grad_norm": 6.3022565841674805,
      "learning_rate": 0.00014008641235114508,
      "loss": 10.4929,
      "step": 109
    },
    {
      "epoch": 0.03910763487689983,
      "grad_norm": 6.827676296234131,
      "learning_rate": 0.00013761309817915014,
      "loss": 10.6284,
      "step": 110
    },
    {
      "epoch": 0.039463158830326195,
      "grad_norm": 5.795304298400879,
      "learning_rate": 0.00013514317046243058,
      "loss": 9.0099,
      "step": 111
    },
    {
      "epoch": 0.03981868278375256,
      "grad_norm": 5.27096700668335,
      "learning_rate": 0.00013267730445456208,
      "loss": 9.5003,
      "step": 112
    },
    {
      "epoch": 0.04017420673717892,
      "grad_norm": 5.735016345977783,
      "learning_rate": 0.00013021617429868963,
      "loss": 10.5266,
      "step": 113
    },
    {
      "epoch": 0.04052973069060528,
      "grad_norm": 5.17439079284668,
      "learning_rate": 0.00012776045284322368,
      "loss": 9.5267,
      "step": 114
    },
    {
      "epoch": 0.04088525464403164,
      "grad_norm": 5.072749614715576,
      "learning_rate": 0.00012531081145788987,
      "loss": 9.9992,
      "step": 115
    },
    {
      "epoch": 0.041240778597458005,
      "grad_norm": 4.426019191741943,
      "learning_rate": 0.00012286791985018355,
      "loss": 8.5191,
      "step": 116
    },
    {
      "epoch": 0.04159630255088437,
      "grad_norm": 5.0171027183532715,
      "learning_rate": 0.00012043244588227796,
      "loss": 10.0848,
      "step": 117
    },
    {
      "epoch": 0.04195182650431073,
      "grad_norm": 5.059338092803955,
      "learning_rate": 0.00011800505538843798,
      "loss": 9.6589,
      "step": 118
    },
    {
      "epoch": 0.04230735045773709,
      "grad_norm": 4.898255825042725,
      "learning_rate": 0.00011558641199298727,
      "loss": 9.9281,
      "step": 119
    },
    {
      "epoch": 0.042662874411163454,
      "grad_norm": 4.372053146362305,
      "learning_rate": 0.00011317717692888012,
      "loss": 9.323,
      "step": 120
    },
    {
      "epoch": 0.043018398364589816,
      "grad_norm": 5.065223693847656,
      "learning_rate": 0.00011077800885692702,
      "loss": 11.5742,
      "step": 121
    },
    {
      "epoch": 0.04337392231801618,
      "grad_norm": 5.381391525268555,
      "learning_rate": 0.00010838956368572334,
      "loss": 10.2001,
      "step": 122
    },
    {
      "epoch": 0.04372944627144254,
      "grad_norm": 4.845911026000977,
      "learning_rate": 0.0001060124943923303,
      "loss": 9.9141,
      "step": 123
    },
    {
      "epoch": 0.0440849702248689,
      "grad_norm": 5.539061069488525,
      "learning_rate": 0.0001036474508437579,
      "loss": 9.1523,
      "step": 124
    },
    {
      "epoch": 0.044440494178295264,
      "grad_norm": 4.919478893280029,
      "learning_rate": 0.00010129507961929748,
      "loss": 8.4648,
      "step": 125
    },
    {
      "epoch": 0.044440494178295264,
      "eval_loss": 2.34893536567688,
      "eval_runtime": 3.4101,
      "eval_samples_per_second": 14.662,
      "eval_steps_per_second": 2.053,
      "step": 125
    },
    {
      "epoch": 0.04479601813172163,
      "grad_norm": 5.182336807250977,
      "learning_rate": 9.895602383375353e-05,
      "loss": 9.3801,
      "step": 126
    },
    {
      "epoch": 0.04515154208514799,
      "grad_norm": 6.5174994468688965,
      "learning_rate": 9.663092296162251e-05,
      "loss": 9.7324,
      "step": 127
    },
    {
      "epoch": 0.04550706603857435,
      "grad_norm": 6.033017635345459,
      "learning_rate": 9.432041266226686e-05,
      "loss": 9.4699,
      "step": 128
    },
    {
      "epoch": 0.04586258999200071,
      "grad_norm": 5.28855562210083,
      "learning_rate": 9.202512460613219e-05,
      "loss": 10.3632,
      "step": 129
    },
    {
      "epoch": 0.046218113945427075,
      "grad_norm": 5.92414665222168,
      "learning_rate": 8.97456863020546e-05,
      "loss": 10.1867,
      "step": 130
    },
    {
      "epoch": 0.04657363789885344,
      "grad_norm": 5.728801250457764,
      "learning_rate": 8.748272092570646e-05,
      "loss": 9.5754,
      "step": 131
    },
    {
      "epoch": 0.0469291618522798,
      "grad_norm": 5.550567150115967,
      "learning_rate": 8.523684714922608e-05,
      "loss": 10.5313,
      "step": 132
    },
    {
      "epoch": 0.04728468580570616,
      "grad_norm": 5.983530521392822,
      "learning_rate": 8.300867897207903e-05,
      "loss": 8.9917,
      "step": 133
    },
    {
      "epoch": 0.047640209759132524,
      "grad_norm": 6.547121047973633,
      "learning_rate": 8.079882555319684e-05,
      "loss": 10.6116,
      "step": 134
    },
    {
      "epoch": 0.047995733712558886,
      "grad_norm": 6.877899169921875,
      "learning_rate": 7.860789104443896e-05,
      "loss": 10.4791,
      "step": 135
    },
    {
      "epoch": 0.04835125766598525,
      "grad_norm": 6.698514461517334,
      "learning_rate": 7.643647442542382e-05,
      "loss": 10.5741,
      "step": 136
    },
    {
      "epoch": 0.04870678161941161,
      "grad_norm": 5.82236385345459,
      "learning_rate": 7.428516933977347e-05,
      "loss": 10.0061,
      "step": 137
    },
    {
      "epoch": 0.04906230557283797,
      "grad_norm": 7.110109806060791,
      "learning_rate": 7.215456393281776e-05,
      "loss": 11.2455,
      "step": 138
    },
    {
      "epoch": 0.049417829526264334,
      "grad_norm": 5.919317245483398,
      "learning_rate": 7.004524069080096e-05,
      "loss": 10.2149,
      "step": 139
    },
    {
      "epoch": 0.049773353479690696,
      "grad_norm": 5.82124662399292,
      "learning_rate": 6.795777628163599e-05,
      "loss": 11.2277,
      "step": 140
    },
    {
      "epoch": 0.05012887743311706,
      "grad_norm": 5.727226734161377,
      "learning_rate": 6.58927413972491e-05,
      "loss": 10.3604,
      "step": 141
    },
    {
      "epoch": 0.05048440138654342,
      "grad_norm": 6.384329795837402,
      "learning_rate": 6.385070059755846e-05,
      "loss": 10.9996,
      "step": 142
    },
    {
      "epoch": 0.05083992533996978,
      "grad_norm": 7.032529354095459,
      "learning_rate": 6.183221215612904e-05,
      "loss": 9.4377,
      "step": 143
    },
    {
      "epoch": 0.051195449293396145,
      "grad_norm": 6.148966312408447,
      "learning_rate": 5.983782790754623e-05,
      "loss": 9.4402,
      "step": 144
    },
    {
      "epoch": 0.05155097324682251,
      "grad_norm": 7.128761291503906,
      "learning_rate": 5.786809309654982e-05,
      "loss": 9.2494,
      "step": 145
    },
    {
      "epoch": 0.05190649720024887,
      "grad_norm": 5.945568084716797,
      "learning_rate": 5.592354622896944e-05,
      "loss": 9.6517,
      "step": 146
    },
    {
      "epoch": 0.05226202115367523,
      "grad_norm": 6.259884834289551,
      "learning_rate": 5.40047189245025e-05,
      "loss": 9.2707,
      "step": 147
    },
    {
      "epoch": 0.05261754510710159,
      "grad_norm": 6.439622402191162,
      "learning_rate": 5.211213577137469e-05,
      "loss": 9.4341,
      "step": 148
    },
    {
      "epoch": 0.052973069060527955,
      "grad_norm": 6.414124011993408,
      "learning_rate": 5.024631418292274e-05,
      "loss": 9.6553,
      "step": 149
    },
    {
      "epoch": 0.05332859301395432,
      "grad_norm": 9.953978538513184,
      "learning_rate": 4.840776425613886e-05,
      "loss": 6.9357,
      "step": 150
    },
    {
      "epoch": 0.05332859301395432,
      "eval_loss": 2.314272403717041,
      "eval_runtime": 3.4086,
      "eval_samples_per_second": 14.669,
      "eval_steps_per_second": 2.054,
      "step": 150
    },
    {
      "epoch": 0.05368411696738068,
      "grad_norm": 8.713624954223633,
      "learning_rate": 4.659698863221513e-05,
      "loss": 8.3145,
      "step": 151
    },
    {
      "epoch": 0.05403964092080704,
      "grad_norm": 7.966327667236328,
      "learning_rate": 4.481448235912671e-05,
      "loss": 8.6993,
      "step": 152
    },
    {
      "epoch": 0.054395164874233404,
      "grad_norm": 6.538430690765381,
      "learning_rate": 4.306073275629044e-05,
      "loss": 7.6628,
      "step": 153
    },
    {
      "epoch": 0.054750688827659766,
      "grad_norm": 8.117944717407227,
      "learning_rate": 4.133621928133665e-05,
      "loss": 9.9395,
      "step": 154
    },
    {
      "epoch": 0.05510621278108613,
      "grad_norm": 7.285843849182129,
      "learning_rate": 3.964141339903026e-05,
      "loss": 9.6924,
      "step": 155
    },
    {
      "epoch": 0.05546173673451249,
      "grad_norm": 7.61773681640625,
      "learning_rate": 3.797677845237696e-05,
      "loss": 10.1125,
      "step": 156
    },
    {
      "epoch": 0.05581726068793885,
      "grad_norm": 5.755801200866699,
      "learning_rate": 3.634276953594982e-05,
      "loss": 9.539,
      "step": 157
    },
    {
      "epoch": 0.056172784641365214,
      "grad_norm": 5.638586521148682,
      "learning_rate": 3.473983337147118e-05,
      "loss": 9.2763,
      "step": 158
    },
    {
      "epoch": 0.056528308594791576,
      "grad_norm": 5.6890549659729,
      "learning_rate": 3.316840818568315e-05,
      "loss": 9.0826,
      "step": 159
    },
    {
      "epoch": 0.05688383254821794,
      "grad_norm": 5.357155799865723,
      "learning_rate": 3.162892359054098e-05,
      "loss": 10.1697,
      "step": 160
    },
    {
      "epoch": 0.0572393565016443,
      "grad_norm": 5.9341630935668945,
      "learning_rate": 3.0121800465761293e-05,
      "loss": 9.6203,
      "step": 161
    },
    {
      "epoch": 0.05759488045507066,
      "grad_norm": 5.837774753570557,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 10.0702,
      "step": 162
    },
    {
      "epoch": 0.057950404408497025,
      "grad_norm": 5.2682785987854,
      "learning_rate": 2.7206277796996144e-05,
      "loss": 9.561,
      "step": 163
    },
    {
      "epoch": 0.05830592836192339,
      "grad_norm": 5.310613632202148,
      "learning_rate": 2.5798675327796993e-05,
      "loss": 9.7458,
      "step": 164
    },
    {
      "epoch": 0.05866145231534975,
      "grad_norm": 5.741307258605957,
      "learning_rate": 2.4425028260620715e-05,
      "loss": 10.4844,
      "step": 165
    },
    {
      "epoch": 0.05901697626877611,
      "grad_norm": 6.544122219085693,
      "learning_rate": 2.3085712136859668e-05,
      "loss": 8.8046,
      "step": 166
    },
    {
      "epoch": 0.05937250022220247,
      "grad_norm": 6.212630271911621,
      "learning_rate": 2.178109311216913e-05,
      "loss": 10.0538,
      "step": 167
    },
    {
      "epoch": 0.059728024175628835,
      "grad_norm": 5.299189567565918,
      "learning_rate": 2.0511527856363912e-05,
      "loss": 10.2602,
      "step": 168
    },
    {
      "epoch": 0.0600835481290552,
      "grad_norm": 5.7751145362854,
      "learning_rate": 1.927736345590839e-05,
      "loss": 9.5055,
      "step": 169
    },
    {
      "epoch": 0.06043907208248156,
      "grad_norm": 5.401315212249756,
      "learning_rate": 1.8078937319026654e-05,
      "loss": 10.03,
      "step": 170
    },
    {
      "epoch": 0.06079459603590792,
      "grad_norm": 6.487131118774414,
      "learning_rate": 1.6916577083458228e-05,
      "loss": 10.216,
      "step": 171
    },
    {
      "epoch": 0.061150119989334284,
      "grad_norm": 5.753161907196045,
      "learning_rate": 1.579060052688548e-05,
      "loss": 9.377,
      "step": 172
    },
    {
      "epoch": 0.061505643942760646,
      "grad_norm": 6.108590602874756,
      "learning_rate": 1.4701315480056164e-05,
      "loss": 9.7962,
      "step": 173
    },
    {
      "epoch": 0.06186116789618701,
      "grad_norm": 6.228653907775879,
      "learning_rate": 1.3649019742625623e-05,
      "loss": 9.6701,
      "step": 174
    },
    {
      "epoch": 0.06221669184961337,
      "grad_norm": 4.956625461578369,
      "learning_rate": 1.2634001001741373e-05,
      "loss": 8.4442,
      "step": 175
    },
    {
      "epoch": 0.06221669184961337,
      "eval_loss": 2.2359719276428223,
      "eval_runtime": 3.4056,
      "eval_samples_per_second": 14.682,
      "eval_steps_per_second": 2.055,
      "step": 175
    },
    {
      "epoch": 0.06257221580303973,
      "grad_norm": 5.659938335418701,
      "learning_rate": 1.1656536753392287e-05,
      "loss": 9.1614,
      "step": 176
    },
    {
      "epoch": 0.0629277397564661,
      "grad_norm": 5.632331371307373,
      "learning_rate": 1.0716894226543953e-05,
      "loss": 9.2837,
      "step": 177
    },
    {
      "epoch": 0.06328326370989246,
      "grad_norm": 6.158392906188965,
      "learning_rate": 9.815330310080887e-06,
      "loss": 10.6873,
      "step": 178
    },
    {
      "epoch": 0.06363878766331882,
      "grad_norm": 5.655581951141357,
      "learning_rate": 8.952091482575824e-06,
      "loss": 9.3116,
      "step": 179
    },
    {
      "epoch": 0.06399431161674518,
      "grad_norm": 5.882752895355225,
      "learning_rate": 8.127413744904804e-06,
      "loss": 9.7047,
      "step": 180
    },
    {
      "epoch": 0.06434983557017154,
      "grad_norm": 6.070702075958252,
      "learning_rate": 7.34152255572697e-06,
      "loss": 10.2734,
      "step": 181
    },
    {
      "epoch": 0.0647053595235979,
      "grad_norm": 6.517852306365967,
      "learning_rate": 6.594632769846353e-06,
      "loss": 10.6647,
      "step": 182
    },
    {
      "epoch": 0.06506088347702427,
      "grad_norm": 6.227158069610596,
      "learning_rate": 5.886948579472778e-06,
      "loss": 9.2133,
      "step": 183
    },
    {
      "epoch": 0.06541640743045063,
      "grad_norm": 5.783818244934082,
      "learning_rate": 5.218663458397715e-06,
      "loss": 10.3477,
      "step": 184
    },
    {
      "epoch": 0.06577193138387699,
      "grad_norm": 5.751105308532715,
      "learning_rate": 4.589960109100444e-06,
      "loss": 9.6947,
      "step": 185
    },
    {
      "epoch": 0.06612745533730335,
      "grad_norm": 5.619855880737305,
      "learning_rate": 4.001010412799138e-06,
      "loss": 10.0627,
      "step": 186
    },
    {
      "epoch": 0.06648297929072972,
      "grad_norm": 5.333779335021973,
      "learning_rate": 3.451975382460109e-06,
      "loss": 9.7599,
      "step": 187
    },
    {
      "epoch": 0.06683850324415608,
      "grad_norm": 6.2255988121032715,
      "learning_rate": 2.9430051187785962e-06,
      "loss": 10.7451,
      "step": 188
    },
    {
      "epoch": 0.06719402719758244,
      "grad_norm": 6.961033344268799,
      "learning_rate": 2.4742387691426445e-06,
      "loss": 10.2383,
      "step": 189
    },
    {
      "epoch": 0.0675495511510088,
      "grad_norm": 6.666347026824951,
      "learning_rate": 2.0458044895916513e-06,
      "loss": 10.132,
      "step": 190
    },
    {
      "epoch": 0.06790507510443516,
      "grad_norm": 7.37328577041626,
      "learning_rate": 1.6578194097797258e-06,
      "loss": 10.2189,
      "step": 191
    },
    {
      "epoch": 0.06826059905786153,
      "grad_norm": 7.116367340087891,
      "learning_rate": 1.3103896009537207e-06,
      "loss": 9.9206,
      "step": 192
    },
    {
      "epoch": 0.06861612301128789,
      "grad_norm": 6.1720404624938965,
      "learning_rate": 1.0036100469542786e-06,
      "loss": 10.1334,
      "step": 193
    },
    {
      "epoch": 0.06897164696471425,
      "grad_norm": 9.900176048278809,
      "learning_rate": 7.375646182482875e-07,
      "loss": 9.7241,
      "step": 194
    },
    {
      "epoch": 0.06932717091814061,
      "grad_norm": 6.8333048820495605,
      "learning_rate": 5.123260489995229e-07,
      "loss": 10.0152,
      "step": 195
    },
    {
      "epoch": 0.06968269487156697,
      "grad_norm": 6.908794403076172,
      "learning_rate": 3.2795591718381975e-07,
      "loss": 10.0908,
      "step": 196
    },
    {
      "epoch": 0.07003821882499334,
      "grad_norm": 7.333555698394775,
      "learning_rate": 1.8450462775428942e-07,
      "loss": 10.8558,
      "step": 197
    },
    {
      "epoch": 0.0703937427784197,
      "grad_norm": 7.865172863006592,
      "learning_rate": 8.201139886109264e-08,
      "loss": 10.5989,
      "step": 198
    },
    {
      "epoch": 0.07074926673184606,
      "grad_norm": 8.003969192504883,
      "learning_rate": 2.0504251129649374e-08,
      "loss": 9.9646,
      "step": 199
    },
    {
      "epoch": 0.07110479068527242,
      "grad_norm": 9.733394622802734,
      "learning_rate": 0.0,
      "loss": 7.8091,
      "step": 200
    },
    {
      "epoch": 0.07110479068527242,
      "eval_loss": 2.242912530899048,
      "eval_runtime": 3.4081,
      "eval_samples_per_second": 14.671,
      "eval_steps_per_second": 2.054,
      "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": 2.7806688547858022e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}