{
  "best_metric": 10.339578628540039,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.03164306621311605,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015821533106558027,
      "grad_norm": 0.021875889971852303,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 10.3791,
      "step": 1
    },
    {
      "epoch": 0.00015821533106558027,
      "eval_loss": 10.377472877502441,
      "eval_runtime": 0.2334,
      "eval_samples_per_second": 214.26,
      "eval_steps_per_second": 29.996,
      "step": 1
    },
    {
      "epoch": 0.00031643066213116053,
      "grad_norm": 0.01897057332098484,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 10.3802,
      "step": 2
    },
    {
      "epoch": 0.00047464599319674077,
      "grad_norm": 0.02046719379723072,
      "learning_rate": 8.999999999999999e-05,
      "loss": 10.38,
      "step": 3
    },
    {
      "epoch": 0.0006328613242623211,
      "grad_norm": 0.0207586158066988,
      "learning_rate": 0.00011999999999999999,
      "loss": 10.3793,
      "step": 4
    },
    {
      "epoch": 0.0007910766553279013,
      "grad_norm": 0.02066042460501194,
      "learning_rate": 0.00015,
      "loss": 10.3792,
      "step": 5
    },
    {
      "epoch": 0.0009492919863934815,
      "grad_norm": 0.017435528337955475,
      "learning_rate": 0.00017999999999999998,
      "loss": 10.3774,
      "step": 6
    },
    {
      "epoch": 0.0011075073174590618,
      "grad_norm": 0.017935169860720634,
      "learning_rate": 0.00020999999999999998,
      "loss": 10.3775,
      "step": 7
    },
    {
      "epoch": 0.0012657226485246421,
      "grad_norm": 0.01680966652929783,
      "learning_rate": 0.00023999999999999998,
      "loss": 10.3771,
      "step": 8
    },
    {
      "epoch": 0.0014239379795902222,
      "grad_norm": 0.0188757311552763,
      "learning_rate": 0.00027,
      "loss": 10.3776,
      "step": 9
    },
    {
      "epoch": 0.0015821533106558025,
      "grad_norm": 0.01867961883544922,
      "learning_rate": 0.0003,
      "loss": 10.3769,
      "step": 10
    },
    {
      "epoch": 0.0017403686417213828,
      "grad_norm": 0.020418278872966766,
      "learning_rate": 0.0002999794957488703,
      "loss": 10.3758,
      "step": 11
    },
    {
      "epoch": 0.001898583972786963,
      "grad_norm": 0.022927168756723404,
      "learning_rate": 0.0002999179886011389,
      "loss": 10.3774,
      "step": 12
    },
    {
      "epoch": 0.002056799303852543,
      "grad_norm": 0.021069170907139778,
      "learning_rate": 0.0002998154953722457,
      "loss": 10.3773,
      "step": 13
    },
    {
      "epoch": 0.0022150146349181237,
      "grad_norm": 0.02218622900545597,
      "learning_rate": 0.00029967204408281613,
      "loss": 10.3762,
      "step": 14
    },
    {
      "epoch": 0.0023732299659837038,
      "grad_norm": 0.02365110069513321,
      "learning_rate": 0.00029948767395100045,
      "loss": 10.3747,
      "step": 15
    },
    {
      "epoch": 0.0025314452970492843,
      "grad_norm": 0.021302424371242523,
      "learning_rate": 0.0002992624353817517,
      "loss": 10.3748,
      "step": 16
    },
    {
      "epoch": 0.0026896606281148643,
      "grad_norm": 0.02328328602015972,
      "learning_rate": 0.0002989963899530457,
      "loss": 10.3749,
      "step": 17
    },
    {
      "epoch": 0.0028478759591804444,
      "grad_norm": 0.02725300006568432,
      "learning_rate": 0.00029868961039904624,
      "loss": 10.3751,
      "step": 18
    },
    {
      "epoch": 0.003006091290246025,
      "grad_norm": 0.031854234635829926,
      "learning_rate": 0.00029834218059022024,
      "loss": 10.3742,
      "step": 19
    },
    {
      "epoch": 0.003164306621311605,
      "grad_norm": 0.02939567342400551,
      "learning_rate": 0.00029795419551040833,
      "loss": 10.3731,
      "step": 20
    },
    {
      "epoch": 0.0033225219523771855,
      "grad_norm": 0.027921071276068687,
      "learning_rate": 0.00029752576123085736,
      "loss": 10.3733,
      "step": 21
    },
    {
      "epoch": 0.0034807372834427656,
      "grad_norm": 0.030107982456684113,
      "learning_rate": 0.0002970569948812214,
      "loss": 10.3717,
      "step": 22
    },
    {
      "epoch": 0.0036389526145083457,
      "grad_norm": 0.03439197689294815,
      "learning_rate": 0.0002965480246175399,
      "loss": 10.3736,
      "step": 23
    },
    {
      "epoch": 0.003797167945573926,
      "grad_norm": 0.03642607852816582,
      "learning_rate": 0.0002959989895872009,
      "loss": 10.3719,
      "step": 24
    },
    {
      "epoch": 0.003955383276639506,
      "grad_norm": 0.03989989310503006,
      "learning_rate": 0.0002954100398908995,
      "loss": 10.3721,
      "step": 25
    },
    {
      "epoch": 0.003955383276639506,
      "eval_loss": 10.37132453918457,
      "eval_runtime": 0.2297,
      "eval_samples_per_second": 217.639,
      "eval_steps_per_second": 30.469,
      "step": 25
    },
    {
      "epoch": 0.004113598607705086,
      "grad_norm": 0.03915803134441376,
      "learning_rate": 0.0002947813365416023,
      "loss": 10.3698,
      "step": 26
    },
    {
      "epoch": 0.004271813938770667,
      "grad_norm": 0.04944615066051483,
      "learning_rate": 0.0002941130514205272,
      "loss": 10.3698,
      "step": 27
    },
    {
      "epoch": 0.004430029269836247,
      "grad_norm": 0.04798049479722977,
      "learning_rate": 0.0002934053672301536,
      "loss": 10.3703,
      "step": 28
    },
    {
      "epoch": 0.004588244600901827,
      "grad_norm": 0.053915835916996,
      "learning_rate": 0.00029265847744427303,
      "loss": 10.3684,
      "step": 29
    },
    {
      "epoch": 0.0047464599319674075,
      "grad_norm": 0.06347091495990753,
      "learning_rate": 0.00029187258625509513,
      "loss": 10.3684,
      "step": 30
    },
    {
      "epoch": 0.004904675263032988,
      "grad_norm": 0.06302763521671295,
      "learning_rate": 0.00029104790851742417,
      "loss": 10.3678,
      "step": 31
    },
    {
      "epoch": 0.0050628905940985685,
      "grad_norm": 0.07511275261640549,
      "learning_rate": 0.0002901846696899191,
      "loss": 10.3665,
      "step": 32
    },
    {
      "epoch": 0.005221105925164149,
      "grad_norm": 0.07003243267536163,
      "learning_rate": 0.00028928310577345606,
      "loss": 10.3646,
      "step": 33
    },
    {
      "epoch": 0.005379321256229729,
      "grad_norm": 0.07078255712985992,
      "learning_rate": 0.0002883434632466077,
      "loss": 10.3642,
      "step": 34
    },
    {
      "epoch": 0.005537536587295309,
      "grad_norm": 0.07881415635347366,
      "learning_rate": 0.00028736599899825856,
      "loss": 10.3631,
      "step": 35
    },
    {
      "epoch": 0.005695751918360889,
      "grad_norm": 0.0780777558684349,
      "learning_rate": 0.00028635098025737434,
      "loss": 10.3652,
      "step": 36
    },
    {
      "epoch": 0.00585396724942647,
      "grad_norm": 0.08199427276849747,
      "learning_rate": 0.00028529868451994384,
      "loss": 10.3634,
      "step": 37
    },
    {
      "epoch": 0.00601218258049205,
      "grad_norm": 0.08409585803747177,
      "learning_rate": 0.0002842093994731145,
      "loss": 10.3608,
      "step": 38
    },
    {
      "epoch": 0.00617039791155763,
      "grad_norm": 0.08222662657499313,
      "learning_rate": 0.00028308342291654174,
      "loss": 10.3594,
      "step": 39
    },
    {
      "epoch": 0.00632861324262321,
      "grad_norm": 0.09460963308811188,
      "learning_rate": 0.00028192106268097334,
      "loss": 10.3561,
      "step": 40
    },
    {
      "epoch": 0.00648682857368879,
      "grad_norm": 0.08171212673187256,
      "learning_rate": 0.00028072263654409154,
      "loss": 10.3589,
      "step": 41
    },
    {
      "epoch": 0.006645043904754371,
      "grad_norm": 0.08128858357667923,
      "learning_rate": 0.0002794884721436361,
      "loss": 10.354,
      "step": 42
    },
    {
      "epoch": 0.006803259235819951,
      "grad_norm": 0.06720028072595596,
      "learning_rate": 0.00027821890688783083,
      "loss": 10.358,
      "step": 43
    },
    {
      "epoch": 0.006961474566885531,
      "grad_norm": 0.06457996368408203,
      "learning_rate": 0.0002769142878631403,
      "loss": 10.354,
      "step": 44
    },
    {
      "epoch": 0.007119689897951111,
      "grad_norm": 0.061683520674705505,
      "learning_rate": 0.00027557497173937923,
      "loss": 10.3526,
      "step": 45
    },
    {
      "epoch": 0.007277905229016691,
      "grad_norm": 0.055995553731918335,
      "learning_rate": 0.000274201324672203,
      "loss": 10.3516,
      "step": 46
    },
    {
      "epoch": 0.007436120560082272,
      "grad_norm": 0.05945537984371185,
      "learning_rate": 0.00027279372220300385,
      "loss": 10.3548,
      "step": 47
    },
    {
      "epoch": 0.007594335891147852,
      "grad_norm": 0.05607013776898384,
      "learning_rate": 0.0002713525491562421,
      "loss": 10.3541,
      "step": 48
    },
    {
      "epoch": 0.0077525512222134324,
      "grad_norm": 0.043242502957582474,
      "learning_rate": 0.00026987819953423867,
      "loss": 10.3491,
      "step": 49
    },
    {
      "epoch": 0.007910766553279013,
      "grad_norm": 0.04895467683672905,
      "learning_rate": 0.00026837107640945905,
      "loss": 10.3518,
      "step": 50
    },
    {
      "epoch": 0.007910766553279013,
      "eval_loss": 10.351200103759766,
      "eval_runtime": 0.2282,
      "eval_samples_per_second": 219.107,
      "eval_steps_per_second": 30.675,
      "step": 50
    },
    {
      "epoch": 0.008068981884344593,
      "grad_norm": 0.06542102992534637,
      "learning_rate": 0.0002668315918143169,
      "loss": 10.3578,
      "step": 51
    },
    {
      "epoch": 0.008227197215410173,
      "grad_norm": 0.06114984676241875,
      "learning_rate": 0.00026526016662852886,
      "loss": 10.3502,
      "step": 52
    },
    {
      "epoch": 0.008385412546475754,
      "grad_norm": 0.04217487946152687,
      "learning_rate": 0.00026365723046405023,
      "loss": 10.3493,
      "step": 53
    },
    {
      "epoch": 0.008543627877541335,
      "grad_norm": 0.04256010428071022,
      "learning_rate": 0.0002620232215476231,
      "loss": 10.3494,
      "step": 54
    },
    {
      "epoch": 0.008701843208606914,
      "grad_norm": 0.04327372834086418,
      "learning_rate": 0.0002603585866009697,
      "loss": 10.3518,
      "step": 55
    },
    {
      "epoch": 0.008860058539672495,
      "grad_norm": 0.029661761596798897,
      "learning_rate": 0.00025866378071866334,
      "loss": 10.3482,
      "step": 56
    },
    {
      "epoch": 0.009018273870738074,
      "grad_norm": 0.028638901188969612,
      "learning_rate": 0.00025693926724370956,
      "loss": 10.3483,
      "step": 57
    },
    {
      "epoch": 0.009176489201803655,
      "grad_norm": 0.030026491731405258,
      "learning_rate": 0.00025518551764087326,
      "loss": 10.3506,
      "step": 58
    },
    {
      "epoch": 0.009334704532869236,
      "grad_norm": 0.03200598806142807,
      "learning_rate": 0.00025340301136778483,
      "loss": 10.3481,
      "step": 59
    },
    {
      "epoch": 0.009492919863934815,
      "grad_norm": 0.034821316599845886,
      "learning_rate": 0.00025159223574386114,
      "loss": 10.35,
      "step": 60
    },
    {
      "epoch": 0.009651135195000396,
      "grad_norm": 0.028358550742268562,
      "learning_rate": 0.0002497536858170772,
      "loss": 10.349,
      "step": 61
    },
    {
      "epoch": 0.009809350526065975,
      "grad_norm": 0.03127292916178703,
      "learning_rate": 0.00024788786422862526,
      "loss": 10.3493,
      "step": 62
    },
    {
      "epoch": 0.009967565857131556,
      "grad_norm": 0.021714964881539345,
      "learning_rate": 0.00024599528107549745,
      "loss": 10.35,
      "step": 63
    },
    {
      "epoch": 0.010125781188197137,
      "grad_norm": 0.0283809807151556,
      "learning_rate": 0.00024407645377103054,
      "loss": 10.3494,
      "step": 64
    },
    {
      "epoch": 0.010283996519262716,
      "grad_norm": 0.021681398153305054,
      "learning_rate": 0.00024213190690345018,
      "loss": 10.3459,
      "step": 65
    },
    {
      "epoch": 0.010442211850328297,
      "grad_norm": 0.023167351260781288,
      "learning_rate": 0.00024016217209245374,
      "loss": 10.3479,
      "step": 66
    },
    {
      "epoch": 0.010600427181393876,
      "grad_norm": 0.027305465191602707,
      "learning_rate": 0.00023816778784387094,
      "loss": 10.3461,
      "step": 67
    },
    {
      "epoch": 0.010758642512459457,
      "grad_norm": 0.02646508999168873,
      "learning_rate": 0.0002361492994024415,
      "loss": 10.3477,
      "step": 68
    },
    {
      "epoch": 0.010916857843525038,
      "grad_norm": 0.026462828740477562,
      "learning_rate": 0.0002341072586027509,
      "loss": 10.3485,
      "step": 69
    },
    {
      "epoch": 0.011075073174590618,
      "grad_norm": 0.038422439247369766,
      "learning_rate": 0.00023204222371836405,
      "loss": 10.3507,
      "step": 70
    },
    {
      "epoch": 0.011233288505656198,
      "grad_norm": 0.030291417613625526,
      "learning_rate": 0.00022995475930919905,
      "loss": 10.3495,
      "step": 71
    },
    {
      "epoch": 0.011391503836721778,
      "grad_norm": 0.028054501861333847,
      "learning_rate": 0.00022784543606718227,
      "loss": 10.3488,
      "step": 72
    },
    {
      "epoch": 0.011549719167787359,
      "grad_norm": 0.033982597291469574,
      "learning_rate": 0.00022571483066022657,
      "loss": 10.3488,
      "step": 73
    },
    {
      "epoch": 0.01170793449885294,
      "grad_norm": 0.03378105163574219,
      "learning_rate": 0.0002235635255745762,
      "loss": 10.3451,
      "step": 74
    },
    {
      "epoch": 0.011866149829918519,
      "grad_norm": 0.0287101399153471,
      "learning_rate": 0.00022139210895556104,
      "loss": 10.3454,
      "step": 75
    },
    {
      "epoch": 0.011866149829918519,
      "eval_loss": 10.347005844116211,
      "eval_runtime": 0.2295,
      "eval_samples_per_second": 217.843,
      "eval_steps_per_second": 30.498,
      "step": 75
    },
    {
      "epoch": 0.0120243651609841,
      "grad_norm": 0.03027266450226307,
      "learning_rate": 0.00021920117444680317,
      "loss": 10.3482,
      "step": 76
    },
    {
      "epoch": 0.012182580492049679,
      "grad_norm": 0.026598526164889336,
      "learning_rate": 0.00021699132102792097,
      "loss": 10.3479,
      "step": 77
    },
    {
      "epoch": 0.01234079582311526,
      "grad_norm": 0.042221516370773315,
      "learning_rate": 0.0002147631528507739,
      "loss": 10.347,
      "step": 78
    },
    {
      "epoch": 0.01249901115418084,
      "grad_norm": 0.03229047358036041,
      "learning_rate": 0.00021251727907429355,
      "loss": 10.3472,
      "step": 79
    },
    {
      "epoch": 0.01265722648524642,
      "grad_norm": 0.032830189913511276,
      "learning_rate": 0.0002102543136979454,
      "loss": 10.3452,
      "step": 80
    },
    {
      "epoch": 0.012815441816312001,
      "grad_norm": 0.03565318509936333,
      "learning_rate": 0.0002079748753938678,
      "loss": 10.3461,
      "step": 81
    },
    {
      "epoch": 0.01297365714737758,
      "grad_norm": 0.03591080382466316,
      "learning_rate": 0.0002056795873377331,
      "loss": 10.3464,
      "step": 82
    },
    {
      "epoch": 0.013131872478443161,
      "grad_norm": 0.02825775556266308,
      "learning_rate": 0.00020336907703837748,
      "loss": 10.3473,
      "step": 83
    },
    {
      "epoch": 0.013290087809508742,
      "grad_norm": 0.033917032182216644,
      "learning_rate": 0.00020104397616624645,
      "loss": 10.345,
      "step": 84
    },
    {
      "epoch": 0.013448303140574321,
      "grad_norm": 0.034388091415166855,
      "learning_rate": 0.00019870492038070252,
      "loss": 10.3465,
      "step": 85
    },
    {
      "epoch": 0.013606518471639902,
      "grad_norm": 0.03005506657063961,
      "learning_rate": 0.0001963525491562421,
      "loss": 10.3457,
      "step": 86
    },
    {
      "epoch": 0.013764733802705481,
      "grad_norm": 0.036363132297992706,
      "learning_rate": 0.0001939875056076697,
      "loss": 10.3473,
      "step": 87
    },
    {
      "epoch": 0.013922949133771062,
      "grad_norm": 0.03449597582221031,
      "learning_rate": 0.00019161043631427666,
      "loss": 10.343,
      "step": 88
    },
    {
      "epoch": 0.014081164464836643,
      "grad_norm": 0.054132360965013504,
      "learning_rate": 0.00018922199114307294,
      "loss": 10.3428,
      "step": 89
    },
    {
      "epoch": 0.014239379795902223,
      "grad_norm": 0.02232685498893261,
      "learning_rate": 0.00018682282307111987,
      "loss": 10.3468,
      "step": 90
    },
    {
      "epoch": 0.014397595126967803,
      "grad_norm": 0.04419301822781563,
      "learning_rate": 0.00018441358800701273,
      "loss": 10.3482,
      "step": 91
    },
    {
      "epoch": 0.014555810458033383,
      "grad_norm": 0.022673867642879486,
      "learning_rate": 0.00018199494461156203,
      "loss": 10.3476,
      "step": 92
    },
    {
      "epoch": 0.014714025789098964,
      "grad_norm": 0.02817053534090519,
      "learning_rate": 0.000179567554117722,
      "loss": 10.3452,
      "step": 93
    },
    {
      "epoch": 0.014872241120164545,
      "grad_norm": 0.029614651575684547,
      "learning_rate": 0.00017713208014981648,
      "loss": 10.3472,
      "step": 94
    },
    {
      "epoch": 0.015030456451230124,
      "grad_norm": 0.03276664391160011,
      "learning_rate": 0.00017468918854211007,
      "loss": 10.346,
      "step": 95
    },
    {
      "epoch": 0.015188671782295705,
      "grad_norm": 0.029041308909654617,
      "learning_rate": 0.00017223954715677627,
      "loss": 10.3456,
      "step": 96
    },
    {
      "epoch": 0.015346887113361284,
      "grad_norm": 0.03056236356496811,
      "learning_rate": 0.00016978382570131034,
      "loss": 10.3482,
      "step": 97
    },
    {
      "epoch": 0.015505102444426865,
      "grad_norm": 0.0330655574798584,
      "learning_rate": 0.00016732269554543794,
      "loss": 10.345,
      "step": 98
    },
    {
      "epoch": 0.015663317775492444,
      "grad_norm": 0.02776387892663479,
      "learning_rate": 0.00016485682953756942,
      "loss": 10.3482,
      "step": 99
    },
    {
      "epoch": 0.015821533106558025,
      "grad_norm": 0.03921705484390259,
      "learning_rate": 0.00016238690182084986,
      "loss": 10.3449,
      "step": 100
    },
    {
      "epoch": 0.015821533106558025,
      "eval_loss": 10.34329605102539,
      "eval_runtime": 0.2301,
      "eval_samples_per_second": 217.303,
      "eval_steps_per_second": 30.422,
      "step": 100
    },
    {
      "epoch": 0.015979748437623606,
      "grad_norm": 0.07488112896680832,
      "learning_rate": 0.0001599135876488549,
      "loss": 10.3535,
      "step": 101
    },
    {
      "epoch": 0.016137963768689187,
      "grad_norm": 0.03560922294855118,
      "learning_rate": 0.00015743756320098332,
      "loss": 10.3455,
      "step": 102
    },
    {
      "epoch": 0.016296179099754768,
      "grad_norm": 0.05139762535691261,
      "learning_rate": 0.0001549595053975962,
      "loss": 10.3424,
      "step": 103
    },
    {
      "epoch": 0.016454394430820345,
      "grad_norm": 0.04562954232096672,
      "learning_rate": 0.00015248009171495378,
      "loss": 10.3454,
      "step": 104
    },
    {
      "epoch": 0.016612609761885926,
      "grad_norm": 0.04147149249911308,
      "learning_rate": 0.00015,
      "loss": 10.3462,
      "step": 105
    },
    {
      "epoch": 0.016770825092951507,
      "grad_norm": 0.04069351777434349,
      "learning_rate": 0.00014751990828504622,
      "loss": 10.3424,
      "step": 106
    },
    {
      "epoch": 0.016929040424017088,
      "grad_norm": 0.03869776055216789,
      "learning_rate": 0.00014504049460240375,
      "loss": 10.3435,
      "step": 107
    },
    {
      "epoch": 0.01708725575508267,
      "grad_norm": 0.0339597687125206,
      "learning_rate": 0.00014256243679901663,
      "loss": 10.3476,
      "step": 108
    },
    {
      "epoch": 0.017245471086148247,
      "grad_norm": 0.040333107113838196,
      "learning_rate": 0.00014008641235114508,
      "loss": 10.3429,
      "step": 109
    },
    {
      "epoch": 0.017403686417213828,
      "grad_norm": 0.031607307493686676,
      "learning_rate": 0.00013761309817915014,
      "loss": 10.345,
      "step": 110
    },
    {
      "epoch": 0.01756190174827941,
      "grad_norm": 0.026629945263266563,
      "learning_rate": 0.00013514317046243058,
      "loss": 10.3417,
      "step": 111
    },
    {
      "epoch": 0.01772011707934499,
      "grad_norm": 0.027132101356983185,
      "learning_rate": 0.00013267730445456208,
      "loss": 10.3438,
      "step": 112
    },
    {
      "epoch": 0.01787833241041057,
      "grad_norm": 0.02767929807305336,
      "learning_rate": 0.00013021617429868963,
      "loss": 10.3404,
      "step": 113
    },
    {
      "epoch": 0.018036547741476148,
      "grad_norm": 0.02483242191374302,
      "learning_rate": 0.00012776045284322368,
      "loss": 10.3406,
      "step": 114
    },
    {
      "epoch": 0.01819476307254173,
      "grad_norm": 0.024782344698905945,
      "learning_rate": 0.00012531081145788987,
      "loss": 10.3427,
      "step": 115
    },
    {
      "epoch": 0.01835297840360731,
      "grad_norm": 0.022066032513976097,
      "learning_rate": 0.00012286791985018355,
      "loss": 10.3444,
      "step": 116
    },
    {
      "epoch": 0.01851119373467289,
      "grad_norm": 0.02212349697947502,
      "learning_rate": 0.00012043244588227796,
      "loss": 10.3423,
      "step": 117
    },
    {
      "epoch": 0.01866940906573847,
      "grad_norm": 0.025567561388015747,
      "learning_rate": 0.00011800505538843798,
      "loss": 10.3452,
      "step": 118
    },
    {
      "epoch": 0.01882762439680405,
      "grad_norm": 0.027332957834005356,
      "learning_rate": 0.00011558641199298727,
      "loss": 10.3452,
      "step": 119
    },
    {
      "epoch": 0.01898583972786963,
      "grad_norm": 0.027964318171143532,
      "learning_rate": 0.00011317717692888012,
      "loss": 10.3429,
      "step": 120
    },
    {
      "epoch": 0.01914405505893521,
      "grad_norm": 0.030954988673329353,
      "learning_rate": 0.00011077800885692702,
      "loss": 10.3403,
      "step": 121
    },
    {
      "epoch": 0.019302270390000792,
      "grad_norm": 0.026920011267066002,
      "learning_rate": 0.00010838956368572334,
      "loss": 10.3424,
      "step": 122
    },
    {
      "epoch": 0.019460485721066373,
      "grad_norm": 0.028243564069271088,
      "learning_rate": 0.0001060124943923303,
      "loss": 10.3412,
      "step": 123
    },
    {
      "epoch": 0.01961870105213195,
      "grad_norm": 0.031169468536973,
      "learning_rate": 0.0001036474508437579,
      "loss": 10.3434,
      "step": 124
    },
    {
      "epoch": 0.01977691638319753,
      "grad_norm": 0.028386911377310753,
      "learning_rate": 0.00010129507961929748,
      "loss": 10.3397,
      "step": 125
    },
    {
      "epoch": 0.01977691638319753,
      "eval_loss": 10.341225624084473,
      "eval_runtime": 0.2291,
      "eval_samples_per_second": 218.275,
      "eval_steps_per_second": 30.559,
      "step": 125
    },
    {
      "epoch": 0.019935131714263112,
      "grad_norm": 0.03132046014070511,
      "learning_rate": 9.895602383375353e-05,
      "loss": 10.342,
      "step": 126
    },
    {
      "epoch": 0.020093347045328693,
      "grad_norm": 0.020751649513840675,
      "learning_rate": 9.663092296162251e-05,
      "loss": 10.3448,
      "step": 127
    },
    {
      "epoch": 0.020251562376394274,
      "grad_norm": 0.034950073808431625,
      "learning_rate": 9.432041266226686e-05,
      "loss": 10.3438,
      "step": 128
    },
    {
      "epoch": 0.02040977770745985,
      "grad_norm": 0.02994920313358307,
      "learning_rate": 9.202512460613219e-05,
      "loss": 10.3481,
      "step": 129
    },
    {
      "epoch": 0.020567993038525433,
      "grad_norm": 0.029735343530774117,
      "learning_rate": 8.97456863020546e-05,
      "loss": 10.3433,
      "step": 130
    },
    {
      "epoch": 0.020726208369591013,
      "grad_norm": 0.023487592115998268,
      "learning_rate": 8.748272092570646e-05,
      "loss": 10.3421,
      "step": 131
    },
    {
      "epoch": 0.020884423700656594,
      "grad_norm": 0.02334105782210827,
      "learning_rate": 8.523684714922608e-05,
      "loss": 10.3426,
      "step": 132
    },
    {
      "epoch": 0.021042639031722175,
      "grad_norm": 0.026596078649163246,
      "learning_rate": 8.300867897207903e-05,
      "loss": 10.3448,
      "step": 133
    },
    {
      "epoch": 0.021200854362787753,
      "grad_norm": 0.027687372639775276,
      "learning_rate": 8.079882555319684e-05,
      "loss": 10.3429,
      "step": 134
    },
    {
      "epoch": 0.021359069693853334,
      "grad_norm": 0.03481639549136162,
      "learning_rate": 7.860789104443896e-05,
      "loss": 10.3408,
      "step": 135
    },
    {
      "epoch": 0.021517285024918915,
      "grad_norm": 0.03177812322974205,
      "learning_rate": 7.643647442542382e-05,
      "loss": 10.3423,
      "step": 136
    },
    {
      "epoch": 0.021675500355984496,
      "grad_norm": 0.036161988973617554,
      "learning_rate": 7.428516933977347e-05,
      "loss": 10.3436,
      "step": 137
    },
    {
      "epoch": 0.021833715687050077,
      "grad_norm": 0.03769077733159065,
      "learning_rate": 7.215456393281776e-05,
      "loss": 10.3454,
      "step": 138
    },
    {
      "epoch": 0.021991931018115654,
      "grad_norm": 0.033461734652519226,
      "learning_rate": 7.004524069080096e-05,
      "loss": 10.3446,
      "step": 139
    },
    {
      "epoch": 0.022150146349181235,
      "grad_norm": 0.0315496101975441,
      "learning_rate": 6.795777628163599e-05,
      "loss": 10.339,
      "step": 140
    },
    {
      "epoch": 0.022308361680246816,
      "grad_norm": 0.03595556318759918,
      "learning_rate": 6.58927413972491e-05,
      "loss": 10.3433,
      "step": 141
    },
    {
      "epoch": 0.022466577011312397,
      "grad_norm": 0.02560241147875786,
      "learning_rate": 6.385070059755846e-05,
      "loss": 10.3444,
      "step": 142
    },
    {
      "epoch": 0.022624792342377978,
      "grad_norm": 0.03386726230382919,
      "learning_rate": 6.183221215612904e-05,
      "loss": 10.3414,
      "step": 143
    },
    {
      "epoch": 0.022783007673443555,
      "grad_norm": 0.025186151266098022,
      "learning_rate": 5.983782790754623e-05,
      "loss": 10.34,
      "step": 144
    },
    {
      "epoch": 0.022941223004509136,
      "grad_norm": 0.02804490737617016,
      "learning_rate": 5.786809309654982e-05,
      "loss": 10.3457,
      "step": 145
    },
    {
      "epoch": 0.023099438335574717,
      "grad_norm": 0.03370380029082298,
      "learning_rate": 5.592354622896944e-05,
      "loss": 10.3451,
      "step": 146
    },
    {
      "epoch": 0.023257653666640298,
      "grad_norm": 0.025604084134101868,
      "learning_rate": 5.40047189245025e-05,
      "loss": 10.3424,
      "step": 147
    },
    {
      "epoch": 0.02341586899770588,
      "grad_norm": 0.02944336086511612,
      "learning_rate": 5.211213577137469e-05,
      "loss": 10.3407,
      "step": 148
    },
    {
      "epoch": 0.023574084328771457,
      "grad_norm": 0.02875279076397419,
      "learning_rate": 5.024631418292274e-05,
      "loss": 10.3394,
      "step": 149
    },
    {
      "epoch": 0.023732299659837038,
      "grad_norm": 0.030480487272143364,
      "learning_rate": 4.840776425613886e-05,
      "loss": 10.3462,
      "step": 150
    },
    {
      "epoch": 0.023732299659837038,
      "eval_loss": 10.340553283691406,
      "eval_runtime": 0.2304,
      "eval_samples_per_second": 217.057,
      "eval_steps_per_second": 30.388,
      "step": 150
    },
    {
      "epoch": 0.02389051499090262,
      "grad_norm": 0.05446632206439972,
      "learning_rate": 4.659698863221513e-05,
      "loss": 10.3473,
      "step": 151
    },
    {
      "epoch": 0.0240487303219682,
      "grad_norm": 0.0344325453042984,
      "learning_rate": 4.481448235912671e-05,
      "loss": 10.3382,
      "step": 152
    },
    {
      "epoch": 0.02420694565303378,
      "grad_norm": 0.03504764661192894,
      "learning_rate": 4.306073275629044e-05,
      "loss": 10.3371,
      "step": 153
    },
    {
      "epoch": 0.024365160984099358,
      "grad_norm": 0.03372582420706749,
      "learning_rate": 4.133621928133665e-05,
      "loss": 10.3388,
      "step": 154
    },
    {
      "epoch": 0.02452337631516494,
      "grad_norm": 0.03590300306677818,
      "learning_rate": 3.964141339903026e-05,
      "loss": 10.3456,
      "step": 155
    },
    {
      "epoch": 0.02468159164623052,
      "grad_norm": 0.038486775010824203,
      "learning_rate": 3.797677845237696e-05,
      "loss": 10.3427,
      "step": 156
    },
    {
      "epoch": 0.0248398069772961,
      "grad_norm": 0.031282972544431686,
      "learning_rate": 3.634276953594982e-05,
      "loss": 10.3405,
      "step": 157
    },
    {
      "epoch": 0.02499802230836168,
      "grad_norm": 0.0262106005102396,
      "learning_rate": 3.473983337147118e-05,
      "loss": 10.3405,
      "step": 158
    },
    {
      "epoch": 0.02515623763942726,
      "grad_norm": 0.026648113504052162,
      "learning_rate": 3.316840818568315e-05,
      "loss": 10.3412,
      "step": 159
    },
    {
      "epoch": 0.02531445297049284,
      "grad_norm": 0.026712529361248016,
      "learning_rate": 3.162892359054098e-05,
      "loss": 10.3392,
      "step": 160
    },
    {
      "epoch": 0.02547266830155842,
      "grad_norm": 0.026354949921369553,
      "learning_rate": 3.0121800465761293e-05,
      "loss": 10.3407,
      "step": 161
    },
    {
      "epoch": 0.025630883632624002,
      "grad_norm": 0.019657624885439873,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 10.3413,
      "step": 162
    },
    {
      "epoch": 0.025789098963689583,
      "grad_norm": 0.028815168887376785,
      "learning_rate": 2.7206277796996144e-05,
      "loss": 10.3389,
      "step": 163
    },
    {
      "epoch": 0.02594731429475516,
      "grad_norm": 0.020832573994994164,
      "learning_rate": 2.5798675327796993e-05,
      "loss": 10.3425,
      "step": 164
    },
    {
      "epoch": 0.02610552962582074,
      "grad_norm": 0.030480805784463882,
      "learning_rate": 2.4425028260620715e-05,
      "loss": 10.3378,
      "step": 165
    },
    {
      "epoch": 0.026263744956886322,
      "grad_norm": 0.02184230647981167,
      "learning_rate": 2.3085712136859668e-05,
      "loss": 10.3415,
      "step": 166
    },
    {
      "epoch": 0.026421960287951903,
      "grad_norm": 0.025421401485800743,
      "learning_rate": 2.178109311216913e-05,
      "loss": 10.3426,
      "step": 167
    },
    {
      "epoch": 0.026580175619017484,
      "grad_norm": 0.035801470279693604,
      "learning_rate": 2.0511527856363912e-05,
      "loss": 10.3418,
      "step": 168
    },
    {
      "epoch": 0.02673839095008306,
      "grad_norm": 0.020739318802952766,
      "learning_rate": 1.927736345590839e-05,
      "loss": 10.3436,
      "step": 169
    },
    {
      "epoch": 0.026896606281148643,
      "grad_norm": 0.02305608242750168,
      "learning_rate": 1.8078937319026654e-05,
      "loss": 10.3459,
      "step": 170
    },
    {
      "epoch": 0.027054821612214223,
      "grad_norm": 0.031699080020189285,
      "learning_rate": 1.6916577083458228e-05,
      "loss": 10.3428,
      "step": 171
    },
    {
      "epoch": 0.027213036943279804,
      "grad_norm": 0.022474488243460655,
      "learning_rate": 1.579060052688548e-05,
      "loss": 10.3458,
      "step": 172
    },
    {
      "epoch": 0.027371252274345385,
      "grad_norm": 0.026044856756925583,
      "learning_rate": 1.4701315480056164e-05,
      "loss": 10.3377,
      "step": 173
    },
    {
      "epoch": 0.027529467605410963,
      "grad_norm": 0.02053038775920868,
      "learning_rate": 1.3649019742625623e-05,
      "loss": 10.3419,
      "step": 174
    },
    {
      "epoch": 0.027687682936476544,
      "grad_norm": 0.024868961423635483,
      "learning_rate": 1.2634001001741373e-05,
      "loss": 10.3397,
      "step": 175
    },
    {
      "epoch": 0.027687682936476544,
      "eval_loss": 10.339838981628418,
      "eval_runtime": 0.2319,
      "eval_samples_per_second": 215.62,
      "eval_steps_per_second": 30.187,
      "step": 175
    },
    {
      "epoch": 0.027845898267542125,
      "grad_norm": 0.02501850575208664,
      "learning_rate": 1.1656536753392287e-05,
      "loss": 10.341,
      "step": 176
    },
    {
      "epoch": 0.028004113598607706,
      "grad_norm": 0.02228490076959133,
      "learning_rate": 1.0716894226543953e-05,
      "loss": 10.3407,
      "step": 177
    },
    {
      "epoch": 0.028162328929673287,
      "grad_norm": 0.030701972544193268,
      "learning_rate": 9.815330310080887e-06,
      "loss": 10.3434,
      "step": 178
    },
    {
      "epoch": 0.028320544260738864,
      "grad_norm": 0.024261988699436188,
      "learning_rate": 8.952091482575824e-06,
      "loss": 10.3411,
      "step": 179
    },
    {
      "epoch": 0.028478759591804445,
      "grad_norm": 0.028678322210907936,
      "learning_rate": 8.127413744904804e-06,
      "loss": 10.3431,
      "step": 180
    },
    {
      "epoch": 0.028636974922870026,
      "grad_norm": 0.02342110686004162,
      "learning_rate": 7.34152255572697e-06,
      "loss": 10.3421,
      "step": 181
    },
    {
      "epoch": 0.028795190253935607,
      "grad_norm": 0.03162185847759247,
      "learning_rate": 6.594632769846353e-06,
      "loss": 10.3412,
      "step": 182
    },
    {
      "epoch": 0.028953405585001188,
      "grad_norm": 0.023181341588497162,
      "learning_rate": 5.886948579472778e-06,
      "loss": 10.3438,
      "step": 183
    },
    {
      "epoch": 0.029111620916066765,
      "grad_norm": 0.02688024565577507,
      "learning_rate": 5.218663458397715e-06,
      "loss": 10.3431,
      "step": 184
    },
    {
      "epoch": 0.029269836247132346,
      "grad_norm": 0.033303286880254745,
      "learning_rate": 4.589960109100444e-06,
      "loss": 10.3446,
      "step": 185
    },
    {
      "epoch": 0.029428051578197927,
      "grad_norm": 0.03468973562121391,
      "learning_rate": 4.001010412799138e-06,
      "loss": 10.3365,
      "step": 186
    },
    {
      "epoch": 0.029586266909263508,
      "grad_norm": 0.04302145540714264,
      "learning_rate": 3.451975382460109e-06,
      "loss": 10.3466,
      "step": 187
    },
    {
      "epoch": 0.02974448224032909,
      "grad_norm": 0.01843208819627762,
      "learning_rate": 2.9430051187785962e-06,
      "loss": 10.3452,
      "step": 188
    },
    {
      "epoch": 0.029902697571394667,
      "grad_norm": 0.019291147589683533,
      "learning_rate": 2.4742387691426445e-06,
      "loss": 10.3425,
      "step": 189
    },
    {
      "epoch": 0.030060912902460248,
      "grad_norm": 0.03046608529984951,
      "learning_rate": 2.0458044895916513e-06,
      "loss": 10.342,
      "step": 190
    },
    {
      "epoch": 0.03021912823352583,
      "grad_norm": 0.027715066447854042,
      "learning_rate": 1.6578194097797258e-06,
      "loss": 10.3438,
      "step": 191
    },
    {
      "epoch": 0.03037734356459141,
      "grad_norm": 0.024937966838479042,
      "learning_rate": 1.3103896009537207e-06,
      "loss": 10.3432,
      "step": 192
    },
    {
      "epoch": 0.03053555889565699,
      "grad_norm": 0.02733934484422207,
      "learning_rate": 1.0036100469542786e-06,
      "loss": 10.3453,
      "step": 193
    },
    {
      "epoch": 0.030693774226722568,
      "grad_norm": 0.03320769965648651,
      "learning_rate": 7.375646182482875e-07,
      "loss": 10.3437,
      "step": 194
    },
    {
      "epoch": 0.03085198955778815,
      "grad_norm": 0.03333364427089691,
      "learning_rate": 5.123260489995229e-07,
      "loss": 10.3435,
      "step": 195
    },
    {
      "epoch": 0.03101020488885373,
      "grad_norm": 0.02381930872797966,
      "learning_rate": 3.2795591718381975e-07,
      "loss": 10.3456,
      "step": 196
    },
    {
      "epoch": 0.03116842021991931,
      "grad_norm": 0.03399330750107765,
      "learning_rate": 1.8450462775428942e-07,
      "loss": 10.3415,
      "step": 197
    },
    {
      "epoch": 0.03132663555098489,
      "grad_norm": 0.02755432203412056,
      "learning_rate": 8.201139886109264e-08,
      "loss": 10.3446,
      "step": 198
    },
    {
      "epoch": 0.03148485088205047,
      "grad_norm": 0.023050131276249886,
      "learning_rate": 2.0504251129649374e-08,
      "loss": 10.3479,
      "step": 199
    },
    {
      "epoch": 0.03164306621311605,
      "grad_norm": 0.023397812619805336,
      "learning_rate": 0.0,
      "loss": 10.3433,
      "step": 200
    },
    {
      "epoch": 0.03164306621311605,
      "eval_loss": 10.339578628540039,
      "eval_runtime": 0.2288,
      "eval_samples_per_second": 218.557,
      "eval_steps_per_second": 30.598,
      "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": 39427872473088.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}