{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 50,
  "global_step": 794,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025220680958385876,
      "grad_norm": 83.50857543945312,
      "learning_rate": 0.0,
      "loss": 3.3887,
      "step": 1
    },
    {
      "epoch": 0.005044136191677175,
      "grad_norm": 71.31573486328125,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.4305,
      "step": 2
    },
    {
      "epoch": 0.007566204287515763,
      "grad_norm": 66.55958557128906,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.0425,
      "step": 3
    },
    {
      "epoch": 0.01008827238335435,
      "grad_norm": 67.16094207763672,
      "learning_rate": 6e-06,
      "loss": 3.1193,
      "step": 4
    },
    {
      "epoch": 0.012610340479192938,
      "grad_norm": 58.159088134765625,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.7595,
      "step": 5
    },
    {
      "epoch": 0.015132408575031526,
      "grad_norm": 39.46601867675781,
      "learning_rate": 1e-05,
      "loss": 2.3184,
      "step": 6
    },
    {
      "epoch": 0.017654476670870115,
      "grad_norm": 45.5927734375,
      "learning_rate": 9.987325728770595e-06,
      "loss": 2.1763,
      "step": 7
    },
    {
      "epoch": 0.0201765447667087,
      "grad_norm": 20.798906326293945,
      "learning_rate": 9.974651457541193e-06,
      "loss": 2.1835,
      "step": 8
    },
    {
      "epoch": 0.02269861286254729,
      "grad_norm": 15.517325401306152,
      "learning_rate": 9.961977186311787e-06,
      "loss": 2.1354,
      "step": 9
    },
    {
      "epoch": 0.025220680958385876,
      "grad_norm": 15.667418479919434,
      "learning_rate": 9.949302915082384e-06,
      "loss": 1.9287,
      "step": 10
    },
    {
      "epoch": 0.027742749054224466,
      "grad_norm": 13.178864479064941,
      "learning_rate": 9.93662864385298e-06,
      "loss": 1.9898,
      "step": 11
    },
    {
      "epoch": 0.03026481715006305,
      "grad_norm": 10.053223609924316,
      "learning_rate": 9.923954372623576e-06,
      "loss": 2.0013,
      "step": 12
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 14.007344245910645,
      "learning_rate": 9.91128010139417e-06,
      "loss": 2.0559,
      "step": 13
    },
    {
      "epoch": 0.03530895334174023,
      "grad_norm": 11.14796257019043,
      "learning_rate": 9.898605830164766e-06,
      "loss": 2.0379,
      "step": 14
    },
    {
      "epoch": 0.03783102143757881,
      "grad_norm": 13.28112506866455,
      "learning_rate": 9.885931558935362e-06,
      "loss": 1.9854,
      "step": 15
    },
    {
      "epoch": 0.0403530895334174,
      "grad_norm": 11.45155143737793,
      "learning_rate": 9.873257287705957e-06,
      "loss": 2.1884,
      "step": 16
    },
    {
      "epoch": 0.04287515762925599,
      "grad_norm": 10.636513710021973,
      "learning_rate": 9.860583016476553e-06,
      "loss": 1.9676,
      "step": 17
    },
    {
      "epoch": 0.04539722572509458,
      "grad_norm": 10.700081825256348,
      "learning_rate": 9.847908745247149e-06,
      "loss": 1.9426,
      "step": 18
    },
    {
      "epoch": 0.04791929382093316,
      "grad_norm": 10.350312232971191,
      "learning_rate": 9.835234474017745e-06,
      "loss": 1.931,
      "step": 19
    },
    {
      "epoch": 0.05044136191677175,
      "grad_norm": 11.60483455657959,
      "learning_rate": 9.822560202788341e-06,
      "loss": 1.9397,
      "step": 20
    },
    {
      "epoch": 0.05296343001261034,
      "grad_norm": 10.923288345336914,
      "learning_rate": 9.809885931558936e-06,
      "loss": 1.8861,
      "step": 21
    },
    {
      "epoch": 0.05548549810844893,
      "grad_norm": 10.222322463989258,
      "learning_rate": 9.797211660329532e-06,
      "loss": 1.8154,
      "step": 22
    },
    {
      "epoch": 0.058007566204287514,
      "grad_norm": 9.665061950683594,
      "learning_rate": 9.784537389100128e-06,
      "loss": 1.9885,
      "step": 23
    },
    {
      "epoch": 0.0605296343001261,
      "grad_norm": 10.544888496398926,
      "learning_rate": 9.771863117870724e-06,
      "loss": 1.9728,
      "step": 24
    },
    {
      "epoch": 0.06305170239596469,
      "grad_norm": 9.924367904663086,
      "learning_rate": 9.759188846641318e-06,
      "loss": 1.9665,
      "step": 25
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 9.470415115356445,
      "learning_rate": 9.746514575411914e-06,
      "loss": 1.8872,
      "step": 26
    },
    {
      "epoch": 0.06809583858764187,
      "grad_norm": 9.330588340759277,
      "learning_rate": 9.73384030418251e-06,
      "loss": 1.9458,
      "step": 27
    },
    {
      "epoch": 0.07061790668348046,
      "grad_norm": 9.101158142089844,
      "learning_rate": 9.721166032953105e-06,
      "loss": 2.0452,
      "step": 28
    },
    {
      "epoch": 0.07313997477931904,
      "grad_norm": 9.63065242767334,
      "learning_rate": 9.708491761723701e-06,
      "loss": 1.9648,
      "step": 29
    },
    {
      "epoch": 0.07566204287515763,
      "grad_norm": 9.038743019104004,
      "learning_rate": 9.695817490494297e-06,
      "loss": 1.9469,
      "step": 30
    },
    {
      "epoch": 0.07818411097099622,
      "grad_norm": 9.375469207763672,
      "learning_rate": 9.683143219264893e-06,
      "loss": 2.0387,
      "step": 31
    },
    {
      "epoch": 0.0807061790668348,
      "grad_norm": 9.170827865600586,
      "learning_rate": 9.670468948035488e-06,
      "loss": 2.0396,
      "step": 32
    },
    {
      "epoch": 0.0832282471626734,
      "grad_norm": 9.155048370361328,
      "learning_rate": 9.657794676806086e-06,
      "loss": 2.1346,
      "step": 33
    },
    {
      "epoch": 0.08575031525851198,
      "grad_norm": 9.660133361816406,
      "learning_rate": 9.64512040557668e-06,
      "loss": 1.814,
      "step": 34
    },
    {
      "epoch": 0.08827238335435057,
      "grad_norm": 9.577939987182617,
      "learning_rate": 9.632446134347276e-06,
      "loss": 1.9353,
      "step": 35
    },
    {
      "epoch": 0.09079445145018916,
      "grad_norm": 9.347375869750977,
      "learning_rate": 9.619771863117872e-06,
      "loss": 1.8748,
      "step": 36
    },
    {
      "epoch": 0.09331651954602774,
      "grad_norm": 9.635443687438965,
      "learning_rate": 9.607097591888467e-06,
      "loss": 2.0299,
      "step": 37
    },
    {
      "epoch": 0.09583858764186633,
      "grad_norm": 9.470548629760742,
      "learning_rate": 9.594423320659063e-06,
      "loss": 1.966,
      "step": 38
    },
    {
      "epoch": 0.09836065573770492,
      "grad_norm": 9.292247772216797,
      "learning_rate": 9.581749049429659e-06,
      "loss": 1.8779,
      "step": 39
    },
    {
      "epoch": 0.1008827238335435,
      "grad_norm": 9.822443962097168,
      "learning_rate": 9.569074778200255e-06,
      "loss": 1.8484,
      "step": 40
    },
    {
      "epoch": 0.1034047919293821,
      "grad_norm": 8.519198417663574,
      "learning_rate": 9.55640050697085e-06,
      "loss": 1.7622,
      "step": 41
    },
    {
      "epoch": 0.10592686002522068,
      "grad_norm": 9.220460891723633,
      "learning_rate": 9.543726235741445e-06,
      "loss": 1.8659,
      "step": 42
    },
    {
      "epoch": 0.10844892812105927,
      "grad_norm": 8.564704895019531,
      "learning_rate": 9.531051964512042e-06,
      "loss": 1.8478,
      "step": 43
    },
    {
      "epoch": 0.11097099621689786,
      "grad_norm": 9.696242332458496,
      "learning_rate": 9.518377693282636e-06,
      "loss": 1.8625,
      "step": 44
    },
    {
      "epoch": 0.11349306431273644,
      "grad_norm": 9.121529579162598,
      "learning_rate": 9.505703422053234e-06,
      "loss": 1.9736,
      "step": 45
    },
    {
      "epoch": 0.11601513240857503,
      "grad_norm": 9.0239896774292,
      "learning_rate": 9.493029150823828e-06,
      "loss": 1.8687,
      "step": 46
    },
    {
      "epoch": 0.11853720050441362,
      "grad_norm": 8.566268920898438,
      "learning_rate": 9.480354879594424e-06,
      "loss": 1.7855,
      "step": 47
    },
    {
      "epoch": 0.1210592686002522,
      "grad_norm": 9.728326797485352,
      "learning_rate": 9.46768060836502e-06,
      "loss": 2.0394,
      "step": 48
    },
    {
      "epoch": 0.1235813366960908,
      "grad_norm": 8.644201278686523,
      "learning_rate": 9.455006337135616e-06,
      "loss": 1.8265,
      "step": 49
    },
    {
      "epoch": 0.12610340479192939,
      "grad_norm": 9.00877857208252,
      "learning_rate": 9.442332065906211e-06,
      "loss": 1.9655,
      "step": 50
    },
    {
      "epoch": 0.12610340479192939,
      "eval_loss": 1.8593257665634155,
      "eval_runtime": 19.3972,
      "eval_samples_per_second": 36.345,
      "eval_steps_per_second": 18.198,
      "step": 50
    },
    {
      "epoch": 0.12862547288776796,
      "grad_norm": 8.626359939575195,
      "learning_rate": 9.429657794676807e-06,
      "loss": 1.8767,
      "step": 51
    },
    {
      "epoch": 0.13114754098360656,
      "grad_norm": 8.989786148071289,
      "learning_rate": 9.416983523447403e-06,
      "loss": 1.9197,
      "step": 52
    },
    {
      "epoch": 0.13366960907944514,
      "grad_norm": 8.265259742736816,
      "learning_rate": 9.404309252217997e-06,
      "loss": 1.7882,
      "step": 53
    },
    {
      "epoch": 0.13619167717528374,
      "grad_norm": 9.578763008117676,
      "learning_rate": 9.391634980988594e-06,
      "loss": 2.0616,
      "step": 54
    },
    {
      "epoch": 0.13871374527112232,
      "grad_norm": 9.27950382232666,
      "learning_rate": 9.37896070975919e-06,
      "loss": 1.9043,
      "step": 55
    },
    {
      "epoch": 0.14123581336696092,
      "grad_norm": 8.789308547973633,
      "learning_rate": 9.366286438529786e-06,
      "loss": 1.8745,
      "step": 56
    },
    {
      "epoch": 0.1437578814627995,
      "grad_norm": 8.460257530212402,
      "learning_rate": 9.35361216730038e-06,
      "loss": 1.9719,
      "step": 57
    },
    {
      "epoch": 0.14627994955863807,
      "grad_norm": 8.686505317687988,
      "learning_rate": 9.340937896070976e-06,
      "loss": 1.8288,
      "step": 58
    },
    {
      "epoch": 0.14880201765447668,
      "grad_norm": 9.074113845825195,
      "learning_rate": 9.328263624841572e-06,
      "loss": 1.8212,
      "step": 59
    },
    {
      "epoch": 0.15132408575031525,
      "grad_norm": 8.919495582580566,
      "learning_rate": 9.315589353612169e-06,
      "loss": 1.9267,
      "step": 60
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 9.349574089050293,
      "learning_rate": 9.302915082382765e-06,
      "loss": 1.8566,
      "step": 61
    },
    {
      "epoch": 0.15636822194199243,
      "grad_norm": 10.293651580810547,
      "learning_rate": 9.290240811153359e-06,
      "loss": 1.7412,
      "step": 62
    },
    {
      "epoch": 0.15889029003783103,
      "grad_norm": 9.373260498046875,
      "learning_rate": 9.277566539923955e-06,
      "loss": 1.9118,
      "step": 63
    },
    {
      "epoch": 0.1614123581336696,
      "grad_norm": 9.066275596618652,
      "learning_rate": 9.264892268694551e-06,
      "loss": 1.89,
      "step": 64
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 9.459461212158203,
      "learning_rate": 9.252217997465146e-06,
      "loss": 1.8408,
      "step": 65
    },
    {
      "epoch": 0.1664564943253468,
      "grad_norm": 9.49438190460205,
      "learning_rate": 9.239543726235742e-06,
      "loss": 1.9826,
      "step": 66
    },
    {
      "epoch": 0.16897856242118536,
      "grad_norm": 9.088374137878418,
      "learning_rate": 9.226869455006338e-06,
      "loss": 1.8442,
      "step": 67
    },
    {
      "epoch": 0.17150063051702397,
      "grad_norm": 8.981496810913086,
      "learning_rate": 9.214195183776934e-06,
      "loss": 1.8115,
      "step": 68
    },
    {
      "epoch": 0.17402269861286254,
      "grad_norm": 9.342341423034668,
      "learning_rate": 9.201520912547528e-06,
      "loss": 1.849,
      "step": 69
    },
    {
      "epoch": 0.17654476670870115,
      "grad_norm": 9.18710708618164,
      "learning_rate": 9.188846641318126e-06,
      "loss": 1.7475,
      "step": 70
    },
    {
      "epoch": 0.17906683480453972,
      "grad_norm": 9.204767227172852,
      "learning_rate": 9.17617237008872e-06,
      "loss": 1.8912,
      "step": 71
    },
    {
      "epoch": 0.18158890290037832,
      "grad_norm": 9.105266571044922,
      "learning_rate": 9.163498098859315e-06,
      "loss": 1.8394,
      "step": 72
    },
    {
      "epoch": 0.1841109709962169,
      "grad_norm": 9.192793846130371,
      "learning_rate": 9.150823827629913e-06,
      "loss": 1.9242,
      "step": 73
    },
    {
      "epoch": 0.18663303909205547,
      "grad_norm": 8.911624908447266,
      "learning_rate": 9.138149556400507e-06,
      "loss": 1.9121,
      "step": 74
    },
    {
      "epoch": 0.18915510718789408,
      "grad_norm": 9.20001220703125,
      "learning_rate": 9.125475285171103e-06,
      "loss": 1.9752,
      "step": 75
    },
    {
      "epoch": 0.19167717528373265,
      "grad_norm": 8.967398643493652,
      "learning_rate": 9.1128010139417e-06,
      "loss": 1.7422,
      "step": 76
    },
    {
      "epoch": 0.19419924337957126,
      "grad_norm": 8.867136001586914,
      "learning_rate": 9.100126742712296e-06,
      "loss": 1.7391,
      "step": 77
    },
    {
      "epoch": 0.19672131147540983,
      "grad_norm": 9.721291542053223,
      "learning_rate": 9.08745247148289e-06,
      "loss": 1.7955,
      "step": 78
    },
    {
      "epoch": 0.19924337957124844,
      "grad_norm": 8.936488151550293,
      "learning_rate": 9.074778200253486e-06,
      "loss": 1.602,
      "step": 79
    },
    {
      "epoch": 0.201765447667087,
      "grad_norm": 8.965775489807129,
      "learning_rate": 9.062103929024082e-06,
      "loss": 1.9918,
      "step": 80
    },
    {
      "epoch": 0.2042875157629256,
      "grad_norm": 9.03048324584961,
      "learning_rate": 9.049429657794677e-06,
      "loss": 1.8228,
      "step": 81
    },
    {
      "epoch": 0.2068095838587642,
      "grad_norm": 9.195337295532227,
      "learning_rate": 9.036755386565273e-06,
      "loss": 1.9259,
      "step": 82
    },
    {
      "epoch": 0.20933165195460277,
      "grad_norm": 9.696627616882324,
      "learning_rate": 9.024081115335869e-06,
      "loss": 1.8497,
      "step": 83
    },
    {
      "epoch": 0.21185372005044137,
      "grad_norm": 9.298614501953125,
      "learning_rate": 9.011406844106465e-06,
      "loss": 1.8685,
      "step": 84
    },
    {
      "epoch": 0.21437578814627994,
      "grad_norm": 8.810253143310547,
      "learning_rate": 8.998732572877061e-06,
      "loss": 1.7147,
      "step": 85
    },
    {
      "epoch": 0.21689785624211855,
      "grad_norm": 8.825125694274902,
      "learning_rate": 8.986058301647655e-06,
      "loss": 1.8466,
      "step": 86
    },
    {
      "epoch": 0.21941992433795712,
      "grad_norm": 8.869908332824707,
      "learning_rate": 8.973384030418252e-06,
      "loss": 1.9044,
      "step": 87
    },
    {
      "epoch": 0.22194199243379573,
      "grad_norm": 9.151841163635254,
      "learning_rate": 8.960709759188848e-06,
      "loss": 1.8922,
      "step": 88
    },
    {
      "epoch": 0.2244640605296343,
      "grad_norm": 9.193544387817383,
      "learning_rate": 8.948035487959444e-06,
      "loss": 1.8199,
      "step": 89
    },
    {
      "epoch": 0.22698612862547288,
      "grad_norm": 8.479183197021484,
      "learning_rate": 8.935361216730038e-06,
      "loss": 1.847,
      "step": 90
    },
    {
      "epoch": 0.22950819672131148,
      "grad_norm": 9.11871337890625,
      "learning_rate": 8.922686945500634e-06,
      "loss": 1.8631,
      "step": 91
    },
    {
      "epoch": 0.23203026481715006,
      "grad_norm": 9.080836296081543,
      "learning_rate": 8.91001267427123e-06,
      "loss": 1.9849,
      "step": 92
    },
    {
      "epoch": 0.23455233291298866,
      "grad_norm": 10.182774543762207,
      "learning_rate": 8.897338403041825e-06,
      "loss": 1.933,
      "step": 93
    },
    {
      "epoch": 0.23707440100882723,
      "grad_norm": 9.077899932861328,
      "learning_rate": 8.884664131812421e-06,
      "loss": 1.7692,
      "step": 94
    },
    {
      "epoch": 0.23959646910466584,
      "grad_norm": 8.86284065246582,
      "learning_rate": 8.871989860583017e-06,
      "loss": 1.7995,
      "step": 95
    },
    {
      "epoch": 0.2421185372005044,
      "grad_norm": 9.612898826599121,
      "learning_rate": 8.859315589353613e-06,
      "loss": 2.045,
      "step": 96
    },
    {
      "epoch": 0.244640605296343,
      "grad_norm": 9.372990608215332,
      "learning_rate": 8.846641318124208e-06,
      "loss": 1.8652,
      "step": 97
    },
    {
      "epoch": 0.2471626733921816,
      "grad_norm": 9.045456886291504,
      "learning_rate": 8.833967046894805e-06,
      "loss": 1.8405,
      "step": 98
    },
    {
      "epoch": 0.24968474148802017,
      "grad_norm": 8.836333274841309,
      "learning_rate": 8.8212927756654e-06,
      "loss": 1.7977,
      "step": 99
    },
    {
      "epoch": 0.25220680958385877,
      "grad_norm": 8.542088508605957,
      "learning_rate": 8.808618504435996e-06,
      "loss": 1.7449,
      "step": 100
    },
    {
      "epoch": 0.25220680958385877,
      "eval_loss": 1.821334719657898,
      "eval_runtime": 19.3187,
      "eval_samples_per_second": 36.493,
      "eval_steps_per_second": 18.272,
      "step": 100
    },
    {
      "epoch": 0.2547288776796974,
      "grad_norm": 9.596298217773438,
      "learning_rate": 8.795944233206592e-06,
      "loss": 1.8074,
      "step": 101
    },
    {
      "epoch": 0.2572509457755359,
      "grad_norm": 8.635272026062012,
      "learning_rate": 8.783269961977186e-06,
      "loss": 2.0499,
      "step": 102
    },
    {
      "epoch": 0.2597730138713745,
      "grad_norm": 8.884391784667969,
      "learning_rate": 8.770595690747782e-06,
      "loss": 1.8544,
      "step": 103
    },
    {
      "epoch": 0.26229508196721313,
      "grad_norm": 8.27906322479248,
      "learning_rate": 8.757921419518379e-06,
      "loss": 1.6638,
      "step": 104
    },
    {
      "epoch": 0.2648171500630517,
      "grad_norm": 8.792101860046387,
      "learning_rate": 8.745247148288975e-06,
      "loss": 1.8727,
      "step": 105
    },
    {
      "epoch": 0.2673392181588903,
      "grad_norm": 8.464868545532227,
      "learning_rate": 8.732572877059569e-06,
      "loss": 1.7947,
      "step": 106
    },
    {
      "epoch": 0.2698612862547289,
      "grad_norm": 9.57347583770752,
      "learning_rate": 8.719898605830165e-06,
      "loss": 2.0333,
      "step": 107
    },
    {
      "epoch": 0.2723833543505675,
      "grad_norm": 8.682156562805176,
      "learning_rate": 8.707224334600761e-06,
      "loss": 1.7808,
      "step": 108
    },
    {
      "epoch": 0.27490542244640603,
      "grad_norm": 9.720832824707031,
      "learning_rate": 8.694550063371356e-06,
      "loss": 1.9601,
      "step": 109
    },
    {
      "epoch": 0.27742749054224464,
      "grad_norm": 8.890487670898438,
      "learning_rate": 8.681875792141954e-06,
      "loss": 1.9123,
      "step": 110
    },
    {
      "epoch": 0.27994955863808324,
      "grad_norm": 9.121131896972656,
      "learning_rate": 8.669201520912548e-06,
      "loss": 1.8399,
      "step": 111
    },
    {
      "epoch": 0.28247162673392184,
      "grad_norm": 8.931142807006836,
      "learning_rate": 8.656527249683144e-06,
      "loss": 1.88,
      "step": 112
    },
    {
      "epoch": 0.2849936948297604,
      "grad_norm": 9.079472541809082,
      "learning_rate": 8.64385297845374e-06,
      "loss": 1.7766,
      "step": 113
    },
    {
      "epoch": 0.287515762925599,
      "grad_norm": 9.532262802124023,
      "learning_rate": 8.631178707224336e-06,
      "loss": 1.7715,
      "step": 114
    },
    {
      "epoch": 0.2900378310214376,
      "grad_norm": 8.928796768188477,
      "learning_rate": 8.61850443599493e-06,
      "loss": 1.6179,
      "step": 115
    },
    {
      "epoch": 0.29255989911727615,
      "grad_norm": 8.79500961303711,
      "learning_rate": 8.605830164765527e-06,
      "loss": 1.7653,
      "step": 116
    },
    {
      "epoch": 0.29508196721311475,
      "grad_norm": 9.038860321044922,
      "learning_rate": 8.593155893536123e-06,
      "loss": 1.8273,
      "step": 117
    },
    {
      "epoch": 0.29760403530895335,
      "grad_norm": 9.18289852142334,
      "learning_rate": 8.580481622306717e-06,
      "loss": 1.945,
      "step": 118
    },
    {
      "epoch": 0.30012610340479196,
      "grad_norm": 9.104387283325195,
      "learning_rate": 8.567807351077313e-06,
      "loss": 1.8444,
      "step": 119
    },
    {
      "epoch": 0.3026481715006305,
      "grad_norm": 9.251449584960938,
      "learning_rate": 8.55513307984791e-06,
      "loss": 1.7502,
      "step": 120
    },
    {
      "epoch": 0.3051702395964691,
      "grad_norm": 9.526406288146973,
      "learning_rate": 8.542458808618506e-06,
      "loss": 1.8277,
      "step": 121
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 9.494799613952637,
      "learning_rate": 8.5297845373891e-06,
      "loss": 1.9802,
      "step": 122
    },
    {
      "epoch": 0.31021437578814626,
      "grad_norm": 9.093886375427246,
      "learning_rate": 8.517110266159696e-06,
      "loss": 1.7598,
      "step": 123
    },
    {
      "epoch": 0.31273644388398486,
      "grad_norm": 9.275187492370605,
      "learning_rate": 8.504435994930292e-06,
      "loss": 1.7269,
      "step": 124
    },
    {
      "epoch": 0.31525851197982346,
      "grad_norm": 8.311441421508789,
      "learning_rate": 8.491761723700888e-06,
      "loss": 1.8353,
      "step": 125
    },
    {
      "epoch": 0.31778058007566207,
      "grad_norm": 8.989309310913086,
      "learning_rate": 8.479087452471484e-06,
      "loss": 1.8799,
      "step": 126
    },
    {
      "epoch": 0.3203026481715006,
      "grad_norm": 9.124334335327148,
      "learning_rate": 8.466413181242079e-06,
      "loss": 1.8709,
      "step": 127
    },
    {
      "epoch": 0.3228247162673392,
      "grad_norm": 9.008078575134277,
      "learning_rate": 8.453738910012675e-06,
      "loss": 1.7002,
      "step": 128
    },
    {
      "epoch": 0.3253467843631778,
      "grad_norm": 8.43070125579834,
      "learning_rate": 8.441064638783271e-06,
      "loss": 1.8012,
      "step": 129
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 9.406371116638184,
      "learning_rate": 8.428390367553865e-06,
      "loss": 1.8611,
      "step": 130
    },
    {
      "epoch": 0.33039092055485497,
      "grad_norm": 8.853006362915039,
      "learning_rate": 8.415716096324462e-06,
      "loss": 1.7709,
      "step": 131
    },
    {
      "epoch": 0.3329129886506936,
      "grad_norm": 9.170083045959473,
      "learning_rate": 8.403041825095058e-06,
      "loss": 2.0669,
      "step": 132
    },
    {
      "epoch": 0.3354350567465322,
      "grad_norm": 9.382063865661621,
      "learning_rate": 8.390367553865654e-06,
      "loss": 1.8012,
      "step": 133
    },
    {
      "epoch": 0.3379571248423707,
      "grad_norm": 9.157647132873535,
      "learning_rate": 8.377693282636248e-06,
      "loss": 1.8584,
      "step": 134
    },
    {
      "epoch": 0.34047919293820933,
      "grad_norm": 9.179341316223145,
      "learning_rate": 8.365019011406846e-06,
      "loss": 1.8589,
      "step": 135
    },
    {
      "epoch": 0.34300126103404793,
      "grad_norm": 9.133096694946289,
      "learning_rate": 8.35234474017744e-06,
      "loss": 1.9222,
      "step": 136
    },
    {
      "epoch": 0.3455233291298865,
      "grad_norm": 8.78919792175293,
      "learning_rate": 8.339670468948035e-06,
      "loss": 1.839,
      "step": 137
    },
    {
      "epoch": 0.3480453972257251,
      "grad_norm": 8.94666576385498,
      "learning_rate": 8.326996197718633e-06,
      "loss": 1.7538,
      "step": 138
    },
    {
      "epoch": 0.3505674653215637,
      "grad_norm": 9.572528839111328,
      "learning_rate": 8.314321926489227e-06,
      "loss": 1.9778,
      "step": 139
    },
    {
      "epoch": 0.3530895334174023,
      "grad_norm": 9.474174499511719,
      "learning_rate": 8.301647655259823e-06,
      "loss": 1.9579,
      "step": 140
    },
    {
      "epoch": 0.35561160151324084,
      "grad_norm": 9.462223052978516,
      "learning_rate": 8.28897338403042e-06,
      "loss": 1.7689,
      "step": 141
    },
    {
      "epoch": 0.35813366960907944,
      "grad_norm": 8.904463768005371,
      "learning_rate": 8.276299112801015e-06,
      "loss": 1.7506,
      "step": 142
    },
    {
      "epoch": 0.36065573770491804,
      "grad_norm": 9.692485809326172,
      "learning_rate": 8.26362484157161e-06,
      "loss": 2.0011,
      "step": 143
    },
    {
      "epoch": 0.36317780580075665,
      "grad_norm": 8.99770450592041,
      "learning_rate": 8.250950570342206e-06,
      "loss": 1.7689,
      "step": 144
    },
    {
      "epoch": 0.3656998738965952,
      "grad_norm": 8.849214553833008,
      "learning_rate": 8.238276299112802e-06,
      "loss": 1.845,
      "step": 145
    },
    {
      "epoch": 0.3682219419924338,
      "grad_norm": 9.16205883026123,
      "learning_rate": 8.225602027883396e-06,
      "loss": 1.9285,
      "step": 146
    },
    {
      "epoch": 0.3707440100882724,
      "grad_norm": 9.169661521911621,
      "learning_rate": 8.212927756653993e-06,
      "loss": 1.8835,
      "step": 147
    },
    {
      "epoch": 0.37326607818411095,
      "grad_norm": 9.326395988464355,
      "learning_rate": 8.200253485424589e-06,
      "loss": 1.8162,
      "step": 148
    },
    {
      "epoch": 0.37578814627994955,
      "grad_norm": 8.962848663330078,
      "learning_rate": 8.187579214195185e-06,
      "loss": 1.8775,
      "step": 149
    },
    {
      "epoch": 0.37831021437578816,
      "grad_norm": 8.53931713104248,
      "learning_rate": 8.17490494296578e-06,
      "loss": 1.7893,
      "step": 150
    },
    {
      "epoch": 0.37831021437578816,
      "eval_loss": 1.8017936944961548,
      "eval_runtime": 19.5165,
      "eval_samples_per_second": 36.123,
      "eval_steps_per_second": 18.087,
      "step": 150
    },
    {
      "epoch": 0.38083228247162676,
      "grad_norm": 8.814638137817383,
      "learning_rate": 8.162230671736375e-06,
      "loss": 1.7401,
      "step": 151
    },
    {
      "epoch": 0.3833543505674653,
      "grad_norm": 9.316661834716797,
      "learning_rate": 8.149556400506971e-06,
      "loss": 1.9799,
      "step": 152
    },
    {
      "epoch": 0.3858764186633039,
      "grad_norm": 9.053354263305664,
      "learning_rate": 8.136882129277567e-06,
      "loss": 1.6721,
      "step": 153
    },
    {
      "epoch": 0.3883984867591425,
      "grad_norm": 9.15576457977295,
      "learning_rate": 8.124207858048164e-06,
      "loss": 1.9065,
      "step": 154
    },
    {
      "epoch": 0.39092055485498106,
      "grad_norm": 8.911511421203613,
      "learning_rate": 8.111533586818758e-06,
      "loss": 1.9229,
      "step": 155
    },
    {
      "epoch": 0.39344262295081966,
      "grad_norm": 8.312164306640625,
      "learning_rate": 8.098859315589354e-06,
      "loss": 1.7699,
      "step": 156
    },
    {
      "epoch": 0.39596469104665827,
      "grad_norm": 9.155098915100098,
      "learning_rate": 8.08618504435995e-06,
      "loss": 1.9292,
      "step": 157
    },
    {
      "epoch": 0.39848675914249687,
      "grad_norm": 8.932412147521973,
      "learning_rate": 8.073510773130546e-06,
      "loss": 1.8102,
      "step": 158
    },
    {
      "epoch": 0.4010088272383354,
      "grad_norm": 8.135700225830078,
      "learning_rate": 8.06083650190114e-06,
      "loss": 1.72,
      "step": 159
    },
    {
      "epoch": 0.403530895334174,
      "grad_norm": 9.693431854248047,
      "learning_rate": 8.048162230671737e-06,
      "loss": 1.8558,
      "step": 160
    },
    {
      "epoch": 0.4060529634300126,
      "grad_norm": 8.98935317993164,
      "learning_rate": 8.035487959442333e-06,
      "loss": 1.9407,
      "step": 161
    },
    {
      "epoch": 0.4085750315258512,
      "grad_norm": 8.735937118530273,
      "learning_rate": 8.022813688212927e-06,
      "loss": 1.8333,
      "step": 162
    },
    {
      "epoch": 0.4110970996216898,
      "grad_norm": 9.313026428222656,
      "learning_rate": 8.010139416983525e-06,
      "loss": 1.9925,
      "step": 163
    },
    {
      "epoch": 0.4136191677175284,
      "grad_norm": 9.607177734375,
      "learning_rate": 7.99746514575412e-06,
      "loss": 1.8164,
      "step": 164
    },
    {
      "epoch": 0.416141235813367,
      "grad_norm": 9.086844444274902,
      "learning_rate": 7.984790874524716e-06,
      "loss": 1.8585,
      "step": 165
    },
    {
      "epoch": 0.41866330390920553,
      "grad_norm": 9.212312698364258,
      "learning_rate": 7.972116603295312e-06,
      "loss": 1.8332,
      "step": 166
    },
    {
      "epoch": 0.42118537200504413,
      "grad_norm": 9.246332168579102,
      "learning_rate": 7.959442332065906e-06,
      "loss": 1.8488,
      "step": 167
    },
    {
      "epoch": 0.42370744010088274,
      "grad_norm": 9.077427864074707,
      "learning_rate": 7.946768060836502e-06,
      "loss": 1.7442,
      "step": 168
    },
    {
      "epoch": 0.4262295081967213,
      "grad_norm": 9.019879341125488,
      "learning_rate": 7.934093789607098e-06,
      "loss": 1.9638,
      "step": 169
    },
    {
      "epoch": 0.4287515762925599,
      "grad_norm": 8.645258903503418,
      "learning_rate": 7.921419518377694e-06,
      "loss": 1.8532,
      "step": 170
    },
    {
      "epoch": 0.4312736443883985,
      "grad_norm": 8.863842010498047,
      "learning_rate": 7.908745247148289e-06,
      "loss": 1.7754,
      "step": 171
    },
    {
      "epoch": 0.4337957124842371,
      "grad_norm": 9.303889274597168,
      "learning_rate": 7.896070975918885e-06,
      "loss": 1.774,
      "step": 172
    },
    {
      "epoch": 0.43631778058007564,
      "grad_norm": 9.072324752807617,
      "learning_rate": 7.883396704689481e-06,
      "loss": 1.9916,
      "step": 173
    },
    {
      "epoch": 0.43883984867591425,
      "grad_norm": 8.935220718383789,
      "learning_rate": 7.870722433460076e-06,
      "loss": 1.7988,
      "step": 174
    },
    {
      "epoch": 0.44136191677175285,
      "grad_norm": 8.469002723693848,
      "learning_rate": 7.858048162230673e-06,
      "loss": 1.7943,
      "step": 175
    },
    {
      "epoch": 0.44388398486759145,
      "grad_norm": 8.663657188415527,
      "learning_rate": 7.845373891001268e-06,
      "loss": 1.9424,
      "step": 176
    },
    {
      "epoch": 0.44640605296343,
      "grad_norm": 9.067521095275879,
      "learning_rate": 7.832699619771864e-06,
      "loss": 1.8128,
      "step": 177
    },
    {
      "epoch": 0.4489281210592686,
      "grad_norm": 8.450661659240723,
      "learning_rate": 7.82002534854246e-06,
      "loss": 1.7287,
      "step": 178
    },
    {
      "epoch": 0.4514501891551072,
      "grad_norm": 8.83759593963623,
      "learning_rate": 7.807351077313056e-06,
      "loss": 1.7602,
      "step": 179
    },
    {
      "epoch": 0.45397225725094575,
      "grad_norm": 8.693680763244629,
      "learning_rate": 7.79467680608365e-06,
      "loss": 2.0174,
      "step": 180
    },
    {
      "epoch": 0.45649432534678436,
      "grad_norm": 9.432674407958984,
      "learning_rate": 7.782002534854247e-06,
      "loss": 1.9696,
      "step": 181
    },
    {
      "epoch": 0.45901639344262296,
      "grad_norm": 8.901416778564453,
      "learning_rate": 7.769328263624843e-06,
      "loss": 1.8075,
      "step": 182
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 8.675703048706055,
      "learning_rate": 7.756653992395437e-06,
      "loss": 1.8696,
      "step": 183
    },
    {
      "epoch": 0.4640605296343001,
      "grad_norm": 9.176361083984375,
      "learning_rate": 7.743979721166033e-06,
      "loss": 1.8572,
      "step": 184
    },
    {
      "epoch": 0.4665825977301387,
      "grad_norm": 8.568829536437988,
      "learning_rate": 7.73130544993663e-06,
      "loss": 1.638,
      "step": 185
    },
    {
      "epoch": 0.4691046658259773,
      "grad_norm": 8.751213073730469,
      "learning_rate": 7.718631178707225e-06,
      "loss": 1.7869,
      "step": 186
    },
    {
      "epoch": 0.47162673392181587,
      "grad_norm": 8.986238479614258,
      "learning_rate": 7.70595690747782e-06,
      "loss": 1.831,
      "step": 187
    },
    {
      "epoch": 0.47414880201765447,
      "grad_norm": 9.22641372680664,
      "learning_rate": 7.693282636248416e-06,
      "loss": 1.7918,
      "step": 188
    },
    {
      "epoch": 0.4766708701134931,
      "grad_norm": 9.145533561706543,
      "learning_rate": 7.680608365019012e-06,
      "loss": 1.6651,
      "step": 189
    },
    {
      "epoch": 0.4791929382093317,
      "grad_norm": 8.419795989990234,
      "learning_rate": 7.667934093789608e-06,
      "loss": 1.6928,
      "step": 190
    },
    {
      "epoch": 0.4817150063051702,
      "grad_norm": 9.782970428466797,
      "learning_rate": 7.655259822560204e-06,
      "loss": 1.9865,
      "step": 191
    },
    {
      "epoch": 0.4842370744010088,
      "grad_norm": 8.885458946228027,
      "learning_rate": 7.642585551330799e-06,
      "loss": 1.9461,
      "step": 192
    },
    {
      "epoch": 0.48675914249684743,
      "grad_norm": 10.114888191223145,
      "learning_rate": 7.629911280101395e-06,
      "loss": 1.6703,
      "step": 193
    },
    {
      "epoch": 0.489281210592686,
      "grad_norm": 9.351268768310547,
      "learning_rate": 7.617237008871991e-06,
      "loss": 1.8674,
      "step": 194
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 9.144396781921387,
      "learning_rate": 7.604562737642585e-06,
      "loss": 2.0062,
      "step": 195
    },
    {
      "epoch": 0.4943253467843632,
      "grad_norm": 9.084301948547363,
      "learning_rate": 7.591888466413182e-06,
      "loss": 2.015,
      "step": 196
    },
    {
      "epoch": 0.4968474148802018,
      "grad_norm": 8.582064628601074,
      "learning_rate": 7.5792141951837775e-06,
      "loss": 1.8281,
      "step": 197
    },
    {
      "epoch": 0.49936948297604034,
      "grad_norm": 8.800094604492188,
      "learning_rate": 7.566539923954374e-06,
      "loss": 1.7135,
      "step": 198
    },
    {
      "epoch": 0.501891551071879,
      "grad_norm": 9.495306015014648,
      "learning_rate": 7.553865652724969e-06,
      "loss": 1.8995,
      "step": 199
    },
    {
      "epoch": 0.5044136191677175,
      "grad_norm": 9.089255332946777,
      "learning_rate": 7.541191381495565e-06,
      "loss": 1.8346,
      "step": 200
    },
    {
      "epoch": 0.5044136191677175,
      "eval_loss": 1.7910906076431274,
      "eval_runtime": 19.0069,
      "eval_samples_per_second": 37.092,
      "eval_steps_per_second": 18.572,
      "step": 200
    },
    {
      "epoch": 0.5069356872635561,
      "grad_norm": 9.345693588256836,
      "learning_rate": 7.52851711026616e-06,
      "loss": 1.7234,
      "step": 201
    },
    {
      "epoch": 0.5094577553593947,
      "grad_norm": 9.04035758972168,
      "learning_rate": 7.5158428390367555e-06,
      "loss": 1.9198,
      "step": 202
    },
    {
      "epoch": 0.5119798234552333,
      "grad_norm": 8.787433624267578,
      "learning_rate": 7.503168567807352e-06,
      "loss": 1.8651,
      "step": 203
    },
    {
      "epoch": 0.5145018915510718,
      "grad_norm": 8.92418098449707,
      "learning_rate": 7.490494296577947e-06,
      "loss": 1.8808,
      "step": 204
    },
    {
      "epoch": 0.5170239596469105,
      "grad_norm": 9.472183227539062,
      "learning_rate": 7.477820025348543e-06,
      "loss": 1.8794,
      "step": 205
    },
    {
      "epoch": 0.519546027742749,
      "grad_norm": 8.935132026672363,
      "learning_rate": 7.465145754119138e-06,
      "loss": 1.9661,
      "step": 206
    },
    {
      "epoch": 0.5220680958385876,
      "grad_norm": 8.539314270019531,
      "learning_rate": 7.452471482889735e-06,
      "loss": 1.7449,
      "step": 207
    },
    {
      "epoch": 0.5245901639344263,
      "grad_norm": 9.224102020263672,
      "learning_rate": 7.4397972116603304e-06,
      "loss": 1.7893,
      "step": 208
    },
    {
      "epoch": 0.5271122320302648,
      "grad_norm": 8.306479454040527,
      "learning_rate": 7.427122940430926e-06,
      "loss": 1.6752,
      "step": 209
    },
    {
      "epoch": 0.5296343001261034,
      "grad_norm": 8.810216903686523,
      "learning_rate": 7.414448669201522e-06,
      "loss": 1.9381,
      "step": 210
    },
    {
      "epoch": 0.532156368221942,
      "grad_norm": 8.660805702209473,
      "learning_rate": 7.401774397972117e-06,
      "loss": 1.7787,
      "step": 211
    },
    {
      "epoch": 0.5346784363177806,
      "grad_norm": 8.914039611816406,
      "learning_rate": 7.389100126742713e-06,
      "loss": 1.9574,
      "step": 212
    },
    {
      "epoch": 0.5372005044136192,
      "grad_norm": 8.298178672790527,
      "learning_rate": 7.376425855513308e-06,
      "loss": 1.7711,
      "step": 213
    },
    {
      "epoch": 0.5397225725094578,
      "grad_norm": 9.578728675842285,
      "learning_rate": 7.3637515842839045e-06,
      "loss": 1.8558,
      "step": 214
    },
    {
      "epoch": 0.5422446406052963,
      "grad_norm": 9.25766658782959,
      "learning_rate": 7.3510773130545e-06,
      "loss": 1.887,
      "step": 215
    },
    {
      "epoch": 0.544766708701135,
      "grad_norm": 9.36644458770752,
      "learning_rate": 7.338403041825095e-06,
      "loss": 1.8779,
      "step": 216
    },
    {
      "epoch": 0.5472887767969735,
      "grad_norm": 9.4396333694458,
      "learning_rate": 7.325728770595691e-06,
      "loss": 1.8936,
      "step": 217
    },
    {
      "epoch": 0.5498108448928121,
      "grad_norm": 8.876384735107422,
      "learning_rate": 7.313054499366286e-06,
      "loss": 1.8349,
      "step": 218
    },
    {
      "epoch": 0.5523329129886507,
      "grad_norm": 9.552757263183594,
      "learning_rate": 7.300380228136883e-06,
      "loss": 1.9562,
      "step": 219
    },
    {
      "epoch": 0.5548549810844893,
      "grad_norm": 8.633830070495605,
      "learning_rate": 7.287705956907478e-06,
      "loss": 1.7676,
      "step": 220
    },
    {
      "epoch": 0.5573770491803278,
      "grad_norm": 9.029250144958496,
      "learning_rate": 7.275031685678075e-06,
      "loss": 1.8633,
      "step": 221
    },
    {
      "epoch": 0.5598991172761665,
      "grad_norm": 9.104911804199219,
      "learning_rate": 7.26235741444867e-06,
      "loss": 1.9103,
      "step": 222
    },
    {
      "epoch": 0.562421185372005,
      "grad_norm": 8.998291015625,
      "learning_rate": 7.249683143219266e-06,
      "loss": 1.6631,
      "step": 223
    },
    {
      "epoch": 0.5649432534678437,
      "grad_norm": 9.102141380310059,
      "learning_rate": 7.237008871989861e-06,
      "loss": 1.8491,
      "step": 224
    },
    {
      "epoch": 0.5674653215636822,
      "grad_norm": 8.94286823272705,
      "learning_rate": 7.224334600760457e-06,
      "loss": 1.6546,
      "step": 225
    },
    {
      "epoch": 0.5699873896595208,
      "grad_norm": 9.074462890625,
      "learning_rate": 7.211660329531053e-06,
      "loss": 1.8034,
      "step": 226
    },
    {
      "epoch": 0.5725094577553594,
      "grad_norm": 8.364324569702148,
      "learning_rate": 7.198986058301648e-06,
      "loss": 1.8561,
      "step": 227
    },
    {
      "epoch": 0.575031525851198,
      "grad_norm": 8.235718727111816,
      "learning_rate": 7.186311787072244e-06,
      "loss": 1.6534,
      "step": 228
    },
    {
      "epoch": 0.5775535939470365,
      "grad_norm": 8.920160293579102,
      "learning_rate": 7.173637515842839e-06,
      "loss": 1.8104,
      "step": 229
    },
    {
      "epoch": 0.5800756620428752,
      "grad_norm": 9.526931762695312,
      "learning_rate": 7.1609632446134354e-06,
      "loss": 1.8956,
      "step": 230
    },
    {
      "epoch": 0.5825977301387137,
      "grad_norm": 10.063536643981934,
      "learning_rate": 7.148288973384031e-06,
      "loss": 1.8132,
      "step": 231
    },
    {
      "epoch": 0.5851197982345523,
      "grad_norm": 8.38437271118164,
      "learning_rate": 7.135614702154626e-06,
      "loss": 1.9233,
      "step": 232
    },
    {
      "epoch": 0.587641866330391,
      "grad_norm": 10.298331260681152,
      "learning_rate": 7.122940430925223e-06,
      "loss": 1.8351,
      "step": 233
    },
    {
      "epoch": 0.5901639344262295,
      "grad_norm": 8.098287582397461,
      "learning_rate": 7.110266159695818e-06,
      "loss": 1.672,
      "step": 234
    },
    {
      "epoch": 0.592686002522068,
      "grad_norm": 9.341371536254883,
      "learning_rate": 7.097591888466414e-06,
      "loss": 1.7139,
      "step": 235
    },
    {
      "epoch": 0.5952080706179067,
      "grad_norm": 9.039361953735352,
      "learning_rate": 7.0849176172370095e-06,
      "loss": 1.6284,
      "step": 236
    },
    {
      "epoch": 0.5977301387137453,
      "grad_norm": 9.125579833984375,
      "learning_rate": 7.072243346007606e-06,
      "loss": 1.8376,
      "step": 237
    },
    {
      "epoch": 0.6002522068095839,
      "grad_norm": 8.501140594482422,
      "learning_rate": 7.059569074778201e-06,
      "loss": 1.7236,
      "step": 238
    },
    {
      "epoch": 0.6027742749054225,
      "grad_norm": 8.870810508728027,
      "learning_rate": 7.046894803548796e-06,
      "loss": 1.724,
      "step": 239
    },
    {
      "epoch": 0.605296343001261,
      "grad_norm": 9.259521484375,
      "learning_rate": 7.034220532319392e-06,
      "loss": 1.7792,
      "step": 240
    },
    {
      "epoch": 0.6078184110970997,
      "grad_norm": 10.289566993713379,
      "learning_rate": 7.0215462610899875e-06,
      "loss": 1.8516,
      "step": 241
    },
    {
      "epoch": 0.6103404791929382,
      "grad_norm": 10.193709373474121,
      "learning_rate": 7.008871989860584e-06,
      "loss": 1.8237,
      "step": 242
    },
    {
      "epoch": 0.6128625472887768,
      "grad_norm": 9.346511840820312,
      "learning_rate": 6.996197718631179e-06,
      "loss": 1.7183,
      "step": 243
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 9.695211410522461,
      "learning_rate": 6.983523447401776e-06,
      "loss": 1.8324,
      "step": 244
    },
    {
      "epoch": 0.617906683480454,
      "grad_norm": 8.961493492126465,
      "learning_rate": 6.97084917617237e-06,
      "loss": 1.8801,
      "step": 245
    },
    {
      "epoch": 0.6204287515762925,
      "grad_norm": 9.273719787597656,
      "learning_rate": 6.9581749049429655e-06,
      "loss": 1.7128,
      "step": 246
    },
    {
      "epoch": 0.6229508196721312,
      "grad_norm": 8.997072219848633,
      "learning_rate": 6.9455006337135625e-06,
      "loss": 1.8675,
      "step": 247
    },
    {
      "epoch": 0.6254728877679697,
      "grad_norm": 8.742542266845703,
      "learning_rate": 6.932826362484158e-06,
      "loss": 1.853,
      "step": 248
    },
    {
      "epoch": 0.6279949558638083,
      "grad_norm": 9.45918083190918,
      "learning_rate": 6.920152091254754e-06,
      "loss": 1.8785,
      "step": 249
    },
    {
      "epoch": 0.6305170239596469,
      "grad_norm": 9.404273986816406,
      "learning_rate": 6.907477820025349e-06,
      "loss": 1.7804,
      "step": 250
    },
    {
      "epoch": 0.6305170239596469,
      "eval_loss": 1.7830545902252197,
      "eval_runtime": 19.0502,
      "eval_samples_per_second": 37.008,
      "eval_steps_per_second": 18.53,
      "step": 250
    },
    {
      "epoch": 0.6330390920554855,
      "grad_norm": 8.45837116241455,
      "learning_rate": 6.894803548795945e-06,
      "loss": 1.776,
      "step": 251
    },
    {
      "epoch": 0.6355611601513241,
      "grad_norm": 8.904789924621582,
      "learning_rate": 6.8821292775665405e-06,
      "loss": 1.6963,
      "step": 252
    },
    {
      "epoch": 0.6380832282471627,
      "grad_norm": 9.281813621520996,
      "learning_rate": 6.869455006337136e-06,
      "loss": 1.8785,
      "step": 253
    },
    {
      "epoch": 0.6406052963430012,
      "grad_norm": 9.524839401245117,
      "learning_rate": 6.856780735107732e-06,
      "loss": 1.9344,
      "step": 254
    },
    {
      "epoch": 0.6431273644388399,
      "grad_norm": 9.229698181152344,
      "learning_rate": 6.844106463878327e-06,
      "loss": 1.7912,
      "step": 255
    },
    {
      "epoch": 0.6456494325346784,
      "grad_norm": 9.272945404052734,
      "learning_rate": 6.831432192648923e-06,
      "loss": 1.7938,
      "step": 256
    },
    {
      "epoch": 0.648171500630517,
      "grad_norm": 8.950004577636719,
      "learning_rate": 6.8187579214195185e-06,
      "loss": 1.8106,
      "step": 257
    },
    {
      "epoch": 0.6506935687263556,
      "grad_norm": 8.666584968566895,
      "learning_rate": 6.806083650190115e-06,
      "loss": 1.6462,
      "step": 258
    },
    {
      "epoch": 0.6532156368221942,
      "grad_norm": 8.683521270751953,
      "learning_rate": 6.793409378960711e-06,
      "loss": 1.9492,
      "step": 259
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 9.300116539001465,
      "learning_rate": 6.780735107731305e-06,
      "loss": 1.7819,
      "step": 260
    },
    {
      "epoch": 0.6582597730138714,
      "grad_norm": 8.165949821472168,
      "learning_rate": 6.768060836501902e-06,
      "loss": 1.6548,
      "step": 261
    },
    {
      "epoch": 0.6607818411097099,
      "grad_norm": 9.01196575164795,
      "learning_rate": 6.755386565272497e-06,
      "loss": 1.7881,
      "step": 262
    },
    {
      "epoch": 0.6633039092055486,
      "grad_norm": 8.698511123657227,
      "learning_rate": 6.742712294043093e-06,
      "loss": 1.7711,
      "step": 263
    },
    {
      "epoch": 0.6658259773013872,
      "grad_norm": 8.930058479309082,
      "learning_rate": 6.730038022813689e-06,
      "loss": 1.7866,
      "step": 264
    },
    {
      "epoch": 0.6683480453972257,
      "grad_norm": 8.760106086730957,
      "learning_rate": 6.717363751584285e-06,
      "loss": 1.6785,
      "step": 265
    },
    {
      "epoch": 0.6708701134930644,
      "grad_norm": 9.946425437927246,
      "learning_rate": 6.70468948035488e-06,
      "loss": 1.7497,
      "step": 266
    },
    {
      "epoch": 0.6733921815889029,
      "grad_norm": 8.68403148651123,
      "learning_rate": 6.692015209125475e-06,
      "loss": 1.7541,
      "step": 267
    },
    {
      "epoch": 0.6759142496847415,
      "grad_norm": 9.644161224365234,
      "learning_rate": 6.679340937896071e-06,
      "loss": 1.9508,
      "step": 268
    },
    {
      "epoch": 0.6784363177805801,
      "grad_norm": 9.56482219696045,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.7228,
      "step": 269
    },
    {
      "epoch": 0.6809583858764187,
      "grad_norm": 10.026971817016602,
      "learning_rate": 6.653992395437263e-06,
      "loss": 1.7829,
      "step": 270
    },
    {
      "epoch": 0.6834804539722572,
      "grad_norm": 9.550620079040527,
      "learning_rate": 6.641318124207858e-06,
      "loss": 1.848,
      "step": 271
    },
    {
      "epoch": 0.6860025220680959,
      "grad_norm": 8.211991310119629,
      "learning_rate": 6.628643852978455e-06,
      "loss": 1.7159,
      "step": 272
    },
    {
      "epoch": 0.6885245901639344,
      "grad_norm": 9.10818862915039,
      "learning_rate": 6.61596958174905e-06,
      "loss": 1.8784,
      "step": 273
    },
    {
      "epoch": 0.691046658259773,
      "grad_norm": 9.215516090393066,
      "learning_rate": 6.6032953105196455e-06,
      "loss": 1.8904,
      "step": 274
    },
    {
      "epoch": 0.6935687263556116,
      "grad_norm": 9.219340324401855,
      "learning_rate": 6.590621039290242e-06,
      "loss": 1.9,
      "step": 275
    },
    {
      "epoch": 0.6960907944514502,
      "grad_norm": 9.658199310302734,
      "learning_rate": 6.577946768060837e-06,
      "loss": 1.8133,
      "step": 276
    },
    {
      "epoch": 0.6986128625472888,
      "grad_norm": 9.81287670135498,
      "learning_rate": 6.565272496831433e-06,
      "loss": 1.9367,
      "step": 277
    },
    {
      "epoch": 0.7011349306431274,
      "grad_norm": 9.701519012451172,
      "learning_rate": 6.552598225602028e-06,
      "loss": 1.8504,
      "step": 278
    },
    {
      "epoch": 0.7036569987389659,
      "grad_norm": 10.293815612792969,
      "learning_rate": 6.539923954372624e-06,
      "loss": 1.9025,
      "step": 279
    },
    {
      "epoch": 0.7061790668348046,
      "grad_norm": 9.13555908203125,
      "learning_rate": 6.52724968314322e-06,
      "loss": 1.7409,
      "step": 280
    },
    {
      "epoch": 0.7087011349306431,
      "grad_norm": 9.631402969360352,
      "learning_rate": 6.514575411913816e-06,
      "loss": 1.8409,
      "step": 281
    },
    {
      "epoch": 0.7112232030264817,
      "grad_norm": 8.498468399047852,
      "learning_rate": 6.501901140684411e-06,
      "loss": 1.6282,
      "step": 282
    },
    {
      "epoch": 0.7137452711223203,
      "grad_norm": 8.965262413024902,
      "learning_rate": 6.489226869455006e-06,
      "loss": 1.9211,
      "step": 283
    },
    {
      "epoch": 0.7162673392181589,
      "grad_norm": 9.177412033081055,
      "learning_rate": 6.476552598225603e-06,
      "loss": 1.8234,
      "step": 284
    },
    {
      "epoch": 0.7187894073139974,
      "grad_norm": 8.464885711669922,
      "learning_rate": 6.4638783269961976e-06,
      "loss": 1.8647,
      "step": 285
    },
    {
      "epoch": 0.7213114754098361,
      "grad_norm": 8.864629745483398,
      "learning_rate": 6.4512040557667945e-06,
      "loss": 1.7649,
      "step": 286
    },
    {
      "epoch": 0.7238335435056746,
      "grad_norm": 9.25640869140625,
      "learning_rate": 6.43852978453739e-06,
      "loss": 1.8066,
      "step": 287
    },
    {
      "epoch": 0.7263556116015133,
      "grad_norm": 9.54092788696289,
      "learning_rate": 6.425855513307986e-06,
      "loss": 1.8847,
      "step": 288
    },
    {
      "epoch": 0.7288776796973518,
      "grad_norm": 7.9918012619018555,
      "learning_rate": 6.413181242078581e-06,
      "loss": 1.7432,
      "step": 289
    },
    {
      "epoch": 0.7313997477931904,
      "grad_norm": 8.696568489074707,
      "learning_rate": 6.400506970849176e-06,
      "loss": 1.6284,
      "step": 290
    },
    {
      "epoch": 0.733921815889029,
      "grad_norm": 9.63094711303711,
      "learning_rate": 6.3878326996197725e-06,
      "loss": 1.7016,
      "step": 291
    },
    {
      "epoch": 0.7364438839848676,
      "grad_norm": 9.056994438171387,
      "learning_rate": 6.375158428390368e-06,
      "loss": 1.6961,
      "step": 292
    },
    {
      "epoch": 0.7389659520807061,
      "grad_norm": 8.675078392028809,
      "learning_rate": 6.362484157160964e-06,
      "loss": 1.6916,
      "step": 293
    },
    {
      "epoch": 0.7414880201765448,
      "grad_norm": 9.566941261291504,
      "learning_rate": 6.349809885931559e-06,
      "loss": 1.8627,
      "step": 294
    },
    {
      "epoch": 0.7440100882723834,
      "grad_norm": 8.477948188781738,
      "learning_rate": 6.337135614702155e-06,
      "loss": 1.8095,
      "step": 295
    },
    {
      "epoch": 0.7465321563682219,
      "grad_norm": 9.392255783081055,
      "learning_rate": 6.3244613434727505e-06,
      "loss": 1.8136,
      "step": 296
    },
    {
      "epoch": 0.7490542244640606,
      "grad_norm": 9.066890716552734,
      "learning_rate": 6.311787072243346e-06,
      "loss": 1.8301,
      "step": 297
    },
    {
      "epoch": 0.7515762925598991,
      "grad_norm": 9.267568588256836,
      "learning_rate": 6.299112801013943e-06,
      "loss": 1.9952,
      "step": 298
    },
    {
      "epoch": 0.7540983606557377,
      "grad_norm": 9.324930191040039,
      "learning_rate": 6.286438529784538e-06,
      "loss": 1.8288,
      "step": 299
    },
    {
      "epoch": 0.7566204287515763,
      "grad_norm": 9.1065034866333,
      "learning_rate": 6.273764258555134e-06,
      "loss": 1.7901,
      "step": 300
    },
    {
      "epoch": 0.7566204287515763,
      "eval_loss": 1.7733962535858154,
      "eval_runtime": 19.1336,
      "eval_samples_per_second": 36.846,
      "eval_steps_per_second": 18.449,
      "step": 300
    },
    {
      "epoch": 0.7591424968474149,
      "grad_norm": 9.206751823425293,
      "learning_rate": 6.261089987325729e-06,
      "loss": 1.6918,
      "step": 301
    },
    {
      "epoch": 0.7616645649432535,
      "grad_norm": 8.51040267944336,
      "learning_rate": 6.2484157160963254e-06,
      "loss": 1.7067,
      "step": 302
    },
    {
      "epoch": 0.7641866330390921,
      "grad_norm": 9.596914291381836,
      "learning_rate": 6.235741444866921e-06,
      "loss": 1.8249,
      "step": 303
    },
    {
      "epoch": 0.7667087011349306,
      "grad_norm": 8.489897727966309,
      "learning_rate": 6.223067173637516e-06,
      "loss": 1.7135,
      "step": 304
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 9.746272087097168,
      "learning_rate": 6.210392902408112e-06,
      "loss": 1.7974,
      "step": 305
    },
    {
      "epoch": 0.7717528373266078,
      "grad_norm": 9.103402137756348,
      "learning_rate": 6.197718631178707e-06,
      "loss": 1.8095,
      "step": 306
    },
    {
      "epoch": 0.7742749054224464,
      "grad_norm": 8.94424057006836,
      "learning_rate": 6.1850443599493034e-06,
      "loss": 1.7711,
      "step": 307
    },
    {
      "epoch": 0.776796973518285,
      "grad_norm": 8.747350692749023,
      "learning_rate": 6.172370088719899e-06,
      "loss": 1.768,
      "step": 308
    },
    {
      "epoch": 0.7793190416141236,
      "grad_norm": 9.339826583862305,
      "learning_rate": 6.159695817490496e-06,
      "loss": 1.9012,
      "step": 309
    },
    {
      "epoch": 0.7818411097099621,
      "grad_norm": 9.367380142211914,
      "learning_rate": 6.147021546261091e-06,
      "loss": 1.8186,
      "step": 310
    },
    {
      "epoch": 0.7843631778058008,
      "grad_norm": 8.484911918640137,
      "learning_rate": 6.134347275031685e-06,
      "loss": 1.6549,
      "step": 311
    },
    {
      "epoch": 0.7868852459016393,
      "grad_norm": 8.981029510498047,
      "learning_rate": 6.121673003802282e-06,
      "loss": 1.6323,
      "step": 312
    },
    {
      "epoch": 0.7894073139974779,
      "grad_norm": 9.16687297821045,
      "learning_rate": 6.1089987325728775e-06,
      "loss": 1.8026,
      "step": 313
    },
    {
      "epoch": 0.7919293820933165,
      "grad_norm": 9.009170532226562,
      "learning_rate": 6.096324461343474e-06,
      "loss": 1.8114,
      "step": 314
    },
    {
      "epoch": 0.7944514501891551,
      "grad_norm": 9.293817520141602,
      "learning_rate": 6.083650190114069e-06,
      "loss": 1.9136,
      "step": 315
    },
    {
      "epoch": 0.7969735182849937,
      "grad_norm": 9.103388786315918,
      "learning_rate": 6.070975918884665e-06,
      "loss": 1.8382,
      "step": 316
    },
    {
      "epoch": 0.7994955863808323,
      "grad_norm": 8.633993148803711,
      "learning_rate": 6.05830164765526e-06,
      "loss": 1.8289,
      "step": 317
    },
    {
      "epoch": 0.8020176544766708,
      "grad_norm": 8.991758346557617,
      "learning_rate": 6.0456273764258555e-06,
      "loss": 1.7802,
      "step": 318
    },
    {
      "epoch": 0.8045397225725095,
      "grad_norm": 8.851658821105957,
      "learning_rate": 6.032953105196452e-06,
      "loss": 1.7659,
      "step": 319
    },
    {
      "epoch": 0.807061790668348,
      "grad_norm": 9.013936996459961,
      "learning_rate": 6.020278833967047e-06,
      "loss": 1.8286,
      "step": 320
    },
    {
      "epoch": 0.8095838587641866,
      "grad_norm": 8.47545337677002,
      "learning_rate": 6.007604562737643e-06,
      "loss": 1.8427,
      "step": 321
    },
    {
      "epoch": 0.8121059268600253,
      "grad_norm": 9.014452934265137,
      "learning_rate": 5.994930291508238e-06,
      "loss": 1.8381,
      "step": 322
    },
    {
      "epoch": 0.8146279949558638,
      "grad_norm": 9.263374328613281,
      "learning_rate": 5.982256020278835e-06,
      "loss": 1.8705,
      "step": 323
    },
    {
      "epoch": 0.8171500630517023,
      "grad_norm": 8.71599006652832,
      "learning_rate": 5.9695817490494305e-06,
      "loss": 1.7928,
      "step": 324
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 9.035847663879395,
      "learning_rate": 5.956907477820026e-06,
      "loss": 1.7995,
      "step": 325
    },
    {
      "epoch": 0.8221941992433796,
      "grad_norm": 10.10317325592041,
      "learning_rate": 5.944233206590622e-06,
      "loss": 1.7779,
      "step": 326
    },
    {
      "epoch": 0.8247162673392182,
      "grad_norm": 8.523378372192383,
      "learning_rate": 5.931558935361217e-06,
      "loss": 1.8369,
      "step": 327
    },
    {
      "epoch": 0.8272383354350568,
      "grad_norm": 8.316461563110352,
      "learning_rate": 5.918884664131813e-06,
      "loss": 1.7562,
      "step": 328
    },
    {
      "epoch": 0.8297604035308953,
      "grad_norm": 9.359851837158203,
      "learning_rate": 5.9062103929024085e-06,
      "loss": 1.949,
      "step": 329
    },
    {
      "epoch": 0.832282471626734,
      "grad_norm": 8.650400161743164,
      "learning_rate": 5.8935361216730046e-06,
      "loss": 1.7913,
      "step": 330
    },
    {
      "epoch": 0.8348045397225725,
      "grad_norm": 9.110953330993652,
      "learning_rate": 5.8808618504436e-06,
      "loss": 1.9973,
      "step": 331
    },
    {
      "epoch": 0.8373266078184111,
      "grad_norm": 8.773159980773926,
      "learning_rate": 5.868187579214195e-06,
      "loss": 1.7421,
      "step": 332
    },
    {
      "epoch": 0.8398486759142497,
      "grad_norm": 9.70534610748291,
      "learning_rate": 5.855513307984791e-06,
      "loss": 1.7871,
      "step": 333
    },
    {
      "epoch": 0.8423707440100883,
      "grad_norm": 8.491693496704102,
      "learning_rate": 5.8428390367553864e-06,
      "loss": 1.9853,
      "step": 334
    },
    {
      "epoch": 0.8448928121059268,
      "grad_norm": 8.736915588378906,
      "learning_rate": 5.830164765525983e-06,
      "loss": 1.7269,
      "step": 335
    },
    {
      "epoch": 0.8474148802017655,
      "grad_norm": 9.396732330322266,
      "learning_rate": 5.817490494296578e-06,
      "loss": 1.7794,
      "step": 336
    },
    {
      "epoch": 0.849936948297604,
      "grad_norm": 9.855878829956055,
      "learning_rate": 5.804816223067175e-06,
      "loss": 1.8781,
      "step": 337
    },
    {
      "epoch": 0.8524590163934426,
      "grad_norm": 9.038098335266113,
      "learning_rate": 5.79214195183777e-06,
      "loss": 1.8115,
      "step": 338
    },
    {
      "epoch": 0.8549810844892812,
      "grad_norm": 9.057479858398438,
      "learning_rate": 5.779467680608365e-06,
      "loss": 1.6469,
      "step": 339
    },
    {
      "epoch": 0.8575031525851198,
      "grad_norm": 8.963297843933105,
      "learning_rate": 5.766793409378961e-06,
      "loss": 1.8032,
      "step": 340
    },
    {
      "epoch": 0.8600252206809584,
      "grad_norm": 9.398365020751953,
      "learning_rate": 5.754119138149557e-06,
      "loss": 1.8722,
      "step": 341
    },
    {
      "epoch": 0.862547288776797,
      "grad_norm": 8.406683921813965,
      "learning_rate": 5.741444866920153e-06,
      "loss": 1.7228,
      "step": 342
    },
    {
      "epoch": 0.8650693568726355,
      "grad_norm": 9.340424537658691,
      "learning_rate": 5.728770595690748e-06,
      "loss": 1.7222,
      "step": 343
    },
    {
      "epoch": 0.8675914249684742,
      "grad_norm": 8.790074348449707,
      "learning_rate": 5.716096324461344e-06,
      "loss": 1.7115,
      "step": 344
    },
    {
      "epoch": 0.8701134930643127,
      "grad_norm": 9.338977813720703,
      "learning_rate": 5.703422053231939e-06,
      "loss": 1.909,
      "step": 345
    },
    {
      "epoch": 0.8726355611601513,
      "grad_norm": 9.146921157836914,
      "learning_rate": 5.6907477820025355e-06,
      "loss": 1.7764,
      "step": 346
    },
    {
      "epoch": 0.8751576292559899,
      "grad_norm": 9.265887260437012,
      "learning_rate": 5.678073510773131e-06,
      "loss": 1.8936,
      "step": 347
    },
    {
      "epoch": 0.8776796973518285,
      "grad_norm": 8.695322036743164,
      "learning_rate": 5.665399239543726e-06,
      "loss": 1.7859,
      "step": 348
    },
    {
      "epoch": 0.880201765447667,
      "grad_norm": 8.807083129882812,
      "learning_rate": 5.652724968314323e-06,
      "loss": 1.6628,
      "step": 349
    },
    {
      "epoch": 0.8827238335435057,
      "grad_norm": 8.45325756072998,
      "learning_rate": 5.640050697084918e-06,
      "loss": 1.8382,
      "step": 350
    },
    {
      "epoch": 0.8827238335435057,
      "eval_loss": 1.7664289474487305,
      "eval_runtime": 19.2628,
      "eval_samples_per_second": 36.599,
      "eval_steps_per_second": 18.326,
      "step": 350
    },
    {
      "epoch": 0.8852459016393442,
      "grad_norm": 8.857064247131348,
      "learning_rate": 5.627376425855514e-06,
      "loss": 1.8234,
      "step": 351
    },
    {
      "epoch": 0.8877679697351829,
      "grad_norm": 8.959634780883789,
      "learning_rate": 5.61470215462611e-06,
      "loss": 1.8097,
      "step": 352
    },
    {
      "epoch": 0.8902900378310215,
      "grad_norm": 8.42651653289795,
      "learning_rate": 5.602027883396706e-06,
      "loss": 1.7802,
      "step": 353
    },
    {
      "epoch": 0.89281210592686,
      "grad_norm": 8.60803508758545,
      "learning_rate": 5.589353612167301e-06,
      "loss": 1.9292,
      "step": 354
    },
    {
      "epoch": 0.8953341740226987,
      "grad_norm": 9.581759452819824,
      "learning_rate": 5.576679340937896e-06,
      "loss": 1.9021,
      "step": 355
    },
    {
      "epoch": 0.8978562421185372,
      "grad_norm": 9.233514785766602,
      "learning_rate": 5.564005069708492e-06,
      "loss": 1.9196,
      "step": 356
    },
    {
      "epoch": 0.9003783102143758,
      "grad_norm": 8.68662166595459,
      "learning_rate": 5.5513307984790876e-06,
      "loss": 1.8241,
      "step": 357
    },
    {
      "epoch": 0.9029003783102144,
      "grad_norm": 9.061554908752441,
      "learning_rate": 5.538656527249684e-06,
      "loss": 1.7981,
      "step": 358
    },
    {
      "epoch": 0.905422446406053,
      "grad_norm": 9.19786548614502,
      "learning_rate": 5.525982256020279e-06,
      "loss": 1.8992,
      "step": 359
    },
    {
      "epoch": 0.9079445145018915,
      "grad_norm": 9.01632308959961,
      "learning_rate": 5.513307984790876e-06,
      "loss": 1.6893,
      "step": 360
    },
    {
      "epoch": 0.9104665825977302,
      "grad_norm": 9.247430801391602,
      "learning_rate": 5.50063371356147e-06,
      "loss": 1.9285,
      "step": 361
    },
    {
      "epoch": 0.9129886506935687,
      "grad_norm": 9.057443618774414,
      "learning_rate": 5.4879594423320656e-06,
      "loss": 1.9432,
      "step": 362
    },
    {
      "epoch": 0.9155107187894073,
      "grad_norm": 8.915752410888672,
      "learning_rate": 5.4752851711026625e-06,
      "loss": 1.6782,
      "step": 363
    },
    {
      "epoch": 0.9180327868852459,
      "grad_norm": 8.549680709838867,
      "learning_rate": 5.462610899873258e-06,
      "loss": 1.7759,
      "step": 364
    },
    {
      "epoch": 0.9205548549810845,
      "grad_norm": 9.016446113586426,
      "learning_rate": 5.449936628643854e-06,
      "loss": 1.834,
      "step": 365
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 8.798394203186035,
      "learning_rate": 5.437262357414449e-06,
      "loss": 1.808,
      "step": 366
    },
    {
      "epoch": 0.9255989911727617,
      "grad_norm": 8.604814529418945,
      "learning_rate": 5.424588086185045e-06,
      "loss": 1.6324,
      "step": 367
    },
    {
      "epoch": 0.9281210592686002,
      "grad_norm": 9.275598526000977,
      "learning_rate": 5.4119138149556405e-06,
      "loss": 1.7661,
      "step": 368
    },
    {
      "epoch": 0.9306431273644389,
      "grad_norm": 8.95068645477295,
      "learning_rate": 5.399239543726236e-06,
      "loss": 1.8052,
      "step": 369
    },
    {
      "epoch": 0.9331651954602774,
      "grad_norm": 9.022995948791504,
      "learning_rate": 5.386565272496832e-06,
      "loss": 1.7969,
      "step": 370
    },
    {
      "epoch": 0.935687263556116,
      "grad_norm": 9.088318824768066,
      "learning_rate": 5.373891001267427e-06,
      "loss": 1.8285,
      "step": 371
    },
    {
      "epoch": 0.9382093316519546,
      "grad_norm": 8.817545890808105,
      "learning_rate": 5.361216730038023e-06,
      "loss": 1.8666,
      "step": 372
    },
    {
      "epoch": 0.9407313997477932,
      "grad_norm": 9.669781684875488,
      "learning_rate": 5.3485424588086185e-06,
      "loss": 1.7006,
      "step": 373
    },
    {
      "epoch": 0.9432534678436317,
      "grad_norm": 9.549946784973145,
      "learning_rate": 5.3358681875792155e-06,
      "loss": 1.8659,
      "step": 374
    },
    {
      "epoch": 0.9457755359394704,
      "grad_norm": 9.192364692687988,
      "learning_rate": 5.323193916349811e-06,
      "loss": 1.925,
      "step": 375
    },
    {
      "epoch": 0.9482976040353089,
      "grad_norm": 8.788030624389648,
      "learning_rate": 5.310519645120405e-06,
      "loss": 1.8452,
      "step": 376
    },
    {
      "epoch": 0.9508196721311475,
      "grad_norm": 8.969650268554688,
      "learning_rate": 5.297845373891002e-06,
      "loss": 2.0042,
      "step": 377
    },
    {
      "epoch": 0.9533417402269861,
      "grad_norm": 9.061970710754395,
      "learning_rate": 5.285171102661597e-06,
      "loss": 1.5893,
      "step": 378
    },
    {
      "epoch": 0.9558638083228247,
      "grad_norm": 8.679773330688477,
      "learning_rate": 5.2724968314321934e-06,
      "loss": 1.8406,
      "step": 379
    },
    {
      "epoch": 0.9583858764186634,
      "grad_norm": 8.501445770263672,
      "learning_rate": 5.259822560202789e-06,
      "loss": 1.8087,
      "step": 380
    },
    {
      "epoch": 0.9609079445145019,
      "grad_norm": 8.920570373535156,
      "learning_rate": 5.247148288973385e-06,
      "loss": 1.817,
      "step": 381
    },
    {
      "epoch": 0.9634300126103404,
      "grad_norm": 9.80816650390625,
      "learning_rate": 5.23447401774398e-06,
      "loss": 1.8126,
      "step": 382
    },
    {
      "epoch": 0.9659520807061791,
      "grad_norm": 9.322412490844727,
      "learning_rate": 5.221799746514575e-06,
      "loss": 1.9843,
      "step": 383
    },
    {
      "epoch": 0.9684741488020177,
      "grad_norm": 8.808110237121582,
      "learning_rate": 5.2091254752851714e-06,
      "loss": 1.7095,
      "step": 384
    },
    {
      "epoch": 0.9709962168978562,
      "grad_norm": 8.641688346862793,
      "learning_rate": 5.196451204055767e-06,
      "loss": 1.7606,
      "step": 385
    },
    {
      "epoch": 0.9735182849936949,
      "grad_norm": 9.103622436523438,
      "learning_rate": 5.183776932826363e-06,
      "loss": 1.9436,
      "step": 386
    },
    {
      "epoch": 0.9760403530895334,
      "grad_norm": 9.417160034179688,
      "learning_rate": 5.171102661596958e-06,
      "loss": 1.7759,
      "step": 387
    },
    {
      "epoch": 0.978562421185372,
      "grad_norm": 8.632150650024414,
      "learning_rate": 5.158428390367555e-06,
      "loss": 1.7394,
      "step": 388
    },
    {
      "epoch": 0.9810844892812106,
      "grad_norm": 8.486221313476562,
      "learning_rate": 5.14575411913815e-06,
      "loss": 1.7502,
      "step": 389
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 8.44924259185791,
      "learning_rate": 5.1330798479087455e-06,
      "loss": 1.8303,
      "step": 390
    },
    {
      "epoch": 0.9861286254728878,
      "grad_norm": 9.206375122070312,
      "learning_rate": 5.120405576679342e-06,
      "loss": 1.791,
      "step": 391
    },
    {
      "epoch": 0.9886506935687264,
      "grad_norm": 9.235477447509766,
      "learning_rate": 5.107731305449937e-06,
      "loss": 1.7277,
      "step": 392
    },
    {
      "epoch": 0.9911727616645649,
      "grad_norm": 8.926923751831055,
      "learning_rate": 5.095057034220533e-06,
      "loss": 1.8509,
      "step": 393
    },
    {
      "epoch": 0.9936948297604036,
      "grad_norm": 9.778203964233398,
      "learning_rate": 5.082382762991128e-06,
      "loss": 1.7962,
      "step": 394
    },
    {
      "epoch": 0.9962168978562421,
      "grad_norm": 9.287840843200684,
      "learning_rate": 5.069708491761724e-06,
      "loss": 1.8611,
      "step": 395
    },
    {
      "epoch": 0.9987389659520807,
      "grad_norm": 8.707663536071777,
      "learning_rate": 5.05703422053232e-06,
      "loss": 1.7496,
      "step": 396
    },
    {
      "epoch": 1.0,
      "grad_norm": 11.88062572479248,
      "learning_rate": 5.044359949302915e-06,
      "loss": 1.7475,
      "step": 397
    },
    {
      "epoch": 1.0025220680958387,
      "grad_norm": 8.590554237365723,
      "learning_rate": 5.031685678073511e-06,
      "loss": 1.7312,
      "step": 398
    },
    {
      "epoch": 1.005044136191677,
      "grad_norm": 8.355072021484375,
      "learning_rate": 5.019011406844106e-06,
      "loss": 1.5855,
      "step": 399
    },
    {
      "epoch": 1.0075662042875158,
      "grad_norm": 8.82670783996582,
      "learning_rate": 5.006337135614703e-06,
      "loss": 1.721,
      "step": 400
    },
    {
      "epoch": 1.0075662042875158,
      "eval_loss": 1.7607698440551758,
      "eval_runtime": 19.095,
      "eval_samples_per_second": 36.921,
      "eval_steps_per_second": 18.487,
      "step": 400
    },
    {
      "epoch": 1.0100882723833544,
      "grad_norm": 9.142245292663574,
      "learning_rate": 4.993662864385298e-06,
      "loss": 1.8552,
      "step": 401
    },
    {
      "epoch": 1.0126103404791928,
      "grad_norm": 8.749809265136719,
      "learning_rate": 4.980988593155894e-06,
      "loss": 1.8215,
      "step": 402
    },
    {
      "epoch": 1.0151324085750315,
      "grad_norm": 8.908941268920898,
      "learning_rate": 4.96831432192649e-06,
      "loss": 1.6916,
      "step": 403
    },
    {
      "epoch": 1.0176544766708702,
      "grad_norm": 8.895804405212402,
      "learning_rate": 4.955640050697085e-06,
      "loss": 1.7288,
      "step": 404
    },
    {
      "epoch": 1.0201765447667086,
      "grad_norm": 8.319515228271484,
      "learning_rate": 4.942965779467681e-06,
      "loss": 1.6982,
      "step": 405
    },
    {
      "epoch": 1.0226986128625473,
      "grad_norm": 8.311009407043457,
      "learning_rate": 4.9302915082382765e-06,
      "loss": 1.6861,
      "step": 406
    },
    {
      "epoch": 1.025220680958386,
      "grad_norm": 8.49014949798584,
      "learning_rate": 4.9176172370088726e-06,
      "loss": 1.7657,
      "step": 407
    },
    {
      "epoch": 1.0277427490542244,
      "grad_norm": 8.252015113830566,
      "learning_rate": 4.904942965779468e-06,
      "loss": 1.5509,
      "step": 408
    },
    {
      "epoch": 1.030264817150063,
      "grad_norm": 9.054285049438477,
      "learning_rate": 4.892268694550064e-06,
      "loss": 1.7749,
      "step": 409
    },
    {
      "epoch": 1.0327868852459017,
      "grad_norm": 9.403254508972168,
      "learning_rate": 4.879594423320659e-06,
      "loss": 1.6967,
      "step": 410
    },
    {
      "epoch": 1.0353089533417403,
      "grad_norm": 8.674240112304688,
      "learning_rate": 4.866920152091255e-06,
      "loss": 1.7625,
      "step": 411
    },
    {
      "epoch": 1.0378310214375788,
      "grad_norm": 9.050286293029785,
      "learning_rate": 4.8542458808618505e-06,
      "loss": 1.6583,
      "step": 412
    },
    {
      "epoch": 1.0403530895334174,
      "grad_norm": 8.864618301391602,
      "learning_rate": 4.841571609632447e-06,
      "loss": 1.594,
      "step": 413
    },
    {
      "epoch": 1.042875157629256,
      "grad_norm": 9.439994812011719,
      "learning_rate": 4.828897338403043e-06,
      "loss": 1.8638,
      "step": 414
    },
    {
      "epoch": 1.0453972257250945,
      "grad_norm": 8.543251037597656,
      "learning_rate": 4.816223067173638e-06,
      "loss": 1.7848,
      "step": 415
    },
    {
      "epoch": 1.0479192938209332,
      "grad_norm": 9.326902389526367,
      "learning_rate": 4.803548795944233e-06,
      "loss": 1.6933,
      "step": 416
    },
    {
      "epoch": 1.0504413619167718,
      "grad_norm": 9.385411262512207,
      "learning_rate": 4.790874524714829e-06,
      "loss": 1.6518,
      "step": 417
    },
    {
      "epoch": 1.0529634300126103,
      "grad_norm": 8.558259963989258,
      "learning_rate": 4.778200253485425e-06,
      "loss": 1.778,
      "step": 418
    },
    {
      "epoch": 1.055485498108449,
      "grad_norm": 9.476303100585938,
      "learning_rate": 4.765525982256021e-06,
      "loss": 1.8428,
      "step": 419
    },
    {
      "epoch": 1.0580075662042876,
      "grad_norm": 9.65798282623291,
      "learning_rate": 4.752851711026617e-06,
      "loss": 1.7092,
      "step": 420
    },
    {
      "epoch": 1.060529634300126,
      "grad_norm": 9.509737014770508,
      "learning_rate": 4.740177439797212e-06,
      "loss": 1.8781,
      "step": 421
    },
    {
      "epoch": 1.0630517023959647,
      "grad_norm": 8.58066177368164,
      "learning_rate": 4.727503168567808e-06,
      "loss": 1.5682,
      "step": 422
    },
    {
      "epoch": 1.0655737704918034,
      "grad_norm": 9.193934440612793,
      "learning_rate": 4.7148288973384035e-06,
      "loss": 1.8033,
      "step": 423
    },
    {
      "epoch": 1.0680958385876418,
      "grad_norm": 9.231853485107422,
      "learning_rate": 4.702154626108999e-06,
      "loss": 1.5837,
      "step": 424
    },
    {
      "epoch": 1.0706179066834804,
      "grad_norm": 9.041360855102539,
      "learning_rate": 4.689480354879595e-06,
      "loss": 1.7435,
      "step": 425
    },
    {
      "epoch": 1.073139974779319,
      "grad_norm": 9.335003852844238,
      "learning_rate": 4.67680608365019e-06,
      "loss": 1.8,
      "step": 426
    },
    {
      "epoch": 1.0756620428751575,
      "grad_norm": 9.047548294067383,
      "learning_rate": 4.664131812420786e-06,
      "loss": 1.7433,
      "step": 427
    },
    {
      "epoch": 1.0781841109709962,
      "grad_norm": 9.200716018676758,
      "learning_rate": 4.651457541191382e-06,
      "loss": 1.6625,
      "step": 428
    },
    {
      "epoch": 1.0807061790668349,
      "grad_norm": 9.45468521118164,
      "learning_rate": 4.638783269961978e-06,
      "loss": 1.762,
      "step": 429
    },
    {
      "epoch": 1.0832282471626733,
      "grad_norm": 9.115446090698242,
      "learning_rate": 4.626108998732573e-06,
      "loss": 1.7267,
      "step": 430
    },
    {
      "epoch": 1.085750315258512,
      "grad_norm": 9.324665069580078,
      "learning_rate": 4.613434727503169e-06,
      "loss": 1.5666,
      "step": 431
    },
    {
      "epoch": 1.0882723833543506,
      "grad_norm": 9.168367385864258,
      "learning_rate": 4.600760456273764e-06,
      "loss": 1.6286,
      "step": 432
    },
    {
      "epoch": 1.090794451450189,
      "grad_norm": 9.02181625366211,
      "learning_rate": 4.58808618504436e-06,
      "loss": 1.7096,
      "step": 433
    },
    {
      "epoch": 1.0933165195460277,
      "grad_norm": 9.085856437683105,
      "learning_rate": 4.575411913814956e-06,
      "loss": 1.6744,
      "step": 434
    },
    {
      "epoch": 1.0958385876418664,
      "grad_norm": 9.598065376281738,
      "learning_rate": 4.562737642585552e-06,
      "loss": 1.6991,
      "step": 435
    },
    {
      "epoch": 1.098360655737705,
      "grad_norm": 9.274950981140137,
      "learning_rate": 4.550063371356148e-06,
      "loss": 1.6642,
      "step": 436
    },
    {
      "epoch": 1.1008827238335435,
      "grad_norm": 9.550910949707031,
      "learning_rate": 4.537389100126743e-06,
      "loss": 1.6957,
      "step": 437
    },
    {
      "epoch": 1.1034047919293821,
      "grad_norm": 8.931519508361816,
      "learning_rate": 4.524714828897338e-06,
      "loss": 1.7028,
      "step": 438
    },
    {
      "epoch": 1.1059268600252208,
      "grad_norm": 9.690319061279297,
      "learning_rate": 4.512040557667934e-06,
      "loss": 1.7442,
      "step": 439
    },
    {
      "epoch": 1.1084489281210592,
      "grad_norm": 8.857930183410645,
      "learning_rate": 4.4993662864385305e-06,
      "loss": 1.741,
      "step": 440
    },
    {
      "epoch": 1.1109709962168979,
      "grad_norm": 8.596811294555664,
      "learning_rate": 4.486692015209126e-06,
      "loss": 1.667,
      "step": 441
    },
    {
      "epoch": 1.1134930643127365,
      "grad_norm": 9.143899917602539,
      "learning_rate": 4.474017743979722e-06,
      "loss": 1.7344,
      "step": 442
    },
    {
      "epoch": 1.116015132408575,
      "grad_norm": 8.82170581817627,
      "learning_rate": 4.461343472750317e-06,
      "loss": 1.6738,
      "step": 443
    },
    {
      "epoch": 1.1185372005044136,
      "grad_norm": 9.04935359954834,
      "learning_rate": 4.448669201520912e-06,
      "loss": 1.8386,
      "step": 444
    },
    {
      "epoch": 1.1210592686002523,
      "grad_norm": 9.859052658081055,
      "learning_rate": 4.4359949302915085e-06,
      "loss": 1.8947,
      "step": 445
    },
    {
      "epoch": 1.1235813366960907,
      "grad_norm": 8.289063453674316,
      "learning_rate": 4.423320659062104e-06,
      "loss": 1.469,
      "step": 446
    },
    {
      "epoch": 1.1261034047919294,
      "grad_norm": 9.797428131103516,
      "learning_rate": 4.4106463878327e-06,
      "loss": 1.6028,
      "step": 447
    },
    {
      "epoch": 1.128625472887768,
      "grad_norm": 9.132006645202637,
      "learning_rate": 4.397972116603296e-06,
      "loss": 1.6548,
      "step": 448
    },
    {
      "epoch": 1.1311475409836065,
      "grad_norm": 9.630876541137695,
      "learning_rate": 4.385297845373891e-06,
      "loss": 1.5891,
      "step": 449
    },
    {
      "epoch": 1.1336696090794451,
      "grad_norm": 9.078959465026855,
      "learning_rate": 4.372623574144487e-06,
      "loss": 1.6075,
      "step": 450
    },
    {
      "epoch": 1.1336696090794451,
      "eval_loss": 1.7592146396636963,
      "eval_runtime": 18.9658,
      "eval_samples_per_second": 37.172,
      "eval_steps_per_second": 18.612,
      "step": 450
    },
    {
      "epoch": 1.1361916771752838,
      "grad_norm": 9.491748809814453,
      "learning_rate": 4.359949302915083e-06,
      "loss": 1.7291,
      "step": 451
    },
    {
      "epoch": 1.1387137452711222,
      "grad_norm": 9.501943588256836,
      "learning_rate": 4.347275031685678e-06,
      "loss": 1.6517,
      "step": 452
    },
    {
      "epoch": 1.141235813366961,
      "grad_norm": 8.992663383483887,
      "learning_rate": 4.334600760456274e-06,
      "loss": 1.7788,
      "step": 453
    },
    {
      "epoch": 1.1437578814627996,
      "grad_norm": 9.186774253845215,
      "learning_rate": 4.32192648922687e-06,
      "loss": 1.8066,
      "step": 454
    },
    {
      "epoch": 1.146279949558638,
      "grad_norm": 8.884696006774902,
      "learning_rate": 4.309252217997465e-06,
      "loss": 1.5364,
      "step": 455
    },
    {
      "epoch": 1.1488020176544766,
      "grad_norm": 8.84166431427002,
      "learning_rate": 4.2965779467680614e-06,
      "loss": 1.6724,
      "step": 456
    },
    {
      "epoch": 1.1513240857503153,
      "grad_norm": 9.553184509277344,
      "learning_rate": 4.283903675538657e-06,
      "loss": 1.6796,
      "step": 457
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 9.203774452209473,
      "learning_rate": 4.271229404309253e-06,
      "loss": 1.7681,
      "step": 458
    },
    {
      "epoch": 1.1563682219419924,
      "grad_norm": 9.575316429138184,
      "learning_rate": 4.258555133079848e-06,
      "loss": 1.8916,
      "step": 459
    },
    {
      "epoch": 1.158890290037831,
      "grad_norm": 9.290874481201172,
      "learning_rate": 4.245880861850444e-06,
      "loss": 1.5212,
      "step": 460
    },
    {
      "epoch": 1.1614123581336697,
      "grad_norm": 9.912353515625,
      "learning_rate": 4.2332065906210394e-06,
      "loss": 1.6978,
      "step": 461
    },
    {
      "epoch": 1.1639344262295082,
      "grad_norm": 8.909394264221191,
      "learning_rate": 4.2205323193916355e-06,
      "loss": 1.4679,
      "step": 462
    },
    {
      "epoch": 1.1664564943253468,
      "grad_norm": 9.081424713134766,
      "learning_rate": 4.207858048162231e-06,
      "loss": 1.6106,
      "step": 463
    },
    {
      "epoch": 1.1689785624211853,
      "grad_norm": 9.273894309997559,
      "learning_rate": 4.195183776932827e-06,
      "loss": 1.7175,
      "step": 464
    },
    {
      "epoch": 1.171500630517024,
      "grad_norm": 9.495081901550293,
      "learning_rate": 4.182509505703423e-06,
      "loss": 1.6843,
      "step": 465
    },
    {
      "epoch": 1.1740226986128626,
      "grad_norm": 9.094228744506836,
      "learning_rate": 4.169835234474017e-06,
      "loss": 1.5378,
      "step": 466
    },
    {
      "epoch": 1.1765447667087012,
      "grad_norm": 8.924116134643555,
      "learning_rate": 4.1571609632446135e-06,
      "loss": 1.6018,
      "step": 467
    },
    {
      "epoch": 1.1790668348045397,
      "grad_norm": 9.25060749053955,
      "learning_rate": 4.14448669201521e-06,
      "loss": 1.6122,
      "step": 468
    },
    {
      "epoch": 1.1815889029003783,
      "grad_norm": 8.897881507873535,
      "learning_rate": 4.131812420785805e-06,
      "loss": 1.6587,
      "step": 469
    },
    {
      "epoch": 1.184110970996217,
      "grad_norm": 10.346816062927246,
      "learning_rate": 4.119138149556401e-06,
      "loss": 1.7723,
      "step": 470
    },
    {
      "epoch": 1.1866330390920554,
      "grad_norm": 9.834297180175781,
      "learning_rate": 4.106463878326996e-06,
      "loss": 1.8203,
      "step": 471
    },
    {
      "epoch": 1.189155107187894,
      "grad_norm": 9.415582656860352,
      "learning_rate": 4.093789607097592e-06,
      "loss": 1.7475,
      "step": 472
    },
    {
      "epoch": 1.1916771752837327,
      "grad_norm": 9.48161792755127,
      "learning_rate": 4.081115335868188e-06,
      "loss": 1.8166,
      "step": 473
    },
    {
      "epoch": 1.1941992433795712,
      "grad_norm": 10.484070777893066,
      "learning_rate": 4.068441064638784e-06,
      "loss": 1.9049,
      "step": 474
    },
    {
      "epoch": 1.1967213114754098,
      "grad_norm": 8.581873893737793,
      "learning_rate": 4.055766793409379e-06,
      "loss": 1.4675,
      "step": 475
    },
    {
      "epoch": 1.1992433795712485,
      "grad_norm": 8.851600646972656,
      "learning_rate": 4.043092522179975e-06,
      "loss": 1.7048,
      "step": 476
    },
    {
      "epoch": 1.201765447667087,
      "grad_norm": 9.339808464050293,
      "learning_rate": 4.03041825095057e-06,
      "loss": 1.6251,
      "step": 477
    },
    {
      "epoch": 1.2042875157629256,
      "grad_norm": 9.338892936706543,
      "learning_rate": 4.0177439797211665e-06,
      "loss": 1.7128,
      "step": 478
    },
    {
      "epoch": 1.2068095838587642,
      "grad_norm": 10.172554016113281,
      "learning_rate": 4.0050697084917626e-06,
      "loss": 1.8141,
      "step": 479
    },
    {
      "epoch": 1.2093316519546027,
      "grad_norm": 9.7528657913208,
      "learning_rate": 3.992395437262358e-06,
      "loss": 1.7939,
      "step": 480
    },
    {
      "epoch": 1.2118537200504413,
      "grad_norm": 9.527520179748535,
      "learning_rate": 3.979721166032953e-06,
      "loss": 1.6164,
      "step": 481
    },
    {
      "epoch": 1.21437578814628,
      "grad_norm": 9.281045913696289,
      "learning_rate": 3.967046894803549e-06,
      "loss": 1.7353,
      "step": 482
    },
    {
      "epoch": 1.2168978562421184,
      "grad_norm": 9.286741256713867,
      "learning_rate": 3.9543726235741444e-06,
      "loss": 1.6235,
      "step": 483
    },
    {
      "epoch": 1.219419924337957,
      "grad_norm": 8.995189666748047,
      "learning_rate": 3.9416983523447406e-06,
      "loss": 1.8666,
      "step": 484
    },
    {
      "epoch": 1.2219419924337958,
      "grad_norm": 9.787041664123535,
      "learning_rate": 3.929024081115337e-06,
      "loss": 1.5452,
      "step": 485
    },
    {
      "epoch": 1.2244640605296344,
      "grad_norm": 9.66303825378418,
      "learning_rate": 3.916349809885932e-06,
      "loss": 1.8347,
      "step": 486
    },
    {
      "epoch": 1.2269861286254728,
      "grad_norm": 9.510695457458496,
      "learning_rate": 3.903675538656528e-06,
      "loss": 1.7819,
      "step": 487
    },
    {
      "epoch": 1.2295081967213115,
      "grad_norm": 9.097454071044922,
      "learning_rate": 3.891001267427123e-06,
      "loss": 1.5485,
      "step": 488
    },
    {
      "epoch": 1.23203026481715,
      "grad_norm": 9.51233959197998,
      "learning_rate": 3.8783269961977185e-06,
      "loss": 1.5994,
      "step": 489
    },
    {
      "epoch": 1.2345523329129886,
      "grad_norm": 9.643257141113281,
      "learning_rate": 3.865652724968315e-06,
      "loss": 1.8419,
      "step": 490
    },
    {
      "epoch": 1.2370744010088273,
      "grad_norm": 9.66042709350586,
      "learning_rate": 3.85297845373891e-06,
      "loss": 1.6727,
      "step": 491
    },
    {
      "epoch": 1.239596469104666,
      "grad_norm": 10.595549583435059,
      "learning_rate": 3.840304182509506e-06,
      "loss": 1.8618,
      "step": 492
    },
    {
      "epoch": 1.2421185372005044,
      "grad_norm": 9.391014099121094,
      "learning_rate": 3.827629911280102e-06,
      "loss": 1.7063,
      "step": 493
    },
    {
      "epoch": 1.244640605296343,
      "grad_norm": 9.038019180297852,
      "learning_rate": 3.814955640050697e-06,
      "loss": 1.6304,
      "step": 494
    },
    {
      "epoch": 1.2471626733921817,
      "grad_norm": 8.65124225616455,
      "learning_rate": 3.8022813688212926e-06,
      "loss": 1.7031,
      "step": 495
    },
    {
      "epoch": 1.2496847414880201,
      "grad_norm": 9.305266380310059,
      "learning_rate": 3.7896070975918887e-06,
      "loss": 1.8554,
      "step": 496
    },
    {
      "epoch": 1.2522068095838588,
      "grad_norm": 9.953511238098145,
      "learning_rate": 3.7769328263624844e-06,
      "loss": 1.7896,
      "step": 497
    },
    {
      "epoch": 1.2547288776796974,
      "grad_norm": 9.709404945373535,
      "learning_rate": 3.76425855513308e-06,
      "loss": 1.7913,
      "step": 498
    },
    {
      "epoch": 1.2572509457755359,
      "grad_norm": 9.037952423095703,
      "learning_rate": 3.751584283903676e-06,
      "loss": 1.6428,
      "step": 499
    },
    {
      "epoch": 1.2597730138713745,
      "grad_norm": 9.028722763061523,
      "learning_rate": 3.7389100126742715e-06,
      "loss": 1.6217,
      "step": 500
    },
    {
      "epoch": 1.2597730138713745,
      "eval_loss": 1.7565970420837402,
      "eval_runtime": 19.3997,
      "eval_samples_per_second": 36.341,
      "eval_steps_per_second": 18.196,
      "step": 500
    },
    {
      "epoch": 1.2622950819672132,
      "grad_norm": 10.283693313598633,
      "learning_rate": 3.7262357414448676e-06,
      "loss": 1.6903,
      "step": 501
    },
    {
      "epoch": 1.2648171500630516,
      "grad_norm": 9.808420181274414,
      "learning_rate": 3.713561470215463e-06,
      "loss": 1.6338,
      "step": 502
    },
    {
      "epoch": 1.2673392181588903,
      "grad_norm": 9.481460571289062,
      "learning_rate": 3.7008871989860585e-06,
      "loss": 1.6287,
      "step": 503
    },
    {
      "epoch": 1.269861286254729,
      "grad_norm": 9.095833778381348,
      "learning_rate": 3.688212927756654e-06,
      "loss": 1.6582,
      "step": 504
    },
    {
      "epoch": 1.2723833543505676,
      "grad_norm": 9.719803810119629,
      "learning_rate": 3.67553865652725e-06,
      "loss": 1.7219,
      "step": 505
    },
    {
      "epoch": 1.274905422446406,
      "grad_norm": 9.337441444396973,
      "learning_rate": 3.6628643852978456e-06,
      "loss": 1.6678,
      "step": 506
    },
    {
      "epoch": 1.2774274905422447,
      "grad_norm": 9.489283561706543,
      "learning_rate": 3.6501901140684417e-06,
      "loss": 1.6106,
      "step": 507
    },
    {
      "epoch": 1.2799495586380831,
      "grad_norm": 9.249103546142578,
      "learning_rate": 3.6375158428390374e-06,
      "loss": 1.5671,
      "step": 508
    },
    {
      "epoch": 1.2824716267339218,
      "grad_norm": 9.883663177490234,
      "learning_rate": 3.624841571609633e-06,
      "loss": 1.6972,
      "step": 509
    },
    {
      "epoch": 1.2849936948297604,
      "grad_norm": 9.603671073913574,
      "learning_rate": 3.6121673003802283e-06,
      "loss": 1.6824,
      "step": 510
    },
    {
      "epoch": 1.287515762925599,
      "grad_norm": 9.937875747680664,
      "learning_rate": 3.599493029150824e-06,
      "loss": 1.6317,
      "step": 511
    },
    {
      "epoch": 1.2900378310214375,
      "grad_norm": 9.144148826599121,
      "learning_rate": 3.5868187579214197e-06,
      "loss": 1.5606,
      "step": 512
    },
    {
      "epoch": 1.2925598991172762,
      "grad_norm": 9.559479713439941,
      "learning_rate": 3.5741444866920154e-06,
      "loss": 1.7815,
      "step": 513
    },
    {
      "epoch": 1.2950819672131146,
      "grad_norm": 10.421140670776367,
      "learning_rate": 3.5614702154626115e-06,
      "loss": 1.6123,
      "step": 514
    },
    {
      "epoch": 1.2976040353089533,
      "grad_norm": 10.148019790649414,
      "learning_rate": 3.548795944233207e-06,
      "loss": 1.6868,
      "step": 515
    },
    {
      "epoch": 1.300126103404792,
      "grad_norm": 9.469623565673828,
      "learning_rate": 3.536121673003803e-06,
      "loss": 1.7786,
      "step": 516
    },
    {
      "epoch": 1.3026481715006306,
      "grad_norm": 9.549322128295898,
      "learning_rate": 3.523447401774398e-06,
      "loss": 1.6055,
      "step": 517
    },
    {
      "epoch": 1.305170239596469,
      "grad_norm": 9.64495849609375,
      "learning_rate": 3.5107731305449938e-06,
      "loss": 1.8256,
      "step": 518
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 9.64932632446289,
      "learning_rate": 3.4980988593155894e-06,
      "loss": 1.7845,
      "step": 519
    },
    {
      "epoch": 1.3102143757881461,
      "grad_norm": 9.426970481872559,
      "learning_rate": 3.485424588086185e-06,
      "loss": 1.6563,
      "step": 520
    },
    {
      "epoch": 1.3127364438839848,
      "grad_norm": 10.129924774169922,
      "learning_rate": 3.4727503168567812e-06,
      "loss": 1.6114,
      "step": 521
    },
    {
      "epoch": 1.3152585119798235,
      "grad_norm": 9.599336624145508,
      "learning_rate": 3.460076045627377e-06,
      "loss": 1.7117,
      "step": 522
    },
    {
      "epoch": 1.3177805800756621,
      "grad_norm": 9.220215797424316,
      "learning_rate": 3.4474017743979726e-06,
      "loss": 1.756,
      "step": 523
    },
    {
      "epoch": 1.3203026481715006,
      "grad_norm": 10.082670211791992,
      "learning_rate": 3.434727503168568e-06,
      "loss": 1.8408,
      "step": 524
    },
    {
      "epoch": 1.3228247162673392,
      "grad_norm": 9.145997047424316,
      "learning_rate": 3.4220532319391635e-06,
      "loss": 1.6742,
      "step": 525
    },
    {
      "epoch": 1.3253467843631779,
      "grad_norm": 9.069123268127441,
      "learning_rate": 3.4093789607097592e-06,
      "loss": 1.3032,
      "step": 526
    },
    {
      "epoch": 1.3278688524590163,
      "grad_norm": 10.052807807922363,
      "learning_rate": 3.3967046894803553e-06,
      "loss": 1.7911,
      "step": 527
    },
    {
      "epoch": 1.330390920554855,
      "grad_norm": 9.340625762939453,
      "learning_rate": 3.384030418250951e-06,
      "loss": 1.5824,
      "step": 528
    },
    {
      "epoch": 1.3329129886506936,
      "grad_norm": 9.335938453674316,
      "learning_rate": 3.3713561470215467e-06,
      "loss": 1.6684,
      "step": 529
    },
    {
      "epoch": 1.3354350567465323,
      "grad_norm": 9.16378402709961,
      "learning_rate": 3.3586818757921424e-06,
      "loss": 1.651,
      "step": 530
    },
    {
      "epoch": 1.3379571248423707,
      "grad_norm": 8.72439193725586,
      "learning_rate": 3.3460076045627376e-06,
      "loss": 1.6884,
      "step": 531
    },
    {
      "epoch": 1.3404791929382094,
      "grad_norm": 10.607090950012207,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.6719,
      "step": 532
    },
    {
      "epoch": 1.3430012610340478,
      "grad_norm": 9.636138916015625,
      "learning_rate": 3.320659062103929e-06,
      "loss": 1.5877,
      "step": 533
    },
    {
      "epoch": 1.3455233291298865,
      "grad_norm": 9.962631225585938,
      "learning_rate": 3.307984790874525e-06,
      "loss": 1.6186,
      "step": 534
    },
    {
      "epoch": 1.3480453972257251,
      "grad_norm": 9.056344032287598,
      "learning_rate": 3.295310519645121e-06,
      "loss": 1.6214,
      "step": 535
    },
    {
      "epoch": 1.3505674653215638,
      "grad_norm": 9.709521293640137,
      "learning_rate": 3.2826362484157165e-06,
      "loss": 1.649,
      "step": 536
    },
    {
      "epoch": 1.3530895334174022,
      "grad_norm": 9.75629711151123,
      "learning_rate": 3.269961977186312e-06,
      "loss": 1.7079,
      "step": 537
    },
    {
      "epoch": 1.355611601513241,
      "grad_norm": 9.115280151367188,
      "learning_rate": 3.257287705956908e-06,
      "loss": 1.6227,
      "step": 538
    },
    {
      "epoch": 1.3581336696090793,
      "grad_norm": 10.036097526550293,
      "learning_rate": 3.244613434727503e-06,
      "loss": 1.6803,
      "step": 539
    },
    {
      "epoch": 1.360655737704918,
      "grad_norm": 8.939905166625977,
      "learning_rate": 3.2319391634980988e-06,
      "loss": 1.5827,
      "step": 540
    },
    {
      "epoch": 1.3631778058007566,
      "grad_norm": 9.506304740905762,
      "learning_rate": 3.219264892268695e-06,
      "loss": 1.6116,
      "step": 541
    },
    {
      "epoch": 1.3656998738965953,
      "grad_norm": 9.476072311401367,
      "learning_rate": 3.2065906210392906e-06,
      "loss": 1.7412,
      "step": 542
    },
    {
      "epoch": 1.3682219419924337,
      "grad_norm": 9.473388671875,
      "learning_rate": 3.1939163498098863e-06,
      "loss": 1.6695,
      "step": 543
    },
    {
      "epoch": 1.3707440100882724,
      "grad_norm": 9.427637100219727,
      "learning_rate": 3.181242078580482e-06,
      "loss": 1.5057,
      "step": 544
    },
    {
      "epoch": 1.3732660781841108,
      "grad_norm": 9.60339069366455,
      "learning_rate": 3.1685678073510776e-06,
      "loss": 1.7181,
      "step": 545
    },
    {
      "epoch": 1.3757881462799495,
      "grad_norm": 9.41893196105957,
      "learning_rate": 3.155893536121673e-06,
      "loss": 1.6774,
      "step": 546
    },
    {
      "epoch": 1.3783102143757882,
      "grad_norm": 9.386926651000977,
      "learning_rate": 3.143219264892269e-06,
      "loss": 1.8136,
      "step": 547
    },
    {
      "epoch": 1.3808322824716268,
      "grad_norm": 9.684150695800781,
      "learning_rate": 3.1305449936628647e-06,
      "loss": 1.6237,
      "step": 548
    },
    {
      "epoch": 1.3833543505674653,
      "grad_norm": 9.075904846191406,
      "learning_rate": 3.1178707224334604e-06,
      "loss": 1.7711,
      "step": 549
    },
    {
      "epoch": 1.385876418663304,
      "grad_norm": 9.657439231872559,
      "learning_rate": 3.105196451204056e-06,
      "loss": 1.6404,
      "step": 550
    },
    {
      "epoch": 1.385876418663304,
      "eval_loss": 1.7535345554351807,
      "eval_runtime": 19.0004,
      "eval_samples_per_second": 37.104,
      "eval_steps_per_second": 18.579,
      "step": 550
    },
    {
      "epoch": 1.3883984867591426,
      "grad_norm": 9.663516998291016,
      "learning_rate": 3.0925221799746517e-06,
      "loss": 1.6659,
      "step": 551
    },
    {
      "epoch": 1.390920554854981,
      "grad_norm": 9.979103088378906,
      "learning_rate": 3.079847908745248e-06,
      "loss": 1.8235,
      "step": 552
    },
    {
      "epoch": 1.3934426229508197,
      "grad_norm": 9.544889450073242,
      "learning_rate": 3.0671736375158427e-06,
      "loss": 1.5428,
      "step": 553
    },
    {
      "epoch": 1.3959646910466583,
      "grad_norm": 9.513182640075684,
      "learning_rate": 3.0544993662864388e-06,
      "loss": 1.8359,
      "step": 554
    },
    {
      "epoch": 1.398486759142497,
      "grad_norm": 9.235311508178711,
      "learning_rate": 3.0418250950570345e-06,
      "loss": 1.6501,
      "step": 555
    },
    {
      "epoch": 1.4010088272383354,
      "grad_norm": 9.953255653381348,
      "learning_rate": 3.02915082382763e-06,
      "loss": 1.6967,
      "step": 556
    },
    {
      "epoch": 1.403530895334174,
      "grad_norm": 9.68874740600586,
      "learning_rate": 3.016476552598226e-06,
      "loss": 1.481,
      "step": 557
    },
    {
      "epoch": 1.4060529634300125,
      "grad_norm": 9.845030784606934,
      "learning_rate": 3.0038022813688215e-06,
      "loss": 1.8484,
      "step": 558
    },
    {
      "epoch": 1.4085750315258512,
      "grad_norm": 8.639726638793945,
      "learning_rate": 2.9911280101394176e-06,
      "loss": 1.5915,
      "step": 559
    },
    {
      "epoch": 1.4110970996216898,
      "grad_norm": 9.13892650604248,
      "learning_rate": 2.978453738910013e-06,
      "loss": 1.8292,
      "step": 560
    },
    {
      "epoch": 1.4136191677175285,
      "grad_norm": 9.717473983764648,
      "learning_rate": 2.9657794676806085e-06,
      "loss": 1.7583,
      "step": 561
    },
    {
      "epoch": 1.416141235813367,
      "grad_norm": 9.23882007598877,
      "learning_rate": 2.9531051964512042e-06,
      "loss": 1.7036,
      "step": 562
    },
    {
      "epoch": 1.4186633039092056,
      "grad_norm": 10.016122817993164,
      "learning_rate": 2.9404309252218e-06,
      "loss": 1.8193,
      "step": 563
    },
    {
      "epoch": 1.421185372005044,
      "grad_norm": 9.860296249389648,
      "learning_rate": 2.9277566539923956e-06,
      "loss": 1.5949,
      "step": 564
    },
    {
      "epoch": 1.4237074401008827,
      "grad_norm": 9.54456901550293,
      "learning_rate": 2.9150823827629917e-06,
      "loss": 1.8371,
      "step": 565
    },
    {
      "epoch": 1.4262295081967213,
      "grad_norm": 9.442201614379883,
      "learning_rate": 2.9024081115335874e-06,
      "loss": 1.6691,
      "step": 566
    },
    {
      "epoch": 1.42875157629256,
      "grad_norm": 9.742538452148438,
      "learning_rate": 2.8897338403041826e-06,
      "loss": 1.7409,
      "step": 567
    },
    {
      "epoch": 1.4312736443883984,
      "grad_norm": 9.25894546508789,
      "learning_rate": 2.8770595690747783e-06,
      "loss": 1.7206,
      "step": 568
    },
    {
      "epoch": 1.433795712484237,
      "grad_norm": 9.535011291503906,
      "learning_rate": 2.864385297845374e-06,
      "loss": 1.5637,
      "step": 569
    },
    {
      "epoch": 1.4363177805800755,
      "grad_norm": 9.569571495056152,
      "learning_rate": 2.8517110266159697e-06,
      "loss": 1.5974,
      "step": 570
    },
    {
      "epoch": 1.4388398486759142,
      "grad_norm": 9.217652320861816,
      "learning_rate": 2.8390367553865654e-06,
      "loss": 1.8384,
      "step": 571
    },
    {
      "epoch": 1.4413619167717528,
      "grad_norm": 9.291997909545898,
      "learning_rate": 2.8263624841571615e-06,
      "loss": 1.709,
      "step": 572
    },
    {
      "epoch": 1.4438839848675915,
      "grad_norm": 9.234197616577148,
      "learning_rate": 2.813688212927757e-06,
      "loss": 1.694,
      "step": 573
    },
    {
      "epoch": 1.44640605296343,
      "grad_norm": 9.295293807983398,
      "learning_rate": 2.801013941698353e-06,
      "loss": 1.5444,
      "step": 574
    },
    {
      "epoch": 1.4489281210592686,
      "grad_norm": 9.15764045715332,
      "learning_rate": 2.788339670468948e-06,
      "loss": 1.6157,
      "step": 575
    },
    {
      "epoch": 1.4514501891551073,
      "grad_norm": 9.808813095092773,
      "learning_rate": 2.7756653992395438e-06,
      "loss": 1.7058,
      "step": 576
    },
    {
      "epoch": 1.4539722572509457,
      "grad_norm": 8.980450630187988,
      "learning_rate": 2.7629911280101395e-06,
      "loss": 1.4614,
      "step": 577
    },
    {
      "epoch": 1.4564943253467844,
      "grad_norm": 9.580355644226074,
      "learning_rate": 2.750316856780735e-06,
      "loss": 1.6912,
      "step": 578
    },
    {
      "epoch": 1.459016393442623,
      "grad_norm": 9.154928207397461,
      "learning_rate": 2.7376425855513313e-06,
      "loss": 1.6747,
      "step": 579
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 9.736513137817383,
      "learning_rate": 2.724968314321927e-06,
      "loss": 1.7184,
      "step": 580
    },
    {
      "epoch": 1.4640605296343001,
      "grad_norm": 10.05449104309082,
      "learning_rate": 2.7122940430925226e-06,
      "loss": 1.8869,
      "step": 581
    },
    {
      "epoch": 1.4665825977301388,
      "grad_norm": 9.355259895324707,
      "learning_rate": 2.699619771863118e-06,
      "loss": 1.5752,
      "step": 582
    },
    {
      "epoch": 1.4691046658259772,
      "grad_norm": 10.399754524230957,
      "learning_rate": 2.6869455006337136e-06,
      "loss": 1.6923,
      "step": 583
    },
    {
      "epoch": 1.4716267339218159,
      "grad_norm": 10.138842582702637,
      "learning_rate": 2.6742712294043092e-06,
      "loss": 1.7969,
      "step": 584
    },
    {
      "epoch": 1.4741488020176545,
      "grad_norm": 9.712721824645996,
      "learning_rate": 2.6615969581749054e-06,
      "loss": 1.716,
      "step": 585
    },
    {
      "epoch": 1.4766708701134932,
      "grad_norm": 9.221614837646484,
      "learning_rate": 2.648922686945501e-06,
      "loss": 1.7073,
      "step": 586
    },
    {
      "epoch": 1.4791929382093316,
      "grad_norm": 9.812952995300293,
      "learning_rate": 2.6362484157160967e-06,
      "loss": 1.7292,
      "step": 587
    },
    {
      "epoch": 1.4817150063051703,
      "grad_norm": 9.644000053405762,
      "learning_rate": 2.6235741444866924e-06,
      "loss": 1.7734,
      "step": 588
    },
    {
      "epoch": 1.4842370744010087,
      "grad_norm": 9.276434898376465,
      "learning_rate": 2.6108998732572877e-06,
      "loss": 1.6883,
      "step": 589
    },
    {
      "epoch": 1.4867591424968474,
      "grad_norm": 9.83614730834961,
      "learning_rate": 2.5982256020278833e-06,
      "loss": 1.8214,
      "step": 590
    },
    {
      "epoch": 1.489281210592686,
      "grad_norm": 9.956547737121582,
      "learning_rate": 2.585551330798479e-06,
      "loss": 1.8715,
      "step": 591
    },
    {
      "epoch": 1.4918032786885247,
      "grad_norm": 9.80245590209961,
      "learning_rate": 2.572877059569075e-06,
      "loss": 1.7674,
      "step": 592
    },
    {
      "epoch": 1.4943253467843631,
      "grad_norm": 9.771615028381348,
      "learning_rate": 2.560202788339671e-06,
      "loss": 1.8212,
      "step": 593
    },
    {
      "epoch": 1.4968474148802018,
      "grad_norm": 10.202628135681152,
      "learning_rate": 2.5475285171102665e-06,
      "loss": 1.6702,
      "step": 594
    },
    {
      "epoch": 1.4993694829760402,
      "grad_norm": 9.16274356842041,
      "learning_rate": 2.534854245880862e-06,
      "loss": 1.7412,
      "step": 595
    },
    {
      "epoch": 1.5018915510718789,
      "grad_norm": 9.05302619934082,
      "learning_rate": 2.5221799746514574e-06,
      "loss": 1.5141,
      "step": 596
    },
    {
      "epoch": 1.5044136191677175,
      "grad_norm": 9.663128852844238,
      "learning_rate": 2.509505703422053e-06,
      "loss": 1.7618,
      "step": 597
    },
    {
      "epoch": 1.5069356872635562,
      "grad_norm": 9.237212181091309,
      "learning_rate": 2.496831432192649e-06,
      "loss": 1.7741,
      "step": 598
    },
    {
      "epoch": 1.5094577553593949,
      "grad_norm": 9.22396183013916,
      "learning_rate": 2.484157160963245e-06,
      "loss": 1.6022,
      "step": 599
    },
    {
      "epoch": 1.5119798234552333,
      "grad_norm": 9.295252799987793,
      "learning_rate": 2.4714828897338406e-06,
      "loss": 1.6741,
      "step": 600
    },
    {
      "epoch": 1.5119798234552333,
      "eval_loss": 1.7527234554290771,
      "eval_runtime": 19.2415,
      "eval_samples_per_second": 36.64,
      "eval_steps_per_second": 18.346,
      "step": 600
    },
    {
      "epoch": 1.5145018915510717,
      "grad_norm": 9.695648193359375,
      "learning_rate": 2.4588086185044363e-06,
      "loss": 1.5484,
      "step": 601
    },
    {
      "epoch": 1.5170239596469104,
      "grad_norm": 9.367477416992188,
      "learning_rate": 2.446134347275032e-06,
      "loss": 1.6098,
      "step": 602
    },
    {
      "epoch": 1.519546027742749,
      "grad_norm": 9.397459983825684,
      "learning_rate": 2.4334600760456276e-06,
      "loss": 1.6935,
      "step": 603
    },
    {
      "epoch": 1.5220680958385877,
      "grad_norm": 9.639983177185059,
      "learning_rate": 2.4207858048162233e-06,
      "loss": 1.8023,
      "step": 604
    },
    {
      "epoch": 1.5245901639344264,
      "grad_norm": 9.886542320251465,
      "learning_rate": 2.408111533586819e-06,
      "loss": 1.7828,
      "step": 605
    },
    {
      "epoch": 1.5271122320302648,
      "grad_norm": 9.943028450012207,
      "learning_rate": 2.3954372623574147e-06,
      "loss": 1.6303,
      "step": 606
    },
    {
      "epoch": 1.5296343001261032,
      "grad_norm": 9.718281745910645,
      "learning_rate": 2.3827629911280104e-06,
      "loss": 1.8397,
      "step": 607
    },
    {
      "epoch": 1.532156368221942,
      "grad_norm": 9.565438270568848,
      "learning_rate": 2.370088719898606e-06,
      "loss": 1.6546,
      "step": 608
    },
    {
      "epoch": 1.5346784363177806,
      "grad_norm": 9.189560890197754,
      "learning_rate": 2.3574144486692017e-06,
      "loss": 1.6681,
      "step": 609
    },
    {
      "epoch": 1.5372005044136192,
      "grad_norm": 9.213074684143066,
      "learning_rate": 2.3447401774397974e-06,
      "loss": 1.5821,
      "step": 610
    },
    {
      "epoch": 1.5397225725094579,
      "grad_norm": 9.724678993225098,
      "learning_rate": 2.332065906210393e-06,
      "loss": 1.6974,
      "step": 611
    },
    {
      "epoch": 1.5422446406052963,
      "grad_norm": 9.944777488708496,
      "learning_rate": 2.319391634980989e-06,
      "loss": 1.6202,
      "step": 612
    },
    {
      "epoch": 1.544766708701135,
      "grad_norm": 9.265429496765137,
      "learning_rate": 2.3067173637515845e-06,
      "loss": 1.5526,
      "step": 613
    },
    {
      "epoch": 1.5472887767969734,
      "grad_norm": 9.836352348327637,
      "learning_rate": 2.29404309252218e-06,
      "loss": 1.7562,
      "step": 614
    },
    {
      "epoch": 1.549810844892812,
      "grad_norm": 9.964411735534668,
      "learning_rate": 2.281368821292776e-06,
      "loss": 1.6235,
      "step": 615
    },
    {
      "epoch": 1.5523329129886507,
      "grad_norm": 9.414365768432617,
      "learning_rate": 2.2686945500633715e-06,
      "loss": 1.6407,
      "step": 616
    },
    {
      "epoch": 1.5548549810844894,
      "grad_norm": 9.408808708190918,
      "learning_rate": 2.256020278833967e-06,
      "loss": 1.4585,
      "step": 617
    },
    {
      "epoch": 1.5573770491803278,
      "grad_norm": 9.52918815612793,
      "learning_rate": 2.243346007604563e-06,
      "loss": 1.7194,
      "step": 618
    },
    {
      "epoch": 1.5598991172761665,
      "grad_norm": 9.441154479980469,
      "learning_rate": 2.2306717363751586e-06,
      "loss": 1.7602,
      "step": 619
    },
    {
      "epoch": 1.562421185372005,
      "grad_norm": 9.504714965820312,
      "learning_rate": 2.2179974651457543e-06,
      "loss": 1.6221,
      "step": 620
    },
    {
      "epoch": 1.5649432534678436,
      "grad_norm": 8.928702354431152,
      "learning_rate": 2.20532319391635e-06,
      "loss": 1.6069,
      "step": 621
    },
    {
      "epoch": 1.5674653215636822,
      "grad_norm": 9.33944320678711,
      "learning_rate": 2.1926489226869456e-06,
      "loss": 1.5649,
      "step": 622
    },
    {
      "epoch": 1.569987389659521,
      "grad_norm": 9.850550651550293,
      "learning_rate": 2.1799746514575413e-06,
      "loss": 1.779,
      "step": 623
    },
    {
      "epoch": 1.5725094577553596,
      "grad_norm": 9.397130012512207,
      "learning_rate": 2.167300380228137e-06,
      "loss": 1.7734,
      "step": 624
    },
    {
      "epoch": 1.575031525851198,
      "grad_norm": 10.042643547058105,
      "learning_rate": 2.1546261089987327e-06,
      "loss": 1.9307,
      "step": 625
    },
    {
      "epoch": 1.5775535939470364,
      "grad_norm": 10.389598846435547,
      "learning_rate": 2.1419518377693283e-06,
      "loss": 1.5473,
      "step": 626
    },
    {
      "epoch": 1.580075662042875,
      "grad_norm": 11.477649688720703,
      "learning_rate": 2.129277566539924e-06,
      "loss": 1.7931,
      "step": 627
    },
    {
      "epoch": 1.5825977301387137,
      "grad_norm": 9.05221176147461,
      "learning_rate": 2.1166032953105197e-06,
      "loss": 1.6282,
      "step": 628
    },
    {
      "epoch": 1.5851197982345524,
      "grad_norm": 10.248181343078613,
      "learning_rate": 2.1039290240811154e-06,
      "loss": 1.6725,
      "step": 629
    },
    {
      "epoch": 1.587641866330391,
      "grad_norm": 9.642772674560547,
      "learning_rate": 2.0912547528517115e-06,
      "loss": 1.6916,
      "step": 630
    },
    {
      "epoch": 1.5901639344262295,
      "grad_norm": 9.863396644592285,
      "learning_rate": 2.0785804816223068e-06,
      "loss": 1.6603,
      "step": 631
    },
    {
      "epoch": 1.592686002522068,
      "grad_norm": 9.734106063842773,
      "learning_rate": 2.0659062103929024e-06,
      "loss": 1.7058,
      "step": 632
    },
    {
      "epoch": 1.5952080706179066,
      "grad_norm": 9.708539009094238,
      "learning_rate": 2.053231939163498e-06,
      "loss": 1.7767,
      "step": 633
    },
    {
      "epoch": 1.5977301387137453,
      "grad_norm": 9.630854606628418,
      "learning_rate": 2.040557667934094e-06,
      "loss": 1.7525,
      "step": 634
    },
    {
      "epoch": 1.600252206809584,
      "grad_norm": 9.335700035095215,
      "learning_rate": 2.0278833967046895e-06,
      "loss": 1.6844,
      "step": 635
    },
    {
      "epoch": 1.6027742749054226,
      "grad_norm": 10.417139053344727,
      "learning_rate": 2.015209125475285e-06,
      "loss": 1.7423,
      "step": 636
    },
    {
      "epoch": 1.605296343001261,
      "grad_norm": 9.053544998168945,
      "learning_rate": 2.0025348542458813e-06,
      "loss": 1.5223,
      "step": 637
    },
    {
      "epoch": 1.6078184110970997,
      "grad_norm": 9.469392776489258,
      "learning_rate": 1.9898605830164765e-06,
      "loss": 1.7589,
      "step": 638
    },
    {
      "epoch": 1.610340479192938,
      "grad_norm": 9.530014038085938,
      "learning_rate": 1.9771863117870722e-06,
      "loss": 1.7119,
      "step": 639
    },
    {
      "epoch": 1.6128625472887768,
      "grad_norm": 9.487112045288086,
      "learning_rate": 1.9645120405576683e-06,
      "loss": 1.7259,
      "step": 640
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 9.483546257019043,
      "learning_rate": 1.951837769328264e-06,
      "loss": 1.6439,
      "step": 641
    },
    {
      "epoch": 1.617906683480454,
      "grad_norm": 9.60571002960205,
      "learning_rate": 1.9391634980988593e-06,
      "loss": 1.838,
      "step": 642
    },
    {
      "epoch": 1.6204287515762925,
      "grad_norm": 9.391358375549316,
      "learning_rate": 1.926489226869455e-06,
      "loss": 1.8589,
      "step": 643
    },
    {
      "epoch": 1.6229508196721312,
      "grad_norm": 9.331633567810059,
      "learning_rate": 1.913814955640051e-06,
      "loss": 1.5623,
      "step": 644
    },
    {
      "epoch": 1.6254728877679696,
      "grad_norm": 9.50513744354248,
      "learning_rate": 1.9011406844106463e-06,
      "loss": 1.7163,
      "step": 645
    },
    {
      "epoch": 1.6279949558638083,
      "grad_norm": 9.98187255859375,
      "learning_rate": 1.8884664131812422e-06,
      "loss": 1.6498,
      "step": 646
    },
    {
      "epoch": 1.630517023959647,
      "grad_norm": 8.810663223266602,
      "learning_rate": 1.875792141951838e-06,
      "loss": 1.5502,
      "step": 647
    },
    {
      "epoch": 1.6330390920554856,
      "grad_norm": 10.034806251525879,
      "learning_rate": 1.8631178707224338e-06,
      "loss": 1.8251,
      "step": 648
    },
    {
      "epoch": 1.6355611601513242,
      "grad_norm": 9.524911880493164,
      "learning_rate": 1.8504435994930293e-06,
      "loss": 1.7457,
      "step": 649
    },
    {
      "epoch": 1.6380832282471627,
      "grad_norm": 9.811185836791992,
      "learning_rate": 1.837769328263625e-06,
      "loss": 1.7881,
      "step": 650
    },
    {
      "epoch": 1.6380832282471627,
      "eval_loss": 1.749564528465271,
      "eval_runtime": 19.1851,
      "eval_samples_per_second": 36.747,
      "eval_steps_per_second": 18.4,
      "step": 650
    },
    {
      "epoch": 1.6406052963430011,
      "grad_norm": 9.91550350189209,
      "learning_rate": 1.8250950570342208e-06,
      "loss": 1.7608,
      "step": 651
    },
    {
      "epoch": 1.6431273644388398,
      "grad_norm": 9.427831649780273,
      "learning_rate": 1.8124207858048165e-06,
      "loss": 1.6911,
      "step": 652
    },
    {
      "epoch": 1.6456494325346784,
      "grad_norm": 9.239514350891113,
      "learning_rate": 1.799746514575412e-06,
      "loss": 1.6725,
      "step": 653
    },
    {
      "epoch": 1.648171500630517,
      "grad_norm": 9.309579849243164,
      "learning_rate": 1.7870722433460077e-06,
      "loss": 1.6271,
      "step": 654
    },
    {
      "epoch": 1.6506935687263558,
      "grad_norm": 9.364089965820312,
      "learning_rate": 1.7743979721166036e-06,
      "loss": 1.5901,
      "step": 655
    },
    {
      "epoch": 1.6532156368221942,
      "grad_norm": 9.668143272399902,
      "learning_rate": 1.761723700887199e-06,
      "loss": 1.6002,
      "step": 656
    },
    {
      "epoch": 1.6557377049180326,
      "grad_norm": 9.19447135925293,
      "learning_rate": 1.7490494296577947e-06,
      "loss": 1.7073,
      "step": 657
    },
    {
      "epoch": 1.6582597730138713,
      "grad_norm": 9.601155281066895,
      "learning_rate": 1.7363751584283906e-06,
      "loss": 1.7861,
      "step": 658
    },
    {
      "epoch": 1.66078184110971,
      "grad_norm": 9.959553718566895,
      "learning_rate": 1.7237008871989863e-06,
      "loss": 1.8846,
      "step": 659
    },
    {
      "epoch": 1.6633039092055486,
      "grad_norm": 9.508479118347168,
      "learning_rate": 1.7110266159695818e-06,
      "loss": 1.7108,
      "step": 660
    },
    {
      "epoch": 1.6658259773013873,
      "grad_norm": 10.047428131103516,
      "learning_rate": 1.6983523447401777e-06,
      "loss": 1.8388,
      "step": 661
    },
    {
      "epoch": 1.6683480453972257,
      "grad_norm": 10.06289005279541,
      "learning_rate": 1.6856780735107733e-06,
      "loss": 1.7148,
      "step": 662
    },
    {
      "epoch": 1.6708701134930644,
      "grad_norm": 9.456268310546875,
      "learning_rate": 1.6730038022813688e-06,
      "loss": 1.8581,
      "step": 663
    },
    {
      "epoch": 1.6733921815889028,
      "grad_norm": 9.375258445739746,
      "learning_rate": 1.6603295310519645e-06,
      "loss": 1.7456,
      "step": 664
    },
    {
      "epoch": 1.6759142496847415,
      "grad_norm": 10.087471961975098,
      "learning_rate": 1.6476552598225604e-06,
      "loss": 1.8193,
      "step": 665
    },
    {
      "epoch": 1.6784363177805801,
      "grad_norm": 8.920852661132812,
      "learning_rate": 1.634980988593156e-06,
      "loss": 1.6298,
      "step": 666
    },
    {
      "epoch": 1.6809583858764188,
      "grad_norm": 8.836207389831543,
      "learning_rate": 1.6223067173637516e-06,
      "loss": 1.5731,
      "step": 667
    },
    {
      "epoch": 1.6834804539722572,
      "grad_norm": 9.333002090454102,
      "learning_rate": 1.6096324461343474e-06,
      "loss": 1.6645,
      "step": 668
    },
    {
      "epoch": 1.6860025220680959,
      "grad_norm": 9.805105209350586,
      "learning_rate": 1.5969581749049431e-06,
      "loss": 1.6835,
      "step": 669
    },
    {
      "epoch": 1.6885245901639343,
      "grad_norm": 9.33131217956543,
      "learning_rate": 1.5842839036755388e-06,
      "loss": 1.6171,
      "step": 670
    },
    {
      "epoch": 1.691046658259773,
      "grad_norm": 9.339081764221191,
      "learning_rate": 1.5716096324461345e-06,
      "loss": 1.7783,
      "step": 671
    },
    {
      "epoch": 1.6935687263556116,
      "grad_norm": 8.751605987548828,
      "learning_rate": 1.5589353612167302e-06,
      "loss": 1.608,
      "step": 672
    },
    {
      "epoch": 1.6960907944514503,
      "grad_norm": 9.277210235595703,
      "learning_rate": 1.5462610899873259e-06,
      "loss": 1.6213,
      "step": 673
    },
    {
      "epoch": 1.698612862547289,
      "grad_norm": 9.225253105163574,
      "learning_rate": 1.5335868187579213e-06,
      "loss": 1.4876,
      "step": 674
    },
    {
      "epoch": 1.7011349306431274,
      "grad_norm": 9.46793270111084,
      "learning_rate": 1.5209125475285172e-06,
      "loss": 1.6303,
      "step": 675
    },
    {
      "epoch": 1.7036569987389658,
      "grad_norm": 9.261821746826172,
      "learning_rate": 1.508238276299113e-06,
      "loss": 1.6565,
      "step": 676
    },
    {
      "epoch": 1.7061790668348045,
      "grad_norm": 9.96898365020752,
      "learning_rate": 1.4955640050697088e-06,
      "loss": 1.8511,
      "step": 677
    },
    {
      "epoch": 1.7087011349306431,
      "grad_norm": 9.247895240783691,
      "learning_rate": 1.4828897338403043e-06,
      "loss": 1.7148,
      "step": 678
    },
    {
      "epoch": 1.7112232030264818,
      "grad_norm": 10.170859336853027,
      "learning_rate": 1.4702154626109e-06,
      "loss": 1.6646,
      "step": 679
    },
    {
      "epoch": 1.7137452711223204,
      "grad_norm": 8.891340255737305,
      "learning_rate": 1.4575411913814959e-06,
      "loss": 1.6741,
      "step": 680
    },
    {
      "epoch": 1.7162673392181589,
      "grad_norm": 9.430920600891113,
      "learning_rate": 1.4448669201520913e-06,
      "loss": 1.7243,
      "step": 681
    },
    {
      "epoch": 1.7187894073139973,
      "grad_norm": 9.737271308898926,
      "learning_rate": 1.432192648922687e-06,
      "loss": 1.65,
      "step": 682
    },
    {
      "epoch": 1.721311475409836,
      "grad_norm": 9.456663131713867,
      "learning_rate": 1.4195183776932827e-06,
      "loss": 1.6646,
      "step": 683
    },
    {
      "epoch": 1.7238335435056746,
      "grad_norm": 9.737414360046387,
      "learning_rate": 1.4068441064638786e-06,
      "loss": 1.7159,
      "step": 684
    },
    {
      "epoch": 1.7263556116015133,
      "grad_norm": 9.30095386505127,
      "learning_rate": 1.394169835234474e-06,
      "loss": 1.8207,
      "step": 685
    },
    {
      "epoch": 1.728877679697352,
      "grad_norm": 9.761159896850586,
      "learning_rate": 1.3814955640050697e-06,
      "loss": 1.7155,
      "step": 686
    },
    {
      "epoch": 1.7313997477931904,
      "grad_norm": 9.230942726135254,
      "learning_rate": 1.3688212927756656e-06,
      "loss": 1.5698,
      "step": 687
    },
    {
      "epoch": 1.733921815889029,
      "grad_norm": 9.392193794250488,
      "learning_rate": 1.3561470215462613e-06,
      "loss": 1.7748,
      "step": 688
    },
    {
      "epoch": 1.7364438839848675,
      "grad_norm": 10.055660247802734,
      "learning_rate": 1.3434727503168568e-06,
      "loss": 1.7277,
      "step": 689
    },
    {
      "epoch": 1.7389659520807061,
      "grad_norm": 10.82951831817627,
      "learning_rate": 1.3307984790874527e-06,
      "loss": 1.7353,
      "step": 690
    },
    {
      "epoch": 1.7414880201765448,
      "grad_norm": 9.445710182189941,
      "learning_rate": 1.3181242078580484e-06,
      "loss": 1.5797,
      "step": 691
    },
    {
      "epoch": 1.7440100882723835,
      "grad_norm": 9.652688980102539,
      "learning_rate": 1.3054499366286438e-06,
      "loss": 1.6493,
      "step": 692
    },
    {
      "epoch": 1.746532156368222,
      "grad_norm": 9.329366683959961,
      "learning_rate": 1.2927756653992395e-06,
      "loss": 1.5877,
      "step": 693
    },
    {
      "epoch": 1.7490542244640606,
      "grad_norm": 9.715190887451172,
      "learning_rate": 1.2801013941698354e-06,
      "loss": 1.6495,
      "step": 694
    },
    {
      "epoch": 1.751576292559899,
      "grad_norm": 9.621136665344238,
      "learning_rate": 1.267427122940431e-06,
      "loss": 1.6353,
      "step": 695
    },
    {
      "epoch": 1.7540983606557377,
      "grad_norm": 9.586950302124023,
      "learning_rate": 1.2547528517110266e-06,
      "loss": 1.7131,
      "step": 696
    },
    {
      "epoch": 1.7566204287515763,
      "grad_norm": 9.65340518951416,
      "learning_rate": 1.2420785804816225e-06,
      "loss": 1.8355,
      "step": 697
    },
    {
      "epoch": 1.759142496847415,
      "grad_norm": 9.164055824279785,
      "learning_rate": 1.2294043092522181e-06,
      "loss": 1.6494,
      "step": 698
    },
    {
      "epoch": 1.7616645649432536,
      "grad_norm": 9.687239646911621,
      "learning_rate": 1.2167300380228138e-06,
      "loss": 1.7757,
      "step": 699
    },
    {
      "epoch": 1.764186633039092,
      "grad_norm": 10.138352394104004,
      "learning_rate": 1.2040557667934095e-06,
      "loss": 1.9317,
      "step": 700
    },
    {
      "epoch": 1.764186633039092,
      "eval_loss": 1.7481378316879272,
      "eval_runtime": 19.0842,
      "eval_samples_per_second": 36.941,
      "eval_steps_per_second": 18.497,
      "step": 700
    },
    {
      "epoch": 1.7667087011349305,
      "grad_norm": 10.055146217346191,
      "learning_rate": 1.1913814955640052e-06,
      "loss": 1.7921,
      "step": 701
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 9.693598747253418,
      "learning_rate": 1.1787072243346009e-06,
      "loss": 1.6781,
      "step": 702
    },
    {
      "epoch": 1.7717528373266078,
      "grad_norm": 9.510719299316406,
      "learning_rate": 1.1660329531051966e-06,
      "loss": 1.6429,
      "step": 703
    },
    {
      "epoch": 1.7742749054224465,
      "grad_norm": 9.209467887878418,
      "learning_rate": 1.1533586818757922e-06,
      "loss": 1.7089,
      "step": 704
    },
    {
      "epoch": 1.7767969735182851,
      "grad_norm": 8.981858253479004,
      "learning_rate": 1.140684410646388e-06,
      "loss": 1.7332,
      "step": 705
    },
    {
      "epoch": 1.7793190416141236,
      "grad_norm": 8.860949516296387,
      "learning_rate": 1.1280101394169836e-06,
      "loss": 1.5045,
      "step": 706
    },
    {
      "epoch": 1.781841109709962,
      "grad_norm": 9.034729957580566,
      "learning_rate": 1.1153358681875793e-06,
      "loss": 1.7599,
      "step": 707
    },
    {
      "epoch": 1.7843631778058007,
      "grad_norm": 9.299259185791016,
      "learning_rate": 1.102661596958175e-06,
      "loss": 1.7029,
      "step": 708
    },
    {
      "epoch": 1.7868852459016393,
      "grad_norm": 10.08253288269043,
      "learning_rate": 1.0899873257287706e-06,
      "loss": 1.7364,
      "step": 709
    },
    {
      "epoch": 1.789407313997478,
      "grad_norm": 9.0954008102417,
      "learning_rate": 1.0773130544993663e-06,
      "loss": 1.7623,
      "step": 710
    },
    {
      "epoch": 1.7919293820933166,
      "grad_norm": 9.60004711151123,
      "learning_rate": 1.064638783269962e-06,
      "loss": 1.6558,
      "step": 711
    },
    {
      "epoch": 1.794451450189155,
      "grad_norm": 9.707661628723145,
      "learning_rate": 1.0519645120405577e-06,
      "loss": 1.6368,
      "step": 712
    },
    {
      "epoch": 1.7969735182849937,
      "grad_norm": 10.129836082458496,
      "learning_rate": 1.0392902408111534e-06,
      "loss": 1.5533,
      "step": 713
    },
    {
      "epoch": 1.7994955863808322,
      "grad_norm": 9.944167137145996,
      "learning_rate": 1.026615969581749e-06,
      "loss": 1.5573,
      "step": 714
    },
    {
      "epoch": 1.8020176544766708,
      "grad_norm": 9.778340339660645,
      "learning_rate": 1.0139416983523447e-06,
      "loss": 1.6241,
      "step": 715
    },
    {
      "epoch": 1.8045397225725095,
      "grad_norm": 9.464924812316895,
      "learning_rate": 1.0012674271229406e-06,
      "loss": 1.6252,
      "step": 716
    },
    {
      "epoch": 1.8070617906683482,
      "grad_norm": 8.913681030273438,
      "learning_rate": 9.885931558935361e-07,
      "loss": 1.6014,
      "step": 717
    },
    {
      "epoch": 1.8095838587641866,
      "grad_norm": 10.015497207641602,
      "learning_rate": 9.75918884664132e-07,
      "loss": 1.8004,
      "step": 718
    },
    {
      "epoch": 1.8121059268600253,
      "grad_norm": 9.229154586791992,
      "learning_rate": 9.632446134347275e-07,
      "loss": 1.6482,
      "step": 719
    },
    {
      "epoch": 1.8146279949558637,
      "grad_norm": 9.433388710021973,
      "learning_rate": 9.505703422053232e-07,
      "loss": 1.6345,
      "step": 720
    },
    {
      "epoch": 1.8171500630517023,
      "grad_norm": 9.447920799255371,
      "learning_rate": 9.37896070975919e-07,
      "loss": 1.7361,
      "step": 721
    },
    {
      "epoch": 1.819672131147541,
      "grad_norm": 9.218050956726074,
      "learning_rate": 9.252217997465146e-07,
      "loss": 1.5587,
      "step": 722
    },
    {
      "epoch": 1.8221941992433797,
      "grad_norm": 10.602153778076172,
      "learning_rate": 9.125475285171104e-07,
      "loss": 1.823,
      "step": 723
    },
    {
      "epoch": 1.8247162673392183,
      "grad_norm": 10.81556510925293,
      "learning_rate": 8.99873257287706e-07,
      "loss": 1.8052,
      "step": 724
    },
    {
      "epoch": 1.8272383354350568,
      "grad_norm": 9.453458786010742,
      "learning_rate": 8.871989860583018e-07,
      "loss": 1.6842,
      "step": 725
    },
    {
      "epoch": 1.8297604035308952,
      "grad_norm": 9.791069030761719,
      "learning_rate": 8.745247148288974e-07,
      "loss": 1.6825,
      "step": 726
    },
    {
      "epoch": 1.8322824716267339,
      "grad_norm": 9.330440521240234,
      "learning_rate": 8.618504435994932e-07,
      "loss": 1.5168,
      "step": 727
    },
    {
      "epoch": 1.8348045397225725,
      "grad_norm": 9.99361515045166,
      "learning_rate": 8.491761723700888e-07,
      "loss": 1.6534,
      "step": 728
    },
    {
      "epoch": 1.8373266078184112,
      "grad_norm": 9.930830001831055,
      "learning_rate": 8.365019011406844e-07,
      "loss": 1.6339,
      "step": 729
    },
    {
      "epoch": 1.8398486759142498,
      "grad_norm": 9.571563720703125,
      "learning_rate": 8.238276299112802e-07,
      "loss": 1.6096,
      "step": 730
    },
    {
      "epoch": 1.8423707440100883,
      "grad_norm": 9.208858489990234,
      "learning_rate": 8.111533586818758e-07,
      "loss": 1.7718,
      "step": 731
    },
    {
      "epoch": 1.8448928121059267,
      "grad_norm": 8.730284690856934,
      "learning_rate": 7.984790874524716e-07,
      "loss": 1.5865,
      "step": 732
    },
    {
      "epoch": 1.8474148802017654,
      "grad_norm": 10.828349113464355,
      "learning_rate": 7.858048162230672e-07,
      "loss": 1.7644,
      "step": 733
    },
    {
      "epoch": 1.849936948297604,
      "grad_norm": 9.517570495605469,
      "learning_rate": 7.731305449936629e-07,
      "loss": 1.6881,
      "step": 734
    },
    {
      "epoch": 1.8524590163934427,
      "grad_norm": 10.17636775970459,
      "learning_rate": 7.604562737642586e-07,
      "loss": 1.7357,
      "step": 735
    },
    {
      "epoch": 1.8549810844892813,
      "grad_norm": 9.773160934448242,
      "learning_rate": 7.477820025348544e-07,
      "loss": 1.5969,
      "step": 736
    },
    {
      "epoch": 1.8575031525851198,
      "grad_norm": 9.466531753540039,
      "learning_rate": 7.3510773130545e-07,
      "loss": 1.7774,
      "step": 737
    },
    {
      "epoch": 1.8600252206809584,
      "grad_norm": 9.757929801940918,
      "learning_rate": 7.224334600760457e-07,
      "loss": 1.6755,
      "step": 738
    },
    {
      "epoch": 1.8625472887767969,
      "grad_norm": 9.96483039855957,
      "learning_rate": 7.097591888466413e-07,
      "loss": 1.7302,
      "step": 739
    },
    {
      "epoch": 1.8650693568726355,
      "grad_norm": 9.63918399810791,
      "learning_rate": 6.97084917617237e-07,
      "loss": 1.6087,
      "step": 740
    },
    {
      "epoch": 1.8675914249684742,
      "grad_norm": 9.94542407989502,
      "learning_rate": 6.844106463878328e-07,
      "loss": 1.7394,
      "step": 741
    },
    {
      "epoch": 1.8701134930643128,
      "grad_norm": 10.425265312194824,
      "learning_rate": 6.717363751584284e-07,
      "loss": 1.6141,
      "step": 742
    },
    {
      "epoch": 1.8726355611601513,
      "grad_norm": 9.782626152038574,
      "learning_rate": 6.590621039290242e-07,
      "loss": 1.7622,
      "step": 743
    },
    {
      "epoch": 1.87515762925599,
      "grad_norm": 9.39716911315918,
      "learning_rate": 6.463878326996198e-07,
      "loss": 1.6118,
      "step": 744
    },
    {
      "epoch": 1.8776796973518284,
      "grad_norm": 9.034061431884766,
      "learning_rate": 6.337135614702155e-07,
      "loss": 1.5968,
      "step": 745
    },
    {
      "epoch": 1.880201765447667,
      "grad_norm": 10.161097526550293,
      "learning_rate": 6.210392902408112e-07,
      "loss": 1.8664,
      "step": 746
    },
    {
      "epoch": 1.8827238335435057,
      "grad_norm": 9.812199592590332,
      "learning_rate": 6.083650190114069e-07,
      "loss": 1.7126,
      "step": 747
    },
    {
      "epoch": 1.8852459016393444,
      "grad_norm": 9.307992935180664,
      "learning_rate": 5.956907477820026e-07,
      "loss": 1.6953,
      "step": 748
    },
    {
      "epoch": 1.887767969735183,
      "grad_norm": 10.021005630493164,
      "learning_rate": 5.830164765525983e-07,
      "loss": 1.6828,
      "step": 749
    },
    {
      "epoch": 1.8902900378310215,
      "grad_norm": 9.987221717834473,
      "learning_rate": 5.70342205323194e-07,
      "loss": 1.6156,
      "step": 750
    },
    {
      "epoch": 1.8902900378310215,
      "eval_loss": 1.7464284896850586,
      "eval_runtime": 19.2249,
      "eval_samples_per_second": 36.671,
      "eval_steps_per_second": 18.362,
      "step": 750
    },
    {
      "epoch": 1.89281210592686,
      "grad_norm": 9.487832069396973,
      "learning_rate": 5.576679340937896e-07,
      "loss": 1.6363,
      "step": 751
    },
    {
      "epoch": 1.8953341740226985,
      "grad_norm": 9.307217597961426,
      "learning_rate": 5.449936628643853e-07,
      "loss": 1.6832,
      "step": 752
    },
    {
      "epoch": 1.8978562421185372,
      "grad_norm": 9.852017402648926,
      "learning_rate": 5.32319391634981e-07,
      "loss": 1.6535,
      "step": 753
    },
    {
      "epoch": 1.9003783102143759,
      "grad_norm": 9.748652458190918,
      "learning_rate": 5.196451204055767e-07,
      "loss": 1.7731,
      "step": 754
    },
    {
      "epoch": 1.9029003783102145,
      "grad_norm": 9.246136665344238,
      "learning_rate": 5.069708491761724e-07,
      "loss": 1.815,
      "step": 755
    },
    {
      "epoch": 1.905422446406053,
      "grad_norm": 9.768349647521973,
      "learning_rate": 4.942965779467681e-07,
      "loss": 1.6391,
      "step": 756
    },
    {
      "epoch": 1.9079445145018914,
      "grad_norm": 9.720023155212402,
      "learning_rate": 4.816223067173637e-07,
      "loss": 1.5792,
      "step": 757
    },
    {
      "epoch": 1.91046658259773,
      "grad_norm": 9.682127952575684,
      "learning_rate": 4.689480354879595e-07,
      "loss": 1.6727,
      "step": 758
    },
    {
      "epoch": 1.9129886506935687,
      "grad_norm": 9.961228370666504,
      "learning_rate": 4.562737642585552e-07,
      "loss": 1.8872,
      "step": 759
    },
    {
      "epoch": 1.9155107187894074,
      "grad_norm": 9.318258285522461,
      "learning_rate": 4.435994930291509e-07,
      "loss": 1.5811,
      "step": 760
    },
    {
      "epoch": 1.918032786885246,
      "grad_norm": 9.372088432312012,
      "learning_rate": 4.309252217997466e-07,
      "loss": 1.722,
      "step": 761
    },
    {
      "epoch": 1.9205548549810845,
      "grad_norm": 9.715049743652344,
      "learning_rate": 4.182509505703422e-07,
      "loss": 1.84,
      "step": 762
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 9.463314056396484,
      "learning_rate": 4.055766793409379e-07,
      "loss": 1.8536,
      "step": 763
    },
    {
      "epoch": 1.9255989911727616,
      "grad_norm": 9.757950782775879,
      "learning_rate": 3.929024081115336e-07,
      "loss": 1.7315,
      "step": 764
    },
    {
      "epoch": 1.9281210592686002,
      "grad_norm": 9.816258430480957,
      "learning_rate": 3.802281368821293e-07,
      "loss": 1.7144,
      "step": 765
    },
    {
      "epoch": 1.9306431273644389,
      "grad_norm": 10.004706382751465,
      "learning_rate": 3.67553865652725e-07,
      "loss": 1.7758,
      "step": 766
    },
    {
      "epoch": 1.9331651954602775,
      "grad_norm": 9.619483947753906,
      "learning_rate": 3.5487959442332067e-07,
      "loss": 1.6603,
      "step": 767
    },
    {
      "epoch": 1.935687263556116,
      "grad_norm": 9.467287063598633,
      "learning_rate": 3.422053231939164e-07,
      "loss": 1.6333,
      "step": 768
    },
    {
      "epoch": 1.9382093316519546,
      "grad_norm": 8.78711223602295,
      "learning_rate": 3.295310519645121e-07,
      "loss": 1.6508,
      "step": 769
    },
    {
      "epoch": 1.940731399747793,
      "grad_norm": 10.25001335144043,
      "learning_rate": 3.1685678073510777e-07,
      "loss": 1.7887,
      "step": 770
    },
    {
      "epoch": 1.9432534678436317,
      "grad_norm": 9.302700996398926,
      "learning_rate": 3.0418250950570346e-07,
      "loss": 1.7453,
      "step": 771
    },
    {
      "epoch": 1.9457755359394704,
      "grad_norm": 9.454636573791504,
      "learning_rate": 2.9150823827629914e-07,
      "loss": 1.6872,
      "step": 772
    },
    {
      "epoch": 1.948297604035309,
      "grad_norm": 8.819103240966797,
      "learning_rate": 2.788339670468948e-07,
      "loss": 1.5166,
      "step": 773
    },
    {
      "epoch": 1.9508196721311475,
      "grad_norm": 9.884016990661621,
      "learning_rate": 2.661596958174905e-07,
      "loss": 1.6901,
      "step": 774
    },
    {
      "epoch": 1.9533417402269861,
      "grad_norm": 9.619026184082031,
      "learning_rate": 2.534854245880862e-07,
      "loss": 1.8408,
      "step": 775
    },
    {
      "epoch": 1.9558638083228246,
      "grad_norm": 9.128280639648438,
      "learning_rate": 2.4081115335868187e-07,
      "loss": 1.6555,
      "step": 776
    },
    {
      "epoch": 1.9583858764186632,
      "grad_norm": 9.426706314086914,
      "learning_rate": 2.281368821292776e-07,
      "loss": 1.5973,
      "step": 777
    },
    {
      "epoch": 1.960907944514502,
      "grad_norm": 9.342316627502441,
      "learning_rate": 2.154626108998733e-07,
      "loss": 1.7493,
      "step": 778
    },
    {
      "epoch": 1.9634300126103406,
      "grad_norm": 9.835463523864746,
      "learning_rate": 2.0278833967046894e-07,
      "loss": 1.7059,
      "step": 779
    },
    {
      "epoch": 1.9659520807061792,
      "grad_norm": 9.093395233154297,
      "learning_rate": 1.9011406844106465e-07,
      "loss": 1.7086,
      "step": 780
    },
    {
      "epoch": 1.9684741488020177,
      "grad_norm": 9.60049819946289,
      "learning_rate": 1.7743979721166034e-07,
      "loss": 1.8316,
      "step": 781
    },
    {
      "epoch": 1.970996216897856,
      "grad_norm": 10.135749816894531,
      "learning_rate": 1.6476552598225605e-07,
      "loss": 1.6949,
      "step": 782
    },
    {
      "epoch": 1.9735182849936947,
      "grad_norm": 9.4168062210083,
      "learning_rate": 1.5209125475285173e-07,
      "loss": 1.7463,
      "step": 783
    },
    {
      "epoch": 1.9760403530895334,
      "grad_norm": 9.066306114196777,
      "learning_rate": 1.394169835234474e-07,
      "loss": 1.6721,
      "step": 784
    },
    {
      "epoch": 1.978562421185372,
      "grad_norm": 9.219725608825684,
      "learning_rate": 1.267427122940431e-07,
      "loss": 1.6483,
      "step": 785
    },
    {
      "epoch": 1.9810844892812107,
      "grad_norm": 9.471524238586426,
      "learning_rate": 1.140684410646388e-07,
      "loss": 1.707,
      "step": 786
    },
    {
      "epoch": 1.9836065573770492,
      "grad_norm": 9.453824996948242,
      "learning_rate": 1.0139416983523447e-07,
      "loss": 1.7015,
      "step": 787
    },
    {
      "epoch": 1.9861286254728878,
      "grad_norm": 9.928653717041016,
      "learning_rate": 8.871989860583017e-08,
      "loss": 1.7654,
      "step": 788
    },
    {
      "epoch": 1.9886506935687263,
      "grad_norm": 9.56442642211914,
      "learning_rate": 7.604562737642586e-08,
      "loss": 1.5788,
      "step": 789
    },
    {
      "epoch": 1.991172761664565,
      "grad_norm": 9.336682319641113,
      "learning_rate": 6.337135614702155e-08,
      "loss": 1.6958,
      "step": 790
    },
    {
      "epoch": 1.9936948297604036,
      "grad_norm": 9.358407974243164,
      "learning_rate": 5.0697084917617236e-08,
      "loss": 1.6702,
      "step": 791
    },
    {
      "epoch": 1.9962168978562422,
      "grad_norm": 8.991886138916016,
      "learning_rate": 3.802281368821293e-08,
      "loss": 1.7324,
      "step": 792
    },
    {
      "epoch": 1.9987389659520807,
      "grad_norm": 10.394177436828613,
      "learning_rate": 2.5348542458808618e-08,
      "loss": 1.6646,
      "step": 793
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.592832565307617,
      "learning_rate": 1.2674271229404309e-08,
      "loss": 1.5761,
      "step": 794
    }
  ],
  "logging_steps": 1,
  "max_steps": 794,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4276469629939200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}