{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3163444639718805,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001054481546572935,
      "grad_norm": 0.9715927243232727,
      "learning_rate": 0.0,
      "loss": 11.2459,
      "num_input_tokens_seen": 2425848,
      "step": 1
    },
    {
      "epoch": 0.00210896309314587,
      "grad_norm": 1.3177887201309204,
      "learning_rate": 5e-06,
      "loss": 11.8548,
      "num_input_tokens_seen": 4956204,
      "step": 2
    },
    {
      "epoch": 0.003163444639718805,
      "grad_norm": 1.0477056503295898,
      "learning_rate": 1e-05,
      "loss": 10.8702,
      "num_input_tokens_seen": 7504132,
      "step": 3
    },
    {
      "epoch": 0.00421792618629174,
      "grad_norm": 0.8938190340995789,
      "learning_rate": 1.5e-05,
      "loss": 10.9133,
      "num_input_tokens_seen": 9828964,
      "step": 4
    },
    {
      "epoch": 0.005272407732864675,
      "grad_norm": 1.3546967506408691,
      "learning_rate": 2e-05,
      "loss": 11.9831,
      "num_input_tokens_seen": 12166228,
      "step": 5
    },
    {
      "epoch": 0.00632688927943761,
      "grad_norm": 0.9909083843231201,
      "learning_rate": 2.5e-05,
      "loss": 11.8687,
      "num_input_tokens_seen": 14513162,
      "step": 6
    },
    {
      "epoch": 0.007381370826010545,
      "grad_norm": 1.127426266670227,
      "learning_rate": 3e-05,
      "loss": 12.2052,
      "num_input_tokens_seen": 16999606,
      "step": 7
    },
    {
      "epoch": 0.00843585237258348,
      "grad_norm": 1.065547227859497,
      "learning_rate": 3.5000000000000004e-05,
      "loss": 11.4018,
      "num_input_tokens_seen": 19495694,
      "step": 8
    },
    {
      "epoch": 0.009490333919156414,
      "grad_norm": 1.1734977960586548,
      "learning_rate": 4e-05,
      "loss": 11.2021,
      "num_input_tokens_seen": 21885690,
      "step": 9
    },
    {
      "epoch": 0.01054481546572935,
      "grad_norm": 1.4789940118789673,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 11.5736,
      "num_input_tokens_seen": 24390702,
      "step": 10
    },
    {
      "epoch": 0.011599297012302284,
      "grad_norm": 0.9825775623321533,
      "learning_rate": 5e-05,
      "loss": 12.1355,
      "num_input_tokens_seen": 26861992,
      "step": 11
    },
    {
      "epoch": 0.01265377855887522,
      "grad_norm": 1.5725144147872925,
      "learning_rate": 5.5e-05,
      "loss": 11.3955,
      "num_input_tokens_seen": 29193680,
      "step": 12
    },
    {
      "epoch": 0.013708260105448155,
      "grad_norm": 1.456314206123352,
      "learning_rate": 6e-05,
      "loss": 11.9303,
      "num_input_tokens_seen": 31664596,
      "step": 13
    },
    {
      "epoch": 0.01476274165202109,
      "grad_norm": 0.9546123743057251,
      "learning_rate": 6.500000000000001e-05,
      "loss": 10.8114,
      "num_input_tokens_seen": 34036374,
      "step": 14
    },
    {
      "epoch": 0.015817223198594025,
      "grad_norm": 1.2968882322311401,
      "learning_rate": 7.000000000000001e-05,
      "loss": 11.6615,
      "num_input_tokens_seen": 36512920,
      "step": 15
    },
    {
      "epoch": 0.01687170474516696,
      "grad_norm": 0.9044846892356873,
      "learning_rate": 7.5e-05,
      "loss": 12.026,
      "num_input_tokens_seen": 38907186,
      "step": 16
    },
    {
      "epoch": 0.017926186291739893,
      "grad_norm": 0.9072983860969543,
      "learning_rate": 8e-05,
      "loss": 11.4538,
      "num_input_tokens_seen": 41485262,
      "step": 17
    },
    {
      "epoch": 0.01898066783831283,
      "grad_norm": 1.5409631729125977,
      "learning_rate": 8.5e-05,
      "loss": 12.0379,
      "num_input_tokens_seen": 43786674,
      "step": 18
    },
    {
      "epoch": 0.020035149384885764,
      "grad_norm": 1.1517468690872192,
      "learning_rate": 8.999999999999999e-05,
      "loss": 11.1949,
      "num_input_tokens_seen": 46102944,
      "step": 19
    },
    {
      "epoch": 0.0210896309314587,
      "grad_norm": 0.6707425117492676,
      "learning_rate": 9.5e-05,
      "loss": 12.1884,
      "num_input_tokens_seen": 48591602,
      "step": 20
    },
    {
      "epoch": 0.022144112478031636,
      "grad_norm": 1.4621737003326416,
      "learning_rate": 0.0001,
      "loss": 12.5171,
      "num_input_tokens_seen": 50987434,
      "step": 21
    },
    {
      "epoch": 0.023198594024604568,
      "grad_norm": 1.3107916116714478,
      "learning_rate": 0.000105,
      "loss": 9.2395,
      "num_input_tokens_seen": 53372194,
      "step": 22
    },
    {
      "epoch": 0.024253075571177504,
      "grad_norm": 1.1481292247772217,
      "learning_rate": 0.00011,
      "loss": 11.0781,
      "num_input_tokens_seen": 55826644,
      "step": 23
    },
    {
      "epoch": 0.02530755711775044,
      "grad_norm": 1.3331198692321777,
      "learning_rate": 0.000115,
      "loss": 11.9342,
      "num_input_tokens_seen": 58227112,
      "step": 24
    },
    {
      "epoch": 0.026362038664323375,
      "grad_norm": 0.9532589912414551,
      "learning_rate": 0.00012,
      "loss": 10.8832,
      "num_input_tokens_seen": 60837186,
      "step": 25
    },
    {
      "epoch": 0.02741652021089631,
      "grad_norm": 1.4355679750442505,
      "learning_rate": 0.000125,
      "loss": 8.6828,
      "num_input_tokens_seen": 63230980,
      "step": 26
    },
    {
      "epoch": 0.028471001757469243,
      "grad_norm": 1.2025192975997925,
      "learning_rate": 0.00013000000000000002,
      "loss": 10.4431,
      "num_input_tokens_seen": 65610708,
      "step": 27
    },
    {
      "epoch": 0.02952548330404218,
      "grad_norm": 0.988655149936676,
      "learning_rate": 0.000135,
      "loss": 11.0779,
      "num_input_tokens_seen": 68080890,
      "step": 28
    },
    {
      "epoch": 0.030579964850615114,
      "grad_norm": 1.0818135738372803,
      "learning_rate": 0.00014000000000000001,
      "loss": 13.0595,
      "num_input_tokens_seen": 70585882,
      "step": 29
    },
    {
      "epoch": 0.03163444639718805,
      "grad_norm": 1.0979222059249878,
      "learning_rate": 0.000145,
      "loss": 11.1297,
      "num_input_tokens_seen": 73104506,
      "step": 30
    },
    {
      "epoch": 0.032688927943760986,
      "grad_norm": 1.0198029279708862,
      "learning_rate": 0.00015,
      "loss": 11.4949,
      "num_input_tokens_seen": 75511970,
      "step": 31
    },
    {
      "epoch": 0.03374340949033392,
      "grad_norm": 0.8834076523780823,
      "learning_rate": 0.000155,
      "loss": 11.0135,
      "num_input_tokens_seen": 78038336,
      "step": 32
    },
    {
      "epoch": 0.03479789103690686,
      "grad_norm": 1.10096275806427,
      "learning_rate": 0.00016,
      "loss": 11.2872,
      "num_input_tokens_seen": 80369394,
      "step": 33
    },
    {
      "epoch": 0.035852372583479786,
      "grad_norm": 1.176360011100769,
      "learning_rate": 0.000165,
      "loss": 10.7974,
      "num_input_tokens_seen": 82753120,
      "step": 34
    },
    {
      "epoch": 0.03690685413005272,
      "grad_norm": 0.9229934215545654,
      "learning_rate": 0.00017,
      "loss": 10.8117,
      "num_input_tokens_seen": 85056206,
      "step": 35
    },
    {
      "epoch": 0.03796133567662566,
      "grad_norm": 1.377319574356079,
      "learning_rate": 0.000175,
      "loss": 12.7367,
      "num_input_tokens_seen": 87639648,
      "step": 36
    },
    {
      "epoch": 0.03901581722319859,
      "grad_norm": 1.0206114053726196,
      "learning_rate": 0.00017999999999999998,
      "loss": 11.8548,
      "num_input_tokens_seen": 89969532,
      "step": 37
    },
    {
      "epoch": 0.04007029876977153,
      "grad_norm": 1.196964144706726,
      "learning_rate": 0.000185,
      "loss": 11.772,
      "num_input_tokens_seen": 92389948,
      "step": 38
    },
    {
      "epoch": 0.041124780316344464,
      "grad_norm": 1.0182139873504639,
      "learning_rate": 0.00019,
      "loss": 12.2716,
      "num_input_tokens_seen": 94893746,
      "step": 39
    },
    {
      "epoch": 0.0421792618629174,
      "grad_norm": 1.1761435270309448,
      "learning_rate": 0.00019500000000000002,
      "loss": 11.2837,
      "num_input_tokens_seen": 97286502,
      "step": 40
    },
    {
      "epoch": 0.043233743409490336,
      "grad_norm": 0.6700538396835327,
      "learning_rate": 0.0002,
      "loss": 12.2248,
      "num_input_tokens_seen": 99689044,
      "step": 41
    },
    {
      "epoch": 0.04428822495606327,
      "grad_norm": 1.307807207107544,
      "learning_rate": 0.000205,
      "loss": 10.7634,
      "num_input_tokens_seen": 102250738,
      "step": 42
    },
    {
      "epoch": 0.04534270650263621,
      "grad_norm": 1.1823184490203857,
      "learning_rate": 0.00021,
      "loss": 12.4119,
      "num_input_tokens_seen": 104683216,
      "step": 43
    },
    {
      "epoch": 0.046397188049209136,
      "grad_norm": 1.0091804265975952,
      "learning_rate": 0.000215,
      "loss": 12.0439,
      "num_input_tokens_seen": 107261470,
      "step": 44
    },
    {
      "epoch": 0.04745166959578207,
      "grad_norm": 1.2117910385131836,
      "learning_rate": 0.00022,
      "loss": 11.6827,
      "num_input_tokens_seen": 109842334,
      "step": 45
    },
    {
      "epoch": 0.04850615114235501,
      "grad_norm": 1.0678317546844482,
      "learning_rate": 0.00022500000000000002,
      "loss": 11.4376,
      "num_input_tokens_seen": 112206494,
      "step": 46
    },
    {
      "epoch": 0.04956063268892794,
      "grad_norm": 1.1838268041610718,
      "learning_rate": 0.00023,
      "loss": 10.6156,
      "num_input_tokens_seen": 114594098,
      "step": 47
    },
    {
      "epoch": 0.05061511423550088,
      "grad_norm": 0.9946988821029663,
      "learning_rate": 0.000235,
      "loss": 11.5055,
      "num_input_tokens_seen": 116970602,
      "step": 48
    },
    {
      "epoch": 0.051669595782073814,
      "grad_norm": 0.9280380010604858,
      "learning_rate": 0.00024,
      "loss": 11.2752,
      "num_input_tokens_seen": 119606816,
      "step": 49
    },
    {
      "epoch": 0.05272407732864675,
      "grad_norm": 1.0243436098098755,
      "learning_rate": 0.000245,
      "loss": 12.5145,
      "num_input_tokens_seen": 121995176,
      "step": 50
    },
    {
      "epoch": 0.053778558875219686,
      "grad_norm": 0.8426516056060791,
      "learning_rate": 0.00025,
      "loss": 11.5149,
      "num_input_tokens_seen": 124419224,
      "step": 51
    },
    {
      "epoch": 0.05483304042179262,
      "grad_norm": 0.9479583501815796,
      "learning_rate": 0.000255,
      "loss": 10.9152,
      "num_input_tokens_seen": 126831556,
      "step": 52
    },
    {
      "epoch": 0.05588752196836556,
      "grad_norm": 1.192730188369751,
      "learning_rate": 0.00026000000000000003,
      "loss": 10.1095,
      "num_input_tokens_seen": 129215044,
      "step": 53
    },
    {
      "epoch": 0.056942003514938486,
      "grad_norm": 0.8085720539093018,
      "learning_rate": 0.00026500000000000004,
      "loss": 11.3386,
      "num_input_tokens_seen": 131708150,
      "step": 54
    },
    {
      "epoch": 0.05799648506151142,
      "grad_norm": 0.9331195950508118,
      "learning_rate": 0.00027,
      "loss": 10.548,
      "num_input_tokens_seen": 134191794,
      "step": 55
    },
    {
      "epoch": 0.05905096660808436,
      "grad_norm": 0.9635204672813416,
      "learning_rate": 0.000275,
      "loss": 10.785,
      "num_input_tokens_seen": 136613856,
      "step": 56
    },
    {
      "epoch": 0.06010544815465729,
      "grad_norm": 1.088985800743103,
      "learning_rate": 0.00028000000000000003,
      "loss": 11.0651,
      "num_input_tokens_seen": 139052346,
      "step": 57
    },
    {
      "epoch": 0.06115992970123023,
      "grad_norm": 1.0904672145843506,
      "learning_rate": 0.000285,
      "loss": 12.6632,
      "num_input_tokens_seen": 141458664,
      "step": 58
    },
    {
      "epoch": 0.062214411247803164,
      "grad_norm": 0.9067728519439697,
      "learning_rate": 0.00029,
      "loss": 11.2291,
      "num_input_tokens_seen": 143985770,
      "step": 59
    },
    {
      "epoch": 0.0632688927943761,
      "grad_norm": 0.8951049447059631,
      "learning_rate": 0.000295,
      "loss": 10.9248,
      "num_input_tokens_seen": 146472938,
      "step": 60
    },
    {
      "epoch": 0.06432337434094904,
      "grad_norm": 0.8976070284843445,
      "learning_rate": 0.0003,
      "loss": 12.2781,
      "num_input_tokens_seen": 148907744,
      "step": 61
    },
    {
      "epoch": 0.06537785588752197,
      "grad_norm": 1.090478777885437,
      "learning_rate": 0.000305,
      "loss": 11.9668,
      "num_input_tokens_seen": 151448294,
      "step": 62
    },
    {
      "epoch": 0.0664323374340949,
      "grad_norm": 0.8273966908454895,
      "learning_rate": 0.00031,
      "loss": 11.9769,
      "num_input_tokens_seen": 153917584,
      "step": 63
    },
    {
      "epoch": 0.06748681898066784,
      "grad_norm": 0.9453766345977783,
      "learning_rate": 0.000315,
      "loss": 10.5521,
      "num_input_tokens_seen": 156591012,
      "step": 64
    },
    {
      "epoch": 0.06854130052724078,
      "grad_norm": 0.9743331074714661,
      "learning_rate": 0.00032,
      "loss": 10.9769,
      "num_input_tokens_seen": 158975418,
      "step": 65
    },
    {
      "epoch": 0.06959578207381371,
      "grad_norm": 0.8688381314277649,
      "learning_rate": 0.00032500000000000004,
      "loss": 11.7594,
      "num_input_tokens_seen": 161420368,
      "step": 66
    },
    {
      "epoch": 0.07065026362038665,
      "grad_norm": 0.9749491810798645,
      "learning_rate": 0.00033,
      "loss": 11.722,
      "num_input_tokens_seen": 163923386,
      "step": 67
    },
    {
      "epoch": 0.07170474516695957,
      "grad_norm": 1.0640383958816528,
      "learning_rate": 0.000335,
      "loss": 10.076,
      "num_input_tokens_seen": 166570580,
      "step": 68
    },
    {
      "epoch": 0.07275922671353251,
      "grad_norm": 0.8262693881988525,
      "learning_rate": 0.00034,
      "loss": 11.4312,
      "num_input_tokens_seen": 169085496,
      "step": 69
    },
    {
      "epoch": 0.07381370826010544,
      "grad_norm": 0.8046846389770508,
      "learning_rate": 0.000345,
      "loss": 11.5264,
      "num_input_tokens_seen": 171510744,
      "step": 70
    },
    {
      "epoch": 0.07486818980667838,
      "grad_norm": 0.8855931758880615,
      "learning_rate": 0.00035,
      "loss": 11.3249,
      "num_input_tokens_seen": 173889198,
      "step": 71
    },
    {
      "epoch": 0.07592267135325131,
      "grad_norm": 0.8355636596679688,
      "learning_rate": 0.000355,
      "loss": 11.1966,
      "num_input_tokens_seen": 176486654,
      "step": 72
    },
    {
      "epoch": 0.07697715289982425,
      "grad_norm": 0.8339463472366333,
      "learning_rate": 0.00035999999999999997,
      "loss": 11.4988,
      "num_input_tokens_seen": 178783436,
      "step": 73
    },
    {
      "epoch": 0.07803163444639719,
      "grad_norm": 0.9186501502990723,
      "learning_rate": 0.000365,
      "loss": 11.9924,
      "num_input_tokens_seen": 181065054,
      "step": 74
    },
    {
      "epoch": 0.07908611599297012,
      "grad_norm": 0.8586037158966064,
      "learning_rate": 0.00037,
      "loss": 11.5861,
      "num_input_tokens_seen": 183491460,
      "step": 75
    },
    {
      "epoch": 0.08014059753954306,
      "grad_norm": 0.8457223773002625,
      "learning_rate": 0.000375,
      "loss": 10.4982,
      "num_input_tokens_seen": 185871790,
      "step": 76
    },
    {
      "epoch": 0.08119507908611599,
      "grad_norm": 0.9979950785636902,
      "learning_rate": 0.00038,
      "loss": 11.2212,
      "num_input_tokens_seen": 188255230,
      "step": 77
    },
    {
      "epoch": 0.08224956063268893,
      "grad_norm": 0.7799087762832642,
      "learning_rate": 0.00038500000000000003,
      "loss": 11.6828,
      "num_input_tokens_seen": 190823556,
      "step": 78
    },
    {
      "epoch": 0.08330404217926186,
      "grad_norm": 0.8413819670677185,
      "learning_rate": 0.00039000000000000005,
      "loss": 11.7884,
      "num_input_tokens_seen": 193241694,
      "step": 79
    },
    {
      "epoch": 0.0843585237258348,
      "grad_norm": 0.9957459568977356,
      "learning_rate": 0.000395,
      "loss": 10.9958,
      "num_input_tokens_seen": 195610918,
      "step": 80
    },
    {
      "epoch": 0.08541300527240774,
      "grad_norm": 0.9195905923843384,
      "learning_rate": 0.0004,
      "loss": 10.5817,
      "num_input_tokens_seen": 197988346,
      "step": 81
    },
    {
      "epoch": 0.08646748681898067,
      "grad_norm": 0.7436060905456543,
      "learning_rate": 0.00040500000000000003,
      "loss": 11.3973,
      "num_input_tokens_seen": 200427190,
      "step": 82
    },
    {
      "epoch": 0.0875219683655536,
      "grad_norm": 0.6289843916893005,
      "learning_rate": 0.00041,
      "loss": 10.6944,
      "num_input_tokens_seen": 202809982,
      "step": 83
    },
    {
      "epoch": 0.08857644991212654,
      "grad_norm": 1.1031980514526367,
      "learning_rate": 0.000415,
      "loss": 9.3328,
      "num_input_tokens_seen": 205157580,
      "step": 84
    },
    {
      "epoch": 0.08963093145869948,
      "grad_norm": 1.117293357849121,
      "learning_rate": 0.00042,
      "loss": 10.7368,
      "num_input_tokens_seen": 207687796,
      "step": 85
    },
    {
      "epoch": 0.09068541300527241,
      "grad_norm": 1.0667115449905396,
      "learning_rate": 0.000425,
      "loss": 11.7286,
      "num_input_tokens_seen": 209997718,
      "step": 86
    },
    {
      "epoch": 0.09173989455184535,
      "grad_norm": 0.831766664981842,
      "learning_rate": 0.00043,
      "loss": 12.5704,
      "num_input_tokens_seen": 212407844,
      "step": 87
    },
    {
      "epoch": 0.09279437609841827,
      "grad_norm": 0.7932964563369751,
      "learning_rate": 0.000435,
      "loss": 11.0015,
      "num_input_tokens_seen": 215008632,
      "step": 88
    },
    {
      "epoch": 0.09384885764499121,
      "grad_norm": 0.8345858454704285,
      "learning_rate": 0.00044,
      "loss": 10.693,
      "num_input_tokens_seen": 217393470,
      "step": 89
    },
    {
      "epoch": 0.09490333919156414,
      "grad_norm": 0.8093012571334839,
      "learning_rate": 0.00044500000000000003,
      "loss": 11.7683,
      "num_input_tokens_seen": 219847368,
      "step": 90
    },
    {
      "epoch": 0.09595782073813708,
      "grad_norm": 0.7983007431030273,
      "learning_rate": 0.00045000000000000004,
      "loss": 12.1621,
      "num_input_tokens_seen": 222195586,
      "step": 91
    },
    {
      "epoch": 0.09701230228471001,
      "grad_norm": 0.8151090741157532,
      "learning_rate": 0.000455,
      "loss": 10.6503,
      "num_input_tokens_seen": 224689946,
      "step": 92
    },
    {
      "epoch": 0.09806678383128295,
      "grad_norm": 0.8428967595100403,
      "learning_rate": 0.00046,
      "loss": 11.032,
      "num_input_tokens_seen": 227147082,
      "step": 93
    },
    {
      "epoch": 0.09912126537785589,
      "grad_norm": 0.7828782200813293,
      "learning_rate": 0.000465,
      "loss": 11.3009,
      "num_input_tokens_seen": 229639860,
      "step": 94
    },
    {
      "epoch": 0.10017574692442882,
      "grad_norm": 0.7996600866317749,
      "learning_rate": 0.00047,
      "loss": 10.4206,
      "num_input_tokens_seen": 232075288,
      "step": 95
    },
    {
      "epoch": 0.10123022847100176,
      "grad_norm": 0.7270877361297607,
      "learning_rate": 0.000475,
      "loss": 11.8104,
      "num_input_tokens_seen": 234546596,
      "step": 96
    },
    {
      "epoch": 0.10228471001757469,
      "grad_norm": 0.8223890662193298,
      "learning_rate": 0.00048,
      "loss": 11.0354,
      "num_input_tokens_seen": 237127696,
      "step": 97
    },
    {
      "epoch": 0.10333919156414763,
      "grad_norm": 0.6856156587600708,
      "learning_rate": 0.00048499999999999997,
      "loss": 10.5128,
      "num_input_tokens_seen": 239595852,
      "step": 98
    },
    {
      "epoch": 0.10439367311072056,
      "grad_norm": 0.75257807970047,
      "learning_rate": 0.00049,
      "loss": 10.3306,
      "num_input_tokens_seen": 242124460,
      "step": 99
    },
    {
      "epoch": 0.1054481546572935,
      "grad_norm": 0.8604240417480469,
      "learning_rate": 0.000495,
      "loss": 11.7441,
      "num_input_tokens_seen": 244549536,
      "step": 100
    },
    {
      "epoch": 0.10650263620386644,
      "grad_norm": 0.7984803318977356,
      "learning_rate": 0.0005,
      "loss": 11.4844,
      "num_input_tokens_seen": 246899676,
      "step": 101
    },
    {
      "epoch": 0.10755711775043937,
      "grad_norm": 0.9181137084960938,
      "learning_rate": 0.0004999922894119685,
      "loss": 11.1044,
      "num_input_tokens_seen": 249263792,
      "step": 102
    },
    {
      "epoch": 0.1086115992970123,
      "grad_norm": 0.719553530216217,
      "learning_rate": 0.0004999691581234994,
      "loss": 11.1713,
      "num_input_tokens_seen": 251764084,
      "step": 103
    },
    {
      "epoch": 0.10966608084358524,
      "grad_norm": 0.9228735566139221,
      "learning_rate": 0.0004999306075614394,
      "loss": 9.0385,
      "num_input_tokens_seen": 254190814,
      "step": 104
    },
    {
      "epoch": 0.11072056239015818,
      "grad_norm": 0.7710055112838745,
      "learning_rate": 0.0004998766401037688,
      "loss": 10.3265,
      "num_input_tokens_seen": 256625058,
      "step": 105
    },
    {
      "epoch": 0.11177504393673111,
      "grad_norm": 0.6903572678565979,
      "learning_rate": 0.0004998072590794548,
      "loss": 11.4626,
      "num_input_tokens_seen": 259008258,
      "step": 106
    },
    {
      "epoch": 0.11282952548330404,
      "grad_norm": 0.7966758012771606,
      "learning_rate": 0.0004997224687682457,
      "loss": 10.8277,
      "num_input_tokens_seen": 261428048,
      "step": 107
    },
    {
      "epoch": 0.11388400702987697,
      "grad_norm": 0.9058545827865601,
      "learning_rate": 0.000499622274400407,
      "loss": 10.7112,
      "num_input_tokens_seen": 263817432,
      "step": 108
    },
    {
      "epoch": 0.11493848857644991,
      "grad_norm": 0.7410884499549866,
      "learning_rate": 0.0004995066821563998,
      "loss": 10.9133,
      "num_input_tokens_seen": 266228540,
      "step": 109
    },
    {
      "epoch": 0.11599297012302284,
      "grad_norm": 0.7807892560958862,
      "learning_rate": 0.0004993756991664976,
      "loss": 10.6102,
      "num_input_tokens_seen": 268491920,
      "step": 110
    },
    {
      "epoch": 0.11704745166959578,
      "grad_norm": 0.9086952805519104,
      "learning_rate": 0.0004992293335103487,
      "loss": 10.5466,
      "num_input_tokens_seen": 271003672,
      "step": 111
    },
    {
      "epoch": 0.11810193321616871,
      "grad_norm": 0.8595651984214783,
      "learning_rate": 0.0004990675942164759,
      "loss": 10.8544,
      "num_input_tokens_seen": 273280584,
      "step": 112
    },
    {
      "epoch": 0.11915641476274165,
      "grad_norm": 0.6959360241889954,
      "learning_rate": 0.0004988904912617209,
      "loss": 10.8134,
      "num_input_tokens_seen": 275653910,
      "step": 113
    },
    {
      "epoch": 0.12021089630931459,
      "grad_norm": 0.6293642520904541,
      "learning_rate": 0.000498698035570628,
      "loss": 10.9262,
      "num_input_tokens_seen": 278191980,
      "step": 114
    },
    {
      "epoch": 0.12126537785588752,
      "grad_norm": 0.6851038336753845,
      "learning_rate": 0.0004984902390147711,
      "loss": 10.6058,
      "num_input_tokens_seen": 280577286,
      "step": 115
    },
    {
      "epoch": 0.12231985940246046,
      "grad_norm": 0.5610032677650452,
      "learning_rate": 0.0004982671144120202,
      "loss": 11.7788,
      "num_input_tokens_seen": 283062546,
      "step": 116
    },
    {
      "epoch": 0.12337434094903339,
      "grad_norm": 0.592146098613739,
      "learning_rate": 0.000498028675525752,
      "loss": 11.8272,
      "num_input_tokens_seen": 285359532,
      "step": 117
    },
    {
      "epoch": 0.12442882249560633,
      "grad_norm": 0.6767431497573853,
      "learning_rate": 0.000497774937064,
      "loss": 10.7975,
      "num_input_tokens_seen": 287755300,
      "step": 118
    },
    {
      "epoch": 0.12548330404217925,
      "grad_norm": 0.7958774566650391,
      "learning_rate": 0.0004975059146785479,
      "loss": 10.2351,
      "num_input_tokens_seen": 290138596,
      "step": 119
    },
    {
      "epoch": 0.1265377855887522,
      "grad_norm": 0.6161935925483704,
      "learning_rate": 0.0004972216249639638,
      "loss": 10.9129,
      "num_input_tokens_seen": 292503656,
      "step": 120
    },
    {
      "epoch": 0.12759226713532512,
      "grad_norm": 0.7886815667152405,
      "learning_rate": 0.000496922085456576,
      "loss": 10.3267,
      "num_input_tokens_seen": 294918832,
      "step": 121
    },
    {
      "epoch": 0.12864674868189807,
      "grad_norm": 0.5889380574226379,
      "learning_rate": 0.0004966073146333924,
      "loss": 11.578,
      "num_input_tokens_seen": 297328590,
      "step": 122
    },
    {
      "epoch": 0.129701230228471,
      "grad_norm": 0.6609049439430237,
      "learning_rate": 0.0004962773319109604,
      "loss": 11.0731,
      "num_input_tokens_seen": 299705308,
      "step": 123
    },
    {
      "epoch": 0.13075571177504394,
      "grad_norm": 0.6637356281280518,
      "learning_rate": 0.0004959321576441683,
      "loss": 10.449,
      "num_input_tokens_seen": 302143056,
      "step": 124
    },
    {
      "epoch": 0.13181019332161686,
      "grad_norm": 0.5731056332588196,
      "learning_rate": 0.0004955718131249909,
      "loss": 10.5012,
      "num_input_tokens_seen": 304570734,
      "step": 125
    },
    {
      "epoch": 0.1328646748681898,
      "grad_norm": 0.7307013869285583,
      "learning_rate": 0.0004951963205811756,
      "loss": 10.557,
      "num_input_tokens_seen": 306918736,
      "step": 126
    },
    {
      "epoch": 0.13391915641476274,
      "grad_norm": 0.4749371111392975,
      "learning_rate": 0.0004948057031748712,
      "loss": 12.2914,
      "num_input_tokens_seen": 309461984,
      "step": 127
    },
    {
      "epoch": 0.13497363796133569,
      "grad_norm": 0.8126282095909119,
      "learning_rate": 0.0004943999850011993,
      "loss": 10.0878,
      "num_input_tokens_seen": 311925540,
      "step": 128
    },
    {
      "epoch": 0.1360281195079086,
      "grad_norm": 0.5017863512039185,
      "learning_rate": 0.0004939791910867678,
      "loss": 12.0397,
      "num_input_tokens_seen": 314443604,
      "step": 129
    },
    {
      "epoch": 0.13708260105448156,
      "grad_norm": 0.5224993228912354,
      "learning_rate": 0.0004935433473881276,
      "loss": 12.0857,
      "num_input_tokens_seen": 316817696,
      "step": 130
    },
    {
      "epoch": 0.13813708260105448,
      "grad_norm": 0.4489041566848755,
      "learning_rate": 0.0004930924807901711,
      "loss": 10.8638,
      "num_input_tokens_seen": 319389504,
      "step": 131
    },
    {
      "epoch": 0.13919156414762743,
      "grad_norm": 0.6408200263977051,
      "learning_rate": 0.0004926266191044738,
      "loss": 11.0014,
      "num_input_tokens_seen": 321932538,
      "step": 132
    },
    {
      "epoch": 0.14024604569420035,
      "grad_norm": 0.5280624628067017,
      "learning_rate": 0.0004921457910675788,
      "loss": 11.3467,
      "num_input_tokens_seen": 324411930,
      "step": 133
    },
    {
      "epoch": 0.1413005272407733,
      "grad_norm": 0.5165160894393921,
      "learning_rate": 0.0004916500263392243,
      "loss": 11.0076,
      "num_input_tokens_seen": 326731560,
      "step": 134
    },
    {
      "epoch": 0.14235500878734622,
      "grad_norm": 0.5510214567184448,
      "learning_rate": 0.000491139355500514,
      "loss": 10.9273,
      "num_input_tokens_seen": 329243246,
      "step": 135
    },
    {
      "epoch": 0.14340949033391914,
      "grad_norm": 0.6016185283660889,
      "learning_rate": 0.0004906138100520309,
      "loss": 10.7259,
      "num_input_tokens_seen": 331831630,
      "step": 136
    },
    {
      "epoch": 0.1444639718804921,
      "grad_norm": 0.6088196635246277,
      "learning_rate": 0.0004900734224118936,
      "loss": 10.6628,
      "num_input_tokens_seen": 334302218,
      "step": 137
    },
    {
      "epoch": 0.14551845342706501,
      "grad_norm": 0.6214354634284973,
      "learning_rate": 0.0004895182259137573,
      "loss": 11.8801,
      "num_input_tokens_seen": 336913326,
      "step": 138
    },
    {
      "epoch": 0.14657293497363796,
      "grad_norm": 0.422093003988266,
      "learning_rate": 0.0004889482548047572,
      "loss": 12.4677,
      "num_input_tokens_seen": 339358906,
      "step": 139
    },
    {
      "epoch": 0.14762741652021089,
      "grad_norm": 0.5529237389564514,
      "learning_rate": 0.0004883635442433959,
      "loss": 10.4447,
      "num_input_tokens_seen": 341933644,
      "step": 140
    },
    {
      "epoch": 0.14868189806678384,
      "grad_norm": 0.5171710848808289,
      "learning_rate": 0.0004877641302973755,
      "loss": 10.9242,
      "num_input_tokens_seen": 344324576,
      "step": 141
    },
    {
      "epoch": 0.14973637961335676,
      "grad_norm": 0.49143025279045105,
      "learning_rate": 0.00048715004994137124,
      "loss": 10.0709,
      "num_input_tokens_seen": 346908972,
      "step": 142
    },
    {
      "epoch": 0.1507908611599297,
      "grad_norm": 0.7775588035583496,
      "learning_rate": 0.0004865213410547524,
      "loss": 11.0975,
      "num_input_tokens_seen": 349386838,
      "step": 143
    },
    {
      "epoch": 0.15184534270650263,
      "grad_norm": 0.6548316478729248,
      "learning_rate": 0.0004858780424192443,
      "loss": 11.7805,
      "num_input_tokens_seen": 351755336,
      "step": 144
    },
    {
      "epoch": 0.15289982425307558,
      "grad_norm": 0.4432781934738159,
      "learning_rate": 0.0004852201937165372,
      "loss": 11.3553,
      "num_input_tokens_seen": 354150620,
      "step": 145
    },
    {
      "epoch": 0.1539543057996485,
      "grad_norm": 0.6089203953742981,
      "learning_rate": 0.0004845478355258377,
      "loss": 10.295,
      "num_input_tokens_seen": 356645140,
      "step": 146
    },
    {
      "epoch": 0.15500878734622145,
      "grad_norm": 0.5045962929725647,
      "learning_rate": 0.00048386100932136614,
      "loss": 11.6037,
      "num_input_tokens_seen": 358928648,
      "step": 147
    },
    {
      "epoch": 0.15606326889279437,
      "grad_norm": 0.4435243606567383,
      "learning_rate": 0.00048315975746979797,
      "loss": 11.9737,
      "num_input_tokens_seen": 361553144,
      "step": 148
    },
    {
      "epoch": 0.15711775043936732,
      "grad_norm": 0.5178308486938477,
      "learning_rate": 0.0004824441232276507,
      "loss": 11.3986,
      "num_input_tokens_seen": 364124878,
      "step": 149
    },
    {
      "epoch": 0.15817223198594024,
      "grad_norm": 0.5703669190406799,
      "learning_rate": 0.0004817141507386153,
      "loss": 11.407,
      "num_input_tokens_seen": 366451036,
      "step": 150
    },
    {
      "epoch": 0.1592267135325132,
      "grad_norm": 0.5979743599891663,
      "learning_rate": 0.0004809698850308334,
      "loss": 10.9108,
      "num_input_tokens_seen": 368799018,
      "step": 151
    },
    {
      "epoch": 0.16028119507908611,
      "grad_norm": 0.4265318214893341,
      "learning_rate": 0.0004802113720141196,
      "loss": 11.0061,
      "num_input_tokens_seen": 371286512,
      "step": 152
    },
    {
      "epoch": 0.16133567662565906,
      "grad_norm": 0.6489496231079102,
      "learning_rate": 0.00047943865847712965,
      "loss": 10.3601,
      "num_input_tokens_seen": 373790542,
      "step": 153
    },
    {
      "epoch": 0.16239015817223199,
      "grad_norm": 0.3896006941795349,
      "learning_rate": 0.0004786517920844744,
      "loss": 11.7572,
      "num_input_tokens_seen": 376164786,
      "step": 154
    },
    {
      "epoch": 0.1634446397188049,
      "grad_norm": 0.48660165071487427,
      "learning_rate": 0.00047785082137377936,
      "loss": 11.2828,
      "num_input_tokens_seen": 378668934,
      "step": 155
    },
    {
      "epoch": 0.16449912126537786,
      "grad_norm": 0.8149150609970093,
      "learning_rate": 0.000477035795752691,
      "loss": 10.8224,
      "num_input_tokens_seen": 380982868,
      "step": 156
    },
    {
      "epoch": 0.16555360281195078,
      "grad_norm": 0.3987499475479126,
      "learning_rate": 0.0004762067654958286,
      "loss": 11.302,
      "num_input_tokens_seen": 383412848,
      "step": 157
    },
    {
      "epoch": 0.16660808435852373,
      "grad_norm": 0.48311105370521545,
      "learning_rate": 0.0004753637817416835,
      "loss": 11.1952,
      "num_input_tokens_seen": 385890530,
      "step": 158
    },
    {
      "epoch": 0.16766256590509665,
      "grad_norm": 0.460369348526001,
      "learning_rate": 0.0004745068964894645,
      "loss": 10.6698,
      "num_input_tokens_seen": 388331186,
      "step": 159
    },
    {
      "epoch": 0.1687170474516696,
      "grad_norm": 0.7765836119651794,
      "learning_rate": 0.00047363616259589025,
      "loss": 10.34,
      "num_input_tokens_seen": 390722478,
      "step": 160
    },
    {
      "epoch": 0.16977152899824252,
      "grad_norm": 0.5638030171394348,
      "learning_rate": 0.00047275163377192886,
      "loss": 10.3372,
      "num_input_tokens_seen": 393128528,
      "step": 161
    },
    {
      "epoch": 0.17082601054481547,
      "grad_norm": 0.3865327537059784,
      "learning_rate": 0.0004718533645794847,
      "loss": 12.1565,
      "num_input_tokens_seen": 395710636,
      "step": 162
    },
    {
      "epoch": 0.1718804920913884,
      "grad_norm": 0.46866747736930847,
      "learning_rate": 0.0004709414104280326,
      "loss": 11.4228,
      "num_input_tokens_seen": 398179608,
      "step": 163
    },
    {
      "epoch": 0.17293497363796134,
      "grad_norm": 0.5363028049468994,
      "learning_rate": 0.00047001582757120054,
      "loss": 10.9585,
      "num_input_tokens_seen": 400581072,
      "step": 164
    },
    {
      "epoch": 0.17398945518453426,
      "grad_norm": 0.4994870722293854,
      "learning_rate": 0.00046907667310329887,
      "loss": 10.8748,
      "num_input_tokens_seen": 403057566,
      "step": 165
    },
    {
      "epoch": 0.1750439367311072,
      "grad_norm": 0.6035915017127991,
      "learning_rate": 0.0004681240049557991,
      "loss": 10.9428,
      "num_input_tokens_seen": 405479554,
      "step": 166
    },
    {
      "epoch": 0.17609841827768014,
      "grad_norm": 0.5696356892585754,
      "learning_rate": 0.00046715788189375995,
      "loss": 11.4068,
      "num_input_tokens_seen": 407921128,
      "step": 167
    },
    {
      "epoch": 0.17715289982425309,
      "grad_norm": 0.5532790422439575,
      "learning_rate": 0.0004661783635122028,
      "loss": 11.0868,
      "num_input_tokens_seen": 410550558,
      "step": 168
    },
    {
      "epoch": 0.178207381370826,
      "grad_norm": 0.43119895458221436,
      "learning_rate": 0.0004651855102324352,
      "loss": 11.4107,
      "num_input_tokens_seen": 412953064,
      "step": 169
    },
    {
      "epoch": 0.17926186291739896,
      "grad_norm": 0.9992315769195557,
      "learning_rate": 0.0004641793832983245,
      "loss": 9.5065,
      "num_input_tokens_seen": 415501368,
      "step": 170
    },
    {
      "epoch": 0.18031634446397188,
      "grad_norm": 0.5675984621047974,
      "learning_rate": 0.0004631600447725189,
      "loss": 11.4787,
      "num_input_tokens_seen": 417838436,
      "step": 171
    },
    {
      "epoch": 0.18137082601054483,
      "grad_norm": 0.4894881546497345,
      "learning_rate": 0.0004621275575326206,
      "loss": 11.05,
      "num_input_tokens_seen": 420236388,
      "step": 172
    },
    {
      "epoch": 0.18242530755711775,
      "grad_norm": 0.5870826244354248,
      "learning_rate": 0.00046108198526730563,
      "loss": 11.1987,
      "num_input_tokens_seen": 422659540,
      "step": 173
    },
    {
      "epoch": 0.1834797891036907,
      "grad_norm": 0.5805984139442444,
      "learning_rate": 0.0004600233924723966,
      "loss": 10.3112,
      "num_input_tokens_seen": 425004762,
      "step": 174
    },
    {
      "epoch": 0.18453427065026362,
      "grad_norm": 0.5345659852027893,
      "learning_rate": 0.0004589518444468836,
      "loss": 10.6756,
      "num_input_tokens_seen": 427453028,
      "step": 175
    },
    {
      "epoch": 0.18558875219683654,
      "grad_norm": 0.4662725627422333,
      "learning_rate": 0.000457867407288896,
      "loss": 11.9868,
      "num_input_tokens_seen": 429911724,
      "step": 176
    },
    {
      "epoch": 0.1866432337434095,
      "grad_norm": 0.4901849329471588,
      "learning_rate": 0.0004567701478916261,
      "loss": 12.0078,
      "num_input_tokens_seen": 432286308,
      "step": 177
    },
    {
      "epoch": 0.18769771528998241,
      "grad_norm": 0.4592384994029999,
      "learning_rate": 0.00045566013393920205,
      "loss": 11.7783,
      "num_input_tokens_seen": 434795636,
      "step": 178
    },
    {
      "epoch": 0.18875219683655536,
      "grad_norm": 0.4543682336807251,
      "learning_rate": 0.0004545374339025129,
      "loss": 11.9031,
      "num_input_tokens_seen": 437315386,
      "step": 179
    },
    {
      "epoch": 0.18980667838312829,
      "grad_norm": 0.5531622767448425,
      "learning_rate": 0.0004534021170349856,
      "loss": 10.913,
      "num_input_tokens_seen": 439795046,
      "step": 180
    },
    {
      "epoch": 0.19086115992970124,
      "grad_norm": 0.4865996539592743,
      "learning_rate": 0.000452254253368312,
      "loss": 10.9763,
      "num_input_tokens_seen": 442280862,
      "step": 181
    },
    {
      "epoch": 0.19191564147627416,
      "grad_norm": 0.5476157665252686,
      "learning_rate": 0.0004510939137081302,
      "loss": 11.3704,
      "num_input_tokens_seen": 444878730,
      "step": 182
    },
    {
      "epoch": 0.1929701230228471,
      "grad_norm": 0.7855698466300964,
      "learning_rate": 0.00044992116962965623,
      "loss": 11.4159,
      "num_input_tokens_seen": 447229276,
      "step": 183
    },
    {
      "epoch": 0.19402460456942003,
      "grad_norm": 0.5010231137275696,
      "learning_rate": 0.00044873609347326866,
      "loss": 12.1404,
      "num_input_tokens_seen": 449598746,
      "step": 184
    },
    {
      "epoch": 0.19507908611599298,
      "grad_norm": 0.7411155104637146,
      "learning_rate": 0.0004475387583400473,
      "loss": 9.5508,
      "num_input_tokens_seen": 452111232,
      "step": 185
    },
    {
      "epoch": 0.1961335676625659,
      "grad_norm": 0.678528904914856,
      "learning_rate": 0.00044632923808726293,
      "loss": 11.2098,
      "num_input_tokens_seen": 454483758,
      "step": 186
    },
    {
      "epoch": 0.19718804920913885,
      "grad_norm": 0.49200311303138733,
      "learning_rate": 0.0004451076073238223,
      "loss": 11.6097,
      "num_input_tokens_seen": 456962194,
      "step": 187
    },
    {
      "epoch": 0.19824253075571177,
      "grad_norm": 0.44871610403060913,
      "learning_rate": 0.0004438739414056651,
      "loss": 11.005,
      "num_input_tokens_seen": 459290608,
      "step": 188
    },
    {
      "epoch": 0.19929701230228472,
      "grad_norm": 0.42474889755249023,
      "learning_rate": 0.0004426283164311162,
      "loss": 12.443,
      "num_input_tokens_seen": 461679768,
      "step": 189
    },
    {
      "epoch": 0.20035149384885764,
      "grad_norm": 0.553240180015564,
      "learning_rate": 0.00044137080923619174,
      "loss": 10.8901,
      "num_input_tokens_seen": 464264660,
      "step": 190
    },
    {
      "epoch": 0.2014059753954306,
      "grad_norm": 0.688330888748169,
      "learning_rate": 0.0004401014973898586,
      "loss": 10.2717,
      "num_input_tokens_seen": 466692112,
      "step": 191
    },
    {
      "epoch": 0.2024604569420035,
      "grad_norm": 0.5714016556739807,
      "learning_rate": 0.0004388204591892506,
      "loss": 10.0244,
      "num_input_tokens_seen": 469183024,
      "step": 192
    },
    {
      "epoch": 0.20351493848857646,
      "grad_norm": 0.5069180727005005,
      "learning_rate": 0.00043752777365483816,
      "loss": 11.5811,
      "num_input_tokens_seen": 471674424,
      "step": 193
    },
    {
      "epoch": 0.20456942003514939,
      "grad_norm": 0.5883907675743103,
      "learning_rate": 0.0004362235205255541,
      "loss": 10.2173,
      "num_input_tokens_seen": 473839978,
      "step": 194
    },
    {
      "epoch": 0.2056239015817223,
      "grad_norm": 0.59784996509552,
      "learning_rate": 0.0004349077802538751,
      "loss": 10.8403,
      "num_input_tokens_seen": 476332186,
      "step": 195
    },
    {
      "epoch": 0.20667838312829526,
      "grad_norm": 0.39995861053466797,
      "learning_rate": 0.0004335806340008587,
      "loss": 11.1878,
      "num_input_tokens_seen": 478785370,
      "step": 196
    },
    {
      "epoch": 0.20773286467486818,
      "grad_norm": 0.33949345350265503,
      "learning_rate": 0.00043224216363113723,
      "loss": 11.6166,
      "num_input_tokens_seen": 481219648,
      "step": 197
    },
    {
      "epoch": 0.20878734622144113,
      "grad_norm": 0.5417101979255676,
      "learning_rate": 0.0004308924517078678,
      "loss": 11.326,
      "num_input_tokens_seen": 483719790,
      "step": 198
    },
    {
      "epoch": 0.20984182776801405,
      "grad_norm": 0.38530680537223816,
      "learning_rate": 0.00042953158148763975,
      "loss": 11.3671,
      "num_input_tokens_seen": 486326140,
      "step": 199
    },
    {
      "epoch": 0.210896309314587,
      "grad_norm": 0.5097330808639526,
      "learning_rate": 0.0004281596369153384,
      "loss": 11.0896,
      "num_input_tokens_seen": 488789092,
      "step": 200
    },
    {
      "epoch": 0.21195079086115992,
      "grad_norm": 0.5015902519226074,
      "learning_rate": 0.0004267767026189673,
      "loss": 12.1989,
      "num_input_tokens_seen": 491188440,
      "step": 201
    },
    {
      "epoch": 0.21300527240773287,
      "grad_norm": 0.5227989554405212,
      "learning_rate": 0.00042538286390442833,
      "loss": 10.9501,
      "num_input_tokens_seen": 493543466,
      "step": 202
    },
    {
      "epoch": 0.2140597539543058,
      "grad_norm": 0.5817456245422363,
      "learning_rate": 0.00042397820675025866,
      "loss": 10.7432,
      "num_input_tokens_seen": 496149784,
      "step": 203
    },
    {
      "epoch": 0.21511423550087874,
      "grad_norm": 0.5026383399963379,
      "learning_rate": 0.0004225628178023283,
      "loss": 10.6559,
      "num_input_tokens_seen": 498838520,
      "step": 204
    },
    {
      "epoch": 0.21616871704745166,
      "grad_norm": 0.6414695382118225,
      "learning_rate": 0.00042113678436849454,
      "loss": 10.5973,
      "num_input_tokens_seen": 501399136,
      "step": 205
    },
    {
      "epoch": 0.2172231985940246,
      "grad_norm": 0.5009418725967407,
      "learning_rate": 0.0004197001944132168,
      "loss": 11.3261,
      "num_input_tokens_seen": 503776514,
      "step": 206
    },
    {
      "epoch": 0.21827768014059754,
      "grad_norm": 0.4332464635372162,
      "learning_rate": 0.0004182531365521305,
      "loss": 11.6269,
      "num_input_tokens_seen": 506130888,
      "step": 207
    },
    {
      "epoch": 0.21933216168717048,
      "grad_norm": 0.4053120017051697,
      "learning_rate": 0.0004167957000465808,
      "loss": 11.353,
      "num_input_tokens_seen": 508565728,
      "step": 208
    },
    {
      "epoch": 0.2203866432337434,
      "grad_norm": 0.5031690001487732,
      "learning_rate": 0.00041532797479811636,
      "loss": 11.5352,
      "num_input_tokens_seen": 511010390,
      "step": 209
    },
    {
      "epoch": 0.22144112478031636,
      "grad_norm": 0.662989616394043,
      "learning_rate": 0.00041385005134294417,
      "loss": 10.9617,
      "num_input_tokens_seen": 513483182,
      "step": 210
    },
    {
      "epoch": 0.22249560632688928,
      "grad_norm": 0.40385428071022034,
      "learning_rate": 0.00041236202084634466,
      "loss": 11.2634,
      "num_input_tokens_seen": 515869144,
      "step": 211
    },
    {
      "epoch": 0.22355008787346223,
      "grad_norm": 0.4567122459411621,
      "learning_rate": 0.0004108639750970481,
      "loss": 10.5655,
      "num_input_tokens_seen": 518419596,
      "step": 212
    },
    {
      "epoch": 0.22460456942003515,
      "grad_norm": 0.38430649042129517,
      "learning_rate": 0.00040935600650157265,
      "loss": 11.2328,
      "num_input_tokens_seen": 520915978,
      "step": 213
    },
    {
      "epoch": 0.22565905096660807,
      "grad_norm": 0.3853931725025177,
      "learning_rate": 0.00040783820807852457,
      "loss": 10.8903,
      "num_input_tokens_seen": 523288654,
      "step": 214
    },
    {
      "epoch": 0.22671353251318102,
      "grad_norm": 0.5151433348655701,
      "learning_rate": 0.00040631067345285994,
      "loss": 10.5469,
      "num_input_tokens_seen": 525939782,
      "step": 215
    },
    {
      "epoch": 0.22776801405975394,
      "grad_norm": 0.5899290442466736,
      "learning_rate": 0.0004047734968501098,
      "loss": 10.6225,
      "num_input_tokens_seen": 528213108,
      "step": 216
    },
    {
      "epoch": 0.2288224956063269,
      "grad_norm": 0.5515417456626892,
      "learning_rate": 0.0004032267730905678,
      "loss": 11.1403,
      "num_input_tokens_seen": 530690074,
      "step": 217
    },
    {
      "epoch": 0.22987697715289981,
      "grad_norm": 0.6135182976722717,
      "learning_rate": 0.00040167059758344114,
      "loss": 9.9438,
      "num_input_tokens_seen": 533032048,
      "step": 218
    },
    {
      "epoch": 0.23093145869947276,
      "grad_norm": 0.4371633529663086,
      "learning_rate": 0.00040010506632096537,
      "loss": 11.5981,
      "num_input_tokens_seen": 535625558,
      "step": 219
    },
    {
      "epoch": 0.23198594024604569,
      "grad_norm": 0.3425651490688324,
      "learning_rate": 0.0003985302758724831,
      "loss": 11.0162,
      "num_input_tokens_seen": 538342358,
      "step": 220
    },
    {
      "epoch": 0.23304042179261863,
      "grad_norm": 0.3134062886238098,
      "learning_rate": 0.000396946323378487,
      "loss": 12.1684,
      "num_input_tokens_seen": 540629126,
      "step": 221
    },
    {
      "epoch": 0.23409490333919156,
      "grad_norm": 0.5026021003723145,
      "learning_rate": 0.0003953533065446281,
      "loss": 11.837,
      "num_input_tokens_seen": 543221254,
      "step": 222
    },
    {
      "epoch": 0.2351493848857645,
      "grad_norm": 0.5490946769714355,
      "learning_rate": 0.00039375132363568836,
      "loss": 11.0225,
      "num_input_tokens_seen": 545592750,
      "step": 223
    },
    {
      "epoch": 0.23620386643233743,
      "grad_norm": 0.5616098642349243,
      "learning_rate": 0.00039214047346951974,
      "loss": 11.3559,
      "num_input_tokens_seen": 547974264,
      "step": 224
    },
    {
      "epoch": 0.23725834797891038,
      "grad_norm": 0.44445741176605225,
      "learning_rate": 0.00039052085541094823,
      "loss": 11.3691,
      "num_input_tokens_seen": 550455212,
      "step": 225
    },
    {
      "epoch": 0.2383128295254833,
      "grad_norm": 0.3331153690814972,
      "learning_rate": 0.0003888925693656447,
      "loss": 11.1528,
      "num_input_tokens_seen": 552934874,
      "step": 226
    },
    {
      "epoch": 0.23936731107205625,
      "grad_norm": 0.33000198006629944,
      "learning_rate": 0.00038725571577396254,
      "loss": 12.5381,
      "num_input_tokens_seen": 555415658,
      "step": 227
    },
    {
      "epoch": 0.24042179261862917,
      "grad_norm": 0.4085153341293335,
      "learning_rate": 0.0003856103956047413,
      "loss": 11.2043,
      "num_input_tokens_seen": 557910548,
      "step": 228
    },
    {
      "epoch": 0.24147627416520212,
      "grad_norm": 0.7109001278877258,
      "learning_rate": 0.0003839567103490793,
      "loss": 10.1943,
      "num_input_tokens_seen": 560400606,
      "step": 229
    },
    {
      "epoch": 0.24253075571177504,
      "grad_norm": 0.6416913866996765,
      "learning_rate": 0.0003822947620140726,
      "loss": 10.3457,
      "num_input_tokens_seen": 562814866,
      "step": 230
    },
    {
      "epoch": 0.243585237258348,
      "grad_norm": 0.43772706389427185,
      "learning_rate": 0.0003806246531165231,
      "loss": 12.1498,
      "num_input_tokens_seen": 565068902,
      "step": 231
    },
    {
      "epoch": 0.2446397188049209,
      "grad_norm": 0.4833686053752899,
      "learning_rate": 0.0003789464866766144,
      "loss": 10.6826,
      "num_input_tokens_seen": 567518434,
      "step": 232
    },
    {
      "epoch": 0.24569420035149384,
      "grad_norm": 0.37340158224105835,
      "learning_rate": 0.0003772603662115575,
      "loss": 11.1719,
      "num_input_tokens_seen": 569850658,
      "step": 233
    },
    {
      "epoch": 0.24674868189806679,
      "grad_norm": 0.5298442244529724,
      "learning_rate": 0.0003755663957292048,
      "loss": 9.6292,
      "num_input_tokens_seen": 572340312,
      "step": 234
    },
    {
      "epoch": 0.2478031634446397,
      "grad_norm": 0.48673802614212036,
      "learning_rate": 0.00037386467972163516,
      "loss": 10.7159,
      "num_input_tokens_seen": 574771196,
      "step": 235
    },
    {
      "epoch": 0.24885764499121266,
      "grad_norm": 0.6027830839157104,
      "learning_rate": 0.00037215532315870774,
      "loss": 11.0987,
      "num_input_tokens_seen": 577234360,
      "step": 236
    },
    {
      "epoch": 0.24991212653778558,
      "grad_norm": 0.47889307141304016,
      "learning_rate": 0.00037043843148158696,
      "loss": 10.5865,
      "num_input_tokens_seen": 579677372,
      "step": 237
    },
    {
      "epoch": 0.2509666080843585,
      "grad_norm": 0.46011844277381897,
      "learning_rate": 0.0003687141105962389,
      "loss": 11.7296,
      "num_input_tokens_seen": 582233734,
      "step": 238
    },
    {
      "epoch": 0.25202108963093145,
      "grad_norm": 0.39201974868774414,
      "learning_rate": 0.000366982466866898,
      "loss": 12.3676,
      "num_input_tokens_seen": 584774048,
      "step": 239
    },
    {
      "epoch": 0.2530755711775044,
      "grad_norm": 0.5027074813842773,
      "learning_rate": 0.00036524360710950624,
      "loss": 11.0958,
      "num_input_tokens_seen": 587165168,
      "step": 240
    },
    {
      "epoch": 0.25413005272407735,
      "grad_norm": 0.6349440217018127,
      "learning_rate": 0.0003634976385851242,
      "loss": 9.6468,
      "num_input_tokens_seen": 589531588,
      "step": 241
    },
    {
      "epoch": 0.25518453427065024,
      "grad_norm": 0.47264474630355835,
      "learning_rate": 0.00036174466899331484,
      "loss": 10.3429,
      "num_input_tokens_seen": 591851982,
      "step": 242
    },
    {
      "epoch": 0.2562390158172232,
      "grad_norm": 0.6780998706817627,
      "learning_rate": 0.0003599848064654995,
      "loss": 9.8026,
      "num_input_tokens_seen": 594293620,
      "step": 243
    },
    {
      "epoch": 0.25729349736379614,
      "grad_norm": 0.45961129665374756,
      "learning_rate": 0.000358218159558289,
      "loss": 11.1722,
      "num_input_tokens_seen": 596810748,
      "step": 244
    },
    {
      "epoch": 0.2583479789103691,
      "grad_norm": 0.5620695352554321,
      "learning_rate": 0.0003564448372467859,
      "loss": 11.2163,
      "num_input_tokens_seen": 599497050,
      "step": 245
    },
    {
      "epoch": 0.259402460456942,
      "grad_norm": 0.4004107713699341,
      "learning_rate": 0.0003546649489178636,
      "loss": 11.6294,
      "num_input_tokens_seen": 601846484,
      "step": 246
    },
    {
      "epoch": 0.26045694200351494,
      "grad_norm": 0.5842926502227783,
      "learning_rate": 0.00035287860436341824,
      "loss": 10.2072,
      "num_input_tokens_seen": 604339142,
      "step": 247
    },
    {
      "epoch": 0.2615114235500879,
      "grad_norm": 0.5138064026832581,
      "learning_rate": 0.0003510859137735964,
      "loss": 11.1892,
      "num_input_tokens_seen": 606890192,
      "step": 248
    },
    {
      "epoch": 0.26256590509666083,
      "grad_norm": 0.4497654139995575,
      "learning_rate": 0.00034928698772999787,
      "loss": 11.39,
      "num_input_tokens_seen": 609336404,
      "step": 249
    },
    {
      "epoch": 0.26362038664323373,
      "grad_norm": 0.47480809688568115,
      "learning_rate": 0.0003474819371988549,
      "loss": 10.8002,
      "num_input_tokens_seen": 611867684,
      "step": 250
    },
    {
      "epoch": 0.2646748681898067,
      "grad_norm": 0.49315816164016724,
      "learning_rate": 0.00034567087352418665,
      "loss": 9.7913,
      "num_input_tokens_seen": 614297542,
      "step": 251
    },
    {
      "epoch": 0.2657293497363796,
      "grad_norm": 0.532971978187561,
      "learning_rate": 0.0003438539084209315,
      "loss": 8.7019,
      "num_input_tokens_seen": 616909048,
      "step": 252
    },
    {
      "epoch": 0.2667838312829525,
      "grad_norm": 0.49788665771484375,
      "learning_rate": 0.0003420311539680557,
      "loss": 10.8312,
      "num_input_tokens_seen": 619209032,
      "step": 253
    },
    {
      "epoch": 0.26783831282952547,
      "grad_norm": 0.5600563883781433,
      "learning_rate": 0.00034020272260163977,
      "loss": 10.4957,
      "num_input_tokens_seen": 621491468,
      "step": 254
    },
    {
      "epoch": 0.2688927943760984,
      "grad_norm": 0.46124720573425293,
      "learning_rate": 0.0003383687271079432,
      "loss": 11.2727,
      "num_input_tokens_seen": 623952608,
      "step": 255
    },
    {
      "epoch": 0.26994727592267137,
      "grad_norm": 0.4204480051994324,
      "learning_rate": 0.0003365292806164468,
      "loss": 10.2706,
      "num_input_tokens_seen": 626508340,
      "step": 256
    },
    {
      "epoch": 0.27100175746924426,
      "grad_norm": 0.35226359963417053,
      "learning_rate": 0.00033468449659287486,
      "loss": 11.4452,
      "num_input_tokens_seen": 628924044,
      "step": 257
    },
    {
      "epoch": 0.2720562390158172,
      "grad_norm": 0.4208810329437256,
      "learning_rate": 0.0003328344888321955,
      "loss": 11.8004,
      "num_input_tokens_seen": 631424656,
      "step": 258
    },
    {
      "epoch": 0.27311072056239016,
      "grad_norm": 0.42234763503074646,
      "learning_rate": 0.0003309793714516019,
      "loss": 10.2814,
      "num_input_tokens_seen": 634003722,
      "step": 259
    },
    {
      "epoch": 0.2741652021089631,
      "grad_norm": 0.7364934086799622,
      "learning_rate": 0.00032911925888347234,
      "loss": 9.4588,
      "num_input_tokens_seen": 636266230,
      "step": 260
    },
    {
      "epoch": 0.275219683655536,
      "grad_norm": 0.595302164554596,
      "learning_rate": 0.00032725426586831203,
      "loss": 11.3085,
      "num_input_tokens_seen": 638937762,
      "step": 261
    },
    {
      "epoch": 0.27627416520210896,
      "grad_norm": 0.5097643136978149,
      "learning_rate": 0.0003253845074476749,
      "loss": 10.8575,
      "num_input_tokens_seen": 641424216,
      "step": 262
    },
    {
      "epoch": 0.2773286467486819,
      "grad_norm": 0.4542533755302429,
      "learning_rate": 0.00032351009895706785,
      "loss": 11.126,
      "num_input_tokens_seen": 643924398,
      "step": 263
    },
    {
      "epoch": 0.27838312829525486,
      "grad_norm": 0.5408210158348083,
      "learning_rate": 0.00032163115601883583,
      "loss": 10.62,
      "num_input_tokens_seen": 646442606,
      "step": 264
    },
    {
      "epoch": 0.27943760984182775,
      "grad_norm": 0.3929187059402466,
      "learning_rate": 0.0003197477945350297,
      "loss": 10.8365,
      "num_input_tokens_seen": 648807396,
      "step": 265
    },
    {
      "epoch": 0.2804920913884007,
      "grad_norm": 0.4019918739795685,
      "learning_rate": 0.0003178601306802573,
      "loss": 11.0141,
      "num_input_tokens_seen": 651255882,
      "step": 266
    },
    {
      "epoch": 0.28154657293497365,
      "grad_norm": 0.41171419620513916,
      "learning_rate": 0.00031596828089451703,
      "loss": 11.1608,
      "num_input_tokens_seen": 653500404,
      "step": 267
    },
    {
      "epoch": 0.2826010544815466,
      "grad_norm": 0.4173177480697632,
      "learning_rate": 0.00031407236187601487,
      "loss": 11.8302,
      "num_input_tokens_seen": 656044100,
      "step": 268
    },
    {
      "epoch": 0.2836555360281195,
      "grad_norm": 0.5411896109580994,
      "learning_rate": 0.0003121724905739666,
      "loss": 10.1021,
      "num_input_tokens_seen": 658675374,
      "step": 269
    },
    {
      "epoch": 0.28471001757469244,
      "grad_norm": 0.37198469042778015,
      "learning_rate": 0.0003102687841813832,
      "loss": 11.3138,
      "num_input_tokens_seen": 661142718,
      "step": 270
    },
    {
      "epoch": 0.2857644991212654,
      "grad_norm": 0.4196586608886719,
      "learning_rate": 0.00030836136012784226,
      "loss": 10.5025,
      "num_input_tokens_seen": 663510590,
      "step": 271
    },
    {
      "epoch": 0.2868189806678383,
      "grad_norm": 0.3854670226573944,
      "learning_rate": 0.00030645033607224425,
      "loss": 11.4875,
      "num_input_tokens_seen": 666115430,
      "step": 272
    },
    {
      "epoch": 0.28787346221441124,
      "grad_norm": 0.4818483591079712,
      "learning_rate": 0.0003045358298955546,
      "loss": 11.0228,
      "num_input_tokens_seen": 668556982,
      "step": 273
    },
    {
      "epoch": 0.2889279437609842,
      "grad_norm": 0.4966771900653839,
      "learning_rate": 0.0003026179596935324,
      "loss": 10.1303,
      "num_input_tokens_seen": 671126456,
      "step": 274
    },
    {
      "epoch": 0.28998242530755713,
      "grad_norm": 0.30973878502845764,
      "learning_rate": 0.00030069684376944573,
      "loss": 11.1264,
      "num_input_tokens_seen": 673578434,
      "step": 275
    },
    {
      "epoch": 0.29103690685413003,
      "grad_norm": 0.6031095385551453,
      "learning_rate": 0.000298772600626774,
      "loss": 11.2413,
      "num_input_tokens_seen": 675988320,
      "step": 276
    },
    {
      "epoch": 0.292091388400703,
      "grad_norm": 0.4558941423892975,
      "learning_rate": 0.00029684534896189834,
      "loss": 11.4214,
      "num_input_tokens_seen": 678558982,
      "step": 277
    },
    {
      "epoch": 0.2931458699472759,
      "grad_norm": 0.46561217308044434,
      "learning_rate": 0.0002949152076567795,
      "loss": 10.6133,
      "num_input_tokens_seen": 681075438,
      "step": 278
    },
    {
      "epoch": 0.2942003514938489,
      "grad_norm": 0.4388117790222168,
      "learning_rate": 0.0002929822957716248,
      "loss": 12.1676,
      "num_input_tokens_seen": 683571248,
      "step": 279
    },
    {
      "epoch": 0.29525483304042177,
      "grad_norm": 0.4060705006122589,
      "learning_rate": 0.00029104673253754456,
      "loss": 10.7931,
      "num_input_tokens_seen": 685872324,
      "step": 280
    },
    {
      "epoch": 0.2963093145869947,
      "grad_norm": 0.3648971915245056,
      "learning_rate": 0.00028910863734919615,
      "loss": 11.5947,
      "num_input_tokens_seen": 688269678,
      "step": 281
    },
    {
      "epoch": 0.29736379613356767,
      "grad_norm": 0.5417793393135071,
      "learning_rate": 0.00028716812975741995,
      "loss": 9.7931,
      "num_input_tokens_seen": 690789842,
      "step": 282
    },
    {
      "epoch": 0.2984182776801406,
      "grad_norm": 0.47309672832489014,
      "learning_rate": 0.00028522532946186486,
      "loss": 10.8822,
      "num_input_tokens_seen": 693146222,
      "step": 283
    },
    {
      "epoch": 0.2994727592267135,
      "grad_norm": 0.566740870475769,
      "learning_rate": 0.0002832803563036046,
      "loss": 10.9888,
      "num_input_tokens_seen": 695527010,
      "step": 284
    },
    {
      "epoch": 0.30052724077328646,
      "grad_norm": 0.4325026869773865,
      "learning_rate": 0.00028133333025774524,
      "loss": 11.0045,
      "num_input_tokens_seen": 697890080,
      "step": 285
    },
    {
      "epoch": 0.3015817223198594,
      "grad_norm": 0.5596818923950195,
      "learning_rate": 0.0002793843714260245,
      "loss": 10.0578,
      "num_input_tokens_seen": 700327360,
      "step": 286
    },
    {
      "epoch": 0.30263620386643236,
      "grad_norm": 0.7821861505508423,
      "learning_rate": 0.0002774336000294035,
      "loss": 12.0288,
      "num_input_tokens_seen": 702777350,
      "step": 287
    },
    {
      "epoch": 0.30369068541300526,
      "grad_norm": 0.49740836024284363,
      "learning_rate": 0.0002754811364006511,
      "loss": 11.6109,
      "num_input_tokens_seen": 705184528,
      "step": 288
    },
    {
      "epoch": 0.3047451669595782,
      "grad_norm": 0.5511218309402466,
      "learning_rate": 0.0002735271009769208,
      "loss": 9.9996,
      "num_input_tokens_seen": 707551254,
      "step": 289
    },
    {
      "epoch": 0.30579964850615116,
      "grad_norm": 0.36505043506622314,
      "learning_rate": 0.00027157161429232173,
      "loss": 10.6945,
      "num_input_tokens_seen": 709824754,
      "step": 290
    },
    {
      "epoch": 0.30685413005272405,
      "grad_norm": 0.5768591165542603,
      "learning_rate": 0.00026961479697048385,
      "loss": 10.4752,
      "num_input_tokens_seen": 712236092,
      "step": 291
    },
    {
      "epoch": 0.307908611599297,
      "grad_norm": 0.3299911916255951,
      "learning_rate": 0.00026765676971711704,
      "loss": 11.6405,
      "num_input_tokens_seen": 714627792,
      "step": 292
    },
    {
      "epoch": 0.30896309314586995,
      "grad_norm": 0.44536301493644714,
      "learning_rate": 0.00026569765331256536,
      "loss": 11.4152,
      "num_input_tokens_seen": 716881324,
      "step": 293
    },
    {
      "epoch": 0.3100175746924429,
      "grad_norm": 0.3655878007411957,
      "learning_rate": 0.000263737568604357,
      "loss": 11.6348,
      "num_input_tokens_seen": 719423592,
      "step": 294
    },
    {
      "epoch": 0.3110720562390158,
      "grad_norm": 0.5900895595550537,
      "learning_rate": 0.00026177663649974936,
      "loss": 10.2198,
      "num_input_tokens_seen": 721913756,
      "step": 295
    },
    {
      "epoch": 0.31212653778558874,
      "grad_norm": 0.7902632355690002,
      "learning_rate": 0.00025981497795827174,
      "loss": 9.868,
      "num_input_tokens_seen": 724446930,
      "step": 296
    },
    {
      "epoch": 0.3131810193321617,
      "grad_norm": 0.4470077455043793,
      "learning_rate": 0.0002578527139842631,
      "loss": 10.5506,
      "num_input_tokens_seen": 726932626,
      "step": 297
    },
    {
      "epoch": 0.31423550087873464,
      "grad_norm": 0.45410841703414917,
      "learning_rate": 0.00025588996561940846,
      "loss": 11.0545,
      "num_input_tokens_seen": 729377678,
      "step": 298
    },
    {
      "epoch": 0.31528998242530754,
      "grad_norm": 0.6242054104804993,
      "learning_rate": 0.0002539268539352723,
      "loss": 10.1522,
      "num_input_tokens_seen": 731835522,
      "step": 299
    },
    {
      "epoch": 0.3163444639718805,
      "grad_norm": 0.49581339955329895,
      "learning_rate": 0.00025196350002583027,
      "loss": 11.9984,
      "num_input_tokens_seen": 734212212,
      "step": 300
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 500,
  "num_input_tokens_seen": 734212212,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.14219679856119e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}