{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.961363636363636,
  "eval_steps": 500,
  "global_step": 3063,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 0.026781119406223297,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.922,
      "step": 10
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.024741673842072487,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.8923,
      "step": 20
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 0.02995569072663784,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.9527,
      "step": 30
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.029402069747447968,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.9525,
      "step": 40
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 0.030222086235880852,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.868,
      "step": 50
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.026196401566267014,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.8827,
      "step": 60
    },
    {
      "epoch": 0.1590909090909091,
      "grad_norm": 0.029812786728143692,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.9446,
      "step": 70
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.02471482940018177,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.9012,
      "step": 80
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 0.032019663602113724,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.9249,
      "step": 90
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.03502049297094345,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.9458,
      "step": 100
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.03877561166882515,
      "learning_rate": 4.4e-06,
      "loss": 0.9368,
      "step": 110
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.03687964007258415,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.9022,
      "step": 120
    },
    {
      "epoch": 0.29545454545454547,
      "grad_norm": 0.03736700490117073,
      "learning_rate": 5.2e-06,
      "loss": 0.9155,
      "step": 130
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.04338955879211426,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.8981,
      "step": 140
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.03441348299384117,
      "learning_rate": 6e-06,
      "loss": 0.8779,
      "step": 150
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.04274949058890343,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.9095,
      "step": 160
    },
    {
      "epoch": 0.38636363636363635,
      "grad_norm": 0.04366679862141609,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.8781,
      "step": 170
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.041996780782938004,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.9327,
      "step": 180
    },
    {
      "epoch": 0.4318181818181818,
      "grad_norm": 0.050978969782590866,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.864,
      "step": 190
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.04162677377462387,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9109,
      "step": 200
    },
    {
      "epoch": 0.4772727272727273,
      "grad_norm": 0.041858162730932236,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.8516,
      "step": 210
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.04480082169175148,
      "learning_rate": 8.8e-06,
      "loss": 0.8642,
      "step": 220
    },
    {
      "epoch": 0.5227272727272727,
      "grad_norm": 0.035324063152074814,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.8552,
      "step": 230
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.04161485657095909,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.8037,
      "step": 240
    },
    {
      "epoch": 0.5681818181818182,
      "grad_norm": 0.04798528924584389,
      "learning_rate": 1e-05,
      "loss": 0.8653,
      "step": 250
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.03867500275373459,
      "learning_rate": 9.999688185881378e-06,
      "loss": 0.8552,
      "step": 260
    },
    {
      "epoch": 0.6136363636363636,
      "grad_norm": 0.04236117750406265,
      "learning_rate": 9.998752782416726e-06,
      "loss": 0.8153,
      "step": 270
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.036168813705444336,
      "learning_rate": 9.997193906274847e-06,
      "loss": 0.8214,
      "step": 280
    },
    {
      "epoch": 0.6590909090909091,
      "grad_norm": 0.042327072471380234,
      "learning_rate": 9.995011751887578e-06,
      "loss": 0.8484,
      "step": 290
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.03896569833159447,
      "learning_rate": 9.992206591425538e-06,
      "loss": 0.8249,
      "step": 300
    },
    {
      "epoch": 0.7045454545454546,
      "grad_norm": 0.042347826063632965,
      "learning_rate": 9.988778774764182e-06,
      "loss": 0.8279,
      "step": 310
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.037002451717853546,
      "learning_rate": 9.984728729440162e-06,
      "loss": 0.8321,
      "step": 320
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.03902013972401619,
      "learning_rate": 9.980056960598003e-06,
      "loss": 0.8043,
      "step": 330
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.03872638940811157,
      "learning_rate": 9.974764050927098e-06,
      "loss": 0.8564,
      "step": 340
    },
    {
      "epoch": 0.7954545454545454,
      "grad_norm": 0.03531708940863609,
      "learning_rate": 9.968850660589034e-06,
      "loss": 0.7862,
      "step": 350
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.03553822636604309,
      "learning_rate": 9.962317527135248e-06,
      "loss": 0.8055,
      "step": 360
    },
    {
      "epoch": 0.8409090909090909,
      "grad_norm": 0.034433577209711075,
      "learning_rate": 9.955165465415041e-06,
      "loss": 0.8178,
      "step": 370
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.03880152851343155,
      "learning_rate": 9.947395367473945e-06,
      "loss": 0.7978,
      "step": 380
    },
    {
      "epoch": 0.8863636363636364,
      "grad_norm": 0.035060495138168335,
      "learning_rate": 9.939008202442448e-06,
      "loss": 0.8052,
      "step": 390
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.029547426849603653,
      "learning_rate": 9.930005016415148e-06,
      "loss": 0.8159,
      "step": 400
    },
    {
      "epoch": 0.9318181818181818,
      "grad_norm": 0.03689836710691452,
      "learning_rate": 9.920386932320243e-06,
      "loss": 0.8229,
      "step": 410
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.035304516553878784,
      "learning_rate": 9.910155149779505e-06,
      "loss": 0.8144,
      "step": 420
    },
    {
      "epoch": 0.9772727272727273,
      "grad_norm": 0.03637601435184479,
      "learning_rate": 9.899310944958634e-06,
      "loss": 0.8451,
      "step": 430
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.032583512365818024,
      "learning_rate": 9.887855670408098e-06,
      "loss": 0.8083,
      "step": 440
    },
    {
      "epoch": 1.0227272727272727,
      "grad_norm": 0.037623800337314606,
      "learning_rate": 9.87579075489443e-06,
      "loss": 0.8463,
      "step": 450
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 0.0319579653441906,
      "learning_rate": 9.863117703222032e-06,
      "loss": 0.8575,
      "step": 460
    },
    {
      "epoch": 1.0681818181818181,
      "grad_norm": 0.03368237987160683,
      "learning_rate": 9.849838096045475e-06,
      "loss": 0.8193,
      "step": 470
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.03865516185760498,
      "learning_rate": 9.835953589672364e-06,
      "loss": 0.7893,
      "step": 480
    },
    {
      "epoch": 1.1136363636363635,
      "grad_norm": 0.0340314581990242,
      "learning_rate": 9.82146591585675e-06,
      "loss": 0.8193,
      "step": 490
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 0.03837134689092636,
      "learning_rate": 9.806376881583122e-06,
      "loss": 0.7955,
      "step": 500
    },
    {
      "epoch": 1.1590909090909092,
      "grad_norm": 0.03679390251636505,
      "learning_rate": 9.790688368841054e-06,
      "loss": 0.8371,
      "step": 510
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.03493216633796692,
      "learning_rate": 9.774402334390454e-06,
      "loss": 0.8137,
      "step": 520
    },
    {
      "epoch": 1.2045454545454546,
      "grad_norm": 0.0344357043504715,
      "learning_rate": 9.757520809517515e-06,
      "loss": 0.8007,
      "step": 530
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 0.036025360226631165,
      "learning_rate": 9.740045899781353e-06,
      "loss": 0.8015,
      "step": 540
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.03330492600798607,
      "learning_rate": 9.721979784751403e-06,
      "loss": 0.8023,
      "step": 550
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.03598447144031525,
      "learning_rate": 9.703324717735556e-06,
      "loss": 0.8281,
      "step": 560
    },
    {
      "epoch": 1.2954545454545454,
      "grad_norm": 0.03607608377933502,
      "learning_rate": 9.684083025499125e-06,
      "loss": 0.8004,
      "step": 570
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 0.03628605976700783,
      "learning_rate": 9.664257107974633e-06,
      "loss": 0.7802,
      "step": 580
    },
    {
      "epoch": 1.3409090909090908,
      "grad_norm": 0.036778271198272705,
      "learning_rate": 9.643849437962476e-06,
      "loss": 0.8156,
      "step": 590
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.03817847743630409,
      "learning_rate": 9.622862560822515e-06,
      "loss": 0.8253,
      "step": 600
    },
    {
      "epoch": 1.3863636363636362,
      "grad_norm": 0.039363328367471695,
      "learning_rate": 9.601299094156584e-06,
      "loss": 0.8231,
      "step": 610
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 0.04012521356344223,
      "learning_rate": 9.579161727482027e-06,
      "loss": 0.7971,
      "step": 620
    },
    {
      "epoch": 1.4318181818181819,
      "grad_norm": 0.03911637142300606,
      "learning_rate": 9.556453221896234e-06,
      "loss": 0.7919,
      "step": 630
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.037754397839307785,
      "learning_rate": 9.53317640973227e-06,
      "loss": 0.8145,
      "step": 640
    },
    {
      "epoch": 1.4772727272727273,
      "grad_norm": 0.03671397641301155,
      "learning_rate": 9.509334194205597e-06,
      "loss": 0.7797,
      "step": 650
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.03528128191828728,
      "learning_rate": 9.484929549051987e-06,
      "loss": 0.8019,
      "step": 660
    },
    {
      "epoch": 1.5227272727272727,
      "grad_norm": 0.038603346794843674,
      "learning_rate": 9.459965518156607e-06,
      "loss": 0.8291,
      "step": 670
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.03947769105434418,
      "learning_rate": 9.434445215174372e-06,
      "loss": 0.8228,
      "step": 680
    },
    {
      "epoch": 1.5681818181818183,
      "grad_norm": 0.037381611764431,
      "learning_rate": 9.408371823141597e-06,
      "loss": 0.8238,
      "step": 690
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 0.03954509273171425,
      "learning_rate": 9.381748594078983e-06,
      "loss": 0.8188,
      "step": 700
    },
    {
      "epoch": 1.6136363636363638,
      "grad_norm": 0.038289956748485565,
      "learning_rate": 9.354578848586011e-06,
      "loss": 0.7787,
      "step": 710
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.038311704993247986,
      "learning_rate": 9.326865975426782e-06,
      "loss": 0.786,
      "step": 720
    },
    {
      "epoch": 1.6590909090909092,
      "grad_norm": 0.03961798921227455,
      "learning_rate": 9.298613431107339e-06,
      "loss": 0.7887,
      "step": 730
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 0.038849055767059326,
      "learning_rate": 9.269824739444568e-06,
      "loss": 0.8028,
      "step": 740
    },
    {
      "epoch": 1.7045454545454546,
      "grad_norm": 0.04103654995560646,
      "learning_rate": 9.240503491126676e-06,
      "loss": 0.8409,
      "step": 750
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.03809870034456253,
      "learning_rate": 9.210653343265341e-06,
      "loss": 0.809,
      "step": 760
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.037855364382267,
      "learning_rate": 9.180278018939581e-06,
      "loss": 0.8192,
      "step": 770
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 0.04093025252223015,
      "learning_rate": 9.149381306731392e-06,
      "loss": 0.8421,
      "step": 780
    },
    {
      "epoch": 1.7954545454545454,
      "grad_norm": 0.036524541676044464,
      "learning_rate": 9.117967060253205e-06,
      "loss": 0.7747,
      "step": 790
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.04049857705831528,
      "learning_rate": 9.086039197667255e-06,
      "loss": 0.8201,
      "step": 800
    },
    {
      "epoch": 1.8409090909090908,
      "grad_norm": 0.0417928546667099,
      "learning_rate": 9.053601701196871e-06,
      "loss": 0.7924,
      "step": 810
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 0.04128099977970123,
      "learning_rate": 9.020658616629804e-06,
      "loss": 0.8143,
      "step": 820
    },
    {
      "epoch": 1.8863636363636362,
      "grad_norm": 0.040873561054468155,
      "learning_rate": 8.987214052813605e-06,
      "loss": 0.8141,
      "step": 830
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.04162426292896271,
      "learning_rate": 8.953272181143149e-06,
      "loss": 0.7927,
      "step": 840
    },
    {
      "epoch": 1.9318181818181817,
      "grad_norm": 0.039612602442502975,
      "learning_rate": 8.918837235040357e-06,
      "loss": 0.8134,
      "step": 850
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 0.039780184626579285,
      "learning_rate": 8.883913509426176e-06,
      "loss": 0.7678,
      "step": 860
    },
    {
      "epoch": 1.9772727272727273,
      "grad_norm": 0.0440000519156456,
      "learning_rate": 8.848505360184895e-06,
      "loss": 0.79,
      "step": 870
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.04121037945151329,
      "learning_rate": 8.812617203620853e-06,
      "loss": 0.7499,
      "step": 880
    },
    {
      "epoch": 2.022727272727273,
      "grad_norm": 0.04250968620181084,
      "learning_rate": 8.776253515907611e-06,
      "loss": 0.8203,
      "step": 890
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 0.04543096572160721,
      "learning_rate": 8.739418832529665e-06,
      "loss": 0.8114,
      "step": 900
    },
    {
      "epoch": 2.0681818181818183,
      "grad_norm": 0.0420922227203846,
      "learning_rate": 8.70211774771675e-06,
      "loss": 0.8247,
      "step": 910
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 0.04692165553569794,
      "learning_rate": 8.664354913870813e-06,
      "loss": 0.8278,
      "step": 920
    },
    {
      "epoch": 2.1136363636363638,
      "grad_norm": 0.040763940662145615,
      "learning_rate": 8.626135040985762e-06,
      "loss": 0.7801,
      "step": 930
    },
    {
      "epoch": 2.1363636363636362,
      "grad_norm": 0.046543512493371964,
      "learning_rate": 8.587462896059986e-06,
      "loss": 0.8104,
      "step": 940
    },
    {
      "epoch": 2.159090909090909,
      "grad_norm": 0.04344585910439491,
      "learning_rate": 8.548343302501796e-06,
      "loss": 0.8122,
      "step": 950
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.046868693083524704,
      "learning_rate": 8.508781139527831e-06,
      "loss": 0.8149,
      "step": 960
    },
    {
      "epoch": 2.2045454545454546,
      "grad_norm": 0.04557256028056145,
      "learning_rate": 8.46878134155448e-06,
      "loss": 0.7924,
      "step": 970
    },
    {
      "epoch": 2.227272727272727,
      "grad_norm": 0.04453985020518303,
      "learning_rate": 8.428348897582442e-06,
      "loss": 0.7918,
      "step": 980
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.04629656299948692,
      "learning_rate": 8.387488850574473e-06,
      "loss": 0.7705,
      "step": 990
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.0446246862411499,
      "learning_rate": 8.346206296826387e-06,
      "loss": 0.7967,
      "step": 1000
    },
    {
      "epoch": 2.2954545454545454,
      "grad_norm": 0.044356152415275574,
      "learning_rate": 8.30450638533143e-06,
      "loss": 0.7817,
      "step": 1010
    },
    {
      "epoch": 2.3181818181818183,
      "grad_norm": 0.043874483555555344,
      "learning_rate": 8.262394317138062e-06,
      "loss": 0.784,
      "step": 1020
    },
    {
      "epoch": 2.340909090909091,
      "grad_norm": 0.044783398509025574,
      "learning_rate": 8.219875344701255e-06,
      "loss": 0.787,
      "step": 1030
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.04361894354224205,
      "learning_rate": 8.176954771227372e-06,
      "loss": 0.7436,
      "step": 1040
    },
    {
      "epoch": 2.3863636363636362,
      "grad_norm": 0.04469903185963631,
      "learning_rate": 8.133637950012732e-06,
      "loss": 0.817,
      "step": 1050
    },
    {
      "epoch": 2.409090909090909,
      "grad_norm": 0.04548465088009834,
      "learning_rate": 8.089930283775906e-06,
      "loss": 0.7791,
      "step": 1060
    },
    {
      "epoch": 2.4318181818181817,
      "grad_norm": 0.04449579119682312,
      "learning_rate": 8.04583722398386e-06,
      "loss": 0.8076,
      "step": 1070
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 0.05069056153297424,
      "learning_rate": 8.001364270172029e-06,
      "loss": 0.7932,
      "step": 1080
    },
    {
      "epoch": 2.4772727272727275,
      "grad_norm": 0.04452840983867645,
      "learning_rate": 7.95651696925837e-06,
      "loss": 0.7752,
      "step": 1090
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.044558193534612656,
      "learning_rate": 7.911300914851523e-06,
      "loss": 0.7854,
      "step": 1100
    },
    {
      "epoch": 2.5227272727272725,
      "grad_norm": 0.044422492384910583,
      "learning_rate": 7.865721746553151e-06,
      "loss": 0.7784,
      "step": 1110
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.04627745598554611,
      "learning_rate": 7.819785149254534e-06,
      "loss": 0.7476,
      "step": 1120
    },
    {
      "epoch": 2.5681818181818183,
      "grad_norm": 0.04218703508377075,
      "learning_rate": 7.773496852427504e-06,
      "loss": 0.8409,
      "step": 1130
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 0.050779055804014206,
      "learning_rate": 7.72686262940986e-06,
      "loss": 0.8242,
      "step": 1140
    },
    {
      "epoch": 2.6136363636363638,
      "grad_norm": 0.04828439652919769,
      "learning_rate": 7.679888296685256e-06,
      "loss": 0.7958,
      "step": 1150
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 0.05190173536539078,
      "learning_rate": 7.632579713157755e-06,
      "loss": 0.8086,
      "step": 1160
    },
    {
      "epoch": 2.659090909090909,
      "grad_norm": 0.046120744198560715,
      "learning_rate": 7.58494277942107e-06,
      "loss": 0.83,
      "step": 1170
    },
    {
      "epoch": 2.6818181818181817,
      "grad_norm": 0.051556602120399475,
      "learning_rate": 7.5369834370226005e-06,
      "loss": 0.8245,
      "step": 1180
    },
    {
      "epoch": 2.7045454545454546,
      "grad_norm": 0.045309435576200485,
      "learning_rate": 7.488707667722381e-06,
      "loss": 0.7797,
      "step": 1190
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.046404462307691574,
      "learning_rate": 7.440121492746992e-06,
      "loss": 0.7935,
      "step": 1200
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.04626648873090744,
      "learning_rate": 7.391230972038567e-06,
      "loss": 0.8127,
      "step": 1210
    },
    {
      "epoch": 2.7727272727272725,
      "grad_norm": 0.049298033118247986,
      "learning_rate": 7.342042203498952e-06,
      "loss": 0.8366,
      "step": 1220
    },
    {
      "epoch": 2.7954545454545454,
      "grad_norm": 0.047652631998062134,
      "learning_rate": 7.292561322229152e-06,
      "loss": 0.7797,
      "step": 1230
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 0.05071092024445534,
      "learning_rate": 7.2427944997641186e-06,
      "loss": 0.7936,
      "step": 1240
    },
    {
      "epoch": 2.840909090909091,
      "grad_norm": 0.04736604541540146,
      "learning_rate": 7.192747943303008e-06,
      "loss": 0.8147,
      "step": 1250
    },
    {
      "epoch": 2.8636363636363638,
      "grad_norm": 0.044138215482234955,
      "learning_rate": 7.142427894934975e-06,
      "loss": 0.7978,
      "step": 1260
    },
    {
      "epoch": 2.8863636363636362,
      "grad_norm": 0.04737458750605583,
      "learning_rate": 7.0918406308606336e-06,
      "loss": 0.8327,
      "step": 1270
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.05238456651568413,
      "learning_rate": 7.040992460609246e-06,
      "loss": 0.816,
      "step": 1280
    },
    {
      "epoch": 2.9318181818181817,
      "grad_norm": 0.04763491824269295,
      "learning_rate": 6.98988972625177e-06,
      "loss": 0.8347,
      "step": 1290
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 0.045320168137550354,
      "learning_rate": 6.938538801609834e-06,
      "loss": 0.79,
      "step": 1300
    },
    {
      "epoch": 2.9772727272727275,
      "grad_norm": 0.04802026227116585,
      "learning_rate": 6.886946091460762e-06,
      "loss": 0.8046,
      "step": 1310
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.047994792461395264,
      "learning_rate": 6.835118030738731e-06,
      "loss": 0.8179,
      "step": 1320
    },
    {
      "epoch": 3.022727272727273,
      "grad_norm": 0.04660705476999283,
      "learning_rate": 6.78306108373217e-06,
      "loss": 0.7756,
      "step": 1330
    },
    {
      "epoch": 3.0454545454545454,
      "grad_norm": 0.04617464914917946,
      "learning_rate": 6.730781743277498e-06,
      "loss": 0.79,
      "step": 1340
    },
    {
      "epoch": 3.0681818181818183,
      "grad_norm": 0.0491408072412014,
      "learning_rate": 6.678286529949303e-06,
      "loss": 0.819,
      "step": 1350
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 0.046425145119428635,
      "learning_rate": 6.625581991247054e-06,
      "loss": 0.7697,
      "step": 1360
    },
    {
      "epoch": 3.1136363636363638,
      "grad_norm": 0.046251095831394196,
      "learning_rate": 6.5726747007784655e-06,
      "loss": 0.7601,
      "step": 1370
    },
    {
      "epoch": 3.1363636363636362,
      "grad_norm": 0.04971086233854294,
      "learning_rate": 6.5195712574395945e-06,
      "loss": 0.784,
      "step": 1380
    },
    {
      "epoch": 3.159090909090909,
      "grad_norm": 0.05220796912908554,
      "learning_rate": 6.466278284591793e-06,
      "loss": 0.7537,
      "step": 1390
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 0.04714221879839897,
      "learning_rate": 6.4128024292356065e-06,
      "loss": 0.8391,
      "step": 1400
    },
    {
      "epoch": 3.2045454545454546,
      "grad_norm": 0.051231637597084045,
      "learning_rate": 6.3591503611817155e-06,
      "loss": 0.8392,
      "step": 1410
    },
    {
      "epoch": 3.227272727272727,
      "grad_norm": 0.0514928475022316,
      "learning_rate": 6.305328772219044e-06,
      "loss": 0.7629,
      "step": 1420
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.05148511752486229,
      "learning_rate": 6.251344375280124e-06,
      "loss": 0.8342,
      "step": 1430
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 0.050781212747097015,
      "learning_rate": 6.197203903603814e-06,
      "loss": 0.7909,
      "step": 1440
    },
    {
      "epoch": 3.2954545454545454,
      "grad_norm": 0.05220821499824524,
      "learning_rate": 6.142914109895499e-06,
      "loss": 0.8147,
      "step": 1450
    },
    {
      "epoch": 3.3181818181818183,
      "grad_norm": 0.055957481265068054,
      "learning_rate": 6.088481765484849e-06,
      "loss": 0.8109,
      "step": 1460
    },
    {
      "epoch": 3.340909090909091,
      "grad_norm": 0.047921840101480484,
      "learning_rate": 6.033913659481261e-06,
      "loss": 0.7386,
      "step": 1470
    },
    {
      "epoch": 3.3636363636363638,
      "grad_norm": 0.05010027065873146,
      "learning_rate": 5.979216597927088e-06,
      "loss": 0.7778,
      "step": 1480
    },
    {
      "epoch": 3.3863636363636362,
      "grad_norm": 0.05108246952295303,
      "learning_rate": 5.924397402948745e-06,
      "loss": 0.7815,
      "step": 1490
    },
    {
      "epoch": 3.409090909090909,
      "grad_norm": 0.05210183188319206,
      "learning_rate": 5.86946291190582e-06,
      "loss": 0.8016,
      "step": 1500
    },
    {
      "epoch": 3.4318181818181817,
      "grad_norm": 0.052292466163635254,
      "learning_rate": 5.8144199765382736e-06,
      "loss": 0.7615,
      "step": 1510
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 0.05555827170610428,
      "learning_rate": 5.759275462111858e-06,
      "loss": 0.773,
      "step": 1520
    },
    {
      "epoch": 3.4772727272727275,
      "grad_norm": 0.05111211910843849,
      "learning_rate": 5.704036246561836e-06,
      "loss": 0.8308,
      "step": 1530
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.05257695913314819,
      "learning_rate": 5.648709219635134e-06,
      "loss": 0.8092,
      "step": 1540
    },
    {
      "epoch": 3.5227272727272725,
      "grad_norm": 0.056300047785043716,
      "learning_rate": 5.5933012820310095e-06,
      "loss": 0.8009,
      "step": 1550
    },
    {
      "epoch": 3.5454545454545454,
      "grad_norm": 0.05202391743659973,
      "learning_rate": 5.537819344540349e-06,
      "loss": 0.8005,
      "step": 1560
    },
    {
      "epoch": 3.5681818181818183,
      "grad_norm": 0.0530916303396225,
      "learning_rate": 5.482270327183732e-06,
      "loss": 0.8038,
      "step": 1570
    },
    {
      "epoch": 3.590909090909091,
      "grad_norm": 0.05197259411215782,
      "learning_rate": 5.42666115834831e-06,
      "loss": 0.7946,
      "step": 1580
    },
    {
      "epoch": 3.6136363636363638,
      "grad_norm": 0.052419282495975494,
      "learning_rate": 5.37099877392367e-06,
      "loss": 0.8152,
      "step": 1590
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.06443214416503906,
      "learning_rate": 5.315290116436752e-06,
      "loss": 0.8069,
      "step": 1600
    },
    {
      "epoch": 3.659090909090909,
      "grad_norm": 0.05957184359431267,
      "learning_rate": 5.259542134185925e-06,
      "loss": 0.8128,
      "step": 1610
    },
    {
      "epoch": 3.6818181818181817,
      "grad_norm": 0.0548897311091423,
      "learning_rate": 5.203761780374372e-06,
      "loss": 0.7734,
      "step": 1620
    },
    {
      "epoch": 3.7045454545454546,
      "grad_norm": 0.05778632313013077,
      "learning_rate": 5.147956012242837e-06,
      "loss": 0.8028,
      "step": 1630
    },
    {
      "epoch": 3.7272727272727275,
      "grad_norm": 0.057780634611845016,
      "learning_rate": 5.092131790201882e-06,
      "loss": 0.7897,
      "step": 1640
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.05503814294934273,
      "learning_rate": 5.0362960769637415e-06,
      "loss": 0.7838,
      "step": 1650
    },
    {
      "epoch": 3.7727272727272725,
      "grad_norm": 0.05687331035733223,
      "learning_rate": 4.980455836673902e-06,
      "loss": 0.7852,
      "step": 1660
    },
    {
      "epoch": 3.7954545454545454,
      "grad_norm": 0.059677232056856155,
      "learning_rate": 4.924618034042488e-06,
      "loss": 0.8021,
      "step": 1670
    },
    {
      "epoch": 3.8181818181818183,
      "grad_norm": 0.056579746305942535,
      "learning_rate": 4.868789633475583e-06,
      "loss": 0.8155,
      "step": 1680
    },
    {
      "epoch": 3.840909090909091,
      "grad_norm": 0.055581267923116684,
      "learning_rate": 4.812977598206595e-06,
      "loss": 0.8065,
      "step": 1690
    },
    {
      "epoch": 3.8636363636363638,
      "grad_norm": 0.047986991703510284,
      "learning_rate": 4.757188889427761e-06,
      "loss": 0.8285,
      "step": 1700
    },
    {
      "epoch": 3.8863636363636362,
      "grad_norm": 0.059346918016672134,
      "learning_rate": 4.701430465421897e-06,
      "loss": 0.7768,
      "step": 1710
    },
    {
      "epoch": 3.909090909090909,
      "grad_norm": 0.059216298162937164,
      "learning_rate": 4.645709280694545e-06,
      "loss": 0.8109,
      "step": 1720
    },
    {
      "epoch": 3.9318181818181817,
      "grad_norm": 0.05952894687652588,
      "learning_rate": 4.590032285106541e-06,
      "loss": 0.8026,
      "step": 1730
    },
    {
      "epoch": 3.9545454545454546,
      "grad_norm": 0.057186175137758255,
      "learning_rate": 4.534406423007212e-06,
      "loss": 0.8187,
      "step": 1740
    },
    {
      "epoch": 3.9772727272727275,
      "grad_norm": 0.059881679713726044,
      "learning_rate": 4.478838632368221e-06,
      "loss": 0.8422,
      "step": 1750
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.057068806141614914,
      "learning_rate": 4.423335843918233e-06,
      "loss": 0.804,
      "step": 1760
    },
    {
      "epoch": 4.0227272727272725,
      "grad_norm": 0.05267658457159996,
      "learning_rate": 4.367904980278475e-06,
      "loss": 0.7534,
      "step": 1770
    },
    {
      "epoch": 4.045454545454546,
      "grad_norm": 0.06152062863111496,
      "learning_rate": 4.312552955099299e-06,
      "loss": 0.8301,
      "step": 1780
    },
    {
      "epoch": 4.068181818181818,
      "grad_norm": 0.05504327639937401,
      "learning_rate": 4.257286672197888e-06,
      "loss": 0.8144,
      "step": 1790
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 0.05590361729264259,
      "learning_rate": 4.202113024697156e-06,
      "loss": 0.7977,
      "step": 1800
    },
    {
      "epoch": 4.113636363636363,
      "grad_norm": 0.06019588187336922,
      "learning_rate": 4.1470388941660076e-06,
      "loss": 0.8213,
      "step": 1810
    },
    {
      "epoch": 4.136363636363637,
      "grad_norm": 0.05402204021811485,
      "learning_rate": 4.092071149761035e-06,
      "loss": 0.7839,
      "step": 1820
    },
    {
      "epoch": 4.159090909090909,
      "grad_norm": 0.05966588109731674,
      "learning_rate": 4.037216647369745e-06,
      "loss": 0.7739,
      "step": 1830
    },
    {
      "epoch": 4.181818181818182,
      "grad_norm": 0.06286252290010452,
      "learning_rate": 3.982482228755468e-06,
      "loss": 0.8067,
      "step": 1840
    },
    {
      "epoch": 4.204545454545454,
      "grad_norm": 0.05303211137652397,
      "learning_rate": 3.9278747207039995e-06,
      "loss": 0.7935,
      "step": 1850
    },
    {
      "epoch": 4.2272727272727275,
      "grad_norm": 0.06371833384037018,
      "learning_rate": 3.873400934172137e-06,
      "loss": 0.7752,
      "step": 1860
    },
    {
      "epoch": 4.25,
      "grad_norm": 0.06287337839603424,
      "learning_rate": 3.8190676634381775e-06,
      "loss": 0.8394,
      "step": 1870
    },
    {
      "epoch": 4.2727272727272725,
      "grad_norm": 0.059799861162900925,
      "learning_rate": 3.7648816852544873e-06,
      "loss": 0.7587,
      "step": 1880
    },
    {
      "epoch": 4.295454545454546,
      "grad_norm": 0.05993163585662842,
      "learning_rate": 3.710849758002282e-06,
      "loss": 0.7891,
      "step": 1890
    },
    {
      "epoch": 4.318181818181818,
      "grad_norm": 0.05344055965542793,
      "learning_rate": 3.6569786208486692e-06,
      "loss": 0.8,
      "step": 1900
    },
    {
      "epoch": 4.340909090909091,
      "grad_norm": 0.05599065497517586,
      "learning_rate": 3.6032749929061078e-06,
      "loss": 0.8135,
      "step": 1910
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 0.0619407594203949,
      "learning_rate": 3.5497455723943673e-06,
      "loss": 0.785,
      "step": 1920
    },
    {
      "epoch": 4.386363636363637,
      "grad_norm": 0.06416480988264084,
      "learning_rate": 3.4963970358050756e-06,
      "loss": 0.8161,
      "step": 1930
    },
    {
      "epoch": 4.409090909090909,
      "grad_norm": 0.05641242861747742,
      "learning_rate": 3.443236037068999e-06,
      "loss": 0.8188,
      "step": 1940
    },
    {
      "epoch": 4.431818181818182,
      "grad_norm": 0.05751458555459976,
      "learning_rate": 3.3902692067261256e-06,
      "loss": 0.801,
      "step": 1950
    },
    {
      "epoch": 4.454545454545454,
      "grad_norm": 0.05939492955803871,
      "learning_rate": 3.3375031510986606e-06,
      "loss": 0.775,
      "step": 1960
    },
    {
      "epoch": 4.4772727272727275,
      "grad_norm": 0.059105709195137024,
      "learning_rate": 3.2849444514670587e-06,
      "loss": 0.7853,
      "step": 1970
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.06332360953092575,
      "learning_rate": 3.2325996632491597e-06,
      "loss": 0.7645,
      "step": 1980
    },
    {
      "epoch": 4.5227272727272725,
      "grad_norm": 0.05962349474430084,
      "learning_rate": 3.180475315182563e-06,
      "loss": 0.8033,
      "step": 1990
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.05617254227399826,
      "learning_rate": 3.1285779085103313e-06,
      "loss": 0.7815,
      "step": 2000
    },
    {
      "epoch": 4.568181818181818,
      "grad_norm": 0.06171968951821327,
      "learning_rate": 3.07691391617011e-06,
      "loss": 0.7809,
      "step": 2010
    },
    {
      "epoch": 4.590909090909091,
      "grad_norm": 0.060661982744932175,
      "learning_rate": 3.0254897819867974e-06,
      "loss": 0.8506,
      "step": 2020
    },
    {
      "epoch": 4.613636363636363,
      "grad_norm": 0.05857427418231964,
      "learning_rate": 2.974311919868821e-06,
      "loss": 0.7433,
      "step": 2030
    },
    {
      "epoch": 4.636363636363637,
      "grad_norm": 0.06344863772392273,
      "learning_rate": 2.9233867130081677e-06,
      "loss": 0.8371,
      "step": 2040
    },
    {
      "epoch": 4.659090909090909,
      "grad_norm": 0.056676462292671204,
      "learning_rate": 2.87272051308424e-06,
      "loss": 0.8027,
      "step": 2050
    },
    {
      "epoch": 4.681818181818182,
      "grad_norm": 0.06252826750278473,
      "learning_rate": 2.822319639471619e-06,
      "loss": 0.8059,
      "step": 2060
    },
    {
      "epoch": 4.704545454545455,
      "grad_norm": 0.06604735553264618,
      "learning_rate": 2.7721903784519056e-06,
      "loss": 0.7642,
      "step": 2070
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.06098971143364906,
      "learning_rate": 2.7223389824296354e-06,
      "loss": 0.7714,
      "step": 2080
    },
    {
      "epoch": 4.75,
      "grad_norm": 0.05798983573913574,
      "learning_rate": 2.6727716691524474e-06,
      "loss": 0.8064,
      "step": 2090
    },
    {
      "epoch": 4.7727272727272725,
      "grad_norm": 0.05816567689180374,
      "learning_rate": 2.6234946209355906e-06,
      "loss": 0.7697,
      "step": 2100
    },
    {
      "epoch": 4.795454545454545,
      "grad_norm": 0.058813825249671936,
      "learning_rate": 2.574513983890803e-06,
      "loss": 0.8058,
      "step": 2110
    },
    {
      "epoch": 4.818181818181818,
      "grad_norm": 0.07025865465402603,
      "learning_rate": 2.525835867159754e-06,
      "loss": 0.8349,
      "step": 2120
    },
    {
      "epoch": 4.840909090909091,
      "grad_norm": 0.056820739060640335,
      "learning_rate": 2.4774663421520688e-06,
      "loss": 0.768,
      "step": 2130
    },
    {
      "epoch": 4.863636363636363,
      "grad_norm": 0.06224190443754196,
      "learning_rate": 2.429411441788072e-06,
      "loss": 0.7897,
      "step": 2140
    },
    {
      "epoch": 4.886363636363637,
      "grad_norm": 0.05832672491669655,
      "learning_rate": 2.381677159746324e-06,
      "loss": 0.8114,
      "step": 2150
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 0.059900589287281036,
      "learning_rate": 2.334269449716058e-06,
      "loss": 0.7891,
      "step": 2160
    },
    {
      "epoch": 4.931818181818182,
      "grad_norm": 0.0635821595788002,
      "learning_rate": 2.287194224654602e-06,
      "loss": 0.8026,
      "step": 2170
    },
    {
      "epoch": 4.954545454545455,
      "grad_norm": 0.05612201988697052,
      "learning_rate": 2.24045735604988e-06,
      "loss": 0.7916,
      "step": 2180
    },
    {
      "epoch": 4.9772727272727275,
      "grad_norm": 0.05763179436326027,
      "learning_rate": 2.1940646731880887e-06,
      "loss": 0.7679,
      "step": 2190
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.05941809341311455,
      "learning_rate": 2.148021962426635e-06,
      "loss": 0.8058,
      "step": 2200
    },
    {
      "epoch": 5.0227272727272725,
      "grad_norm": 0.07011684030294418,
      "learning_rate": 2.102334966472429e-06,
      "loss": 0.8188,
      "step": 2210
    },
    {
      "epoch": 5.045454545454546,
      "grad_norm": 0.056112293154001236,
      "learning_rate": 2.057009383665621e-06,
      "loss": 0.7685,
      "step": 2220
    },
    {
      "epoch": 5.068181818181818,
      "grad_norm": 0.05940523371100426,
      "learning_rate": 2.012050867268873e-06,
      "loss": 0.7676,
      "step": 2230
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 0.06017325818538666,
      "learning_rate": 1.967465024762251e-06,
      "loss": 0.7589,
      "step": 2240
    },
    {
      "epoch": 5.113636363636363,
      "grad_norm": 0.05958075076341629,
      "learning_rate": 1.9232574171438273e-06,
      "loss": 0.8143,
      "step": 2250
    },
    {
      "epoch": 5.136363636363637,
      "grad_norm": 0.059776924550533295,
      "learning_rate": 1.8794335582360873e-06,
      "loss": 0.8186,
      "step": 2260
    },
    {
      "epoch": 5.159090909090909,
      "grad_norm": 0.061050403863191605,
      "learning_rate": 1.8359989139982021e-06,
      "loss": 0.7815,
      "step": 2270
    },
    {
      "epoch": 5.181818181818182,
      "grad_norm": 0.05887814611196518,
      "learning_rate": 1.7929589018443016e-06,
      "loss": 0.8223,
      "step": 2280
    },
    {
      "epoch": 5.204545454545454,
      "grad_norm": 0.0575253888964653,
      "learning_rate": 1.7503188899677642e-06,
      "loss": 0.8012,
      "step": 2290
    },
    {
      "epoch": 5.2272727272727275,
      "grad_norm": 0.06290145218372345,
      "learning_rate": 1.7080841966716777e-06,
      "loss": 0.7403,
      "step": 2300
    },
    {
      "epoch": 5.25,
      "grad_norm": 0.06359874457120895,
      "learning_rate": 1.6662600897055132e-06,
      "loss": 0.8377,
      "step": 2310
    },
    {
      "epoch": 5.2727272727272725,
      "grad_norm": 0.06408390402793884,
      "learning_rate": 1.6248517856080848e-06,
      "loss": 0.7776,
      "step": 2320
    },
    {
      "epoch": 5.295454545454546,
      "grad_norm": 0.0607023611664772,
      "learning_rate": 1.5838644490569372e-06,
      "loss": 0.8408,
      "step": 2330
    },
    {
      "epoch": 5.318181818181818,
      "grad_norm": 0.06409065425395966,
      "learning_rate": 1.5433031922241538e-06,
      "loss": 0.8198,
      "step": 2340
    },
    {
      "epoch": 5.340909090909091,
      "grad_norm": 0.06282657384872437,
      "learning_rate": 1.5031730741387567e-06,
      "loss": 0.7881,
      "step": 2350
    },
    {
      "epoch": 5.363636363636363,
      "grad_norm": 0.06287471950054169,
      "learning_rate": 1.4634791000557058e-06,
      "loss": 0.7462,
      "step": 2360
    },
    {
      "epoch": 5.386363636363637,
      "grad_norm": 0.06724315136671066,
      "learning_rate": 1.4242262208316187e-06,
      "loss": 0.8024,
      "step": 2370
    },
    {
      "epoch": 5.409090909090909,
      "grad_norm": 0.061781395226716995,
      "learning_rate": 1.3854193323072707e-06,
      "loss": 0.7826,
      "step": 2380
    },
    {
      "epoch": 5.431818181818182,
      "grad_norm": 0.06064334139227867,
      "learning_rate": 1.3470632746969586e-06,
      "loss": 0.7883,
      "step": 2390
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.05812542885541916,
      "learning_rate": 1.3091628319848016e-06,
      "loss": 0.7925,
      "step": 2400
    },
    {
      "epoch": 5.4772727272727275,
      "grad_norm": 0.059440333396196365,
      "learning_rate": 1.271722731328055e-06,
      "loss": 0.7692,
      "step": 2410
    },
    {
      "epoch": 5.5,
      "grad_norm": 0.06575117260217667,
      "learning_rate": 1.2347476424675142e-06,
      "loss": 0.7772,
      "step": 2420
    },
    {
      "epoch": 5.5227272727272725,
      "grad_norm": 0.06302516162395477,
      "learning_rate": 1.1982421771450775e-06,
      "loss": 0.7927,
      "step": 2430
    },
    {
      "epoch": 5.545454545454545,
      "grad_norm": 0.06540846079587936,
      "learning_rate": 1.1622108885285415e-06,
      "loss": 0.7724,
      "step": 2440
    },
    {
      "epoch": 5.568181818181818,
      "grad_norm": 0.06591441482305527,
      "learning_rate": 1.126658270643708e-06,
      "loss": 0.779,
      "step": 2450
    },
    {
      "epoch": 5.590909090909091,
      "grad_norm": 0.06068432703614235,
      "learning_rate": 1.0915887578138606e-06,
      "loss": 0.7768,
      "step": 2460
    },
    {
      "epoch": 5.613636363636363,
      "grad_norm": 0.0614112988114357,
      "learning_rate": 1.057006724106695e-06,
      "loss": 0.8061,
      "step": 2470
    },
    {
      "epoch": 5.636363636363637,
      "grad_norm": 0.06147473677992821,
      "learning_rate": 1.0229164827887512e-06,
      "loss": 0.805,
      "step": 2480
    },
    {
      "epoch": 5.659090909090909,
      "grad_norm": 0.06091708317399025,
      "learning_rate": 9.89322285787454e-07,
      "loss": 0.7883,
      "step": 2490
    },
    {
      "epoch": 5.681818181818182,
      "grad_norm": 0.05688236653804779,
      "learning_rate": 9.5622832316077e-07,
      "loss": 0.7763,
      "step": 2500
    },
    {
      "epoch": 5.704545454545455,
      "grad_norm": 0.06602354347705841,
      "learning_rate": 9.236387225746185e-07,
      "loss": 0.809,
      "step": 2510
    },
    {
      "epoch": 5.7272727272727275,
      "grad_norm": 0.06536935269832611,
      "learning_rate": 8.915575487880324e-07,
      "loss": 0.779,
      "step": 2520
    },
    {
      "epoch": 5.75,
      "grad_norm": 0.06449291855096817,
      "learning_rate": 8.599888031461801e-07,
      "loss": 0.7984,
      "step": 2530
    },
    {
      "epoch": 5.7727272727272725,
      "grad_norm": 0.06858620792627335,
      "learning_rate": 8.289364230813052e-07,
      "loss": 0.8298,
      "step": 2540
    },
    {
      "epoch": 5.795454545454545,
      "grad_norm": 0.05864429101347923,
      "learning_rate": 7.984042816216109e-07,
      "loss": 0.7846,
      "step": 2550
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 0.059347003698349,
      "learning_rate": 7.683961869082146e-07,
      "loss": 0.8246,
      "step": 2560
    },
    {
      "epoch": 5.840909090909091,
      "grad_norm": 0.06505056470632553,
      "learning_rate": 7.389158817201541e-07,
      "loss": 0.811,
      "step": 2570
    },
    {
      "epoch": 5.863636363636363,
      "grad_norm": 0.06296805292367935,
      "learning_rate": 7.099670430075828e-07,
      "loss": 0.8004,
      "step": 2580
    },
    {
      "epoch": 5.886363636363637,
      "grad_norm": 0.06585711985826492,
      "learning_rate": 6.815532814331505e-07,
      "loss": 0.7814,
      "step": 2590
    },
    {
      "epoch": 5.909090909090909,
      "grad_norm": 0.06298382580280304,
      "learning_rate": 6.536781409216664e-07,
      "loss": 0.8115,
      "step": 2600
    },
    {
      "epoch": 5.931818181818182,
      "grad_norm": 0.06103487312793732,
      "learning_rate": 6.263450982180813e-07,
      "loss": 0.8036,
      "step": 2610
    },
    {
      "epoch": 5.954545454545455,
      "grad_norm": 0.06315191090106964,
      "learning_rate": 5.995575624538397e-07,
      "loss": 0.7637,
      "step": 2620
    },
    {
      "epoch": 5.9772727272727275,
      "grad_norm": 0.06248250976204872,
      "learning_rate": 5.733188747216845e-07,
      "loss": 0.7912,
      "step": 2630
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.06412005424499512,
      "learning_rate": 5.476323076589319e-07,
      "loss": 0.815,
      "step": 2640
    },
    {
      "epoch": 6.0227272727272725,
      "grad_norm": 0.060897987335920334,
      "learning_rate": 5.225010650392887e-07,
      "loss": 0.8012,
      "step": 2650
    },
    {
      "epoch": 6.045454545454546,
      "grad_norm": 0.06144240126013756,
      "learning_rate": 4.979282813732622e-07,
      "loss": 0.798,
      "step": 2660
    },
    {
      "epoch": 6.068181818181818,
      "grad_norm": 0.05944688990712166,
      "learning_rate": 4.739170215172051e-07,
      "loss": 0.7948,
      "step": 2670
    },
    {
      "epoch": 6.090909090909091,
      "grad_norm": 0.06139964610338211,
      "learning_rate": 4.5047028029104877e-07,
      "loss": 0.8287,
      "step": 2680
    },
    {
      "epoch": 6.113636363636363,
      "grad_norm": 0.06420081108808517,
      "learning_rate": 4.27590982104773e-07,
      "loss": 0.7973,
      "step": 2690
    },
    {
      "epoch": 6.136363636363637,
      "grad_norm": 0.06291543692350388,
      "learning_rate": 4.0528198059365863e-07,
      "loss": 0.7956,
      "step": 2700
    },
    {
      "epoch": 6.159090909090909,
      "grad_norm": 0.05762983486056328,
      "learning_rate": 3.8354605826235957e-07,
      "loss": 0.8054,
      "step": 2710
    },
    {
      "epoch": 6.181818181818182,
      "grad_norm": 0.05916955694556236,
      "learning_rate": 3.623859261378654e-07,
      "loss": 0.7634,
      "step": 2720
    },
    {
      "epoch": 6.204545454545454,
      "grad_norm": 0.064091257750988,
      "learning_rate": 3.4180422343135346e-07,
      "loss": 0.8345,
      "step": 2730
    },
    {
      "epoch": 6.2272727272727275,
      "grad_norm": 0.061927612870931625,
      "learning_rate": 3.2180351720902003e-07,
      "loss": 0.8129,
      "step": 2740
    },
    {
      "epoch": 6.25,
      "grad_norm": 0.06499668955802917,
      "learning_rate": 3.0238630207189867e-07,
      "loss": 0.8057,
      "step": 2750
    },
    {
      "epoch": 6.2727272727272725,
      "grad_norm": 0.06719426810741425,
      "learning_rate": 2.8355499984471737e-07,
      "loss": 0.7677,
      "step": 2760
    },
    {
      "epoch": 6.295454545454546,
      "grad_norm": 0.07048514485359192,
      "learning_rate": 2.6531195927384067e-07,
      "loss": 0.8099,
      "step": 2770
    },
    {
      "epoch": 6.318181818181818,
      "grad_norm": 0.06214950233697891,
      "learning_rate": 2.476594557343126e-07,
      "loss": 0.7769,
      "step": 2780
    },
    {
      "epoch": 6.340909090909091,
      "grad_norm": 0.06586616486310959,
      "learning_rate": 2.305996909460695e-07,
      "loss": 0.8022,
      "step": 2790
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 0.06200889125466347,
      "learning_rate": 2.141347926993176e-07,
      "loss": 0.771,
      "step": 2800
    },
    {
      "epoch": 6.386363636363637,
      "grad_norm": 0.058896422386169434,
      "learning_rate": 1.9826681458915088e-07,
      "loss": 0.7611,
      "step": 2810
    },
    {
      "epoch": 6.409090909090909,
      "grad_norm": 0.06591584533452988,
      "learning_rate": 1.8299773575941483e-07,
      "loss": 0.8151,
      "step": 2820
    },
    {
      "epoch": 6.431818181818182,
      "grad_norm": 0.05796649307012558,
      "learning_rate": 1.6832946065585e-07,
      "loss": 0.8017,
      "step": 2830
    },
    {
      "epoch": 6.454545454545454,
      "grad_norm": 0.059807244688272476,
      "learning_rate": 1.542638187885681e-07,
      "loss": 0.812,
      "step": 2840
    },
    {
      "epoch": 6.4772727272727275,
      "grad_norm": 0.06900903582572937,
      "learning_rate": 1.4080256450385578e-07,
      "loss": 0.8105,
      "step": 2850
    },
    {
      "epoch": 6.5,
      "grad_norm": 0.06508809328079224,
      "learning_rate": 1.2794737676536993e-07,
      "loss": 0.7147,
      "step": 2860
    },
    {
      "epoch": 6.5227272727272725,
      "grad_norm": 0.06716930121183395,
      "learning_rate": 1.1569985894472446e-07,
      "loss": 0.7677,
      "step": 2870
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 0.06471340358257294,
      "learning_rate": 1.0406153862150881e-07,
      "loss": 0.82,
      "step": 2880
    },
    {
      "epoch": 6.568181818181818,
      "grad_norm": 0.05981110781431198,
      "learning_rate": 9.30338673927611e-08,
      "loss": 0.7904,
      "step": 2890
    },
    {
      "epoch": 6.590909090909091,
      "grad_norm": 0.06340961158275604,
      "learning_rate": 8.261822069191461e-08,
      "loss": 0.8186,
      "step": 2900
    },
    {
      "epoch": 6.613636363636363,
      "grad_norm": 0.06290656328201294,
      "learning_rate": 7.281589761724828e-08,
      "loss": 0.7665,
      "step": 2910
    },
    {
      "epoch": 6.636363636363637,
      "grad_norm": 0.07086827605962753,
      "learning_rate": 6.362812076985359e-08,
      "loss": 0.7613,
      "step": 2920
    },
    {
      "epoch": 6.659090909090909,
      "grad_norm": 0.06620458513498306,
      "learning_rate": 5.505603610114651e-08,
      "loss": 0.7762,
      "step": 2930
    },
    {
      "epoch": 6.681818181818182,
      "grad_norm": 0.06518013775348663,
      "learning_rate": 4.7100712769937994e-08,
      "loss": 0.7707,
      "step": 2940
    },
    {
      "epoch": 6.704545454545455,
      "grad_norm": 0.06568311899900436,
      "learning_rate": 3.976314300908002e-08,
      "loss": 0.8052,
      "step": 2950
    },
    {
      "epoch": 6.7272727272727275,
      "grad_norm": 0.06033078953623772,
      "learning_rate": 3.3044242001712415e-08,
      "loss": 0.7725,
      "step": 2960
    },
    {
      "epoch": 6.75,
      "grad_norm": 0.060128528624773026,
      "learning_rate": 2.6944847767114146e-08,
      "loss": 0.7712,
      "step": 2970
    },
    {
      "epoch": 6.7727272727272725,
      "grad_norm": 0.06406668573617935,
      "learning_rate": 2.1465721056179168e-08,
      "loss": 0.8116,
      "step": 2980
    },
    {
      "epoch": 6.795454545454545,
      "grad_norm": 0.05837489292025566,
      "learning_rate": 1.6607545256533407e-08,
      "loss": 0.8084,
      "step": 2990
    },
    {
      "epoch": 6.818181818181818,
      "grad_norm": 0.06511975079774857,
      "learning_rate": 1.2370926307300746e-08,
      "loss": 0.8018,
      "step": 3000
    },
    {
      "epoch": 6.840909090909091,
      "grad_norm": 0.0646391287446022,
      "learning_rate": 8.756392623521237e-09,
      "loss": 0.7921,
      "step": 3010
    },
    {
      "epoch": 6.863636363636363,
      "grad_norm": 0.06122921034693718,
      "learning_rate": 5.7643950302488375e-09,
      "loss": 0.7981,
      "step": 3020
    },
    {
      "epoch": 6.886363636363637,
      "grad_norm": 0.06278009712696075,
      "learning_rate": 3.3953067063213772e-09,
      "loss": 0.7755,
      "step": 3030
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 0.06424996256828308,
      "learning_rate": 1.649423137813355e-09,
      "loss": 0.7825,
      "step": 3040
    },
    {
      "epoch": 6.931818181818182,
      "grad_norm": 0.07108237594366074,
      "learning_rate": 5.26962081183191e-10,
      "loss": 0.8121,
      "step": 3050
    },
    {
      "epoch": 6.954545454545455,
      "grad_norm": 0.06434624642133713,
      "learning_rate": 2.806353611273238e-11,
      "loss": 0.8185,
      "step": 3060
    }
  ],
  "logging_steps": 10,
  "max_steps": 3063,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 5.098946440672051e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}