{
  "best_metric": 0.008054222911596298,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.46822665749025,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00734113328745125,
      "grad_norm": 1.0009183883666992,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.7152,
      "step": 1
    },
    {
      "epoch": 0.00734113328745125,
      "eval_loss": 2.739882469177246,
      "eval_runtime": 11.5725,
      "eval_samples_per_second": 4.321,
      "eval_steps_per_second": 4.321,
      "step": 1
    },
    {
      "epoch": 0.0146822665749025,
      "grad_norm": 1.0102258920669556,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.6972,
      "step": 2
    },
    {
      "epoch": 0.02202339986235375,
      "grad_norm": 0.9687394499778748,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.7558,
      "step": 3
    },
    {
      "epoch": 0.029364533149805,
      "grad_norm": 0.7906656265258789,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.5397,
      "step": 4
    },
    {
      "epoch": 0.03670566643725625,
      "grad_norm": 0.4140726625919342,
      "learning_rate": 0.00015,
      "loss": 2.5202,
      "step": 5
    },
    {
      "epoch": 0.0440467997247075,
      "grad_norm": 0.68717360496521,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.5802,
      "step": 6
    },
    {
      "epoch": 0.05138793301215875,
      "grad_norm": 0.9959529042243958,
      "learning_rate": 0.00020999999999999998,
      "loss": 2.563,
      "step": 7
    },
    {
      "epoch": 0.05872906629961,
      "grad_norm": 0.5985053777694702,
      "learning_rate": 0.00023999999999999998,
      "loss": 2.5683,
      "step": 8
    },
    {
      "epoch": 0.06607019958706126,
      "grad_norm": 0.2967154085636139,
      "learning_rate": 0.00027,
      "loss": 2.539,
      "step": 9
    },
    {
      "epoch": 0.0734113328745125,
      "grad_norm": 0.28381672501564026,
      "learning_rate": 0.0003,
      "loss": 2.5398,
      "step": 10
    },
    {
      "epoch": 0.08075246616196376,
      "grad_norm": 0.38264232873916626,
      "learning_rate": 0.0002999794957488703,
      "loss": 2.5249,
      "step": 11
    },
    {
      "epoch": 0.088093599449415,
      "grad_norm": 0.33728712797164917,
      "learning_rate": 0.0002999179886011389,
      "loss": 2.4142,
      "step": 12
    },
    {
      "epoch": 0.09543473273686626,
      "grad_norm": 0.26186007261276245,
      "learning_rate": 0.0002998154953722457,
      "loss": 2.3963,
      "step": 13
    },
    {
      "epoch": 0.1027758660243175,
      "grad_norm": 0.26044395565986633,
      "learning_rate": 0.00029967204408281613,
      "loss": 2.4171,
      "step": 14
    },
    {
      "epoch": 0.11011699931176876,
      "grad_norm": 0.33337321877479553,
      "learning_rate": 0.00029948767395100045,
      "loss": 2.3295,
      "step": 15
    },
    {
      "epoch": 0.11745813259922,
      "grad_norm": 0.2713659703731537,
      "learning_rate": 0.0002992624353817517,
      "loss": 2.3165,
      "step": 16
    },
    {
      "epoch": 0.12479926588667126,
      "grad_norm": 0.24857458472251892,
      "learning_rate": 0.0002989963899530457,
      "loss": 2.3045,
      "step": 17
    },
    {
      "epoch": 0.1321403991741225,
      "grad_norm": 0.2671072781085968,
      "learning_rate": 0.00029868961039904624,
      "loss": 2.3119,
      "step": 18
    },
    {
      "epoch": 0.13948153246157374,
      "grad_norm": 0.2695709466934204,
      "learning_rate": 0.00029834218059022024,
      "loss": 2.319,
      "step": 19
    },
    {
      "epoch": 0.146822665749025,
      "grad_norm": 0.2995961010456085,
      "learning_rate": 0.00029795419551040833,
      "loss": 2.252,
      "step": 20
    },
    {
      "epoch": 0.15416379903647626,
      "grad_norm": 0.2794254422187805,
      "learning_rate": 0.00029752576123085736,
      "loss": 2.2558,
      "step": 21
    },
    {
      "epoch": 0.1615049323239275,
      "grad_norm": 0.31873247027397156,
      "learning_rate": 0.0002970569948812214,
      "loss": 2.2161,
      "step": 22
    },
    {
      "epoch": 0.16884606561137874,
      "grad_norm": 0.3151024878025055,
      "learning_rate": 0.0002965480246175399,
      "loss": 2.2114,
      "step": 23
    },
    {
      "epoch": 0.17618719889883,
      "grad_norm": 0.3369925022125244,
      "learning_rate": 0.0002959989895872009,
      "loss": 2.1251,
      "step": 24
    },
    {
      "epoch": 0.18352833218628126,
      "grad_norm": 0.3629818260669708,
      "learning_rate": 0.0002954100398908995,
      "loss": 2.2003,
      "step": 25
    },
    {
      "epoch": 0.18352833218628126,
      "eval_loss": 2.0463967323303223,
      "eval_runtime": 11.771,
      "eval_samples_per_second": 4.248,
      "eval_steps_per_second": 4.248,
      "step": 25
    },
    {
      "epoch": 0.1908694654737325,
      "grad_norm": 0.4075523316860199,
      "learning_rate": 0.0002947813365416023,
      "loss": 2.0395,
      "step": 26
    },
    {
      "epoch": 0.19821059876118377,
      "grad_norm": 0.4278491139411926,
      "learning_rate": 0.0002941130514205272,
      "loss": 2.0627,
      "step": 27
    },
    {
      "epoch": 0.205551732048635,
      "grad_norm": 0.5144158005714417,
      "learning_rate": 0.0002934053672301536,
      "loss": 2.1029,
      "step": 28
    },
    {
      "epoch": 0.21289286533608626,
      "grad_norm": 0.5315491557121277,
      "learning_rate": 0.00029265847744427303,
      "loss": 2.0312,
      "step": 29
    },
    {
      "epoch": 0.2202339986235375,
      "grad_norm": 0.5522644519805908,
      "learning_rate": 0.00029187258625509513,
      "loss": 2.0579,
      "step": 30
    },
    {
      "epoch": 0.22757513191098877,
      "grad_norm": 0.5328534841537476,
      "learning_rate": 0.00029104790851742417,
      "loss": 1.9475,
      "step": 31
    },
    {
      "epoch": 0.23491626519844,
      "grad_norm": 0.6033841371536255,
      "learning_rate": 0.0002901846696899191,
      "loss": 1.8248,
      "step": 32
    },
    {
      "epoch": 0.24225739848589126,
      "grad_norm": 0.7932512760162354,
      "learning_rate": 0.00028928310577345606,
      "loss": 1.9608,
      "step": 33
    },
    {
      "epoch": 0.2495985317733425,
      "grad_norm": 0.6182257533073425,
      "learning_rate": 0.0002883434632466077,
      "loss": 1.8797,
      "step": 34
    },
    {
      "epoch": 0.25693966506079374,
      "grad_norm": 0.6742249131202698,
      "learning_rate": 0.00028736599899825856,
      "loss": 1.8248,
      "step": 35
    },
    {
      "epoch": 0.264280798348245,
      "grad_norm": 0.7396733164787292,
      "learning_rate": 0.00028635098025737434,
      "loss": 1.8357,
      "step": 36
    },
    {
      "epoch": 0.27162193163569626,
      "grad_norm": 0.701486349105835,
      "learning_rate": 0.00028529868451994384,
      "loss": 1.7344,
      "step": 37
    },
    {
      "epoch": 0.2789630649231475,
      "grad_norm": 0.6000120639801025,
      "learning_rate": 0.0002842093994731145,
      "loss": 1.7778,
      "step": 38
    },
    {
      "epoch": 0.28630419821059877,
      "grad_norm": 0.7575259804725647,
      "learning_rate": 0.00028308342291654174,
      "loss": 1.6843,
      "step": 39
    },
    {
      "epoch": 0.29364533149805,
      "grad_norm": 0.8110001683235168,
      "learning_rate": 0.00028192106268097334,
      "loss": 1.6607,
      "step": 40
    },
    {
      "epoch": 0.3009864647855013,
      "grad_norm": 0.7647180557250977,
      "learning_rate": 0.00028072263654409154,
      "loss": 1.7497,
      "step": 41
    },
    {
      "epoch": 0.3083275980729525,
      "grad_norm": 0.785166323184967,
      "learning_rate": 0.0002794884721436361,
      "loss": 1.515,
      "step": 42
    },
    {
      "epoch": 0.31566873136040374,
      "grad_norm": 1.9912952184677124,
      "learning_rate": 0.00027821890688783083,
      "loss": 1.553,
      "step": 43
    },
    {
      "epoch": 0.323009864647855,
      "grad_norm": 0.9436890482902527,
      "learning_rate": 0.0002769142878631403,
      "loss": 1.644,
      "step": 44
    },
    {
      "epoch": 0.33035099793530626,
      "grad_norm": 1.1021350622177124,
      "learning_rate": 0.00027557497173937923,
      "loss": 1.3351,
      "step": 45
    },
    {
      "epoch": 0.3376921312227575,
      "grad_norm": 1.1297169923782349,
      "learning_rate": 0.000274201324672203,
      "loss": 1.4851,
      "step": 46
    },
    {
      "epoch": 0.34503326451020877,
      "grad_norm": 1.3415935039520264,
      "learning_rate": 0.00027279372220300385,
      "loss": 1.4308,
      "step": 47
    },
    {
      "epoch": 0.35237439779766,
      "grad_norm": 1.052236557006836,
      "learning_rate": 0.0002713525491562421,
      "loss": 1.3211,
      "step": 48
    },
    {
      "epoch": 0.3597155310851113,
      "grad_norm": 1.047372579574585,
      "learning_rate": 0.00026987819953423867,
      "loss": 1.1593,
      "step": 49
    },
    {
      "epoch": 0.3670566643725625,
      "grad_norm": 1.29693603515625,
      "learning_rate": 0.00026837107640945905,
      "loss": 1.2361,
      "step": 50
    },
    {
      "epoch": 0.3670566643725625,
      "eval_loss": 1.266974925994873,
      "eval_runtime": 11.7783,
      "eval_samples_per_second": 4.245,
      "eval_steps_per_second": 4.245,
      "step": 50
    },
    {
      "epoch": 0.37439779766001374,
      "grad_norm": 1.1293262243270874,
      "learning_rate": 0.0002668315918143169,
      "loss": 1.1617,
      "step": 51
    },
    {
      "epoch": 0.381738930947465,
      "grad_norm": 1.1484521627426147,
      "learning_rate": 0.00026526016662852886,
      "loss": 1.2379,
      "step": 52
    },
    {
      "epoch": 0.38908006423491626,
      "grad_norm": 1.064557671546936,
      "learning_rate": 0.00026365723046405023,
      "loss": 1.1066,
      "step": 53
    },
    {
      "epoch": 0.39642119752236754,
      "grad_norm": 0.9905532002449036,
      "learning_rate": 0.0002620232215476231,
      "loss": 1.1669,
      "step": 54
    },
    {
      "epoch": 0.40376233080981877,
      "grad_norm": 1.251165509223938,
      "learning_rate": 0.0002603585866009697,
      "loss": 1.0054,
      "step": 55
    },
    {
      "epoch": 0.41110346409727,
      "grad_norm": 1.0376931428909302,
      "learning_rate": 0.00025866378071866334,
      "loss": 1.0141,
      "step": 56
    },
    {
      "epoch": 0.4184445973847213,
      "grad_norm": 1.1509113311767578,
      "learning_rate": 0.00025693926724370956,
      "loss": 0.8967,
      "step": 57
    },
    {
      "epoch": 0.4257857306721725,
      "grad_norm": 1.2194794416427612,
      "learning_rate": 0.00025518551764087326,
      "loss": 1.0544,
      "step": 58
    },
    {
      "epoch": 0.43312686395962374,
      "grad_norm": 0.999973475933075,
      "learning_rate": 0.00025340301136778483,
      "loss": 0.8905,
      "step": 59
    },
    {
      "epoch": 0.440467997247075,
      "grad_norm": 1.0643336772918701,
      "learning_rate": 0.00025159223574386114,
      "loss": 1.0378,
      "step": 60
    },
    {
      "epoch": 0.44780913053452626,
      "grad_norm": 1.0134408473968506,
      "learning_rate": 0.0002497536858170772,
      "loss": 0.8218,
      "step": 61
    },
    {
      "epoch": 0.45515026382197754,
      "grad_norm": 1.4050616025924683,
      "learning_rate": 0.00024788786422862526,
      "loss": 0.8544,
      "step": 62
    },
    {
      "epoch": 0.46249139710942877,
      "grad_norm": 1.4386414289474487,
      "learning_rate": 0.00024599528107549745,
      "loss": 0.8324,
      "step": 63
    },
    {
      "epoch": 0.46983253039688,
      "grad_norm": 1.1594165563583374,
      "learning_rate": 0.00024407645377103054,
      "loss": 0.7453,
      "step": 64
    },
    {
      "epoch": 0.4771736636843313,
      "grad_norm": 1.2135729789733887,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.8184,
      "step": 65
    },
    {
      "epoch": 0.4845147969717825,
      "grad_norm": 0.9763234257698059,
      "learning_rate": 0.00024016217209245374,
      "loss": 0.596,
      "step": 66
    },
    {
      "epoch": 0.49185593025923374,
      "grad_norm": 1.1825246810913086,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.6871,
      "step": 67
    },
    {
      "epoch": 0.499197063546685,
      "grad_norm": 1.0060195922851562,
      "learning_rate": 0.0002361492994024415,
      "loss": 0.658,
      "step": 68
    },
    {
      "epoch": 0.5065381968341363,
      "grad_norm": 1.87339186668396,
      "learning_rate": 0.0002341072586027509,
      "loss": 0.7342,
      "step": 69
    },
    {
      "epoch": 0.5138793301215875,
      "grad_norm": 1.2143769264221191,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.6153,
      "step": 70
    },
    {
      "epoch": 0.5212204634090388,
      "grad_norm": 1.0467982292175293,
      "learning_rate": 0.00022995475930919905,
      "loss": 0.5277,
      "step": 71
    },
    {
      "epoch": 0.52856159669649,
      "grad_norm": 1.0355846881866455,
      "learning_rate": 0.00022784543606718227,
      "loss": 0.5707,
      "step": 72
    },
    {
      "epoch": 0.5359027299839413,
      "grad_norm": 0.8927159905433655,
      "learning_rate": 0.00022571483066022657,
      "loss": 0.3879,
      "step": 73
    },
    {
      "epoch": 0.5432438632713925,
      "grad_norm": 1.427565097808838,
      "learning_rate": 0.0002235635255745762,
      "loss": 0.6126,
      "step": 74
    },
    {
      "epoch": 0.5505849965588437,
      "grad_norm": 1.1537415981292725,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.5787,
      "step": 75
    },
    {
      "epoch": 0.5505849965588437,
      "eval_loss": 0.3803807497024536,
      "eval_runtime": 11.7561,
      "eval_samples_per_second": 4.253,
      "eval_steps_per_second": 4.253,
      "step": 75
    },
    {
      "epoch": 0.557926129846295,
      "grad_norm": 0.9431911706924438,
      "learning_rate": 0.00021920117444680317,
      "loss": 0.3773,
      "step": 76
    },
    {
      "epoch": 0.5652672631337463,
      "grad_norm": 0.9953020215034485,
      "learning_rate": 0.00021699132102792097,
      "loss": 0.3676,
      "step": 77
    },
    {
      "epoch": 0.5726083964211975,
      "grad_norm": 0.98787921667099,
      "learning_rate": 0.0002147631528507739,
      "loss": 0.3079,
      "step": 78
    },
    {
      "epoch": 0.5799495297086488,
      "grad_norm": 1.191606879234314,
      "learning_rate": 0.00021251727907429355,
      "loss": 0.3129,
      "step": 79
    },
    {
      "epoch": 0.5872906629961,
      "grad_norm": 1.0935895442962646,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.3122,
      "step": 80
    },
    {
      "epoch": 0.5946317962835512,
      "grad_norm": 1.4533487558364868,
      "learning_rate": 0.0002079748753938678,
      "loss": 0.5123,
      "step": 81
    },
    {
      "epoch": 0.6019729295710026,
      "grad_norm": 1.176979422569275,
      "learning_rate": 0.0002056795873377331,
      "loss": 0.3833,
      "step": 82
    },
    {
      "epoch": 0.6093140628584538,
      "grad_norm": 1.027469277381897,
      "learning_rate": 0.00020336907703837748,
      "loss": 0.2685,
      "step": 83
    },
    {
      "epoch": 0.616655196145905,
      "grad_norm": 0.9938647747039795,
      "learning_rate": 0.00020104397616624645,
      "loss": 0.2836,
      "step": 84
    },
    {
      "epoch": 0.6239963294333563,
      "grad_norm": 0.8680717349052429,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.2036,
      "step": 85
    },
    {
      "epoch": 0.6313374627208075,
      "grad_norm": 1.1820261478424072,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.3018,
      "step": 86
    },
    {
      "epoch": 0.6386785960082588,
      "grad_norm": 0.9207668900489807,
      "learning_rate": 0.0001939875056076697,
      "loss": 0.1357,
      "step": 87
    },
    {
      "epoch": 0.64601972929571,
      "grad_norm": 0.6974514126777649,
      "learning_rate": 0.00019161043631427666,
      "loss": 0.1046,
      "step": 88
    },
    {
      "epoch": 0.6533608625831613,
      "grad_norm": 1.2946507930755615,
      "learning_rate": 0.00018922199114307294,
      "loss": 0.2132,
      "step": 89
    },
    {
      "epoch": 0.6607019958706125,
      "grad_norm": 0.9494311213493347,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.1881,
      "step": 90
    },
    {
      "epoch": 0.6680431291580637,
      "grad_norm": 0.921244204044342,
      "learning_rate": 0.00018441358800701273,
      "loss": 0.26,
      "step": 91
    },
    {
      "epoch": 0.675384262445515,
      "grad_norm": 0.8400191068649292,
      "learning_rate": 0.00018199494461156203,
      "loss": 0.153,
      "step": 92
    },
    {
      "epoch": 0.6827253957329663,
      "grad_norm": 0.7949177622795105,
      "learning_rate": 0.000179567554117722,
      "loss": 0.1471,
      "step": 93
    },
    {
      "epoch": 0.6900665290204175,
      "grad_norm": 0.9048661589622498,
      "learning_rate": 0.00017713208014981648,
      "loss": 0.126,
      "step": 94
    },
    {
      "epoch": 0.6974076623078688,
      "grad_norm": 0.8785199522972107,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.1536,
      "step": 95
    },
    {
      "epoch": 0.70474879559532,
      "grad_norm": 0.6925604939460754,
      "learning_rate": 0.00017223954715677627,
      "loss": 0.1041,
      "step": 96
    },
    {
      "epoch": 0.7120899288827712,
      "grad_norm": 0.7400240898132324,
      "learning_rate": 0.00016978382570131034,
      "loss": 0.0924,
      "step": 97
    },
    {
      "epoch": 0.7194310621702226,
      "grad_norm": 0.6650524139404297,
      "learning_rate": 0.00016732269554543794,
      "loss": 0.0788,
      "step": 98
    },
    {
      "epoch": 0.7267721954576738,
      "grad_norm": 0.5950520038604736,
      "learning_rate": 0.00016485682953756942,
      "loss": 0.066,
      "step": 99
    },
    {
      "epoch": 0.734113328745125,
      "grad_norm": 0.6176964640617371,
      "learning_rate": 0.00016238690182084986,
      "loss": 0.0628,
      "step": 100
    },
    {
      "epoch": 0.734113328745125,
      "eval_loss": 0.1003895029425621,
      "eval_runtime": 11.7465,
      "eval_samples_per_second": 4.257,
      "eval_steps_per_second": 4.257,
      "step": 100
    },
    {
      "epoch": 0.7414544620325763,
      "grad_norm": 0.7126716375350952,
      "learning_rate": 0.0001599135876488549,
      "loss": 0.1003,
      "step": 101
    },
    {
      "epoch": 0.7487955953200275,
      "grad_norm": 0.666622519493103,
      "learning_rate": 0.00015743756320098332,
      "loss": 0.0848,
      "step": 102
    },
    {
      "epoch": 0.7561367286074788,
      "grad_norm": 1.0065160989761353,
      "learning_rate": 0.0001549595053975962,
      "loss": 0.1229,
      "step": 103
    },
    {
      "epoch": 0.76347786189493,
      "grad_norm": 0.8639866709709167,
      "learning_rate": 0.00015248009171495378,
      "loss": 0.0971,
      "step": 104
    },
    {
      "epoch": 0.7708189951823813,
      "grad_norm": 0.5344640016555786,
      "learning_rate": 0.00015,
      "loss": 0.0597,
      "step": 105
    },
    {
      "epoch": 0.7781601284698325,
      "grad_norm": 0.7466907501220703,
      "learning_rate": 0.00014751990828504622,
      "loss": 0.0987,
      "step": 106
    },
    {
      "epoch": 0.7855012617572837,
      "grad_norm": 0.5494584441184998,
      "learning_rate": 0.00014504049460240375,
      "loss": 0.0618,
      "step": 107
    },
    {
      "epoch": 0.7928423950447351,
      "grad_norm": 0.6100556254386902,
      "learning_rate": 0.00014256243679901663,
      "loss": 0.0793,
      "step": 108
    },
    {
      "epoch": 0.8001835283321863,
      "grad_norm": 0.6060194969177246,
      "learning_rate": 0.00014008641235114508,
      "loss": 0.0789,
      "step": 109
    },
    {
      "epoch": 0.8075246616196375,
      "grad_norm": 0.6377370357513428,
      "learning_rate": 0.00013761309817915014,
      "loss": 0.077,
      "step": 110
    },
    {
      "epoch": 0.8148657949070888,
      "grad_norm": 0.4830247461795807,
      "learning_rate": 0.00013514317046243058,
      "loss": 0.043,
      "step": 111
    },
    {
      "epoch": 0.82220692819454,
      "grad_norm": 0.44580113887786865,
      "learning_rate": 0.00013267730445456208,
      "loss": 0.0416,
      "step": 112
    },
    {
      "epoch": 0.8295480614819912,
      "grad_norm": 0.37075257301330566,
      "learning_rate": 0.00013021617429868963,
      "loss": 0.0312,
      "step": 113
    },
    {
      "epoch": 0.8368891947694426,
      "grad_norm": 0.3857726752758026,
      "learning_rate": 0.00012776045284322368,
      "loss": 0.0332,
      "step": 114
    },
    {
      "epoch": 0.8442303280568938,
      "grad_norm": 0.562850296497345,
      "learning_rate": 0.00012531081145788987,
      "loss": 0.0345,
      "step": 115
    },
    {
      "epoch": 0.851571461344345,
      "grad_norm": 0.41303595900535583,
      "learning_rate": 0.00012286791985018355,
      "loss": 0.0312,
      "step": 116
    },
    {
      "epoch": 0.8589125946317963,
      "grad_norm": 0.4234278202056885,
      "learning_rate": 0.00012043244588227796,
      "loss": 0.036,
      "step": 117
    },
    {
      "epoch": 0.8662537279192475,
      "grad_norm": 0.46443456411361694,
      "learning_rate": 0.00011800505538843798,
      "loss": 0.0341,
      "step": 118
    },
    {
      "epoch": 0.8735948612066988,
      "grad_norm": 0.41802355647087097,
      "learning_rate": 0.00011558641199298727,
      "loss": 0.0249,
      "step": 119
    },
    {
      "epoch": 0.88093599449415,
      "grad_norm": 0.41087275743484497,
      "learning_rate": 0.00011317717692888012,
      "loss": 0.0234,
      "step": 120
    },
    {
      "epoch": 0.8882771277816013,
      "grad_norm": 0.3621070683002472,
      "learning_rate": 0.00011077800885692702,
      "loss": 0.0249,
      "step": 121
    },
    {
      "epoch": 0.8956182610690525,
      "grad_norm": 0.31254327297210693,
      "learning_rate": 0.00010838956368572334,
      "loss": 0.0223,
      "step": 122
    },
    {
      "epoch": 0.9029593943565037,
      "grad_norm": 0.4205554127693176,
      "learning_rate": 0.0001060124943923303,
      "loss": 0.0219,
      "step": 123
    },
    {
      "epoch": 0.9103005276439551,
      "grad_norm": 0.2622913122177124,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.016,
      "step": 124
    },
    {
      "epoch": 0.9176416609314063,
      "grad_norm": 0.32347017526626587,
      "learning_rate": 0.00010129507961929748,
      "loss": 0.022,
      "step": 125
    },
    {
      "epoch": 0.9176416609314063,
      "eval_loss": 0.015302430838346481,
      "eval_runtime": 11.7443,
      "eval_samples_per_second": 4.257,
      "eval_steps_per_second": 4.257,
      "step": 125
    },
    {
      "epoch": 0.9249827942188575,
      "grad_norm": 0.3583570718765259,
      "learning_rate": 9.895602383375353e-05,
      "loss": 0.0211,
      "step": 126
    },
    {
      "epoch": 0.9323239275063088,
      "grad_norm": 0.45600995421409607,
      "learning_rate": 9.663092296162251e-05,
      "loss": 0.0227,
      "step": 127
    },
    {
      "epoch": 0.93966506079376,
      "grad_norm": 0.30763763189315796,
      "learning_rate": 9.432041266226686e-05,
      "loss": 0.0221,
      "step": 128
    },
    {
      "epoch": 0.9470061940812113,
      "grad_norm": 0.271857887506485,
      "learning_rate": 9.202512460613219e-05,
      "loss": 0.0173,
      "step": 129
    },
    {
      "epoch": 0.9543473273686626,
      "grad_norm": 0.33396950364112854,
      "learning_rate": 8.97456863020546e-05,
      "loss": 0.0198,
      "step": 130
    },
    {
      "epoch": 0.9616884606561138,
      "grad_norm": 0.2286490797996521,
      "learning_rate": 8.748272092570646e-05,
      "loss": 0.018,
      "step": 131
    },
    {
      "epoch": 0.969029593943565,
      "grad_norm": 0.28220534324645996,
      "learning_rate": 8.523684714922608e-05,
      "loss": 0.0173,
      "step": 132
    },
    {
      "epoch": 0.9763707272310163,
      "grad_norm": 0.2242220640182495,
      "learning_rate": 8.300867897207903e-05,
      "loss": 0.0147,
      "step": 133
    },
    {
      "epoch": 0.9837118605184675,
      "grad_norm": 0.17104695737361908,
      "learning_rate": 8.079882555319684e-05,
      "loss": 0.0137,
      "step": 134
    },
    {
      "epoch": 0.9910529938059188,
      "grad_norm": 0.1608731746673584,
      "learning_rate": 7.860789104443896e-05,
      "loss": 0.014,
      "step": 135
    },
    {
      "epoch": 0.99839412709337,
      "grad_norm": 0.18688522279262543,
      "learning_rate": 7.643647442542382e-05,
      "loss": 0.0169,
      "step": 136
    },
    {
      "epoch": 1.0057352603808214,
      "grad_norm": 0.3710830807685852,
      "learning_rate": 7.428516933977347e-05,
      "loss": 0.0245,
      "step": 137
    },
    {
      "epoch": 1.0130763936682725,
      "grad_norm": 0.18911249935626984,
      "learning_rate": 7.215456393281776e-05,
      "loss": 0.0126,
      "step": 138
    },
    {
      "epoch": 1.0204175269557239,
      "grad_norm": 0.17865748703479767,
      "learning_rate": 7.004524069080096e-05,
      "loss": 0.0114,
      "step": 139
    },
    {
      "epoch": 1.027758660243175,
      "grad_norm": 0.21352513134479523,
      "learning_rate": 6.795777628163599e-05,
      "loss": 0.013,
      "step": 140
    },
    {
      "epoch": 1.0350997935306263,
      "grad_norm": 0.22643503546714783,
      "learning_rate": 6.58927413972491e-05,
      "loss": 0.0115,
      "step": 141
    },
    {
      "epoch": 1.0424409268180774,
      "grad_norm": 0.13287460803985596,
      "learning_rate": 6.385070059755846e-05,
      "loss": 0.011,
      "step": 142
    },
    {
      "epoch": 1.0497820601055288,
      "grad_norm": 0.16233468055725098,
      "learning_rate": 6.183221215612904e-05,
      "loss": 0.011,
      "step": 143
    },
    {
      "epoch": 1.05712319339298,
      "grad_norm": 0.13603505492210388,
      "learning_rate": 5.983782790754623e-05,
      "loss": 0.0103,
      "step": 144
    },
    {
      "epoch": 1.0644643266804312,
      "grad_norm": 0.16562862694263458,
      "learning_rate": 5.786809309654982e-05,
      "loss": 0.0124,
      "step": 145
    },
    {
      "epoch": 1.0718054599678826,
      "grad_norm": 0.10689730197191238,
      "learning_rate": 5.592354622896944e-05,
      "loss": 0.0103,
      "step": 146
    },
    {
      "epoch": 1.079146593255334,
      "grad_norm": 0.1163170337677002,
      "learning_rate": 5.40047189245025e-05,
      "loss": 0.0087,
      "step": 147
    },
    {
      "epoch": 1.086487726542785,
      "grad_norm": 0.0866883397102356,
      "learning_rate": 5.211213577137469e-05,
      "loss": 0.0089,
      "step": 148
    },
    {
      "epoch": 1.0938288598302364,
      "grad_norm": 0.210052490234375,
      "learning_rate": 5.024631418292274e-05,
      "loss": 0.0099,
      "step": 149
    },
    {
      "epoch": 1.1011699931176875,
      "grad_norm": 0.09379356354475021,
      "learning_rate": 4.840776425613886e-05,
      "loss": 0.0085,
      "step": 150
    },
    {
      "epoch": 1.1011699931176875,
      "eval_loss": 0.009465327486395836,
      "eval_runtime": 11.7556,
      "eval_samples_per_second": 4.253,
      "eval_steps_per_second": 4.253,
      "step": 150
    },
    {
      "epoch": 1.1085111264051388,
      "grad_norm": 0.1046932116150856,
      "learning_rate": 4.659698863221513e-05,
      "loss": 0.0092,
      "step": 151
    },
    {
      "epoch": 1.11585225969259,
      "grad_norm": 0.1279962807893753,
      "learning_rate": 4.481448235912671e-05,
      "loss": 0.0088,
      "step": 152
    },
    {
      "epoch": 1.1231933929800413,
      "grad_norm": 0.09951797872781754,
      "learning_rate": 4.306073275629044e-05,
      "loss": 0.009,
      "step": 153
    },
    {
      "epoch": 1.1305345262674926,
      "grad_norm": 0.08270489424467087,
      "learning_rate": 4.133621928133665e-05,
      "loss": 0.009,
      "step": 154
    },
    {
      "epoch": 1.1378756595549437,
      "grad_norm": 0.12509401142597198,
      "learning_rate": 3.964141339903026e-05,
      "loss": 0.009,
      "step": 155
    },
    {
      "epoch": 1.145216792842395,
      "grad_norm": 0.09262503683567047,
      "learning_rate": 3.797677845237696e-05,
      "loss": 0.0093,
      "step": 156
    },
    {
      "epoch": 1.1525579261298462,
      "grad_norm": 0.14835160970687866,
      "learning_rate": 3.634276953594982e-05,
      "loss": 0.0093,
      "step": 157
    },
    {
      "epoch": 1.1598990594172975,
      "grad_norm": 0.1489514261484146,
      "learning_rate": 3.473983337147118e-05,
      "loss": 0.0087,
      "step": 158
    },
    {
      "epoch": 1.1672401927047489,
      "grad_norm": 0.08459539711475372,
      "learning_rate": 3.316840818568315e-05,
      "loss": 0.0086,
      "step": 159
    },
    {
      "epoch": 1.1745813259922,
      "grad_norm": 0.07776027172803879,
      "learning_rate": 3.162892359054098e-05,
      "loss": 0.0085,
      "step": 160
    },
    {
      "epoch": 1.1819224592796513,
      "grad_norm": 0.10657629370689392,
      "learning_rate": 3.0121800465761293e-05,
      "loss": 0.0102,
      "step": 161
    },
    {
      "epoch": 1.1892635925671025,
      "grad_norm": 0.11768706142902374,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.0084,
      "step": 162
    },
    {
      "epoch": 1.1966047258545538,
      "grad_norm": 0.06789965182542801,
      "learning_rate": 2.7206277796996144e-05,
      "loss": 0.0088,
      "step": 163
    },
    {
      "epoch": 1.2039458591420051,
      "grad_norm": 0.0690593272447586,
      "learning_rate": 2.5798675327796993e-05,
      "loss": 0.0089,
      "step": 164
    },
    {
      "epoch": 1.2112869924294563,
      "grad_norm": 0.0753282979130745,
      "learning_rate": 2.4425028260620715e-05,
      "loss": 0.0086,
      "step": 165
    },
    {
      "epoch": 1.2186281257169076,
      "grad_norm": 0.08168316632509232,
      "learning_rate": 2.3085712136859668e-05,
      "loss": 0.0092,
      "step": 166
    },
    {
      "epoch": 1.2259692590043587,
      "grad_norm": 0.07094614207744598,
      "learning_rate": 2.178109311216913e-05,
      "loss": 0.0086,
      "step": 167
    },
    {
      "epoch": 1.23331039229181,
      "grad_norm": 0.07788494229316711,
      "learning_rate": 2.0511527856363912e-05,
      "loss": 0.0092,
      "step": 168
    },
    {
      "epoch": 1.2406515255792614,
      "grad_norm": 0.0890539214015007,
      "learning_rate": 1.927736345590839e-05,
      "loss": 0.0091,
      "step": 169
    },
    {
      "epoch": 1.2479926588667125,
      "grad_norm": 0.07291329652070999,
      "learning_rate": 1.8078937319026654e-05,
      "loss": 0.0088,
      "step": 170
    },
    {
      "epoch": 1.2553337921541639,
      "grad_norm": 0.15383583307266235,
      "learning_rate": 1.6916577083458228e-05,
      "loss": 0.0099,
      "step": 171
    },
    {
      "epoch": 1.262674925441615,
      "grad_norm": 0.11793084442615509,
      "learning_rate": 1.579060052688548e-05,
      "loss": 0.0084,
      "step": 172
    },
    {
      "epoch": 1.2700160587290663,
      "grad_norm": 0.12637172639369965,
      "learning_rate": 1.4701315480056164e-05,
      "loss": 0.0081,
      "step": 173
    },
    {
      "epoch": 1.2773571920165177,
      "grad_norm": 0.14355821907520294,
      "learning_rate": 1.3649019742625623e-05,
      "loss": 0.0081,
      "step": 174
    },
    {
      "epoch": 1.2846983253039688,
      "grad_norm": 0.08072730153799057,
      "learning_rate": 1.2634001001741373e-05,
      "loss": 0.0074,
      "step": 175
    },
    {
      "epoch": 1.2846983253039688,
      "eval_loss": 0.008246883749961853,
      "eval_runtime": 11.7543,
      "eval_samples_per_second": 4.254,
      "eval_steps_per_second": 4.254,
      "step": 175
    },
    {
      "epoch": 1.29203945859142,
      "grad_norm": 0.09285271167755127,
      "learning_rate": 1.1656536753392287e-05,
      "loss": 0.0077,
      "step": 176
    },
    {
      "epoch": 1.2993805918788712,
      "grad_norm": 0.19393013417720795,
      "learning_rate": 1.0716894226543953e-05,
      "loss": 0.0078,
      "step": 177
    },
    {
      "epoch": 1.3067217251663226,
      "grad_norm": 0.08033546060323715,
      "learning_rate": 9.815330310080887e-06,
      "loss": 0.0078,
      "step": 178
    },
    {
      "epoch": 1.3140628584537737,
      "grad_norm": 0.07477666437625885,
      "learning_rate": 8.952091482575824e-06,
      "loss": 0.0078,
      "step": 179
    },
    {
      "epoch": 1.321403991741225,
      "grad_norm": 0.11381042748689651,
      "learning_rate": 8.127413744904804e-06,
      "loss": 0.0088,
      "step": 180
    },
    {
      "epoch": 1.3287451250286764,
      "grad_norm": 0.11595188826322556,
      "learning_rate": 7.34152255572697e-06,
      "loss": 0.008,
      "step": 181
    },
    {
      "epoch": 1.3360862583161275,
      "grad_norm": 0.08916410803794861,
      "learning_rate": 6.594632769846353e-06,
      "loss": 0.008,
      "step": 182
    },
    {
      "epoch": 1.3434273916035788,
      "grad_norm": 0.07762780040502548,
      "learning_rate": 5.886948579472778e-06,
      "loss": 0.0087,
      "step": 183
    },
    {
      "epoch": 1.3507685248910302,
      "grad_norm": 0.09823337942361832,
      "learning_rate": 5.218663458397715e-06,
      "loss": 0.0078,
      "step": 184
    },
    {
      "epoch": 1.3581096581784813,
      "grad_norm": 0.06783485412597656,
      "learning_rate": 4.589960109100444e-06,
      "loss": 0.0073,
      "step": 185
    },
    {
      "epoch": 1.3654507914659326,
      "grad_norm": 0.06596047431230545,
      "learning_rate": 4.001010412799138e-06,
      "loss": 0.0078,
      "step": 186
    },
    {
      "epoch": 1.3727919247533837,
      "grad_norm": 0.06541063636541367,
      "learning_rate": 3.451975382460109e-06,
      "loss": 0.0079,
      "step": 187
    },
    {
      "epoch": 1.380133058040835,
      "grad_norm": 0.09579785168170929,
      "learning_rate": 2.9430051187785962e-06,
      "loss": 0.0078,
      "step": 188
    },
    {
      "epoch": 1.3874741913282862,
      "grad_norm": 0.0694115087389946,
      "learning_rate": 2.4742387691426445e-06,
      "loss": 0.0078,
      "step": 189
    },
    {
      "epoch": 1.3948153246157375,
      "grad_norm": 0.08039668947458267,
      "learning_rate": 2.0458044895916513e-06,
      "loss": 0.0086,
      "step": 190
    },
    {
      "epoch": 1.4021564579031889,
      "grad_norm": 0.07761088013648987,
      "learning_rate": 1.6578194097797258e-06,
      "loss": 0.0081,
      "step": 191
    },
    {
      "epoch": 1.40949759119064,
      "grad_norm": 0.06957986950874329,
      "learning_rate": 1.3103896009537207e-06,
      "loss": 0.008,
      "step": 192
    },
    {
      "epoch": 1.4168387244780913,
      "grad_norm": 0.06713756173849106,
      "learning_rate": 1.0036100469542786e-06,
      "loss": 0.0085,
      "step": 193
    },
    {
      "epoch": 1.4241798577655427,
      "grad_norm": 0.07192526757717133,
      "learning_rate": 7.375646182482875e-07,
      "loss": 0.0084,
      "step": 194
    },
    {
      "epoch": 1.4315209910529938,
      "grad_norm": 0.09869284182786942,
      "learning_rate": 5.123260489995229e-07,
      "loss": 0.0087,
      "step": 195
    },
    {
      "epoch": 1.4388621243404451,
      "grad_norm": 0.0659685879945755,
      "learning_rate": 3.2795591718381975e-07,
      "loss": 0.0082,
      "step": 196
    },
    {
      "epoch": 1.4462032576278963,
      "grad_norm": 0.06561301648616791,
      "learning_rate": 1.8450462775428942e-07,
      "loss": 0.008,
      "step": 197
    },
    {
      "epoch": 1.4535443909153476,
      "grad_norm": 0.06952385604381561,
      "learning_rate": 8.201139886109264e-08,
      "loss": 0.0091,
      "step": 198
    },
    {
      "epoch": 1.4608855242027987,
      "grad_norm": 0.09199344366788864,
      "learning_rate": 2.0504251129649374e-08,
      "loss": 0.0088,
      "step": 199
    },
    {
      "epoch": 1.46822665749025,
      "grad_norm": 0.08041491359472275,
      "learning_rate": 0.0,
      "loss": 0.009,
      "step": 200
    },
    {
      "epoch": 1.46822665749025,
      "eval_loss": 0.008054222911596298,
      "eval_runtime": 11.7496,
      "eval_samples_per_second": 4.255,
      "eval_steps_per_second": 4.255,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.5025410244241e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}