{
  "best_metric": 1.1628694534301758,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.3104384943733023,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015521924718665113,
      "grad_norm": 0.18503686785697937,
      "learning_rate": 5e-06,
      "loss": 0.6515,
      "step": 1
    },
    {
      "epoch": 0.0015521924718665113,
      "eval_loss": 1.4058570861816406,
      "eval_runtime": 83.3584,
      "eval_samples_per_second": 13.016,
      "eval_steps_per_second": 6.514,
      "step": 1
    },
    {
      "epoch": 0.0031043849437330227,
      "grad_norm": 0.21703191101551056,
      "learning_rate": 1e-05,
      "loss": 0.8251,
      "step": 2
    },
    {
      "epoch": 0.004656577415599534,
      "grad_norm": 0.2690574526786804,
      "learning_rate": 1.5e-05,
      "loss": 0.9786,
      "step": 3
    },
    {
      "epoch": 0.006208769887466045,
      "grad_norm": 0.26256296038627625,
      "learning_rate": 2e-05,
      "loss": 0.9597,
      "step": 4
    },
    {
      "epoch": 0.007760962359332557,
      "grad_norm": 0.28159835934638977,
      "learning_rate": 2.5e-05,
      "loss": 0.9861,
      "step": 5
    },
    {
      "epoch": 0.009313154831199068,
      "grad_norm": 0.2422163337469101,
      "learning_rate": 3e-05,
      "loss": 0.9501,
      "step": 6
    },
    {
      "epoch": 0.01086534730306558,
      "grad_norm": 0.2566586434841156,
      "learning_rate": 3.5e-05,
      "loss": 1.1036,
      "step": 7
    },
    {
      "epoch": 0.01241753977493209,
      "grad_norm": 0.25555717945098877,
      "learning_rate": 4e-05,
      "loss": 1.0891,
      "step": 8
    },
    {
      "epoch": 0.013969732246798603,
      "grad_norm": 0.25616592168807983,
      "learning_rate": 4.5e-05,
      "loss": 1.0693,
      "step": 9
    },
    {
      "epoch": 0.015521924718665115,
      "grad_norm": 0.2807532846927643,
      "learning_rate": 5e-05,
      "loss": 1.1407,
      "step": 10
    },
    {
      "epoch": 0.017074117190531625,
      "grad_norm": 0.29218876361846924,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.1332,
      "step": 11
    },
    {
      "epoch": 0.018626309662398137,
      "grad_norm": 0.3137388825416565,
      "learning_rate": 6e-05,
      "loss": 1.1886,
      "step": 12
    },
    {
      "epoch": 0.02017850213426465,
      "grad_norm": 0.3073325455188751,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.2433,
      "step": 13
    },
    {
      "epoch": 0.02173069460613116,
      "grad_norm": 0.3186430037021637,
      "learning_rate": 7e-05,
      "loss": 1.1397,
      "step": 14
    },
    {
      "epoch": 0.023282887077997673,
      "grad_norm": 0.32625216245651245,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1369,
      "step": 15
    },
    {
      "epoch": 0.02483507954986418,
      "grad_norm": 0.37930625677108765,
      "learning_rate": 8e-05,
      "loss": 1.2547,
      "step": 16
    },
    {
      "epoch": 0.026387272021730693,
      "grad_norm": 0.3755185902118683,
      "learning_rate": 8.5e-05,
      "loss": 1.2252,
      "step": 17
    },
    {
      "epoch": 0.027939464493597205,
      "grad_norm": 0.38259395956993103,
      "learning_rate": 9e-05,
      "loss": 1.2257,
      "step": 18
    },
    {
      "epoch": 0.029491656965463717,
      "grad_norm": 0.3669893741607666,
      "learning_rate": 9.5e-05,
      "loss": 1.1849,
      "step": 19
    },
    {
      "epoch": 0.03104384943733023,
      "grad_norm": 0.34851202368736267,
      "learning_rate": 0.0001,
      "loss": 1.1709,
      "step": 20
    },
    {
      "epoch": 0.03259604190919674,
      "grad_norm": 0.36455070972442627,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.2213,
      "step": 21
    },
    {
      "epoch": 0.03414823438106325,
      "grad_norm": 0.38422465324401855,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.2971,
      "step": 22
    },
    {
      "epoch": 0.03570042685292976,
      "grad_norm": 0.36575639247894287,
      "learning_rate": 9.99314767377287e-05,
      "loss": 1.2899,
      "step": 23
    },
    {
      "epoch": 0.037252619324796274,
      "grad_norm": 0.3730488419532776,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.3122,
      "step": 24
    },
    {
      "epoch": 0.038804811796662786,
      "grad_norm": 0.3623234033584595,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.2621,
      "step": 25
    },
    {
      "epoch": 0.0403570042685293,
      "grad_norm": 0.40793418884277344,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.2989,
      "step": 26
    },
    {
      "epoch": 0.04190919674039581,
      "grad_norm": 0.39662837982177734,
      "learning_rate": 9.962730758206611e-05,
      "loss": 1.3058,
      "step": 27
    },
    {
      "epoch": 0.04346138921226232,
      "grad_norm": 0.42494845390319824,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.3119,
      "step": 28
    },
    {
      "epoch": 0.045013581684128834,
      "grad_norm": 0.429860383272171,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.2452,
      "step": 29
    },
    {
      "epoch": 0.046565774155995346,
      "grad_norm": 0.4707893133163452,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.1891,
      "step": 30
    },
    {
      "epoch": 0.04811796662786186,
      "grad_norm": 0.5009111762046814,
      "learning_rate": 9.908135917238321e-05,
      "loss": 1.3307,
      "step": 31
    },
    {
      "epoch": 0.04967015909972836,
      "grad_norm": 0.49140918254852295,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.2803,
      "step": 32
    },
    {
      "epoch": 0.051222351571594875,
      "grad_norm": 0.49774688482284546,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.3875,
      "step": 33
    },
    {
      "epoch": 0.05277454404346139,
      "grad_norm": 0.5047544836997986,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.2994,
      "step": 34
    },
    {
      "epoch": 0.0543267365153279,
      "grad_norm": 0.5006894469261169,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.332,
      "step": 35
    },
    {
      "epoch": 0.05587892898719441,
      "grad_norm": 0.515229344367981,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.2985,
      "step": 36
    },
    {
      "epoch": 0.05743112145906092,
      "grad_norm": 0.5397118926048279,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.3506,
      "step": 37
    },
    {
      "epoch": 0.058983313930927435,
      "grad_norm": 0.47588130831718445,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3326,
      "step": 38
    },
    {
      "epoch": 0.06053550640279395,
      "grad_norm": 0.5251979827880859,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.3764,
      "step": 39
    },
    {
      "epoch": 0.06208769887466046,
      "grad_norm": 0.5344756841659546,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.2655,
      "step": 40
    },
    {
      "epoch": 0.06363989134652696,
      "grad_norm": 0.5431151390075684,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.3312,
      "step": 41
    },
    {
      "epoch": 0.06519208381839348,
      "grad_norm": 0.5688284039497375,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.2599,
      "step": 42
    },
    {
      "epoch": 0.06674427629025999,
      "grad_norm": 0.6097058653831482,
      "learning_rate": 9.602524267262203e-05,
      "loss": 1.3808,
      "step": 43
    },
    {
      "epoch": 0.0682964687621265,
      "grad_norm": 0.5607826709747314,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.3462,
      "step": 44
    },
    {
      "epoch": 0.06984866123399301,
      "grad_norm": 0.5400423407554626,
      "learning_rate": 9.53153893518325e-05,
      "loss": 1.2345,
      "step": 45
    },
    {
      "epoch": 0.07140085370585952,
      "grad_norm": 0.5579301118850708,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.3386,
      "step": 46
    },
    {
      "epoch": 0.07295304617772604,
      "grad_norm": 0.600250780582428,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.473,
      "step": 47
    },
    {
      "epoch": 0.07450523864959255,
      "grad_norm": 0.609580934047699,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4143,
      "step": 48
    },
    {
      "epoch": 0.07605743112145906,
      "grad_norm": 0.7040746808052063,
      "learning_rate": 9.373098535696979e-05,
      "loss": 1.465,
      "step": 49
    },
    {
      "epoch": 0.07760962359332557,
      "grad_norm": 1.0788086652755737,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5379,
      "step": 50
    },
    {
      "epoch": 0.07760962359332557,
      "eval_loss": 1.2365593910217285,
      "eval_runtime": 84.2918,
      "eval_samples_per_second": 12.872,
      "eval_steps_per_second": 6.442,
      "step": 50
    },
    {
      "epoch": 0.07916181606519208,
      "grad_norm": 0.208244189620018,
      "learning_rate": 9.285836503510562e-05,
      "loss": 0.7064,
      "step": 51
    },
    {
      "epoch": 0.0807140085370586,
      "grad_norm": 0.25803104043006897,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.835,
      "step": 52
    },
    {
      "epoch": 0.08226620100892511,
      "grad_norm": 0.2872063219547272,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.9635,
      "step": 53
    },
    {
      "epoch": 0.08381839348079162,
      "grad_norm": 0.27456480264663696,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.0085,
      "step": 54
    },
    {
      "epoch": 0.08537058595265813,
      "grad_norm": 0.2541908323764801,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.98,
      "step": 55
    },
    {
      "epoch": 0.08692277842452464,
      "grad_norm": 0.24798186123371124,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.043,
      "step": 56
    },
    {
      "epoch": 0.08847497089639116,
      "grad_norm": 0.24266217648983002,
      "learning_rate": 8.993177550236464e-05,
      "loss": 0.975,
      "step": 57
    },
    {
      "epoch": 0.09002716336825767,
      "grad_norm": 0.23755359649658203,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.103,
      "step": 58
    },
    {
      "epoch": 0.09157935584012418,
      "grad_norm": 0.2594914734363556,
      "learning_rate": 8.885729807284856e-05,
      "loss": 1.1108,
      "step": 59
    },
    {
      "epoch": 0.09313154831199069,
      "grad_norm": 0.260532945394516,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.9986,
      "step": 60
    },
    {
      "epoch": 0.0946837407838572,
      "grad_norm": 0.26638638973236084,
      "learning_rate": 8.773547901113862e-05,
      "loss": 1.1747,
      "step": 61
    },
    {
      "epoch": 0.09623593325572372,
      "grad_norm": 0.25695279240608215,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.1011,
      "step": 62
    },
    {
      "epoch": 0.09778812572759023,
      "grad_norm": 0.28216707706451416,
      "learning_rate": 8.656768508095853e-05,
      "loss": 1.1402,
      "step": 63
    },
    {
      "epoch": 0.09934031819945673,
      "grad_norm": 0.27320596575737,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1755,
      "step": 64
    },
    {
      "epoch": 0.10089251067132324,
      "grad_norm": 0.30737578868865967,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.106,
      "step": 65
    },
    {
      "epoch": 0.10244470314318975,
      "grad_norm": 0.28403839468955994,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.1238,
      "step": 66
    },
    {
      "epoch": 0.10399689561505626,
      "grad_norm": 0.2960684597492218,
      "learning_rate": 8.409991800312493e-05,
      "loss": 1.1425,
      "step": 67
    },
    {
      "epoch": 0.10554908808692277,
      "grad_norm": 0.29324308037757874,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.1544,
      "step": 68
    },
    {
      "epoch": 0.10710128055878929,
      "grad_norm": 0.30567237734794617,
      "learning_rate": 8.280295144952536e-05,
      "loss": 1.2075,
      "step": 69
    },
    {
      "epoch": 0.1086534730306558,
      "grad_norm": 0.32144761085510254,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.2646,
      "step": 70
    },
    {
      "epoch": 0.11020566550252231,
      "grad_norm": 0.3119107186794281,
      "learning_rate": 8.146601955249188e-05,
      "loss": 1.154,
      "step": 71
    },
    {
      "epoch": 0.11175785797438882,
      "grad_norm": 0.34419557452201843,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.1839,
      "step": 72
    },
    {
      "epoch": 0.11331005044625533,
      "grad_norm": 0.32192665338516235,
      "learning_rate": 8.009075115760243e-05,
      "loss": 1.2252,
      "step": 73
    },
    {
      "epoch": 0.11486224291812185,
      "grad_norm": 0.3307979106903076,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1931,
      "step": 74
    },
    {
      "epoch": 0.11641443538998836,
      "grad_norm": 0.3643626272678375,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.2355,
      "step": 75
    },
    {
      "epoch": 0.11796662786185487,
      "grad_norm": 0.3622789680957794,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.2064,
      "step": 76
    },
    {
      "epoch": 0.11951882033372138,
      "grad_norm": 0.3453439474105835,
      "learning_rate": 7.723195175075136e-05,
      "loss": 1.0944,
      "step": 77
    },
    {
      "epoch": 0.1210710128055879,
      "grad_norm": 0.373737633228302,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2976,
      "step": 78
    },
    {
      "epoch": 0.1226232052774544,
      "grad_norm": 0.40315911173820496,
      "learning_rate": 7.575190374550272e-05,
      "loss": 1.2818,
      "step": 79
    },
    {
      "epoch": 0.12417539774932092,
      "grad_norm": 0.44741833209991455,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3029,
      "step": 80
    },
    {
      "epoch": 0.12572759022118743,
      "grad_norm": 0.41700729727745056,
      "learning_rate": 7.424048101231686e-05,
      "loss": 1.3157,
      "step": 81
    },
    {
      "epoch": 0.12727978269305393,
      "grad_norm": 0.42594003677368164,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.2919,
      "step": 82
    },
    {
      "epoch": 0.12883197516492045,
      "grad_norm": 0.4305015206336975,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.2893,
      "step": 83
    },
    {
      "epoch": 0.13038416763678695,
      "grad_norm": 0.4550113081932068,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.4103,
      "step": 84
    },
    {
      "epoch": 0.13193636010865348,
      "grad_norm": 0.4780341386795044,
      "learning_rate": 7.113091308703498e-05,
      "loss": 1.3371,
      "step": 85
    },
    {
      "epoch": 0.13348855258051998,
      "grad_norm": 0.4826207160949707,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.3083,
      "step": 86
    },
    {
      "epoch": 0.1350407450523865,
      "grad_norm": 0.5050732493400574,
      "learning_rate": 6.953655642446368e-05,
      "loss": 1.3091,
      "step": 87
    },
    {
      "epoch": 0.136592937524253,
      "grad_norm": 0.5040425658226013,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.2558,
      "step": 88
    },
    {
      "epoch": 0.13814512999611953,
      "grad_norm": 0.5459226965904236,
      "learning_rate": 6.7918397477265e-05,
      "loss": 1.1998,
      "step": 89
    },
    {
      "epoch": 0.13969732246798602,
      "grad_norm": 0.5227588415145874,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.3123,
      "step": 90
    },
    {
      "epoch": 0.14124951493985255,
      "grad_norm": 0.5383272767066956,
      "learning_rate": 6.627840772285784e-05,
      "loss": 1.264,
      "step": 91
    },
    {
      "epoch": 0.14280170741171905,
      "grad_norm": 0.5507062077522278,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3205,
      "step": 92
    },
    {
      "epoch": 0.14435389988358557,
      "grad_norm": 0.5608528256416321,
      "learning_rate": 6.461858523613684e-05,
      "loss": 1.3012,
      "step": 93
    },
    {
      "epoch": 0.14590609235545207,
      "grad_norm": 0.5358137488365173,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.2865,
      "step": 94
    },
    {
      "epoch": 0.1474582848273186,
      "grad_norm": 0.5364001393318176,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.3138,
      "step": 95
    },
    {
      "epoch": 0.1490104772991851,
      "grad_norm": 0.5460485816001892,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.4544,
      "step": 96
    },
    {
      "epoch": 0.15056266977105162,
      "grad_norm": 0.5636151432991028,
      "learning_rate": 6.124755271719325e-05,
      "loss": 1.3556,
      "step": 97
    },
    {
      "epoch": 0.15211486224291812,
      "grad_norm": 0.5942332148551941,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.331,
      "step": 98
    },
    {
      "epoch": 0.15366705471478465,
      "grad_norm": 0.6374626159667969,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 1.4722,
      "step": 99
    },
    {
      "epoch": 0.15521924718665114,
      "grad_norm": 0.8560624122619629,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.2749,
      "step": 100
    },
    {
      "epoch": 0.15521924718665114,
      "eval_loss": 1.1981837749481201,
      "eval_runtime": 84.0952,
      "eval_samples_per_second": 12.902,
      "eval_steps_per_second": 6.457,
      "step": 100
    },
    {
      "epoch": 0.15677143965851767,
      "grad_norm": 0.17679108679294586,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.799,
      "step": 101
    },
    {
      "epoch": 0.15832363213038417,
      "grad_norm": 0.21500533819198608,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.8486,
      "step": 102
    },
    {
      "epoch": 0.15987582460225067,
      "grad_norm": 0.22146056592464447,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 0.8614,
      "step": 103
    },
    {
      "epoch": 0.1614280170741172,
      "grad_norm": 0.26255136728286743,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.0168,
      "step": 104
    },
    {
      "epoch": 0.1629802095459837,
      "grad_norm": 0.23788823187351227,
      "learning_rate": 5.435778713738292e-05,
      "loss": 1.0063,
      "step": 105
    },
    {
      "epoch": 0.16453240201785022,
      "grad_norm": 0.24406470358371735,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.9463,
      "step": 106
    },
    {
      "epoch": 0.1660845944897167,
      "grad_norm": 0.2359701246023178,
      "learning_rate": 5.26167978121472e-05,
      "loss": 1.0042,
      "step": 107
    },
    {
      "epoch": 0.16763678696158324,
      "grad_norm": 0.45982709527015686,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.0701,
      "step": 108
    },
    {
      "epoch": 0.16918897943344974,
      "grad_norm": 0.2334708571434021,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 1.0063,
      "step": 109
    },
    {
      "epoch": 0.17074117190531626,
      "grad_norm": 0.24308626353740692,
      "learning_rate": 5e-05,
      "loss": 1.0113,
      "step": 110
    },
    {
      "epoch": 0.17229336437718276,
      "grad_norm": 0.2540592551231384,
      "learning_rate": 4.912737967813583e-05,
      "loss": 1.0861,
      "step": 111
    },
    {
      "epoch": 0.1738455568490493,
      "grad_norm": 0.2556550204753876,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.1639,
      "step": 112
    },
    {
      "epoch": 0.17539774932091579,
      "grad_norm": 0.2509619891643524,
      "learning_rate": 4.738320218785281e-05,
      "loss": 1.1022,
      "step": 113
    },
    {
      "epoch": 0.1769499417927823,
      "grad_norm": 0.27927160263061523,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.0619,
      "step": 114
    },
    {
      "epoch": 0.1785021342646488,
      "grad_norm": 0.27921226620674133,
      "learning_rate": 4.564221286261709e-05,
      "loss": 1.135,
      "step": 115
    },
    {
      "epoch": 0.18005432673651534,
      "grad_norm": 0.27985909581184387,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.2055,
      "step": 116
    },
    {
      "epoch": 0.18160651920838183,
      "grad_norm": 0.28013497591018677,
      "learning_rate": 4.390653282974264e-05,
      "loss": 1.1392,
      "step": 117
    },
    {
      "epoch": 0.18315871168024836,
      "grad_norm": 0.2879810631275177,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.1487,
      "step": 118
    },
    {
      "epoch": 0.18471090415211486,
      "grad_norm": 0.29554373025894165,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.1189,
      "step": 119
    },
    {
      "epoch": 0.18626309662398138,
      "grad_norm": 0.29500454664230347,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.1911,
      "step": 120
    },
    {
      "epoch": 0.18781528909584788,
      "grad_norm": 0.2961357831954956,
      "learning_rate": 4.045955023117276e-05,
      "loss": 1.1043,
      "step": 121
    },
    {
      "epoch": 0.1893674815677144,
      "grad_norm": 0.3352125287055969,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.2578,
      "step": 122
    },
    {
      "epoch": 0.1909196740395809,
      "grad_norm": 0.33993181586265564,
      "learning_rate": 3.875244728280676e-05,
      "loss": 1.2228,
      "step": 123
    },
    {
      "epoch": 0.19247186651144743,
      "grad_norm": 0.3543814718723297,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.2523,
      "step": 124
    },
    {
      "epoch": 0.19402405898331393,
      "grad_norm": 0.34547507762908936,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.233,
      "step": 125
    },
    {
      "epoch": 0.19557625145518046,
      "grad_norm": 0.33998626470565796,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.2057,
      "step": 126
    },
    {
      "epoch": 0.19712844392704695,
      "grad_norm": 0.37567129731178284,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 1.3237,
      "step": 127
    },
    {
      "epoch": 0.19868063639891345,
      "grad_norm": 0.36463621258735657,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.2959,
      "step": 128
    },
    {
      "epoch": 0.20023282887077998,
      "grad_norm": 0.38328975439071655,
      "learning_rate": 3.372159227714218e-05,
      "loss": 1.2529,
      "step": 129
    },
    {
      "epoch": 0.20178502134264648,
      "grad_norm": 0.3917052447795868,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.2928,
      "step": 130
    },
    {
      "epoch": 0.203337213814513,
      "grad_norm": 0.3970443308353424,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 1.1732,
      "step": 131
    },
    {
      "epoch": 0.2048894062863795,
      "grad_norm": 0.43389272689819336,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.3013,
      "step": 132
    },
    {
      "epoch": 0.20644159875824603,
      "grad_norm": 0.4360358715057373,
      "learning_rate": 3.046344357553632e-05,
      "loss": 1.2674,
      "step": 133
    },
    {
      "epoch": 0.20799379123011252,
      "grad_norm": 0.45030710101127625,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.2964,
      "step": 134
    },
    {
      "epoch": 0.20954598370197905,
      "grad_norm": 0.45357832312583923,
      "learning_rate": 2.886908691296504e-05,
      "loss": 1.2428,
      "step": 135
    },
    {
      "epoch": 0.21109817617384555,
      "grad_norm": 0.4770860970020294,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.252,
      "step": 136
    },
    {
      "epoch": 0.21265036864571207,
      "grad_norm": 0.46414923667907715,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.2981,
      "step": 137
    },
    {
      "epoch": 0.21420256111757857,
      "grad_norm": 0.4736550748348236,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.269,
      "step": 138
    },
    {
      "epoch": 0.2157547535894451,
      "grad_norm": 0.47675976157188416,
      "learning_rate": 2.575951898768315e-05,
      "loss": 1.2472,
      "step": 139
    },
    {
      "epoch": 0.2173069460613116,
      "grad_norm": 0.48701146245002747,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.3839,
      "step": 140
    },
    {
      "epoch": 0.21885913853317812,
      "grad_norm": 0.5033087730407715,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 1.1504,
      "step": 141
    },
    {
      "epoch": 0.22041133100504462,
      "grad_norm": 0.5181295871734619,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.3645,
      "step": 142
    },
    {
      "epoch": 0.22196352347691115,
      "grad_norm": 0.5079509019851685,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 1.2558,
      "step": 143
    },
    {
      "epoch": 0.22351571594877764,
      "grad_norm": 0.5224129557609558,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.3698,
      "step": 144
    },
    {
      "epoch": 0.22506790842064417,
      "grad_norm": 0.5362732410430908,
      "learning_rate": 2.132117818244771e-05,
      "loss": 1.2566,
      "step": 145
    },
    {
      "epoch": 0.22662010089251067,
      "grad_norm": 0.5596816539764404,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.396,
      "step": 146
    },
    {
      "epoch": 0.2281722933643772,
      "grad_norm": 0.5064431428909302,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 1.2597,
      "step": 147
    },
    {
      "epoch": 0.2297244858362437,
      "grad_norm": 0.5758273601531982,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.2895,
      "step": 148
    },
    {
      "epoch": 0.23127667830811022,
      "grad_norm": 0.6258172988891602,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 1.3318,
      "step": 149
    },
    {
      "epoch": 0.23282887077997672,
      "grad_norm": 0.8499401211738586,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.519,
      "step": 150
    },
    {
      "epoch": 0.23282887077997672,
      "eval_loss": 1.1672673225402832,
      "eval_runtime": 84.0738,
      "eval_samples_per_second": 12.905,
      "eval_steps_per_second": 6.459,
      "step": 150
    },
    {
      "epoch": 0.23438106325184324,
      "grad_norm": 0.17299634218215942,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 0.7786,
      "step": 151
    },
    {
      "epoch": 0.23593325572370974,
      "grad_norm": 0.19577302038669586,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.8748,
      "step": 152
    },
    {
      "epoch": 0.23748544819557627,
      "grad_norm": 0.20664645731449127,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 0.8597,
      "step": 153
    },
    {
      "epoch": 0.23903764066744276,
      "grad_norm": 0.20882728695869446,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.95,
      "step": 154
    },
    {
      "epoch": 0.24058983313930926,
      "grad_norm": 0.22323079407215118,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.936,
      "step": 155
    },
    {
      "epoch": 0.2421420256111758,
      "grad_norm": 0.23030349612236023,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.0173,
      "step": 156
    },
    {
      "epoch": 0.24369421808304229,
      "grad_norm": 0.23430734872817993,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 1.0162,
      "step": 157
    },
    {
      "epoch": 0.2452464105549088,
      "grad_norm": 0.23629391193389893,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.0534,
      "step": 158
    },
    {
      "epoch": 0.2467986030267753,
      "grad_norm": 0.2447493076324463,
      "learning_rate": 1.22645209888614e-05,
      "loss": 1.0471,
      "step": 159
    },
    {
      "epoch": 0.24835079549864184,
      "grad_norm": 0.25912949442863464,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.0991,
      "step": 160
    },
    {
      "epoch": 0.24990298797050833,
      "grad_norm": 0.2570056617259979,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 1.0746,
      "step": 161
    },
    {
      "epoch": 0.25145518044237486,
      "grad_norm": 0.25544220209121704,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.124,
      "step": 162
    },
    {
      "epoch": 0.25300737291424136,
      "grad_norm": 0.27445948123931885,
      "learning_rate": 1.006822449763537e-05,
      "loss": 1.1435,
      "step": 163
    },
    {
      "epoch": 0.25455956538610786,
      "grad_norm": 0.2732482850551605,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2122,
      "step": 164
    },
    {
      "epoch": 0.2561117578579744,
      "grad_norm": 0.2644514739513397,
      "learning_rate": 9.042397785550405e-06,
      "loss": 1.114,
      "step": 165
    },
    {
      "epoch": 0.2576639503298409,
      "grad_norm": 0.27963027358055115,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.2008,
      "step": 166
    },
    {
      "epoch": 0.2592161428017074,
      "grad_norm": 0.28873342275619507,
      "learning_rate": 8.066471602728803e-06,
      "loss": 1.157,
      "step": 167
    },
    {
      "epoch": 0.2607683352735739,
      "grad_norm": 0.2958706021308899,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.174,
      "step": 168
    },
    {
      "epoch": 0.26232052774544046,
      "grad_norm": 0.3139137029647827,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 1.139,
      "step": 169
    },
    {
      "epoch": 0.26387272021730696,
      "grad_norm": 0.3384767174720764,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.2659,
      "step": 170
    },
    {
      "epoch": 0.26542491268917345,
      "grad_norm": 0.32462865114212036,
      "learning_rate": 6.269014643030213e-06,
      "loss": 1.1862,
      "step": 171
    },
    {
      "epoch": 0.26697710516103995,
      "grad_norm": 0.3157460689544678,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.2289,
      "step": 172
    },
    {
      "epoch": 0.2685292976329065,
      "grad_norm": 0.35785654187202454,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.2688,
      "step": 173
    },
    {
      "epoch": 0.270081490104773,
      "grad_norm": 0.3600394129753113,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.249,
      "step": 174
    },
    {
      "epoch": 0.2716336825766395,
      "grad_norm": 0.35414648056030273,
      "learning_rate": 4.684610648167503e-06,
      "loss": 1.1348,
      "step": 175
    },
    {
      "epoch": 0.273185875048506,
      "grad_norm": 0.39005619287490845,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.2229,
      "step": 176
    },
    {
      "epoch": 0.27473806752037255,
      "grad_norm": 0.3633173108100891,
      "learning_rate": 3.974757327377981e-06,
      "loss": 1.0981,
      "step": 177
    },
    {
      "epoch": 0.27629025999223905,
      "grad_norm": 0.3896339237689972,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.239,
      "step": 178
    },
    {
      "epoch": 0.27784245246410555,
      "grad_norm": 0.3801780343055725,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 1.1479,
      "step": 179
    },
    {
      "epoch": 0.27939464493597205,
      "grad_norm": 0.410643994808197,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.2703,
      "step": 180
    },
    {
      "epoch": 0.28094683740783855,
      "grad_norm": 0.41522127389907837,
      "learning_rate": 2.724071220034158e-06,
      "loss": 1.2798,
      "step": 181
    },
    {
      "epoch": 0.2824990298797051,
      "grad_norm": 0.4511876404285431,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2399,
      "step": 182
    },
    {
      "epoch": 0.2840512223515716,
      "grad_norm": 0.44222402572631836,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 1.3106,
      "step": 183
    },
    {
      "epoch": 0.2856034148234381,
      "grad_norm": 0.4436941146850586,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.2857,
      "step": 184
    },
    {
      "epoch": 0.2871556072953046,
      "grad_norm": 0.4583612382411957,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.3339,
      "step": 185
    },
    {
      "epoch": 0.28870779976717115,
      "grad_norm": 0.4590003490447998,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.2323,
      "step": 186
    },
    {
      "epoch": 0.29025999223903765,
      "grad_norm": 0.4813213348388672,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 1.2357,
      "step": 187
    },
    {
      "epoch": 0.29181218471090414,
      "grad_norm": 0.4743642210960388,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.3341,
      "step": 188
    },
    {
      "epoch": 0.29336437718277064,
      "grad_norm": 0.5076556205749512,
      "learning_rate": 9.186408276168013e-07,
      "loss": 1.2657,
      "step": 189
    },
    {
      "epoch": 0.2949165696546372,
      "grad_norm": 0.5171471238136292,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.3414,
      "step": 190
    },
    {
      "epoch": 0.2964687621265037,
      "grad_norm": 0.5316108465194702,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.2698,
      "step": 191
    },
    {
      "epoch": 0.2980209545983702,
      "grad_norm": 0.5149205327033997,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.1859,
      "step": 192
    },
    {
      "epoch": 0.2995731470702367,
      "grad_norm": 0.5591493248939514,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 1.3979,
      "step": 193
    },
    {
      "epoch": 0.30112533954210324,
      "grad_norm": 0.5425105690956116,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.2699,
      "step": 194
    },
    {
      "epoch": 0.30267753201396974,
      "grad_norm": 0.5106943845748901,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 1.3963,
      "step": 195
    },
    {
      "epoch": 0.30422972448583624,
      "grad_norm": 0.520468533039093,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.3648,
      "step": 196
    },
    {
      "epoch": 0.30578191695770274,
      "grad_norm": 0.5118442177772522,
      "learning_rate": 6.852326227130834e-08,
      "loss": 1.3784,
      "step": 197
    },
    {
      "epoch": 0.3073341094295693,
      "grad_norm": 0.5514056086540222,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.4421,
      "step": 198
    },
    {
      "epoch": 0.3088863019014358,
      "grad_norm": 0.6693518757820129,
      "learning_rate": 7.615242180436522e-09,
      "loss": 1.376,
      "step": 199
    },
    {
      "epoch": 0.3104384943733023,
      "grad_norm": 1.0523006916046143,
      "learning_rate": 0.0,
      "loss": 1.4615,
      "step": 200
    },
    {
      "epoch": 0.3104384943733023,
      "eval_loss": 1.1628694534301758,
      "eval_runtime": 84.1145,
      "eval_samples_per_second": 12.899,
      "eval_steps_per_second": 6.455,
      "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": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8757698661056512e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}