{
  "best_metric": 0.7776356339454651,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.10675206832132372,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005337603416066186,
      "grad_norm": 0.21030399203300476,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.0292,
      "step": 1
    },
    {
      "epoch": 0.0005337603416066186,
      "eval_loss": 1.1873221397399902,
      "eval_runtime": 8.4145,
      "eval_samples_per_second": 5.942,
      "eval_steps_per_second": 0.832,
      "step": 1
    },
    {
      "epoch": 0.0010675206832132373,
      "grad_norm": 0.19265241920948029,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.9164,
      "step": 2
    },
    {
      "epoch": 0.0016012810248198558,
      "grad_norm": 0.18795327842235565,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.8732,
      "step": 3
    },
    {
      "epoch": 0.0021350413664264745,
      "grad_norm": 0.1864738166332245,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.7532,
      "step": 4
    },
    {
      "epoch": 0.0026688017080330933,
      "grad_norm": 0.19504335522651672,
      "learning_rate": 0.00015,
      "loss": 1.0093,
      "step": 5
    },
    {
      "epoch": 0.0032025620496397116,
      "grad_norm": 0.17015689611434937,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.024,
      "step": 6
    },
    {
      "epoch": 0.0037363223912463303,
      "grad_norm": 0.14508552849292755,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.8628,
      "step": 7
    },
    {
      "epoch": 0.004270082732852949,
      "grad_norm": 0.22223599255084991,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.8438,
      "step": 8
    },
    {
      "epoch": 0.004803843074459567,
      "grad_norm": 0.22927789390087128,
      "learning_rate": 0.00027,
      "loss": 0.9133,
      "step": 9
    },
    {
      "epoch": 0.0053376034160661865,
      "grad_norm": 0.20617060363292694,
      "learning_rate": 0.0003,
      "loss": 0.9452,
      "step": 10
    },
    {
      "epoch": 0.005871363757672805,
      "grad_norm": 0.15300868451595306,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.8835,
      "step": 11
    },
    {
      "epoch": 0.006405124099279423,
      "grad_norm": 0.12331876158714294,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.8207,
      "step": 12
    },
    {
      "epoch": 0.006938884440886042,
      "grad_norm": 0.12863071262836456,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.9267,
      "step": 13
    },
    {
      "epoch": 0.007472644782492661,
      "grad_norm": 0.12051154673099518,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.8229,
      "step": 14
    },
    {
      "epoch": 0.008006405124099279,
      "grad_norm": 0.14710567891597748,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.7377,
      "step": 15
    },
    {
      "epoch": 0.008540165465705898,
      "grad_norm": 0.13789963722229004,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.9229,
      "step": 16
    },
    {
      "epoch": 0.009073925807312517,
      "grad_norm": 0.16651029884815216,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.7604,
      "step": 17
    },
    {
      "epoch": 0.009607686148919135,
      "grad_norm": 0.12664462625980377,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.6897,
      "step": 18
    },
    {
      "epoch": 0.010141446490525754,
      "grad_norm": 0.1488250344991684,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.8952,
      "step": 19
    },
    {
      "epoch": 0.010675206832132373,
      "grad_norm": 0.15764887630939484,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.813,
      "step": 20
    },
    {
      "epoch": 0.01120896717373899,
      "grad_norm": 0.16447287797927856,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.7716,
      "step": 21
    },
    {
      "epoch": 0.01174272751534561,
      "grad_norm": 0.18892335891723633,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.9181,
      "step": 22
    },
    {
      "epoch": 0.012276487856952229,
      "grad_norm": 0.18801233172416687,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.8915,
      "step": 23
    },
    {
      "epoch": 0.012810248198558846,
      "grad_norm": 0.23430532217025757,
      "learning_rate": 0.0002959989895872009,
      "loss": 1.0565,
      "step": 24
    },
    {
      "epoch": 0.013344008540165465,
      "grad_norm": 0.232516810297966,
      "learning_rate": 0.0002954100398908995,
      "loss": 1.0213,
      "step": 25
    },
    {
      "epoch": 0.013344008540165465,
      "eval_loss": 0.8986374735832214,
      "eval_runtime": 8.546,
      "eval_samples_per_second": 5.851,
      "eval_steps_per_second": 0.819,
      "step": 25
    },
    {
      "epoch": 0.013877768881772085,
      "grad_norm": 0.27450525760650635,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.9864,
      "step": 26
    },
    {
      "epoch": 0.014411529223378704,
      "grad_norm": 0.3355092704296112,
      "learning_rate": 0.0002941130514205272,
      "loss": 1.0317,
      "step": 27
    },
    {
      "epoch": 0.014945289564985321,
      "grad_norm": 0.4094313681125641,
      "learning_rate": 0.0002934053672301536,
      "loss": 1.0007,
      "step": 28
    },
    {
      "epoch": 0.01547904990659194,
      "grad_norm": 0.3952488303184509,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.8705,
      "step": 29
    },
    {
      "epoch": 0.016012810248198558,
      "grad_norm": 0.48022404313087463,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.7177,
      "step": 30
    },
    {
      "epoch": 0.016546570589805177,
      "grad_norm": 0.47059381008148193,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.8944,
      "step": 31
    },
    {
      "epoch": 0.017080330931411796,
      "grad_norm": 0.4650598466396332,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.601,
      "step": 32
    },
    {
      "epoch": 0.017614091273018415,
      "grad_norm": 0.5162337422370911,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.6646,
      "step": 33
    },
    {
      "epoch": 0.018147851614625034,
      "grad_norm": 0.5358498692512512,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.6376,
      "step": 34
    },
    {
      "epoch": 0.018681611956231654,
      "grad_norm": 0.5043929219245911,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.6887,
      "step": 35
    },
    {
      "epoch": 0.01921537229783827,
      "grad_norm": 0.4514540433883667,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.642,
      "step": 36
    },
    {
      "epoch": 0.01974913263944489,
      "grad_norm": 0.5326736569404602,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.7795,
      "step": 37
    },
    {
      "epoch": 0.020282892981051508,
      "grad_norm": 0.44132864475250244,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.7115,
      "step": 38
    },
    {
      "epoch": 0.020816653322658127,
      "grad_norm": 0.5747407674789429,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.9388,
      "step": 39
    },
    {
      "epoch": 0.021350413664264746,
      "grad_norm": 0.6286762356758118,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.9211,
      "step": 40
    },
    {
      "epoch": 0.021884174005871365,
      "grad_norm": 1.5400742292404175,
      "learning_rate": 0.00028072263654409154,
      "loss": 1.6283,
      "step": 41
    },
    {
      "epoch": 0.02241793434747798,
      "grad_norm": 0.6354691386222839,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.8042,
      "step": 42
    },
    {
      "epoch": 0.0229516946890846,
      "grad_norm": 0.7523931860923767,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.9738,
      "step": 43
    },
    {
      "epoch": 0.02348545503069122,
      "grad_norm": 0.7767601013183594,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.7038,
      "step": 44
    },
    {
      "epoch": 0.02401921537229784,
      "grad_norm": 0.8243088722229004,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.8889,
      "step": 45
    },
    {
      "epoch": 0.024552975713904458,
      "grad_norm": 0.8106098175048828,
      "learning_rate": 0.000274201324672203,
      "loss": 0.6959,
      "step": 46
    },
    {
      "epoch": 0.025086736055511077,
      "grad_norm": 0.7986267805099487,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.9941,
      "step": 47
    },
    {
      "epoch": 0.025620496397117692,
      "grad_norm": 0.6979802846908569,
      "learning_rate": 0.0002713525491562421,
      "loss": 1.1686,
      "step": 48
    },
    {
      "epoch": 0.02615425673872431,
      "grad_norm": 0.9864975810050964,
      "learning_rate": 0.00026987819953423867,
      "loss": 1.6443,
      "step": 49
    },
    {
      "epoch": 0.02668801708033093,
      "grad_norm": 1.6048346757888794,
      "learning_rate": 0.00026837107640945905,
      "loss": 1.9021,
      "step": 50
    },
    {
      "epoch": 0.02668801708033093,
      "eval_loss": 0.9616906642913818,
      "eval_runtime": 8.5444,
      "eval_samples_per_second": 5.852,
      "eval_steps_per_second": 0.819,
      "step": 50
    },
    {
      "epoch": 0.02722177742193755,
      "grad_norm": 0.7169445157051086,
      "learning_rate": 0.0002668315918143169,
      "loss": 1.0791,
      "step": 51
    },
    {
      "epoch": 0.02775553776354417,
      "grad_norm": 0.4671402871608734,
      "learning_rate": 0.00026526016662852886,
      "loss": 0.9742,
      "step": 52
    },
    {
      "epoch": 0.02828929810515079,
      "grad_norm": 0.21854619681835175,
      "learning_rate": 0.00026365723046405023,
      "loss": 0.5941,
      "step": 53
    },
    {
      "epoch": 0.028823058446757407,
      "grad_norm": 0.19089387357234955,
      "learning_rate": 0.0002620232215476231,
      "loss": 0.7088,
      "step": 54
    },
    {
      "epoch": 0.029356818788364023,
      "grad_norm": 0.1763996034860611,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.7788,
      "step": 55
    },
    {
      "epoch": 0.029890579129970642,
      "grad_norm": 0.15595336258411407,
      "learning_rate": 0.00025866378071866334,
      "loss": 0.7146,
      "step": 56
    },
    {
      "epoch": 0.03042433947157726,
      "grad_norm": 0.14780502021312714,
      "learning_rate": 0.00025693926724370956,
      "loss": 0.6833,
      "step": 57
    },
    {
      "epoch": 0.03095809981318388,
      "grad_norm": 0.17299458384513855,
      "learning_rate": 0.00025518551764087326,
      "loss": 0.7231,
      "step": 58
    },
    {
      "epoch": 0.031491860154790496,
      "grad_norm": 0.18208518624305725,
      "learning_rate": 0.00025340301136778483,
      "loss": 0.8604,
      "step": 59
    },
    {
      "epoch": 0.032025620496397116,
      "grad_norm": 0.16208447515964508,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.8371,
      "step": 60
    },
    {
      "epoch": 0.032559380838003735,
      "grad_norm": 0.15310491621494293,
      "learning_rate": 0.0002497536858170772,
      "loss": 0.8561,
      "step": 61
    },
    {
      "epoch": 0.033093141179610354,
      "grad_norm": 0.15301284193992615,
      "learning_rate": 0.00024788786422862526,
      "loss": 0.7726,
      "step": 62
    },
    {
      "epoch": 0.03362690152121697,
      "grad_norm": 0.13006936013698578,
      "learning_rate": 0.00024599528107549745,
      "loss": 0.7302,
      "step": 63
    },
    {
      "epoch": 0.03416066186282359,
      "grad_norm": 0.13080370426177979,
      "learning_rate": 0.00024407645377103054,
      "loss": 0.7331,
      "step": 64
    },
    {
      "epoch": 0.03469442220443021,
      "grad_norm": 0.14722546935081482,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.7572,
      "step": 65
    },
    {
      "epoch": 0.03522818254603683,
      "grad_norm": 0.16325244307518005,
      "learning_rate": 0.00024016217209245374,
      "loss": 0.7179,
      "step": 66
    },
    {
      "epoch": 0.03576194288764345,
      "grad_norm": 0.1760217547416687,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.812,
      "step": 67
    },
    {
      "epoch": 0.03629570322925007,
      "grad_norm": 0.15352703630924225,
      "learning_rate": 0.0002361492994024415,
      "loss": 0.6364,
      "step": 68
    },
    {
      "epoch": 0.03682946357085669,
      "grad_norm": 0.17676758766174316,
      "learning_rate": 0.0002341072586027509,
      "loss": 0.7238,
      "step": 69
    },
    {
      "epoch": 0.03736322391246331,
      "grad_norm": 0.1657458245754242,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.7399,
      "step": 70
    },
    {
      "epoch": 0.03789698425406992,
      "grad_norm": 0.19465292990207672,
      "learning_rate": 0.00022995475930919905,
      "loss": 0.7834,
      "step": 71
    },
    {
      "epoch": 0.03843074459567654,
      "grad_norm": 0.21434198319911957,
      "learning_rate": 0.00022784543606718227,
      "loss": 0.7693,
      "step": 72
    },
    {
      "epoch": 0.03896450493728316,
      "grad_norm": 0.22707851231098175,
      "learning_rate": 0.00022571483066022657,
      "loss": 0.8932,
      "step": 73
    },
    {
      "epoch": 0.03949826527888978,
      "grad_norm": 0.19171050190925598,
      "learning_rate": 0.0002235635255745762,
      "loss": 0.8832,
      "step": 74
    },
    {
      "epoch": 0.040032025620496396,
      "grad_norm": 0.24807709455490112,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.8486,
      "step": 75
    },
    {
      "epoch": 0.040032025620496396,
      "eval_loss": 0.8277331590652466,
      "eval_runtime": 8.557,
      "eval_samples_per_second": 5.843,
      "eval_steps_per_second": 0.818,
      "step": 75
    },
    {
      "epoch": 0.040565785962103015,
      "grad_norm": 0.24164411425590515,
      "learning_rate": 0.00021920117444680317,
      "loss": 0.8722,
      "step": 76
    },
    {
      "epoch": 0.041099546303709635,
      "grad_norm": 0.2500685155391693,
      "learning_rate": 0.00021699132102792097,
      "loss": 0.9,
      "step": 77
    },
    {
      "epoch": 0.041633306645316254,
      "grad_norm": 0.29831573367118835,
      "learning_rate": 0.0002147631528507739,
      "loss": 0.9498,
      "step": 78
    },
    {
      "epoch": 0.04216706698692287,
      "grad_norm": 0.2891542613506317,
      "learning_rate": 0.00021251727907429355,
      "loss": 0.8771,
      "step": 79
    },
    {
      "epoch": 0.04270082732852949,
      "grad_norm": 0.2749815583229065,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.7353,
      "step": 80
    },
    {
      "epoch": 0.04323458767013611,
      "grad_norm": 0.3279361128807068,
      "learning_rate": 0.0002079748753938678,
      "loss": 0.6975,
      "step": 81
    },
    {
      "epoch": 0.04376834801174273,
      "grad_norm": 0.3204759657382965,
      "learning_rate": 0.0002056795873377331,
      "loss": 0.6162,
      "step": 82
    },
    {
      "epoch": 0.04430210835334935,
      "grad_norm": 0.3467862904071808,
      "learning_rate": 0.00020336907703837748,
      "loss": 0.5846,
      "step": 83
    },
    {
      "epoch": 0.04483586869495596,
      "grad_norm": 0.42016375064849854,
      "learning_rate": 0.00020104397616624645,
      "loss": 0.5752,
      "step": 84
    },
    {
      "epoch": 0.04536962903656258,
      "grad_norm": 0.3800203502178192,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.6557,
      "step": 85
    },
    {
      "epoch": 0.0459033893781692,
      "grad_norm": 0.38055434823036194,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.4237,
      "step": 86
    },
    {
      "epoch": 0.04643714971977582,
      "grad_norm": 0.653908371925354,
      "learning_rate": 0.0001939875056076697,
      "loss": 0.5485,
      "step": 87
    },
    {
      "epoch": 0.04697091006138244,
      "grad_norm": 0.5021263957023621,
      "learning_rate": 0.00019161043631427666,
      "loss": 0.6399,
      "step": 88
    },
    {
      "epoch": 0.04750467040298906,
      "grad_norm": 0.6231861710548401,
      "learning_rate": 0.00018922199114307294,
      "loss": 0.6163,
      "step": 89
    },
    {
      "epoch": 0.04803843074459568,
      "grad_norm": 0.818639874458313,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.6114,
      "step": 90
    },
    {
      "epoch": 0.048572191086202296,
      "grad_norm": 0.7167706489562988,
      "learning_rate": 0.00018441358800701273,
      "loss": 0.5995,
      "step": 91
    },
    {
      "epoch": 0.049105951427808915,
      "grad_norm": 0.5616716742515564,
      "learning_rate": 0.00018199494461156203,
      "loss": 0.6759,
      "step": 92
    },
    {
      "epoch": 0.049639711769415534,
      "grad_norm": 0.5227298140525818,
      "learning_rate": 0.000179567554117722,
      "loss": 0.5994,
      "step": 93
    },
    {
      "epoch": 0.050173472111022153,
      "grad_norm": 0.6581361293792725,
      "learning_rate": 0.00017713208014981648,
      "loss": 0.4901,
      "step": 94
    },
    {
      "epoch": 0.05070723245262877,
      "grad_norm": 0.6080806255340576,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.5543,
      "step": 95
    },
    {
      "epoch": 0.051240992794235385,
      "grad_norm": 0.5447089076042175,
      "learning_rate": 0.00017223954715677627,
      "loss": 0.5089,
      "step": 96
    },
    {
      "epoch": 0.051774753135842004,
      "grad_norm": 0.7999978065490723,
      "learning_rate": 0.00016978382570131034,
      "loss": 0.8464,
      "step": 97
    },
    {
      "epoch": 0.05230851347744862,
      "grad_norm": 0.8551626205444336,
      "learning_rate": 0.00016732269554543794,
      "loss": 0.9699,
      "step": 98
    },
    {
      "epoch": 0.05284227381905524,
      "grad_norm": 1.0573757886886597,
      "learning_rate": 0.00016485682953756942,
      "loss": 1.4928,
      "step": 99
    },
    {
      "epoch": 0.05337603416066186,
      "grad_norm": 1.3176006078720093,
      "learning_rate": 0.00016238690182084986,
      "loss": 1.6708,
      "step": 100
    },
    {
      "epoch": 0.05337603416066186,
      "eval_loss": 0.842303454875946,
      "eval_runtime": 8.54,
      "eval_samples_per_second": 5.855,
      "eval_steps_per_second": 0.82,
      "step": 100
    },
    {
      "epoch": 0.05390979450226848,
      "grad_norm": 0.41997581720352173,
      "learning_rate": 0.0001599135876488549,
      "loss": 1.0473,
      "step": 101
    },
    {
      "epoch": 0.0544435548438751,
      "grad_norm": 0.35345515608787537,
      "learning_rate": 0.00015743756320098332,
      "loss": 0.85,
      "step": 102
    },
    {
      "epoch": 0.05497731518548172,
      "grad_norm": 0.2466951459646225,
      "learning_rate": 0.0001549595053975962,
      "loss": 0.65,
      "step": 103
    },
    {
      "epoch": 0.05551107552708834,
      "grad_norm": 0.2203168272972107,
      "learning_rate": 0.00015248009171495378,
      "loss": 0.6473,
      "step": 104
    },
    {
      "epoch": 0.05604483586869496,
      "grad_norm": 0.19800366461277008,
      "learning_rate": 0.00015,
      "loss": 0.7189,
      "step": 105
    },
    {
      "epoch": 0.05657859621030158,
      "grad_norm": 0.22387845814228058,
      "learning_rate": 0.00014751990828504622,
      "loss": 0.8798,
      "step": 106
    },
    {
      "epoch": 0.057112356551908196,
      "grad_norm": 0.1651087999343872,
      "learning_rate": 0.00014504049460240375,
      "loss": 0.7402,
      "step": 107
    },
    {
      "epoch": 0.057646116893514815,
      "grad_norm": 0.17520180344581604,
      "learning_rate": 0.00014256243679901663,
      "loss": 0.7301,
      "step": 108
    },
    {
      "epoch": 0.05817987723512143,
      "grad_norm": 0.15045854449272156,
      "learning_rate": 0.00014008641235114508,
      "loss": 0.7576,
      "step": 109
    },
    {
      "epoch": 0.058713637576728046,
      "grad_norm": 0.14351311326026917,
      "learning_rate": 0.00013761309817915014,
      "loss": 0.7368,
      "step": 110
    },
    {
      "epoch": 0.059247397918334666,
      "grad_norm": 0.16061748564243317,
      "learning_rate": 0.00013514317046243058,
      "loss": 0.7314,
      "step": 111
    },
    {
      "epoch": 0.059781158259941285,
      "grad_norm": 0.15314024686813354,
      "learning_rate": 0.00013267730445456208,
      "loss": 0.8795,
      "step": 112
    },
    {
      "epoch": 0.060314918601547904,
      "grad_norm": 0.12754754722118378,
      "learning_rate": 0.00013021617429868963,
      "loss": 0.7307,
      "step": 113
    },
    {
      "epoch": 0.06084867894315452,
      "grad_norm": 0.13579390943050385,
      "learning_rate": 0.00012776045284322368,
      "loss": 0.7191,
      "step": 114
    },
    {
      "epoch": 0.06138243928476114,
      "grad_norm": 0.14304156601428986,
      "learning_rate": 0.00012531081145788987,
      "loss": 0.6623,
      "step": 115
    },
    {
      "epoch": 0.06191619962636776,
      "grad_norm": 0.1579105108976364,
      "learning_rate": 0.00012286791985018355,
      "loss": 0.7182,
      "step": 116
    },
    {
      "epoch": 0.06244995996797438,
      "grad_norm": 0.15043635666370392,
      "learning_rate": 0.00012043244588227796,
      "loss": 0.583,
      "step": 117
    },
    {
      "epoch": 0.06298372030958099,
      "grad_norm": 0.1684529185295105,
      "learning_rate": 0.00011800505538843798,
      "loss": 0.6604,
      "step": 118
    },
    {
      "epoch": 0.06351748065118762,
      "grad_norm": 0.16202481091022491,
      "learning_rate": 0.00011558641199298727,
      "loss": 0.6118,
      "step": 119
    },
    {
      "epoch": 0.06405124099279423,
      "grad_norm": 0.18917706608772278,
      "learning_rate": 0.00011317717692888012,
      "loss": 0.8129,
      "step": 120
    },
    {
      "epoch": 0.06458500133440086,
      "grad_norm": 0.18614037334918976,
      "learning_rate": 0.00011077800885692702,
      "loss": 0.7546,
      "step": 121
    },
    {
      "epoch": 0.06511876167600747,
      "grad_norm": 0.18998053669929504,
      "learning_rate": 0.00010838956368572334,
      "loss": 0.7052,
      "step": 122
    },
    {
      "epoch": 0.0656525220176141,
      "grad_norm": 0.1965724527835846,
      "learning_rate": 0.0001060124943923303,
      "loss": 0.7949,
      "step": 123
    },
    {
      "epoch": 0.06618628235922071,
      "grad_norm": 0.23425693809986115,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.9352,
      "step": 124
    },
    {
      "epoch": 0.06672004270082733,
      "grad_norm": 0.23918041586875916,
      "learning_rate": 0.00010129507961929748,
      "loss": 0.742,
      "step": 125
    },
    {
      "epoch": 0.06672004270082733,
      "eval_loss": 0.7936726212501526,
      "eval_runtime": 8.5376,
      "eval_samples_per_second": 5.856,
      "eval_steps_per_second": 0.82,
      "step": 125
    },
    {
      "epoch": 0.06725380304243395,
      "grad_norm": 0.2907886207103729,
      "learning_rate": 9.895602383375353e-05,
      "loss": 0.7562,
      "step": 126
    },
    {
      "epoch": 0.06778756338404057,
      "grad_norm": 0.2939864695072174,
      "learning_rate": 9.663092296162251e-05,
      "loss": 0.7447,
      "step": 127
    },
    {
      "epoch": 0.06832132372564718,
      "grad_norm": 0.2739841639995575,
      "learning_rate": 9.432041266226686e-05,
      "loss": 0.779,
      "step": 128
    },
    {
      "epoch": 0.0688550840672538,
      "grad_norm": 0.2792784869670868,
      "learning_rate": 9.202512460613219e-05,
      "loss": 0.7842,
      "step": 129
    },
    {
      "epoch": 0.06938884440886042,
      "grad_norm": 0.3062306344509125,
      "learning_rate": 8.97456863020546e-05,
      "loss": 0.6149,
      "step": 130
    },
    {
      "epoch": 0.06992260475046704,
      "grad_norm": 0.2703125774860382,
      "learning_rate": 8.748272092570646e-05,
      "loss": 0.5391,
      "step": 131
    },
    {
      "epoch": 0.07045636509207366,
      "grad_norm": 0.2713692784309387,
      "learning_rate": 8.523684714922608e-05,
      "loss": 0.4925,
      "step": 132
    },
    {
      "epoch": 0.07099012543368027,
      "grad_norm": 0.29232826828956604,
      "learning_rate": 8.300867897207903e-05,
      "loss": 0.5386,
      "step": 133
    },
    {
      "epoch": 0.0715238857752869,
      "grad_norm": 0.3139735758304596,
      "learning_rate": 8.079882555319684e-05,
      "loss": 0.4719,
      "step": 134
    },
    {
      "epoch": 0.07205764611689351,
      "grad_norm": 0.319461852312088,
      "learning_rate": 7.860789104443896e-05,
      "loss": 0.6369,
      "step": 135
    },
    {
      "epoch": 0.07259140645850014,
      "grad_norm": 0.3390499949455261,
      "learning_rate": 7.643647442542382e-05,
      "loss": 0.5597,
      "step": 136
    },
    {
      "epoch": 0.07312516680010675,
      "grad_norm": 0.4175979197025299,
      "learning_rate": 7.428516933977347e-05,
      "loss": 0.6021,
      "step": 137
    },
    {
      "epoch": 0.07365892714171338,
      "grad_norm": 0.35204628109931946,
      "learning_rate": 7.215456393281776e-05,
      "loss": 0.453,
      "step": 138
    },
    {
      "epoch": 0.07419268748331999,
      "grad_norm": 0.45142585039138794,
      "learning_rate": 7.004524069080096e-05,
      "loss": 0.5564,
      "step": 139
    },
    {
      "epoch": 0.07472644782492661,
      "grad_norm": 1.1171234846115112,
      "learning_rate": 6.795777628163599e-05,
      "loss": 0.4785,
      "step": 140
    },
    {
      "epoch": 0.07526020816653323,
      "grad_norm": 0.4686049222946167,
      "learning_rate": 6.58927413972491e-05,
      "loss": 0.6147,
      "step": 141
    },
    {
      "epoch": 0.07579396850813984,
      "grad_norm": 0.4740322232246399,
      "learning_rate": 6.385070059755846e-05,
      "loss": 0.7019,
      "step": 142
    },
    {
      "epoch": 0.07632772884974647,
      "grad_norm": 0.49105554819107056,
      "learning_rate": 6.183221215612904e-05,
      "loss": 0.6943,
      "step": 143
    },
    {
      "epoch": 0.07686148919135308,
      "grad_norm": 0.5147189497947693,
      "learning_rate": 5.983782790754623e-05,
      "loss": 0.4911,
      "step": 144
    },
    {
      "epoch": 0.0773952495329597,
      "grad_norm": 0.5466910600662231,
      "learning_rate": 5.786809309654982e-05,
      "loss": 0.6712,
      "step": 145
    },
    {
      "epoch": 0.07792900987456632,
      "grad_norm": 0.550325870513916,
      "learning_rate": 5.592354622896944e-05,
      "loss": 0.6235,
      "step": 146
    },
    {
      "epoch": 0.07846277021617294,
      "grad_norm": 0.6209217309951782,
      "learning_rate": 5.40047189245025e-05,
      "loss": 0.801,
      "step": 147
    },
    {
      "epoch": 0.07899653055777955,
      "grad_norm": 0.6642343401908875,
      "learning_rate": 5.211213577137469e-05,
      "loss": 0.8934,
      "step": 148
    },
    {
      "epoch": 0.07953029089938618,
      "grad_norm": 0.9150252342224121,
      "learning_rate": 5.024631418292274e-05,
      "loss": 0.9947,
      "step": 149
    },
    {
      "epoch": 0.08006405124099279,
      "grad_norm": 1.090462565422058,
      "learning_rate": 4.840776425613886e-05,
      "loss": 1.1159,
      "step": 150
    },
    {
      "epoch": 0.08006405124099279,
      "eval_loss": 0.8031909465789795,
      "eval_runtime": 8.5418,
      "eval_samples_per_second": 5.854,
      "eval_steps_per_second": 0.82,
      "step": 150
    },
    {
      "epoch": 0.08059781158259942,
      "grad_norm": 0.22424638271331787,
      "learning_rate": 4.659698863221513e-05,
      "loss": 0.8929,
      "step": 151
    },
    {
      "epoch": 0.08113157192420603,
      "grad_norm": 0.21926997601985931,
      "learning_rate": 4.481448235912671e-05,
      "loss": 0.7804,
      "step": 152
    },
    {
      "epoch": 0.08166533226581266,
      "grad_norm": 0.1946469396352768,
      "learning_rate": 4.306073275629044e-05,
      "loss": 0.5875,
      "step": 153
    },
    {
      "epoch": 0.08219909260741927,
      "grad_norm": 0.224387064576149,
      "learning_rate": 4.133621928133665e-05,
      "loss": 0.5804,
      "step": 154
    },
    {
      "epoch": 0.08273285294902588,
      "grad_norm": 0.19957810640335083,
      "learning_rate": 3.964141339903026e-05,
      "loss": 0.6845,
      "step": 155
    },
    {
      "epoch": 0.08326661329063251,
      "grad_norm": 0.19750872254371643,
      "learning_rate": 3.797677845237696e-05,
      "loss": 0.7725,
      "step": 156
    },
    {
      "epoch": 0.08380037363223912,
      "grad_norm": 0.19317828118801117,
      "learning_rate": 3.634276953594982e-05,
      "loss": 0.7535,
      "step": 157
    },
    {
      "epoch": 0.08433413397384575,
      "grad_norm": 0.18441618978977203,
      "learning_rate": 3.473983337147118e-05,
      "loss": 0.727,
      "step": 158
    },
    {
      "epoch": 0.08486789431545236,
      "grad_norm": 0.17659269273281097,
      "learning_rate": 3.316840818568315e-05,
      "loss": 0.7734,
      "step": 159
    },
    {
      "epoch": 0.08540165465705898,
      "grad_norm": 0.1908242404460907,
      "learning_rate": 3.162892359054098e-05,
      "loss": 0.6538,
      "step": 160
    },
    {
      "epoch": 0.0859354149986656,
      "grad_norm": 0.16535666584968567,
      "learning_rate": 3.0121800465761293e-05,
      "loss": 0.6792,
      "step": 161
    },
    {
      "epoch": 0.08646917534027222,
      "grad_norm": 0.1628248691558838,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.6498,
      "step": 162
    },
    {
      "epoch": 0.08700293568187883,
      "grad_norm": 0.15709134936332703,
      "learning_rate": 2.7206277796996144e-05,
      "loss": 0.7424,
      "step": 163
    },
    {
      "epoch": 0.08753669602348546,
      "grad_norm": 0.15620659291744232,
      "learning_rate": 2.5798675327796993e-05,
      "loss": 0.622,
      "step": 164
    },
    {
      "epoch": 0.08807045636509207,
      "grad_norm": 0.15363053977489471,
      "learning_rate": 2.4425028260620715e-05,
      "loss": 0.6708,
      "step": 165
    },
    {
      "epoch": 0.0886042167066987,
      "grad_norm": 0.17389169335365295,
      "learning_rate": 2.3085712136859668e-05,
      "loss": 0.7038,
      "step": 166
    },
    {
      "epoch": 0.08913797704830531,
      "grad_norm": 0.17458435893058777,
      "learning_rate": 2.178109311216913e-05,
      "loss": 0.5587,
      "step": 167
    },
    {
      "epoch": 0.08967173738991192,
      "grad_norm": 0.18360799551010132,
      "learning_rate": 2.0511527856363912e-05,
      "loss": 0.7867,
      "step": 168
    },
    {
      "epoch": 0.09020549773151855,
      "grad_norm": 0.17545649409294128,
      "learning_rate": 1.927736345590839e-05,
      "loss": 0.7613,
      "step": 169
    },
    {
      "epoch": 0.09073925807312516,
      "grad_norm": 0.20500288903713226,
      "learning_rate": 1.8078937319026654e-05,
      "loss": 0.6963,
      "step": 170
    },
    {
      "epoch": 0.09127301841473179,
      "grad_norm": 0.1982969343662262,
      "learning_rate": 1.6916577083458228e-05,
      "loss": 0.7627,
      "step": 171
    },
    {
      "epoch": 0.0918067787563384,
      "grad_norm": 0.20568282902240753,
      "learning_rate": 1.579060052688548e-05,
      "loss": 0.7856,
      "step": 172
    },
    {
      "epoch": 0.09234053909794503,
      "grad_norm": 0.24100317060947418,
      "learning_rate": 1.4701315480056164e-05,
      "loss": 0.6432,
      "step": 173
    },
    {
      "epoch": 0.09287429943955164,
      "grad_norm": 0.23193538188934326,
      "learning_rate": 1.3649019742625623e-05,
      "loss": 0.8268,
      "step": 174
    },
    {
      "epoch": 0.09340805978115826,
      "grad_norm": 0.2548185884952545,
      "learning_rate": 1.2634001001741373e-05,
      "loss": 0.7186,
      "step": 175
    },
    {
      "epoch": 0.09340805978115826,
      "eval_loss": 0.7821811437606812,
      "eval_runtime": 8.5383,
      "eval_samples_per_second": 5.856,
      "eval_steps_per_second": 0.82,
      "step": 175
    },
    {
      "epoch": 0.09394182012276488,
      "grad_norm": 0.2970718741416931,
      "learning_rate": 1.1656536753392287e-05,
      "loss": 0.6491,
      "step": 176
    },
    {
      "epoch": 0.0944755804643715,
      "grad_norm": 0.3625304400920868,
      "learning_rate": 1.0716894226543953e-05,
      "loss": 0.6183,
      "step": 177
    },
    {
      "epoch": 0.09500934080597812,
      "grad_norm": 0.3171631395816803,
      "learning_rate": 9.815330310080887e-06,
      "loss": 0.8154,
      "step": 178
    },
    {
      "epoch": 0.09554310114758474,
      "grad_norm": 0.26550373435020447,
      "learning_rate": 8.952091482575824e-06,
      "loss": 0.7494,
      "step": 179
    },
    {
      "epoch": 0.09607686148919135,
      "grad_norm": 0.3588647246360779,
      "learning_rate": 8.127413744904804e-06,
      "loss": 0.5587,
      "step": 180
    },
    {
      "epoch": 0.09661062183079797,
      "grad_norm": 0.32790133357048035,
      "learning_rate": 7.34152255572697e-06,
      "loss": 0.5329,
      "step": 181
    },
    {
      "epoch": 0.09714438217240459,
      "grad_norm": 0.4465741515159607,
      "learning_rate": 6.594632769846353e-06,
      "loss": 0.3294,
      "step": 182
    },
    {
      "epoch": 0.0976781425140112,
      "grad_norm": 0.33372461795806885,
      "learning_rate": 5.886948579472778e-06,
      "loss": 0.386,
      "step": 183
    },
    {
      "epoch": 0.09821190285561783,
      "grad_norm": 0.38536709547042847,
      "learning_rate": 5.218663458397715e-06,
      "loss": 0.6134,
      "step": 184
    },
    {
      "epoch": 0.09874566319722444,
      "grad_norm": 0.3927061855792999,
      "learning_rate": 4.589960109100444e-06,
      "loss": 0.3782,
      "step": 185
    },
    {
      "epoch": 0.09927942353883107,
      "grad_norm": 0.41644033789634705,
      "learning_rate": 4.001010412799138e-06,
      "loss": 0.3936,
      "step": 186
    },
    {
      "epoch": 0.09981318388043768,
      "grad_norm": 0.38533538579940796,
      "learning_rate": 3.451975382460109e-06,
      "loss": 0.478,
      "step": 187
    },
    {
      "epoch": 0.10034694422204431,
      "grad_norm": 0.3394060730934143,
      "learning_rate": 2.9430051187785962e-06,
      "loss": 0.5653,
      "step": 188
    },
    {
      "epoch": 0.10088070456365092,
      "grad_norm": 0.47515639662742615,
      "learning_rate": 2.4742387691426445e-06,
      "loss": 0.6107,
      "step": 189
    },
    {
      "epoch": 0.10141446490525755,
      "grad_norm": 0.7346295118331909,
      "learning_rate": 2.0458044895916513e-06,
      "loss": 0.3244,
      "step": 190
    },
    {
      "epoch": 0.10194822524686416,
      "grad_norm": 0.41510871052742004,
      "learning_rate": 1.6578194097797258e-06,
      "loss": 0.5225,
      "step": 191
    },
    {
      "epoch": 0.10248198558847077,
      "grad_norm": 0.43027785420417786,
      "learning_rate": 1.3103896009537207e-06,
      "loss": 0.6227,
      "step": 192
    },
    {
      "epoch": 0.1030157459300774,
      "grad_norm": 0.4818989932537079,
      "learning_rate": 1.0036100469542786e-06,
      "loss": 0.6171,
      "step": 193
    },
    {
      "epoch": 0.10354950627168401,
      "grad_norm": 0.4520052373409271,
      "learning_rate": 7.375646182482875e-07,
      "loss": 0.5551,
      "step": 194
    },
    {
      "epoch": 0.10408326661329063,
      "grad_norm": 0.4551260769367218,
      "learning_rate": 5.123260489995229e-07,
      "loss": 0.4864,
      "step": 195
    },
    {
      "epoch": 0.10461702695489725,
      "grad_norm": 0.5285947918891907,
      "learning_rate": 3.2795591718381975e-07,
      "loss": 0.7324,
      "step": 196
    },
    {
      "epoch": 0.10515078729650387,
      "grad_norm": 0.6320045590400696,
      "learning_rate": 1.8450462775428942e-07,
      "loss": 0.7488,
      "step": 197
    },
    {
      "epoch": 0.10568454763811048,
      "grad_norm": 0.6292834877967834,
      "learning_rate": 8.201139886109264e-08,
      "loss": 0.9015,
      "step": 198
    },
    {
      "epoch": 0.10621830797971711,
      "grad_norm": 0.8106058239936829,
      "learning_rate": 2.0504251129649374e-08,
      "loss": 1.0793,
      "step": 199
    },
    {
      "epoch": 0.10675206832132372,
      "grad_norm": 1.118652582168579,
      "learning_rate": 0.0,
      "loss": 1.5208,
      "step": 200
    },
    {
      "epoch": 0.10675206832132372,
      "eval_loss": 0.7776356339454651,
      "eval_runtime": 8.533,
      "eval_samples_per_second": 5.86,
      "eval_steps_per_second": 0.82,
      "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": 1.4133880444944384e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}