{
  "best_metric": 1.3772375583648682,
  "best_model_checkpoint": "4bit_repro_03022025/host8_seed_42_full_det_fp16_no_flash_attn_fix_pad_llama-3.1-instruct-l16-cot-wt-4ep-lr3e04-ws20-bs4-ga4-fp16-05022025/checkpoint-109",
  "epoch": 3.9655172413793105,
  "eval_steps": 500,
  "global_step": 432,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009195402298850575,
      "grad_norm": 1.2664293050765991,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 2.501,
      "step": 1
    },
    {
      "epoch": 0.01839080459770115,
      "grad_norm": 0.8997858762741089,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.5106,
      "step": 2
    },
    {
      "epoch": 0.027586206896551724,
      "grad_norm": 1.056443214416504,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 2.3968,
      "step": 3
    },
    {
      "epoch": 0.0367816091954023,
      "grad_norm": 0.7283720374107361,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.2734,
      "step": 4
    },
    {
      "epoch": 0.04597701149425287,
      "grad_norm": 2.1415610313415527,
      "learning_rate": 7.5e-05,
      "loss": 2.3937,
      "step": 5
    },
    {
      "epoch": 0.05517241379310345,
      "grad_norm": 0.9106594920158386,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.2477,
      "step": 6
    },
    {
      "epoch": 0.06436781609195402,
      "grad_norm": 0.5318637490272522,
      "learning_rate": 0.00010499999999999999,
      "loss": 2.315,
      "step": 7
    },
    {
      "epoch": 0.0735632183908046,
      "grad_norm": 0.5165982246398926,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.2767,
      "step": 8
    },
    {
      "epoch": 0.08275862068965517,
      "grad_norm": 0.6848683953285217,
      "learning_rate": 0.000135,
      "loss": 2.1223,
      "step": 9
    },
    {
      "epoch": 0.09195402298850575,
      "grad_norm": 0.9631755948066711,
      "learning_rate": 0.00015,
      "loss": 1.8723,
      "step": 10
    },
    {
      "epoch": 0.10114942528735632,
      "grad_norm": 0.5025399923324585,
      "learning_rate": 0.000165,
      "loss": 1.903,
      "step": 11
    },
    {
      "epoch": 0.1103448275862069,
      "grad_norm": 0.6477987170219421,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.8794,
      "step": 12
    },
    {
      "epoch": 0.11954022988505747,
      "grad_norm": 0.8744252324104309,
      "learning_rate": 0.000195,
      "loss": 1.5671,
      "step": 13
    },
    {
      "epoch": 0.12873563218390804,
      "grad_norm": 0.5130301713943481,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.7795,
      "step": 14
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 0.40617436170578003,
      "learning_rate": 0.000225,
      "loss": 1.763,
      "step": 15
    },
    {
      "epoch": 0.1471264367816092,
      "grad_norm": 0.46318596601486206,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.9987,
      "step": 16
    },
    {
      "epoch": 0.15632183908045977,
      "grad_norm": 0.5236511826515198,
      "learning_rate": 0.00025499999999999996,
      "loss": 1.4979,
      "step": 17
    },
    {
      "epoch": 0.16551724137931034,
      "grad_norm": 0.5424871444702148,
      "learning_rate": 0.00027,
      "loss": 1.4402,
      "step": 18
    },
    {
      "epoch": 0.17471264367816092,
      "grad_norm": 0.4224435091018677,
      "learning_rate": 0.000285,
      "loss": 1.4267,
      "step": 19
    },
    {
      "epoch": 0.1839080459770115,
      "grad_norm": 0.3918392062187195,
      "learning_rate": 0.0003,
      "loss": 1.682,
      "step": 20
    },
    {
      "epoch": 0.19310344827586207,
      "grad_norm": 0.38505086302757263,
      "learning_rate": 0.00029927184466019415,
      "loss": 1.8057,
      "step": 21
    },
    {
      "epoch": 0.20229885057471264,
      "grad_norm": 0.3489862382411957,
      "learning_rate": 0.00029854368932038833,
      "loss": 1.7206,
      "step": 22
    },
    {
      "epoch": 0.21149425287356322,
      "grad_norm": 0.42483219504356384,
      "learning_rate": 0.0002978155339805825,
      "loss": 1.5119,
      "step": 23
    },
    {
      "epoch": 0.2206896551724138,
      "grad_norm": 0.3796898424625397,
      "learning_rate": 0.0002970873786407767,
      "loss": 1.6089,
      "step": 24
    },
    {
      "epoch": 0.22988505747126436,
      "grad_norm": 0.32184913754463196,
      "learning_rate": 0.00029635922330097087,
      "loss": 1.7786,
      "step": 25
    },
    {
      "epoch": 0.23908045977011494,
      "grad_norm": 0.35197311639785767,
      "learning_rate": 0.00029563106796116505,
      "loss": 1.5639,
      "step": 26
    },
    {
      "epoch": 0.2482758620689655,
      "grad_norm": 0.4310867488384247,
      "learning_rate": 0.0002949029126213592,
      "loss": 1.5192,
      "step": 27
    },
    {
      "epoch": 0.2574712643678161,
      "grad_norm": 0.3951260447502136,
      "learning_rate": 0.00029417475728155335,
      "loss": 1.4559,
      "step": 28
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.3948059678077698,
      "learning_rate": 0.00029344660194174753,
      "loss": 1.7552,
      "step": 29
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 0.3327697515487671,
      "learning_rate": 0.0002927184466019417,
      "loss": 1.9249,
      "step": 30
    },
    {
      "epoch": 0.2850574712643678,
      "grad_norm": 0.3762843906879425,
      "learning_rate": 0.0002919902912621359,
      "loss": 1.6966,
      "step": 31
    },
    {
      "epoch": 0.2942528735632184,
      "grad_norm": 0.3671524226665497,
      "learning_rate": 0.00029126213592233006,
      "loss": 1.4718,
      "step": 32
    },
    {
      "epoch": 0.30344827586206896,
      "grad_norm": 0.5411608815193176,
      "learning_rate": 0.00029053398058252424,
      "loss": 1.3394,
      "step": 33
    },
    {
      "epoch": 0.31264367816091954,
      "grad_norm": 0.4906865656375885,
      "learning_rate": 0.0002898058252427184,
      "loss": 1.688,
      "step": 34
    },
    {
      "epoch": 0.3218390804597701,
      "grad_norm": 0.4257373511791229,
      "learning_rate": 0.0002890776699029126,
      "loss": 1.7126,
      "step": 35
    },
    {
      "epoch": 0.3310344827586207,
      "grad_norm": 0.44731780886650085,
      "learning_rate": 0.0002883495145631068,
      "loss": 1.5332,
      "step": 36
    },
    {
      "epoch": 0.34022988505747126,
      "grad_norm": 0.34879976511001587,
      "learning_rate": 0.00028762135922330096,
      "loss": 1.6599,
      "step": 37
    },
    {
      "epoch": 0.34942528735632183,
      "grad_norm": 0.328622043132782,
      "learning_rate": 0.00028689320388349513,
      "loss": 1.7865,
      "step": 38
    },
    {
      "epoch": 0.3586206896551724,
      "grad_norm": 0.4515538811683655,
      "learning_rate": 0.0002861650485436893,
      "loss": 1.3684,
      "step": 39
    },
    {
      "epoch": 0.367816091954023,
      "grad_norm": 0.39751267433166504,
      "learning_rate": 0.0002854368932038835,
      "loss": 1.7847,
      "step": 40
    },
    {
      "epoch": 0.37701149425287356,
      "grad_norm": 0.33651894330978394,
      "learning_rate": 0.00028470873786407767,
      "loss": 1.602,
      "step": 41
    },
    {
      "epoch": 0.38620689655172413,
      "grad_norm": 0.5487242341041565,
      "learning_rate": 0.00028398058252427185,
      "loss": 1.2588,
      "step": 42
    },
    {
      "epoch": 0.3954022988505747,
      "grad_norm": 0.373512327671051,
      "learning_rate": 0.00028325242718446603,
      "loss": 1.5344,
      "step": 43
    },
    {
      "epoch": 0.4045977011494253,
      "grad_norm": 0.4022233486175537,
      "learning_rate": 0.00028252427184466015,
      "loss": 1.4503,
      "step": 44
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 0.4379498064517975,
      "learning_rate": 0.00028179611650485433,
      "loss": 1.3271,
      "step": 45
    },
    {
      "epoch": 0.42298850574712643,
      "grad_norm": 0.3380189538002014,
      "learning_rate": 0.0002810679611650485,
      "loss": 1.6746,
      "step": 46
    },
    {
      "epoch": 0.432183908045977,
      "grad_norm": 0.41873887181282043,
      "learning_rate": 0.0002803398058252427,
      "loss": 1.4792,
      "step": 47
    },
    {
      "epoch": 0.4413793103448276,
      "grad_norm": 0.3990491032600403,
      "learning_rate": 0.00027961165048543687,
      "loss": 1.4309,
      "step": 48
    },
    {
      "epoch": 0.45057471264367815,
      "grad_norm": 0.41645604372024536,
      "learning_rate": 0.00027888349514563105,
      "loss": 1.4003,
      "step": 49
    },
    {
      "epoch": 0.45977011494252873,
      "grad_norm": 0.46974533796310425,
      "learning_rate": 0.0002781553398058252,
      "loss": 1.2245,
      "step": 50
    },
    {
      "epoch": 0.4689655172413793,
      "grad_norm": 0.36877307295799255,
      "learning_rate": 0.0002774271844660194,
      "loss": 1.5979,
      "step": 51
    },
    {
      "epoch": 0.4781609195402299,
      "grad_norm": 0.35563924908638,
      "learning_rate": 0.0002766990291262136,
      "loss": 1.3965,
      "step": 52
    },
    {
      "epoch": 0.48735632183908045,
      "grad_norm": 0.44057121872901917,
      "learning_rate": 0.00027597087378640776,
      "loss": 1.2961,
      "step": 53
    },
    {
      "epoch": 0.496551724137931,
      "grad_norm": 0.46805521845817566,
      "learning_rate": 0.00027524271844660194,
      "loss": 1.2184,
      "step": 54
    },
    {
      "epoch": 0.5057471264367817,
      "grad_norm": 0.3901378810405731,
      "learning_rate": 0.0002745145631067961,
      "loss": 1.6127,
      "step": 55
    },
    {
      "epoch": 0.5149425287356322,
      "grad_norm": 0.471978098154068,
      "learning_rate": 0.0002737864077669903,
      "loss": 1.4896,
      "step": 56
    },
    {
      "epoch": 0.5241379310344828,
      "grad_norm": 0.4229693114757538,
      "learning_rate": 0.0002730582524271845,
      "loss": 1.3084,
      "step": 57
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.4022842049598694,
      "learning_rate": 0.00027233009708737865,
      "loss": 1.464,
      "step": 58
    },
    {
      "epoch": 0.542528735632184,
      "grad_norm": 0.4753398895263672,
      "learning_rate": 0.0002716019417475728,
      "loss": 1.4227,
      "step": 59
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.3991449475288391,
      "learning_rate": 0.00027087378640776696,
      "loss": 1.4973,
      "step": 60
    },
    {
      "epoch": 0.5609195402298851,
      "grad_norm": 0.5638157725334167,
      "learning_rate": 0.00027014563106796114,
      "loss": 1.3702,
      "step": 61
    },
    {
      "epoch": 0.5701149425287356,
      "grad_norm": 0.3964412808418274,
      "learning_rate": 0.0002694174757281553,
      "loss": 1.3154,
      "step": 62
    },
    {
      "epoch": 0.5793103448275863,
      "grad_norm": 0.4884161055088043,
      "learning_rate": 0.0002686893203883495,
      "loss": 1.2915,
      "step": 63
    },
    {
      "epoch": 0.5885057471264368,
      "grad_norm": 0.5821394920349121,
      "learning_rate": 0.00026796116504854367,
      "loss": 1.1925,
      "step": 64
    },
    {
      "epoch": 0.5977011494252874,
      "grad_norm": 0.8125529289245605,
      "learning_rate": 0.00026723300970873785,
      "loss": 1.4684,
      "step": 65
    },
    {
      "epoch": 0.6068965517241379,
      "grad_norm": 0.46448639035224915,
      "learning_rate": 0.00026650485436893203,
      "loss": 1.0113,
      "step": 66
    },
    {
      "epoch": 0.6160919540229886,
      "grad_norm": 0.5045990347862244,
      "learning_rate": 0.0002657766990291262,
      "loss": 1.424,
      "step": 67
    },
    {
      "epoch": 0.6252873563218391,
      "grad_norm": 0.4608731269836426,
      "learning_rate": 0.0002650485436893204,
      "loss": 1.4203,
      "step": 68
    },
    {
      "epoch": 0.6344827586206897,
      "grad_norm": 0.6361207962036133,
      "learning_rate": 0.00026432038834951456,
      "loss": 1.4455,
      "step": 69
    },
    {
      "epoch": 0.6436781609195402,
      "grad_norm": 0.4667050838470459,
      "learning_rate": 0.00026359223300970874,
      "loss": 1.3269,
      "step": 70
    },
    {
      "epoch": 0.6528735632183909,
      "grad_norm": 0.5672599673271179,
      "learning_rate": 0.0002628640776699029,
      "loss": 1.2629,
      "step": 71
    },
    {
      "epoch": 0.6620689655172414,
      "grad_norm": 0.5386179089546204,
      "learning_rate": 0.00026213592233009705,
      "loss": 1.2188,
      "step": 72
    },
    {
      "epoch": 0.671264367816092,
      "grad_norm": 0.4968770146369934,
      "learning_rate": 0.0002614077669902912,
      "loss": 1.3148,
      "step": 73
    },
    {
      "epoch": 0.6804597701149425,
      "grad_norm": 0.5847041010856628,
      "learning_rate": 0.0002606796116504854,
      "loss": 1.457,
      "step": 74
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.5828786492347717,
      "learning_rate": 0.0002599514563106796,
      "loss": 1.2948,
      "step": 75
    },
    {
      "epoch": 0.6988505747126437,
      "grad_norm": 0.7716859579086304,
      "learning_rate": 0.00025922330097087376,
      "loss": 1.5078,
      "step": 76
    },
    {
      "epoch": 0.7080459770114943,
      "grad_norm": 0.6014898419380188,
      "learning_rate": 0.00025849514563106794,
      "loss": 1.2796,
      "step": 77
    },
    {
      "epoch": 0.7172413793103448,
      "grad_norm": 0.5102112293243408,
      "learning_rate": 0.0002577669902912621,
      "loss": 1.178,
      "step": 78
    },
    {
      "epoch": 0.7264367816091954,
      "grad_norm": 0.5293049812316895,
      "learning_rate": 0.0002570388349514563,
      "loss": 1.6404,
      "step": 79
    },
    {
      "epoch": 0.735632183908046,
      "grad_norm": 0.5157208442687988,
      "learning_rate": 0.0002563106796116505,
      "loss": 1.4367,
      "step": 80
    },
    {
      "epoch": 0.7448275862068966,
      "grad_norm": 0.4517700672149658,
      "learning_rate": 0.0002555825242718446,
      "loss": 1.3063,
      "step": 81
    },
    {
      "epoch": 0.7540229885057471,
      "grad_norm": 0.42310649156570435,
      "learning_rate": 0.0002548543689320388,
      "loss": 1.2749,
      "step": 82
    },
    {
      "epoch": 0.7632183908045977,
      "grad_norm": 0.5767822861671448,
      "learning_rate": 0.00025412621359223296,
      "loss": 1.3432,
      "step": 83
    },
    {
      "epoch": 0.7724137931034483,
      "grad_norm": 0.49889254570007324,
      "learning_rate": 0.00025339805825242714,
      "loss": 1.3629,
      "step": 84
    },
    {
      "epoch": 0.7816091954022989,
      "grad_norm": 0.5736685395240784,
      "learning_rate": 0.0002526699029126213,
      "loss": 1.1754,
      "step": 85
    },
    {
      "epoch": 0.7908045977011494,
      "grad_norm": 0.4891297221183777,
      "learning_rate": 0.0002519417475728155,
      "loss": 1.2404,
      "step": 86
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.45507243275642395,
      "learning_rate": 0.00025121359223300967,
      "loss": 1.3653,
      "step": 87
    },
    {
      "epoch": 0.8091954022988506,
      "grad_norm": 0.43236321210861206,
      "learning_rate": 0.00025048543689320385,
      "loss": 1.3037,
      "step": 88
    },
    {
      "epoch": 0.8183908045977012,
      "grad_norm": 0.5662382245063782,
      "learning_rate": 0.00024975728155339803,
      "loss": 1.2031,
      "step": 89
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 0.5644109845161438,
      "learning_rate": 0.0002490291262135922,
      "loss": 1.0595,
      "step": 90
    },
    {
      "epoch": 0.8367816091954023,
      "grad_norm": 0.4636576473712921,
      "learning_rate": 0.0002483009708737864,
      "loss": 1.3056,
      "step": 91
    },
    {
      "epoch": 0.8459770114942529,
      "grad_norm": 0.4858672022819519,
      "learning_rate": 0.00024757281553398056,
      "loss": 1.1215,
      "step": 92
    },
    {
      "epoch": 0.8551724137931035,
      "grad_norm": 0.5379095673561096,
      "learning_rate": 0.00024684466019417474,
      "loss": 1.0833,
      "step": 93
    },
    {
      "epoch": 0.864367816091954,
      "grad_norm": 0.6066029667854309,
      "learning_rate": 0.0002461165048543689,
      "loss": 1.1953,
      "step": 94
    },
    {
      "epoch": 0.8735632183908046,
      "grad_norm": 0.5864242315292358,
      "learning_rate": 0.0002453883495145631,
      "loss": 1.2868,
      "step": 95
    },
    {
      "epoch": 0.8827586206896552,
      "grad_norm": 0.47946035861968994,
      "learning_rate": 0.0002446601941747572,
      "loss": 1.0682,
      "step": 96
    },
    {
      "epoch": 0.8919540229885058,
      "grad_norm": 0.5266394019126892,
      "learning_rate": 0.00024393203883495143,
      "loss": 1.2363,
      "step": 97
    },
    {
      "epoch": 0.9011494252873563,
      "grad_norm": 0.49734389781951904,
      "learning_rate": 0.0002432038834951456,
      "loss": 1.2858,
      "step": 98
    },
    {
      "epoch": 0.9103448275862069,
      "grad_norm": 0.5391829013824463,
      "learning_rate": 0.0002424757281553398,
      "loss": 1.1882,
      "step": 99
    },
    {
      "epoch": 0.9195402298850575,
      "grad_norm": 0.4663216769695282,
      "learning_rate": 0.00024174757281553394,
      "loss": 1.1461,
      "step": 100
    },
    {
      "epoch": 0.9287356321839081,
      "grad_norm": 0.5432461500167847,
      "learning_rate": 0.00024101941747572812,
      "loss": 1.134,
      "step": 101
    },
    {
      "epoch": 0.9379310344827586,
      "grad_norm": 0.6043102145195007,
      "learning_rate": 0.0002402912621359223,
      "loss": 1.0859,
      "step": 102
    },
    {
      "epoch": 0.9471264367816092,
      "grad_norm": 0.5635194778442383,
      "learning_rate": 0.00023956310679611648,
      "loss": 1.0828,
      "step": 103
    },
    {
      "epoch": 0.9563218390804598,
      "grad_norm": 0.5683427453041077,
      "learning_rate": 0.00023883495145631065,
      "loss": 1.0066,
      "step": 104
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 0.550366997718811,
      "learning_rate": 0.00023810679611650483,
      "loss": 1.0664,
      "step": 105
    },
    {
      "epoch": 0.9747126436781609,
      "grad_norm": 0.5590884685516357,
      "learning_rate": 0.000237378640776699,
      "loss": 1.3188,
      "step": 106
    },
    {
      "epoch": 0.9839080459770115,
      "grad_norm": 0.49222445487976074,
      "learning_rate": 0.0002366504854368932,
      "loss": 1.1888,
      "step": 107
    },
    {
      "epoch": 0.993103448275862,
      "grad_norm": 0.5352950096130371,
      "learning_rate": 0.00023592233009708734,
      "loss": 0.9848,
      "step": 108
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6914329528808594,
      "learning_rate": 0.00023519417475728152,
      "loss": 1.1814,
      "step": 109
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.3772375583648682,
      "eval_runtime": 70.9021,
      "eval_samples_per_second": 4.683,
      "eval_steps_per_second": 2.341,
      "step": 109
    },
    {
      "epoch": 1.0091954022988505,
      "grad_norm": 0.5395228862762451,
      "learning_rate": 0.0002344660194174757,
      "loss": 1.0255,
      "step": 110
    },
    {
      "epoch": 1.018390804597701,
      "grad_norm": 0.5161539316177368,
      "learning_rate": 0.00023373786407766988,
      "loss": 1.0072,
      "step": 111
    },
    {
      "epoch": 1.0275862068965518,
      "grad_norm": 0.4717608094215393,
      "learning_rate": 0.00023300970873786406,
      "loss": 0.9007,
      "step": 112
    },
    {
      "epoch": 1.0367816091954023,
      "grad_norm": 0.6422189474105835,
      "learning_rate": 0.00023228155339805823,
      "loss": 1.1458,
      "step": 113
    },
    {
      "epoch": 1.0459770114942528,
      "grad_norm": 0.5921640992164612,
      "learning_rate": 0.0002315533980582524,
      "loss": 1.0321,
      "step": 114
    },
    {
      "epoch": 1.0551724137931036,
      "grad_norm": 0.6381415128707886,
      "learning_rate": 0.0002308252427184466,
      "loss": 1.0119,
      "step": 115
    },
    {
      "epoch": 1.064367816091954,
      "grad_norm": 0.49388617277145386,
      "learning_rate": 0.00023009708737864074,
      "loss": 0.9483,
      "step": 116
    },
    {
      "epoch": 1.0735632183908046,
      "grad_norm": 0.669136106967926,
      "learning_rate": 0.00022936893203883492,
      "loss": 1.0767,
      "step": 117
    },
    {
      "epoch": 1.0827586206896551,
      "grad_norm": 0.5716057419776917,
      "learning_rate": 0.0002286407766990291,
      "loss": 1.0632,
      "step": 118
    },
    {
      "epoch": 1.0919540229885056,
      "grad_norm": 0.5134244561195374,
      "learning_rate": 0.00022791262135922328,
      "loss": 0.9554,
      "step": 119
    },
    {
      "epoch": 1.1011494252873564,
      "grad_norm": 0.49190524220466614,
      "learning_rate": 0.00022718446601941746,
      "loss": 0.9927,
      "step": 120
    },
    {
      "epoch": 1.110344827586207,
      "grad_norm": 0.7558183073997498,
      "learning_rate": 0.00022645631067961164,
      "loss": 1.0067,
      "step": 121
    },
    {
      "epoch": 1.1195402298850574,
      "grad_norm": 0.5597643852233887,
      "learning_rate": 0.00022572815533980582,
      "loss": 0.8869,
      "step": 122
    },
    {
      "epoch": 1.1287356321839082,
      "grad_norm": 0.6764683127403259,
      "learning_rate": 0.000225,
      "loss": 0.9806,
      "step": 123
    },
    {
      "epoch": 1.1379310344827587,
      "grad_norm": 0.5788061618804932,
      "learning_rate": 0.00022427184466019415,
      "loss": 1.0121,
      "step": 124
    },
    {
      "epoch": 1.1471264367816092,
      "grad_norm": 0.5578724145889282,
      "learning_rate": 0.00022354368932038832,
      "loss": 0.91,
      "step": 125
    },
    {
      "epoch": 1.1563218390804597,
      "grad_norm": 0.5371822714805603,
      "learning_rate": 0.0002228155339805825,
      "loss": 0.8422,
      "step": 126
    },
    {
      "epoch": 1.1655172413793102,
      "grad_norm": 0.7994176149368286,
      "learning_rate": 0.00022208737864077668,
      "loss": 0.9105,
      "step": 127
    },
    {
      "epoch": 1.174712643678161,
      "grad_norm": 0.5430970788002014,
      "learning_rate": 0.00022135922330097086,
      "loss": 0.9843,
      "step": 128
    },
    {
      "epoch": 1.1839080459770115,
      "grad_norm": 0.5710289478302002,
      "learning_rate": 0.00022063106796116504,
      "loss": 0.9191,
      "step": 129
    },
    {
      "epoch": 1.193103448275862,
      "grad_norm": 0.6985263228416443,
      "learning_rate": 0.00021990291262135922,
      "loss": 0.892,
      "step": 130
    },
    {
      "epoch": 1.2022988505747128,
      "grad_norm": 0.532593309879303,
      "learning_rate": 0.00021917475728155337,
      "loss": 0.7993,
      "step": 131
    },
    {
      "epoch": 1.2114942528735633,
      "grad_norm": 0.5657442808151245,
      "learning_rate": 0.00021844660194174755,
      "loss": 0.8961,
      "step": 132
    },
    {
      "epoch": 1.2206896551724138,
      "grad_norm": 0.5356594920158386,
      "learning_rate": 0.00021771844660194173,
      "loss": 0.867,
      "step": 133
    },
    {
      "epoch": 1.2298850574712643,
      "grad_norm": 0.9694854617118835,
      "learning_rate": 0.0002169902912621359,
      "loss": 0.8823,
      "step": 134
    },
    {
      "epoch": 1.2390804597701148,
      "grad_norm": 0.5810908675193787,
      "learning_rate": 0.00021626213592233008,
      "loss": 0.9571,
      "step": 135
    },
    {
      "epoch": 1.2482758620689656,
      "grad_norm": 0.5119120478630066,
      "learning_rate": 0.00021553398058252426,
      "loss": 1.0567,
      "step": 136
    },
    {
      "epoch": 1.257471264367816,
      "grad_norm": 0.5349586009979248,
      "learning_rate": 0.00021480582524271844,
      "loss": 0.8422,
      "step": 137
    },
    {
      "epoch": 1.2666666666666666,
      "grad_norm": 0.5498553514480591,
      "learning_rate": 0.00021407766990291262,
      "loss": 0.9509,
      "step": 138
    },
    {
      "epoch": 1.2758620689655173,
      "grad_norm": 0.6952114701271057,
      "learning_rate": 0.00021334951456310677,
      "loss": 1.062,
      "step": 139
    },
    {
      "epoch": 1.2850574712643679,
      "grad_norm": 0.5768996477127075,
      "learning_rate": 0.00021262135922330095,
      "loss": 0.9139,
      "step": 140
    },
    {
      "epoch": 1.2942528735632184,
      "grad_norm": 0.559478759765625,
      "learning_rate": 0.00021189320388349513,
      "loss": 1.0465,
      "step": 141
    },
    {
      "epoch": 1.303448275862069,
      "grad_norm": 0.5405702590942383,
      "learning_rate": 0.0002111650485436893,
      "loss": 0.7433,
      "step": 142
    },
    {
      "epoch": 1.3126436781609194,
      "grad_norm": 0.5924260020256042,
      "learning_rate": 0.00021043689320388349,
      "loss": 0.6828,
      "step": 143
    },
    {
      "epoch": 1.3218390804597702,
      "grad_norm": 0.7219521403312683,
      "learning_rate": 0.00020970873786407766,
      "loss": 0.8972,
      "step": 144
    },
    {
      "epoch": 1.3310344827586207,
      "grad_norm": 0.8541707396507263,
      "learning_rate": 0.00020898058252427184,
      "loss": 0.7595,
      "step": 145
    },
    {
      "epoch": 1.3402298850574712,
      "grad_norm": 0.5988287925720215,
      "learning_rate": 0.00020825242718446602,
      "loss": 0.7803,
      "step": 146
    },
    {
      "epoch": 1.349425287356322,
      "grad_norm": 0.6142683625221252,
      "learning_rate": 0.00020752427184466017,
      "loss": 0.8507,
      "step": 147
    },
    {
      "epoch": 1.3586206896551725,
      "grad_norm": 0.5336320400238037,
      "learning_rate": 0.00020679611650485435,
      "loss": 0.7742,
      "step": 148
    },
    {
      "epoch": 1.367816091954023,
      "grad_norm": 0.5284804701805115,
      "learning_rate": 0.00020606796116504853,
      "loss": 0.6759,
      "step": 149
    },
    {
      "epoch": 1.3770114942528735,
      "grad_norm": 0.4955348074436188,
      "learning_rate": 0.0002053398058252427,
      "loss": 0.7054,
      "step": 150
    },
    {
      "epoch": 1.386206896551724,
      "grad_norm": 0.5454412698745728,
      "learning_rate": 0.0002046116504854369,
      "loss": 0.8826,
      "step": 151
    },
    {
      "epoch": 1.3954022988505748,
      "grad_norm": 0.7631385326385498,
      "learning_rate": 0.00020388349514563107,
      "loss": 0.8582,
      "step": 152
    },
    {
      "epoch": 1.4045977011494253,
      "grad_norm": 0.5374491810798645,
      "learning_rate": 0.00020315533980582524,
      "loss": 0.9728,
      "step": 153
    },
    {
      "epoch": 1.4137931034482758,
      "grad_norm": 0.5633158087730408,
      "learning_rate": 0.00020242718446601942,
      "loss": 0.8275,
      "step": 154
    },
    {
      "epoch": 1.4229885057471265,
      "grad_norm": 0.572356641292572,
      "learning_rate": 0.00020169902912621357,
      "loss": 0.6565,
      "step": 155
    },
    {
      "epoch": 1.432183908045977,
      "grad_norm": 0.6513031125068665,
      "learning_rate": 0.00020097087378640775,
      "loss": 0.9112,
      "step": 156
    },
    {
      "epoch": 1.4413793103448276,
      "grad_norm": 0.48528391122817993,
      "learning_rate": 0.00020024271844660193,
      "loss": 0.7623,
      "step": 157
    },
    {
      "epoch": 1.450574712643678,
      "grad_norm": 0.47339922189712524,
      "learning_rate": 0.0001995145631067961,
      "loss": 0.621,
      "step": 158
    },
    {
      "epoch": 1.4597701149425286,
      "grad_norm": 0.5684221386909485,
      "learning_rate": 0.0001987864077669903,
      "loss": 0.7902,
      "step": 159
    },
    {
      "epoch": 1.4689655172413794,
      "grad_norm": 0.87876296043396,
      "learning_rate": 0.00019805825242718447,
      "loss": 0.9629,
      "step": 160
    },
    {
      "epoch": 1.4781609195402299,
      "grad_norm": 0.5925374031066895,
      "learning_rate": 0.00019733009708737865,
      "loss": 0.9815,
      "step": 161
    },
    {
      "epoch": 1.4873563218390804,
      "grad_norm": 0.48992210626602173,
      "learning_rate": 0.0001966019417475728,
      "loss": 0.6662,
      "step": 162
    },
    {
      "epoch": 1.4965517241379311,
      "grad_norm": 0.9017893075942993,
      "learning_rate": 0.00019587378640776698,
      "loss": 0.7229,
      "step": 163
    },
    {
      "epoch": 1.5057471264367817,
      "grad_norm": 0.6186094880104065,
      "learning_rate": 0.00019514563106796116,
      "loss": 0.6594,
      "step": 164
    },
    {
      "epoch": 1.5149425287356322,
      "grad_norm": 0.5197699069976807,
      "learning_rate": 0.00019441747572815533,
      "loss": 0.8404,
      "step": 165
    },
    {
      "epoch": 1.524137931034483,
      "grad_norm": 0.4972164034843445,
      "learning_rate": 0.0001936893203883495,
      "loss": 0.8106,
      "step": 166
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 0.5052672028541565,
      "learning_rate": 0.0001929611650485437,
      "loss": 0.7682,
      "step": 167
    },
    {
      "epoch": 1.542528735632184,
      "grad_norm": 1.1433080434799194,
      "learning_rate": 0.00019223300970873787,
      "loss": 0.8409,
      "step": 168
    },
    {
      "epoch": 1.5517241379310345,
      "grad_norm": 0.730868399143219,
      "learning_rate": 0.00019150485436893205,
      "loss": 0.7541,
      "step": 169
    },
    {
      "epoch": 1.560919540229885,
      "grad_norm": 0.7178101539611816,
      "learning_rate": 0.0001907766990291262,
      "loss": 0.6899,
      "step": 170
    },
    {
      "epoch": 1.5701149425287357,
      "grad_norm": 0.5060885548591614,
      "learning_rate": 0.00019004854368932038,
      "loss": 0.97,
      "step": 171
    },
    {
      "epoch": 1.5793103448275863,
      "grad_norm": 0.7058172821998596,
      "learning_rate": 0.00018932038834951456,
      "loss": 0.8883,
      "step": 172
    },
    {
      "epoch": 1.5885057471264368,
      "grad_norm": 0.6002851128578186,
      "learning_rate": 0.00018859223300970874,
      "loss": 0.8808,
      "step": 173
    },
    {
      "epoch": 1.5977011494252875,
      "grad_norm": 0.5641213059425354,
      "learning_rate": 0.00018786407766990291,
      "loss": 0.6536,
      "step": 174
    },
    {
      "epoch": 1.6068965517241378,
      "grad_norm": 0.621860146522522,
      "learning_rate": 0.00018713592233009707,
      "loss": 0.784,
      "step": 175
    },
    {
      "epoch": 1.6160919540229886,
      "grad_norm": 0.6033377051353455,
      "learning_rate": 0.00018640776699029122,
      "loss": 0.8755,
      "step": 176
    },
    {
      "epoch": 1.625287356321839,
      "grad_norm": 0.7301514148712158,
      "learning_rate": 0.0001856796116504854,
      "loss": 0.5401,
      "step": 177
    },
    {
      "epoch": 1.6344827586206896,
      "grad_norm": 0.6001805067062378,
      "learning_rate": 0.00018495145631067957,
      "loss": 0.5086,
      "step": 178
    },
    {
      "epoch": 1.6436781609195403,
      "grad_norm": 0.5408189296722412,
      "learning_rate": 0.00018422330097087375,
      "loss": 0.8864,
      "step": 179
    },
    {
      "epoch": 1.6528735632183909,
      "grad_norm": 0.548526406288147,
      "learning_rate": 0.00018349514563106793,
      "loss": 0.7745,
      "step": 180
    },
    {
      "epoch": 1.6620689655172414,
      "grad_norm": 0.5930566787719727,
      "learning_rate": 0.0001827669902912621,
      "loss": 0.8096,
      "step": 181
    },
    {
      "epoch": 1.6712643678160921,
      "grad_norm": 0.5918225049972534,
      "learning_rate": 0.0001820388349514563,
      "loss": 0.8386,
      "step": 182
    },
    {
      "epoch": 1.6804597701149424,
      "grad_norm": 0.5837062001228333,
      "learning_rate": 0.00018131067961165047,
      "loss": 0.6873,
      "step": 183
    },
    {
      "epoch": 1.6896551724137931,
      "grad_norm": 0.5399461984634399,
      "learning_rate": 0.00018058252427184462,
      "loss": 0.8788,
      "step": 184
    },
    {
      "epoch": 1.6988505747126437,
      "grad_norm": 0.48315730690956116,
      "learning_rate": 0.0001798543689320388,
      "loss": 0.7834,
      "step": 185
    },
    {
      "epoch": 1.7080459770114942,
      "grad_norm": 0.5982978343963623,
      "learning_rate": 0.00017912621359223298,
      "loss": 0.6913,
      "step": 186
    },
    {
      "epoch": 1.717241379310345,
      "grad_norm": 0.9199710488319397,
      "learning_rate": 0.00017839805825242716,
      "loss": 0.6592,
      "step": 187
    },
    {
      "epoch": 1.7264367816091954,
      "grad_norm": 0.8085829615592957,
      "learning_rate": 0.00017766990291262133,
      "loss": 0.7439,
      "step": 188
    },
    {
      "epoch": 1.735632183908046,
      "grad_norm": 0.6275731325149536,
      "learning_rate": 0.0001769417475728155,
      "loss": 0.7331,
      "step": 189
    },
    {
      "epoch": 1.7448275862068967,
      "grad_norm": 0.5255990624427795,
      "learning_rate": 0.0001762135922330097,
      "loss": 0.7255,
      "step": 190
    },
    {
      "epoch": 1.754022988505747,
      "grad_norm": 0.5680968165397644,
      "learning_rate": 0.00017548543689320387,
      "loss": 0.7446,
      "step": 191
    },
    {
      "epoch": 1.7632183908045977,
      "grad_norm": 0.5626929402351379,
      "learning_rate": 0.00017475728155339802,
      "loss": 0.7948,
      "step": 192
    },
    {
      "epoch": 1.7724137931034483,
      "grad_norm": 0.4922776222229004,
      "learning_rate": 0.0001740291262135922,
      "loss": 0.6568,
      "step": 193
    },
    {
      "epoch": 1.7816091954022988,
      "grad_norm": 0.5294581651687622,
      "learning_rate": 0.00017330097087378638,
      "loss": 0.5458,
      "step": 194
    },
    {
      "epoch": 1.7908045977011495,
      "grad_norm": 0.5421092510223389,
      "learning_rate": 0.00017257281553398056,
      "loss": 0.6159,
      "step": 195
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.7755627036094666,
      "learning_rate": 0.00017184466019417474,
      "loss": 0.7165,
      "step": 196
    },
    {
      "epoch": 1.8091954022988506,
      "grad_norm": 0.9723690748214722,
      "learning_rate": 0.00017111650485436891,
      "loss": 0.7743,
      "step": 197
    },
    {
      "epoch": 1.8183908045977013,
      "grad_norm": 0.6832698583602905,
      "learning_rate": 0.0001703883495145631,
      "loss": 0.7539,
      "step": 198
    },
    {
      "epoch": 1.8275862068965516,
      "grad_norm": 0.592229962348938,
      "learning_rate": 0.00016966019417475724,
      "loss": 0.6838,
      "step": 199
    },
    {
      "epoch": 1.8367816091954023,
      "grad_norm": 0.5979653596878052,
      "learning_rate": 0.00016893203883495142,
      "loss": 0.5518,
      "step": 200
    },
    {
      "epoch": 1.8459770114942529,
      "grad_norm": 0.5223293304443359,
      "learning_rate": 0.0001682038834951456,
      "loss": 0.5327,
      "step": 201
    },
    {
      "epoch": 1.8551724137931034,
      "grad_norm": 0.5753535032272339,
      "learning_rate": 0.00016747572815533978,
      "loss": 0.5783,
      "step": 202
    },
    {
      "epoch": 1.8643678160919541,
      "grad_norm": 0.4552556276321411,
      "learning_rate": 0.00016674757281553396,
      "loss": 0.726,
      "step": 203
    },
    {
      "epoch": 1.8735632183908046,
      "grad_norm": 0.46313363313674927,
      "learning_rate": 0.00016601941747572814,
      "loss": 0.7472,
      "step": 204
    },
    {
      "epoch": 1.8827586206896552,
      "grad_norm": 0.7298106551170349,
      "learning_rate": 0.00016529126213592232,
      "loss": 0.6869,
      "step": 205
    },
    {
      "epoch": 1.891954022988506,
      "grad_norm": 0.45026591420173645,
      "learning_rate": 0.0001645631067961165,
      "loss": 0.6929,
      "step": 206
    },
    {
      "epoch": 1.9011494252873562,
      "grad_norm": 0.5525459051132202,
      "learning_rate": 0.00016383495145631065,
      "loss": 0.6441,
      "step": 207
    },
    {
      "epoch": 1.910344827586207,
      "grad_norm": 0.5456161499023438,
      "learning_rate": 0.00016310679611650483,
      "loss": 0.8553,
      "step": 208
    },
    {
      "epoch": 1.9195402298850575,
      "grad_norm": 0.5439329147338867,
      "learning_rate": 0.000162378640776699,
      "loss": 0.7111,
      "step": 209
    },
    {
      "epoch": 1.928735632183908,
      "grad_norm": 0.49237221479415894,
      "learning_rate": 0.00016165048543689318,
      "loss": 0.6243,
      "step": 210
    },
    {
      "epoch": 1.9379310344827587,
      "grad_norm": 0.493568480014801,
      "learning_rate": 0.00016092233009708736,
      "loss": 0.5351,
      "step": 211
    },
    {
      "epoch": 1.9471264367816092,
      "grad_norm": 0.6934286952018738,
      "learning_rate": 0.00016019417475728154,
      "loss": 0.7098,
      "step": 212
    },
    {
      "epoch": 1.9563218390804598,
      "grad_norm": 0.47321686148643494,
      "learning_rate": 0.00015946601941747572,
      "loss": 0.5246,
      "step": 213
    },
    {
      "epoch": 1.9655172413793105,
      "grad_norm": 0.4709272086620331,
      "learning_rate": 0.0001587378640776699,
      "loss": 0.5498,
      "step": 214
    },
    {
      "epoch": 1.9747126436781608,
      "grad_norm": 0.5461050271987915,
      "learning_rate": 0.00015800970873786405,
      "loss": 0.9668,
      "step": 215
    },
    {
      "epoch": 1.9839080459770115,
      "grad_norm": 0.5588494539260864,
      "learning_rate": 0.00015728155339805823,
      "loss": 0.9515,
      "step": 216
    },
    {
      "epoch": 1.993103448275862,
      "grad_norm": 0.6440616846084595,
      "learning_rate": 0.0001565533980582524,
      "loss": 0.7871,
      "step": 217
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6609704494476318,
      "learning_rate": 0.00015582524271844658,
      "loss": 0.9322,
      "step": 218
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.3917137384414673,
      "eval_runtime": 70.9533,
      "eval_samples_per_second": 4.679,
      "eval_steps_per_second": 2.34,
      "step": 218
    },
    {
      "epoch": 2.0091954022988507,
      "grad_norm": 0.6179903745651245,
      "learning_rate": 0.00015509708737864076,
      "loss": 0.4927,
      "step": 219
    },
    {
      "epoch": 2.018390804597701,
      "grad_norm": 0.48804861307144165,
      "learning_rate": 0.00015436893203883494,
      "loss": 0.6208,
      "step": 220
    },
    {
      "epoch": 2.027586206896552,
      "grad_norm": 0.5461186766624451,
      "learning_rate": 0.00015364077669902912,
      "loss": 0.5774,
      "step": 221
    },
    {
      "epoch": 2.036781609195402,
      "grad_norm": 0.4856977164745331,
      "learning_rate": 0.0001529126213592233,
      "loss": 0.6426,
      "step": 222
    },
    {
      "epoch": 2.045977011494253,
      "grad_norm": 0.3683694005012512,
      "learning_rate": 0.00015218446601941745,
      "loss": 0.4752,
      "step": 223
    },
    {
      "epoch": 2.0551724137931036,
      "grad_norm": 0.5229505300521851,
      "learning_rate": 0.00015145631067961163,
      "loss": 0.5244,
      "step": 224
    },
    {
      "epoch": 2.064367816091954,
      "grad_norm": 0.4558103084564209,
      "learning_rate": 0.0001507281553398058,
      "loss": 0.5453,
      "step": 225
    },
    {
      "epoch": 2.0735632183908046,
      "grad_norm": 0.49105018377304077,
      "learning_rate": 0.00015,
      "loss": 0.4759,
      "step": 226
    },
    {
      "epoch": 2.0827586206896553,
      "grad_norm": 0.6662527322769165,
      "learning_rate": 0.00014927184466019417,
      "loss": 0.8146,
      "step": 227
    },
    {
      "epoch": 2.0919540229885056,
      "grad_norm": 0.6585009694099426,
      "learning_rate": 0.00014854368932038834,
      "loss": 0.4853,
      "step": 228
    },
    {
      "epoch": 2.1011494252873564,
      "grad_norm": 0.46196475625038147,
      "learning_rate": 0.00014781553398058252,
      "loss": 0.5042,
      "step": 229
    },
    {
      "epoch": 2.110344827586207,
      "grad_norm": 0.4975808262825012,
      "learning_rate": 0.00014708737864077667,
      "loss": 0.5507,
      "step": 230
    },
    {
      "epoch": 2.1195402298850574,
      "grad_norm": 0.4535251259803772,
      "learning_rate": 0.00014635922330097085,
      "loss": 0.5138,
      "step": 231
    },
    {
      "epoch": 2.128735632183908,
      "grad_norm": 0.5737034678459167,
      "learning_rate": 0.00014563106796116503,
      "loss": 0.6338,
      "step": 232
    },
    {
      "epoch": 2.1379310344827585,
      "grad_norm": 0.4570606052875519,
      "learning_rate": 0.0001449029126213592,
      "loss": 0.4852,
      "step": 233
    },
    {
      "epoch": 2.147126436781609,
      "grad_norm": 0.571922242641449,
      "learning_rate": 0.0001441747572815534,
      "loss": 0.6671,
      "step": 234
    },
    {
      "epoch": 2.15632183908046,
      "grad_norm": 0.5813591480255127,
      "learning_rate": 0.00014344660194174757,
      "loss": 0.6764,
      "step": 235
    },
    {
      "epoch": 2.1655172413793102,
      "grad_norm": 0.6348188519477844,
      "learning_rate": 0.00014271844660194175,
      "loss": 0.5268,
      "step": 236
    },
    {
      "epoch": 2.174712643678161,
      "grad_norm": 0.5119661688804626,
      "learning_rate": 0.00014199029126213592,
      "loss": 0.6359,
      "step": 237
    },
    {
      "epoch": 2.1839080459770113,
      "grad_norm": 0.478588342666626,
      "learning_rate": 0.00014126213592233008,
      "loss": 0.6315,
      "step": 238
    },
    {
      "epoch": 2.193103448275862,
      "grad_norm": 0.4163134694099426,
      "learning_rate": 0.00014053398058252425,
      "loss": 0.5183,
      "step": 239
    },
    {
      "epoch": 2.2022988505747128,
      "grad_norm": 0.4251859188079834,
      "learning_rate": 0.00013980582524271843,
      "loss": 0.4611,
      "step": 240
    },
    {
      "epoch": 2.211494252873563,
      "grad_norm": 0.6032213568687439,
      "learning_rate": 0.0001390776699029126,
      "loss": 0.8345,
      "step": 241
    },
    {
      "epoch": 2.220689655172414,
      "grad_norm": 0.48562517762184143,
      "learning_rate": 0.0001383495145631068,
      "loss": 0.4118,
      "step": 242
    },
    {
      "epoch": 2.2298850574712645,
      "grad_norm": 0.45934462547302246,
      "learning_rate": 0.00013762135922330097,
      "loss": 0.4099,
      "step": 243
    },
    {
      "epoch": 2.239080459770115,
      "grad_norm": 0.5195468068122864,
      "learning_rate": 0.00013689320388349515,
      "loss": 0.6766,
      "step": 244
    },
    {
      "epoch": 2.2482758620689656,
      "grad_norm": 0.5700232982635498,
      "learning_rate": 0.00013616504854368933,
      "loss": 0.8323,
      "step": 245
    },
    {
      "epoch": 2.2574712643678163,
      "grad_norm": 0.4179138243198395,
      "learning_rate": 0.00013543689320388348,
      "loss": 0.3745,
      "step": 246
    },
    {
      "epoch": 2.2666666666666666,
      "grad_norm": 0.5863101482391357,
      "learning_rate": 0.00013470873786407766,
      "loss": 0.7907,
      "step": 247
    },
    {
      "epoch": 2.2758620689655173,
      "grad_norm": 0.3810423016548157,
      "learning_rate": 0.00013398058252427184,
      "loss": 0.3766,
      "step": 248
    },
    {
      "epoch": 2.2850574712643676,
      "grad_norm": 0.6277771592140198,
      "learning_rate": 0.00013325242718446601,
      "loss": 0.6325,
      "step": 249
    },
    {
      "epoch": 2.2942528735632184,
      "grad_norm": 0.5368175506591797,
      "learning_rate": 0.0001325242718446602,
      "loss": 0.8255,
      "step": 250
    },
    {
      "epoch": 2.303448275862069,
      "grad_norm": 0.5138571262359619,
      "learning_rate": 0.00013179611650485437,
      "loss": 0.5017,
      "step": 251
    },
    {
      "epoch": 2.3126436781609194,
      "grad_norm": 0.42882323265075684,
      "learning_rate": 0.00013106796116504852,
      "loss": 0.4303,
      "step": 252
    },
    {
      "epoch": 2.32183908045977,
      "grad_norm": 0.4786723256111145,
      "learning_rate": 0.0001303398058252427,
      "loss": 0.5765,
      "step": 253
    },
    {
      "epoch": 2.3310344827586205,
      "grad_norm": 0.39283815026283264,
      "learning_rate": 0.00012961165048543688,
      "loss": 0.4495,
      "step": 254
    },
    {
      "epoch": 2.340229885057471,
      "grad_norm": 0.4181981086730957,
      "learning_rate": 0.00012888349514563106,
      "loss": 0.4583,
      "step": 255
    },
    {
      "epoch": 2.349425287356322,
      "grad_norm": 0.5347463488578796,
      "learning_rate": 0.00012815533980582524,
      "loss": 0.6027,
      "step": 256
    },
    {
      "epoch": 2.3586206896551722,
      "grad_norm": 0.578888475894928,
      "learning_rate": 0.0001274271844660194,
      "loss": 0.7933,
      "step": 257
    },
    {
      "epoch": 2.367816091954023,
      "grad_norm": 0.5870189666748047,
      "learning_rate": 0.00012669902912621357,
      "loss": 0.4751,
      "step": 258
    },
    {
      "epoch": 2.3770114942528737,
      "grad_norm": 0.43344399333000183,
      "learning_rate": 0.00012597087378640775,
      "loss": 0.6022,
      "step": 259
    },
    {
      "epoch": 2.386206896551724,
      "grad_norm": 0.5693091750144958,
      "learning_rate": 0.00012524271844660192,
      "loss": 0.6392,
      "step": 260
    },
    {
      "epoch": 2.3954022988505748,
      "grad_norm": 0.5089174509048462,
      "learning_rate": 0.0001245145631067961,
      "loss": 0.6056,
      "step": 261
    },
    {
      "epoch": 2.4045977011494255,
      "grad_norm": 0.35980507731437683,
      "learning_rate": 0.00012378640776699028,
      "loss": 0.4163,
      "step": 262
    },
    {
      "epoch": 2.413793103448276,
      "grad_norm": 0.47071072459220886,
      "learning_rate": 0.00012305825242718446,
      "loss": 0.3934,
      "step": 263
    },
    {
      "epoch": 2.4229885057471265,
      "grad_norm": 0.44740450382232666,
      "learning_rate": 0.0001223300970873786,
      "loss": 0.3688,
      "step": 264
    },
    {
      "epoch": 2.432183908045977,
      "grad_norm": 0.3945635259151459,
      "learning_rate": 0.0001216019417475728,
      "loss": 0.44,
      "step": 265
    },
    {
      "epoch": 2.4413793103448276,
      "grad_norm": 0.5359259843826294,
      "learning_rate": 0.00012087378640776697,
      "loss": 0.7224,
      "step": 266
    },
    {
      "epoch": 2.4505747126436783,
      "grad_norm": 0.47032058238983154,
      "learning_rate": 0.00012014563106796115,
      "loss": 0.5569,
      "step": 267
    },
    {
      "epoch": 2.4597701149425286,
      "grad_norm": 0.37549111247062683,
      "learning_rate": 0.00011941747572815533,
      "loss": 0.431,
      "step": 268
    },
    {
      "epoch": 2.4689655172413794,
      "grad_norm": 0.39742720127105713,
      "learning_rate": 0.0001186893203883495,
      "loss": 0.4328,
      "step": 269
    },
    {
      "epoch": 2.4781609195402297,
      "grad_norm": 0.3550657629966736,
      "learning_rate": 0.00011796116504854367,
      "loss": 0.377,
      "step": 270
    },
    {
      "epoch": 2.4873563218390804,
      "grad_norm": 0.4095318615436554,
      "learning_rate": 0.00011723300970873785,
      "loss": 0.4171,
      "step": 271
    },
    {
      "epoch": 2.496551724137931,
      "grad_norm": 0.512859582901001,
      "learning_rate": 0.00011650485436893203,
      "loss": 0.8625,
      "step": 272
    },
    {
      "epoch": 2.5057471264367814,
      "grad_norm": 0.3573138117790222,
      "learning_rate": 0.0001157766990291262,
      "loss": 0.2954,
      "step": 273
    },
    {
      "epoch": 2.514942528735632,
      "grad_norm": 0.38249099254608154,
      "learning_rate": 0.00011504854368932037,
      "loss": 0.5005,
      "step": 274
    },
    {
      "epoch": 2.524137931034483,
      "grad_norm": 0.47415104508399963,
      "learning_rate": 0.00011432038834951455,
      "loss": 0.538,
      "step": 275
    },
    {
      "epoch": 2.533333333333333,
      "grad_norm": 0.2491881549358368,
      "learning_rate": 0.00011359223300970873,
      "loss": 0.2644,
      "step": 276
    },
    {
      "epoch": 2.542528735632184,
      "grad_norm": 0.44782719016075134,
      "learning_rate": 0.00011286407766990291,
      "loss": 0.5777,
      "step": 277
    },
    {
      "epoch": 2.5517241379310347,
      "grad_norm": 0.416042685508728,
      "learning_rate": 0.00011213592233009707,
      "loss": 0.5316,
      "step": 278
    },
    {
      "epoch": 2.560919540229885,
      "grad_norm": 0.3350113034248352,
      "learning_rate": 0.00011140776699029125,
      "loss": 0.3597,
      "step": 279
    },
    {
      "epoch": 2.5701149425287357,
      "grad_norm": 0.2985689640045166,
      "learning_rate": 0.00011067961165048543,
      "loss": 0.3409,
      "step": 280
    },
    {
      "epoch": 2.5793103448275865,
      "grad_norm": 0.3801935613155365,
      "learning_rate": 0.00010995145631067961,
      "loss": 0.4334,
      "step": 281
    },
    {
      "epoch": 2.5885057471264368,
      "grad_norm": 0.42416247725486755,
      "learning_rate": 0.00010922330097087377,
      "loss": 0.4395,
      "step": 282
    },
    {
      "epoch": 2.5977011494252875,
      "grad_norm": 0.5186505913734436,
      "learning_rate": 0.00010849514563106795,
      "loss": 0.6245,
      "step": 283
    },
    {
      "epoch": 2.606896551724138,
      "grad_norm": 0.3158859312534332,
      "learning_rate": 0.00010776699029126213,
      "loss": 0.3056,
      "step": 284
    },
    {
      "epoch": 2.6160919540229886,
      "grad_norm": 0.761823832988739,
      "learning_rate": 0.00010703883495145631,
      "loss": 0.4312,
      "step": 285
    },
    {
      "epoch": 2.625287356321839,
      "grad_norm": 0.38367024064064026,
      "learning_rate": 0.00010631067961165047,
      "loss": 0.4427,
      "step": 286
    },
    {
      "epoch": 2.6344827586206896,
      "grad_norm": 0.389691561460495,
      "learning_rate": 0.00010558252427184465,
      "loss": 0.3895,
      "step": 287
    },
    {
      "epoch": 2.6436781609195403,
      "grad_norm": 0.29964563250541687,
      "learning_rate": 0.00010485436893203883,
      "loss": 0.2478,
      "step": 288
    },
    {
      "epoch": 2.6528735632183906,
      "grad_norm": 0.45362621545791626,
      "learning_rate": 0.00010412621359223301,
      "loss": 0.5568,
      "step": 289
    },
    {
      "epoch": 2.6620689655172414,
      "grad_norm": 0.509632408618927,
      "learning_rate": 0.00010339805825242718,
      "loss": 0.5516,
      "step": 290
    },
    {
      "epoch": 2.671264367816092,
      "grad_norm": 0.4448017477989197,
      "learning_rate": 0.00010266990291262135,
      "loss": 0.6105,
      "step": 291
    },
    {
      "epoch": 2.6804597701149424,
      "grad_norm": 0.3983929455280304,
      "learning_rate": 0.00010194174757281553,
      "loss": 0.4041,
      "step": 292
    },
    {
      "epoch": 2.689655172413793,
      "grad_norm": 0.43729811906814575,
      "learning_rate": 0.00010121359223300971,
      "loss": 0.6012,
      "step": 293
    },
    {
      "epoch": 2.698850574712644,
      "grad_norm": 0.38785648345947266,
      "learning_rate": 0.00010048543689320388,
      "loss": 0.4812,
      "step": 294
    },
    {
      "epoch": 2.708045977011494,
      "grad_norm": 0.6477203369140625,
      "learning_rate": 9.975728155339806e-05,
      "loss": 0.8292,
      "step": 295
    },
    {
      "epoch": 2.717241379310345,
      "grad_norm": 0.5400519967079163,
      "learning_rate": 9.902912621359223e-05,
      "loss": 0.6755,
      "step": 296
    },
    {
      "epoch": 2.7264367816091957,
      "grad_norm": 0.39632365107536316,
      "learning_rate": 9.83009708737864e-05,
      "loss": 0.4604,
      "step": 297
    },
    {
      "epoch": 2.735632183908046,
      "grad_norm": 0.4676194190979004,
      "learning_rate": 9.757281553398058e-05,
      "loss": 0.5986,
      "step": 298
    },
    {
      "epoch": 2.7448275862068967,
      "grad_norm": 0.34826210141181946,
      "learning_rate": 9.684466019417476e-05,
      "loss": 0.4151,
      "step": 299
    },
    {
      "epoch": 2.754022988505747,
      "grad_norm": 0.4393360912799835,
      "learning_rate": 9.611650485436893e-05,
      "loss": 0.4995,
      "step": 300
    },
    {
      "epoch": 2.7632183908045977,
      "grad_norm": 0.39754021167755127,
      "learning_rate": 9.53883495145631e-05,
      "loss": 0.4783,
      "step": 301
    },
    {
      "epoch": 2.772413793103448,
      "grad_norm": 0.5463854074478149,
      "learning_rate": 9.466019417475728e-05,
      "loss": 0.5441,
      "step": 302
    },
    {
      "epoch": 2.781609195402299,
      "grad_norm": 0.3881894648075104,
      "learning_rate": 9.393203883495146e-05,
      "loss": 0.3949,
      "step": 303
    },
    {
      "epoch": 2.7908045977011495,
      "grad_norm": 0.5275911688804626,
      "learning_rate": 9.320388349514561e-05,
      "loss": 0.6102,
      "step": 304
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.3656928241252899,
      "learning_rate": 9.247572815533979e-05,
      "loss": 0.4045,
      "step": 305
    },
    {
      "epoch": 2.8091954022988506,
      "grad_norm": 0.35572561621665955,
      "learning_rate": 9.174757281553397e-05,
      "loss": 0.3061,
      "step": 306
    },
    {
      "epoch": 2.8183908045977013,
      "grad_norm": 0.569115400314331,
      "learning_rate": 9.101941747572814e-05,
      "loss": 0.8109,
      "step": 307
    },
    {
      "epoch": 2.8275862068965516,
      "grad_norm": 0.29033228754997253,
      "learning_rate": 9.029126213592231e-05,
      "loss": 0.317,
      "step": 308
    },
    {
      "epoch": 2.8367816091954023,
      "grad_norm": 0.3231950104236603,
      "learning_rate": 8.956310679611649e-05,
      "loss": 0.3689,
      "step": 309
    },
    {
      "epoch": 2.845977011494253,
      "grad_norm": 0.374177485704422,
      "learning_rate": 8.883495145631067e-05,
      "loss": 0.3802,
      "step": 310
    },
    {
      "epoch": 2.8551724137931034,
      "grad_norm": 0.25250348448753357,
      "learning_rate": 8.810679611650485e-05,
      "loss": 0.236,
      "step": 311
    },
    {
      "epoch": 2.864367816091954,
      "grad_norm": 0.5510450005531311,
      "learning_rate": 8.737864077669901e-05,
      "loss": 0.6565,
      "step": 312
    },
    {
      "epoch": 2.873563218390805,
      "grad_norm": 0.32372424006462097,
      "learning_rate": 8.665048543689319e-05,
      "loss": 0.4243,
      "step": 313
    },
    {
      "epoch": 2.882758620689655,
      "grad_norm": 0.34822607040405273,
      "learning_rate": 8.592233009708737e-05,
      "loss": 0.3775,
      "step": 314
    },
    {
      "epoch": 2.891954022988506,
      "grad_norm": 0.535407304763794,
      "learning_rate": 8.519417475728155e-05,
      "loss": 0.7348,
      "step": 315
    },
    {
      "epoch": 2.901149425287356,
      "grad_norm": 0.46572351455688477,
      "learning_rate": 8.446601941747571e-05,
      "loss": 0.5116,
      "step": 316
    },
    {
      "epoch": 2.910344827586207,
      "grad_norm": 0.6060393452644348,
      "learning_rate": 8.373786407766989e-05,
      "loss": 0.8337,
      "step": 317
    },
    {
      "epoch": 2.9195402298850572,
      "grad_norm": 0.3930990397930145,
      "learning_rate": 8.300970873786407e-05,
      "loss": 0.4314,
      "step": 318
    },
    {
      "epoch": 2.928735632183908,
      "grad_norm": 0.3868286907672882,
      "learning_rate": 8.228155339805825e-05,
      "loss": 0.3842,
      "step": 319
    },
    {
      "epoch": 2.9379310344827587,
      "grad_norm": 0.5302227139472961,
      "learning_rate": 8.155339805825241e-05,
      "loss": 0.7226,
      "step": 320
    },
    {
      "epoch": 2.947126436781609,
      "grad_norm": 0.46904534101486206,
      "learning_rate": 8.082524271844659e-05,
      "loss": 0.5142,
      "step": 321
    },
    {
      "epoch": 2.9563218390804598,
      "grad_norm": 0.4153412878513336,
      "learning_rate": 8.009708737864077e-05,
      "loss": 0.4995,
      "step": 322
    },
    {
      "epoch": 2.9655172413793105,
      "grad_norm": 0.3775100111961365,
      "learning_rate": 7.936893203883495e-05,
      "loss": 0.4082,
      "step": 323
    },
    {
      "epoch": 2.974712643678161,
      "grad_norm": 0.49698036909103394,
      "learning_rate": 7.864077669902911e-05,
      "loss": 0.58,
      "step": 324
    },
    {
      "epoch": 2.9839080459770115,
      "grad_norm": 0.6160023808479309,
      "learning_rate": 7.791262135922329e-05,
      "loss": 0.6326,
      "step": 325
    },
    {
      "epoch": 2.9931034482758623,
      "grad_norm": 0.5694648623466492,
      "learning_rate": 7.718446601941747e-05,
      "loss": 0.5942,
      "step": 326
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6814332604408264,
      "learning_rate": 7.645631067961165e-05,
      "loss": 0.7482,
      "step": 327
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.406995415687561,
      "eval_runtime": 70.8982,
      "eval_samples_per_second": 4.683,
      "eval_steps_per_second": 2.341,
      "step": 327
    },
    {
      "epoch": 3.0091954022988507,
      "grad_norm": 0.3148242235183716,
      "learning_rate": 7.572815533980581e-05,
      "loss": 0.2836,
      "step": 328
    },
    {
      "epoch": 3.018390804597701,
      "grad_norm": 0.2789768576622009,
      "learning_rate": 7.5e-05,
      "loss": 0.2641,
      "step": 329
    },
    {
      "epoch": 3.027586206896552,
      "grad_norm": 0.3457227051258087,
      "learning_rate": 7.427184466019417e-05,
      "loss": 0.3137,
      "step": 330
    },
    {
      "epoch": 3.036781609195402,
      "grad_norm": 0.3316015601158142,
      "learning_rate": 7.354368932038834e-05,
      "loss": 0.3261,
      "step": 331
    },
    {
      "epoch": 3.045977011494253,
      "grad_norm": 0.44476330280303955,
      "learning_rate": 7.281553398058252e-05,
      "loss": 0.446,
      "step": 332
    },
    {
      "epoch": 3.0551724137931036,
      "grad_norm": 0.4332521855831146,
      "learning_rate": 7.20873786407767e-05,
      "loss": 0.4406,
      "step": 333
    },
    {
      "epoch": 3.064367816091954,
      "grad_norm": 0.3380160331726074,
      "learning_rate": 7.135922330097087e-05,
      "loss": 0.2874,
      "step": 334
    },
    {
      "epoch": 3.0735632183908046,
      "grad_norm": 0.341746985912323,
      "learning_rate": 7.063106796116504e-05,
      "loss": 0.306,
      "step": 335
    },
    {
      "epoch": 3.0827586206896553,
      "grad_norm": 0.6307492256164551,
      "learning_rate": 6.990291262135922e-05,
      "loss": 0.682,
      "step": 336
    },
    {
      "epoch": 3.0919540229885056,
      "grad_norm": 0.5883364677429199,
      "learning_rate": 6.91747572815534e-05,
      "loss": 0.5423,
      "step": 337
    },
    {
      "epoch": 3.1011494252873564,
      "grad_norm": 0.36848077178001404,
      "learning_rate": 6.844660194174757e-05,
      "loss": 0.3521,
      "step": 338
    },
    {
      "epoch": 3.110344827586207,
      "grad_norm": 0.38027411699295044,
      "learning_rate": 6.771844660194174e-05,
      "loss": 0.3215,
      "step": 339
    },
    {
      "epoch": 3.1195402298850574,
      "grad_norm": 0.45381873846054077,
      "learning_rate": 6.699029126213592e-05,
      "loss": 0.5169,
      "step": 340
    },
    {
      "epoch": 3.128735632183908,
      "grad_norm": 0.574475884437561,
      "learning_rate": 6.62621359223301e-05,
      "loss": 0.5358,
      "step": 341
    },
    {
      "epoch": 3.1379310344827585,
      "grad_norm": 0.6136448979377747,
      "learning_rate": 6.553398058252426e-05,
      "loss": 0.7514,
      "step": 342
    },
    {
      "epoch": 3.147126436781609,
      "grad_norm": 0.32782498002052307,
      "learning_rate": 6.480582524271844e-05,
      "loss": 0.3133,
      "step": 343
    },
    {
      "epoch": 3.15632183908046,
      "grad_norm": 0.4657121002674103,
      "learning_rate": 6.407766990291262e-05,
      "loss": 0.4632,
      "step": 344
    },
    {
      "epoch": 3.1655172413793102,
      "grad_norm": 0.33205467462539673,
      "learning_rate": 6.334951456310678e-05,
      "loss": 0.298,
      "step": 345
    },
    {
      "epoch": 3.174712643678161,
      "grad_norm": 0.37659305334091187,
      "learning_rate": 6.262135922330096e-05,
      "loss": 0.2884,
      "step": 346
    },
    {
      "epoch": 3.1839080459770113,
      "grad_norm": 0.47502419352531433,
      "learning_rate": 6.189320388349514e-05,
      "loss": 0.5064,
      "step": 347
    },
    {
      "epoch": 3.193103448275862,
      "grad_norm": 0.6712875366210938,
      "learning_rate": 6.11650485436893e-05,
      "loss": 0.6806,
      "step": 348
    },
    {
      "epoch": 3.2022988505747128,
      "grad_norm": 0.5198653340339661,
      "learning_rate": 6.0436893203883485e-05,
      "loss": 0.5421,
      "step": 349
    },
    {
      "epoch": 3.211494252873563,
      "grad_norm": 0.43809249997138977,
      "learning_rate": 5.9708737864077663e-05,
      "loss": 0.4123,
      "step": 350
    },
    {
      "epoch": 3.220689655172414,
      "grad_norm": 0.3182849884033203,
      "learning_rate": 5.8980582524271835e-05,
      "loss": 0.3025,
      "step": 351
    },
    {
      "epoch": 3.2298850574712645,
      "grad_norm": 0.32380396127700806,
      "learning_rate": 5.8252427184466014e-05,
      "loss": 0.3006,
      "step": 352
    },
    {
      "epoch": 3.239080459770115,
      "grad_norm": 0.32146674394607544,
      "learning_rate": 5.7524271844660186e-05,
      "loss": 0.2698,
      "step": 353
    },
    {
      "epoch": 3.2482758620689656,
      "grad_norm": 0.3990193009376526,
      "learning_rate": 5.6796116504854364e-05,
      "loss": 0.379,
      "step": 354
    },
    {
      "epoch": 3.2574712643678163,
      "grad_norm": 0.5906070470809937,
      "learning_rate": 5.6067961165048536e-05,
      "loss": 0.5351,
      "step": 355
    },
    {
      "epoch": 3.2666666666666666,
      "grad_norm": 0.4367024004459381,
      "learning_rate": 5.5339805825242715e-05,
      "loss": 0.4316,
      "step": 356
    },
    {
      "epoch": 3.2758620689655173,
      "grad_norm": 0.4074479639530182,
      "learning_rate": 5.461165048543689e-05,
      "loss": 0.323,
      "step": 357
    },
    {
      "epoch": 3.2850574712643676,
      "grad_norm": 0.3967445194721222,
      "learning_rate": 5.3883495145631065e-05,
      "loss": 0.3267,
      "step": 358
    },
    {
      "epoch": 3.2942528735632184,
      "grad_norm": 0.4907247722148895,
      "learning_rate": 5.315533980582524e-05,
      "loss": 0.4108,
      "step": 359
    },
    {
      "epoch": 3.303448275862069,
      "grad_norm": 0.24740606546401978,
      "learning_rate": 5.2427184466019416e-05,
      "loss": 0.1978,
      "step": 360
    },
    {
      "epoch": 3.3126436781609194,
      "grad_norm": 0.6829200387001038,
      "learning_rate": 5.169902912621359e-05,
      "loss": 0.6487,
      "step": 361
    },
    {
      "epoch": 3.32183908045977,
      "grad_norm": 0.5345665216445923,
      "learning_rate": 5.0970873786407766e-05,
      "loss": 0.4638,
      "step": 362
    },
    {
      "epoch": 3.3310344827586205,
      "grad_norm": 0.3852749466896057,
      "learning_rate": 5.024271844660194e-05,
      "loss": 0.4437,
      "step": 363
    },
    {
      "epoch": 3.340229885057471,
      "grad_norm": 0.3901817202568054,
      "learning_rate": 4.951456310679612e-05,
      "loss": 0.425,
      "step": 364
    },
    {
      "epoch": 3.349425287356322,
      "grad_norm": 0.5544285178184509,
      "learning_rate": 4.878640776699029e-05,
      "loss": 0.4356,
      "step": 365
    },
    {
      "epoch": 3.3586206896551722,
      "grad_norm": 0.49693530797958374,
      "learning_rate": 4.805825242718447e-05,
      "loss": 0.4442,
      "step": 366
    },
    {
      "epoch": 3.367816091954023,
      "grad_norm": 0.48270636796951294,
      "learning_rate": 4.733009708737864e-05,
      "loss": 0.5047,
      "step": 367
    },
    {
      "epoch": 3.3770114942528737,
      "grad_norm": 0.5815203189849854,
      "learning_rate": 4.6601941747572804e-05,
      "loss": 0.7068,
      "step": 368
    },
    {
      "epoch": 3.386206896551724,
      "grad_norm": 0.6433053612709045,
      "learning_rate": 4.587378640776698e-05,
      "loss": 0.5708,
      "step": 369
    },
    {
      "epoch": 3.3954022988505748,
      "grad_norm": 0.35983002185821533,
      "learning_rate": 4.5145631067961155e-05,
      "loss": 0.289,
      "step": 370
    },
    {
      "epoch": 3.4045977011494255,
      "grad_norm": 0.4140273630619049,
      "learning_rate": 4.4417475728155334e-05,
      "loss": 0.4028,
      "step": 371
    },
    {
      "epoch": 3.413793103448276,
      "grad_norm": 0.36001721024513245,
      "learning_rate": 4.3689320388349505e-05,
      "loss": 0.3798,
      "step": 372
    },
    {
      "epoch": 3.4229885057471265,
      "grad_norm": 0.3390791416168213,
      "learning_rate": 4.2961165048543684e-05,
      "loss": 0.271,
      "step": 373
    },
    {
      "epoch": 3.432183908045977,
      "grad_norm": 0.44555366039276123,
      "learning_rate": 4.2233009708737856e-05,
      "loss": 0.3578,
      "step": 374
    },
    {
      "epoch": 3.4413793103448276,
      "grad_norm": 0.5408360958099365,
      "learning_rate": 4.1504854368932035e-05,
      "loss": 0.6705,
      "step": 375
    },
    {
      "epoch": 3.4505747126436783,
      "grad_norm": 0.3276488482952118,
      "learning_rate": 4.0776699029126206e-05,
      "loss": 0.302,
      "step": 376
    },
    {
      "epoch": 3.4597701149425286,
      "grad_norm": 0.5470909476280212,
      "learning_rate": 4.0048543689320385e-05,
      "loss": 0.4292,
      "step": 377
    },
    {
      "epoch": 3.4689655172413794,
      "grad_norm": 0.3690268099308014,
      "learning_rate": 3.932038834951456e-05,
      "loss": 0.3245,
      "step": 378
    },
    {
      "epoch": 3.4781609195402297,
      "grad_norm": 0.5388251543045044,
      "learning_rate": 3.8592233009708736e-05,
      "loss": 0.5772,
      "step": 379
    },
    {
      "epoch": 3.4873563218390804,
      "grad_norm": 0.39318031072616577,
      "learning_rate": 3.786407766990291e-05,
      "loss": 0.3266,
      "step": 380
    },
    {
      "epoch": 3.496551724137931,
      "grad_norm": 0.3929058313369751,
      "learning_rate": 3.7135922330097086e-05,
      "loss": 0.3401,
      "step": 381
    },
    {
      "epoch": 3.5057471264367814,
      "grad_norm": 0.4667484760284424,
      "learning_rate": 3.640776699029126e-05,
      "loss": 0.3983,
      "step": 382
    },
    {
      "epoch": 3.514942528735632,
      "grad_norm": 0.4457002282142639,
      "learning_rate": 3.5679611650485437e-05,
      "loss": 0.3478,
      "step": 383
    },
    {
      "epoch": 3.524137931034483,
      "grad_norm": 0.4100305736064911,
      "learning_rate": 3.495145631067961e-05,
      "loss": 0.3732,
      "step": 384
    },
    {
      "epoch": 3.533333333333333,
      "grad_norm": 0.46938103437423706,
      "learning_rate": 3.422330097087379e-05,
      "loss": 0.4959,
      "step": 385
    },
    {
      "epoch": 3.542528735632184,
      "grad_norm": 0.6163147687911987,
      "learning_rate": 3.349514563106796e-05,
      "loss": 0.6359,
      "step": 386
    },
    {
      "epoch": 3.5517241379310347,
      "grad_norm": 0.39543232321739197,
      "learning_rate": 3.276699029126213e-05,
      "loss": 0.3193,
      "step": 387
    },
    {
      "epoch": 3.560919540229885,
      "grad_norm": 0.3851659297943115,
      "learning_rate": 3.203883495145631e-05,
      "loss": 0.2912,
      "step": 388
    },
    {
      "epoch": 3.5701149425287357,
      "grad_norm": 0.31686195731163025,
      "learning_rate": 3.131067961165048e-05,
      "loss": 0.2545,
      "step": 389
    },
    {
      "epoch": 3.5793103448275865,
      "grad_norm": 0.4179750084877014,
      "learning_rate": 3.058252427184465e-05,
      "loss": 0.3569,
      "step": 390
    },
    {
      "epoch": 3.5885057471264368,
      "grad_norm": 0.49302592873573303,
      "learning_rate": 2.9854368932038832e-05,
      "loss": 0.4231,
      "step": 391
    },
    {
      "epoch": 3.5977011494252875,
      "grad_norm": 0.4251144826412201,
      "learning_rate": 2.9126213592233007e-05,
      "loss": 0.363,
      "step": 392
    },
    {
      "epoch": 3.606896551724138,
      "grad_norm": 0.5428581237792969,
      "learning_rate": 2.8398058252427182e-05,
      "loss": 0.491,
      "step": 393
    },
    {
      "epoch": 3.6160919540229886,
      "grad_norm": 0.4546624720096588,
      "learning_rate": 2.7669902912621357e-05,
      "loss": 0.4286,
      "step": 394
    },
    {
      "epoch": 3.625287356321839,
      "grad_norm": 0.6219410300254822,
      "learning_rate": 2.6941747572815533e-05,
      "loss": 0.5962,
      "step": 395
    },
    {
      "epoch": 3.6344827586206896,
      "grad_norm": 0.4943522810935974,
      "learning_rate": 2.6213592233009708e-05,
      "loss": 0.3746,
      "step": 396
    },
    {
      "epoch": 3.6436781609195403,
      "grad_norm": 0.34759849309921265,
      "learning_rate": 2.5485436893203883e-05,
      "loss": 0.3504,
      "step": 397
    },
    {
      "epoch": 3.6528735632183906,
      "grad_norm": 0.45892637968063354,
      "learning_rate": 2.475728155339806e-05,
      "loss": 0.2571,
      "step": 398
    },
    {
      "epoch": 3.6620689655172414,
      "grad_norm": 0.4840629994869232,
      "learning_rate": 2.4029126213592234e-05,
      "loss": 0.4038,
      "step": 399
    },
    {
      "epoch": 3.671264367816092,
      "grad_norm": 0.5587469339370728,
      "learning_rate": 2.3300970873786402e-05,
      "loss": 0.6057,
      "step": 400
    },
    {
      "epoch": 3.6804597701149424,
      "grad_norm": 0.30649712681770325,
      "learning_rate": 2.2572815533980577e-05,
      "loss": 0.2603,
      "step": 401
    },
    {
      "epoch": 3.689655172413793,
      "grad_norm": 0.41518911719322205,
      "learning_rate": 2.1844660194174753e-05,
      "loss": 0.3146,
      "step": 402
    },
    {
      "epoch": 3.698850574712644,
      "grad_norm": 0.596571147441864,
      "learning_rate": 2.1116504854368928e-05,
      "loss": 0.6675,
      "step": 403
    },
    {
      "epoch": 3.708045977011494,
      "grad_norm": 0.4106796085834503,
      "learning_rate": 2.0388349514563103e-05,
      "loss": 0.4136,
      "step": 404
    },
    {
      "epoch": 3.717241379310345,
      "grad_norm": 0.5261825323104858,
      "learning_rate": 1.966019417475728e-05,
      "loss": 0.6104,
      "step": 405
    },
    {
      "epoch": 3.7264367816091957,
      "grad_norm": 0.5117531418800354,
      "learning_rate": 1.8932038834951454e-05,
      "loss": 0.4088,
      "step": 406
    },
    {
      "epoch": 3.735632183908046,
      "grad_norm": 0.46011051535606384,
      "learning_rate": 1.820388349514563e-05,
      "loss": 0.3203,
      "step": 407
    },
    {
      "epoch": 3.7448275862068967,
      "grad_norm": 0.5213779211044312,
      "learning_rate": 1.7475728155339804e-05,
      "loss": 0.4547,
      "step": 408
    },
    {
      "epoch": 3.754022988505747,
      "grad_norm": 0.6189706921577454,
      "learning_rate": 1.674757281553398e-05,
      "loss": 0.4992,
      "step": 409
    },
    {
      "epoch": 3.7632183908045977,
      "grad_norm": 0.38668373227119446,
      "learning_rate": 1.6019417475728155e-05,
      "loss": 0.3237,
      "step": 410
    },
    {
      "epoch": 3.772413793103448,
      "grad_norm": 0.6517217755317688,
      "learning_rate": 1.5291262135922327e-05,
      "loss": 0.6421,
      "step": 411
    },
    {
      "epoch": 3.781609195402299,
      "grad_norm": 0.4396495223045349,
      "learning_rate": 1.4563106796116503e-05,
      "loss": 0.4529,
      "step": 412
    },
    {
      "epoch": 3.7908045977011495,
      "grad_norm": 0.5464988350868225,
      "learning_rate": 1.3834951456310679e-05,
      "loss": 0.5085,
      "step": 413
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.49847450852394104,
      "learning_rate": 1.3106796116504854e-05,
      "loss": 0.4448,
      "step": 414
    },
    {
      "epoch": 3.8091954022988506,
      "grad_norm": 0.26215147972106934,
      "learning_rate": 1.237864077669903e-05,
      "loss": 0.207,
      "step": 415
    },
    {
      "epoch": 3.8183908045977013,
      "grad_norm": 0.5166394710540771,
      "learning_rate": 1.1650485436893201e-05,
      "loss": 0.4386,
      "step": 416
    },
    {
      "epoch": 3.8275862068965516,
      "grad_norm": 0.3470999002456665,
      "learning_rate": 1.0922330097087376e-05,
      "loss": 0.3337,
      "step": 417
    },
    {
      "epoch": 3.8367816091954023,
      "grad_norm": 0.41472527384757996,
      "learning_rate": 1.0194174757281552e-05,
      "loss": 0.3873,
      "step": 418
    },
    {
      "epoch": 3.845977011494253,
      "grad_norm": 0.3731400668621063,
      "learning_rate": 9.466019417475727e-06,
      "loss": 0.3003,
      "step": 419
    },
    {
      "epoch": 3.8551724137931034,
      "grad_norm": 0.4794781506061554,
      "learning_rate": 8.737864077669902e-06,
      "loss": 0.4373,
      "step": 420
    },
    {
      "epoch": 3.864367816091954,
      "grad_norm": 0.4784807562828064,
      "learning_rate": 8.009708737864077e-06,
      "loss": 0.3727,
      "step": 421
    },
    {
      "epoch": 3.873563218390805,
      "grad_norm": 0.4147201478481293,
      "learning_rate": 7.281553398058252e-06,
      "loss": 0.416,
      "step": 422
    },
    {
      "epoch": 3.882758620689655,
      "grad_norm": 0.33760857582092285,
      "learning_rate": 6.553398058252427e-06,
      "loss": 0.2351,
      "step": 423
    },
    {
      "epoch": 3.891954022988506,
      "grad_norm": 0.38601207733154297,
      "learning_rate": 5.8252427184466006e-06,
      "loss": 0.328,
      "step": 424
    },
    {
      "epoch": 3.901149425287356,
      "grad_norm": 0.5886791944503784,
      "learning_rate": 5.097087378640776e-06,
      "loss": 0.523,
      "step": 425
    },
    {
      "epoch": 3.910344827586207,
      "grad_norm": 0.497087687253952,
      "learning_rate": 4.368932038834951e-06,
      "loss": 0.4786,
      "step": 426
    },
    {
      "epoch": 3.9195402298850572,
      "grad_norm": 0.29946476221084595,
      "learning_rate": 3.640776699029126e-06,
      "loss": 0.208,
      "step": 427
    },
    {
      "epoch": 3.928735632183908,
      "grad_norm": 0.4071413576602936,
      "learning_rate": 2.9126213592233003e-06,
      "loss": 0.3595,
      "step": 428
    },
    {
      "epoch": 3.9379310344827587,
      "grad_norm": 0.4986608624458313,
      "learning_rate": 2.1844660194174755e-06,
      "loss": 0.3931,
      "step": 429
    },
    {
      "epoch": 3.947126436781609,
      "grad_norm": 0.32442793250083923,
      "learning_rate": 1.4563106796116501e-06,
      "loss": 0.4026,
      "step": 430
    },
    {
      "epoch": 3.9563218390804598,
      "grad_norm": 0.6014803051948547,
      "learning_rate": 7.281553398058251e-07,
      "loss": 0.6049,
      "step": 431
    },
    {
      "epoch": 3.9655172413793105,
      "grad_norm": 0.6689134836196899,
      "learning_rate": 0.0,
      "loss": 0.6334,
      "step": 432
    },
    {
      "epoch": 3.9655172413793105,
      "eval_loss": 1.4621280431747437,
      "eval_runtime": 70.3815,
      "eval_samples_per_second": 4.717,
      "eval_steps_per_second": 2.359,
      "step": 432
    }
  ],
  "logging_steps": 1,
  "max_steps": 432,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5357902367421235e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}