{
  "best_global_step": 1400,
  "best_metric": 0.17420975863933563,
  "best_model_checkpoint": "saves/prompt-tuning/gemma-3-1b-it/train_copa_1745950322/checkpoint-1400",
  "epoch": 444.44444444444446,
  "eval_steps": 200,
  "global_step": 40000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 26.2646484375,
      "learning_rate": 0.29999999259779675,
      "loss": 9.8054,
      "num_input_tokens_seen": 1376,
      "step": 5
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 6.734050750732422,
      "learning_rate": 0.29999996252634736,
      "loss": 6.8378,
      "num_input_tokens_seen": 2800,
      "step": 10
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 7.134005546569824,
      "learning_rate": 0.2999999093230187,
      "loss": 4.5419,
      "num_input_tokens_seen": 4240,
      "step": 15
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 3.0850746631622314,
      "learning_rate": 0.299999832987819,
      "loss": 2.5896,
      "num_input_tokens_seen": 5664,
      "step": 20
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.29398512840271,
      "learning_rate": 0.29999973352076004,
      "loss": 1.1372,
      "num_input_tokens_seen": 7072,
      "step": 25
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.8208290338516235,
      "learning_rate": 0.2999996109218572,
      "loss": 0.9272,
      "num_input_tokens_seen": 8480,
      "step": 30
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.17350365221500397,
      "learning_rate": 0.2999994651911293,
      "loss": 0.6033,
      "num_input_tokens_seen": 9840,
      "step": 35
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.21312664449214935,
      "learning_rate": 0.2999992963285989,
      "loss": 0.4719,
      "num_input_tokens_seen": 11200,
      "step": 40
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.11440593749284744,
      "learning_rate": 0.29999910433429194,
      "loss": 0.3556,
      "num_input_tokens_seen": 12640,
      "step": 45
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.3636986315250397,
      "learning_rate": 0.29999888920823814,
      "loss": 0.5066,
      "num_input_tokens_seen": 14032,
      "step": 50
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.26909419894218445,
      "learning_rate": 0.29999865095047057,
      "loss": 0.3132,
      "num_input_tokens_seen": 15472,
      "step": 55
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.0741322711110115,
      "learning_rate": 0.29999838956102604,
      "loss": 0.308,
      "num_input_tokens_seen": 16896,
      "step": 60
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.10366097837686539,
      "learning_rate": 0.29999810503994484,
      "loss": 0.2331,
      "num_input_tokens_seen": 18336,
      "step": 65
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.045879822224378586,
      "learning_rate": 0.29999779738727084,
      "loss": 0.2147,
      "num_input_tokens_seen": 19760,
      "step": 70
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.028972703963518143,
      "learning_rate": 0.29999746660305154,
      "loss": 0.1688,
      "num_input_tokens_seen": 21136,
      "step": 75
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.038240786641836166,
      "learning_rate": 0.2999971126873379,
      "loss": 0.2121,
      "num_input_tokens_seen": 22544,
      "step": 80
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 0.035504795610904694,
      "learning_rate": 0.2999967356401845,
      "loss": 0.2116,
      "num_input_tokens_seen": 23920,
      "step": 85
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.01857122592628002,
      "learning_rate": 0.29999633546164944,
      "loss": 0.1905,
      "num_input_tokens_seen": 25312,
      "step": 90
    },
    {
      "epoch": 1.0555555555555556,
      "grad_norm": 0.01520504616200924,
      "learning_rate": 0.29999591215179444,
      "loss": 0.1813,
      "num_input_tokens_seen": 26720,
      "step": 95
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.020665550604462624,
      "learning_rate": 0.2999954657106849,
      "loss": 0.1774,
      "num_input_tokens_seen": 28096,
      "step": 100
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 0.033821530640125275,
      "learning_rate": 0.2999949961383896,
      "loss": 0.2003,
      "num_input_tokens_seen": 29488,
      "step": 105
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.029723070561885834,
      "learning_rate": 0.2999945034349809,
      "loss": 0.1822,
      "num_input_tokens_seen": 30880,
      "step": 110
    },
    {
      "epoch": 1.2777777777777777,
      "grad_norm": 0.02188202366232872,
      "learning_rate": 0.2999939876005348,
      "loss": 0.1849,
      "num_input_tokens_seen": 32256,
      "step": 115
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.01074980292469263,
      "learning_rate": 0.29999344863513094,
      "loss": 0.1901,
      "num_input_tokens_seen": 33616,
      "step": 120
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 0.012513234280049801,
      "learning_rate": 0.2999928865388523,
      "loss": 0.1707,
      "num_input_tokens_seen": 35040,
      "step": 125
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.029837168753147125,
      "learning_rate": 0.29999230131178567,
      "loss": 0.1935,
      "num_input_tokens_seen": 36480,
      "step": 130
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.01531287282705307,
      "learning_rate": 0.2999916929540212,
      "loss": 0.1853,
      "num_input_tokens_seen": 37888,
      "step": 135
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.02153068408370018,
      "learning_rate": 0.29999106146565285,
      "loss": 0.2435,
      "num_input_tokens_seen": 39296,
      "step": 140
    },
    {
      "epoch": 1.6111111111111112,
      "grad_norm": 0.017031118273735046,
      "learning_rate": 0.29999040684677786,
      "loss": 0.1948,
      "num_input_tokens_seen": 40704,
      "step": 145
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.019320111721754074,
      "learning_rate": 0.2999897290974972,
      "loss": 0.1977,
      "num_input_tokens_seen": 42112,
      "step": 150
    },
    {
      "epoch": 1.7222222222222223,
      "grad_norm": 0.026812076568603516,
      "learning_rate": 0.2999890282179155,
      "loss": 0.1788,
      "num_input_tokens_seen": 43520,
      "step": 155
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.013033929280936718,
      "learning_rate": 0.29998830420814077,
      "loss": 0.1779,
      "num_input_tokens_seen": 44912,
      "step": 160
    },
    {
      "epoch": 1.8333333333333335,
      "grad_norm": 0.01356493216007948,
      "learning_rate": 0.2999875570682846,
      "loss": 0.1839,
      "num_input_tokens_seen": 46272,
      "step": 165
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.008423026651144028,
      "learning_rate": 0.2999867867984623,
      "loss": 0.1771,
      "num_input_tokens_seen": 47664,
      "step": 170
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 0.011230957694351673,
      "learning_rate": 0.29998599339879267,
      "loss": 0.1791,
      "num_input_tokens_seen": 49072,
      "step": 175
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.012008532881736755,
      "learning_rate": 0.29998517686939796,
      "loss": 0.174,
      "num_input_tokens_seen": 50464,
      "step": 180
    },
    {
      "epoch": 2.0555555555555554,
      "grad_norm": 0.015351595357060432,
      "learning_rate": 0.29998433721040413,
      "loss": 0.167,
      "num_input_tokens_seen": 51904,
      "step": 185
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 0.016086090356111526,
      "learning_rate": 0.29998347442194073,
      "loss": 0.1692,
      "num_input_tokens_seen": 53280,
      "step": 190
    },
    {
      "epoch": 2.1666666666666665,
      "grad_norm": 0.014304152689874172,
      "learning_rate": 0.2999825885041407,
      "loss": 0.178,
      "num_input_tokens_seen": 54720,
      "step": 195
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.010784662328660488,
      "learning_rate": 0.29998167945714077,
      "loss": 0.1585,
      "num_input_tokens_seen": 56176,
      "step": 200
    },
    {
      "epoch": 2.2222222222222223,
      "eval_loss": 0.19602972269058228,
      "eval_runtime": 1.1768,
      "eval_samples_per_second": 33.991,
      "eval_steps_per_second": 16.996,
      "num_input_tokens_seen": 56176,
      "step": 200
    },
    {
      "epoch": 2.2777777777777777,
      "grad_norm": 0.013954675756394863,
      "learning_rate": 0.2999807472810811,
      "loss": 0.1925,
      "num_input_tokens_seen": 57584,
      "step": 205
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.028864869847893715,
      "learning_rate": 0.29997979197610536,
      "loss": 0.1734,
      "num_input_tokens_seen": 58944,
      "step": 210
    },
    {
      "epoch": 2.388888888888889,
      "grad_norm": 0.021881699562072754,
      "learning_rate": 0.299978813542361,
      "loss": 0.1786,
      "num_input_tokens_seen": 60352,
      "step": 215
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.012504903599619865,
      "learning_rate": 0.2999778119799988,
      "loss": 0.2209,
      "num_input_tokens_seen": 61728,
      "step": 220
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.010295767337083817,
      "learning_rate": 0.29997678728917326,
      "loss": 0.169,
      "num_input_tokens_seen": 63136,
      "step": 225
    },
    {
      "epoch": 2.5555555555555554,
      "grad_norm": 0.00809690821915865,
      "learning_rate": 0.2999757394700424,
      "loss": 0.2061,
      "num_input_tokens_seen": 64528,
      "step": 230
    },
    {
      "epoch": 2.611111111111111,
      "grad_norm": 0.012911868281662464,
      "learning_rate": 0.29997466852276783,
      "loss": 0.1752,
      "num_input_tokens_seen": 65936,
      "step": 235
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.03666610270738602,
      "learning_rate": 0.29997357444751466,
      "loss": 0.1863,
      "num_input_tokens_seen": 67312,
      "step": 240
    },
    {
      "epoch": 2.7222222222222223,
      "grad_norm": 0.006968713831156492,
      "learning_rate": 0.2999724572444516,
      "loss": 0.1742,
      "num_input_tokens_seen": 68768,
      "step": 245
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.008031822741031647,
      "learning_rate": 0.29997131691375095,
      "loss": 0.1901,
      "num_input_tokens_seen": 70144,
      "step": 250
    },
    {
      "epoch": 2.8333333333333335,
      "grad_norm": 0.011283697560429573,
      "learning_rate": 0.2999701534555886,
      "loss": 0.1715,
      "num_input_tokens_seen": 71568,
      "step": 255
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.006987257394939661,
      "learning_rate": 0.2999689668701439,
      "loss": 0.1743,
      "num_input_tokens_seen": 72976,
      "step": 260
    },
    {
      "epoch": 2.9444444444444446,
      "grad_norm": 0.015548300929367542,
      "learning_rate": 0.29996775715759993,
      "loss": 0.168,
      "num_input_tokens_seen": 74368,
      "step": 265
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.01022126991301775,
      "learning_rate": 0.2999665243181432,
      "loss": 0.2023,
      "num_input_tokens_seen": 75760,
      "step": 270
    },
    {
      "epoch": 3.0555555555555554,
      "grad_norm": 0.012241411954164505,
      "learning_rate": 0.2999652683519638,
      "loss": 0.1898,
      "num_input_tokens_seen": 77168,
      "step": 275
    },
    {
      "epoch": 3.111111111111111,
      "grad_norm": 0.011399047449231148,
      "learning_rate": 0.29996398925925544,
      "loss": 0.1718,
      "num_input_tokens_seen": 78624,
      "step": 280
    },
    {
      "epoch": 3.1666666666666665,
      "grad_norm": 0.008148890919983387,
      "learning_rate": 0.2999626870402154,
      "loss": 0.1746,
      "num_input_tokens_seen": 80016,
      "step": 285
    },
    {
      "epoch": 3.2222222222222223,
      "grad_norm": 0.017135225236415863,
      "learning_rate": 0.29996136169504445,
      "loss": 0.1866,
      "num_input_tokens_seen": 81424,
      "step": 290
    },
    {
      "epoch": 3.2777777777777777,
      "grad_norm": 0.006589976139366627,
      "learning_rate": 0.29996001322394694,
      "loss": 0.1686,
      "num_input_tokens_seen": 82784,
      "step": 295
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.00785944052040577,
      "learning_rate": 0.29995864162713093,
      "loss": 0.181,
      "num_input_tokens_seen": 84208,
      "step": 300
    },
    {
      "epoch": 3.388888888888889,
      "grad_norm": 0.024439379572868347,
      "learning_rate": 0.2999572469048079,
      "loss": 0.1709,
      "num_input_tokens_seen": 85632,
      "step": 305
    },
    {
      "epoch": 3.4444444444444446,
      "grad_norm": 0.011661767028272152,
      "learning_rate": 0.29995582905719287,
      "loss": 0.1838,
      "num_input_tokens_seen": 87040,
      "step": 310
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.005533503368496895,
      "learning_rate": 0.2999543880845046,
      "loss": 0.1725,
      "num_input_tokens_seen": 88432,
      "step": 315
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.005009176675230265,
      "learning_rate": 0.2999529239869652,
      "loss": 0.1728,
      "num_input_tokens_seen": 89824,
      "step": 320
    },
    {
      "epoch": 3.611111111111111,
      "grad_norm": 0.007506446912884712,
      "learning_rate": 0.2999514367648005,
      "loss": 0.1761,
      "num_input_tokens_seen": 91216,
      "step": 325
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 0.01066611148416996,
      "learning_rate": 0.29994992641823987,
      "loss": 0.1744,
      "num_input_tokens_seen": 92640,
      "step": 330
    },
    {
      "epoch": 3.7222222222222223,
      "grad_norm": 0.017240602523088455,
      "learning_rate": 0.29994839294751613,
      "loss": 0.1763,
      "num_input_tokens_seen": 94032,
      "step": 335
    },
    {
      "epoch": 3.7777777777777777,
      "grad_norm": 0.004004449117928743,
      "learning_rate": 0.29994683635286584,
      "loss": 0.1844,
      "num_input_tokens_seen": 95424,
      "step": 340
    },
    {
      "epoch": 3.8333333333333335,
      "grad_norm": 0.01559668779373169,
      "learning_rate": 0.2999452566345291,
      "loss": 0.1791,
      "num_input_tokens_seen": 96816,
      "step": 345
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 0.005074370186775923,
      "learning_rate": 0.2999436537927494,
      "loss": 0.1643,
      "num_input_tokens_seen": 98192,
      "step": 350
    },
    {
      "epoch": 3.9444444444444446,
      "grad_norm": 0.010658484883606434,
      "learning_rate": 0.299942027827774,
      "loss": 0.1662,
      "num_input_tokens_seen": 99584,
      "step": 355
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.004640329163521528,
      "learning_rate": 0.29994037873985363,
      "loss": 0.1851,
      "num_input_tokens_seen": 100960,
      "step": 360
    },
    {
      "epoch": 4.055555555555555,
      "grad_norm": 0.006661151070147753,
      "learning_rate": 0.29993870652924254,
      "loss": 0.164,
      "num_input_tokens_seen": 102400,
      "step": 365
    },
    {
      "epoch": 4.111111111111111,
      "grad_norm": 0.00942284893244505,
      "learning_rate": 0.29993701119619876,
      "loss": 0.1817,
      "num_input_tokens_seen": 103792,
      "step": 370
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 0.0043636346235871315,
      "learning_rate": 0.2999352927409835,
      "loss": 0.1707,
      "num_input_tokens_seen": 105136,
      "step": 375
    },
    {
      "epoch": 4.222222222222222,
      "grad_norm": 0.006523436866700649,
      "learning_rate": 0.29993355116386194,
      "loss": 0.1696,
      "num_input_tokens_seen": 106528,
      "step": 380
    },
    {
      "epoch": 4.277777777777778,
      "grad_norm": 0.010107730515301228,
      "learning_rate": 0.29993178646510266,
      "loss": 0.167,
      "num_input_tokens_seen": 107936,
      "step": 385
    },
    {
      "epoch": 4.333333333333333,
      "grad_norm": 0.018732238560914993,
      "learning_rate": 0.2999299986449777,
      "loss": 0.182,
      "num_input_tokens_seen": 109296,
      "step": 390
    },
    {
      "epoch": 4.388888888888889,
      "grad_norm": 0.010023904033005238,
      "learning_rate": 0.29992818770376284,
      "loss": 0.1698,
      "num_input_tokens_seen": 110688,
      "step": 395
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.006985049229115248,
      "learning_rate": 0.29992635364173725,
      "loss": 0.1537,
      "num_input_tokens_seen": 112064,
      "step": 400
    },
    {
      "epoch": 4.444444444444445,
      "eval_loss": 0.19319061934947968,
      "eval_runtime": 1.1831,
      "eval_samples_per_second": 33.808,
      "eval_steps_per_second": 16.904,
      "num_input_tokens_seen": 112064,
      "step": 400
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.012053967453539371,
      "learning_rate": 0.2999244964591839,
      "loss": 0.1764,
      "num_input_tokens_seen": 113472,
      "step": 405
    },
    {
      "epoch": 4.555555555555555,
      "grad_norm": 0.013991639949381351,
      "learning_rate": 0.2999226161563891,
      "loss": 0.2048,
      "num_input_tokens_seen": 114880,
      "step": 410
    },
    {
      "epoch": 4.611111111111111,
      "grad_norm": 0.004777251742780209,
      "learning_rate": 0.2999207127336429,
      "loss": 0.1715,
      "num_input_tokens_seen": 116224,
      "step": 415
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 0.010359075851738453,
      "learning_rate": 0.2999187861912387,
      "loss": 0.172,
      "num_input_tokens_seen": 117680,
      "step": 420
    },
    {
      "epoch": 4.722222222222222,
      "grad_norm": 0.010338827036321163,
      "learning_rate": 0.2999168365294737,
      "loss": 0.172,
      "num_input_tokens_seen": 119072,
      "step": 425
    },
    {
      "epoch": 4.777777777777778,
      "grad_norm": 0.008693099021911621,
      "learning_rate": 0.29991486374864856,
      "loss": 0.1653,
      "num_input_tokens_seen": 120496,
      "step": 430
    },
    {
      "epoch": 4.833333333333333,
      "grad_norm": 0.02814670093357563,
      "learning_rate": 0.29991286784906745,
      "loss": 0.1654,
      "num_input_tokens_seen": 121936,
      "step": 435
    },
    {
      "epoch": 4.888888888888889,
      "grad_norm": 0.008226778358221054,
      "learning_rate": 0.2999108488310382,
      "loss": 0.204,
      "num_input_tokens_seen": 123344,
      "step": 440
    },
    {
      "epoch": 4.944444444444445,
      "grad_norm": 0.010014109313488007,
      "learning_rate": 0.29990880669487213,
      "loss": 0.1638,
      "num_input_tokens_seen": 124736,
      "step": 445
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.016229297965765,
      "learning_rate": 0.29990674144088425,
      "loss": 0.168,
      "num_input_tokens_seen": 126144,
      "step": 450
    },
    {
      "epoch": 5.055555555555555,
      "grad_norm": 0.012176155112683773,
      "learning_rate": 0.299904653069393,
      "loss": 0.2036,
      "num_input_tokens_seen": 127520,
      "step": 455
    },
    {
      "epoch": 5.111111111111111,
      "grad_norm": 0.011558020487427711,
      "learning_rate": 0.29990254158072044,
      "loss": 0.1716,
      "num_input_tokens_seen": 128944,
      "step": 460
    },
    {
      "epoch": 5.166666666666667,
      "grad_norm": 0.009276878088712692,
      "learning_rate": 0.2999004069751921,
      "loss": 0.1761,
      "num_input_tokens_seen": 130336,
      "step": 465
    },
    {
      "epoch": 5.222222222222222,
      "grad_norm": 0.014409287832677364,
      "learning_rate": 0.2998982492531373,
      "loss": 0.1751,
      "num_input_tokens_seen": 131696,
      "step": 470
    },
    {
      "epoch": 5.277777777777778,
      "grad_norm": 0.00653785839676857,
      "learning_rate": 0.2998960684148887,
      "loss": 0.1654,
      "num_input_tokens_seen": 133088,
      "step": 475
    },
    {
      "epoch": 5.333333333333333,
      "grad_norm": 0.012684590183198452,
      "learning_rate": 0.29989386446078264,
      "loss": 0.169,
      "num_input_tokens_seen": 134464,
      "step": 480
    },
    {
      "epoch": 5.388888888888889,
      "grad_norm": 0.005768038798123598,
      "learning_rate": 0.299891637391159,
      "loss": 0.1863,
      "num_input_tokens_seen": 135856,
      "step": 485
    },
    {
      "epoch": 5.444444444444445,
      "grad_norm": 0.006622848566621542,
      "learning_rate": 0.2998893872063612,
      "loss": 0.1784,
      "num_input_tokens_seen": 137248,
      "step": 490
    },
    {
      "epoch": 5.5,
      "grad_norm": 0.006602656561881304,
      "learning_rate": 0.2998871139067363,
      "loss": 0.1586,
      "num_input_tokens_seen": 138592,
      "step": 495
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.00585530512034893,
      "learning_rate": 0.2998848174926348,
      "loss": 0.1688,
      "num_input_tokens_seen": 140016,
      "step": 500
    },
    {
      "epoch": 5.611111111111111,
      "grad_norm": 0.009475620463490486,
      "learning_rate": 0.2998824979644109,
      "loss": 0.1696,
      "num_input_tokens_seen": 141424,
      "step": 505
    },
    {
      "epoch": 5.666666666666667,
      "grad_norm": 0.02456592209637165,
      "learning_rate": 0.29988015532242224,
      "loss": 0.1586,
      "num_input_tokens_seen": 142864,
      "step": 510
    },
    {
      "epoch": 5.722222222222222,
      "grad_norm": 0.009982617571949959,
      "learning_rate": 0.29987778956703015,
      "loss": 0.197,
      "num_input_tokens_seen": 144320,
      "step": 515
    },
    {
      "epoch": 5.777777777777778,
      "grad_norm": 0.006730268243700266,
      "learning_rate": 0.2998754006985994,
      "loss": 0.1824,
      "num_input_tokens_seen": 145712,
      "step": 520
    },
    {
      "epoch": 5.833333333333333,
      "grad_norm": 0.01130148209631443,
      "learning_rate": 0.29987298871749846,
      "loss": 0.181,
      "num_input_tokens_seen": 147088,
      "step": 525
    },
    {
      "epoch": 5.888888888888889,
      "grad_norm": 0.010423286817967892,
      "learning_rate": 0.2998705536240992,
      "loss": 0.1814,
      "num_input_tokens_seen": 148464,
      "step": 530
    },
    {
      "epoch": 5.944444444444445,
      "grad_norm": 0.012042532674968243,
      "learning_rate": 0.2998680954187772,
      "loss": 0.1771,
      "num_input_tokens_seen": 149840,
      "step": 535
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0051346635445952415,
      "learning_rate": 0.2998656141019115,
      "loss": 0.1811,
      "num_input_tokens_seen": 151248,
      "step": 540
    },
    {
      "epoch": 6.055555555555555,
      "grad_norm": 0.007081231102347374,
      "learning_rate": 0.2998631096738848,
      "loss": 0.1714,
      "num_input_tokens_seen": 152624,
      "step": 545
    },
    {
      "epoch": 6.111111111111111,
      "grad_norm": 0.008715678937733173,
      "learning_rate": 0.29986058213508326,
      "loss": 0.1747,
      "num_input_tokens_seen": 154032,
      "step": 550
    },
    {
      "epoch": 6.166666666666667,
      "grad_norm": 0.007505562622100115,
      "learning_rate": 0.29985803148589674,
      "loss": 0.1689,
      "num_input_tokens_seen": 155456,
      "step": 555
    },
    {
      "epoch": 6.222222222222222,
      "grad_norm": 0.009290432557463646,
      "learning_rate": 0.2998554577267185,
      "loss": 0.1699,
      "num_input_tokens_seen": 156864,
      "step": 560
    },
    {
      "epoch": 6.277777777777778,
      "grad_norm": 0.004864121321588755,
      "learning_rate": 0.2998528608579455,
      "loss": 0.1792,
      "num_input_tokens_seen": 158304,
      "step": 565
    },
    {
      "epoch": 6.333333333333333,
      "grad_norm": 0.008819629438221455,
      "learning_rate": 0.2998502408799781,
      "loss": 0.1684,
      "num_input_tokens_seen": 159712,
      "step": 570
    },
    {
      "epoch": 6.388888888888889,
      "grad_norm": 0.012704544700682163,
      "learning_rate": 0.2998475977932205,
      "loss": 0.1739,
      "num_input_tokens_seen": 161088,
      "step": 575
    },
    {
      "epoch": 6.444444444444445,
      "grad_norm": 0.00658687949180603,
      "learning_rate": 0.29984493159808023,
      "loss": 0.1672,
      "num_input_tokens_seen": 162464,
      "step": 580
    },
    {
      "epoch": 6.5,
      "grad_norm": 0.01154596172273159,
      "learning_rate": 0.29984224229496836,
      "loss": 0.1864,
      "num_input_tokens_seen": 163872,
      "step": 585
    },
    {
      "epoch": 6.555555555555555,
      "grad_norm": 0.010976460762321949,
      "learning_rate": 0.2998395298842998,
      "loss": 0.1627,
      "num_input_tokens_seen": 165280,
      "step": 590
    },
    {
      "epoch": 6.611111111111111,
      "grad_norm": 0.00563057092949748,
      "learning_rate": 0.29983679436649263,
      "loss": 0.1664,
      "num_input_tokens_seen": 166704,
      "step": 595
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.0070015499368309975,
      "learning_rate": 0.2998340357419689,
      "loss": 0.1745,
      "num_input_tokens_seen": 168112,
      "step": 600
    },
    {
      "epoch": 6.666666666666667,
      "eval_loss": 0.18660125136375427,
      "eval_runtime": 1.182,
      "eval_samples_per_second": 33.841,
      "eval_steps_per_second": 16.92,
      "num_input_tokens_seen": 168112,
      "step": 600
    },
    {
      "epoch": 6.722222222222222,
      "grad_norm": 0.014138597063720226,
      "learning_rate": 0.29983125401115385,
      "loss": 0.1757,
      "num_input_tokens_seen": 169504,
      "step": 605
    },
    {
      "epoch": 6.777777777777778,
      "grad_norm": 0.006092917174100876,
      "learning_rate": 0.29982844917447654,
      "loss": 0.1737,
      "num_input_tokens_seen": 170880,
      "step": 610
    },
    {
      "epoch": 6.833333333333333,
      "grad_norm": 0.007335526403039694,
      "learning_rate": 0.2998256212323695,
      "loss": 0.172,
      "num_input_tokens_seen": 172256,
      "step": 615
    },
    {
      "epoch": 6.888888888888889,
      "grad_norm": 0.008890067227184772,
      "learning_rate": 0.29982277018526887,
      "loss": 0.1759,
      "num_input_tokens_seen": 173664,
      "step": 620
    },
    {
      "epoch": 6.944444444444445,
      "grad_norm": 0.006479010451585054,
      "learning_rate": 0.2998198960336143,
      "loss": 0.1678,
      "num_input_tokens_seen": 175024,
      "step": 625
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.007298365700989962,
      "learning_rate": 0.299816998777849,
      "loss": 0.1736,
      "num_input_tokens_seen": 176400,
      "step": 630
    },
    {
      "epoch": 7.055555555555555,
      "grad_norm": 0.01127561368048191,
      "learning_rate": 0.2998140784184197,
      "loss": 0.1627,
      "num_input_tokens_seen": 177792,
      "step": 635
    },
    {
      "epoch": 7.111111111111111,
      "grad_norm": 0.011858913116157055,
      "learning_rate": 0.2998111349557769,
      "loss": 0.1802,
      "num_input_tokens_seen": 179168,
      "step": 640
    },
    {
      "epoch": 7.166666666666667,
      "grad_norm": 0.01731405407190323,
      "learning_rate": 0.29980816839037444,
      "loss": 0.1876,
      "num_input_tokens_seen": 180544,
      "step": 645
    },
    {
      "epoch": 7.222222222222222,
      "grad_norm": 0.006793128326535225,
      "learning_rate": 0.2998051787226698,
      "loss": 0.1895,
      "num_input_tokens_seen": 181984,
      "step": 650
    },
    {
      "epoch": 7.277777777777778,
      "grad_norm": 0.008062001317739487,
      "learning_rate": 0.29980216595312403,
      "loss": 0.1642,
      "num_input_tokens_seen": 183392,
      "step": 655
    },
    {
      "epoch": 7.333333333333333,
      "grad_norm": 0.007302538026124239,
      "learning_rate": 0.29979913008220177,
      "loss": 0.1808,
      "num_input_tokens_seen": 184784,
      "step": 660
    },
    {
      "epoch": 7.388888888888889,
      "grad_norm": 0.0073290239088237286,
      "learning_rate": 0.2997960711103711,
      "loss": 0.1677,
      "num_input_tokens_seen": 186192,
      "step": 665
    },
    {
      "epoch": 7.444444444444445,
      "grad_norm": 0.020056355744600296,
      "learning_rate": 0.29979298903810386,
      "loss": 0.1924,
      "num_input_tokens_seen": 187568,
      "step": 670
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.011205075308680534,
      "learning_rate": 0.29978988386587524,
      "loss": 0.1723,
      "num_input_tokens_seen": 188928,
      "step": 675
    },
    {
      "epoch": 7.555555555555555,
      "grad_norm": 0.004778179340064526,
      "learning_rate": 0.2997867555941642,
      "loss": 0.1706,
      "num_input_tokens_seen": 190336,
      "step": 680
    },
    {
      "epoch": 7.611111111111111,
      "grad_norm": 0.006385219749063253,
      "learning_rate": 0.299783604223453,
      "loss": 0.1811,
      "num_input_tokens_seen": 191712,
      "step": 685
    },
    {
      "epoch": 7.666666666666667,
      "grad_norm": 0.00513053173199296,
      "learning_rate": 0.29978042975422786,
      "loss": 0.1713,
      "num_input_tokens_seen": 193056,
      "step": 690
    },
    {
      "epoch": 7.722222222222222,
      "grad_norm": 0.004299720283597708,
      "learning_rate": 0.29977723218697816,
      "loss": 0.1692,
      "num_input_tokens_seen": 194496,
      "step": 695
    },
    {
      "epoch": 7.777777777777778,
      "grad_norm": 0.013878688216209412,
      "learning_rate": 0.299774011522197,
      "loss": 0.1826,
      "num_input_tokens_seen": 195936,
      "step": 700
    },
    {
      "epoch": 7.833333333333333,
      "grad_norm": 0.006820328067988157,
      "learning_rate": 0.29977076776038114,
      "loss": 0.1715,
      "num_input_tokens_seen": 197360,
      "step": 705
    },
    {
      "epoch": 7.888888888888889,
      "grad_norm": 0.005347720347344875,
      "learning_rate": 0.2997675009020307,
      "loss": 0.1715,
      "num_input_tokens_seen": 198784,
      "step": 710
    },
    {
      "epoch": 7.944444444444445,
      "grad_norm": 0.010840505361557007,
      "learning_rate": 0.2997642109476496,
      "loss": 0.1639,
      "num_input_tokens_seen": 200192,
      "step": 715
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.005601742770522833,
      "learning_rate": 0.299760897897745,
      "loss": 0.1841,
      "num_input_tokens_seen": 201616,
      "step": 720
    },
    {
      "epoch": 8.055555555555555,
      "grad_norm": 0.004982451908290386,
      "learning_rate": 0.29975756175282803,
      "loss": 0.1847,
      "num_input_tokens_seen": 203024,
      "step": 725
    },
    {
      "epoch": 8.11111111111111,
      "grad_norm": 0.009648389182984829,
      "learning_rate": 0.29975420251341306,
      "loss": 0.165,
      "num_input_tokens_seen": 204400,
      "step": 730
    },
    {
      "epoch": 8.166666666666666,
      "grad_norm": 0.00777561217546463,
      "learning_rate": 0.29975082018001814,
      "loss": 0.1643,
      "num_input_tokens_seen": 205824,
      "step": 735
    },
    {
      "epoch": 8.222222222222221,
      "grad_norm": 0.005667414050549269,
      "learning_rate": 0.2997474147531648,
      "loss": 0.1783,
      "num_input_tokens_seen": 207264,
      "step": 740
    },
    {
      "epoch": 8.277777777777779,
      "grad_norm": 0.00998706929385662,
      "learning_rate": 0.29974398623337833,
      "loss": 0.1661,
      "num_input_tokens_seen": 208656,
      "step": 745
    },
    {
      "epoch": 8.333333333333334,
      "grad_norm": 0.01285590697079897,
      "learning_rate": 0.2997405346211873,
      "loss": 0.167,
      "num_input_tokens_seen": 210064,
      "step": 750
    },
    {
      "epoch": 8.38888888888889,
      "grad_norm": 0.00936108361929655,
      "learning_rate": 0.2997370599171241,
      "loss": 0.1829,
      "num_input_tokens_seen": 211440,
      "step": 755
    },
    {
      "epoch": 8.444444444444445,
      "grad_norm": 0.014205697923898697,
      "learning_rate": 0.2997335621217246,
      "loss": 0.1793,
      "num_input_tokens_seen": 212848,
      "step": 760
    },
    {
      "epoch": 8.5,
      "grad_norm": 0.008453095331788063,
      "learning_rate": 0.29973004123552816,
      "loss": 0.1735,
      "num_input_tokens_seen": 214272,
      "step": 765
    },
    {
      "epoch": 8.555555555555555,
      "grad_norm": 0.00653674453496933,
      "learning_rate": 0.2997264972590777,
      "loss": 0.1682,
      "num_input_tokens_seen": 215696,
      "step": 770
    },
    {
      "epoch": 8.61111111111111,
      "grad_norm": 0.008766479790210724,
      "learning_rate": 0.29972293019291973,
      "loss": 0.1655,
      "num_input_tokens_seen": 217088,
      "step": 775
    },
    {
      "epoch": 8.666666666666666,
      "grad_norm": 0.006444925907999277,
      "learning_rate": 0.2997193400376045,
      "loss": 0.1824,
      "num_input_tokens_seen": 218496,
      "step": 780
    },
    {
      "epoch": 8.722222222222221,
      "grad_norm": 0.006574252620339394,
      "learning_rate": 0.2997157267936854,
      "loss": 0.1689,
      "num_input_tokens_seen": 219840,
      "step": 785
    },
    {
      "epoch": 8.777777777777779,
      "grad_norm": 0.008576479740440845,
      "learning_rate": 0.2997120904617199,
      "loss": 0.1682,
      "num_input_tokens_seen": 221264,
      "step": 790
    },
    {
      "epoch": 8.833333333333334,
      "grad_norm": 0.005988797172904015,
      "learning_rate": 0.29970843104226863,
      "loss": 0.1632,
      "num_input_tokens_seen": 222656,
      "step": 795
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 0.007260475307703018,
      "learning_rate": 0.2997047485358959,
      "loss": 0.1615,
      "num_input_tokens_seen": 224048,
      "step": 800
    },
    {
      "epoch": 8.88888888888889,
      "eval_loss": 0.18277287483215332,
      "eval_runtime": 1.1868,
      "eval_samples_per_second": 33.704,
      "eval_steps_per_second": 16.852,
      "num_input_tokens_seen": 224048,
      "step": 800
    },
    {
      "epoch": 8.944444444444445,
      "grad_norm": 0.010432131588459015,
      "learning_rate": 0.2997010429431697,
      "loss": 0.1795,
      "num_input_tokens_seen": 225440,
      "step": 805
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.015587030909955502,
      "learning_rate": 0.29969731426466134,
      "loss": 0.176,
      "num_input_tokens_seen": 226816,
      "step": 810
    },
    {
      "epoch": 9.055555555555555,
      "grad_norm": 0.008372838608920574,
      "learning_rate": 0.299693562500946,
      "loss": 0.1607,
      "num_input_tokens_seen": 228176,
      "step": 815
    },
    {
      "epoch": 9.11111111111111,
      "grad_norm": 0.0076927971094846725,
      "learning_rate": 0.29968978765260207,
      "loss": 0.1572,
      "num_input_tokens_seen": 229584,
      "step": 820
    },
    {
      "epoch": 9.166666666666666,
      "grad_norm": 0.011969087645411491,
      "learning_rate": 0.2996859897202118,
      "loss": 0.1513,
      "num_input_tokens_seen": 230944,
      "step": 825
    },
    {
      "epoch": 9.222222222222221,
      "grad_norm": 0.014713197015225887,
      "learning_rate": 0.2996821687043609,
      "loss": 0.168,
      "num_input_tokens_seen": 232368,
      "step": 830
    },
    {
      "epoch": 9.277777777777779,
      "grad_norm": 0.02058650180697441,
      "learning_rate": 0.2996783246056384,
      "loss": 0.1468,
      "num_input_tokens_seen": 233792,
      "step": 835
    },
    {
      "epoch": 9.333333333333334,
      "grad_norm": 0.014496113173663616,
      "learning_rate": 0.29967445742463744,
      "loss": 0.1795,
      "num_input_tokens_seen": 235216,
      "step": 840
    },
    {
      "epoch": 9.38888888888889,
      "grad_norm": 0.025157498195767403,
      "learning_rate": 0.29967056716195417,
      "loss": 0.2333,
      "num_input_tokens_seen": 236576,
      "step": 845
    },
    {
      "epoch": 9.444444444444445,
      "grad_norm": 0.23397578299045563,
      "learning_rate": 0.2996666538181885,
      "loss": 0.2134,
      "num_input_tokens_seen": 237952,
      "step": 850
    },
    {
      "epoch": 9.5,
      "grad_norm": 0.2684135138988495,
      "learning_rate": 0.29966271739394407,
      "loss": 0.3232,
      "num_input_tokens_seen": 239360,
      "step": 855
    },
    {
      "epoch": 9.555555555555555,
      "grad_norm": 0.07409919053316116,
      "learning_rate": 0.29965875788982776,
      "loss": 0.2183,
      "num_input_tokens_seen": 240784,
      "step": 860
    },
    {
      "epoch": 9.61111111111111,
      "grad_norm": 0.33453863859176636,
      "learning_rate": 0.2996547753064503,
      "loss": 0.3159,
      "num_input_tokens_seen": 242208,
      "step": 865
    },
    {
      "epoch": 9.666666666666666,
      "grad_norm": 0.04304603487253189,
      "learning_rate": 0.29965076964442583,
      "loss": 0.2581,
      "num_input_tokens_seen": 243584,
      "step": 870
    },
    {
      "epoch": 9.722222222222221,
      "grad_norm": 0.01687885820865631,
      "learning_rate": 0.299646740904372,
      "loss": 0.1721,
      "num_input_tokens_seen": 244960,
      "step": 875
    },
    {
      "epoch": 9.777777777777779,
      "grad_norm": 0.009620764292776585,
      "learning_rate": 0.29964268908691016,
      "loss": 0.2242,
      "num_input_tokens_seen": 246384,
      "step": 880
    },
    {
      "epoch": 9.833333333333334,
      "grad_norm": 0.01655917800962925,
      "learning_rate": 0.29963861419266513,
      "loss": 0.1728,
      "num_input_tokens_seen": 247840,
      "step": 885
    },
    {
      "epoch": 9.88888888888889,
      "grad_norm": 0.012662457302212715,
      "learning_rate": 0.29963451622226533,
      "loss": 0.1916,
      "num_input_tokens_seen": 249216,
      "step": 890
    },
    {
      "epoch": 9.944444444444445,
      "grad_norm": 0.00737393693998456,
      "learning_rate": 0.29963039517634277,
      "loss": 0.1762,
      "num_input_tokens_seen": 250592,
      "step": 895
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.012014100328087807,
      "learning_rate": 0.2996262510555328,
      "loss": 0.1738,
      "num_input_tokens_seen": 251968,
      "step": 900
    },
    {
      "epoch": 10.055555555555555,
      "grad_norm": 0.013095392845571041,
      "learning_rate": 0.2996220838604746,
      "loss": 0.1757,
      "num_input_tokens_seen": 253392,
      "step": 905
    },
    {
      "epoch": 10.11111111111111,
      "grad_norm": 0.010680286213755608,
      "learning_rate": 0.29961789359181085,
      "loss": 0.1797,
      "num_input_tokens_seen": 254752,
      "step": 910
    },
    {
      "epoch": 10.166666666666666,
      "grad_norm": 0.019692029803991318,
      "learning_rate": 0.29961368025018764,
      "loss": 0.1695,
      "num_input_tokens_seen": 256176,
      "step": 915
    },
    {
      "epoch": 10.222222222222221,
      "grad_norm": 0.005068867467343807,
      "learning_rate": 0.2996094438362548,
      "loss": 0.1956,
      "num_input_tokens_seen": 257584,
      "step": 920
    },
    {
      "epoch": 10.277777777777779,
      "grad_norm": 0.014082315377891064,
      "learning_rate": 0.2996051843506657,
      "loss": 0.1806,
      "num_input_tokens_seen": 259008,
      "step": 925
    },
    {
      "epoch": 10.333333333333334,
      "grad_norm": 0.006147919222712517,
      "learning_rate": 0.299600901794077,
      "loss": 0.1828,
      "num_input_tokens_seen": 260416,
      "step": 930
    },
    {
      "epoch": 10.38888888888889,
      "grad_norm": 0.004847577307373285,
      "learning_rate": 0.29959659616714923,
      "loss": 0.1825,
      "num_input_tokens_seen": 261872,
      "step": 935
    },
    {
      "epoch": 10.444444444444445,
      "grad_norm": 0.01497169490903616,
      "learning_rate": 0.2995922674705464,
      "loss": 0.1876,
      "num_input_tokens_seen": 263232,
      "step": 940
    },
    {
      "epoch": 10.5,
      "grad_norm": 0.004491967614740133,
      "learning_rate": 0.2995879157049361,
      "loss": 0.1768,
      "num_input_tokens_seen": 264656,
      "step": 945
    },
    {
      "epoch": 10.555555555555555,
      "grad_norm": 0.004627041053026915,
      "learning_rate": 0.2995835408709893,
      "loss": 0.1862,
      "num_input_tokens_seen": 266016,
      "step": 950
    },
    {
      "epoch": 10.61111111111111,
      "grad_norm": 0.008092841133475304,
      "learning_rate": 0.29957914296938076,
      "loss": 0.1809,
      "num_input_tokens_seen": 267408,
      "step": 955
    },
    {
      "epoch": 10.666666666666666,
      "grad_norm": 0.003695400431752205,
      "learning_rate": 0.2995747220007886,
      "loss": 0.1854,
      "num_input_tokens_seen": 268800,
      "step": 960
    },
    {
      "epoch": 10.722222222222221,
      "grad_norm": 0.005023834761232138,
      "learning_rate": 0.2995702779658947,
      "loss": 0.1822,
      "num_input_tokens_seen": 270208,
      "step": 965
    },
    {
      "epoch": 10.777777777777779,
      "grad_norm": 0.0036950467620044947,
      "learning_rate": 0.29956581086538425,
      "loss": 0.1951,
      "num_input_tokens_seen": 271552,
      "step": 970
    },
    {
      "epoch": 10.833333333333334,
      "grad_norm": 0.006418588105589151,
      "learning_rate": 0.2995613206999462,
      "loss": 0.1811,
      "num_input_tokens_seen": 272928,
      "step": 975
    },
    {
      "epoch": 10.88888888888889,
      "grad_norm": 0.008415152318775654,
      "learning_rate": 0.29955680747027297,
      "loss": 0.1806,
      "num_input_tokens_seen": 274352,
      "step": 980
    },
    {
      "epoch": 10.944444444444445,
      "grad_norm": 0.006677409168332815,
      "learning_rate": 0.2995522711770607,
      "loss": 0.1778,
      "num_input_tokens_seen": 275760,
      "step": 985
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.008808573707938194,
      "learning_rate": 0.2995477118210087,
      "loss": 0.1658,
      "num_input_tokens_seen": 277152,
      "step": 990
    },
    {
      "epoch": 11.055555555555555,
      "grad_norm": 0.0030982501339167356,
      "learning_rate": 0.29954312940282024,
      "loss": 0.1774,
      "num_input_tokens_seen": 278512,
      "step": 995
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 0.0035590464249253273,
      "learning_rate": 0.29953852392320196,
      "loss": 0.1705,
      "num_input_tokens_seen": 279904,
      "step": 1000
    },
    {
      "epoch": 11.11111111111111,
      "eval_loss": 0.18196964263916016,
      "eval_runtime": 1.1809,
      "eval_samples_per_second": 33.872,
      "eval_steps_per_second": 16.936,
      "num_input_tokens_seen": 279904,
      "step": 1000
    },
    {
      "epoch": 11.166666666666666,
      "grad_norm": 0.005693016108125448,
      "learning_rate": 0.2995338953828641,
      "loss": 0.1806,
      "num_input_tokens_seen": 281360,
      "step": 1005
    },
    {
      "epoch": 11.222222222222221,
      "grad_norm": 0.005512291099876165,
      "learning_rate": 0.2995292437825204,
      "loss": 0.1746,
      "num_input_tokens_seen": 282752,
      "step": 1010
    },
    {
      "epoch": 11.277777777777779,
      "grad_norm": 0.005516815464943647,
      "learning_rate": 0.29952456912288816,
      "loss": 0.1747,
      "num_input_tokens_seen": 284160,
      "step": 1015
    },
    {
      "epoch": 11.333333333333334,
      "grad_norm": 0.005407862830907106,
      "learning_rate": 0.2995198714046884,
      "loss": 0.1682,
      "num_input_tokens_seen": 285536,
      "step": 1020
    },
    {
      "epoch": 11.38888888888889,
      "grad_norm": 0.005507236812263727,
      "learning_rate": 0.2995151506286454,
      "loss": 0.1599,
      "num_input_tokens_seen": 286896,
      "step": 1025
    },
    {
      "epoch": 11.444444444444445,
      "grad_norm": 0.02259698696434498,
      "learning_rate": 0.2995104067954873,
      "loss": 0.1998,
      "num_input_tokens_seen": 288256,
      "step": 1030
    },
    {
      "epoch": 11.5,
      "grad_norm": 0.004489980638027191,
      "learning_rate": 0.2995056399059456,
      "loss": 0.1788,
      "num_input_tokens_seen": 289680,
      "step": 1035
    },
    {
      "epoch": 11.555555555555555,
      "grad_norm": 0.004264044109731913,
      "learning_rate": 0.2995008499607554,
      "loss": 0.172,
      "num_input_tokens_seen": 291040,
      "step": 1040
    },
    {
      "epoch": 11.61111111111111,
      "grad_norm": 0.004590227734297514,
      "learning_rate": 0.2994960369606554,
      "loss": 0.1755,
      "num_input_tokens_seen": 292400,
      "step": 1045
    },
    {
      "epoch": 11.666666666666666,
      "grad_norm": 0.008317027240991592,
      "learning_rate": 0.2994912009063878,
      "loss": 0.178,
      "num_input_tokens_seen": 293824,
      "step": 1050
    },
    {
      "epoch": 11.722222222222221,
      "grad_norm": 0.005839454475790262,
      "learning_rate": 0.29948634179869843,
      "loss": 0.1766,
      "num_input_tokens_seen": 295232,
      "step": 1055
    },
    {
      "epoch": 11.777777777777779,
      "grad_norm": 0.004186820704489946,
      "learning_rate": 0.29948145963833656,
      "loss": 0.1755,
      "num_input_tokens_seen": 296640,
      "step": 1060
    },
    {
      "epoch": 11.833333333333334,
      "grad_norm": 0.0032488422002643347,
      "learning_rate": 0.29947655442605514,
      "loss": 0.1671,
      "num_input_tokens_seen": 298048,
      "step": 1065
    },
    {
      "epoch": 11.88888888888889,
      "grad_norm": 0.004798372276127338,
      "learning_rate": 0.2994716261626106,
      "loss": 0.1816,
      "num_input_tokens_seen": 299456,
      "step": 1070
    },
    {
      "epoch": 11.944444444444445,
      "grad_norm": 0.0018594684079289436,
      "learning_rate": 0.2994666748487629,
      "loss": 0.1778,
      "num_input_tokens_seen": 300848,
      "step": 1075
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.007977169007062912,
      "learning_rate": 0.2994617004852756,
      "loss": 0.181,
      "num_input_tokens_seen": 302224,
      "step": 1080
    },
    {
      "epoch": 12.055555555555555,
      "grad_norm": 0.004238820169121027,
      "learning_rate": 0.2994567030729159,
      "loss": 0.1746,
      "num_input_tokens_seen": 303648,
      "step": 1085
    },
    {
      "epoch": 12.11111111111111,
      "grad_norm": 0.004725300706923008,
      "learning_rate": 0.29945168261245436,
      "loss": 0.1733,
      "num_input_tokens_seen": 305024,
      "step": 1090
    },
    {
      "epoch": 12.166666666666666,
      "grad_norm": 0.002322317333891988,
      "learning_rate": 0.29944663910466524,
      "loss": 0.1729,
      "num_input_tokens_seen": 306448,
      "step": 1095
    },
    {
      "epoch": 12.222222222222221,
      "grad_norm": 0.003992755431681871,
      "learning_rate": 0.2994415725503263,
      "loss": 0.1806,
      "num_input_tokens_seen": 307856,
      "step": 1100
    },
    {
      "epoch": 12.277777777777779,
      "grad_norm": 0.004765807185322046,
      "learning_rate": 0.29943648295021885,
      "loss": 0.1748,
      "num_input_tokens_seen": 309280,
      "step": 1105
    },
    {
      "epoch": 12.333333333333334,
      "grad_norm": 0.003923375159502029,
      "learning_rate": 0.2994313703051278,
      "loss": 0.1698,
      "num_input_tokens_seen": 310704,
      "step": 1110
    },
    {
      "epoch": 12.38888888888889,
      "grad_norm": 0.0034897353034466505,
      "learning_rate": 0.29942623461584156,
      "loss": 0.1771,
      "num_input_tokens_seen": 312080,
      "step": 1115
    },
    {
      "epoch": 12.444444444444445,
      "grad_norm": 0.0036262180656194687,
      "learning_rate": 0.29942107588315214,
      "loss": 0.1911,
      "num_input_tokens_seen": 313520,
      "step": 1120
    },
    {
      "epoch": 12.5,
      "grad_norm": 0.004453627858310938,
      "learning_rate": 0.29941589410785513,
      "loss": 0.1693,
      "num_input_tokens_seen": 314912,
      "step": 1125
    },
    {
      "epoch": 12.555555555555555,
      "grad_norm": 0.007391678635030985,
      "learning_rate": 0.29941068929074954,
      "loss": 0.1747,
      "num_input_tokens_seen": 316336,
      "step": 1130
    },
    {
      "epoch": 12.61111111111111,
      "grad_norm": 0.002816025400534272,
      "learning_rate": 0.2994054614326381,
      "loss": 0.1684,
      "num_input_tokens_seen": 317744,
      "step": 1135
    },
    {
      "epoch": 12.666666666666666,
      "grad_norm": 0.004360495135188103,
      "learning_rate": 0.29940021053432686,
      "loss": 0.1783,
      "num_input_tokens_seen": 319136,
      "step": 1140
    },
    {
      "epoch": 12.722222222222221,
      "grad_norm": 0.012536060065031052,
      "learning_rate": 0.29939493659662575,
      "loss": 0.1819,
      "num_input_tokens_seen": 320528,
      "step": 1145
    },
    {
      "epoch": 12.777777777777779,
      "grad_norm": 0.0066773309372365475,
      "learning_rate": 0.299389639620348,
      "loss": 0.173,
      "num_input_tokens_seen": 321936,
      "step": 1150
    },
    {
      "epoch": 12.833333333333334,
      "grad_norm": 0.005493476055562496,
      "learning_rate": 0.29938431960631046,
      "loss": 0.1705,
      "num_input_tokens_seen": 323344,
      "step": 1155
    },
    {
      "epoch": 12.88888888888889,
      "grad_norm": 0.003596017137169838,
      "learning_rate": 0.2993789765553335,
      "loss": 0.1724,
      "num_input_tokens_seen": 324784,
      "step": 1160
    },
    {
      "epoch": 12.944444444444445,
      "grad_norm": 0.005095710977911949,
      "learning_rate": 0.2993736104682412,
      "loss": 0.1789,
      "num_input_tokens_seen": 326208,
      "step": 1165
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.009764239192008972,
      "learning_rate": 0.299368221345861,
      "loss": 0.1715,
      "num_input_tokens_seen": 327600,
      "step": 1170
    },
    {
      "epoch": 13.055555555555555,
      "grad_norm": 0.003054642118513584,
      "learning_rate": 0.29936280918902397,
      "loss": 0.1624,
      "num_input_tokens_seen": 329024,
      "step": 1175
    },
    {
      "epoch": 13.11111111111111,
      "grad_norm": 0.007703561335802078,
      "learning_rate": 0.2993573739985648,
      "loss": 0.1885,
      "num_input_tokens_seen": 330400,
      "step": 1180
    },
    {
      "epoch": 13.166666666666666,
      "grad_norm": 0.006532945670187473,
      "learning_rate": 0.2993519157753216,
      "loss": 0.1841,
      "num_input_tokens_seen": 331808,
      "step": 1185
    },
    {
      "epoch": 13.222222222222221,
      "grad_norm": 0.006262554787099361,
      "learning_rate": 0.2993464345201361,
      "loss": 0.1757,
      "num_input_tokens_seen": 333200,
      "step": 1190
    },
    {
      "epoch": 13.277777777777779,
      "grad_norm": 0.0026370063424110413,
      "learning_rate": 0.2993409302338536,
      "loss": 0.1711,
      "num_input_tokens_seen": 334640,
      "step": 1195
    },
    {
      "epoch": 13.333333333333334,
      "grad_norm": 0.005537119228392839,
      "learning_rate": 0.2993354029173229,
      "loss": 0.1756,
      "num_input_tokens_seen": 336032,
      "step": 1200
    },
    {
      "epoch": 13.333333333333334,
      "eval_loss": 0.17687320709228516,
      "eval_runtime": 1.1847,
      "eval_samples_per_second": 33.763,
      "eval_steps_per_second": 16.882,
      "num_input_tokens_seen": 336032,
      "step": 1200
    },
    {
      "epoch": 13.38888888888889,
      "grad_norm": 0.0034983735531568527,
      "learning_rate": 0.2993298525713965,
      "loss": 0.1793,
      "num_input_tokens_seen": 337440,
      "step": 1205
    },
    {
      "epoch": 13.444444444444445,
      "grad_norm": 0.0037378165870904922,
      "learning_rate": 0.29932427919693017,
      "loss": 0.1705,
      "num_input_tokens_seen": 338832,
      "step": 1210
    },
    {
      "epoch": 13.5,
      "grad_norm": 0.0036266183014959097,
      "learning_rate": 0.2993186827947834,
      "loss": 0.1669,
      "num_input_tokens_seen": 340224,
      "step": 1215
    },
    {
      "epoch": 13.555555555555555,
      "grad_norm": 0.005932566709816456,
      "learning_rate": 0.2993130633658194,
      "loss": 0.1983,
      "num_input_tokens_seen": 341616,
      "step": 1220
    },
    {
      "epoch": 13.61111111111111,
      "grad_norm": 0.004077613819390535,
      "learning_rate": 0.29930742091090456,
      "loss": 0.1641,
      "num_input_tokens_seen": 342992,
      "step": 1225
    },
    {
      "epoch": 13.666666666666666,
      "grad_norm": 0.004171263892203569,
      "learning_rate": 0.29930175543090914,
      "loss": 0.1786,
      "num_input_tokens_seen": 344384,
      "step": 1230
    },
    {
      "epoch": 13.722222222222221,
      "grad_norm": 0.014602097682654858,
      "learning_rate": 0.2992960669267068,
      "loss": 0.188,
      "num_input_tokens_seen": 345824,
      "step": 1235
    },
    {
      "epoch": 13.777777777777779,
      "grad_norm": 0.016857454553246498,
      "learning_rate": 0.29929035539917476,
      "loss": 0.1705,
      "num_input_tokens_seen": 347248,
      "step": 1240
    },
    {
      "epoch": 13.833333333333334,
      "grad_norm": 0.012672705575823784,
      "learning_rate": 0.2992846208491938,
      "loss": 0.1707,
      "num_input_tokens_seen": 348672,
      "step": 1245
    },
    {
      "epoch": 13.88888888888889,
      "grad_norm": 0.004621115047484636,
      "learning_rate": 0.2992788632776483,
      "loss": 0.1754,
      "num_input_tokens_seen": 350032,
      "step": 1250
    },
    {
      "epoch": 13.944444444444445,
      "grad_norm": 0.009017455391585827,
      "learning_rate": 0.29927308268542613,
      "loss": 0.176,
      "num_input_tokens_seen": 351392,
      "step": 1255
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.006667544599622488,
      "learning_rate": 0.2992672790734187,
      "loss": 0.1874,
      "num_input_tokens_seen": 352784,
      "step": 1260
    },
    {
      "epoch": 14.055555555555555,
      "grad_norm": 0.004002798348665237,
      "learning_rate": 0.299261452442521,
      "loss": 0.1739,
      "num_input_tokens_seen": 354176,
      "step": 1265
    },
    {
      "epoch": 14.11111111111111,
      "grad_norm": 0.005514585878700018,
      "learning_rate": 0.29925560279363167,
      "loss": 0.1718,
      "num_input_tokens_seen": 355568,
      "step": 1270
    },
    {
      "epoch": 14.166666666666666,
      "grad_norm": 0.004711905028671026,
      "learning_rate": 0.29924973012765266,
      "loss": 0.1717,
      "num_input_tokens_seen": 356960,
      "step": 1275
    },
    {
      "epoch": 14.222222222222221,
      "grad_norm": 0.004868326708674431,
      "learning_rate": 0.29924383444548974,
      "loss": 0.1697,
      "num_input_tokens_seen": 358368,
      "step": 1280
    },
    {
      "epoch": 14.277777777777779,
      "grad_norm": 0.0032445332035422325,
      "learning_rate": 0.299237915748052,
      "loss": 0.1726,
      "num_input_tokens_seen": 359760,
      "step": 1285
    },
    {
      "epoch": 14.333333333333334,
      "grad_norm": 0.0035816174931824207,
      "learning_rate": 0.2992319740362522,
      "loss": 0.1692,
      "num_input_tokens_seen": 361200,
      "step": 1290
    },
    {
      "epoch": 14.38888888888889,
      "grad_norm": 0.007958526723086834,
      "learning_rate": 0.2992260093110066,
      "loss": 0.177,
      "num_input_tokens_seen": 362656,
      "step": 1295
    },
    {
      "epoch": 14.444444444444445,
      "grad_norm": 0.006710560526698828,
      "learning_rate": 0.2992200215732352,
      "loss": 0.1867,
      "num_input_tokens_seen": 364032,
      "step": 1300
    },
    {
      "epoch": 14.5,
      "grad_norm": 0.0036737779155373573,
      "learning_rate": 0.2992140108238611,
      "loss": 0.167,
      "num_input_tokens_seen": 365408,
      "step": 1305
    },
    {
      "epoch": 14.555555555555555,
      "grad_norm": 0.004349966067820787,
      "learning_rate": 0.2992079770638115,
      "loss": 0.161,
      "num_input_tokens_seen": 366784,
      "step": 1310
    },
    {
      "epoch": 14.61111111111111,
      "grad_norm": 0.0030140706803649664,
      "learning_rate": 0.29920192029401677,
      "loss": 0.1759,
      "num_input_tokens_seen": 368176,
      "step": 1315
    },
    {
      "epoch": 14.666666666666666,
      "grad_norm": 0.0025623731780797243,
      "learning_rate": 0.2991958405154109,
      "loss": 0.1776,
      "num_input_tokens_seen": 369552,
      "step": 1320
    },
    {
      "epoch": 14.722222222222221,
      "grad_norm": 0.005390144418925047,
      "learning_rate": 0.29918973772893154,
      "loss": 0.1744,
      "num_input_tokens_seen": 370944,
      "step": 1325
    },
    {
      "epoch": 14.777777777777779,
      "grad_norm": 0.00425472017377615,
      "learning_rate": 0.29918361193551973,
      "loss": 0.1748,
      "num_input_tokens_seen": 372368,
      "step": 1330
    },
    {
      "epoch": 14.833333333333334,
      "grad_norm": 0.0027810493484139442,
      "learning_rate": 0.29917746313612026,
      "loss": 0.1734,
      "num_input_tokens_seen": 373760,
      "step": 1335
    },
    {
      "epoch": 14.88888888888889,
      "grad_norm": 0.003921749070286751,
      "learning_rate": 0.29917129133168124,
      "loss": 0.1694,
      "num_input_tokens_seen": 375120,
      "step": 1340
    },
    {
      "epoch": 14.944444444444445,
      "grad_norm": 0.004692870192229748,
      "learning_rate": 0.2991650965231546,
      "loss": 0.169,
      "num_input_tokens_seen": 376528,
      "step": 1345
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.006828210782259703,
      "learning_rate": 0.29915887871149544,
      "loss": 0.1685,
      "num_input_tokens_seen": 377952,
      "step": 1350
    },
    {
      "epoch": 15.055555555555555,
      "grad_norm": 0.0027236940804868937,
      "learning_rate": 0.2991526378976628,
      "loss": 0.1693,
      "num_input_tokens_seen": 379328,
      "step": 1355
    },
    {
      "epoch": 15.11111111111111,
      "grad_norm": 0.004414111841470003,
      "learning_rate": 0.29914637408261896,
      "loss": 0.1679,
      "num_input_tokens_seen": 380720,
      "step": 1360
    },
    {
      "epoch": 15.166666666666666,
      "grad_norm": 0.0042732530273497105,
      "learning_rate": 0.29914008726733,
      "loss": 0.1666,
      "num_input_tokens_seen": 382096,
      "step": 1365
    },
    {
      "epoch": 15.222222222222221,
      "grad_norm": 0.007262461353093386,
      "learning_rate": 0.2991337774527653,
      "loss": 0.1783,
      "num_input_tokens_seen": 383488,
      "step": 1370
    },
    {
      "epoch": 15.277777777777779,
      "grad_norm": 0.006404122803360224,
      "learning_rate": 0.2991274446398981,
      "loss": 0.1856,
      "num_input_tokens_seen": 384848,
      "step": 1375
    },
    {
      "epoch": 15.333333333333334,
      "grad_norm": 0.0036777430213987827,
      "learning_rate": 0.29912108882970484,
      "loss": 0.1604,
      "num_input_tokens_seen": 386256,
      "step": 1380
    },
    {
      "epoch": 15.38888888888889,
      "grad_norm": 0.007058757357299328,
      "learning_rate": 0.2991147100231657,
      "loss": 0.1761,
      "num_input_tokens_seen": 387696,
      "step": 1385
    },
    {
      "epoch": 15.444444444444445,
      "grad_norm": 0.004902208223938942,
      "learning_rate": 0.2991083082212644,
      "loss": 0.168,
      "num_input_tokens_seen": 389072,
      "step": 1390
    },
    {
      "epoch": 15.5,
      "grad_norm": 0.006436290685087442,
      "learning_rate": 0.2991018834249881,
      "loss": 0.1753,
      "num_input_tokens_seen": 390464,
      "step": 1395
    },
    {
      "epoch": 15.555555555555555,
      "grad_norm": 0.007415710482746363,
      "learning_rate": 0.29909543563532764,
      "loss": 0.1546,
      "num_input_tokens_seen": 391904,
      "step": 1400
    },
    {
      "epoch": 15.555555555555555,
      "eval_loss": 0.17420975863933563,
      "eval_runtime": 1.1802,
      "eval_samples_per_second": 33.893,
      "eval_steps_per_second": 16.947,
      "num_input_tokens_seen": 391904,
      "step": 1400
    },
    {
      "epoch": 15.61111111111111,
      "grad_norm": 0.006743347737938166,
      "learning_rate": 0.29908896485327746,
      "loss": 0.178,
      "num_input_tokens_seen": 393344,
      "step": 1405
    },
    {
      "epoch": 15.666666666666666,
      "grad_norm": 0.008449414744973183,
      "learning_rate": 0.29908247107983527,
      "loss": 0.1727,
      "num_input_tokens_seen": 394784,
      "step": 1410
    },
    {
      "epoch": 15.722222222222221,
      "grad_norm": 0.00778926769271493,
      "learning_rate": 0.29907595431600253,
      "loss": 0.1656,
      "num_input_tokens_seen": 396176,
      "step": 1415
    },
    {
      "epoch": 15.777777777777779,
      "grad_norm": 0.005410360172390938,
      "learning_rate": 0.29906941456278424,
      "loss": 0.1708,
      "num_input_tokens_seen": 397552,
      "step": 1420
    },
    {
      "epoch": 15.833333333333334,
      "grad_norm": 0.006964739877730608,
      "learning_rate": 0.2990628518211889,
      "loss": 0.1728,
      "num_input_tokens_seen": 398960,
      "step": 1425
    },
    {
      "epoch": 15.88888888888889,
      "grad_norm": 0.0062829055823385715,
      "learning_rate": 0.2990562660922286,
      "loss": 0.1676,
      "num_input_tokens_seen": 400384,
      "step": 1430
    },
    {
      "epoch": 15.944444444444445,
      "grad_norm": 0.00704622408375144,
      "learning_rate": 0.2990496573769189,
      "loss": 0.1768,
      "num_input_tokens_seen": 401776,
      "step": 1435
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.0038941199891269207,
      "learning_rate": 0.29904302567627894,
      "loss": 0.1689,
      "num_input_tokens_seen": 403168,
      "step": 1440
    },
    {
      "epoch": 16.055555555555557,
      "grad_norm": 0.005561035592108965,
      "learning_rate": 0.2990363709913314,
      "loss": 0.1713,
      "num_input_tokens_seen": 404592,
      "step": 1445
    },
    {
      "epoch": 16.11111111111111,
      "grad_norm": 0.007382064592093229,
      "learning_rate": 0.29902969332310264,
      "loss": 0.1636,
      "num_input_tokens_seen": 405984,
      "step": 1450
    },
    {
      "epoch": 16.166666666666668,
      "grad_norm": 0.007476955186575651,
      "learning_rate": 0.2990229926726223,
      "loss": 0.1684,
      "num_input_tokens_seen": 407392,
      "step": 1455
    },
    {
      "epoch": 16.22222222222222,
      "grad_norm": 0.012936102226376534,
      "learning_rate": 0.29901626904092365,
      "loss": 0.1592,
      "num_input_tokens_seen": 408768,
      "step": 1460
    },
    {
      "epoch": 16.27777777777778,
      "grad_norm": 0.0072236377745866776,
      "learning_rate": 0.2990095224290438,
      "loss": 0.1683,
      "num_input_tokens_seen": 410144,
      "step": 1465
    },
    {
      "epoch": 16.333333333333332,
      "grad_norm": 0.0241326205432415,
      "learning_rate": 0.29900275283802297,
      "loss": 0.189,
      "num_input_tokens_seen": 411568,
      "step": 1470
    },
    {
      "epoch": 16.38888888888889,
      "grad_norm": 0.00902120117098093,
      "learning_rate": 0.2989959602689051,
      "loss": 0.1751,
      "num_input_tokens_seen": 412976,
      "step": 1475
    },
    {
      "epoch": 16.444444444444443,
      "grad_norm": 0.011170067824423313,
      "learning_rate": 0.2989891447227379,
      "loss": 0.1769,
      "num_input_tokens_seen": 414368,
      "step": 1480
    },
    {
      "epoch": 16.5,
      "grad_norm": 0.010861322283744812,
      "learning_rate": 0.29898230620057215,
      "loss": 0.1766,
      "num_input_tokens_seen": 415760,
      "step": 1485
    },
    {
      "epoch": 16.555555555555557,
      "grad_norm": 0.008054593577980995,
      "learning_rate": 0.2989754447034626,
      "loss": 0.162,
      "num_input_tokens_seen": 417184,
      "step": 1490
    },
    {
      "epoch": 16.61111111111111,
      "grad_norm": 0.0073050945065915585,
      "learning_rate": 0.2989685602324673,
      "loss": 0.1971,
      "num_input_tokens_seen": 418544,
      "step": 1495
    },
    {
      "epoch": 16.666666666666668,
      "grad_norm": 0.007746637333184481,
      "learning_rate": 0.298961652788648,
      "loss": 0.1719,
      "num_input_tokens_seen": 419952,
      "step": 1500
    },
    {
      "epoch": 16.72222222222222,
      "grad_norm": 0.029215006157755852,
      "learning_rate": 0.29895472237306986,
      "loss": 0.1818,
      "num_input_tokens_seen": 421392,
      "step": 1505
    },
    {
      "epoch": 16.77777777777778,
      "grad_norm": 0.09845131635665894,
      "learning_rate": 0.29894776898680164,
      "loss": 0.2023,
      "num_input_tokens_seen": 422784,
      "step": 1510
    },
    {
      "epoch": 16.833333333333332,
      "grad_norm": 0.00546360295265913,
      "learning_rate": 0.29894079263091566,
      "loss": 0.1603,
      "num_input_tokens_seen": 424192,
      "step": 1515
    },
    {
      "epoch": 16.88888888888889,
      "grad_norm": 0.006391468457877636,
      "learning_rate": 0.2989337933064877,
      "loss": 0.1735,
      "num_input_tokens_seen": 425568,
      "step": 1520
    },
    {
      "epoch": 16.944444444444443,
      "grad_norm": 0.0038179983384907246,
      "learning_rate": 0.29892677101459725,
      "loss": 0.1731,
      "num_input_tokens_seen": 426960,
      "step": 1525
    },
    {
      "epoch": 17.0,
      "grad_norm": 0.0031775319948792458,
      "learning_rate": 0.2989197257563272,
      "loss": 0.1729,
      "num_input_tokens_seen": 428384,
      "step": 1530
    },
    {
      "epoch": 17.055555555555557,
      "grad_norm": 0.006537334062159061,
      "learning_rate": 0.2989126575327639,
      "loss": 0.1869,
      "num_input_tokens_seen": 429776,
      "step": 1535
    },
    {
      "epoch": 17.11111111111111,
      "grad_norm": 0.0057896943762898445,
      "learning_rate": 0.29890556634499754,
      "loss": 0.1752,
      "num_input_tokens_seen": 431248,
      "step": 1540
    },
    {
      "epoch": 17.166666666666668,
      "grad_norm": 0.004804255440831184,
      "learning_rate": 0.2988984521941216,
      "loss": 0.1716,
      "num_input_tokens_seen": 432656,
      "step": 1545
    },
    {
      "epoch": 17.22222222222222,
      "grad_norm": 0.004060376435518265,
      "learning_rate": 0.29889131508123307,
      "loss": 0.1747,
      "num_input_tokens_seen": 434048,
      "step": 1550
    },
    {
      "epoch": 17.27777777777778,
      "grad_norm": 0.003497556783258915,
      "learning_rate": 0.2988841550074327,
      "loss": 0.1705,
      "num_input_tokens_seen": 435488,
      "step": 1555
    },
    {
      "epoch": 17.333333333333332,
      "grad_norm": 0.003570201573893428,
      "learning_rate": 0.2988769719738246,
      "loss": 0.1717,
      "num_input_tokens_seen": 436880,
      "step": 1560
    },
    {
      "epoch": 17.38888888888889,
      "grad_norm": 0.009563388302922249,
      "learning_rate": 0.29886976598151666,
      "loss": 0.1761,
      "num_input_tokens_seen": 438256,
      "step": 1565
    },
    {
      "epoch": 17.444444444444443,
      "grad_norm": 0.003832289483398199,
      "learning_rate": 0.29886253703161986,
      "loss": 0.1922,
      "num_input_tokens_seen": 439664,
      "step": 1570
    },
    {
      "epoch": 17.5,
      "grad_norm": 0.005391442216932774,
      "learning_rate": 0.29885528512524917,
      "loss": 0.1669,
      "num_input_tokens_seen": 441088,
      "step": 1575
    },
    {
      "epoch": 17.555555555555557,
      "grad_norm": 0.0026272828690707684,
      "learning_rate": 0.29884801026352287,
      "loss": 0.1695,
      "num_input_tokens_seen": 442496,
      "step": 1580
    },
    {
      "epoch": 17.61111111111111,
      "grad_norm": 0.0021701750811189413,
      "learning_rate": 0.2988407124475629,
      "loss": 0.1563,
      "num_input_tokens_seen": 443872,
      "step": 1585
    },
    {
      "epoch": 17.666666666666668,
      "grad_norm": 0.005678958259522915,
      "learning_rate": 0.2988333916784945,
      "loss": 0.1921,
      "num_input_tokens_seen": 445312,
      "step": 1590
    },
    {
      "epoch": 17.72222222222222,
      "grad_norm": 0.0023620210122317076,
      "learning_rate": 0.2988260479574468,
      "loss": 0.1721,
      "num_input_tokens_seen": 446736,
      "step": 1595
    },
    {
      "epoch": 17.77777777777778,
      "grad_norm": 0.004116011783480644,
      "learning_rate": 0.2988186812855523,
      "loss": 0.1698,
      "num_input_tokens_seen": 448112,
      "step": 1600
    },
    {
      "epoch": 17.77777777777778,
      "eval_loss": 0.1744115650653839,
      "eval_runtime": 1.1837,
      "eval_samples_per_second": 33.794,
      "eval_steps_per_second": 16.897,
      "num_input_tokens_seen": 448112,
      "step": 1600
    },
    {
      "epoch": 17.833333333333332,
      "grad_norm": 0.002703665988519788,
      "learning_rate": 0.29881129166394693,
      "loss": 0.1752,
      "num_input_tokens_seen": 449504,
      "step": 1605
    },
    {
      "epoch": 17.88888888888889,
      "grad_norm": 0.003802638500928879,
      "learning_rate": 0.29880387909377026,
      "loss": 0.1728,
      "num_input_tokens_seen": 450896,
      "step": 1610
    },
    {
      "epoch": 17.944444444444443,
      "grad_norm": 0.007174426689743996,
      "learning_rate": 0.2987964435761655,
      "loss": 0.1763,
      "num_input_tokens_seen": 452256,
      "step": 1615
    },
    {
      "epoch": 18.0,
      "grad_norm": 0.0021126328501850367,
      "learning_rate": 0.29878898511227925,
      "loss": 0.1763,
      "num_input_tokens_seen": 453648,
      "step": 1620
    },
    {
      "epoch": 18.055555555555557,
      "grad_norm": 0.006316913291811943,
      "learning_rate": 0.2987815037032617,
      "loss": 0.1658,
      "num_input_tokens_seen": 455024,
      "step": 1625
    },
    {
      "epoch": 18.11111111111111,
      "grad_norm": 0.003521303180605173,
      "learning_rate": 0.29877399935026655,
      "loss": 0.1741,
      "num_input_tokens_seen": 456384,
      "step": 1630
    },
    {
      "epoch": 18.166666666666668,
      "grad_norm": 0.0037656037602573633,
      "learning_rate": 0.2987664720544511,
      "loss": 0.1645,
      "num_input_tokens_seen": 457824,
      "step": 1635
    },
    {
      "epoch": 18.22222222222222,
      "grad_norm": 0.0031731477938592434,
      "learning_rate": 0.2987589218169761,
      "loss": 0.1749,
      "num_input_tokens_seen": 459136,
      "step": 1640
    },
    {
      "epoch": 18.27777777777778,
      "grad_norm": 0.0028441296890378,
      "learning_rate": 0.29875134863900604,
      "loss": 0.1764,
      "num_input_tokens_seen": 460544,
      "step": 1645
    },
    {
      "epoch": 18.333333333333332,
      "grad_norm": 0.002371678128838539,
      "learning_rate": 0.29874375252170865,
      "loss": 0.1734,
      "num_input_tokens_seen": 461968,
      "step": 1650
    },
    {
      "epoch": 18.38888888888889,
      "grad_norm": 0.0028279079124331474,
      "learning_rate": 0.2987361334662553,
      "loss": 0.1741,
      "num_input_tokens_seen": 463376,
      "step": 1655
    },
    {
      "epoch": 18.444444444444443,
      "grad_norm": 0.0061046467162668705,
      "learning_rate": 0.29872849147382113,
      "loss": 0.1686,
      "num_input_tokens_seen": 464768,
      "step": 1660
    },
    {
      "epoch": 18.5,
      "grad_norm": 0.00508917635306716,
      "learning_rate": 0.2987208265455845,
      "loss": 0.1787,
      "num_input_tokens_seen": 466144,
      "step": 1665
    },
    {
      "epoch": 18.555555555555557,
      "grad_norm": 0.005896742921322584,
      "learning_rate": 0.29871313868272753,
      "loss": 0.1679,
      "num_input_tokens_seen": 467504,
      "step": 1670
    },
    {
      "epoch": 18.61111111111111,
      "grad_norm": 0.004169300198554993,
      "learning_rate": 0.29870542788643567,
      "loss": 0.181,
      "num_input_tokens_seen": 468912,
      "step": 1675
    },
    {
      "epoch": 18.666666666666668,
      "grad_norm": 0.00366671709343791,
      "learning_rate": 0.2986976941578981,
      "loss": 0.1592,
      "num_input_tokens_seen": 470304,
      "step": 1680
    },
    {
      "epoch": 18.72222222222222,
      "grad_norm": 0.003961179871112108,
      "learning_rate": 0.29868993749830747,
      "loss": 0.1743,
      "num_input_tokens_seen": 471712,
      "step": 1685
    },
    {
      "epoch": 18.77777777777778,
      "grad_norm": 0.008186398074030876,
      "learning_rate": 0.2986821579088598,
      "loss": 0.1727,
      "num_input_tokens_seen": 473072,
      "step": 1690
    },
    {
      "epoch": 18.833333333333332,
      "grad_norm": 0.003745185909792781,
      "learning_rate": 0.29867435539075504,
      "loss": 0.1723,
      "num_input_tokens_seen": 474512,
      "step": 1695
    },
    {
      "epoch": 18.88888888888889,
      "grad_norm": 0.0056685637682676315,
      "learning_rate": 0.2986665299451963,
      "loss": 0.1644,
      "num_input_tokens_seen": 475936,
      "step": 1700
    },
    {
      "epoch": 18.944444444444443,
      "grad_norm": 0.006180883385241032,
      "learning_rate": 0.29865868157339037,
      "loss": 0.1756,
      "num_input_tokens_seen": 477392,
      "step": 1705
    },
    {
      "epoch": 19.0,
      "grad_norm": 0.006767569575458765,
      "learning_rate": 0.2986508102765476,
      "loss": 0.1634,
      "num_input_tokens_seen": 478768,
      "step": 1710
    },
    {
      "epoch": 19.055555555555557,
      "grad_norm": 0.008925042115151882,
      "learning_rate": 0.2986429160558818,
      "loss": 0.1775,
      "num_input_tokens_seen": 480176,
      "step": 1715
    },
    {
      "epoch": 19.11111111111111,
      "grad_norm": 0.010770408436655998,
      "learning_rate": 0.2986349989126104,
      "loss": 0.177,
      "num_input_tokens_seen": 481552,
      "step": 1720
    },
    {
      "epoch": 19.166666666666668,
      "grad_norm": 0.006137126125395298,
      "learning_rate": 0.29862705884795426,
      "loss": 0.1654,
      "num_input_tokens_seen": 482928,
      "step": 1725
    },
    {
      "epoch": 19.22222222222222,
      "grad_norm": 0.006887048948556185,
      "learning_rate": 0.2986190958631379,
      "loss": 0.1624,
      "num_input_tokens_seen": 484320,
      "step": 1730
    },
    {
      "epoch": 19.27777777777778,
      "grad_norm": 0.008304418064653873,
      "learning_rate": 0.29861110995938933,
      "loss": 0.1771,
      "num_input_tokens_seen": 485712,
      "step": 1735
    },
    {
      "epoch": 19.333333333333332,
      "grad_norm": 0.004565942566841841,
      "learning_rate": 0.29860310113794,
      "loss": 0.1755,
      "num_input_tokens_seen": 487168,
      "step": 1740
    },
    {
      "epoch": 19.38888888888889,
      "grad_norm": 0.006411653012037277,
      "learning_rate": 0.29859506940002506,
      "loss": 0.1665,
      "num_input_tokens_seen": 488528,
      "step": 1745
    },
    {
      "epoch": 19.444444444444443,
      "grad_norm": 0.020208822563290596,
      "learning_rate": 0.298587014746883,
      "loss": 0.1892,
      "num_input_tokens_seen": 489920,
      "step": 1750
    },
    {
      "epoch": 19.5,
      "grad_norm": 0.005653726402670145,
      "learning_rate": 0.298578937179756,
      "loss": 0.1603,
      "num_input_tokens_seen": 491328,
      "step": 1755
    },
    {
      "epoch": 19.555555555555557,
      "grad_norm": 0.006872037425637245,
      "learning_rate": 0.29857083669988976,
      "loss": 0.1713,
      "num_input_tokens_seen": 492704,
      "step": 1760
    },
    {
      "epoch": 19.61111111111111,
      "grad_norm": 0.006079623010009527,
      "learning_rate": 0.29856271330853346,
      "loss": 0.1743,
      "num_input_tokens_seen": 494096,
      "step": 1765
    },
    {
      "epoch": 19.666666666666668,
      "grad_norm": 0.00857944879680872,
      "learning_rate": 0.2985545670069398,
      "loss": 0.1563,
      "num_input_tokens_seen": 495504,
      "step": 1770
    },
    {
      "epoch": 19.72222222222222,
      "grad_norm": 0.0064294408075511456,
      "learning_rate": 0.29854639779636505,
      "loss": 0.1746,
      "num_input_tokens_seen": 496944,
      "step": 1775
    },
    {
      "epoch": 19.77777777777778,
      "grad_norm": 0.0071604992263019085,
      "learning_rate": 0.298538205678069,
      "loss": 0.1776,
      "num_input_tokens_seen": 498336,
      "step": 1780
    },
    {
      "epoch": 19.833333333333332,
      "grad_norm": 0.00592733733355999,
      "learning_rate": 0.298529990653315,
      "loss": 0.1605,
      "num_input_tokens_seen": 499776,
      "step": 1785
    },
    {
      "epoch": 19.88888888888889,
      "grad_norm": 0.007601930294185877,
      "learning_rate": 0.29852175272336984,
      "loss": 0.1805,
      "num_input_tokens_seen": 501120,
      "step": 1790
    },
    {
      "epoch": 19.944444444444443,
      "grad_norm": 0.007028522435575724,
      "learning_rate": 0.29851349188950405,
      "loss": 0.1731,
      "num_input_tokens_seen": 502480,
      "step": 1795
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.009828051552176476,
      "learning_rate": 0.2985052081529914,
      "loss": 0.1734,
      "num_input_tokens_seen": 503920,
      "step": 1800
    },
    {
      "epoch": 20.0,
      "eval_loss": 0.17556536197662354,
      "eval_runtime": 1.1792,
      "eval_samples_per_second": 33.921,
      "eval_steps_per_second": 16.961,
      "num_input_tokens_seen": 503920,
      "step": 1800
    },
    {
      "epoch": 20.055555555555557,
      "grad_norm": 0.0077247535809874535,
      "learning_rate": 0.29849690151510944,
      "loss": 0.1545,
      "num_input_tokens_seen": 505296,
      "step": 1805
    },
    {
      "epoch": 20.11111111111111,
      "grad_norm": 0.010482233949005604,
      "learning_rate": 0.2984885719771392,
      "loss": 0.1622,
      "num_input_tokens_seen": 506688,
      "step": 1810
    },
    {
      "epoch": 20.166666666666668,
      "grad_norm": 0.012891927734017372,
      "learning_rate": 0.2984802195403651,
      "loss": 0.1543,
      "num_input_tokens_seen": 508112,
      "step": 1815
    },
    {
      "epoch": 20.22222222222222,
      "grad_norm": 0.013015256263315678,
      "learning_rate": 0.2984718442060752,
      "loss": 0.1515,
      "num_input_tokens_seen": 509488,
      "step": 1820
    },
    {
      "epoch": 20.27777777777778,
      "grad_norm": 0.03112434782087803,
      "learning_rate": 0.2984634459755611,
      "loss": 0.1707,
      "num_input_tokens_seen": 510928,
      "step": 1825
    },
    {
      "epoch": 20.333333333333332,
      "grad_norm": 0.0368560329079628,
      "learning_rate": 0.29845502485011793,
      "loss": 0.1802,
      "num_input_tokens_seen": 512352,
      "step": 1830
    },
    {
      "epoch": 20.38888888888889,
      "grad_norm": 0.008416109718382359,
      "learning_rate": 0.2984465808310444,
      "loss": 0.203,
      "num_input_tokens_seen": 513792,
      "step": 1835
    },
    {
      "epoch": 20.444444444444443,
      "grad_norm": 0.012559815309941769,
      "learning_rate": 0.29843811391964253,
      "loss": 0.1778,
      "num_input_tokens_seen": 515232,
      "step": 1840
    },
    {
      "epoch": 20.5,
      "grad_norm": 0.0071220058016479015,
      "learning_rate": 0.2984296241172182,
      "loss": 0.1668,
      "num_input_tokens_seen": 516608,
      "step": 1845
    },
    {
      "epoch": 20.555555555555557,
      "grad_norm": 0.007233915850520134,
      "learning_rate": 0.29842111142508043,
      "loss": 0.1729,
      "num_input_tokens_seen": 517984,
      "step": 1850
    },
    {
      "epoch": 20.61111111111111,
      "grad_norm": 0.0057553318329155445,
      "learning_rate": 0.29841257584454217,
      "loss": 0.1656,
      "num_input_tokens_seen": 519392,
      "step": 1855
    },
    {
      "epoch": 20.666666666666668,
      "grad_norm": 0.006228514946997166,
      "learning_rate": 0.29840401737691963,
      "loss": 0.1853,
      "num_input_tokens_seen": 520768,
      "step": 1860
    },
    {
      "epoch": 20.72222222222222,
      "grad_norm": 0.005604911129921675,
      "learning_rate": 0.29839543602353263,
      "loss": 0.1635,
      "num_input_tokens_seen": 522192,
      "step": 1865
    },
    {
      "epoch": 20.77777777777778,
      "grad_norm": 0.006576955784112215,
      "learning_rate": 0.2983868317857046,
      "loss": 0.162,
      "num_input_tokens_seen": 523616,
      "step": 1870
    },
    {
      "epoch": 20.833333333333332,
      "grad_norm": 0.008782811462879181,
      "learning_rate": 0.2983782046647623,
      "loss": 0.1965,
      "num_input_tokens_seen": 525008,
      "step": 1875
    },
    {
      "epoch": 20.88888888888889,
      "grad_norm": 0.003768229391425848,
      "learning_rate": 0.2983695546620362,
      "loss": 0.1683,
      "num_input_tokens_seen": 526384,
      "step": 1880
    },
    {
      "epoch": 20.944444444444443,
      "grad_norm": 0.004797907546162605,
      "learning_rate": 0.2983608817788603,
      "loss": 0.167,
      "num_input_tokens_seen": 527808,
      "step": 1885
    },
    {
      "epoch": 21.0,
      "grad_norm": 0.006949875969439745,
      "learning_rate": 0.29835218601657193,
      "loss": 0.1732,
      "num_input_tokens_seen": 529216,
      "step": 1890
    },
    {
      "epoch": 21.055555555555557,
      "grad_norm": 0.00326824514195323,
      "learning_rate": 0.29834346737651224,
      "loss": 0.1705,
      "num_input_tokens_seen": 530624,
      "step": 1895
    },
    {
      "epoch": 21.11111111111111,
      "grad_norm": 0.009640603326261044,
      "learning_rate": 0.29833472586002563,
      "loss": 0.1791,
      "num_input_tokens_seen": 532032,
      "step": 1900
    },
    {
      "epoch": 21.166666666666668,
      "grad_norm": 0.003133743302896619,
      "learning_rate": 0.29832596146846024,
      "loss": 0.1785,
      "num_input_tokens_seen": 533408,
      "step": 1905
    },
    {
      "epoch": 21.22222222222222,
      "grad_norm": 0.004656275734305382,
      "learning_rate": 0.2983171742031676,
      "loss": 0.177,
      "num_input_tokens_seen": 534816,
      "step": 1910
    },
    {
      "epoch": 21.27777777777778,
      "grad_norm": 0.00397328520193696,
      "learning_rate": 0.2983083640655028,
      "loss": 0.168,
      "num_input_tokens_seen": 536208,
      "step": 1915
    },
    {
      "epoch": 21.333333333333332,
      "grad_norm": 0.003357134060934186,
      "learning_rate": 0.29829953105682455,
      "loss": 0.1636,
      "num_input_tokens_seen": 537632,
      "step": 1920
    },
    {
      "epoch": 21.38888888888889,
      "grad_norm": 0.006366443820297718,
      "learning_rate": 0.29829067517849495,
      "loss": 0.172,
      "num_input_tokens_seen": 539040,
      "step": 1925
    },
    {
      "epoch": 21.444444444444443,
      "grad_norm": 0.24966253340244293,
      "learning_rate": 0.2982817964318797,
      "loss": 0.1785,
      "num_input_tokens_seen": 540464,
      "step": 1930
    },
    {
      "epoch": 21.5,
      "grad_norm": 0.04674345254898071,
      "learning_rate": 0.298272894818348,
      "loss": 0.1885,
      "num_input_tokens_seen": 541872,
      "step": 1935
    },
    {
      "epoch": 21.555555555555557,
      "grad_norm": 0.009635956026613712,
      "learning_rate": 0.2982639703392726,
      "loss": 0.1841,
      "num_input_tokens_seen": 543264,
      "step": 1940
    },
    {
      "epoch": 21.61111111111111,
      "grad_norm": 0.011453678831458092,
      "learning_rate": 0.29825502299602974,
      "loss": 0.1949,
      "num_input_tokens_seen": 544688,
      "step": 1945
    },
    {
      "epoch": 21.666666666666668,
      "grad_norm": 0.018026864156126976,
      "learning_rate": 0.2982460527899993,
      "loss": 0.1755,
      "num_input_tokens_seen": 546096,
      "step": 1950
    },
    {
      "epoch": 21.72222222222222,
      "grad_norm": 0.01168943103402853,
      "learning_rate": 0.29823705972256453,
      "loss": 0.1843,
      "num_input_tokens_seen": 547472,
      "step": 1955
    },
    {
      "epoch": 21.77777777777778,
      "grad_norm": 0.005740626249462366,
      "learning_rate": 0.2982280437951123,
      "loss": 0.1712,
      "num_input_tokens_seen": 548912,
      "step": 1960
    },
    {
      "epoch": 21.833333333333332,
      "grad_norm": 0.0047860960476100445,
      "learning_rate": 0.298219005009033,
      "loss": 0.1782,
      "num_input_tokens_seen": 550304,
      "step": 1965
    },
    {
      "epoch": 21.88888888888889,
      "grad_norm": 0.013611485250294209,
      "learning_rate": 0.29820994336572043,
      "loss": 0.1847,
      "num_input_tokens_seen": 551664,
      "step": 1970
    },
    {
      "epoch": 21.944444444444443,
      "grad_norm": 0.009965701960027218,
      "learning_rate": 0.2982008588665721,
      "loss": 0.1751,
      "num_input_tokens_seen": 553040,
      "step": 1975
    },
    {
      "epoch": 22.0,
      "grad_norm": 0.010292254388332367,
      "learning_rate": 0.2981917515129889,
      "loss": 0.1827,
      "num_input_tokens_seen": 554400,
      "step": 1980
    },
    {
      "epoch": 22.055555555555557,
      "grad_norm": 0.0034435829147696495,
      "learning_rate": 0.2981826213063753,
      "loss": 0.1755,
      "num_input_tokens_seen": 555856,
      "step": 1985
    },
    {
      "epoch": 22.11111111111111,
      "grad_norm": 0.01039603166282177,
      "learning_rate": 0.2981734682481394,
      "loss": 0.1795,
      "num_input_tokens_seen": 557232,
      "step": 1990
    },
    {
      "epoch": 22.166666666666668,
      "grad_norm": 0.0025410677772015333,
      "learning_rate": 0.29816429233969255,
      "loss": 0.1744,
      "num_input_tokens_seen": 558640,
      "step": 1995
    },
    {
      "epoch": 22.22222222222222,
      "grad_norm": 0.004349651746451855,
      "learning_rate": 0.2981550935824499,
      "loss": 0.1819,
      "num_input_tokens_seen": 560016,
      "step": 2000
    },
    {
      "epoch": 22.22222222222222,
      "eval_loss": 0.1746228188276291,
      "eval_runtime": 1.1832,
      "eval_samples_per_second": 33.808,
      "eval_steps_per_second": 16.904,
      "num_input_tokens_seen": 560016,
      "step": 2000
    },
    {
      "epoch": 22.27777777777778,
      "grad_norm": 0.0066347988322377205,
      "learning_rate": 0.29814587197783,
      "loss": 0.1978,
      "num_input_tokens_seen": 561408,
      "step": 2005
    },
    {
      "epoch": 22.333333333333332,
      "grad_norm": 0.007606601808220148,
      "learning_rate": 0.29813662752725495,
      "loss": 0.1664,
      "num_input_tokens_seen": 562784,
      "step": 2010
    },
    {
      "epoch": 22.38888888888889,
      "grad_norm": 0.04297380521893501,
      "learning_rate": 0.29812736023215025,
      "loss": 0.1584,
      "num_input_tokens_seen": 564224,
      "step": 2015
    },
    {
      "epoch": 22.444444444444443,
      "grad_norm": 0.0076819974929094315,
      "learning_rate": 0.29811807009394514,
      "loss": 0.2222,
      "num_input_tokens_seen": 565616,
      "step": 2020
    },
    {
      "epoch": 22.5,
      "grad_norm": 0.007630663458257914,
      "learning_rate": 0.2981087571140723,
      "loss": 0.1835,
      "num_input_tokens_seen": 566992,
      "step": 2025
    },
    {
      "epoch": 22.555555555555557,
      "grad_norm": 0.004418624099344015,
      "learning_rate": 0.2980994212939678,
      "loss": 0.1954,
      "num_input_tokens_seen": 568384,
      "step": 2030
    },
    {
      "epoch": 22.61111111111111,
      "grad_norm": 0.007118997164070606,
      "learning_rate": 0.2980900626350715,
      "loss": 0.1809,
      "num_input_tokens_seen": 569792,
      "step": 2035
    },
    {
      "epoch": 22.666666666666668,
      "grad_norm": 0.0032298339065164328,
      "learning_rate": 0.29808068113882646,
      "loss": 0.1642,
      "num_input_tokens_seen": 571216,
      "step": 2040
    },
    {
      "epoch": 22.72222222222222,
      "grad_norm": 0.00402980949729681,
      "learning_rate": 0.2980712768066795,
      "loss": 0.1734,
      "num_input_tokens_seen": 572640,
      "step": 2045
    },
    {
      "epoch": 22.77777777777778,
      "grad_norm": 0.0052002910524606705,
      "learning_rate": 0.2980618496400809,
      "loss": 0.1831,
      "num_input_tokens_seen": 573968,
      "step": 2050
    },
    {
      "epoch": 22.833333333333332,
      "grad_norm": 0.004411559551954269,
      "learning_rate": 0.2980523996404844,
      "loss": 0.19,
      "num_input_tokens_seen": 575360,
      "step": 2055
    },
    {
      "epoch": 22.88888888888889,
      "grad_norm": 0.0064622401259839535,
      "learning_rate": 0.2980429268093473,
      "loss": 0.167,
      "num_input_tokens_seen": 576752,
      "step": 2060
    },
    {
      "epoch": 22.944444444444443,
      "grad_norm": 0.003765117609873414,
      "learning_rate": 0.29803343114813047,
      "loss": 0.1886,
      "num_input_tokens_seen": 578192,
      "step": 2065
    },
    {
      "epoch": 23.0,
      "grad_norm": 0.003793770680204034,
      "learning_rate": 0.2980239126582983,
      "loss": 0.1747,
      "num_input_tokens_seen": 579584,
      "step": 2070
    },
    {
      "epoch": 23.055555555555557,
      "grad_norm": 0.003144647693261504,
      "learning_rate": 0.2980143713413186,
      "loss": 0.1737,
      "num_input_tokens_seen": 580992,
      "step": 2075
    },
    {
      "epoch": 23.11111111111111,
      "grad_norm": 0.0017861989326775074,
      "learning_rate": 0.29800480719866274,
      "loss": 0.172,
      "num_input_tokens_seen": 582368,
      "step": 2080
    },
    {
      "epoch": 23.166666666666668,
      "grad_norm": 0.0017149434424936771,
      "learning_rate": 0.2979952202318057,
      "loss": 0.1727,
      "num_input_tokens_seen": 583760,
      "step": 2085
    },
    {
      "epoch": 23.22222222222222,
      "grad_norm": 0.004406941123306751,
      "learning_rate": 0.2979856104422259,
      "loss": 0.1775,
      "num_input_tokens_seen": 585184,
      "step": 2090
    },
    {
      "epoch": 23.27777777777778,
      "grad_norm": 0.0035247537307441235,
      "learning_rate": 0.2979759778314052,
      "loss": 0.1774,
      "num_input_tokens_seen": 586544,
      "step": 2095
    },
    {
      "epoch": 23.333333333333332,
      "grad_norm": 0.002953993622213602,
      "learning_rate": 0.2979663224008292,
      "loss": 0.172,
      "num_input_tokens_seen": 587952,
      "step": 2100
    },
    {
      "epoch": 23.38888888888889,
      "grad_norm": 0.00326116313226521,
      "learning_rate": 0.2979566441519868,
      "loss": 0.1713,
      "num_input_tokens_seen": 589376,
      "step": 2105
    },
    {
      "epoch": 23.444444444444443,
      "grad_norm": 0.003601839067414403,
      "learning_rate": 0.29794694308637054,
      "loss": 0.1704,
      "num_input_tokens_seen": 590832,
      "step": 2110
    },
    {
      "epoch": 23.5,
      "grad_norm": 0.0025815931148827076,
      "learning_rate": 0.2979372192054764,
      "loss": 0.1759,
      "num_input_tokens_seen": 592208,
      "step": 2115
    },
    {
      "epoch": 23.555555555555557,
      "grad_norm": 0.004768666811287403,
      "learning_rate": 0.297927472510804,
      "loss": 0.1745,
      "num_input_tokens_seen": 593584,
      "step": 2120
    },
    {
      "epoch": 23.61111111111111,
      "grad_norm": 0.0030980813317000866,
      "learning_rate": 0.29791770300385634,
      "loss": 0.169,
      "num_input_tokens_seen": 594928,
      "step": 2125
    },
    {
      "epoch": 23.666666666666668,
      "grad_norm": 0.002299671294167638,
      "learning_rate": 0.29790791068614003,
      "loss": 0.1731,
      "num_input_tokens_seen": 596304,
      "step": 2130
    },
    {
      "epoch": 23.72222222222222,
      "grad_norm": 0.0038470050785690546,
      "learning_rate": 0.2978980955591652,
      "loss": 0.1746,
      "num_input_tokens_seen": 597712,
      "step": 2135
    },
    {
      "epoch": 23.77777777777778,
      "grad_norm": 0.002911829389631748,
      "learning_rate": 0.2978882576244454,
      "loss": 0.1713,
      "num_input_tokens_seen": 599120,
      "step": 2140
    },
    {
      "epoch": 23.833333333333332,
      "grad_norm": 0.0033624249044805765,
      "learning_rate": 0.2978783968834978,
      "loss": 0.1762,
      "num_input_tokens_seen": 600528,
      "step": 2145
    },
    {
      "epoch": 23.88888888888889,
      "grad_norm": 0.007513659540563822,
      "learning_rate": 0.29786851333784303,
      "loss": 0.1827,
      "num_input_tokens_seen": 601920,
      "step": 2150
    },
    {
      "epoch": 23.944444444444443,
      "grad_norm": 0.00407102657482028,
      "learning_rate": 0.2978586069890053,
      "loss": 0.1739,
      "num_input_tokens_seen": 603296,
      "step": 2155
    },
    {
      "epoch": 24.0,
      "grad_norm": 0.0043313391506671906,
      "learning_rate": 0.29784867783851227,
      "loss": 0.1788,
      "num_input_tokens_seen": 604720,
      "step": 2160
    },
    {
      "epoch": 24.055555555555557,
      "grad_norm": 0.005618773866444826,
      "learning_rate": 0.2978387258878951,
      "loss": 0.1795,
      "num_input_tokens_seen": 606112,
      "step": 2165
    },
    {
      "epoch": 24.11111111111111,
      "grad_norm": 0.0038168500177562237,
      "learning_rate": 0.29782875113868856,
      "loss": 0.1788,
      "num_input_tokens_seen": 607488,
      "step": 2170
    },
    {
      "epoch": 24.166666666666668,
      "grad_norm": 0.003766281995922327,
      "learning_rate": 0.2978187535924309,
      "loss": 0.1807,
      "num_input_tokens_seen": 608912,
      "step": 2175
    },
    {
      "epoch": 24.22222222222222,
      "grad_norm": 0.0020905237179249525,
      "learning_rate": 0.29780873325066376,
      "loss": 0.1677,
      "num_input_tokens_seen": 610320,
      "step": 2180
    },
    {
      "epoch": 24.27777777777778,
      "grad_norm": 0.0037034957204014063,
      "learning_rate": 0.2977986901149325,
      "loss": 0.1721,
      "num_input_tokens_seen": 611760,
      "step": 2185
    },
    {
      "epoch": 24.333333333333332,
      "grad_norm": 0.0023015455808490515,
      "learning_rate": 0.29778862418678587,
      "loss": 0.1705,
      "num_input_tokens_seen": 613120,
      "step": 2190
    },
    {
      "epoch": 24.38888888888889,
      "grad_norm": 0.0038095531053841114,
      "learning_rate": 0.29777853546777616,
      "loss": 0.1697,
      "num_input_tokens_seen": 614544,
      "step": 2195
    },
    {
      "epoch": 24.444444444444443,
      "grad_norm": 0.00583682069554925,
      "learning_rate": 0.2977684239594592,
      "loss": 0.1603,
      "num_input_tokens_seen": 615952,
      "step": 2200
    },
    {
      "epoch": 24.444444444444443,
      "eval_loss": 0.18188528716564178,
      "eval_runtime": 1.1801,
      "eval_samples_per_second": 33.894,
      "eval_steps_per_second": 16.947,
      "num_input_tokens_seen": 615952,
      "step": 2200
    },
    {
      "epoch": 24.5,
      "grad_norm": 0.002657005563378334,
      "learning_rate": 0.29775828966339424,
      "loss": 0.1867,
      "num_input_tokens_seen": 617360,
      "step": 2205
    },
    {
      "epoch": 24.555555555555557,
      "grad_norm": 0.0030574880074709654,
      "learning_rate": 0.29774813258114424,
      "loss": 0.1585,
      "num_input_tokens_seen": 618736,
      "step": 2210
    },
    {
      "epoch": 24.61111111111111,
      "grad_norm": 0.002387805376201868,
      "learning_rate": 0.29773795271427544,
      "loss": 0.1812,
      "num_input_tokens_seen": 620128,
      "step": 2215
    },
    {
      "epoch": 24.666666666666668,
      "grad_norm": 0.0025200543459504843,
      "learning_rate": 0.2977277500643577,
      "loss": 0.1768,
      "num_input_tokens_seen": 621488,
      "step": 2220
    },
    {
      "epoch": 24.72222222222222,
      "grad_norm": 0.0036220685578882694,
      "learning_rate": 0.29771752463296447,
      "loss": 0.168,
      "num_input_tokens_seen": 622880,
      "step": 2225
    },
    {
      "epoch": 24.77777777777778,
      "grad_norm": 0.00685362983494997,
      "learning_rate": 0.29770727642167266,
      "loss": 0.1721,
      "num_input_tokens_seen": 624304,
      "step": 2230
    },
    {
      "epoch": 24.833333333333332,
      "grad_norm": 0.00426349276676774,
      "learning_rate": 0.29769700543206257,
      "loss": 0.1686,
      "num_input_tokens_seen": 625696,
      "step": 2235
    },
    {
      "epoch": 24.88888888888889,
      "grad_norm": 0.004541852977126837,
      "learning_rate": 0.2976867116657182,
      "loss": 0.1778,
      "num_input_tokens_seen": 627120,
      "step": 2240
    },
    {
      "epoch": 24.944444444444443,
      "grad_norm": 0.0037061835173517466,
      "learning_rate": 0.2976763951242269,
      "loss": 0.169,
      "num_input_tokens_seen": 628528,
      "step": 2245
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.004360519349575043,
      "learning_rate": 0.29766605580917965,
      "loss": 0.1803,
      "num_input_tokens_seen": 630000,
      "step": 2250
    },
    {
      "epoch": 25.055555555555557,
      "grad_norm": 0.0048615229316055775,
      "learning_rate": 0.29765569372217093,
      "loss": 0.1695,
      "num_input_tokens_seen": 631408,
      "step": 2255
    },
    {
      "epoch": 25.11111111111111,
      "grad_norm": 0.004213685169816017,
      "learning_rate": 0.2976453088647987,
      "loss": 0.1764,
      "num_input_tokens_seen": 632800,
      "step": 2260
    },
    {
      "epoch": 25.166666666666668,
      "grad_norm": 0.006403025239706039,
      "learning_rate": 0.2976349012386644,
      "loss": 0.1644,
      "num_input_tokens_seen": 634240,
      "step": 2265
    },
    {
      "epoch": 25.22222222222222,
      "grad_norm": 0.004406776744872332,
      "learning_rate": 0.29762447084537297,
      "loss": 0.1647,
      "num_input_tokens_seen": 635632,
      "step": 2270
    },
    {
      "epoch": 25.27777777777778,
      "grad_norm": 0.011858637444674969,
      "learning_rate": 0.29761401768653306,
      "loss": 0.1512,
      "num_input_tokens_seen": 637008,
      "step": 2275
    },
    {
      "epoch": 25.333333333333332,
      "grad_norm": 0.006876767612993717,
      "learning_rate": 0.29760354176375653,
      "loss": 0.1967,
      "num_input_tokens_seen": 638384,
      "step": 2280
    },
    {
      "epoch": 25.38888888888889,
      "grad_norm": 0.005625031888484955,
      "learning_rate": 0.29759304307865897,
      "loss": 0.1688,
      "num_input_tokens_seen": 639808,
      "step": 2285
    },
    {
      "epoch": 25.444444444444443,
      "grad_norm": 0.006492828018963337,
      "learning_rate": 0.2975825216328594,
      "loss": 0.1477,
      "num_input_tokens_seen": 641232,
      "step": 2290
    },
    {
      "epoch": 25.5,
      "grad_norm": 0.004590787924826145,
      "learning_rate": 0.2975719774279804,
      "loss": 0.2062,
      "num_input_tokens_seen": 642608,
      "step": 2295
    },
    {
      "epoch": 25.555555555555557,
      "grad_norm": 0.006149137392640114,
      "learning_rate": 0.29756141046564794,
      "loss": 0.1867,
      "num_input_tokens_seen": 644032,
      "step": 2300
    },
    {
      "epoch": 25.61111111111111,
      "grad_norm": 0.0027989353984594345,
      "learning_rate": 0.2975508207474916,
      "loss": 0.1729,
      "num_input_tokens_seen": 645440,
      "step": 2305
    },
    {
      "epoch": 25.666666666666668,
      "grad_norm": 0.005116558633744717,
      "learning_rate": 0.2975402082751445,
      "loss": 0.1719,
      "num_input_tokens_seen": 646816,
      "step": 2310
    },
    {
      "epoch": 25.72222222222222,
      "grad_norm": 0.0037031627725809813,
      "learning_rate": 0.29752957305024313,
      "loss": 0.1826,
      "num_input_tokens_seen": 648240,
      "step": 2315
    },
    {
      "epoch": 25.77777777777778,
      "grad_norm": 0.002485636156052351,
      "learning_rate": 0.2975189150744277,
      "loss": 0.1716,
      "num_input_tokens_seen": 649632,
      "step": 2320
    },
    {
      "epoch": 25.833333333333332,
      "grad_norm": 0.0028013659175485373,
      "learning_rate": 0.29750823434934165,
      "loss": 0.1673,
      "num_input_tokens_seen": 651040,
      "step": 2325
    },
    {
      "epoch": 25.88888888888889,
      "grad_norm": 0.004759748466312885,
      "learning_rate": 0.29749753087663217,
      "loss": 0.1831,
      "num_input_tokens_seen": 652432,
      "step": 2330
    },
    {
      "epoch": 25.944444444444443,
      "grad_norm": 0.003025615122169256,
      "learning_rate": 0.29748680465794985,
      "loss": 0.1589,
      "num_input_tokens_seen": 653808,
      "step": 2335
    },
    {
      "epoch": 26.0,
      "grad_norm": 0.003075771499425173,
      "learning_rate": 0.29747605569494884,
      "loss": 0.1795,
      "num_input_tokens_seen": 655200,
      "step": 2340
    },
    {
      "epoch": 26.055555555555557,
      "grad_norm": 0.003401621477678418,
      "learning_rate": 0.29746528398928673,
      "loss": 0.1695,
      "num_input_tokens_seen": 656624,
      "step": 2345
    },
    {
      "epoch": 26.11111111111111,
      "grad_norm": 0.0031574696768075228,
      "learning_rate": 0.2974544895426247,
      "loss": 0.1709,
      "num_input_tokens_seen": 658048,
      "step": 2350
    },
    {
      "epoch": 26.166666666666668,
      "grad_norm": 0.004537466447800398,
      "learning_rate": 0.29744367235662733,
      "loss": 0.175,
      "num_input_tokens_seen": 659456,
      "step": 2355
    },
    {
      "epoch": 26.22222222222222,
      "grad_norm": 0.005004187114536762,
      "learning_rate": 0.29743283243296276,
      "loss": 0.1738,
      "num_input_tokens_seen": 660864,
      "step": 2360
    },
    {
      "epoch": 26.27777777777778,
      "grad_norm": 0.003110629739239812,
      "learning_rate": 0.29742196977330276,
      "loss": 0.17,
      "num_input_tokens_seen": 662224,
      "step": 2365
    },
    {
      "epoch": 26.333333333333332,
      "grad_norm": 0.004632778000086546,
      "learning_rate": 0.2974110843793223,
      "loss": 0.168,
      "num_input_tokens_seen": 663680,
      "step": 2370
    },
    {
      "epoch": 26.38888888888889,
      "grad_norm": 0.006792825181037188,
      "learning_rate": 0.2974001762527002,
      "loss": 0.177,
      "num_input_tokens_seen": 665104,
      "step": 2375
    },
    {
      "epoch": 26.444444444444443,
      "grad_norm": 0.0032938190270215273,
      "learning_rate": 0.2973892453951186,
      "loss": 0.1729,
      "num_input_tokens_seen": 666496,
      "step": 2380
    },
    {
      "epoch": 26.5,
      "grad_norm": 0.003718575229868293,
      "learning_rate": 0.2973782918082631,
      "loss": 0.165,
      "num_input_tokens_seen": 667904,
      "step": 2385
    },
    {
      "epoch": 26.555555555555557,
      "grad_norm": 0.0050234864465892315,
      "learning_rate": 0.29736731549382295,
      "loss": 0.1805,
      "num_input_tokens_seen": 669280,
      "step": 2390
    },
    {
      "epoch": 26.61111111111111,
      "grad_norm": 0.004653002135455608,
      "learning_rate": 0.2973563164534908,
      "loss": 0.1796,
      "num_input_tokens_seen": 670720,
      "step": 2395
    },
    {
      "epoch": 26.666666666666668,
      "grad_norm": 0.006743906997144222,
      "learning_rate": 0.29734529468896287,
      "loss": 0.177,
      "num_input_tokens_seen": 672080,
      "step": 2400
    },
    {
      "epoch": 26.666666666666668,
      "eval_loss": 0.1764102727174759,
      "eval_runtime": 1.1861,
      "eval_samples_per_second": 33.723,
      "eval_steps_per_second": 16.861,
      "num_input_tokens_seen": 672080,
      "step": 2400
    },
    {
      "epoch": 26.72222222222222,
      "grad_norm": 0.005226130597293377,
      "learning_rate": 0.2973342502019388,
      "loss": 0.169,
      "num_input_tokens_seen": 673440,
      "step": 2405
    },
    {
      "epoch": 26.77777777777778,
      "grad_norm": 0.008853388950228691,
      "learning_rate": 0.2973231829941219,
      "loss": 0.1634,
      "num_input_tokens_seen": 674816,
      "step": 2410
    },
    {
      "epoch": 26.833333333333332,
      "grad_norm": 0.009519246406853199,
      "learning_rate": 0.2973120930672188,
      "loss": 0.1671,
      "num_input_tokens_seen": 676176,
      "step": 2415
    },
    {
      "epoch": 26.88888888888889,
      "grad_norm": 0.01616480201482773,
      "learning_rate": 0.2973009804229397,
      "loss": 0.1719,
      "num_input_tokens_seen": 677552,
      "step": 2420
    },
    {
      "epoch": 26.944444444444443,
      "grad_norm": 0.007620757445693016,
      "learning_rate": 0.29728984506299827,
      "loss": 0.1714,
      "num_input_tokens_seen": 678960,
      "step": 2425
    },
    {
      "epoch": 27.0,
      "grad_norm": 0.011772445403039455,
      "learning_rate": 0.2972786869891118,
      "loss": 0.1732,
      "num_input_tokens_seen": 680432,
      "step": 2430
    },
    {
      "epoch": 27.055555555555557,
      "grad_norm": 0.005076311528682709,
      "learning_rate": 0.29726750620300096,
      "loss": 0.1669,
      "num_input_tokens_seen": 681808,
      "step": 2435
    },
    {
      "epoch": 27.11111111111111,
      "grad_norm": 0.007193455006927252,
      "learning_rate": 0.29725630270639003,
      "loss": 0.1642,
      "num_input_tokens_seen": 683216,
      "step": 2440
    },
    {
      "epoch": 27.166666666666668,
      "grad_norm": 0.00685628317296505,
      "learning_rate": 0.2972450765010067,
      "loss": 0.174,
      "num_input_tokens_seen": 684608,
      "step": 2445
    },
    {
      "epoch": 27.22222222222222,
      "grad_norm": 0.005447004456073046,
      "learning_rate": 0.29723382758858213,
      "loss": 0.1692,
      "num_input_tokens_seen": 686000,
      "step": 2450
    },
    {
      "epoch": 27.27777777777778,
      "grad_norm": 0.010902178473770618,
      "learning_rate": 0.29722255597085107,
      "loss": 0.1672,
      "num_input_tokens_seen": 687408,
      "step": 2455
    },
    {
      "epoch": 27.333333333333332,
      "grad_norm": 0.010559946298599243,
      "learning_rate": 0.2972112616495518,
      "loss": 0.1629,
      "num_input_tokens_seen": 688800,
      "step": 2460
    },
    {
      "epoch": 27.38888888888889,
      "grad_norm": 0.015475851483643055,
      "learning_rate": 0.297199944626426,
      "loss": 0.1843,
      "num_input_tokens_seen": 690208,
      "step": 2465
    },
    {
      "epoch": 27.444444444444443,
      "grad_norm": 0.0067200628109276295,
      "learning_rate": 0.2971886049032189,
      "loss": 0.1579,
      "num_input_tokens_seen": 691568,
      "step": 2470
    },
    {
      "epoch": 27.5,
      "grad_norm": 0.00997807364910841,
      "learning_rate": 0.29717724248167926,
      "loss": 0.1745,
      "num_input_tokens_seen": 692976,
      "step": 2475
    },
    {
      "epoch": 27.555555555555557,
      "grad_norm": 0.006561033893376589,
      "learning_rate": 0.29716585736355927,
      "loss": 0.1564,
      "num_input_tokens_seen": 694336,
      "step": 2480
    },
    {
      "epoch": 27.61111111111111,
      "grad_norm": 0.007077552378177643,
      "learning_rate": 0.2971544495506147,
      "loss": 0.1644,
      "num_input_tokens_seen": 695744,
      "step": 2485
    },
    {
      "epoch": 27.666666666666668,
      "grad_norm": 0.007343405857682228,
      "learning_rate": 0.2971430190446048,
      "loss": 0.1832,
      "num_input_tokens_seen": 697152,
      "step": 2490
    },
    {
      "epoch": 27.72222222222222,
      "grad_norm": 0.007614629343152046,
      "learning_rate": 0.2971315658472921,
      "loss": 0.1733,
      "num_input_tokens_seen": 698592,
      "step": 2495
    },
    {
      "epoch": 27.77777777777778,
      "grad_norm": 0.008477159775793552,
      "learning_rate": 0.2971200899604431,
      "loss": 0.1738,
      "num_input_tokens_seen": 700000,
      "step": 2500
    },
    {
      "epoch": 27.833333333333332,
      "grad_norm": 0.010351340286433697,
      "learning_rate": 0.29710859138582735,
      "loss": 0.1799,
      "num_input_tokens_seen": 701424,
      "step": 2505
    },
    {
      "epoch": 27.88888888888889,
      "grad_norm": 0.014595734886825085,
      "learning_rate": 0.29709707012521813,
      "loss": 0.1672,
      "num_input_tokens_seen": 702816,
      "step": 2510
    },
    {
      "epoch": 27.944444444444443,
      "grad_norm": 0.008078561164438725,
      "learning_rate": 0.29708552618039213,
      "loss": 0.1914,
      "num_input_tokens_seen": 704208,
      "step": 2515
    },
    {
      "epoch": 28.0,
      "grad_norm": 0.005994453560560942,
      "learning_rate": 0.2970739595531296,
      "loss": 0.174,
      "num_input_tokens_seen": 705616,
      "step": 2520
    },
    {
      "epoch": 28.055555555555557,
      "grad_norm": 0.007937452755868435,
      "learning_rate": 0.2970623702452143,
      "loss": 0.172,
      "num_input_tokens_seen": 706992,
      "step": 2525
    },
    {
      "epoch": 28.11111111111111,
      "grad_norm": 0.00951820332556963,
      "learning_rate": 0.2970507582584334,
      "loss": 0.1754,
      "num_input_tokens_seen": 708448,
      "step": 2530
    },
    {
      "epoch": 28.166666666666668,
      "grad_norm": 0.006070100236684084,
      "learning_rate": 0.2970391235945776,
      "loss": 0.1692,
      "num_input_tokens_seen": 709840,
      "step": 2535
    },
    {
      "epoch": 28.22222222222222,
      "grad_norm": 0.006360044702887535,
      "learning_rate": 0.2970274662554412,
      "loss": 0.1581,
      "num_input_tokens_seen": 711216,
      "step": 2540
    },
    {
      "epoch": 28.27777777777778,
      "grad_norm": 0.007729613222181797,
      "learning_rate": 0.2970157862428218,
      "loss": 0.1727,
      "num_input_tokens_seen": 712624,
      "step": 2545
    },
    {
      "epoch": 28.333333333333332,
      "grad_norm": 0.007938053458929062,
      "learning_rate": 0.2970040835585206,
      "loss": 0.1635,
      "num_input_tokens_seen": 714048,
      "step": 2550
    },
    {
      "epoch": 28.38888888888889,
      "grad_norm": 0.00992555171251297,
      "learning_rate": 0.2969923582043424,
      "loss": 0.172,
      "num_input_tokens_seen": 715424,
      "step": 2555
    },
    {
      "epoch": 28.444444444444443,
      "grad_norm": 0.01160434354096651,
      "learning_rate": 0.2969806101820953,
      "loss": 0.1642,
      "num_input_tokens_seen": 716800,
      "step": 2560
    },
    {
      "epoch": 28.5,
      "grad_norm": 0.014462222345173359,
      "learning_rate": 0.2969688394935911,
      "loss": 0.1663,
      "num_input_tokens_seen": 718208,
      "step": 2565
    },
    {
      "epoch": 28.555555555555557,
      "grad_norm": 0.020582495257258415,
      "learning_rate": 0.2969570461406449,
      "loss": 0.1837,
      "num_input_tokens_seen": 719600,
      "step": 2570
    },
    {
      "epoch": 28.61111111111111,
      "grad_norm": 0.01100417971611023,
      "learning_rate": 0.29694523012507534,
      "loss": 0.1713,
      "num_input_tokens_seen": 720976,
      "step": 2575
    },
    {
      "epoch": 28.666666666666668,
      "grad_norm": 0.010098906233906746,
      "learning_rate": 0.2969333914487048,
      "loss": 0.16,
      "num_input_tokens_seen": 722368,
      "step": 2580
    },
    {
      "epoch": 28.72222222222222,
      "grad_norm": 0.007554182317107916,
      "learning_rate": 0.2969215301133587,
      "loss": 0.1819,
      "num_input_tokens_seen": 723808,
      "step": 2585
    },
    {
      "epoch": 28.77777777777778,
      "grad_norm": 0.006091501098126173,
      "learning_rate": 0.29690964612086634,
      "loss": 0.1796,
      "num_input_tokens_seen": 725216,
      "step": 2590
    },
    {
      "epoch": 28.833333333333332,
      "grad_norm": 0.009422751143574715,
      "learning_rate": 0.2968977394730604,
      "loss": 0.1759,
      "num_input_tokens_seen": 726624,
      "step": 2595
    },
    {
      "epoch": 28.88888888888889,
      "grad_norm": 0.00835881195962429,
      "learning_rate": 0.296885810171777,
      "loss": 0.176,
      "num_input_tokens_seen": 728000,
      "step": 2600
    },
    {
      "epoch": 28.88888888888889,
      "eval_loss": 0.18168728053569794,
      "eval_runtime": 1.1884,
      "eval_samples_per_second": 33.659,
      "eval_steps_per_second": 16.829,
      "num_input_tokens_seen": 728000,
      "step": 2600
    },
    {
      "epoch": 28.944444444444443,
      "grad_norm": 0.008467704989016056,
      "learning_rate": 0.2968738582188558,
      "loss": 0.1788,
      "num_input_tokens_seen": 729424,
      "step": 2605
    },
    {
      "epoch": 29.0,
      "grad_norm": 0.005395814776420593,
      "learning_rate": 0.2968618836161399,
      "loss": 0.1948,
      "num_input_tokens_seen": 730816,
      "step": 2610
    },
    {
      "epoch": 29.055555555555557,
      "grad_norm": 0.005059633404016495,
      "learning_rate": 0.296849886365476,
      "loss": 0.1661,
      "num_input_tokens_seen": 732208,
      "step": 2615
    },
    {
      "epoch": 29.11111111111111,
      "grad_norm": 0.004031448625028133,
      "learning_rate": 0.2968378664687142,
      "loss": 0.1735,
      "num_input_tokens_seen": 733584,
      "step": 2620
    },
    {
      "epoch": 29.166666666666668,
      "grad_norm": 0.004177070688456297,
      "learning_rate": 0.296825823927708,
      "loss": 0.1684,
      "num_input_tokens_seen": 734992,
      "step": 2625
    },
    {
      "epoch": 29.22222222222222,
      "grad_norm": 0.004584380891174078,
      "learning_rate": 0.29681375874431476,
      "loss": 0.1776,
      "num_input_tokens_seen": 736400,
      "step": 2630
    },
    {
      "epoch": 29.27777777777778,
      "grad_norm": 0.005303497891873121,
      "learning_rate": 0.29680167092039483,
      "loss": 0.1703,
      "num_input_tokens_seen": 737776,
      "step": 2635
    },
    {
      "epoch": 29.333333333333332,
      "grad_norm": 0.007617706432938576,
      "learning_rate": 0.2967895604578125,
      "loss": 0.1825,
      "num_input_tokens_seen": 739152,
      "step": 2640
    },
    {
      "epoch": 29.38888888888889,
      "grad_norm": 0.011771601624786854,
      "learning_rate": 0.2967774273584352,
      "loss": 0.1808,
      "num_input_tokens_seen": 740576,
      "step": 2645
    },
    {
      "epoch": 29.444444444444443,
      "grad_norm": 0.00923055037856102,
      "learning_rate": 0.2967652716241342,
      "loss": 0.1754,
      "num_input_tokens_seen": 741968,
      "step": 2650
    },
    {
      "epoch": 29.5,
      "grad_norm": 0.005218639504164457,
      "learning_rate": 0.29675309325678384,
      "loss": 0.1698,
      "num_input_tokens_seen": 743328,
      "step": 2655
    },
    {
      "epoch": 29.555555555555557,
      "grad_norm": 0.005681400187313557,
      "learning_rate": 0.29674089225826233,
      "loss": 0.1593,
      "num_input_tokens_seen": 744704,
      "step": 2660
    },
    {
      "epoch": 29.61111111111111,
      "grad_norm": 0.009799323976039886,
      "learning_rate": 0.29672866863045116,
      "loss": 0.1708,
      "num_input_tokens_seen": 746112,
      "step": 2665
    },
    {
      "epoch": 29.666666666666668,
      "grad_norm": 0.0069627827033400536,
      "learning_rate": 0.2967164223752354,
      "loss": 0.1762,
      "num_input_tokens_seen": 747536,
      "step": 2670
    },
    {
      "epoch": 29.72222222222222,
      "grad_norm": 0.00654571782797575,
      "learning_rate": 0.2967041534945035,
      "loss": 0.1726,
      "num_input_tokens_seen": 748944,
      "step": 2675
    },
    {
      "epoch": 29.77777777777778,
      "grad_norm": 0.0072985682636499405,
      "learning_rate": 0.2966918619901476,
      "loss": 0.1631,
      "num_input_tokens_seen": 750368,
      "step": 2680
    },
    {
      "epoch": 29.833333333333332,
      "grad_norm": 0.007033657748252153,
      "learning_rate": 0.2966795478640631,
      "loss": 0.1731,
      "num_input_tokens_seen": 751776,
      "step": 2685
    },
    {
      "epoch": 29.88888888888889,
      "grad_norm": 0.006612233817577362,
      "learning_rate": 0.29666721111814903,
      "loss": 0.1696,
      "num_input_tokens_seen": 753184,
      "step": 2690
    },
    {
      "epoch": 29.944444444444443,
      "grad_norm": 0.005315669812262058,
      "learning_rate": 0.2966548517543079,
      "loss": 0.1791,
      "num_input_tokens_seen": 754544,
      "step": 2695
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.008974014781415462,
      "learning_rate": 0.29664246977444564,
      "loss": 0.1777,
      "num_input_tokens_seen": 755952,
      "step": 2700
    },
    {
      "epoch": 30.055555555555557,
      "grad_norm": 0.006600822787731886,
      "learning_rate": 0.2966300651804717,
      "loss": 0.1539,
      "num_input_tokens_seen": 757408,
      "step": 2705
    },
    {
      "epoch": 30.11111111111111,
      "grad_norm": 0.006698332726955414,
      "learning_rate": 0.296617637974299,
      "loss": 0.1736,
      "num_input_tokens_seen": 758816,
      "step": 2710
    },
    {
      "epoch": 30.166666666666668,
      "grad_norm": 0.006079916842281818,
      "learning_rate": 0.2966051881578441,
      "loss": 0.1682,
      "num_input_tokens_seen": 760224,
      "step": 2715
    },
    {
      "epoch": 30.22222222222222,
      "grad_norm": 0.007556289900094271,
      "learning_rate": 0.29659271573302676,
      "loss": 0.1564,
      "num_input_tokens_seen": 761616,
      "step": 2720
    },
    {
      "epoch": 30.27777777777778,
      "grad_norm": 0.009176715277135372,
      "learning_rate": 0.2965802207017705,
      "loss": 0.1658,
      "num_input_tokens_seen": 762992,
      "step": 2725
    },
    {
      "epoch": 30.333333333333332,
      "grad_norm": 0.006910781376063824,
      "learning_rate": 0.2965677030660021,
      "loss": 0.1672,
      "num_input_tokens_seen": 764384,
      "step": 2730
    },
    {
      "epoch": 30.38888888888889,
      "grad_norm": 0.010234422981739044,
      "learning_rate": 0.2965551628276521,
      "loss": 0.1523,
      "num_input_tokens_seen": 765760,
      "step": 2735
    },
    {
      "epoch": 30.444444444444443,
      "grad_norm": 0.01238138135522604,
      "learning_rate": 0.29654259998865423,
      "loss": 0.1733,
      "num_input_tokens_seen": 767168,
      "step": 2740
    },
    {
      "epoch": 30.5,
      "grad_norm": 0.03081406280398369,
      "learning_rate": 0.2965300145509458,
      "loss": 0.1774,
      "num_input_tokens_seen": 768560,
      "step": 2745
    },
    {
      "epoch": 30.555555555555557,
      "grad_norm": 0.01932019181549549,
      "learning_rate": 0.2965174065164678,
      "loss": 0.1256,
      "num_input_tokens_seen": 769936,
      "step": 2750
    },
    {
      "epoch": 30.61111111111111,
      "grad_norm": 0.015147669240832329,
      "learning_rate": 0.2965047758871644,
      "loss": 0.1949,
      "num_input_tokens_seen": 771360,
      "step": 2755
    },
    {
      "epoch": 30.666666666666668,
      "grad_norm": 0.008001032285392284,
      "learning_rate": 0.2964921226649835,
      "loss": 0.1752,
      "num_input_tokens_seen": 772816,
      "step": 2760
    },
    {
      "epoch": 30.72222222222222,
      "grad_norm": 0.012106535956263542,
      "learning_rate": 0.2964794468518763,
      "loss": 0.1774,
      "num_input_tokens_seen": 774208,
      "step": 2765
    },
    {
      "epoch": 30.77777777777778,
      "grad_norm": 0.004737128969281912,
      "learning_rate": 0.2964667484497977,
      "loss": 0.1878,
      "num_input_tokens_seen": 775584,
      "step": 2770
    },
    {
      "epoch": 30.833333333333332,
      "grad_norm": 0.004061547107994556,
      "learning_rate": 0.29645402746070587,
      "loss": 0.1752,
      "num_input_tokens_seen": 776944,
      "step": 2775
    },
    {
      "epoch": 30.88888888888889,
      "grad_norm": 0.005707850679755211,
      "learning_rate": 0.2964412838865625,
      "loss": 0.191,
      "num_input_tokens_seen": 778352,
      "step": 2780
    },
    {
      "epoch": 30.944444444444443,
      "grad_norm": 0.0036923170555382967,
      "learning_rate": 0.29642851772933293,
      "loss": 0.1715,
      "num_input_tokens_seen": 779744,
      "step": 2785
    },
    {
      "epoch": 31.0,
      "grad_norm": 0.004975760821253061,
      "learning_rate": 0.29641572899098567,
      "loss": 0.1736,
      "num_input_tokens_seen": 781088,
      "step": 2790
    },
    {
      "epoch": 31.055555555555557,
      "grad_norm": 0.005147086456418037,
      "learning_rate": 0.29640291767349314,
      "loss": 0.1749,
      "num_input_tokens_seen": 782480,
      "step": 2795
    },
    {
      "epoch": 31.11111111111111,
      "grad_norm": 0.002735703717917204,
      "learning_rate": 0.2963900837788308,
      "loss": 0.1629,
      "num_input_tokens_seen": 783872,
      "step": 2800
    },
    {
      "epoch": 31.11111111111111,
      "eval_loss": 0.1786024123430252,
      "eval_runtime": 1.1915,
      "eval_samples_per_second": 33.572,
      "eval_steps_per_second": 16.786,
      "num_input_tokens_seen": 783872,
      "step": 2800
    },
    {
      "epoch": 31.166666666666668,
      "grad_norm": 0.009570744819939137,
      "learning_rate": 0.2963772273089779,
      "loss": 0.1777,
      "num_input_tokens_seen": 785264,
      "step": 2805
    },
    {
      "epoch": 31.22222222222222,
      "grad_norm": 0.00529533950611949,
      "learning_rate": 0.2963643482659171,
      "loss": 0.1824,
      "num_input_tokens_seen": 786704,
      "step": 2810
    },
    {
      "epoch": 31.27777777777778,
      "grad_norm": 0.0026384377852082253,
      "learning_rate": 0.2963514466516345,
      "loss": 0.1683,
      "num_input_tokens_seen": 788064,
      "step": 2815
    },
    {
      "epoch": 31.333333333333332,
      "grad_norm": 0.003332601860165596,
      "learning_rate": 0.2963385224681196,
      "loss": 0.1274,
      "num_input_tokens_seen": 789472,
      "step": 2820
    },
    {
      "epoch": 31.38888888888889,
      "grad_norm": 0.005020501557737589,
      "learning_rate": 0.29632557571736556,
      "loss": 0.1977,
      "num_input_tokens_seen": 790848,
      "step": 2825
    },
    {
      "epoch": 31.444444444444443,
      "grad_norm": 0.0028292411006987095,
      "learning_rate": 0.2963126064013689,
      "loss": 0.2233,
      "num_input_tokens_seen": 792192,
      "step": 2830
    },
    {
      "epoch": 31.5,
      "grad_norm": 0.003246239386498928,
      "learning_rate": 0.29629961452212966,
      "loss": 0.1846,
      "num_input_tokens_seen": 793648,
      "step": 2835
    },
    {
      "epoch": 31.555555555555557,
      "grad_norm": 0.004780214745551348,
      "learning_rate": 0.2962866000816513,
      "loss": 0.168,
      "num_input_tokens_seen": 795056,
      "step": 2840
    },
    {
      "epoch": 31.61111111111111,
      "grad_norm": 0.0053945984691381454,
      "learning_rate": 0.2962735630819409,
      "loss": 0.1956,
      "num_input_tokens_seen": 796480,
      "step": 2845
    },
    {
      "epoch": 31.666666666666668,
      "grad_norm": 0.00444582337513566,
      "learning_rate": 0.2962605035250089,
      "loss": 0.2067,
      "num_input_tokens_seen": 797888,
      "step": 2850
    },
    {
      "epoch": 31.72222222222222,
      "grad_norm": 0.00334547134116292,
      "learning_rate": 0.29624742141286914,
      "loss": 0.1748,
      "num_input_tokens_seen": 799328,
      "step": 2855
    },
    {
      "epoch": 31.77777777777778,
      "grad_norm": 0.006178698502480984,
      "learning_rate": 0.29623431674753925,
      "loss": 0.1782,
      "num_input_tokens_seen": 800752,
      "step": 2860
    },
    {
      "epoch": 31.833333333333332,
      "grad_norm": 0.004670277237892151,
      "learning_rate": 0.29622118953103993,
      "loss": 0.1635,
      "num_input_tokens_seen": 802144,
      "step": 2865
    },
    {
      "epoch": 31.88888888888889,
      "grad_norm": 0.005782892927527428,
      "learning_rate": 0.2962080397653957,
      "loss": 0.1762,
      "num_input_tokens_seen": 803504,
      "step": 2870
    },
    {
      "epoch": 31.944444444444443,
      "grad_norm": 0.0027819976676255465,
      "learning_rate": 0.29619486745263435,
      "loss": 0.1813,
      "num_input_tokens_seen": 804944,
      "step": 2875
    },
    {
      "epoch": 32.0,
      "grad_norm": 0.002426605671644211,
      "learning_rate": 0.2961816725947873,
      "loss": 0.17,
      "num_input_tokens_seen": 806352,
      "step": 2880
    },
    {
      "epoch": 32.05555555555556,
      "grad_norm": 0.001925749471411109,
      "learning_rate": 0.29616845519388924,
      "loss": 0.165,
      "num_input_tokens_seen": 807760,
      "step": 2885
    },
    {
      "epoch": 32.111111111111114,
      "grad_norm": 0.0037339390255510807,
      "learning_rate": 0.2961552152519785,
      "loss": 0.1611,
      "num_input_tokens_seen": 809184,
      "step": 2890
    },
    {
      "epoch": 32.166666666666664,
      "grad_norm": 0.004915200173854828,
      "learning_rate": 0.29614195277109695,
      "loss": 0.1641,
      "num_input_tokens_seen": 810576,
      "step": 2895
    },
    {
      "epoch": 32.22222222222222,
      "grad_norm": 0.005038919392973185,
      "learning_rate": 0.2961286677532897,
      "loss": 0.1581,
      "num_input_tokens_seen": 812000,
      "step": 2900
    },
    {
      "epoch": 32.27777777777778,
      "grad_norm": 0.0064183128997683525,
      "learning_rate": 0.2961153602006055,
      "loss": 0.1758,
      "num_input_tokens_seen": 813392,
      "step": 2905
    },
    {
      "epoch": 32.333333333333336,
      "grad_norm": 0.006566015537828207,
      "learning_rate": 0.29610203011509656,
      "loss": 0.176,
      "num_input_tokens_seen": 814800,
      "step": 2910
    },
    {
      "epoch": 32.388888888888886,
      "grad_norm": 0.00741724343970418,
      "learning_rate": 0.29608867749881856,
      "loss": 0.1725,
      "num_input_tokens_seen": 816176,
      "step": 2915
    },
    {
      "epoch": 32.44444444444444,
      "grad_norm": 0.011484237387776375,
      "learning_rate": 0.29607530235383067,
      "loss": 0.1711,
      "num_input_tokens_seen": 817584,
      "step": 2920
    },
    {
      "epoch": 32.5,
      "grad_norm": 0.004472308326512575,
      "learning_rate": 0.2960619046821954,
      "loss": 0.1577,
      "num_input_tokens_seen": 818944,
      "step": 2925
    },
    {
      "epoch": 32.55555555555556,
      "grad_norm": 0.004106978885829449,
      "learning_rate": 0.2960484844859789,
      "loss": 0.1715,
      "num_input_tokens_seen": 820336,
      "step": 2930
    },
    {
      "epoch": 32.611111111111114,
      "grad_norm": 0.006625488866120577,
      "learning_rate": 0.29603504176725076,
      "loss": 0.1676,
      "num_input_tokens_seen": 821728,
      "step": 2935
    },
    {
      "epoch": 32.666666666666664,
      "grad_norm": 0.006466888356953859,
      "learning_rate": 0.296021576528084,
      "loss": 0.1774,
      "num_input_tokens_seen": 823136,
      "step": 2940
    },
    {
      "epoch": 32.72222222222222,
      "grad_norm": 0.003972261678427458,
      "learning_rate": 0.29600808877055507,
      "loss": 0.161,
      "num_input_tokens_seen": 824528,
      "step": 2945
    },
    {
      "epoch": 32.77777777777778,
      "grad_norm": 0.006044627632945776,
      "learning_rate": 0.29599457849674404,
      "loss": 0.1586,
      "num_input_tokens_seen": 825984,
      "step": 2950
    },
    {
      "epoch": 32.833333333333336,
      "grad_norm": 0.004930890165269375,
      "learning_rate": 0.2959810457087343,
      "loss": 0.163,
      "num_input_tokens_seen": 827360,
      "step": 2955
    },
    {
      "epoch": 32.888888888888886,
      "grad_norm": 0.0073300194926559925,
      "learning_rate": 0.2959674904086128,
      "loss": 0.1562,
      "num_input_tokens_seen": 828752,
      "step": 2960
    },
    {
      "epoch": 32.94444444444444,
      "grad_norm": 0.00852897297590971,
      "learning_rate": 0.2959539125984699,
      "loss": 0.18,
      "num_input_tokens_seen": 830160,
      "step": 2965
    },
    {
      "epoch": 33.0,
      "grad_norm": 0.008056346327066422,
      "learning_rate": 0.2959403122803996,
      "loss": 0.1545,
      "num_input_tokens_seen": 831520,
      "step": 2970
    },
    {
      "epoch": 33.05555555555556,
      "grad_norm": 0.01378944143652916,
      "learning_rate": 0.2959266894564991,
      "loss": 0.1512,
      "num_input_tokens_seen": 832880,
      "step": 2975
    },
    {
      "epoch": 33.111111111111114,
      "grad_norm": 0.007373968604952097,
      "learning_rate": 0.2959130441288692,
      "loss": 0.1492,
      "num_input_tokens_seen": 834240,
      "step": 2980
    },
    {
      "epoch": 33.166666666666664,
      "grad_norm": 0.017709536477923393,
      "learning_rate": 0.2958993762996143,
      "loss": 0.1626,
      "num_input_tokens_seen": 835616,
      "step": 2985
    },
    {
      "epoch": 33.22222222222222,
      "grad_norm": 0.008547809906303883,
      "learning_rate": 0.2958856859708421,
      "loss": 0.1623,
      "num_input_tokens_seen": 837024,
      "step": 2990
    },
    {
      "epoch": 33.27777777777778,
      "grad_norm": 0.008116820827126503,
      "learning_rate": 0.2958719731446638,
      "loss": 0.1471,
      "num_input_tokens_seen": 838416,
      "step": 2995
    },
    {
      "epoch": 33.333333333333336,
      "grad_norm": 0.010031360201537609,
      "learning_rate": 0.29585823782319404,
      "loss": 0.1461,
      "num_input_tokens_seen": 839808,
      "step": 3000
    },
    {
      "epoch": 33.333333333333336,
      "eval_loss": 0.1880679875612259,
      "eval_runtime": 1.1833,
      "eval_samples_per_second": 33.804,
      "eval_steps_per_second": 16.902,
      "num_input_tokens_seen": 839808,
      "step": 3000
    },
    {
      "epoch": 33.388888888888886,
      "grad_norm": 0.007179555017501116,
      "learning_rate": 0.2958444800085511,
      "loss": 0.1936,
      "num_input_tokens_seen": 841200,
      "step": 3005
    },
    {
      "epoch": 33.44444444444444,
      "grad_norm": 0.009627573192119598,
      "learning_rate": 0.2958306997028565,
      "loss": 0.18,
      "num_input_tokens_seen": 842560,
      "step": 3010
    },
    {
      "epoch": 33.5,
      "grad_norm": 0.008277557790279388,
      "learning_rate": 0.2958168969082354,
      "loss": 0.1781,
      "num_input_tokens_seen": 843984,
      "step": 3015
    },
    {
      "epoch": 33.55555555555556,
      "grad_norm": 0.009113146923482418,
      "learning_rate": 0.2958030716268164,
      "loss": 0.1531,
      "num_input_tokens_seen": 845392,
      "step": 3020
    },
    {
      "epoch": 33.611111111111114,
      "grad_norm": 0.008612486533820629,
      "learning_rate": 0.2957892238607314,
      "loss": 0.1927,
      "num_input_tokens_seen": 846832,
      "step": 3025
    },
    {
      "epoch": 33.666666666666664,
      "grad_norm": 0.007704026531428099,
      "learning_rate": 0.2957753536121161,
      "loss": 0.1561,
      "num_input_tokens_seen": 848224,
      "step": 3030
    },
    {
      "epoch": 33.72222222222222,
      "grad_norm": 0.014744067564606667,
      "learning_rate": 0.29576146088310923,
      "loss": 0.1852,
      "num_input_tokens_seen": 849616,
      "step": 3035
    },
    {
      "epoch": 33.77777777777778,
      "grad_norm": 0.007031816989183426,
      "learning_rate": 0.2957475456758533,
      "loss": 0.1682,
      "num_input_tokens_seen": 851040,
      "step": 3040
    },
    {
      "epoch": 33.833333333333336,
      "grad_norm": 0.010060785338282585,
      "learning_rate": 0.2957336079924944,
      "loss": 0.1669,
      "num_input_tokens_seen": 852480,
      "step": 3045
    },
    {
      "epoch": 33.888888888888886,
      "grad_norm": 0.012074586935341358,
      "learning_rate": 0.2957196478351816,
      "loss": 0.1812,
      "num_input_tokens_seen": 853872,
      "step": 3050
    },
    {
      "epoch": 33.94444444444444,
      "grad_norm": 0.005645620170980692,
      "learning_rate": 0.295705665206068,
      "loss": 0.1604,
      "num_input_tokens_seen": 855280,
      "step": 3055
    },
    {
      "epoch": 34.0,
      "grad_norm": 0.007819549180567265,
      "learning_rate": 0.2956916601073097,
      "loss": 0.1712,
      "num_input_tokens_seen": 856688,
      "step": 3060
    },
    {
      "epoch": 34.05555555555556,
      "grad_norm": 0.007146310992538929,
      "learning_rate": 0.29567763254106655,
      "loss": 0.1636,
      "num_input_tokens_seen": 858128,
      "step": 3065
    },
    {
      "epoch": 34.111111111111114,
      "grad_norm": 0.007513787131756544,
      "learning_rate": 0.29566358250950175,
      "loss": 0.1597,
      "num_input_tokens_seen": 859520,
      "step": 3070
    },
    {
      "epoch": 34.166666666666664,
      "grad_norm": 0.005892554298043251,
      "learning_rate": 0.295649510014782,
      "loss": 0.1535,
      "num_input_tokens_seen": 860928,
      "step": 3075
    },
    {
      "epoch": 34.22222222222222,
      "grad_norm": 0.008413909003138542,
      "learning_rate": 0.2956354150590775,
      "loss": 0.1583,
      "num_input_tokens_seen": 862320,
      "step": 3080
    },
    {
      "epoch": 34.27777777777778,
      "grad_norm": 0.005636701360344887,
      "learning_rate": 0.2956212976445618,
      "loss": 0.1472,
      "num_input_tokens_seen": 863712,
      "step": 3085
    },
    {
      "epoch": 34.333333333333336,
      "grad_norm": 0.007368806749582291,
      "learning_rate": 0.295607157773412,
      "loss": 0.1568,
      "num_input_tokens_seen": 865104,
      "step": 3090
    },
    {
      "epoch": 34.388888888888886,
      "grad_norm": 0.010633757337927818,
      "learning_rate": 0.2955929954478087,
      "loss": 0.1671,
      "num_input_tokens_seen": 866464,
      "step": 3095
    },
    {
      "epoch": 34.44444444444444,
      "grad_norm": 0.010701186023652554,
      "learning_rate": 0.29557881066993585,
      "loss": 0.1457,
      "num_input_tokens_seen": 867856,
      "step": 3100
    },
    {
      "epoch": 34.5,
      "grad_norm": 0.017947372049093246,
      "learning_rate": 0.29556460344198093,
      "loss": 0.1559,
      "num_input_tokens_seen": 869216,
      "step": 3105
    },
    {
      "epoch": 34.55555555555556,
      "grad_norm": 0.014955323189496994,
      "learning_rate": 0.29555037376613486,
      "loss": 0.1459,
      "num_input_tokens_seen": 870656,
      "step": 3110
    },
    {
      "epoch": 34.611111111111114,
      "grad_norm": 0.014664866030216217,
      "learning_rate": 0.29553612164459203,
      "loss": 0.1601,
      "num_input_tokens_seen": 872032,
      "step": 3115
    },
    {
      "epoch": 34.666666666666664,
      "grad_norm": 0.011490235105156898,
      "learning_rate": 0.29552184707955037,
      "loss": 0.1892,
      "num_input_tokens_seen": 873440,
      "step": 3120
    },
    {
      "epoch": 34.72222222222222,
      "grad_norm": 0.007325805723667145,
      "learning_rate": 0.29550755007321117,
      "loss": 0.1841,
      "num_input_tokens_seen": 874864,
      "step": 3125
    },
    {
      "epoch": 34.77777777777778,
      "grad_norm": 0.006760095711797476,
      "learning_rate": 0.29549323062777916,
      "loss": 0.1652,
      "num_input_tokens_seen": 876288,
      "step": 3130
    },
    {
      "epoch": 34.833333333333336,
      "grad_norm": 0.006380920298397541,
      "learning_rate": 0.29547888874546263,
      "loss": 0.1867,
      "num_input_tokens_seen": 877744,
      "step": 3135
    },
    {
      "epoch": 34.888888888888886,
      "grad_norm": 0.006363583263009787,
      "learning_rate": 0.2954645244284732,
      "loss": 0.1735,
      "num_input_tokens_seen": 879152,
      "step": 3140
    },
    {
      "epoch": 34.94444444444444,
      "grad_norm": 0.006600761786103249,
      "learning_rate": 0.2954501376790261,
      "loss": 0.1663,
      "num_input_tokens_seen": 880544,
      "step": 3145
    },
    {
      "epoch": 35.0,
      "grad_norm": 0.008626434952020645,
      "learning_rate": 0.29543572849933997,
      "loss": 0.1707,
      "num_input_tokens_seen": 881984,
      "step": 3150
    },
    {
      "epoch": 35.05555555555556,
      "grad_norm": 0.015642235055565834,
      "learning_rate": 0.2954212968916368,
      "loss": 0.1566,
      "num_input_tokens_seen": 883392,
      "step": 3155
    },
    {
      "epoch": 35.111111111111114,
      "grad_norm": 0.01712111197412014,
      "learning_rate": 0.29540684285814217,
      "loss": 0.1509,
      "num_input_tokens_seen": 884848,
      "step": 3160
    },
    {
      "epoch": 35.166666666666664,
      "grad_norm": 0.015242992900311947,
      "learning_rate": 0.2953923664010851,
      "loss": 0.1398,
      "num_input_tokens_seen": 886272,
      "step": 3165
    },
    {
      "epoch": 35.22222222222222,
      "grad_norm": 0.018422581255435944,
      "learning_rate": 0.295377867522698,
      "loss": 0.1666,
      "num_input_tokens_seen": 887680,
      "step": 3170
    },
    {
      "epoch": 35.27777777777778,
      "grad_norm": 0.009930006228387356,
      "learning_rate": 0.2953633462252168,
      "loss": 0.1464,
      "num_input_tokens_seen": 889056,
      "step": 3175
    },
    {
      "epoch": 35.333333333333336,
      "grad_norm": 0.010793906636536121,
      "learning_rate": 0.2953488025108809,
      "loss": 0.1536,
      "num_input_tokens_seen": 890400,
      "step": 3180
    },
    {
      "epoch": 35.388888888888886,
      "grad_norm": 0.009103021584451199,
      "learning_rate": 0.295334236381933,
      "loss": 0.1288,
      "num_input_tokens_seen": 891792,
      "step": 3185
    },
    {
      "epoch": 35.44444444444444,
      "grad_norm": 0.009383324533700943,
      "learning_rate": 0.29531964784061954,
      "loss": 0.195,
      "num_input_tokens_seen": 893248,
      "step": 3190
    },
    {
      "epoch": 35.5,
      "grad_norm": 0.007461462169885635,
      "learning_rate": 0.2953050368891902,
      "loss": 0.151,
      "num_input_tokens_seen": 894672,
      "step": 3195
    },
    {
      "epoch": 35.55555555555556,
      "grad_norm": 0.009141882881522179,
      "learning_rate": 0.29529040352989805,
      "loss": 0.1762,
      "num_input_tokens_seen": 896064,
      "step": 3200
    },
    {
      "epoch": 35.55555555555556,
      "eval_loss": 0.19121959805488586,
      "eval_runtime": 1.1881,
      "eval_samples_per_second": 33.666,
      "eval_steps_per_second": 16.833,
      "num_input_tokens_seen": 896064,
      "step": 3200
    },
    {
      "epoch": 35.611111111111114,
      "grad_norm": 0.008887710981070995,
      "learning_rate": 0.29527574776499993,
      "loss": 0.169,
      "num_input_tokens_seen": 897456,
      "step": 3205
    },
    {
      "epoch": 35.666666666666664,
      "grad_norm": 0.01379062607884407,
      "learning_rate": 0.2952610695967558,
      "loss": 0.145,
      "num_input_tokens_seen": 898832,
      "step": 3210
    },
    {
      "epoch": 35.72222222222222,
      "grad_norm": 0.010952775366604328,
      "learning_rate": 0.29524636902742935,
      "loss": 0.144,
      "num_input_tokens_seen": 900192,
      "step": 3215
    },
    {
      "epoch": 35.77777777777778,
      "grad_norm": 0.016155943274497986,
      "learning_rate": 0.2952316460592875,
      "loss": 0.1859,
      "num_input_tokens_seen": 901536,
      "step": 3220
    },
    {
      "epoch": 35.833333333333336,
      "grad_norm": 0.017939141020178795,
      "learning_rate": 0.29521690069460066,
      "loss": 0.1619,
      "num_input_tokens_seen": 902960,
      "step": 3225
    },
    {
      "epoch": 35.888888888888886,
      "grad_norm": 0.01045024674385786,
      "learning_rate": 0.29520213293564285,
      "loss": 0.1831,
      "num_input_tokens_seen": 904384,
      "step": 3230
    },
    {
      "epoch": 35.94444444444444,
      "grad_norm": 0.0073639340698719025,
      "learning_rate": 0.29518734278469144,
      "loss": 0.1775,
      "num_input_tokens_seen": 905792,
      "step": 3235
    },
    {
      "epoch": 36.0,
      "grad_norm": 0.006037806160748005,
      "learning_rate": 0.29517253024402723,
      "loss": 0.177,
      "num_input_tokens_seen": 907168,
      "step": 3240
    },
    {
      "epoch": 36.05555555555556,
      "grad_norm": 0.008367171511054039,
      "learning_rate": 0.2951576953159345,
      "loss": 0.1747,
      "num_input_tokens_seen": 908544,
      "step": 3245
    },
    {
      "epoch": 36.111111111111114,
      "grad_norm": 0.010530834086239338,
      "learning_rate": 0.29514283800270097,
      "loss": 0.1721,
      "num_input_tokens_seen": 909952,
      "step": 3250
    },
    {
      "epoch": 36.166666666666664,
      "grad_norm": 0.006563905160874128,
      "learning_rate": 0.2951279583066179,
      "loss": 0.1468,
      "num_input_tokens_seen": 911328,
      "step": 3255
    },
    {
      "epoch": 36.22222222222222,
      "grad_norm": 0.005530665162950754,
      "learning_rate": 0.2951130562299798,
      "loss": 0.1382,
      "num_input_tokens_seen": 912704,
      "step": 3260
    },
    {
      "epoch": 36.27777777777778,
      "grad_norm": 0.006732076406478882,
      "learning_rate": 0.29509813177508487,
      "loss": 0.1695,
      "num_input_tokens_seen": 914128,
      "step": 3265
    },
    {
      "epoch": 36.333333333333336,
      "grad_norm": 0.005024148151278496,
      "learning_rate": 0.2950831849442346,
      "loss": 0.1869,
      "num_input_tokens_seen": 915536,
      "step": 3270
    },
    {
      "epoch": 36.388888888888886,
      "grad_norm": 0.00828483048826456,
      "learning_rate": 0.2950682157397339,
      "loss": 0.164,
      "num_input_tokens_seen": 916944,
      "step": 3275
    },
    {
      "epoch": 36.44444444444444,
      "grad_norm": 0.01851535774767399,
      "learning_rate": 0.2950532241638914,
      "loss": 0.1716,
      "num_input_tokens_seen": 918368,
      "step": 3280
    },
    {
      "epoch": 36.5,
      "grad_norm": 0.009570122696459293,
      "learning_rate": 0.2950382102190188,
      "loss": 0.1618,
      "num_input_tokens_seen": 919792,
      "step": 3285
    },
    {
      "epoch": 36.55555555555556,
      "grad_norm": 0.005393456667661667,
      "learning_rate": 0.2950231739074316,
      "loss": 0.1665,
      "num_input_tokens_seen": 921200,
      "step": 3290
    },
    {
      "epoch": 36.611111111111114,
      "grad_norm": 0.008858796209096909,
      "learning_rate": 0.29500811523144843,
      "loss": 0.1762,
      "num_input_tokens_seen": 922592,
      "step": 3295
    },
    {
      "epoch": 36.666666666666664,
      "grad_norm": 0.007424605544656515,
      "learning_rate": 0.2949930341933917,
      "loss": 0.1657,
      "num_input_tokens_seen": 924000,
      "step": 3300
    },
    {
      "epoch": 36.72222222222222,
      "grad_norm": 0.006688026245683432,
      "learning_rate": 0.29497793079558693,
      "loss": 0.166,
      "num_input_tokens_seen": 925376,
      "step": 3305
    },
    {
      "epoch": 36.77777777777778,
      "grad_norm": 0.008946339599788189,
      "learning_rate": 0.2949628050403633,
      "loss": 0.1525,
      "num_input_tokens_seen": 926816,
      "step": 3310
    },
    {
      "epoch": 36.833333333333336,
      "grad_norm": 0.010125641711056232,
      "learning_rate": 0.2949476569300535,
      "loss": 0.1694,
      "num_input_tokens_seen": 928176,
      "step": 3315
    },
    {
      "epoch": 36.888888888888886,
      "grad_norm": 0.007320010103285313,
      "learning_rate": 0.29493248646699344,
      "loss": 0.1533,
      "num_input_tokens_seen": 929568,
      "step": 3320
    },
    {
      "epoch": 36.94444444444444,
      "grad_norm": 0.01254670787602663,
      "learning_rate": 0.29491729365352265,
      "loss": 0.1552,
      "num_input_tokens_seen": 930992,
      "step": 3325
    },
    {
      "epoch": 37.0,
      "grad_norm": 0.01182131003588438,
      "learning_rate": 0.29490207849198397,
      "loss": 0.1312,
      "num_input_tokens_seen": 932384,
      "step": 3330
    },
    {
      "epoch": 37.05555555555556,
      "grad_norm": 0.008299699984490871,
      "learning_rate": 0.29488684098472384,
      "loss": 0.142,
      "num_input_tokens_seen": 933776,
      "step": 3335
    },
    {
      "epoch": 37.111111111111114,
      "grad_norm": 0.014130964875221252,
      "learning_rate": 0.2948715811340921,
      "loss": 0.1224,
      "num_input_tokens_seen": 935184,
      "step": 3340
    },
    {
      "epoch": 37.166666666666664,
      "grad_norm": 0.018782034516334534,
      "learning_rate": 0.294856298942442,
      "loss": 0.1106,
      "num_input_tokens_seen": 936576,
      "step": 3345
    },
    {
      "epoch": 37.22222222222222,
      "grad_norm": 0.03225155174732208,
      "learning_rate": 0.2948409944121302,
      "loss": 0.1295,
      "num_input_tokens_seen": 938032,
      "step": 3350
    },
    {
      "epoch": 37.27777777777778,
      "grad_norm": 0.02146998606622219,
      "learning_rate": 0.29482566754551687,
      "loss": 0.1802,
      "num_input_tokens_seen": 939456,
      "step": 3355
    },
    {
      "epoch": 37.333333333333336,
      "grad_norm": 0.01933373510837555,
      "learning_rate": 0.2948103183449656,
      "loss": 0.1545,
      "num_input_tokens_seen": 940800,
      "step": 3360
    },
    {
      "epoch": 37.388888888888886,
      "grad_norm": 0.019534239545464516,
      "learning_rate": 0.2947949468128435,
      "loss": 0.1545,
      "num_input_tokens_seen": 942160,
      "step": 3365
    },
    {
      "epoch": 37.44444444444444,
      "grad_norm": 0.011507189832627773,
      "learning_rate": 0.2947795529515209,
      "loss": 0.1596,
      "num_input_tokens_seen": 943536,
      "step": 3370
    },
    {
      "epoch": 37.5,
      "grad_norm": 0.010750706307590008,
      "learning_rate": 0.29476413676337193,
      "loss": 0.1699,
      "num_input_tokens_seen": 944928,
      "step": 3375
    },
    {
      "epoch": 37.55555555555556,
      "grad_norm": 0.007319947704672813,
      "learning_rate": 0.2947486982507738,
      "loss": 0.1654,
      "num_input_tokens_seen": 946336,
      "step": 3380
    },
    {
      "epoch": 37.611111111111114,
      "grad_norm": 0.006967152468860149,
      "learning_rate": 0.29473323741610735,
      "loss": 0.1688,
      "num_input_tokens_seen": 947712,
      "step": 3385
    },
    {
      "epoch": 37.666666666666664,
      "grad_norm": 0.007695432752370834,
      "learning_rate": 0.2947177542617569,
      "loss": 0.1985,
      "num_input_tokens_seen": 949104,
      "step": 3390
    },
    {
      "epoch": 37.72222222222222,
      "grad_norm": 0.007392461411654949,
      "learning_rate": 0.2947022487901101,
      "loss": 0.1733,
      "num_input_tokens_seen": 950496,
      "step": 3395
    },
    {
      "epoch": 37.77777777777778,
      "grad_norm": 0.004907126072794199,
      "learning_rate": 0.2946867210035581,
      "loss": 0.1672,
      "num_input_tokens_seen": 951888,
      "step": 3400
    },
    {
      "epoch": 37.77777777777778,
      "eval_loss": 0.1762980967760086,
      "eval_runtime": 1.1792,
      "eval_samples_per_second": 33.921,
      "eval_steps_per_second": 16.96,
      "num_input_tokens_seen": 951888,
      "step": 3400
    },
    {
      "epoch": 37.833333333333336,
      "grad_norm": 0.005614597350358963,
      "learning_rate": 0.2946711709044954,
      "loss": 0.161,
      "num_input_tokens_seen": 953264,
      "step": 3405
    },
    {
      "epoch": 37.888888888888886,
      "grad_norm": 0.009413735009729862,
      "learning_rate": 0.2946555984953202,
      "loss": 0.1674,
      "num_input_tokens_seen": 954656,
      "step": 3410
    },
    {
      "epoch": 37.94444444444444,
      "grad_norm": 0.010540284216403961,
      "learning_rate": 0.2946400037784338,
      "loss": 0.1594,
      "num_input_tokens_seen": 956032,
      "step": 3415
    },
    {
      "epoch": 38.0,
      "grad_norm": 0.010625059716403484,
      "learning_rate": 0.29462438675624114,
      "loss": 0.1692,
      "num_input_tokens_seen": 957424,
      "step": 3420
    },
    {
      "epoch": 38.05555555555556,
      "grad_norm": 0.011628188192844391,
      "learning_rate": 0.2946087474311506,
      "loss": 0.1645,
      "num_input_tokens_seen": 958768,
      "step": 3425
    },
    {
      "epoch": 38.111111111111114,
      "grad_norm": 0.009606382809579372,
      "learning_rate": 0.294593085805574,
      "loss": 0.1224,
      "num_input_tokens_seen": 960192,
      "step": 3430
    },
    {
      "epoch": 38.166666666666664,
      "grad_norm": 0.01013089343905449,
      "learning_rate": 0.2945774018819264,
      "loss": 0.1505,
      "num_input_tokens_seen": 961600,
      "step": 3435
    },
    {
      "epoch": 38.22222222222222,
      "grad_norm": 0.015379806980490685,
      "learning_rate": 0.2945616956626266,
      "loss": 0.1695,
      "num_input_tokens_seen": 963024,
      "step": 3440
    },
    {
      "epoch": 38.27777777777778,
      "grad_norm": 0.010527809150516987,
      "learning_rate": 0.2945459671500966,
      "loss": 0.1706,
      "num_input_tokens_seen": 964384,
      "step": 3445
    },
    {
      "epoch": 38.333333333333336,
      "grad_norm": 0.011676009744405746,
      "learning_rate": 0.2945302163467621,
      "loss": 0.1557,
      "num_input_tokens_seen": 965760,
      "step": 3450
    },
    {
      "epoch": 38.388888888888886,
      "grad_norm": 0.008661073632538319,
      "learning_rate": 0.2945144432550519,
      "loss": 0.2201,
      "num_input_tokens_seen": 967152,
      "step": 3455
    },
    {
      "epoch": 38.44444444444444,
      "grad_norm": 0.006359363906085491,
      "learning_rate": 0.29449864787739843,
      "loss": 0.1885,
      "num_input_tokens_seen": 968528,
      "step": 3460
    },
    {
      "epoch": 38.5,
      "grad_norm": 0.006495029665529728,
      "learning_rate": 0.2944828302162376,
      "loss": 0.1641,
      "num_input_tokens_seen": 969968,
      "step": 3465
    },
    {
      "epoch": 38.55555555555556,
      "grad_norm": 0.0047569917514920235,
      "learning_rate": 0.2944669902740087,
      "loss": 0.1911,
      "num_input_tokens_seen": 971376,
      "step": 3470
    },
    {
      "epoch": 38.611111111111114,
      "grad_norm": 0.004765784367918968,
      "learning_rate": 0.2944511280531544,
      "loss": 0.1649,
      "num_input_tokens_seen": 972816,
      "step": 3475
    },
    {
      "epoch": 38.666666666666664,
      "grad_norm": 0.006673949770629406,
      "learning_rate": 0.29443524355612083,
      "loss": 0.1765,
      "num_input_tokens_seen": 974192,
      "step": 3480
    },
    {
      "epoch": 38.72222222222222,
      "grad_norm": 0.008549465797841549,
      "learning_rate": 0.29441933678535764,
      "loss": 0.1691,
      "num_input_tokens_seen": 975600,
      "step": 3485
    },
    {
      "epoch": 38.77777777777778,
      "grad_norm": 0.005346004385501146,
      "learning_rate": 0.29440340774331786,
      "loss": 0.1634,
      "num_input_tokens_seen": 976992,
      "step": 3490
    },
    {
      "epoch": 38.833333333333336,
      "grad_norm": 0.006549772806465626,
      "learning_rate": 0.2943874564324579,
      "loss": 0.1431,
      "num_input_tokens_seen": 978384,
      "step": 3495
    },
    {
      "epoch": 38.888888888888886,
      "grad_norm": 0.007635694462805986,
      "learning_rate": 0.2943714828552376,
      "loss": 0.2218,
      "num_input_tokens_seen": 979776,
      "step": 3500
    },
    {
      "epoch": 38.94444444444444,
      "grad_norm": 0.0038596990052610636,
      "learning_rate": 0.29435548701412045,
      "loss": 0.1623,
      "num_input_tokens_seen": 981200,
      "step": 3505
    },
    {
      "epoch": 39.0,
      "grad_norm": 0.005101977847516537,
      "learning_rate": 0.2943394689115731,
      "loss": 0.1652,
      "num_input_tokens_seen": 982624,
      "step": 3510
    },
    {
      "epoch": 39.05555555555556,
      "grad_norm": 0.004797002300620079,
      "learning_rate": 0.29432342855006577,
      "loss": 0.158,
      "num_input_tokens_seen": 984048,
      "step": 3515
    },
    {
      "epoch": 39.111111111111114,
      "grad_norm": 0.007027363404631615,
      "learning_rate": 0.294307365932072,
      "loss": 0.1538,
      "num_input_tokens_seen": 985472,
      "step": 3520
    },
    {
      "epoch": 39.166666666666664,
      "grad_norm": 0.0068823485635221004,
      "learning_rate": 0.294291281060069,
      "loss": 0.1693,
      "num_input_tokens_seen": 986880,
      "step": 3525
    },
    {
      "epoch": 39.22222222222222,
      "grad_norm": 0.01248107012361288,
      "learning_rate": 0.29427517393653724,
      "loss": 0.1558,
      "num_input_tokens_seen": 988320,
      "step": 3530
    },
    {
      "epoch": 39.27777777777778,
      "grad_norm": 0.008489509113132954,
      "learning_rate": 0.29425904456396046,
      "loss": 0.1256,
      "num_input_tokens_seen": 989680,
      "step": 3535
    },
    {
      "epoch": 39.333333333333336,
      "grad_norm": 0.008076280355453491,
      "learning_rate": 0.2942428929448262,
      "loss": 0.2041,
      "num_input_tokens_seen": 991136,
      "step": 3540
    },
    {
      "epoch": 39.388888888888886,
      "grad_norm": 0.010678770951926708,
      "learning_rate": 0.2942267190816252,
      "loss": 0.1458,
      "num_input_tokens_seen": 992528,
      "step": 3545
    },
    {
      "epoch": 39.44444444444444,
      "grad_norm": 0.014181979931890965,
      "learning_rate": 0.2942105229768516,
      "loss": 0.1578,
      "num_input_tokens_seen": 993920,
      "step": 3550
    },
    {
      "epoch": 39.5,
      "grad_norm": 0.016211776062846184,
      "learning_rate": 0.29419430463300306,
      "loss": 0.1513,
      "num_input_tokens_seen": 995312,
      "step": 3555
    },
    {
      "epoch": 39.55555555555556,
      "grad_norm": 0.010563892312347889,
      "learning_rate": 0.2941780640525808,
      "loss": 0.1744,
      "num_input_tokens_seen": 996656,
      "step": 3560
    },
    {
      "epoch": 39.611111111111114,
      "grad_norm": 0.012746032327413559,
      "learning_rate": 0.2941618012380891,
      "loss": 0.1753,
      "num_input_tokens_seen": 998064,
      "step": 3565
    },
    {
      "epoch": 39.666666666666664,
      "grad_norm": 0.018007032573223114,
      "learning_rate": 0.29414551619203605,
      "loss": 0.1628,
      "num_input_tokens_seen": 999504,
      "step": 3570
    },
    {
      "epoch": 39.72222222222222,
      "grad_norm": 0.009329908527433872,
      "learning_rate": 0.29412920891693295,
      "loss": 0.1664,
      "num_input_tokens_seen": 1000864,
      "step": 3575
    },
    {
      "epoch": 39.77777777777778,
      "grad_norm": 0.006969841197133064,
      "learning_rate": 0.2941128794152946,
      "loss": 0.1879,
      "num_input_tokens_seen": 1002272,
      "step": 3580
    },
    {
      "epoch": 39.833333333333336,
      "grad_norm": 0.008797816000878811,
      "learning_rate": 0.2940965276896392,
      "loss": 0.1558,
      "num_input_tokens_seen": 1003648,
      "step": 3585
    },
    {
      "epoch": 39.888888888888886,
      "grad_norm": 0.007957507856190205,
      "learning_rate": 0.2940801537424884,
      "loss": 0.161,
      "num_input_tokens_seen": 1005008,
      "step": 3590
    },
    {
      "epoch": 39.94444444444444,
      "grad_norm": 0.0065572503954172134,
      "learning_rate": 0.2940637575763673,
      "loss": 0.1747,
      "num_input_tokens_seen": 1006384,
      "step": 3595
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.006154822651296854,
      "learning_rate": 0.2940473391938043,
      "loss": 0.1666,
      "num_input_tokens_seen": 1007760,
      "step": 3600
    },
    {
      "epoch": 40.0,
      "eval_loss": 0.18249337375164032,
      "eval_runtime": 1.1876,
      "eval_samples_per_second": 33.682,
      "eval_steps_per_second": 16.841,
      "num_input_tokens_seen": 1007760,
      "step": 3600
    },
    {
      "epoch": 40.05555555555556,
      "grad_norm": 0.00842934101819992,
      "learning_rate": 0.29403089859733145,
      "loss": 0.1411,
      "num_input_tokens_seen": 1009168,
      "step": 3605
    },
    {
      "epoch": 40.111111111111114,
      "grad_norm": 0.007992678321897984,
      "learning_rate": 0.294014435789484,
      "loss": 0.1485,
      "num_input_tokens_seen": 1010576,
      "step": 3610
    },
    {
      "epoch": 40.166666666666664,
      "grad_norm": 0.009821692481637001,
      "learning_rate": 0.2939979507728007,
      "loss": 0.1504,
      "num_input_tokens_seen": 1011952,
      "step": 3615
    },
    {
      "epoch": 40.22222222222222,
      "grad_norm": 0.020951321348547935,
      "learning_rate": 0.2939814435498239,
      "loss": 0.1393,
      "num_input_tokens_seen": 1013408,
      "step": 3620
    },
    {
      "epoch": 40.27777777777778,
      "grad_norm": 0.016210751608014107,
      "learning_rate": 0.29396491412309905,
      "loss": 0.1409,
      "num_input_tokens_seen": 1014832,
      "step": 3625
    },
    {
      "epoch": 40.333333333333336,
      "grad_norm": 0.011309824883937836,
      "learning_rate": 0.2939483624951753,
      "loss": 0.1302,
      "num_input_tokens_seen": 1016256,
      "step": 3630
    },
    {
      "epoch": 40.388888888888886,
      "grad_norm": 0.023337598890066147,
      "learning_rate": 0.2939317886686051,
      "loss": 0.1642,
      "num_input_tokens_seen": 1017632,
      "step": 3635
    },
    {
      "epoch": 40.44444444444444,
      "grad_norm": 0.01002898532897234,
      "learning_rate": 0.2939151926459443,
      "loss": 0.1268,
      "num_input_tokens_seen": 1019008,
      "step": 3640
    },
    {
      "epoch": 40.5,
      "grad_norm": 0.009863869287073612,
      "learning_rate": 0.2938985744297522,
      "loss": 0.1264,
      "num_input_tokens_seen": 1020432,
      "step": 3645
    },
    {
      "epoch": 40.55555555555556,
      "grad_norm": 0.0125508364289999,
      "learning_rate": 0.29388193402259166,
      "loss": 0.1129,
      "num_input_tokens_seen": 1021776,
      "step": 3650
    },
    {
      "epoch": 40.611111111111114,
      "grad_norm": 0.012633213773369789,
      "learning_rate": 0.29386527142702873,
      "loss": 0.1737,
      "num_input_tokens_seen": 1023120,
      "step": 3655
    },
    {
      "epoch": 40.666666666666664,
      "grad_norm": 0.013900013640522957,
      "learning_rate": 0.293848586645633,
      "loss": 0.1444,
      "num_input_tokens_seen": 1024512,
      "step": 3660
    },
    {
      "epoch": 40.72222222222222,
      "grad_norm": 0.006607291288673878,
      "learning_rate": 0.2938318796809775,
      "loss": 0.1875,
      "num_input_tokens_seen": 1025920,
      "step": 3665
    },
    {
      "epoch": 40.77777777777778,
      "grad_norm": 0.006938711274415255,
      "learning_rate": 0.29381515053563867,
      "loss": 0.1675,
      "num_input_tokens_seen": 1027360,
      "step": 3670
    },
    {
      "epoch": 40.833333333333336,
      "grad_norm": 0.005630281753838062,
      "learning_rate": 0.29379839921219636,
      "loss": 0.1584,
      "num_input_tokens_seen": 1028752,
      "step": 3675
    },
    {
      "epoch": 40.888888888888886,
      "grad_norm": 0.006126451771706343,
      "learning_rate": 0.2937816257132338,
      "loss": 0.1684,
      "num_input_tokens_seen": 1030128,
      "step": 3680
    },
    {
      "epoch": 40.94444444444444,
      "grad_norm": 0.009161708876490593,
      "learning_rate": 0.2937648300413376,
      "loss": 0.1768,
      "num_input_tokens_seen": 1031584,
      "step": 3685
    },
    {
      "epoch": 41.0,
      "grad_norm": 0.008299505338072777,
      "learning_rate": 0.293748012199098,
      "loss": 0.1719,
      "num_input_tokens_seen": 1032960,
      "step": 3690
    },
    {
      "epoch": 41.05555555555556,
      "grad_norm": 0.013671575114130974,
      "learning_rate": 0.29373117218910844,
      "loss": 0.1505,
      "num_input_tokens_seen": 1034416,
      "step": 3695
    },
    {
      "epoch": 41.111111111111114,
      "grad_norm": 0.008755671791732311,
      "learning_rate": 0.2937143100139659,
      "loss": 0.1586,
      "num_input_tokens_seen": 1035824,
      "step": 3700
    },
    {
      "epoch": 41.166666666666664,
      "grad_norm": 0.01713762991130352,
      "learning_rate": 0.29369742567627083,
      "loss": 0.1755,
      "num_input_tokens_seen": 1037184,
      "step": 3705
    },
    {
      "epoch": 41.22222222222222,
      "grad_norm": 0.009950939565896988,
      "learning_rate": 0.29368051917862675,
      "loss": 0.1801,
      "num_input_tokens_seen": 1038544,
      "step": 3710
    },
    {
      "epoch": 41.27777777777778,
      "grad_norm": 0.011864854954183102,
      "learning_rate": 0.2936635905236411,
      "loss": 0.1617,
      "num_input_tokens_seen": 1039920,
      "step": 3715
    },
    {
      "epoch": 41.333333333333336,
      "grad_norm": 0.0066434722393751144,
      "learning_rate": 0.2936466397139244,
      "loss": 0.1633,
      "num_input_tokens_seen": 1041344,
      "step": 3720
    },
    {
      "epoch": 41.388888888888886,
      "grad_norm": 0.008090745657682419,
      "learning_rate": 0.2936296667520907,
      "loss": 0.1439,
      "num_input_tokens_seen": 1042704,
      "step": 3725
    },
    {
      "epoch": 41.44444444444444,
      "grad_norm": 0.012468607164919376,
      "learning_rate": 0.2936126716407574,
      "loss": 0.1374,
      "num_input_tokens_seen": 1044080,
      "step": 3730
    },
    {
      "epoch": 41.5,
      "grad_norm": 0.023784905672073364,
      "learning_rate": 0.29359565438254537,
      "loss": 0.1436,
      "num_input_tokens_seen": 1045520,
      "step": 3735
    },
    {
      "epoch": 41.55555555555556,
      "grad_norm": 0.010647406801581383,
      "learning_rate": 0.29357861498007887,
      "loss": 0.1431,
      "num_input_tokens_seen": 1046944,
      "step": 3740
    },
    {
      "epoch": 41.611111111111114,
      "grad_norm": 0.008144333958625793,
      "learning_rate": 0.29356155343598567,
      "loss": 0.1534,
      "num_input_tokens_seen": 1048336,
      "step": 3745
    },
    {
      "epoch": 41.666666666666664,
      "grad_norm": 0.011066996492445469,
      "learning_rate": 0.2935444697528968,
      "loss": 0.1871,
      "num_input_tokens_seen": 1049760,
      "step": 3750
    },
    {
      "epoch": 41.72222222222222,
      "grad_norm": 0.005996601190418005,
      "learning_rate": 0.2935273639334468,
      "loss": 0.1775,
      "num_input_tokens_seen": 1051088,
      "step": 3755
    },
    {
      "epoch": 41.77777777777778,
      "grad_norm": 0.005698866210877895,
      "learning_rate": 0.29351023598027365,
      "loss": 0.1804,
      "num_input_tokens_seen": 1052448,
      "step": 3760
    },
    {
      "epoch": 41.833333333333336,
      "grad_norm": 0.006237776484340429,
      "learning_rate": 0.2934930858960186,
      "loss": 0.1593,
      "num_input_tokens_seen": 1053840,
      "step": 3765
    },
    {
      "epoch": 41.888888888888886,
      "grad_norm": 0.006712848786264658,
      "learning_rate": 0.29347591368332643,
      "loss": 0.156,
      "num_input_tokens_seen": 1055232,
      "step": 3770
    },
    {
      "epoch": 41.94444444444444,
      "grad_norm": 0.00643483130261302,
      "learning_rate": 0.2934587193448454,
      "loss": 0.1693,
      "num_input_tokens_seen": 1056672,
      "step": 3775
    },
    {
      "epoch": 42.0,
      "grad_norm": 0.0075499252416193485,
      "learning_rate": 0.29344150288322696,
      "loss": 0.1509,
      "num_input_tokens_seen": 1058080,
      "step": 3780
    },
    {
      "epoch": 42.05555555555556,
      "grad_norm": 0.011047343723475933,
      "learning_rate": 0.2934242643011263,
      "loss": 0.1323,
      "num_input_tokens_seen": 1059440,
      "step": 3785
    },
    {
      "epoch": 42.111111111111114,
      "grad_norm": 0.01965431310236454,
      "learning_rate": 0.2934070036012016,
      "loss": 0.1406,
      "num_input_tokens_seen": 1060864,
      "step": 3790
    },
    {
      "epoch": 42.166666666666664,
      "grad_norm": 0.03578559309244156,
      "learning_rate": 0.29338972078611475,
      "loss": 0.1285,
      "num_input_tokens_seen": 1062224,
      "step": 3795
    },
    {
      "epoch": 42.22222222222222,
      "grad_norm": 0.013650728389620781,
      "learning_rate": 0.2933724158585311,
      "loss": 0.1347,
      "num_input_tokens_seen": 1063648,
      "step": 3800
    },
    {
      "epoch": 42.22222222222222,
      "eval_loss": 0.24739770591259003,
      "eval_runtime": 1.1957,
      "eval_samples_per_second": 33.453,
      "eval_steps_per_second": 16.727,
      "num_input_tokens_seen": 1063648,
      "step": 3800
    },
    {
      "epoch": 42.27777777777778,
      "grad_norm": 0.02099555917084217,
      "learning_rate": 0.29335508882111916,
      "loss": 0.1268,
      "num_input_tokens_seen": 1065024,
      "step": 3805
    },
    {
      "epoch": 42.333333333333336,
      "grad_norm": 0.008811743929982185,
      "learning_rate": 0.29333773967655097,
      "loss": 0.1643,
      "num_input_tokens_seen": 1066432,
      "step": 3810
    },
    {
      "epoch": 42.388888888888886,
      "grad_norm": 0.010887356474995613,
      "learning_rate": 0.2933203684275021,
      "loss": 0.1553,
      "num_input_tokens_seen": 1067872,
      "step": 3815
    },
    {
      "epoch": 42.44444444444444,
      "grad_norm": 0.010096041485667229,
      "learning_rate": 0.2933029750766513,
      "loss": 0.122,
      "num_input_tokens_seen": 1069264,
      "step": 3820
    },
    {
      "epoch": 42.5,
      "grad_norm": 0.014164523221552372,
      "learning_rate": 0.2932855596266809,
      "loss": 0.1556,
      "num_input_tokens_seen": 1070688,
      "step": 3825
    },
    {
      "epoch": 42.55555555555556,
      "grad_norm": 0.012026185169816017,
      "learning_rate": 0.2932681220802765,
      "loss": 0.1787,
      "num_input_tokens_seen": 1072096,
      "step": 3830
    },
    {
      "epoch": 42.611111111111114,
      "grad_norm": 0.008486979641020298,
      "learning_rate": 0.2932506624401274,
      "loss": 0.139,
      "num_input_tokens_seen": 1073456,
      "step": 3835
    },
    {
      "epoch": 42.666666666666664,
      "grad_norm": 0.00827824417501688,
      "learning_rate": 0.29323318070892584,
      "loss": 0.1392,
      "num_input_tokens_seen": 1074864,
      "step": 3840
    },
    {
      "epoch": 42.72222222222222,
      "grad_norm": 0.010546333156526089,
      "learning_rate": 0.29321567688936784,
      "loss": 0.1596,
      "num_input_tokens_seen": 1076256,
      "step": 3845
    },
    {
      "epoch": 42.77777777777778,
      "grad_norm": 0.011708997189998627,
      "learning_rate": 0.29319815098415275,
      "loss": 0.1505,
      "num_input_tokens_seen": 1077664,
      "step": 3850
    },
    {
      "epoch": 42.833333333333336,
      "grad_norm": 0.02657490409910679,
      "learning_rate": 0.2931806029959832,
      "loss": 0.2111,
      "num_input_tokens_seen": 1079072,
      "step": 3855
    },
    {
      "epoch": 42.888888888888886,
      "grad_norm": 0.010936660692095757,
      "learning_rate": 0.29316303292756535,
      "loss": 0.1556,
      "num_input_tokens_seen": 1080480,
      "step": 3860
    },
    {
      "epoch": 42.94444444444444,
      "grad_norm": 0.019860781729221344,
      "learning_rate": 0.29314544078160876,
      "loss": 0.157,
      "num_input_tokens_seen": 1081888,
      "step": 3865
    },
    {
      "epoch": 43.0,
      "grad_norm": 0.005134686827659607,
      "learning_rate": 0.2931278265608263,
      "loss": 0.1523,
      "num_input_tokens_seen": 1083264,
      "step": 3870
    },
    {
      "epoch": 43.05555555555556,
      "grad_norm": 0.007735198829323053,
      "learning_rate": 0.29311019026793433,
      "loss": 0.1142,
      "num_input_tokens_seen": 1084688,
      "step": 3875
    },
    {
      "epoch": 43.111111111111114,
      "grad_norm": 0.010310879908502102,
      "learning_rate": 0.29309253190565254,
      "loss": 0.151,
      "num_input_tokens_seen": 1086096,
      "step": 3880
    },
    {
      "epoch": 43.166666666666664,
      "grad_norm": 0.008113245479762554,
      "learning_rate": 0.2930748514767042,
      "loss": 0.1346,
      "num_input_tokens_seen": 1087456,
      "step": 3885
    },
    {
      "epoch": 43.22222222222222,
      "grad_norm": 0.010445191524922848,
      "learning_rate": 0.29305714898381574,
      "loss": 0.1493,
      "num_input_tokens_seen": 1088864,
      "step": 3890
    },
    {
      "epoch": 43.27777777777778,
      "grad_norm": 0.026607178151607513,
      "learning_rate": 0.29303942442971714,
      "loss": 0.1414,
      "num_input_tokens_seen": 1090256,
      "step": 3895
    },
    {
      "epoch": 43.333333333333336,
      "grad_norm": 0.014741186983883381,
      "learning_rate": 0.2930216778171417,
      "loss": 0.1319,
      "num_input_tokens_seen": 1091696,
      "step": 3900
    },
    {
      "epoch": 43.388888888888886,
      "grad_norm": 0.01421715971082449,
      "learning_rate": 0.2930039091488263,
      "loss": 0.1509,
      "num_input_tokens_seen": 1093040,
      "step": 3905
    },
    {
      "epoch": 43.44444444444444,
      "grad_norm": 0.013771611265838146,
      "learning_rate": 0.29298611842751093,
      "loss": 0.1202,
      "num_input_tokens_seen": 1094464,
      "step": 3910
    },
    {
      "epoch": 43.5,
      "grad_norm": 0.014890527352690697,
      "learning_rate": 0.29296830565593923,
      "loss": 0.1188,
      "num_input_tokens_seen": 1095856,
      "step": 3915
    },
    {
      "epoch": 43.55555555555556,
      "grad_norm": 0.0336003340780735,
      "learning_rate": 0.2929504708368582,
      "loss": 0.1842,
      "num_input_tokens_seen": 1097264,
      "step": 3920
    },
    {
      "epoch": 43.611111111111114,
      "grad_norm": 0.01638762466609478,
      "learning_rate": 0.29293261397301806,
      "loss": 0.1141,
      "num_input_tokens_seen": 1098656,
      "step": 3925
    },
    {
      "epoch": 43.666666666666664,
      "grad_norm": 0.01901433989405632,
      "learning_rate": 0.29291473506717275,
      "loss": 0.1372,
      "num_input_tokens_seen": 1100096,
      "step": 3930
    },
    {
      "epoch": 43.72222222222222,
      "grad_norm": 0.013121563009917736,
      "learning_rate": 0.29289683412207923,
      "loss": 0.1916,
      "num_input_tokens_seen": 1101568,
      "step": 3935
    },
    {
      "epoch": 43.77777777777778,
      "grad_norm": 0.012965218164026737,
      "learning_rate": 0.29287891114049813,
      "loss": 0.148,
      "num_input_tokens_seen": 1102976,
      "step": 3940
    },
    {
      "epoch": 43.833333333333336,
      "grad_norm": 0.009364652447402477,
      "learning_rate": 0.29286096612519347,
      "loss": 0.1412,
      "num_input_tokens_seen": 1104352,
      "step": 3945
    },
    {
      "epoch": 43.888888888888886,
      "grad_norm": 0.009169028140604496,
      "learning_rate": 0.2928429990789325,
      "loss": 0.1592,
      "num_input_tokens_seen": 1105776,
      "step": 3950
    },
    {
      "epoch": 43.94444444444444,
      "grad_norm": 0.012774704024195671,
      "learning_rate": 0.29282501000448596,
      "loss": 0.166,
      "num_input_tokens_seen": 1107168,
      "step": 3955
    },
    {
      "epoch": 44.0,
      "grad_norm": 0.014217126183211803,
      "learning_rate": 0.2928069989046281,
      "loss": 0.1461,
      "num_input_tokens_seen": 1108592,
      "step": 3960
    },
    {
      "epoch": 44.05555555555556,
      "grad_norm": 0.010686341673135757,
      "learning_rate": 0.2927889657821363,
      "loss": 0.1332,
      "num_input_tokens_seen": 1110000,
      "step": 3965
    },
    {
      "epoch": 44.111111111111114,
      "grad_norm": 0.020788727328181267,
      "learning_rate": 0.2927709106397916,
      "loss": 0.1413,
      "num_input_tokens_seen": 1111376,
      "step": 3970
    },
    {
      "epoch": 44.166666666666664,
      "grad_norm": 0.007399877533316612,
      "learning_rate": 0.29275283348037834,
      "loss": 0.1282,
      "num_input_tokens_seen": 1112800,
      "step": 3975
    },
    {
      "epoch": 44.22222222222222,
      "grad_norm": 0.011034148745238781,
      "learning_rate": 0.29273473430668423,
      "loss": 0.1073,
      "num_input_tokens_seen": 1114224,
      "step": 3980
    },
    {
      "epoch": 44.27777777777778,
      "grad_norm": 0.017085213214159012,
      "learning_rate": 0.2927166131215003,
      "loss": 0.0883,
      "num_input_tokens_seen": 1115600,
      "step": 3985
    },
    {
      "epoch": 44.333333333333336,
      "grad_norm": 0.010037760250270367,
      "learning_rate": 0.2926984699276212,
      "loss": 0.1069,
      "num_input_tokens_seen": 1116976,
      "step": 3990
    },
    {
      "epoch": 44.388888888888886,
      "grad_norm": 0.01673319563269615,
      "learning_rate": 0.29268030472784473,
      "loss": 0.1016,
      "num_input_tokens_seen": 1118336,
      "step": 3995
    },
    {
      "epoch": 44.44444444444444,
      "grad_norm": 0.02251831442117691,
      "learning_rate": 0.2926621175249723,
      "loss": 0.1005,
      "num_input_tokens_seen": 1119744,
      "step": 4000
    },
    {
      "epoch": 44.44444444444444,
      "eval_loss": 0.26122796535491943,
      "eval_runtime": 1.1863,
      "eval_samples_per_second": 33.717,
      "eval_steps_per_second": 16.859,
      "num_input_tokens_seen": 1119744,
      "step": 4000
    },
    {
      "epoch": 44.5,
      "grad_norm": 0.03461332246661186,
      "learning_rate": 0.29264390832180853,
      "loss": 0.1656,
      "num_input_tokens_seen": 1121088,
      "step": 4005
    },
    {
      "epoch": 44.55555555555556,
      "grad_norm": 0.004151101224124432,
      "learning_rate": 0.29262567712116144,
      "loss": 0.0953,
      "num_input_tokens_seen": 1122512,
      "step": 4010
    },
    {
      "epoch": 44.611111111111114,
      "grad_norm": 0.09055086225271225,
      "learning_rate": 0.29260742392584266,
      "loss": 0.3616,
      "num_input_tokens_seen": 1123936,
      "step": 4015
    },
    {
      "epoch": 44.666666666666664,
      "grad_norm": 0.0037557499017566442,
      "learning_rate": 0.292589148738667,
      "loss": 0.1674,
      "num_input_tokens_seen": 1125312,
      "step": 4020
    },
    {
      "epoch": 44.72222222222222,
      "grad_norm": 0.003249181667342782,
      "learning_rate": 0.2925708515624527,
      "loss": 0.1674,
      "num_input_tokens_seen": 1126736,
      "step": 4025
    },
    {
      "epoch": 44.77777777777778,
      "grad_norm": 0.003979255445301533,
      "learning_rate": 0.29255253240002144,
      "loss": 0.1658,
      "num_input_tokens_seen": 1128176,
      "step": 4030
    },
    {
      "epoch": 44.833333333333336,
      "grad_norm": 0.006073941942304373,
      "learning_rate": 0.2925341912541983,
      "loss": 0.1682,
      "num_input_tokens_seen": 1129568,
      "step": 4035
    },
    {
      "epoch": 44.888888888888886,
      "grad_norm": 0.0045706587843596935,
      "learning_rate": 0.2925158281278116,
      "loss": 0.1742,
      "num_input_tokens_seen": 1131008,
      "step": 4040
    },
    {
      "epoch": 44.94444444444444,
      "grad_norm": 0.003747757989913225,
      "learning_rate": 0.29249744302369324,
      "loss": 0.1581,
      "num_input_tokens_seen": 1132368,
      "step": 4045
    },
    {
      "epoch": 45.0,
      "grad_norm": 0.0058518750593066216,
      "learning_rate": 0.29247903594467844,
      "loss": 0.1456,
      "num_input_tokens_seen": 1133744,
      "step": 4050
    },
    {
      "epoch": 45.05555555555556,
      "grad_norm": 0.004045119043439627,
      "learning_rate": 0.2924606068936058,
      "loss": 0.1344,
      "num_input_tokens_seen": 1135152,
      "step": 4055
    },
    {
      "epoch": 45.111111111111114,
      "grad_norm": 0.006716578733175993,
      "learning_rate": 0.2924421558733173,
      "loss": 0.1515,
      "num_input_tokens_seen": 1136560,
      "step": 4060
    },
    {
      "epoch": 45.166666666666664,
      "grad_norm": 0.010578520596027374,
      "learning_rate": 0.2924236828866583,
      "loss": 0.1118,
      "num_input_tokens_seen": 1137952,
      "step": 4065
    },
    {
      "epoch": 45.22222222222222,
      "grad_norm": 0.00406291987746954,
      "learning_rate": 0.29240518793647763,
      "loss": 0.1688,
      "num_input_tokens_seen": 1139328,
      "step": 4070
    },
    {
      "epoch": 45.27777777777778,
      "grad_norm": 0.009222897700965405,
      "learning_rate": 0.29238667102562743,
      "loss": 0.1433,
      "num_input_tokens_seen": 1140752,
      "step": 4075
    },
    {
      "epoch": 45.333333333333336,
      "grad_norm": 0.00932307168841362,
      "learning_rate": 0.29236813215696317,
      "loss": 0.1036,
      "num_input_tokens_seen": 1142096,
      "step": 4080
    },
    {
      "epoch": 45.388888888888886,
      "grad_norm": 0.011117205955088139,
      "learning_rate": 0.2923495713333439,
      "loss": 0.1432,
      "num_input_tokens_seen": 1143440,
      "step": 4085
    },
    {
      "epoch": 45.44444444444444,
      "grad_norm": 0.016215791925787926,
      "learning_rate": 0.29233098855763173,
      "loss": 0.1175,
      "num_input_tokens_seen": 1144832,
      "step": 4090
    },
    {
      "epoch": 45.5,
      "grad_norm": 0.02205170877277851,
      "learning_rate": 0.29231238383269254,
      "loss": 0.1065,
      "num_input_tokens_seen": 1146240,
      "step": 4095
    },
    {
      "epoch": 45.55555555555556,
      "grad_norm": 0.009378481656312943,
      "learning_rate": 0.2922937571613954,
      "loss": 0.1031,
      "num_input_tokens_seen": 1147648,
      "step": 4100
    },
    {
      "epoch": 45.611111111111114,
      "grad_norm": 0.0180798526853323,
      "learning_rate": 0.29227510854661265,
      "loss": 0.1111,
      "num_input_tokens_seen": 1149040,
      "step": 4105
    },
    {
      "epoch": 45.666666666666664,
      "grad_norm": 0.01416570134460926,
      "learning_rate": 0.29225643799122025,
      "loss": 0.1307,
      "num_input_tokens_seen": 1150448,
      "step": 4110
    },
    {
      "epoch": 45.72222222222222,
      "grad_norm": 0.018018942326307297,
      "learning_rate": 0.2922377454980974,
      "loss": 0.1227,
      "num_input_tokens_seen": 1151856,
      "step": 4115
    },
    {
      "epoch": 45.77777777777778,
      "grad_norm": 0.025197185575962067,
      "learning_rate": 0.29221903107012676,
      "loss": 0.1973,
      "num_input_tokens_seen": 1153264,
      "step": 4120
    },
    {
      "epoch": 45.833333333333336,
      "grad_norm": 0.00511532835662365,
      "learning_rate": 0.29220029471019426,
      "loss": 0.1306,
      "num_input_tokens_seen": 1154656,
      "step": 4125
    },
    {
      "epoch": 45.888888888888886,
      "grad_norm": 0.00557267852127552,
      "learning_rate": 0.2921815364211893,
      "loss": 0.1485,
      "num_input_tokens_seen": 1156096,
      "step": 4130
    },
    {
      "epoch": 45.94444444444444,
      "grad_norm": 0.005174088757485151,
      "learning_rate": 0.29216275620600474,
      "loss": 0.1629,
      "num_input_tokens_seen": 1157488,
      "step": 4135
    },
    {
      "epoch": 46.0,
      "grad_norm": 0.009299512952566147,
      "learning_rate": 0.29214395406753657,
      "loss": 0.124,
      "num_input_tokens_seen": 1158864,
      "step": 4140
    },
    {
      "epoch": 46.05555555555556,
      "grad_norm": 0.007559367921203375,
      "learning_rate": 0.2921251300086844,
      "loss": 0.0969,
      "num_input_tokens_seen": 1160256,
      "step": 4145
    },
    {
      "epoch": 46.111111111111114,
      "grad_norm": 0.01497260294854641,
      "learning_rate": 0.2921062840323511,
      "loss": 0.0919,
      "num_input_tokens_seen": 1161616,
      "step": 4150
    },
    {
      "epoch": 46.166666666666664,
      "grad_norm": 0.004870262928307056,
      "learning_rate": 0.29208741614144307,
      "loss": 0.0768,
      "num_input_tokens_seen": 1163040,
      "step": 4155
    },
    {
      "epoch": 46.22222222222222,
      "grad_norm": 0.02116168849170208,
      "learning_rate": 0.2920685263388698,
      "loss": 0.1561,
      "num_input_tokens_seen": 1164448,
      "step": 4160
    },
    {
      "epoch": 46.27777777777778,
      "grad_norm": 0.011667999438941479,
      "learning_rate": 0.2920496146275445,
      "loss": 0.0595,
      "num_input_tokens_seen": 1165888,
      "step": 4165
    },
    {
      "epoch": 46.333333333333336,
      "grad_norm": 0.008168819360435009,
      "learning_rate": 0.29203068101038343,
      "loss": 0.1174,
      "num_input_tokens_seen": 1167296,
      "step": 4170
    },
    {
      "epoch": 46.388888888888886,
      "grad_norm": 0.009019758552312851,
      "learning_rate": 0.2920117254903065,
      "loss": 0.1172,
      "num_input_tokens_seen": 1168688,
      "step": 4175
    },
    {
      "epoch": 46.44444444444444,
      "grad_norm": 0.014706544578075409,
      "learning_rate": 0.29199274807023695,
      "loss": 0.1234,
      "num_input_tokens_seen": 1170064,
      "step": 4180
    },
    {
      "epoch": 46.5,
      "grad_norm": 0.009332605637609959,
      "learning_rate": 0.29197374875310117,
      "loss": 0.1087,
      "num_input_tokens_seen": 1171472,
      "step": 4185
    },
    {
      "epoch": 46.55555555555556,
      "grad_norm": 0.020564088597893715,
      "learning_rate": 0.2919547275418292,
      "loss": 0.1321,
      "num_input_tokens_seen": 1172880,
      "step": 4190
    },
    {
      "epoch": 46.611111111111114,
      "grad_norm": 0.011331847868859768,
      "learning_rate": 0.29193568443935436,
      "loss": 0.0841,
      "num_input_tokens_seen": 1174288,
      "step": 4195
    },
    {
      "epoch": 46.666666666666664,
      "grad_norm": 0.009844960644841194,
      "learning_rate": 0.2919166194486133,
      "loss": 0.0669,
      "num_input_tokens_seen": 1175680,
      "step": 4200
    },
    {
      "epoch": 46.666666666666664,
      "eval_loss": 0.2603604793548584,
      "eval_runtime": 1.1845,
      "eval_samples_per_second": 33.768,
      "eval_steps_per_second": 16.884,
      "num_input_tokens_seen": 1175680,
      "step": 4200
    },
    {
      "epoch": 46.72222222222222,
      "grad_norm": 0.009003742597997189,
      "learning_rate": 0.2918975325725461,
      "loss": 0.1516,
      "num_input_tokens_seen": 1177056,
      "step": 4205
    },
    {
      "epoch": 46.77777777777778,
      "grad_norm": 0.010627806186676025,
      "learning_rate": 0.29187842381409607,
      "loss": 0.1196,
      "num_input_tokens_seen": 1178464,
      "step": 4210
    },
    {
      "epoch": 46.833333333333336,
      "grad_norm": 0.010312028229236603,
      "learning_rate": 0.29185929317621023,
      "loss": 0.0987,
      "num_input_tokens_seen": 1179872,
      "step": 4215
    },
    {
      "epoch": 46.888888888888886,
      "grad_norm": 0.00920235924422741,
      "learning_rate": 0.29184014066183867,
      "loss": 0.0997,
      "num_input_tokens_seen": 1181280,
      "step": 4220
    },
    {
      "epoch": 46.94444444444444,
      "grad_norm": 0.019210945814847946,
      "learning_rate": 0.2918209662739349,
      "loss": 0.1326,
      "num_input_tokens_seen": 1182704,
      "step": 4225
    },
    {
      "epoch": 47.0,
      "grad_norm": 0.016998646780848503,
      "learning_rate": 0.29180177001545593,
      "loss": 0.1236,
      "num_input_tokens_seen": 1184112,
      "step": 4230
    },
    {
      "epoch": 47.05555555555556,
      "grad_norm": 0.009610595181584358,
      "learning_rate": 0.29178255188936203,
      "loss": 0.057,
      "num_input_tokens_seen": 1185488,
      "step": 4235
    },
    {
      "epoch": 47.111111111111114,
      "grad_norm": 0.01907520182430744,
      "learning_rate": 0.2917633118986169,
      "loss": 0.0935,
      "num_input_tokens_seen": 1186848,
      "step": 4240
    },
    {
      "epoch": 47.166666666666664,
      "grad_norm": 0.009127464145421982,
      "learning_rate": 0.2917440500461875,
      "loss": 0.0438,
      "num_input_tokens_seen": 1188240,
      "step": 4245
    },
    {
      "epoch": 47.22222222222222,
      "grad_norm": 0.02318316325545311,
      "learning_rate": 0.29172476633504435,
      "loss": 0.1308,
      "num_input_tokens_seen": 1189680,
      "step": 4250
    },
    {
      "epoch": 47.27777777777778,
      "grad_norm": 0.014378661289811134,
      "learning_rate": 0.2917054607681612,
      "loss": 0.1687,
      "num_input_tokens_seen": 1191072,
      "step": 4255
    },
    {
      "epoch": 47.333333333333336,
      "grad_norm": 0.010842772200703621,
      "learning_rate": 0.29168613334851523,
      "loss": 0.1621,
      "num_input_tokens_seen": 1192480,
      "step": 4260
    },
    {
      "epoch": 47.388888888888886,
      "grad_norm": 0.017746733501553535,
      "learning_rate": 0.2916667840790869,
      "loss": 0.164,
      "num_input_tokens_seen": 1193872,
      "step": 4265
    },
    {
      "epoch": 47.44444444444444,
      "grad_norm": 0.008913563564419746,
      "learning_rate": 0.2916474129628603,
      "loss": 0.1014,
      "num_input_tokens_seen": 1195296,
      "step": 4270
    },
    {
      "epoch": 47.5,
      "grad_norm": 0.00562835531309247,
      "learning_rate": 0.29162802000282245,
      "loss": 0.1101,
      "num_input_tokens_seen": 1196672,
      "step": 4275
    },
    {
      "epoch": 47.55555555555556,
      "grad_norm": 0.008012562990188599,
      "learning_rate": 0.2916086052019642,
      "loss": 0.0867,
      "num_input_tokens_seen": 1198064,
      "step": 4280
    },
    {
      "epoch": 47.611111111111114,
      "grad_norm": 0.007173314690589905,
      "learning_rate": 0.2915891685632794,
      "loss": 0.1332,
      "num_input_tokens_seen": 1199456,
      "step": 4285
    },
    {
      "epoch": 47.666666666666664,
      "grad_norm": 0.007563200779259205,
      "learning_rate": 0.29156971008976545,
      "loss": 0.1114,
      "num_input_tokens_seen": 1200864,
      "step": 4290
    },
    {
      "epoch": 47.72222222222222,
      "grad_norm": 0.01091946754604578,
      "learning_rate": 0.2915502297844232,
      "loss": 0.1058,
      "num_input_tokens_seen": 1202224,
      "step": 4295
    },
    {
      "epoch": 47.77777777777778,
      "grad_norm": 0.005960257723927498,
      "learning_rate": 0.2915307276502566,
      "loss": 0.0748,
      "num_input_tokens_seen": 1203632,
      "step": 4300
    },
    {
      "epoch": 47.833333333333336,
      "grad_norm": 0.0067018806003034115,
      "learning_rate": 0.29151120369027334,
      "loss": 0.0771,
      "num_input_tokens_seen": 1205040,
      "step": 4305
    },
    {
      "epoch": 47.888888888888886,
      "grad_norm": 0.01829219050705433,
      "learning_rate": 0.29149165790748405,
      "loss": 0.1131,
      "num_input_tokens_seen": 1206480,
      "step": 4310
    },
    {
      "epoch": 47.94444444444444,
      "grad_norm": 0.023718802258372307,
      "learning_rate": 0.291472090304903,
      "loss": 0.0891,
      "num_input_tokens_seen": 1207952,
      "step": 4315
    },
    {
      "epoch": 48.0,
      "grad_norm": 0.010259167291224003,
      "learning_rate": 0.2914525008855478,
      "loss": 0.0891,
      "num_input_tokens_seen": 1209328,
      "step": 4320
    },
    {
      "epoch": 48.05555555555556,
      "grad_norm": 0.0031361919827759266,
      "learning_rate": 0.2914328896524394,
      "loss": 0.0718,
      "num_input_tokens_seen": 1210768,
      "step": 4325
    },
    {
      "epoch": 48.111111111111114,
      "grad_norm": 0.002401787554845214,
      "learning_rate": 0.291413256608602,
      "loss": 0.1222,
      "num_input_tokens_seen": 1212096,
      "step": 4330
    },
    {
      "epoch": 48.166666666666664,
      "grad_norm": 0.009483395144343376,
      "learning_rate": 0.29139360175706336,
      "loss": 0.0319,
      "num_input_tokens_seen": 1213504,
      "step": 4335
    },
    {
      "epoch": 48.22222222222222,
      "grad_norm": 0.011617295444011688,
      "learning_rate": 0.2913739251008544,
      "loss": 0.068,
      "num_input_tokens_seen": 1214944,
      "step": 4340
    },
    {
      "epoch": 48.27777777777778,
      "grad_norm": 0.014599977061152458,
      "learning_rate": 0.29135422664300964,
      "loss": 0.1229,
      "num_input_tokens_seen": 1216336,
      "step": 4345
    },
    {
      "epoch": 48.333333333333336,
      "grad_norm": 0.02827306091785431,
      "learning_rate": 0.29133450638656677,
      "loss": 0.0659,
      "num_input_tokens_seen": 1217760,
      "step": 4350
    },
    {
      "epoch": 48.388888888888886,
      "grad_norm": 0.018751392140984535,
      "learning_rate": 0.2913147643345669,
      "loss": 0.0671,
      "num_input_tokens_seen": 1219136,
      "step": 4355
    },
    {
      "epoch": 48.44444444444444,
      "grad_norm": 0.028922956436872482,
      "learning_rate": 0.29129500049005447,
      "loss": 0.0765,
      "num_input_tokens_seen": 1220512,
      "step": 4360
    },
    {
      "epoch": 48.5,
      "grad_norm": 0.026054006069898605,
      "learning_rate": 0.2912752148560773,
      "loss": 0.1054,
      "num_input_tokens_seen": 1221888,
      "step": 4365
    },
    {
      "epoch": 48.55555555555556,
      "grad_norm": 0.010559933260083199,
      "learning_rate": 0.2912554074356866,
      "loss": 0.1117,
      "num_input_tokens_seen": 1223264,
      "step": 4370
    },
    {
      "epoch": 48.611111111111114,
      "grad_norm": 0.007528443355113268,
      "learning_rate": 0.2912355782319371,
      "loss": 0.0811,
      "num_input_tokens_seen": 1224640,
      "step": 4375
    },
    {
      "epoch": 48.666666666666664,
      "grad_norm": 0.006012480240315199,
      "learning_rate": 0.2912157272478864,
      "loss": 0.0647,
      "num_input_tokens_seen": 1226016,
      "step": 4380
    },
    {
      "epoch": 48.72222222222222,
      "grad_norm": 0.017608514055609703,
      "learning_rate": 0.291195854486596,
      "loss": 0.0774,
      "num_input_tokens_seen": 1227424,
      "step": 4385
    },
    {
      "epoch": 48.77777777777778,
      "grad_norm": 0.02308967523276806,
      "learning_rate": 0.2911759599511305,
      "loss": 0.0996,
      "num_input_tokens_seen": 1228864,
      "step": 4390
    },
    {
      "epoch": 48.833333333333336,
      "grad_norm": 0.02257877215743065,
      "learning_rate": 0.29115604364455777,
      "loss": 0.1574,
      "num_input_tokens_seen": 1230272,
      "step": 4395
    },
    {
      "epoch": 48.888888888888886,
      "grad_norm": 0.0076314909383654594,
      "learning_rate": 0.2911361055699493,
      "loss": 0.1043,
      "num_input_tokens_seen": 1231696,
      "step": 4400
    },
    {
      "epoch": 48.888888888888886,
      "eval_loss": 0.24143151938915253,
      "eval_runtime": 1.186,
      "eval_samples_per_second": 33.726,
      "eval_steps_per_second": 16.863,
      "num_input_tokens_seen": 1231696,
      "step": 4400
    },
    {
      "epoch": 48.94444444444444,
      "grad_norm": 0.012104646302759647,
      "learning_rate": 0.2911161457303797,
      "loss": 0.0765,
      "num_input_tokens_seen": 1233136,
      "step": 4405
    },
    {
      "epoch": 49.0,
      "grad_norm": 0.016912899911403656,
      "learning_rate": 0.291096164128927,
      "loss": 0.1031,
      "num_input_tokens_seen": 1234528,
      "step": 4410
    },
    {
      "epoch": 49.05555555555556,
      "grad_norm": 0.008161507546901703,
      "learning_rate": 0.2910761607686727,
      "loss": 0.0742,
      "num_input_tokens_seen": 1235904,
      "step": 4415
    },
    {
      "epoch": 49.111111111111114,
      "grad_norm": 0.02223162353038788,
      "learning_rate": 0.2910561356527016,
      "loss": 0.0628,
      "num_input_tokens_seen": 1237312,
      "step": 4420
    },
    {
      "epoch": 49.166666666666664,
      "grad_norm": 0.008575462736189365,
      "learning_rate": 0.2910360887841017,
      "loss": 0.0956,
      "num_input_tokens_seen": 1238736,
      "step": 4425
    },
    {
      "epoch": 49.22222222222222,
      "grad_norm": 0.012073691934347153,
      "learning_rate": 0.2910160201659645,
      "loss": 0.0405,
      "num_input_tokens_seen": 1240128,
      "step": 4430
    },
    {
      "epoch": 49.27777777777778,
      "grad_norm": 0.024626407772302628,
      "learning_rate": 0.29099592980138494,
      "loss": 0.0363,
      "num_input_tokens_seen": 1241568,
      "step": 4435
    },
    {
      "epoch": 49.333333333333336,
      "grad_norm": 0.0031997307669371367,
      "learning_rate": 0.29097581769346115,
      "loss": 0.0487,
      "num_input_tokens_seen": 1242976,
      "step": 4440
    },
    {
      "epoch": 49.388888888888886,
      "grad_norm": 0.01329235453158617,
      "learning_rate": 0.29095568384529463,
      "loss": 0.0279,
      "num_input_tokens_seen": 1244384,
      "step": 4445
    },
    {
      "epoch": 49.44444444444444,
      "grad_norm": 0.020213307812809944,
      "learning_rate": 0.2909355282599903,
      "loss": 0.0527,
      "num_input_tokens_seen": 1245776,
      "step": 4450
    },
    {
      "epoch": 49.5,
      "grad_norm": 0.034707117825746536,
      "learning_rate": 0.29091535094065635,
      "loss": 0.0582,
      "num_input_tokens_seen": 1247200,
      "step": 4455
    },
    {
      "epoch": 49.55555555555556,
      "grad_norm": 0.05286236107349396,
      "learning_rate": 0.2908951518904045,
      "loss": 0.1093,
      "num_input_tokens_seen": 1248656,
      "step": 4460
    },
    {
      "epoch": 49.611111111111114,
      "grad_norm": 0.01212973054498434,
      "learning_rate": 0.29087493111234963,
      "loss": 0.0946,
      "num_input_tokens_seen": 1250048,
      "step": 4465
    },
    {
      "epoch": 49.666666666666664,
      "grad_norm": 0.005039738491177559,
      "learning_rate": 0.29085468860961,
      "loss": 0.1197,
      "num_input_tokens_seen": 1251424,
      "step": 4470
    },
    {
      "epoch": 49.72222222222222,
      "grad_norm": 0.012651720084249973,
      "learning_rate": 0.2908344243853073,
      "loss": 0.1238,
      "num_input_tokens_seen": 1252816,
      "step": 4475
    },
    {
      "epoch": 49.77777777777778,
      "grad_norm": 0.011401446536183357,
      "learning_rate": 0.2908141384425666,
      "loss": 0.1428,
      "num_input_tokens_seen": 1254160,
      "step": 4480
    },
    {
      "epoch": 49.833333333333336,
      "grad_norm": 0.008762190118432045,
      "learning_rate": 0.2907938307845161,
      "loss": 0.1272,
      "num_input_tokens_seen": 1255536,
      "step": 4485
    },
    {
      "epoch": 49.888888888888886,
      "grad_norm": 0.024201568216085434,
      "learning_rate": 0.2907735014142876,
      "loss": 0.1389,
      "num_input_tokens_seen": 1256960,
      "step": 4490
    },
    {
      "epoch": 49.94444444444444,
      "grad_norm": 0.013585845939815044,
      "learning_rate": 0.2907531503350161,
      "loss": 0.1089,
      "num_input_tokens_seen": 1258352,
      "step": 4495
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.016100892797112465,
      "learning_rate": 0.29073277754983995,
      "loss": 0.0818,
      "num_input_tokens_seen": 1259744,
      "step": 4500
    },
    {
      "epoch": 50.05555555555556,
      "grad_norm": 0.007038208656013012,
      "learning_rate": 0.290712383061901,
      "loss": 0.0474,
      "num_input_tokens_seen": 1261152,
      "step": 4505
    },
    {
      "epoch": 50.111111111111114,
      "grad_norm": 0.04005928337574005,
      "learning_rate": 0.2906919668743443,
      "loss": 0.066,
      "num_input_tokens_seen": 1262528,
      "step": 4510
    },
    {
      "epoch": 50.166666666666664,
      "grad_norm": 0.012391636148095131,
      "learning_rate": 0.29067152899031823,
      "loss": 0.1344,
      "num_input_tokens_seen": 1263936,
      "step": 4515
    },
    {
      "epoch": 50.22222222222222,
      "grad_norm": 0.014308658428490162,
      "learning_rate": 0.2906510694129746,
      "loss": 0.0744,
      "num_input_tokens_seen": 1265312,
      "step": 4520
    },
    {
      "epoch": 50.27777777777778,
      "grad_norm": 0.008641687221825123,
      "learning_rate": 0.2906305881454685,
      "loss": 0.0866,
      "num_input_tokens_seen": 1266720,
      "step": 4525
    },
    {
      "epoch": 50.333333333333336,
      "grad_norm": 0.014889465644955635,
      "learning_rate": 0.2906100851909585,
      "loss": 0.0351,
      "num_input_tokens_seen": 1268144,
      "step": 4530
    },
    {
      "epoch": 50.388888888888886,
      "grad_norm": 0.010792124085128307,
      "learning_rate": 0.29058956055260626,
      "loss": 0.0554,
      "num_input_tokens_seen": 1269568,
      "step": 4535
    },
    {
      "epoch": 50.44444444444444,
      "grad_norm": 0.003204318694770336,
      "learning_rate": 0.2905690142335771,
      "loss": 0.0363,
      "num_input_tokens_seen": 1270896,
      "step": 4540
    },
    {
      "epoch": 50.5,
      "grad_norm": 0.004111207090318203,
      "learning_rate": 0.29054844623703946,
      "loss": 0.0158,
      "num_input_tokens_seen": 1272304,
      "step": 4545
    },
    {
      "epoch": 50.55555555555556,
      "grad_norm": 0.041297152638435364,
      "learning_rate": 0.2905278565661651,
      "loss": 0.0626,
      "num_input_tokens_seen": 1273712,
      "step": 4550
    },
    {
      "epoch": 50.611111111111114,
      "grad_norm": 0.01885414309799671,
      "learning_rate": 0.2905072452241293,
      "loss": 0.051,
      "num_input_tokens_seen": 1275120,
      "step": 4555
    },
    {
      "epoch": 50.666666666666664,
      "grad_norm": 0.003682026406750083,
      "learning_rate": 0.2904866122141106,
      "loss": 0.0325,
      "num_input_tokens_seen": 1276528,
      "step": 4560
    },
    {
      "epoch": 50.72222222222222,
      "grad_norm": 0.007531265262514353,
      "learning_rate": 0.2904659575392908,
      "loss": 0.0365,
      "num_input_tokens_seen": 1277952,
      "step": 4565
    },
    {
      "epoch": 50.77777777777778,
      "grad_norm": 0.004015096463263035,
      "learning_rate": 0.2904452812028551,
      "loss": 0.0311,
      "num_input_tokens_seen": 1279312,
      "step": 4570
    },
    {
      "epoch": 50.833333333333336,
      "grad_norm": 0.016867298632860184,
      "learning_rate": 0.2904245832079922,
      "loss": 0.0479,
      "num_input_tokens_seen": 1280672,
      "step": 4575
    },
    {
      "epoch": 50.888888888888886,
      "grad_norm": 0.0021780694369226694,
      "learning_rate": 0.29040386355789377,
      "loss": 0.031,
      "num_input_tokens_seen": 1282096,
      "step": 4580
    },
    {
      "epoch": 50.94444444444444,
      "grad_norm": 0.01203781645745039,
      "learning_rate": 0.29038312225575524,
      "loss": 0.059,
      "num_input_tokens_seen": 1283520,
      "step": 4585
    },
    {
      "epoch": 51.0,
      "grad_norm": 0.0190347321331501,
      "learning_rate": 0.29036235930477505,
      "loss": 0.0795,
      "num_input_tokens_seen": 1284912,
      "step": 4590
    },
    {
      "epoch": 51.05555555555556,
      "grad_norm": 0.019493136554956436,
      "learning_rate": 0.29034157470815514,
      "loss": 0.0395,
      "num_input_tokens_seen": 1286320,
      "step": 4595
    },
    {
      "epoch": 51.111111111111114,
      "grad_norm": 0.017089426517486572,
      "learning_rate": 0.2903207684691008,
      "loss": 0.0445,
      "num_input_tokens_seen": 1287744,
      "step": 4600
    },
    {
      "epoch": 51.111111111111114,
      "eval_loss": 0.33786630630493164,
      "eval_runtime": 1.1833,
      "eval_samples_per_second": 33.804,
      "eval_steps_per_second": 16.902,
      "num_input_tokens_seen": 1287744,
      "step": 4600
    },
    {
      "epoch": 51.166666666666664,
      "grad_norm": 0.0013698092661798,
      "learning_rate": 0.29029994059082054,
      "loss": 0.0219,
      "num_input_tokens_seen": 1289136,
      "step": 4605
    },
    {
      "epoch": 51.22222222222222,
      "grad_norm": 0.004758996888995171,
      "learning_rate": 0.2902790910765264,
      "loss": 0.0275,
      "num_input_tokens_seen": 1290544,
      "step": 4610
    },
    {
      "epoch": 51.27777777777778,
      "grad_norm": 0.013396023772656918,
      "learning_rate": 0.29025821992943346,
      "loss": 0.043,
      "num_input_tokens_seen": 1291920,
      "step": 4615
    },
    {
      "epoch": 51.333333333333336,
      "grad_norm": 0.030855832621455193,
      "learning_rate": 0.29023732715276046,
      "loss": 0.0467,
      "num_input_tokens_seen": 1293248,
      "step": 4620
    },
    {
      "epoch": 51.388888888888886,
      "grad_norm": 0.02688567526638508,
      "learning_rate": 0.2902164127497293,
      "loss": 0.0511,
      "num_input_tokens_seen": 1294688,
      "step": 4625
    },
    {
      "epoch": 51.44444444444444,
      "grad_norm": 0.0016930957790464163,
      "learning_rate": 0.2901954767235652,
      "loss": 0.088,
      "num_input_tokens_seen": 1296128,
      "step": 4630
    },
    {
      "epoch": 51.5,
      "grad_norm": 0.002127778483554721,
      "learning_rate": 0.2901745190774968,
      "loss": 0.105,
      "num_input_tokens_seen": 1297616,
      "step": 4635
    },
    {
      "epoch": 51.55555555555556,
      "grad_norm": 0.0030874605290591717,
      "learning_rate": 0.290153539814756,
      "loss": 0.0184,
      "num_input_tokens_seen": 1298992,
      "step": 4640
    },
    {
      "epoch": 51.611111111111114,
      "grad_norm": 0.003355346852913499,
      "learning_rate": 0.2901325389385781,
      "loss": 0.0662,
      "num_input_tokens_seen": 1300336,
      "step": 4645
    },
    {
      "epoch": 51.666666666666664,
      "grad_norm": 0.004112964030355215,
      "learning_rate": 0.2901115164522016,
      "loss": 0.0443,
      "num_input_tokens_seen": 1301728,
      "step": 4650
    },
    {
      "epoch": 51.72222222222222,
      "grad_norm": 0.018226707354187965,
      "learning_rate": 0.29009047235886865,
      "loss": 0.0767,
      "num_input_tokens_seen": 1303120,
      "step": 4655
    },
    {
      "epoch": 51.77777777777778,
      "grad_norm": 0.01319198776036501,
      "learning_rate": 0.2900694066618243,
      "loss": 0.0429,
      "num_input_tokens_seen": 1304544,
      "step": 4660
    },
    {
      "epoch": 51.833333333333336,
      "grad_norm": 0.0020565264858305454,
      "learning_rate": 0.2900483193643172,
      "loss": 0.0391,
      "num_input_tokens_seen": 1305920,
      "step": 4665
    },
    {
      "epoch": 51.888888888888886,
      "grad_norm": 0.0010707821929827332,
      "learning_rate": 0.29002721046959934,
      "loss": 0.0161,
      "num_input_tokens_seen": 1307312,
      "step": 4670
    },
    {
      "epoch": 51.94444444444444,
      "grad_norm": 0.0031878906302154064,
      "learning_rate": 0.29000607998092587,
      "loss": 0.089,
      "num_input_tokens_seen": 1308752,
      "step": 4675
    },
    {
      "epoch": 52.0,
      "grad_norm": 0.0022451768163591623,
      "learning_rate": 0.2899849279015555,
      "loss": 0.0301,
      "num_input_tokens_seen": 1310128,
      "step": 4680
    },
    {
      "epoch": 52.05555555555556,
      "grad_norm": 0.0022829892113804817,
      "learning_rate": 0.28996375423475007,
      "loss": 0.0463,
      "num_input_tokens_seen": 1311488,
      "step": 4685
    },
    {
      "epoch": 52.111111111111114,
      "grad_norm": 0.016041075810790062,
      "learning_rate": 0.28994255898377486,
      "loss": 0.021,
      "num_input_tokens_seen": 1312896,
      "step": 4690
    },
    {
      "epoch": 52.166666666666664,
      "grad_norm": 0.00022742139117326587,
      "learning_rate": 0.2899213421518984,
      "loss": 0.0109,
      "num_input_tokens_seen": 1314288,
      "step": 4695
    },
    {
      "epoch": 52.22222222222222,
      "grad_norm": 0.002010809723287821,
      "learning_rate": 0.2899001037423926,
      "loss": 0.0065,
      "num_input_tokens_seen": 1315696,
      "step": 4700
    },
    {
      "epoch": 52.27777777777778,
      "grad_norm": 0.0036121883895248175,
      "learning_rate": 0.28987884375853273,
      "loss": 0.0167,
      "num_input_tokens_seen": 1317120,
      "step": 4705
    },
    {
      "epoch": 52.333333333333336,
      "grad_norm": 0.0015540665481239557,
      "learning_rate": 0.2898575622035974,
      "loss": 0.0086,
      "num_input_tokens_seen": 1318528,
      "step": 4710
    },
    {
      "epoch": 52.388888888888886,
      "grad_norm": 0.00042118545388802886,
      "learning_rate": 0.2898362590808683,
      "loss": 0.0148,
      "num_input_tokens_seen": 1319904,
      "step": 4715
    },
    {
      "epoch": 52.44444444444444,
      "grad_norm": 0.03788743540644646,
      "learning_rate": 0.2898149343936308,
      "loss": 0.0394,
      "num_input_tokens_seen": 1321312,
      "step": 4720
    },
    {
      "epoch": 52.5,
      "grad_norm": 0.01577278971672058,
      "learning_rate": 0.2897935881451734,
      "loss": 0.0238,
      "num_input_tokens_seen": 1322784,
      "step": 4725
    },
    {
      "epoch": 52.55555555555556,
      "grad_norm": 0.001027735648676753,
      "learning_rate": 0.28977222033878797,
      "loss": 0.0281,
      "num_input_tokens_seen": 1324160,
      "step": 4730
    },
    {
      "epoch": 52.611111111111114,
      "grad_norm": 0.0025213512126356363,
      "learning_rate": 0.28975083097776966,
      "loss": 0.0335,
      "num_input_tokens_seen": 1325536,
      "step": 4735
    },
    {
      "epoch": 52.666666666666664,
      "grad_norm": 0.0026616768445819616,
      "learning_rate": 0.28972942006541696,
      "loss": 0.0269,
      "num_input_tokens_seen": 1326880,
      "step": 4740
    },
    {
      "epoch": 52.72222222222222,
      "grad_norm": 0.006717302370816469,
      "learning_rate": 0.2897079876050318,
      "loss": 0.0197,
      "num_input_tokens_seen": 1328256,
      "step": 4745
    },
    {
      "epoch": 52.77777777777778,
      "grad_norm": 0.005089208018034697,
      "learning_rate": 0.2896865335999192,
      "loss": 0.0193,
      "num_input_tokens_seen": 1329648,
      "step": 4750
    },
    {
      "epoch": 52.833333333333336,
      "grad_norm": 0.013908397406339645,
      "learning_rate": 0.28966505805338777,
      "loss": 0.0158,
      "num_input_tokens_seen": 1331056,
      "step": 4755
    },
    {
      "epoch": 52.888888888888886,
      "grad_norm": 0.0005519343540072441,
      "learning_rate": 0.2896435609687492,
      "loss": 0.013,
      "num_input_tokens_seen": 1332464,
      "step": 4760
    },
    {
      "epoch": 52.94444444444444,
      "grad_norm": 0.0006731806788593531,
      "learning_rate": 0.2896220423493187,
      "loss": 0.0182,
      "num_input_tokens_seen": 1333856,
      "step": 4765
    },
    {
      "epoch": 53.0,
      "grad_norm": 0.025122079998254776,
      "learning_rate": 0.28960050219841466,
      "loss": 0.0441,
      "num_input_tokens_seen": 1335264,
      "step": 4770
    },
    {
      "epoch": 53.05555555555556,
      "grad_norm": 0.0025586639530956745,
      "learning_rate": 0.28957894051935884,
      "loss": 0.006,
      "num_input_tokens_seen": 1336672,
      "step": 4775
    },
    {
      "epoch": 53.111111111111114,
      "grad_norm": 0.012999184429645538,
      "learning_rate": 0.2895573573154764,
      "loss": 0.0612,
      "num_input_tokens_seen": 1338048,
      "step": 4780
    },
    {
      "epoch": 53.166666666666664,
      "grad_norm": 0.0007059326744638383,
      "learning_rate": 0.28953575259009556,
      "loss": 0.0468,
      "num_input_tokens_seen": 1339488,
      "step": 4785
    },
    {
      "epoch": 53.22222222222222,
      "grad_norm": 0.0037578647024929523,
      "learning_rate": 0.2895141263465482,
      "loss": 0.0153,
      "num_input_tokens_seen": 1340912,
      "step": 4790
    },
    {
      "epoch": 53.27777777777778,
      "grad_norm": 0.006300702691078186,
      "learning_rate": 0.28949247858816934,
      "loss": 0.0173,
      "num_input_tokens_seen": 1342352,
      "step": 4795
    },
    {
      "epoch": 53.333333333333336,
      "grad_norm": 0.013513053767383099,
      "learning_rate": 0.2894708093182973,
      "loss": 0.0243,
      "num_input_tokens_seen": 1343760,
      "step": 4800
    },
    {
      "epoch": 53.333333333333336,
      "eval_loss": 0.4503675401210785,
      "eval_runtime": 1.1822,
      "eval_samples_per_second": 33.835,
      "eval_steps_per_second": 16.918,
      "num_input_tokens_seen": 1343760,
      "step": 4800
    },
    {
      "epoch": 53.388888888888886,
      "grad_norm": 0.006363093852996826,
      "learning_rate": 0.2894491185402737,
      "loss": 0.0121,
      "num_input_tokens_seen": 1345152,
      "step": 4805
    },
    {
      "epoch": 53.44444444444444,
      "grad_norm": 0.03722948208451271,
      "learning_rate": 0.2894274062574437,
      "loss": 0.0673,
      "num_input_tokens_seen": 1346576,
      "step": 4810
    },
    {
      "epoch": 53.5,
      "grad_norm": 0.012150808237493038,
      "learning_rate": 0.2894056724731554,
      "loss": 0.0894,
      "num_input_tokens_seen": 1348016,
      "step": 4815
    },
    {
      "epoch": 53.55555555555556,
      "grad_norm": 0.005334048066288233,
      "learning_rate": 0.28938391719076056,
      "loss": 0.0643,
      "num_input_tokens_seen": 1349408,
      "step": 4820
    },
    {
      "epoch": 53.611111111111114,
      "grad_norm": 0.012316511943936348,
      "learning_rate": 0.28936214041361413,
      "loss": 0.0743,
      "num_input_tokens_seen": 1350816,
      "step": 4825
    },
    {
      "epoch": 53.666666666666664,
      "grad_norm": 0.012062269262969494,
      "learning_rate": 0.2893403421450743,
      "loss": 0.0591,
      "num_input_tokens_seen": 1352176,
      "step": 4830
    },
    {
      "epoch": 53.72222222222222,
      "grad_norm": 0.008470937609672546,
      "learning_rate": 0.2893185223885026,
      "loss": 0.025,
      "num_input_tokens_seen": 1353552,
      "step": 4835
    },
    {
      "epoch": 53.77777777777778,
      "grad_norm": 0.0008591145160607994,
      "learning_rate": 0.289296681147264,
      "loss": 0.0121,
      "num_input_tokens_seen": 1354928,
      "step": 4840
    },
    {
      "epoch": 53.833333333333336,
      "grad_norm": 0.03557891771197319,
      "learning_rate": 0.28927481842472663,
      "loss": 0.0535,
      "num_input_tokens_seen": 1356336,
      "step": 4845
    },
    {
      "epoch": 53.888888888888886,
      "grad_norm": 0.001330534229055047,
      "learning_rate": 0.28925293422426207,
      "loss": 0.0087,
      "num_input_tokens_seen": 1357776,
      "step": 4850
    },
    {
      "epoch": 53.94444444444444,
      "grad_norm": 0.0009261758532375097,
      "learning_rate": 0.28923102854924504,
      "loss": 0.0155,
      "num_input_tokens_seen": 1359184,
      "step": 4855
    },
    {
      "epoch": 54.0,
      "grad_norm": 0.03090188466012478,
      "learning_rate": 0.2892091014030537,
      "loss": 0.0906,
      "num_input_tokens_seen": 1360592,
      "step": 4860
    },
    {
      "epoch": 54.05555555555556,
      "grad_norm": 0.00576817337423563,
      "learning_rate": 0.2891871527890696,
      "loss": 0.0251,
      "num_input_tokens_seen": 1361936,
      "step": 4865
    },
    {
      "epoch": 54.111111111111114,
      "grad_norm": 0.00509682996198535,
      "learning_rate": 0.2891651827106773,
      "loss": 0.0237,
      "num_input_tokens_seen": 1363360,
      "step": 4870
    },
    {
      "epoch": 54.166666666666664,
      "grad_norm": 0.02168102189898491,
      "learning_rate": 0.2891431911712651,
      "loss": 0.0359,
      "num_input_tokens_seen": 1364784,
      "step": 4875
    },
    {
      "epoch": 54.22222222222222,
      "grad_norm": 0.005732239224016666,
      "learning_rate": 0.2891211781742241,
      "loss": 0.0149,
      "num_input_tokens_seen": 1366176,
      "step": 4880
    },
    {
      "epoch": 54.27777777777778,
      "grad_norm": 0.006400665268301964,
      "learning_rate": 0.2890991437229492,
      "loss": 0.0129,
      "num_input_tokens_seen": 1367568,
      "step": 4885
    },
    {
      "epoch": 54.333333333333336,
      "grad_norm": 0.0031840745359659195,
      "learning_rate": 0.2890770878208383,
      "loss": 0.0092,
      "num_input_tokens_seen": 1368944,
      "step": 4890
    },
    {
      "epoch": 54.388888888888886,
      "grad_norm": 0.02088986337184906,
      "learning_rate": 0.28905501047129273,
      "loss": 0.0305,
      "num_input_tokens_seen": 1370352,
      "step": 4895
    },
    {
      "epoch": 54.44444444444444,
      "grad_norm": 0.03072499856352806,
      "learning_rate": 0.289032911677717,
      "loss": 0.0275,
      "num_input_tokens_seen": 1371760,
      "step": 4900
    },
    {
      "epoch": 54.5,
      "grad_norm": 0.0006099167512729764,
      "learning_rate": 0.28901079144351915,
      "loss": 0.0322,
      "num_input_tokens_seen": 1373168,
      "step": 4905
    },
    {
      "epoch": 54.55555555555556,
      "grad_norm": 0.0002950042253360152,
      "learning_rate": 0.2889886497721103,
      "loss": 0.0628,
      "num_input_tokens_seen": 1374544,
      "step": 4910
    },
    {
      "epoch": 54.611111111111114,
      "grad_norm": 0.003491449635475874,
      "learning_rate": 0.28896648666690505,
      "loss": 0.04,
      "num_input_tokens_seen": 1375936,
      "step": 4915
    },
    {
      "epoch": 54.666666666666664,
      "grad_norm": 0.004152149427682161,
      "learning_rate": 0.2889443021313212,
      "loss": 0.0263,
      "num_input_tokens_seen": 1377344,
      "step": 4920
    },
    {
      "epoch": 54.72222222222222,
      "grad_norm": 0.01029179897159338,
      "learning_rate": 0.28892209616877984,
      "loss": 0.0255,
      "num_input_tokens_seen": 1378752,
      "step": 4925
    },
    {
      "epoch": 54.77777777777778,
      "grad_norm": 0.005093003157526255,
      "learning_rate": 0.28889986878270546,
      "loss": 0.0174,
      "num_input_tokens_seen": 1380112,
      "step": 4930
    },
    {
      "epoch": 54.833333333333336,
      "grad_norm": 0.0022194001358002424,
      "learning_rate": 0.28887761997652583,
      "loss": 0.0146,
      "num_input_tokens_seen": 1381536,
      "step": 4935
    },
    {
      "epoch": 54.888888888888886,
      "grad_norm": 0.02759363129734993,
      "learning_rate": 0.2888553497536719,
      "loss": 0.0352,
      "num_input_tokens_seen": 1382944,
      "step": 4940
    },
    {
      "epoch": 54.94444444444444,
      "grad_norm": 0.027272364124655724,
      "learning_rate": 0.2888330581175781,
      "loss": 0.0164,
      "num_input_tokens_seen": 1384384,
      "step": 4945
    },
    {
      "epoch": 55.0,
      "grad_norm": 0.0028132558800280094,
      "learning_rate": 0.28881074507168203,
      "loss": 0.0136,
      "num_input_tokens_seen": 1385760,
      "step": 4950
    },
    {
      "epoch": 55.05555555555556,
      "grad_norm": 0.0006485749618150294,
      "learning_rate": 0.2887884106194247,
      "loss": 0.0018,
      "num_input_tokens_seen": 1387136,
      "step": 4955
    },
    {
      "epoch": 55.111111111111114,
      "grad_norm": 0.0006209530401974916,
      "learning_rate": 0.28876605476425027,
      "loss": 0.0104,
      "num_input_tokens_seen": 1388560,
      "step": 4960
    },
    {
      "epoch": 55.166666666666664,
      "grad_norm": 0.0007403910858556628,
      "learning_rate": 0.2887436775096064,
      "loss": 0.0126,
      "num_input_tokens_seen": 1389952,
      "step": 4965
    },
    {
      "epoch": 55.22222222222222,
      "grad_norm": 0.00015948763757478446,
      "learning_rate": 0.2887212788589439,
      "loss": 0.0321,
      "num_input_tokens_seen": 1391344,
      "step": 4970
    },
    {
      "epoch": 55.27777777777778,
      "grad_norm": 0.028178153559565544,
      "learning_rate": 0.2886988588157169,
      "loss": 0.1532,
      "num_input_tokens_seen": 1392752,
      "step": 4975
    },
    {
      "epoch": 55.333333333333336,
      "grad_norm": 0.01612267643213272,
      "learning_rate": 0.28867641738338284,
      "loss": 0.0413,
      "num_input_tokens_seen": 1394112,
      "step": 4980
    },
    {
      "epoch": 55.388888888888886,
      "grad_norm": 0.021878251805901527,
      "learning_rate": 0.2886539545654026,
      "loss": 0.0442,
      "num_input_tokens_seen": 1395520,
      "step": 4985
    },
    {
      "epoch": 55.44444444444444,
      "grad_norm": 0.002040211809799075,
      "learning_rate": 0.28863147036524006,
      "loss": 0.0286,
      "num_input_tokens_seen": 1396960,
      "step": 4990
    },
    {
      "epoch": 55.5,
      "grad_norm": 0.014165718108415604,
      "learning_rate": 0.2886089647863626,
      "loss": 0.0186,
      "num_input_tokens_seen": 1398416,
      "step": 4995
    },
    {
      "epoch": 55.55555555555556,
      "grad_norm": 0.00020756651065312326,
      "learning_rate": 0.288586437832241,
      "loss": 0.0371,
      "num_input_tokens_seen": 1399856,
      "step": 5000
    },
    {
      "epoch": 55.55555555555556,
      "eval_loss": 0.5647741556167603,
      "eval_runtime": 1.1941,
      "eval_samples_per_second": 33.497,
      "eval_steps_per_second": 16.748,
      "num_input_tokens_seen": 1399856,
      "step": 5000
    },
    {
      "epoch": 55.611111111111114,
      "grad_norm": 0.03609771654009819,
      "learning_rate": 0.28856388950634904,
      "loss": 0.0557,
      "num_input_tokens_seen": 1401264,
      "step": 5005
    },
    {
      "epoch": 55.666666666666664,
      "grad_norm": 0.012119943276047707,
      "learning_rate": 0.288541319812164,
      "loss": 0.0346,
      "num_input_tokens_seen": 1402656,
      "step": 5010
    },
    {
      "epoch": 55.72222222222222,
      "grad_norm": 0.0012671237345784903,
      "learning_rate": 0.2885187287531665,
      "loss": 0.0081,
      "num_input_tokens_seen": 1404032,
      "step": 5015
    },
    {
      "epoch": 55.77777777777778,
      "grad_norm": 0.0009512195247225463,
      "learning_rate": 0.2884961163328402,
      "loss": 0.0182,
      "num_input_tokens_seen": 1405424,
      "step": 5020
    },
    {
      "epoch": 55.833333333333336,
      "grad_norm": 0.0006863231537863612,
      "learning_rate": 0.28847348255467237,
      "loss": 0.0173,
      "num_input_tokens_seen": 1406800,
      "step": 5025
    },
    {
      "epoch": 55.888888888888886,
      "grad_norm": 0.012187965214252472,
      "learning_rate": 0.28845082742215333,
      "loss": 0.037,
      "num_input_tokens_seen": 1408192,
      "step": 5030
    },
    {
      "epoch": 55.94444444444444,
      "grad_norm": 0.022489402443170547,
      "learning_rate": 0.2884281509387769,
      "loss": 0.044,
      "num_input_tokens_seen": 1409552,
      "step": 5035
    },
    {
      "epoch": 56.0,
      "grad_norm": 0.03114420175552368,
      "learning_rate": 0.2884054531080399,
      "loss": 0.0768,
      "num_input_tokens_seen": 1410992,
      "step": 5040
    },
    {
      "epoch": 56.05555555555556,
      "grad_norm": 0.0005339816561900079,
      "learning_rate": 0.28838273393344277,
      "loss": 0.0042,
      "num_input_tokens_seen": 1412400,
      "step": 5045
    },
    {
      "epoch": 56.111111111111114,
      "grad_norm": 0.0009310201276093721,
      "learning_rate": 0.288359993418489,
      "loss": 0.0855,
      "num_input_tokens_seen": 1413792,
      "step": 5050
    },
    {
      "epoch": 56.166666666666664,
      "grad_norm": 0.0012949504889547825,
      "learning_rate": 0.28833723156668556,
      "loss": 0.0139,
      "num_input_tokens_seen": 1415200,
      "step": 5055
    },
    {
      "epoch": 56.22222222222222,
      "grad_norm": 0.002935689641162753,
      "learning_rate": 0.2883144483815425,
      "loss": 0.102,
      "num_input_tokens_seen": 1416608,
      "step": 5060
    },
    {
      "epoch": 56.27777777777778,
      "grad_norm": 0.01062070019543171,
      "learning_rate": 0.28829164386657335,
      "loss": 0.031,
      "num_input_tokens_seen": 1418000,
      "step": 5065
    },
    {
      "epoch": 56.333333333333336,
      "grad_norm": 0.005923325661569834,
      "learning_rate": 0.28826881802529486,
      "loss": 0.0264,
      "num_input_tokens_seen": 1419376,
      "step": 5070
    },
    {
      "epoch": 56.388888888888886,
      "grad_norm": 0.0009538491722196341,
      "learning_rate": 0.28824597086122705,
      "loss": 0.021,
      "num_input_tokens_seen": 1420752,
      "step": 5075
    },
    {
      "epoch": 56.44444444444444,
      "grad_norm": 0.005777293350547552,
      "learning_rate": 0.28822310237789317,
      "loss": 0.0174,
      "num_input_tokens_seen": 1422112,
      "step": 5080
    },
    {
      "epoch": 56.5,
      "grad_norm": 0.0016271299682557583,
      "learning_rate": 0.2882002125788199,
      "loss": 0.0426,
      "num_input_tokens_seen": 1423536,
      "step": 5085
    },
    {
      "epoch": 56.55555555555556,
      "grad_norm": 0.00084514613263309,
      "learning_rate": 0.2881773014675371,
      "loss": 0.0212,
      "num_input_tokens_seen": 1424944,
      "step": 5090
    },
    {
      "epoch": 56.611111111111114,
      "grad_norm": 0.01207202859222889,
      "learning_rate": 0.288154369047578,
      "loss": 0.0455,
      "num_input_tokens_seen": 1426416,
      "step": 5095
    },
    {
      "epoch": 56.666666666666664,
      "grad_norm": 0.004033952485769987,
      "learning_rate": 0.28813141532247905,
      "loss": 0.0154,
      "num_input_tokens_seen": 1427856,
      "step": 5100
    },
    {
      "epoch": 56.72222222222222,
      "grad_norm": 0.002274486469104886,
      "learning_rate": 0.28810844029578,
      "loss": 0.0652,
      "num_input_tokens_seen": 1429168,
      "step": 5105
    },
    {
      "epoch": 56.77777777777778,
      "grad_norm": 0.008109740912914276,
      "learning_rate": 0.2880854439710238,
      "loss": 0.0551,
      "num_input_tokens_seen": 1430576,
      "step": 5110
    },
    {
      "epoch": 56.833333333333336,
      "grad_norm": 0.010049001313745975,
      "learning_rate": 0.28806242635175694,
      "loss": 0.0247,
      "num_input_tokens_seen": 1431952,
      "step": 5115
    },
    {
      "epoch": 56.888888888888886,
      "grad_norm": 0.03248031064867973,
      "learning_rate": 0.2880393874415289,
      "loss": 0.0478,
      "num_input_tokens_seen": 1433344,
      "step": 5120
    },
    {
      "epoch": 56.94444444444444,
      "grad_norm": 0.004580209497362375,
      "learning_rate": 0.2880163272438926,
      "loss": 0.0395,
      "num_input_tokens_seen": 1434752,
      "step": 5125
    },
    {
      "epoch": 57.0,
      "grad_norm": 0.0023286696523427963,
      "learning_rate": 0.2879932457624042,
      "loss": 0.0101,
      "num_input_tokens_seen": 1436160,
      "step": 5130
    },
    {
      "epoch": 57.05555555555556,
      "grad_norm": 0.00038812035927549005,
      "learning_rate": 0.2879701430006232,
      "loss": 0.0092,
      "num_input_tokens_seen": 1437600,
      "step": 5135
    },
    {
      "epoch": 57.111111111111114,
      "grad_norm": 0.00242378911934793,
      "learning_rate": 0.28794701896211233,
      "loss": 0.0035,
      "num_input_tokens_seen": 1439024,
      "step": 5140
    },
    {
      "epoch": 57.166666666666664,
      "grad_norm": 0.0008851406164467335,
      "learning_rate": 0.28792387365043753,
      "loss": 0.0095,
      "num_input_tokens_seen": 1440432,
      "step": 5145
    },
    {
      "epoch": 57.22222222222222,
      "grad_norm": 0.0018554887501522899,
      "learning_rate": 0.28790070706916815,
      "loss": 0.003,
      "num_input_tokens_seen": 1441824,
      "step": 5150
    },
    {
      "epoch": 57.27777777777778,
      "grad_norm": 0.0006175789749249816,
      "learning_rate": 0.2878775192218768,
      "loss": 0.005,
      "num_input_tokens_seen": 1443200,
      "step": 5155
    },
    {
      "epoch": 57.333333333333336,
      "grad_norm": 0.01187864039093256,
      "learning_rate": 0.2878543101121393,
      "loss": 0.0099,
      "num_input_tokens_seen": 1444592,
      "step": 5160
    },
    {
      "epoch": 57.388888888888886,
      "grad_norm": 0.011936604976654053,
      "learning_rate": 0.28783107974353483,
      "loss": 0.01,
      "num_input_tokens_seen": 1446016,
      "step": 5165
    },
    {
      "epoch": 57.44444444444444,
      "grad_norm": 0.0015208390541374683,
      "learning_rate": 0.2878078281196457,
      "loss": 0.0079,
      "num_input_tokens_seen": 1447408,
      "step": 5170
    },
    {
      "epoch": 57.5,
      "grad_norm": 0.0022480706684291363,
      "learning_rate": 0.28778455524405777,
      "loss": 0.0416,
      "num_input_tokens_seen": 1448800,
      "step": 5175
    },
    {
      "epoch": 57.55555555555556,
      "grad_norm": 0.011397106572985649,
      "learning_rate": 0.2877612611203598,
      "loss": 0.0278,
      "num_input_tokens_seen": 1450176,
      "step": 5180
    },
    {
      "epoch": 57.611111111111114,
      "grad_norm": 0.0003961942857131362,
      "learning_rate": 0.28773794575214423,
      "loss": 0.0157,
      "num_input_tokens_seen": 1451568,
      "step": 5185
    },
    {
      "epoch": 57.666666666666664,
      "grad_norm": 0.006891903001815081,
      "learning_rate": 0.28771460914300645,
      "loss": 0.0171,
      "num_input_tokens_seen": 1452992,
      "step": 5190
    },
    {
      "epoch": 57.72222222222222,
      "grad_norm": 0.00041903360397554934,
      "learning_rate": 0.2876912512965454,
      "loss": 0.0159,
      "num_input_tokens_seen": 1454416,
      "step": 5195
    },
    {
      "epoch": 57.77777777777778,
      "grad_norm": 0.016581587493419647,
      "learning_rate": 0.287667872216363,
      "loss": 0.0138,
      "num_input_tokens_seen": 1455808,
      "step": 5200
    },
    {
      "epoch": 57.77777777777778,
      "eval_loss": 0.520499050617218,
      "eval_runtime": 1.1885,
      "eval_samples_per_second": 33.656,
      "eval_steps_per_second": 16.828,
      "num_input_tokens_seen": 1455808,
      "step": 5200
    },
    {
      "epoch": 57.833333333333336,
      "grad_norm": 0.0005689059616997838,
      "learning_rate": 0.2876444719060647,
      "loss": 0.0132,
      "num_input_tokens_seen": 1457200,
      "step": 5205
    },
    {
      "epoch": 57.888888888888886,
      "grad_norm": 0.002515150234103203,
      "learning_rate": 0.287621050369259,
      "loss": 0.0105,
      "num_input_tokens_seen": 1458560,
      "step": 5210
    },
    {
      "epoch": 57.94444444444444,
      "grad_norm": 0.004688643850386143,
      "learning_rate": 0.28759760760955794,
      "loss": 0.0052,
      "num_input_tokens_seen": 1460000,
      "step": 5215
    },
    {
      "epoch": 58.0,
      "grad_norm": 0.0008744586957618594,
      "learning_rate": 0.2875741436305766,
      "loss": 0.0041,
      "num_input_tokens_seen": 1461440,
      "step": 5220
    },
    {
      "epoch": 58.05555555555556,
      "grad_norm": 0.0003255280898883939,
      "learning_rate": 0.28755065843593347,
      "loss": 0.0044,
      "num_input_tokens_seen": 1462800,
      "step": 5225
    },
    {
      "epoch": 58.111111111111114,
      "grad_norm": 0.00022061228810343891,
      "learning_rate": 0.2875271520292502,
      "loss": 0.0031,
      "num_input_tokens_seen": 1464192,
      "step": 5230
    },
    {
      "epoch": 58.166666666666664,
      "grad_norm": 0.0001287984341615811,
      "learning_rate": 0.28750362441415184,
      "loss": 0.0181,
      "num_input_tokens_seen": 1465568,
      "step": 5235
    },
    {
      "epoch": 58.22222222222222,
      "grad_norm": 0.00020179091370664537,
      "learning_rate": 0.28748007559426664,
      "loss": 0.0021,
      "num_input_tokens_seen": 1466976,
      "step": 5240
    },
    {
      "epoch": 58.27777777777778,
      "grad_norm": 8.052181328821462e-06,
      "learning_rate": 0.2874565055732261,
      "loss": 0.0058,
      "num_input_tokens_seen": 1468368,
      "step": 5245
    },
    {
      "epoch": 58.333333333333336,
      "grad_norm": 2.3042141037876718e-05,
      "learning_rate": 0.28743291435466495,
      "loss": 0.001,
      "num_input_tokens_seen": 1469760,
      "step": 5250
    },
    {
      "epoch": 58.388888888888886,
      "grad_norm": 0.0038408252876251936,
      "learning_rate": 0.2874093019422214,
      "loss": 0.0053,
      "num_input_tokens_seen": 1471152,
      "step": 5255
    },
    {
      "epoch": 58.44444444444444,
      "grad_norm": 0.0005868284497410059,
      "learning_rate": 0.28738566833953666,
      "loss": 0.0032,
      "num_input_tokens_seen": 1472608,
      "step": 5260
    },
    {
      "epoch": 58.5,
      "grad_norm": 0.002067601541057229,
      "learning_rate": 0.28736201355025537,
      "loss": 0.0024,
      "num_input_tokens_seen": 1474016,
      "step": 5265
    },
    {
      "epoch": 58.55555555555556,
      "grad_norm": 0.00015700455696787685,
      "learning_rate": 0.28733833757802535,
      "loss": 0.0027,
      "num_input_tokens_seen": 1475424,
      "step": 5270
    },
    {
      "epoch": 58.611111111111114,
      "grad_norm": 0.0008452918264083564,
      "learning_rate": 0.28731464042649785,
      "loss": 0.0013,
      "num_input_tokens_seen": 1476832,
      "step": 5275
    },
    {
      "epoch": 58.666666666666664,
      "grad_norm": 4.8875906941248104e-05,
      "learning_rate": 0.2872909220993271,
      "loss": 0.0016,
      "num_input_tokens_seen": 1478240,
      "step": 5280
    },
    {
      "epoch": 58.72222222222222,
      "grad_norm": 8.55427497299388e-05,
      "learning_rate": 0.287267182600171,
      "loss": 0.0003,
      "num_input_tokens_seen": 1479648,
      "step": 5285
    },
    {
      "epoch": 58.77777777777778,
      "grad_norm": 6.0232832765905187e-05,
      "learning_rate": 0.2872434219326902,
      "loss": 0.0033,
      "num_input_tokens_seen": 1481088,
      "step": 5290
    },
    {
      "epoch": 58.833333333333336,
      "grad_norm": 0.006356652360409498,
      "learning_rate": 0.28721964010054907,
      "loss": 0.0031,
      "num_input_tokens_seen": 1482512,
      "step": 5295
    },
    {
      "epoch": 58.888888888888886,
      "grad_norm": 0.0006605468806810677,
      "learning_rate": 0.28719583710741503,
      "loss": 0.0004,
      "num_input_tokens_seen": 1483888,
      "step": 5300
    },
    {
      "epoch": 58.94444444444444,
      "grad_norm": 0.001332515967078507,
      "learning_rate": 0.28717201295695877,
      "loss": 0.0026,
      "num_input_tokens_seen": 1485280,
      "step": 5305
    },
    {
      "epoch": 59.0,
      "grad_norm": 0.001248084707185626,
      "learning_rate": 0.28714816765285434,
      "loss": 0.0094,
      "num_input_tokens_seen": 1486688,
      "step": 5310
    },
    {
      "epoch": 59.05555555555556,
      "grad_norm": 0.0001445368689019233,
      "learning_rate": 0.28712430119877896,
      "loss": 0.0003,
      "num_input_tokens_seen": 1488080,
      "step": 5315
    },
    {
      "epoch": 59.111111111111114,
      "grad_norm": 0.0030829168390482664,
      "learning_rate": 0.28710041359841304,
      "loss": 0.002,
      "num_input_tokens_seen": 1489472,
      "step": 5320
    },
    {
      "epoch": 59.166666666666664,
      "grad_norm": 0.005915164947509766,
      "learning_rate": 0.28707650485544056,
      "loss": 0.0015,
      "num_input_tokens_seen": 1490880,
      "step": 5325
    },
    {
      "epoch": 59.22222222222222,
      "grad_norm": 3.2891632145037875e-05,
      "learning_rate": 0.28705257497354836,
      "loss": 0.0002,
      "num_input_tokens_seen": 1492240,
      "step": 5330
    },
    {
      "epoch": 59.27777777777778,
      "grad_norm": 0.001771969604305923,
      "learning_rate": 0.28702862395642675,
      "loss": 0.0006,
      "num_input_tokens_seen": 1493664,
      "step": 5335
    },
    {
      "epoch": 59.333333333333336,
      "grad_norm": 1.946365591720678e-05,
      "learning_rate": 0.28700465180776935,
      "loss": 0.0005,
      "num_input_tokens_seen": 1495072,
      "step": 5340
    },
    {
      "epoch": 59.388888888888886,
      "grad_norm": 0.00039472171920351684,
      "learning_rate": 0.2869806585312729,
      "loss": 0.0009,
      "num_input_tokens_seen": 1496512,
      "step": 5345
    },
    {
      "epoch": 59.44444444444444,
      "grad_norm": 0.00040285862633027136,
      "learning_rate": 0.28695664413063754,
      "loss": 0.0002,
      "num_input_tokens_seen": 1497904,
      "step": 5350
    },
    {
      "epoch": 59.5,
      "grad_norm": 5.508664980879985e-05,
      "learning_rate": 0.28693260860956654,
      "loss": 0.0003,
      "num_input_tokens_seen": 1499280,
      "step": 5355
    },
    {
      "epoch": 59.55555555555556,
      "grad_norm": 0.000118862277304288,
      "learning_rate": 0.2869085519717665,
      "loss": 0.0001,
      "num_input_tokens_seen": 1500688,
      "step": 5360
    },
    {
      "epoch": 59.611111111111114,
      "grad_norm": 1.5322566468967125e-05,
      "learning_rate": 0.28688447422094726,
      "loss": 0.0002,
      "num_input_tokens_seen": 1502112,
      "step": 5365
    },
    {
      "epoch": 59.666666666666664,
      "grad_norm": 0.00018097452993970364,
      "learning_rate": 0.2868603753608219,
      "loss": 0.0003,
      "num_input_tokens_seen": 1503520,
      "step": 5370
    },
    {
      "epoch": 59.72222222222222,
      "grad_norm": 3.68160976904619e-06,
      "learning_rate": 0.28683625539510665,
      "loss": 0.0001,
      "num_input_tokens_seen": 1504928,
      "step": 5375
    },
    {
      "epoch": 59.77777777777778,
      "grad_norm": 7.197549712145701e-05,
      "learning_rate": 0.28681211432752135,
      "loss": 0.0001,
      "num_input_tokens_seen": 1506288,
      "step": 5380
    },
    {
      "epoch": 59.833333333333336,
      "grad_norm": 2.5038338208105415e-05,
      "learning_rate": 0.2867879521617887,
      "loss": 0.0003,
      "num_input_tokens_seen": 1507712,
      "step": 5385
    },
    {
      "epoch": 59.888888888888886,
      "grad_norm": 6.49143330520019e-05,
      "learning_rate": 0.28676376890163485,
      "loss": 0.0015,
      "num_input_tokens_seen": 1509088,
      "step": 5390
    },
    {
      "epoch": 59.94444444444444,
      "grad_norm": 0.00010060891509056091,
      "learning_rate": 0.2867395645507891,
      "loss": 0.0001,
      "num_input_tokens_seen": 1510464,
      "step": 5395
    },
    {
      "epoch": 60.0,
      "grad_norm": 0.00026632149820216,
      "learning_rate": 0.2867153391129842,
      "loss": 0.0002,
      "num_input_tokens_seen": 1511856,
      "step": 5400
    },
    {
      "epoch": 60.0,
      "eval_loss": 0.7807838320732117,
      "eval_runtime": 1.1768,
      "eval_samples_per_second": 33.989,
      "eval_steps_per_second": 16.995,
      "num_input_tokens_seen": 1511856,
      "step": 5400
    },
    {
      "epoch": 60.05555555555556,
      "grad_norm": 1.0033960279542953e-05,
      "learning_rate": 0.28669109259195585,
      "loss": 0.0002,
      "num_input_tokens_seen": 1513280,
      "step": 5405
    },
    {
      "epoch": 60.111111111111114,
      "grad_norm": 8.31927354738582e-06,
      "learning_rate": 0.2866668249914433,
      "loss": 0.0001,
      "num_input_tokens_seen": 1514656,
      "step": 5410
    },
    {
      "epoch": 60.166666666666664,
      "grad_norm": 5.618717841571197e-05,
      "learning_rate": 0.2866425363151889,
      "loss": 0.0003,
      "num_input_tokens_seen": 1516064,
      "step": 5415
    },
    {
      "epoch": 60.22222222222222,
      "grad_norm": 7.021682904451154e-06,
      "learning_rate": 0.2866182265669382,
      "loss": 0.0001,
      "num_input_tokens_seen": 1517456,
      "step": 5420
    },
    {
      "epoch": 60.27777777777778,
      "grad_norm": 6.5445838117739186e-06,
      "learning_rate": 0.28659389575044014,
      "loss": 0.0002,
      "num_input_tokens_seen": 1518832,
      "step": 5425
    },
    {
      "epoch": 60.333333333333336,
      "grad_norm": 0.00010093834134750068,
      "learning_rate": 0.28656954386944683,
      "loss": 0.0001,
      "num_input_tokens_seen": 1520256,
      "step": 5430
    },
    {
      "epoch": 60.388888888888886,
      "grad_norm": 0.00010371638927608728,
      "learning_rate": 0.28654517092771353,
      "loss": 0.0001,
      "num_input_tokens_seen": 1521632,
      "step": 5435
    },
    {
      "epoch": 60.44444444444444,
      "grad_norm": 7.039368210826069e-05,
      "learning_rate": 0.286520776928999,
      "loss": 0.0001,
      "num_input_tokens_seen": 1523056,
      "step": 5440
    },
    {
      "epoch": 60.5,
      "grad_norm": 1.909182537929155e-05,
      "learning_rate": 0.286496361877065,
      "loss": 0.0001,
      "num_input_tokens_seen": 1524480,
      "step": 5445
    },
    {
      "epoch": 60.55555555555556,
      "grad_norm": 5.249466630630195e-05,
      "learning_rate": 0.28647192577567676,
      "loss": 0.0001,
      "num_input_tokens_seen": 1525920,
      "step": 5450
    },
    {
      "epoch": 60.611111111111114,
      "grad_norm": 8.892318146536127e-05,
      "learning_rate": 0.28644746862860254,
      "loss": 0.0001,
      "num_input_tokens_seen": 1527344,
      "step": 5455
    },
    {
      "epoch": 60.666666666666664,
      "grad_norm": 4.8312886065104976e-05,
      "learning_rate": 0.2864229904396139,
      "loss": 0.0002,
      "num_input_tokens_seen": 1528704,
      "step": 5460
    },
    {
      "epoch": 60.72222222222222,
      "grad_norm": 7.42434203857556e-05,
      "learning_rate": 0.28639849121248573,
      "loss": 0.0001,
      "num_input_tokens_seen": 1530080,
      "step": 5465
    },
    {
      "epoch": 60.77777777777778,
      "grad_norm": 1.0577464308880735e-05,
      "learning_rate": 0.28637397095099615,
      "loss": 0.0001,
      "num_input_tokens_seen": 1531440,
      "step": 5470
    },
    {
      "epoch": 60.833333333333336,
      "grad_norm": 8.405082553508691e-06,
      "learning_rate": 0.28634942965892646,
      "loss": 0.0,
      "num_input_tokens_seen": 1532832,
      "step": 5475
    },
    {
      "epoch": 60.888888888888886,
      "grad_norm": 3.36396878992673e-05,
      "learning_rate": 0.28632486734006124,
      "loss": 0.0,
      "num_input_tokens_seen": 1534224,
      "step": 5480
    },
    {
      "epoch": 60.94444444444444,
      "grad_norm": 2.227877666882705e-05,
      "learning_rate": 0.28630028399818835,
      "loss": 0.0001,
      "num_input_tokens_seen": 1535632,
      "step": 5485
    },
    {
      "epoch": 61.0,
      "grad_norm": 2.0911975298076868e-05,
      "learning_rate": 0.2862756796370987,
      "loss": 0.0001,
      "num_input_tokens_seen": 1537008,
      "step": 5490
    },
    {
      "epoch": 61.05555555555556,
      "grad_norm": 1.3748310720984591e-06,
      "learning_rate": 0.2862510542605868,
      "loss": 0.0001,
      "num_input_tokens_seen": 1538432,
      "step": 5495
    },
    {
      "epoch": 61.111111111111114,
      "grad_norm": 1.961952330020722e-05,
      "learning_rate": 0.2862264078724501,
      "loss": 0.0001,
      "num_input_tokens_seen": 1539840,
      "step": 5500
    },
    {
      "epoch": 61.166666666666664,
      "grad_norm": 8.623833127785474e-05,
      "learning_rate": 0.28620174047648933,
      "loss": 0.0001,
      "num_input_tokens_seen": 1541248,
      "step": 5505
    },
    {
      "epoch": 61.22222222222222,
      "grad_norm": 1.5199788322206587e-05,
      "learning_rate": 0.2861770520765086,
      "loss": 0.0,
      "num_input_tokens_seen": 1542688,
      "step": 5510
    },
    {
      "epoch": 61.27777777777778,
      "grad_norm": 1.0274155101797078e-05,
      "learning_rate": 0.2861523426763151,
      "loss": 0.0,
      "num_input_tokens_seen": 1544128,
      "step": 5515
    },
    {
      "epoch": 61.333333333333336,
      "grad_norm": 1.2979934581380803e-05,
      "learning_rate": 0.2861276122797194,
      "loss": 0.0001,
      "num_input_tokens_seen": 1545504,
      "step": 5520
    },
    {
      "epoch": 61.388888888888886,
      "grad_norm": 3.987317995779449e-06,
      "learning_rate": 0.28610286089053516,
      "loss": 0.0001,
      "num_input_tokens_seen": 1546864,
      "step": 5525
    },
    {
      "epoch": 61.44444444444444,
      "grad_norm": 4.638698555936571e-06,
      "learning_rate": 0.28607808851257943,
      "loss": 0.0001,
      "num_input_tokens_seen": 1548272,
      "step": 5530
    },
    {
      "epoch": 61.5,
      "grad_norm": 7.187552000686992e-06,
      "learning_rate": 0.28605329514967237,
      "loss": 0.0001,
      "num_input_tokens_seen": 1549648,
      "step": 5535
    },
    {
      "epoch": 61.55555555555556,
      "grad_norm": 4.148333391640335e-05,
      "learning_rate": 0.2860284808056374,
      "loss": 0.0001,
      "num_input_tokens_seen": 1551072,
      "step": 5540
    },
    {
      "epoch": 61.611111111111114,
      "grad_norm": 8.612682722741738e-05,
      "learning_rate": 0.28600364548430135,
      "loss": 0.0,
      "num_input_tokens_seen": 1552464,
      "step": 5545
    },
    {
      "epoch": 61.666666666666664,
      "grad_norm": 2.0623838281608187e-05,
      "learning_rate": 0.28597878918949393,
      "loss": 0.0001,
      "num_input_tokens_seen": 1553776,
      "step": 5550
    },
    {
      "epoch": 61.72222222222222,
      "grad_norm": 5.181270535103977e-05,
      "learning_rate": 0.2859539119250485,
      "loss": 0.0001,
      "num_input_tokens_seen": 1555216,
      "step": 5555
    },
    {
      "epoch": 61.77777777777778,
      "grad_norm": 5.044814315624535e-05,
      "learning_rate": 0.2859290136948013,
      "loss": 0.0001,
      "num_input_tokens_seen": 1556608,
      "step": 5560
    },
    {
      "epoch": 61.833333333333336,
      "grad_norm": 1.963806789717637e-05,
      "learning_rate": 0.28590409450259197,
      "loss": 0.0001,
      "num_input_tokens_seen": 1558000,
      "step": 5565
    },
    {
      "epoch": 61.888888888888886,
      "grad_norm": 7.5220336839265656e-06,
      "learning_rate": 0.28587915435226346,
      "loss": 0.0001,
      "num_input_tokens_seen": 1559408,
      "step": 5570
    },
    {
      "epoch": 61.94444444444444,
      "grad_norm": 1.4911254766047932e-05,
      "learning_rate": 0.2858541932476617,
      "loss": 0.0001,
      "num_input_tokens_seen": 1560832,
      "step": 5575
    },
    {
      "epoch": 62.0,
      "grad_norm": 4.843464012083132e-06,
      "learning_rate": 0.2858292111926361,
      "loss": 0.0001,
      "num_input_tokens_seen": 1562240,
      "step": 5580
    },
    {
      "epoch": 62.05555555555556,
      "grad_norm": 8.662903383083176e-06,
      "learning_rate": 0.28580420819103924,
      "loss": 0.0,
      "num_input_tokens_seen": 1563680,
      "step": 5585
    },
    {
      "epoch": 62.111111111111114,
      "grad_norm": 4.842783528147265e-05,
      "learning_rate": 0.2857791842467269,
      "loss": 0.0001,
      "num_input_tokens_seen": 1565056,
      "step": 5590
    },
    {
      "epoch": 62.166666666666664,
      "grad_norm": 2.686382686079014e-05,
      "learning_rate": 0.2857541393635579,
      "loss": 0.0001,
      "num_input_tokens_seen": 1566432,
      "step": 5595
    },
    {
      "epoch": 62.22222222222222,
      "grad_norm": 1.9071563656325452e-05,
      "learning_rate": 0.2857290735453948,
      "loss": 0.0001,
      "num_input_tokens_seen": 1567808,
      "step": 5600
    },
    {
      "epoch": 62.22222222222222,
      "eval_loss": 0.7838108539581299,
      "eval_runtime": 1.1844,
      "eval_samples_per_second": 33.772,
      "eval_steps_per_second": 16.886,
      "num_input_tokens_seen": 1567808,
      "step": 5600
    },
    {
      "epoch": 62.27777777777778,
      "grad_norm": 3.7628044537996175e-06,
      "learning_rate": 0.28570398679610276,
      "loss": 0.0001,
      "num_input_tokens_seen": 1569248,
      "step": 5605
    },
    {
      "epoch": 62.333333333333336,
      "grad_norm": 6.795009994675638e-06,
      "learning_rate": 0.2856788791195506,
      "loss": 0.0,
      "num_input_tokens_seen": 1570640,
      "step": 5610
    },
    {
      "epoch": 62.388888888888886,
      "grad_norm": 7.719069685663271e-07,
      "learning_rate": 0.28565375051961023,
      "loss": 0.0001,
      "num_input_tokens_seen": 1572032,
      "step": 5615
    },
    {
      "epoch": 62.44444444444444,
      "grad_norm": 1.329784845438553e-05,
      "learning_rate": 0.28562860100015686,
      "loss": 0.0,
      "num_input_tokens_seen": 1573456,
      "step": 5620
    },
    {
      "epoch": 62.5,
      "grad_norm": 3.2278829166898504e-05,
      "learning_rate": 0.2856034305650687,
      "loss": 0.0001,
      "num_input_tokens_seen": 1574896,
      "step": 5625
    },
    {
      "epoch": 62.55555555555556,
      "grad_norm": 5.684421466867207e-06,
      "learning_rate": 0.28557823921822756,
      "loss": 0.0,
      "num_input_tokens_seen": 1576320,
      "step": 5630
    },
    {
      "epoch": 62.611111111111114,
      "grad_norm": 1.5564641216769814e-05,
      "learning_rate": 0.2855530269635181,
      "loss": 0.0,
      "num_input_tokens_seen": 1577680,
      "step": 5635
    },
    {
      "epoch": 62.666666666666664,
      "grad_norm": 9.417138244316448e-06,
      "learning_rate": 0.2855277938048284,
      "loss": 0.0,
      "num_input_tokens_seen": 1579040,
      "step": 5640
    },
    {
      "epoch": 62.72222222222222,
      "grad_norm": 7.199110405053943e-05,
      "learning_rate": 0.2855025397460498,
      "loss": 0.0001,
      "num_input_tokens_seen": 1580432,
      "step": 5645
    },
    {
      "epoch": 62.77777777777778,
      "grad_norm": 3.2908294087974355e-05,
      "learning_rate": 0.28547726479107666,
      "loss": 0.0001,
      "num_input_tokens_seen": 1581872,
      "step": 5650
    },
    {
      "epoch": 62.833333333333336,
      "grad_norm": 7.86786858952837e-06,
      "learning_rate": 0.2854519689438068,
      "loss": 0.0001,
      "num_input_tokens_seen": 1583296,
      "step": 5655
    },
    {
      "epoch": 62.888888888888886,
      "grad_norm": 1.4318172361527104e-05,
      "learning_rate": 0.2854266522081412,
      "loss": 0.0,
      "num_input_tokens_seen": 1584688,
      "step": 5660
    },
    {
      "epoch": 62.94444444444444,
      "grad_norm": 4.7509598516626284e-05,
      "learning_rate": 0.28540131458798385,
      "loss": 0.0001,
      "num_input_tokens_seen": 1586096,
      "step": 5665
    },
    {
      "epoch": 63.0,
      "grad_norm": 1.8089742297888733e-05,
      "learning_rate": 0.28537595608724226,
      "loss": 0.0,
      "num_input_tokens_seen": 1587488,
      "step": 5670
    },
    {
      "epoch": 63.05555555555556,
      "grad_norm": 1.9561655790312216e-05,
      "learning_rate": 0.28535057670982705,
      "loss": 0.0,
      "num_input_tokens_seen": 1588880,
      "step": 5675
    },
    {
      "epoch": 63.111111111111114,
      "grad_norm": 1.049026832333766e-05,
      "learning_rate": 0.285325176459652,
      "loss": 0.0001,
      "num_input_tokens_seen": 1590272,
      "step": 5680
    },
    {
      "epoch": 63.166666666666664,
      "grad_norm": 5.3285534704627935e-06,
      "learning_rate": 0.28529975534063406,
      "loss": 0.0,
      "num_input_tokens_seen": 1591696,
      "step": 5685
    },
    {
      "epoch": 63.22222222222222,
      "grad_norm": 4.366530629340559e-05,
      "learning_rate": 0.2852743133566936,
      "loss": 0.0001,
      "num_input_tokens_seen": 1593024,
      "step": 5690
    },
    {
      "epoch": 63.27777777777778,
      "grad_norm": 9.190761375066359e-06,
      "learning_rate": 0.2852488505117541,
      "loss": 0.0,
      "num_input_tokens_seen": 1594432,
      "step": 5695
    },
    {
      "epoch": 63.333333333333336,
      "grad_norm": 1.4418001228477806e-06,
      "learning_rate": 0.28522336680974214,
      "loss": 0.0,
      "num_input_tokens_seen": 1595808,
      "step": 5700
    },
    {
      "epoch": 63.388888888888886,
      "grad_norm": 1.0803691111505032e-05,
      "learning_rate": 0.2851978622545877,
      "loss": 0.0,
      "num_input_tokens_seen": 1597216,
      "step": 5705
    },
    {
      "epoch": 63.44444444444444,
      "grad_norm": 5.5007098126225173e-05,
      "learning_rate": 0.285172336850224,
      "loss": 0.0001,
      "num_input_tokens_seen": 1598624,
      "step": 5710
    },
    {
      "epoch": 63.5,
      "grad_norm": 3.119937173323706e-05,
      "learning_rate": 0.2851467906005871,
      "loss": 0.0001,
      "num_input_tokens_seen": 1600000,
      "step": 5715
    },
    {
      "epoch": 63.55555555555556,
      "grad_norm": 6.956050128792413e-06,
      "learning_rate": 0.28512122350961683,
      "loss": 0.0,
      "num_input_tokens_seen": 1601392,
      "step": 5720
    },
    {
      "epoch": 63.611111111111114,
      "grad_norm": 3.94215476262616e-06,
      "learning_rate": 0.2850956355812559,
      "loss": 0.0,
      "num_input_tokens_seen": 1602768,
      "step": 5725
    },
    {
      "epoch": 63.666666666666664,
      "grad_norm": 1.7336169548798352e-05,
      "learning_rate": 0.28507002681945015,
      "loss": 0.0001,
      "num_input_tokens_seen": 1604160,
      "step": 5730
    },
    {
      "epoch": 63.72222222222222,
      "grad_norm": 1.381686070089927e-05,
      "learning_rate": 0.28504439722814895,
      "loss": 0.0,
      "num_input_tokens_seen": 1605584,
      "step": 5735
    },
    {
      "epoch": 63.77777777777778,
      "grad_norm": 1.0137713616131805e-05,
      "learning_rate": 0.28501874681130457,
      "loss": 0.0,
      "num_input_tokens_seen": 1607008,
      "step": 5740
    },
    {
      "epoch": 63.833333333333336,
      "grad_norm": 3.5308723909110995e-06,
      "learning_rate": 0.2849930755728727,
      "loss": 0.0,
      "num_input_tokens_seen": 1608400,
      "step": 5745
    },
    {
      "epoch": 63.888888888888886,
      "grad_norm": 7.14610132490634e-06,
      "learning_rate": 0.28496738351681217,
      "loss": 0.0,
      "num_input_tokens_seen": 1609808,
      "step": 5750
    },
    {
      "epoch": 63.94444444444444,
      "grad_norm": 5.5563677960890345e-06,
      "learning_rate": 0.284941670647085,
      "loss": 0.0,
      "num_input_tokens_seen": 1611232,
      "step": 5755
    },
    {
      "epoch": 64.0,
      "grad_norm": 1.9662698832689784e-05,
      "learning_rate": 0.2849159369676563,
      "loss": 0.0,
      "num_input_tokens_seen": 1612624,
      "step": 5760
    },
    {
      "epoch": 64.05555555555556,
      "grad_norm": 8.172115485649556e-06,
      "learning_rate": 0.2848901824824948,
      "loss": 0.0,
      "num_input_tokens_seen": 1614048,
      "step": 5765
    },
    {
      "epoch": 64.11111111111111,
      "grad_norm": 1.7218591210621526e-06,
      "learning_rate": 0.284864407195572,
      "loss": 0.0001,
      "num_input_tokens_seen": 1615408,
      "step": 5770
    },
    {
      "epoch": 64.16666666666667,
      "grad_norm": 1.9374130715732463e-05,
      "learning_rate": 0.28483861111086284,
      "loss": 0.0,
      "num_input_tokens_seen": 1616800,
      "step": 5775
    },
    {
      "epoch": 64.22222222222223,
      "grad_norm": 3.7684945709770545e-05,
      "learning_rate": 0.2848127942323453,
      "loss": 0.0,
      "num_input_tokens_seen": 1618192,
      "step": 5780
    },
    {
      "epoch": 64.27777777777777,
      "grad_norm": 9.101674550038297e-06,
      "learning_rate": 0.2847869565640007,
      "loss": 0.0,
      "num_input_tokens_seen": 1619568,
      "step": 5785
    },
    {
      "epoch": 64.33333333333333,
      "grad_norm": 1.6486777894897386e-05,
      "learning_rate": 0.2847610981098136,
      "loss": 0.0,
      "num_input_tokens_seen": 1620944,
      "step": 5790
    },
    {
      "epoch": 64.38888888888889,
      "grad_norm": 1.0057682629849296e-05,
      "learning_rate": 0.2847352188737716,
      "loss": 0.0,
      "num_input_tokens_seen": 1622384,
      "step": 5795
    },
    {
      "epoch": 64.44444444444444,
      "grad_norm": 1.2206310202600434e-05,
      "learning_rate": 0.2847093188598658,
      "loss": 0.0,
      "num_input_tokens_seen": 1623744,
      "step": 5800
    },
    {
      "epoch": 64.44444444444444,
      "eval_loss": 0.8039748072624207,
      "eval_runtime": 1.1836,
      "eval_samples_per_second": 33.796,
      "eval_steps_per_second": 16.898,
      "num_input_tokens_seen": 1623744,
      "step": 5800
    },
    {
      "epoch": 64.5,
      "grad_norm": 1.3958538147562649e-05,
      "learning_rate": 0.28468339807209003,
      "loss": 0.0,
      "num_input_tokens_seen": 1625152,
      "step": 5805
    },
    {
      "epoch": 64.55555555555556,
      "grad_norm": 1.130627197198919e-06,
      "learning_rate": 0.2846574565144418,
      "loss": 0.0,
      "num_input_tokens_seen": 1626560,
      "step": 5810
    },
    {
      "epoch": 64.61111111111111,
      "grad_norm": 5.36435845788219e-06,
      "learning_rate": 0.28463149419092154,
      "loss": 0.0,
      "num_input_tokens_seen": 1627952,
      "step": 5815
    },
    {
      "epoch": 64.66666666666667,
      "grad_norm": 3.5045363802055363e-06,
      "learning_rate": 0.284605511105533,
      "loss": 0.0,
      "num_input_tokens_seen": 1629392,
      "step": 5820
    },
    {
      "epoch": 64.72222222222223,
      "grad_norm": 2.785498509183526e-06,
      "learning_rate": 0.28457950726228315,
      "loss": 0.0,
      "num_input_tokens_seen": 1630784,
      "step": 5825
    },
    {
      "epoch": 64.77777777777777,
      "grad_norm": 1.4074929822527338e-05,
      "learning_rate": 0.28455348266518193,
      "loss": 0.0,
      "num_input_tokens_seen": 1632160,
      "step": 5830
    },
    {
      "epoch": 64.83333333333333,
      "grad_norm": 3.623855263867881e-06,
      "learning_rate": 0.28452743731824287,
      "loss": 0.0,
      "num_input_tokens_seen": 1633600,
      "step": 5835
    },
    {
      "epoch": 64.88888888888889,
      "grad_norm": 3.507248402456753e-05,
      "learning_rate": 0.28450137122548236,
      "loss": 0.0001,
      "num_input_tokens_seen": 1635008,
      "step": 5840
    },
    {
      "epoch": 64.94444444444444,
      "grad_norm": 3.0493623853544705e-05,
      "learning_rate": 0.2844752843909201,
      "loss": 0.0001,
      "num_input_tokens_seen": 1636416,
      "step": 5845
    },
    {
      "epoch": 65.0,
      "grad_norm": 9.295369636674877e-06,
      "learning_rate": 0.28444917681857923,
      "loss": 0.0,
      "num_input_tokens_seen": 1637824,
      "step": 5850
    },
    {
      "epoch": 65.05555555555556,
      "grad_norm": 3.054939952562563e-05,
      "learning_rate": 0.28442304851248557,
      "loss": 0.0,
      "num_input_tokens_seen": 1639216,
      "step": 5855
    },
    {
      "epoch": 65.11111111111111,
      "grad_norm": 9.19643025554251e-06,
      "learning_rate": 0.2843968994766686,
      "loss": 0.0,
      "num_input_tokens_seen": 1640624,
      "step": 5860
    },
    {
      "epoch": 65.16666666666667,
      "grad_norm": 2.445897507641348e-06,
      "learning_rate": 0.28437072971516075,
      "loss": 0.0,
      "num_input_tokens_seen": 1642000,
      "step": 5865
    },
    {
      "epoch": 65.22222222222223,
      "grad_norm": 2.4098726498777978e-05,
      "learning_rate": 0.2843445392319979,
      "loss": 0.0,
      "num_input_tokens_seen": 1643376,
      "step": 5870
    },
    {
      "epoch": 65.27777777777777,
      "grad_norm": 1.3999824659549631e-05,
      "learning_rate": 0.28431832803121865,
      "loss": 0.0,
      "num_input_tokens_seen": 1644832,
      "step": 5875
    },
    {
      "epoch": 65.33333333333333,
      "grad_norm": 1.3174361811252311e-05,
      "learning_rate": 0.28429209611686534,
      "loss": 0.0,
      "num_input_tokens_seen": 1646208,
      "step": 5880
    },
    {
      "epoch": 65.38888888888889,
      "grad_norm": 1.9606117348303087e-05,
      "learning_rate": 0.28426584349298323,
      "loss": 0.0,
      "num_input_tokens_seen": 1647600,
      "step": 5885
    },
    {
      "epoch": 65.44444444444444,
      "grad_norm": 1.4953591744415462e-05,
      "learning_rate": 0.2842395701636207,
      "loss": 0.0,
      "num_input_tokens_seen": 1648976,
      "step": 5890
    },
    {
      "epoch": 65.5,
      "grad_norm": 1.7029154832925997e-06,
      "learning_rate": 0.28421327613282954,
      "loss": 0.0,
      "num_input_tokens_seen": 1650352,
      "step": 5895
    },
    {
      "epoch": 65.55555555555556,
      "grad_norm": 5.1747092584264465e-06,
      "learning_rate": 0.28418696140466454,
      "loss": 0.0,
      "num_input_tokens_seen": 1651744,
      "step": 5900
    },
    {
      "epoch": 65.61111111111111,
      "grad_norm": 1.9954479284933768e-05,
      "learning_rate": 0.2841606259831838,
      "loss": 0.0,
      "num_input_tokens_seen": 1653152,
      "step": 5905
    },
    {
      "epoch": 65.66666666666667,
      "grad_norm": 2.735780071816407e-05,
      "learning_rate": 0.2841342698724486,
      "loss": 0.0,
      "num_input_tokens_seen": 1654576,
      "step": 5910
    },
    {
      "epoch": 65.72222222222223,
      "grad_norm": 3.4817196592484834e-06,
      "learning_rate": 0.28410789307652334,
      "loss": 0.0,
      "num_input_tokens_seen": 1656032,
      "step": 5915
    },
    {
      "epoch": 65.77777777777777,
      "grad_norm": 1.4570347047992982e-05,
      "learning_rate": 0.2840814955994756,
      "loss": 0.0,
      "num_input_tokens_seen": 1657408,
      "step": 5920
    },
    {
      "epoch": 65.83333333333333,
      "grad_norm": 2.622537977003958e-05,
      "learning_rate": 0.2840550774453763,
      "loss": 0.0,
      "num_input_tokens_seen": 1658800,
      "step": 5925
    },
    {
      "epoch": 65.88888888888889,
      "grad_norm": 2.951151827801368e-06,
      "learning_rate": 0.28402863861829947,
      "loss": 0.0,
      "num_input_tokens_seen": 1660192,
      "step": 5930
    },
    {
      "epoch": 65.94444444444444,
      "grad_norm": 1.6985039110295475e-05,
      "learning_rate": 0.2840021791223222,
      "loss": 0.0,
      "num_input_tokens_seen": 1661616,
      "step": 5935
    },
    {
      "epoch": 66.0,
      "grad_norm": 1.8168984752264805e-06,
      "learning_rate": 0.2839756989615249,
      "loss": 0.0,
      "num_input_tokens_seen": 1663072,
      "step": 5940
    },
    {
      "epoch": 66.05555555555556,
      "grad_norm": 3.036865791727905e-06,
      "learning_rate": 0.28394919813999125,
      "loss": 0.0,
      "num_input_tokens_seen": 1664432,
      "step": 5945
    },
    {
      "epoch": 66.11111111111111,
      "grad_norm": 4.4190414882905316e-06,
      "learning_rate": 0.28392267666180787,
      "loss": 0.0,
      "num_input_tokens_seen": 1665808,
      "step": 5950
    },
    {
      "epoch": 66.16666666666667,
      "grad_norm": 1.1743179129553027e-05,
      "learning_rate": 0.2838961345310648,
      "loss": 0.0,
      "num_input_tokens_seen": 1667200,
      "step": 5955
    },
    {
      "epoch": 66.22222222222223,
      "grad_norm": 9.782546840142459e-06,
      "learning_rate": 0.2838695717518552,
      "loss": 0.0,
      "num_input_tokens_seen": 1668608,
      "step": 5960
    },
    {
      "epoch": 66.27777777777777,
      "grad_norm": 2.5101393475779332e-05,
      "learning_rate": 0.28384298832827526,
      "loss": 0.0,
      "num_input_tokens_seen": 1669984,
      "step": 5965
    },
    {
      "epoch": 66.33333333333333,
      "grad_norm": 1.358394820272224e-05,
      "learning_rate": 0.28381638426442457,
      "loss": 0.0,
      "num_input_tokens_seen": 1671440,
      "step": 5970
    },
    {
      "epoch": 66.38888888888889,
      "grad_norm": 7.308014573936816e-06,
      "learning_rate": 0.2837897595644057,
      "loss": 0.0,
      "num_input_tokens_seen": 1672816,
      "step": 5975
    },
    {
      "epoch": 66.44444444444444,
      "grad_norm": 3.60370950147626e-06,
      "learning_rate": 0.28376311423232475,
      "loss": 0.0,
      "num_input_tokens_seen": 1674240,
      "step": 5980
    },
    {
      "epoch": 66.5,
      "grad_norm": 4.098318640899379e-06,
      "learning_rate": 0.2837364482722905,
      "loss": 0.0,
      "num_input_tokens_seen": 1675648,
      "step": 5985
    },
    {
      "epoch": 66.55555555555556,
      "grad_norm": 1.4799984455748927e-06,
      "learning_rate": 0.28370976168841533,
      "loss": 0.0,
      "num_input_tokens_seen": 1677024,
      "step": 5990
    },
    {
      "epoch": 66.61111111111111,
      "grad_norm": 1.1844471373478882e-05,
      "learning_rate": 0.2836830544848146,
      "loss": 0.0,
      "num_input_tokens_seen": 1678464,
      "step": 5995
    },
    {
      "epoch": 66.66666666666667,
      "grad_norm": 1.1276355508016422e-05,
      "learning_rate": 0.2836563266656069,
      "loss": 0.0,
      "num_input_tokens_seen": 1679888,
      "step": 6000
    },
    {
      "epoch": 66.66666666666667,
      "eval_loss": 0.8280493021011353,
      "eval_runtime": 1.1832,
      "eval_samples_per_second": 33.806,
      "eval_steps_per_second": 16.903,
      "num_input_tokens_seen": 1679888,
      "step": 6000
    },
    {
      "epoch": 66.72222222222223,
      "grad_norm": 3.145145456073806e-05,
      "learning_rate": 0.283629578234914,
      "loss": 0.0001,
      "num_input_tokens_seen": 1681264,
      "step": 6005
    },
    {
      "epoch": 66.77777777777777,
      "grad_norm": 3.25101086673385e-06,
      "learning_rate": 0.2836028091968608,
      "loss": 0.0,
      "num_input_tokens_seen": 1682688,
      "step": 6010
    },
    {
      "epoch": 66.83333333333333,
      "grad_norm": 1.500569487689063e-05,
      "learning_rate": 0.28357601955557554,
      "loss": 0.0,
      "num_input_tokens_seen": 1684064,
      "step": 6015
    },
    {
      "epoch": 66.88888888888889,
      "grad_norm": 1.0042518852060311e-06,
      "learning_rate": 0.2835492093151894,
      "loss": 0.0,
      "num_input_tokens_seen": 1685440,
      "step": 6020
    },
    {
      "epoch": 66.94444444444444,
      "grad_norm": 9.235435754817445e-06,
      "learning_rate": 0.2835223784798369,
      "loss": 0.0,
      "num_input_tokens_seen": 1686832,
      "step": 6025
    },
    {
      "epoch": 67.0,
      "grad_norm": 1.5557958249701187e-05,
      "learning_rate": 0.2834955270536557,
      "loss": 0.0,
      "num_input_tokens_seen": 1688272,
      "step": 6030
    },
    {
      "epoch": 67.05555555555556,
      "grad_norm": 1.068958044925239e-05,
      "learning_rate": 0.2834686550407866,
      "loss": 0.0,
      "num_input_tokens_seen": 1689680,
      "step": 6035
    },
    {
      "epoch": 67.11111111111111,
      "grad_norm": 2.744694756984245e-05,
      "learning_rate": 0.28344176244537367,
      "loss": 0.0,
      "num_input_tokens_seen": 1691104,
      "step": 6040
    },
    {
      "epoch": 67.16666666666667,
      "grad_norm": 2.2516212993650697e-05,
      "learning_rate": 0.28341484927156396,
      "loss": 0.0,
      "num_input_tokens_seen": 1692512,
      "step": 6045
    },
    {
      "epoch": 67.22222222222223,
      "grad_norm": 2.601186679385137e-06,
      "learning_rate": 0.28338791552350795,
      "loss": 0.0,
      "num_input_tokens_seen": 1693936,
      "step": 6050
    },
    {
      "epoch": 67.27777777777777,
      "grad_norm": 1.074984720617067e-05,
      "learning_rate": 0.28336096120535914,
      "loss": 0.0,
      "num_input_tokens_seen": 1695344,
      "step": 6055
    },
    {
      "epoch": 67.33333333333333,
      "grad_norm": 7.564780389657244e-06,
      "learning_rate": 0.2833339863212741,
      "loss": 0.0,
      "num_input_tokens_seen": 1696736,
      "step": 6060
    },
    {
      "epoch": 67.38888888888889,
      "grad_norm": 4.026847364002606e-06,
      "learning_rate": 0.28330699087541283,
      "loss": 0.0,
      "num_input_tokens_seen": 1698128,
      "step": 6065
    },
    {
      "epoch": 67.44444444444444,
      "grad_norm": 1.4309422113001347e-05,
      "learning_rate": 0.2832799748719384,
      "loss": 0.0,
      "num_input_tokens_seen": 1699504,
      "step": 6070
    },
    {
      "epoch": 67.5,
      "grad_norm": 3.480254235910252e-05,
      "learning_rate": 0.28325293831501686,
      "loss": 0.0,
      "num_input_tokens_seen": 1700896,
      "step": 6075
    },
    {
      "epoch": 67.55555555555556,
      "grad_norm": 1.8697144241741626e-06,
      "learning_rate": 0.2832258812088177,
      "loss": 0.0,
      "num_input_tokens_seen": 1702272,
      "step": 6080
    },
    {
      "epoch": 67.61111111111111,
      "grad_norm": 8.05457602837123e-06,
      "learning_rate": 0.2831988035575134,
      "loss": 0.0,
      "num_input_tokens_seen": 1703680,
      "step": 6085
    },
    {
      "epoch": 67.66666666666667,
      "grad_norm": 1.946379416040145e-05,
      "learning_rate": 0.28317170536527975,
      "loss": 0.0,
      "num_input_tokens_seen": 1705088,
      "step": 6090
    },
    {
      "epoch": 67.72222222222223,
      "grad_norm": 2.0551946363411844e-05,
      "learning_rate": 0.2831445866362956,
      "loss": 0.0,
      "num_input_tokens_seen": 1706496,
      "step": 6095
    },
    {
      "epoch": 67.77777777777777,
      "grad_norm": 1.5654483149774023e-06,
      "learning_rate": 0.2831174473747429,
      "loss": 0.0,
      "num_input_tokens_seen": 1707904,
      "step": 6100
    },
    {
      "epoch": 67.83333333333333,
      "grad_norm": 1.740940751915332e-05,
      "learning_rate": 0.2830902875848071,
      "loss": 0.0,
      "num_input_tokens_seen": 1709296,
      "step": 6105
    },
    {
      "epoch": 67.88888888888889,
      "grad_norm": 5.416316980699776e-06,
      "learning_rate": 0.28306310727067635,
      "loss": 0.0,
      "num_input_tokens_seen": 1710672,
      "step": 6110
    },
    {
      "epoch": 67.94444444444444,
      "grad_norm": 1.1091813576058485e-05,
      "learning_rate": 0.2830359064365423,
      "loss": 0.0,
      "num_input_tokens_seen": 1712048,
      "step": 6115
    },
    {
      "epoch": 68.0,
      "grad_norm": 7.611216915393015e-06,
      "learning_rate": 0.28300868508659965,
      "loss": 0.0,
      "num_input_tokens_seen": 1713488,
      "step": 6120
    },
    {
      "epoch": 68.05555555555556,
      "grad_norm": 4.592341156239854e-06,
      "learning_rate": 0.28298144322504626,
      "loss": 0.0,
      "num_input_tokens_seen": 1714864,
      "step": 6125
    },
    {
      "epoch": 68.11111111111111,
      "grad_norm": 1.998257721425034e-05,
      "learning_rate": 0.2829541808560832,
      "loss": 0.0,
      "num_input_tokens_seen": 1716240,
      "step": 6130
    },
    {
      "epoch": 68.16666666666667,
      "grad_norm": 5.1240740503999405e-06,
      "learning_rate": 0.2829268979839146,
      "loss": 0.0,
      "num_input_tokens_seen": 1717648,
      "step": 6135
    },
    {
      "epoch": 68.22222222222223,
      "grad_norm": 2.1050166196801e-06,
      "learning_rate": 0.2828995946127479,
      "loss": 0.0,
      "num_input_tokens_seen": 1719072,
      "step": 6140
    },
    {
      "epoch": 68.27777777777777,
      "grad_norm": 7.220596216939157e-06,
      "learning_rate": 0.2828722707467936,
      "loss": 0.0,
      "num_input_tokens_seen": 1720480,
      "step": 6145
    },
    {
      "epoch": 68.33333333333333,
      "grad_norm": 6.849955980214872e-07,
      "learning_rate": 0.2828449263902653,
      "loss": 0.0,
      "num_input_tokens_seen": 1721888,
      "step": 6150
    },
    {
      "epoch": 68.38888888888889,
      "grad_norm": 2.187928112107329e-05,
      "learning_rate": 0.28281756154738,
      "loss": 0.0,
      "num_input_tokens_seen": 1723312,
      "step": 6155
    },
    {
      "epoch": 68.44444444444444,
      "grad_norm": 5.721330580854556e-06,
      "learning_rate": 0.28279017622235764,
      "loss": 0.0,
      "num_input_tokens_seen": 1724672,
      "step": 6160
    },
    {
      "epoch": 68.5,
      "grad_norm": 6.117159045970766e-06,
      "learning_rate": 0.28276277041942127,
      "loss": 0.0,
      "num_input_tokens_seen": 1726048,
      "step": 6165
    },
    {
      "epoch": 68.55555555555556,
      "grad_norm": 1.3550901712733321e-05,
      "learning_rate": 0.2827353441427974,
      "loss": 0.0,
      "num_input_tokens_seen": 1727504,
      "step": 6170
    },
    {
      "epoch": 68.61111111111111,
      "grad_norm": 4.87704846818815e-06,
      "learning_rate": 0.2827078973967153,
      "loss": 0.0,
      "num_input_tokens_seen": 1728928,
      "step": 6175
    },
    {
      "epoch": 68.66666666666667,
      "grad_norm": 1.9221886759623885e-05,
      "learning_rate": 0.2826804301854078,
      "loss": 0.0,
      "num_input_tokens_seen": 1730368,
      "step": 6180
    },
    {
      "epoch": 68.72222222222223,
      "grad_norm": 1.6357862477889284e-05,
      "learning_rate": 0.2826529425131105,
      "loss": 0.0,
      "num_input_tokens_seen": 1731792,
      "step": 6185
    },
    {
      "epoch": 68.77777777777777,
      "grad_norm": 3.4037930163322017e-06,
      "learning_rate": 0.2826254343840625,
      "loss": 0.0,
      "num_input_tokens_seen": 1733184,
      "step": 6190
    },
    {
      "epoch": 68.83333333333333,
      "grad_norm": 1.3925069879405783e-06,
      "learning_rate": 0.2825979058025059,
      "loss": 0.0,
      "num_input_tokens_seen": 1734576,
      "step": 6195
    },
    {
      "epoch": 68.88888888888889,
      "grad_norm": 1.2646041795960627e-05,
      "learning_rate": 0.2825703567726858,
      "loss": 0.0,
      "num_input_tokens_seen": 1735952,
      "step": 6200
    },
    {
      "epoch": 68.88888888888889,
      "eval_loss": 0.8333526849746704,
      "eval_runtime": 1.1927,
      "eval_samples_per_second": 33.537,
      "eval_steps_per_second": 16.768,
      "num_input_tokens_seen": 1735952,
      "step": 6200
    },
    {
      "epoch": 68.94444444444444,
      "grad_norm": 1.5543460904154927e-05,
      "learning_rate": 0.2825427872988508,
      "loss": 0.0,
      "num_input_tokens_seen": 1737344,
      "step": 6205
    },
    {
      "epoch": 69.0,
      "grad_norm": 1.2478246389946435e-05,
      "learning_rate": 0.28251519738525227,
      "loss": 0.0,
      "num_input_tokens_seen": 1738752,
      "step": 6210
    },
    {
      "epoch": 69.05555555555556,
      "grad_norm": 2.8811703032260993e-06,
      "learning_rate": 0.28248758703614507,
      "loss": 0.0,
      "num_input_tokens_seen": 1740176,
      "step": 6215
    },
    {
      "epoch": 69.11111111111111,
      "grad_norm": 1.892263412628381e-06,
      "learning_rate": 0.28245995625578696,
      "loss": 0.0,
      "num_input_tokens_seen": 1741536,
      "step": 6220
    },
    {
      "epoch": 69.16666666666667,
      "grad_norm": 1.1547040230652783e-05,
      "learning_rate": 0.282432305048439,
      "loss": 0.0,
      "num_input_tokens_seen": 1742944,
      "step": 6225
    },
    {
      "epoch": 69.22222222222223,
      "grad_norm": 5.041952135798056e-06,
      "learning_rate": 0.28240463341836536,
      "loss": 0.0,
      "num_input_tokens_seen": 1744384,
      "step": 6230
    },
    {
      "epoch": 69.27777777777777,
      "grad_norm": 1.3241238775663078e-05,
      "learning_rate": 0.2823769413698334,
      "loss": 0.0,
      "num_input_tokens_seen": 1745760,
      "step": 6235
    },
    {
      "epoch": 69.33333333333333,
      "grad_norm": 1.1751662896131165e-05,
      "learning_rate": 0.2823492289071135,
      "loss": 0.0,
      "num_input_tokens_seen": 1747136,
      "step": 6240
    },
    {
      "epoch": 69.38888888888889,
      "grad_norm": 1.3277091056806967e-05,
      "learning_rate": 0.2823214960344793,
      "loss": 0.0,
      "num_input_tokens_seen": 1748544,
      "step": 6245
    },
    {
      "epoch": 69.44444444444444,
      "grad_norm": 5.7030065363505855e-06,
      "learning_rate": 0.28229374275620756,
      "loss": 0.0,
      "num_input_tokens_seen": 1749984,
      "step": 6250
    },
    {
      "epoch": 69.5,
      "grad_norm": 7.681029273953754e-06,
      "learning_rate": 0.28226596907657814,
      "loss": 0.0,
      "num_input_tokens_seen": 1751392,
      "step": 6255
    },
    {
      "epoch": 69.55555555555556,
      "grad_norm": 1.2207448207846028e-06,
      "learning_rate": 0.28223817499987414,
      "loss": 0.0,
      "num_input_tokens_seen": 1752784,
      "step": 6260
    },
    {
      "epoch": 69.61111111111111,
      "grad_norm": 3.155241756758187e-06,
      "learning_rate": 0.2822103605303818,
      "loss": 0.0,
      "num_input_tokens_seen": 1754160,
      "step": 6265
    },
    {
      "epoch": 69.66666666666667,
      "grad_norm": 8.548609002900776e-06,
      "learning_rate": 0.2821825256723903,
      "loss": 0.0,
      "num_input_tokens_seen": 1755584,
      "step": 6270
    },
    {
      "epoch": 69.72222222222223,
      "grad_norm": 6.557379492733162e-06,
      "learning_rate": 0.2821546704301923,
      "loss": 0.0,
      "num_input_tokens_seen": 1756992,
      "step": 6275
    },
    {
      "epoch": 69.77777777777777,
      "grad_norm": 3.694651923069614e-06,
      "learning_rate": 0.2821267948080834,
      "loss": 0.0,
      "num_input_tokens_seen": 1758384,
      "step": 6280
    },
    {
      "epoch": 69.83333333333333,
      "grad_norm": 1.9822840840788558e-05,
      "learning_rate": 0.28209889881036226,
      "loss": 0.0,
      "num_input_tokens_seen": 1759792,
      "step": 6285
    },
    {
      "epoch": 69.88888888888889,
      "grad_norm": 9.587039130565245e-06,
      "learning_rate": 0.28207098244133094,
      "loss": 0.0,
      "num_input_tokens_seen": 1761152,
      "step": 6290
    },
    {
      "epoch": 69.94444444444444,
      "grad_norm": 1.1409235412429553e-05,
      "learning_rate": 0.2820430457052943,
      "loss": 0.0,
      "num_input_tokens_seen": 1762608,
      "step": 6295
    },
    {
      "epoch": 70.0,
      "grad_norm": 6.564981504197931e-06,
      "learning_rate": 0.28201508860656077,
      "loss": 0.0,
      "num_input_tokens_seen": 1764000,
      "step": 6300
    },
    {
      "epoch": 70.05555555555556,
      "grad_norm": 1.1992035069852136e-05,
      "learning_rate": 0.2819871111494415,
      "loss": 0.0,
      "num_input_tokens_seen": 1765376,
      "step": 6305
    },
    {
      "epoch": 70.11111111111111,
      "grad_norm": 6.463136287493398e-06,
      "learning_rate": 0.28195911333825113,
      "loss": 0.0,
      "num_input_tokens_seen": 1766752,
      "step": 6310
    },
    {
      "epoch": 70.16666666666667,
      "grad_norm": 6.839217689957877e-07,
      "learning_rate": 0.28193109517730713,
      "loss": 0.0,
      "num_input_tokens_seen": 1768160,
      "step": 6315
    },
    {
      "epoch": 70.22222222222223,
      "grad_norm": 1.945167241501622e-05,
      "learning_rate": 0.2819030566709303,
      "loss": 0.0,
      "num_input_tokens_seen": 1769632,
      "step": 6320
    },
    {
      "epoch": 70.27777777777777,
      "grad_norm": 1.0853158528334461e-05,
      "learning_rate": 0.2818749978234445,
      "loss": 0.0,
      "num_input_tokens_seen": 1771008,
      "step": 6325
    },
    {
      "epoch": 70.33333333333333,
      "grad_norm": 9.746320756676141e-06,
      "learning_rate": 0.2818469186391768,
      "loss": 0.0,
      "num_input_tokens_seen": 1772368,
      "step": 6330
    },
    {
      "epoch": 70.38888888888889,
      "grad_norm": 1.1400190942367772e-06,
      "learning_rate": 0.28181881912245743,
      "loss": 0.0,
      "num_input_tokens_seen": 1773744,
      "step": 6335
    },
    {
      "epoch": 70.44444444444444,
      "grad_norm": 9.804223736864515e-06,
      "learning_rate": 0.2817906992776195,
      "loss": 0.0,
      "num_input_tokens_seen": 1775168,
      "step": 6340
    },
    {
      "epoch": 70.5,
      "grad_norm": 6.5984277171082795e-06,
      "learning_rate": 0.28176255910899967,
      "loss": 0.0,
      "num_input_tokens_seen": 1776544,
      "step": 6345
    },
    {
      "epoch": 70.55555555555556,
      "grad_norm": 7.517252015531994e-06,
      "learning_rate": 0.2817343986209373,
      "loss": 0.0,
      "num_input_tokens_seen": 1777952,
      "step": 6350
    },
    {
      "epoch": 70.61111111111111,
      "grad_norm": 3.752224301933893e-06,
      "learning_rate": 0.2817062178177753,
      "loss": 0.0,
      "num_input_tokens_seen": 1779328,
      "step": 6355
    },
    {
      "epoch": 70.66666666666667,
      "grad_norm": 1.1253555385337677e-05,
      "learning_rate": 0.2816780167038593,
      "loss": 0.0,
      "num_input_tokens_seen": 1780736,
      "step": 6360
    },
    {
      "epoch": 70.72222222222223,
      "grad_norm": 1.0251500498270616e-05,
      "learning_rate": 0.28164979528353834,
      "loss": 0.0,
      "num_input_tokens_seen": 1782112,
      "step": 6365
    },
    {
      "epoch": 70.77777777777777,
      "grad_norm": 9.975543434848078e-06,
      "learning_rate": 0.28162155356116453,
      "loss": 0.0,
      "num_input_tokens_seen": 1783520,
      "step": 6370
    },
    {
      "epoch": 70.83333333333333,
      "grad_norm": 1.5001081010268535e-05,
      "learning_rate": 0.28159329154109314,
      "loss": 0.0,
      "num_input_tokens_seen": 1784928,
      "step": 6375
    },
    {
      "epoch": 70.88888888888889,
      "grad_norm": 2.9770981200272217e-06,
      "learning_rate": 0.28156500922768246,
      "loss": 0.0,
      "num_input_tokens_seen": 1786304,
      "step": 6380
    },
    {
      "epoch": 70.94444444444444,
      "grad_norm": 5.410479843703797e-06,
      "learning_rate": 0.28153670662529406,
      "loss": 0.0,
      "num_input_tokens_seen": 1787712,
      "step": 6385
    },
    {
      "epoch": 71.0,
      "grad_norm": 3.8662253132315527e-07,
      "learning_rate": 0.28150838373829246,
      "loss": 0.0,
      "num_input_tokens_seen": 1789088,
      "step": 6390
    },
    {
      "epoch": 71.05555555555556,
      "grad_norm": 8.959388651419431e-06,
      "learning_rate": 0.2814800405710455,
      "loss": 0.0,
      "num_input_tokens_seen": 1790496,
      "step": 6395
    },
    {
      "epoch": 71.11111111111111,
      "grad_norm": 6.9802313191758e-06,
      "learning_rate": 0.2814516771279239,
      "loss": 0.0,
      "num_input_tokens_seen": 1791904,
      "step": 6400
    },
    {
      "epoch": 71.11111111111111,
      "eval_loss": 0.8473631143569946,
      "eval_runtime": 1.1921,
      "eval_samples_per_second": 33.555,
      "eval_steps_per_second": 16.778,
      "num_input_tokens_seen": 1791904,
      "step": 6400
    },
    {
      "epoch": 71.16666666666667,
      "grad_norm": 5.3320700317271985e-06,
      "learning_rate": 0.28142329341330186,
      "loss": 0.0,
      "num_input_tokens_seen": 1793296,
      "step": 6405
    },
    {
      "epoch": 71.22222222222223,
      "grad_norm": 3.958036359108519e-06,
      "learning_rate": 0.2813948894315564,
      "loss": 0.0,
      "num_input_tokens_seen": 1794688,
      "step": 6410
    },
    {
      "epoch": 71.27777777777777,
      "grad_norm": 3.648731535577099e-06,
      "learning_rate": 0.2813664651870677,
      "loss": 0.0,
      "num_input_tokens_seen": 1796112,
      "step": 6415
    },
    {
      "epoch": 71.33333333333333,
      "grad_norm": 4.095702024642378e-06,
      "learning_rate": 0.28133802068421926,
      "loss": 0.0,
      "num_input_tokens_seen": 1797520,
      "step": 6420
    },
    {
      "epoch": 71.38888888888889,
      "grad_norm": 2.186023948524962e-06,
      "learning_rate": 0.28130955592739754,
      "loss": 0.0,
      "num_input_tokens_seen": 1798896,
      "step": 6425
    },
    {
      "epoch": 71.44444444444444,
      "grad_norm": 7.887483661761507e-06,
      "learning_rate": 0.2812810709209922,
      "loss": 0.0,
      "num_input_tokens_seen": 1800304,
      "step": 6430
    },
    {
      "epoch": 71.5,
      "grad_norm": 2.0243210201442707e-06,
      "learning_rate": 0.2812525656693959,
      "loss": 0.0,
      "num_input_tokens_seen": 1801664,
      "step": 6435
    },
    {
      "epoch": 71.55555555555556,
      "grad_norm": 1.4725490473210812e-05,
      "learning_rate": 0.28122404017700453,
      "loss": 0.0,
      "num_input_tokens_seen": 1803056,
      "step": 6440
    },
    {
      "epoch": 71.61111111111111,
      "grad_norm": 1.349986905552214e-05,
      "learning_rate": 0.2811954944482171,
      "loss": 0.0,
      "num_input_tokens_seen": 1804432,
      "step": 6445
    },
    {
      "epoch": 71.66666666666667,
      "grad_norm": 4.971906037098961e-06,
      "learning_rate": 0.2811669284874358,
      "loss": 0.0,
      "num_input_tokens_seen": 1805856,
      "step": 6450
    },
    {
      "epoch": 71.72222222222223,
      "grad_norm": 8.665169843879994e-06,
      "learning_rate": 0.2811383422990657,
      "loss": 0.0,
      "num_input_tokens_seen": 1807264,
      "step": 6455
    },
    {
      "epoch": 71.77777777777777,
      "grad_norm": 5.089628757559694e-06,
      "learning_rate": 0.2811097358875152,
      "loss": 0.0,
      "num_input_tokens_seen": 1808688,
      "step": 6460
    },
    {
      "epoch": 71.83333333333333,
      "grad_norm": 2.2030908439774066e-06,
      "learning_rate": 0.2810811092571959,
      "loss": 0.0,
      "num_input_tokens_seen": 1810096,
      "step": 6465
    },
    {
      "epoch": 71.88888888888889,
      "grad_norm": 1.4615744703405653e-06,
      "learning_rate": 0.28105246241252224,
      "loss": 0.0,
      "num_input_tokens_seen": 1811488,
      "step": 6470
    },
    {
      "epoch": 71.94444444444444,
      "grad_norm": 6.282274171098834e-06,
      "learning_rate": 0.28102379535791194,
      "loss": 0.0,
      "num_input_tokens_seen": 1812896,
      "step": 6475
    },
    {
      "epoch": 72.0,
      "grad_norm": 7.662799362151418e-06,
      "learning_rate": 0.2809951080977859,
      "loss": 0.0,
      "num_input_tokens_seen": 1814288,
      "step": 6480
    },
    {
      "epoch": 72.05555555555556,
      "grad_norm": 1.1377866030670702e-05,
      "learning_rate": 0.28096640063656797,
      "loss": 0.0,
      "num_input_tokens_seen": 1815696,
      "step": 6485
    },
    {
      "epoch": 72.11111111111111,
      "grad_norm": 8.314965270983521e-06,
      "learning_rate": 0.2809376729786852,
      "loss": 0.0,
      "num_input_tokens_seen": 1817104,
      "step": 6490
    },
    {
      "epoch": 72.16666666666667,
      "grad_norm": 8.776185495662503e-06,
      "learning_rate": 0.28090892512856785,
      "loss": 0.0,
      "num_input_tokens_seen": 1818528,
      "step": 6495
    },
    {
      "epoch": 72.22222222222223,
      "grad_norm": 4.290862761990866e-06,
      "learning_rate": 0.2808801570906491,
      "loss": 0.0,
      "num_input_tokens_seen": 1819920,
      "step": 6500
    },
    {
      "epoch": 72.27777777777777,
      "grad_norm": 3.7324298318708315e-06,
      "learning_rate": 0.2808513688693654,
      "loss": 0.0,
      "num_input_tokens_seen": 1821312,
      "step": 6505
    },
    {
      "epoch": 72.33333333333333,
      "grad_norm": 3.6086266845813952e-06,
      "learning_rate": 0.28082256046915627,
      "loss": 0.0,
      "num_input_tokens_seen": 1822720,
      "step": 6510
    },
    {
      "epoch": 72.38888888888889,
      "grad_norm": 1.2475054063543212e-05,
      "learning_rate": 0.28079373189446427,
      "loss": 0.0,
      "num_input_tokens_seen": 1824096,
      "step": 6515
    },
    {
      "epoch": 72.44444444444444,
      "grad_norm": 1.7205331914738053e-06,
      "learning_rate": 0.28076488314973513,
      "loss": 0.0,
      "num_input_tokens_seen": 1825472,
      "step": 6520
    },
    {
      "epoch": 72.5,
      "grad_norm": 1.5653755554012605e-06,
      "learning_rate": 0.28073601423941774,
      "loss": 0.0,
      "num_input_tokens_seen": 1826832,
      "step": 6525
    },
    {
      "epoch": 72.55555555555556,
      "grad_norm": 2.625391744004446e-06,
      "learning_rate": 0.28070712516796403,
      "loss": 0.0,
      "num_input_tokens_seen": 1828272,
      "step": 6530
    },
    {
      "epoch": 72.61111111111111,
      "grad_norm": 6.858330380055122e-06,
      "learning_rate": 0.28067821593982906,
      "loss": 0.0,
      "num_input_tokens_seen": 1829680,
      "step": 6535
    },
    {
      "epoch": 72.66666666666667,
      "grad_norm": 7.340317552007036e-06,
      "learning_rate": 0.28064928655947097,
      "loss": 0.0,
      "num_input_tokens_seen": 1831072,
      "step": 6540
    },
    {
      "epoch": 72.72222222222223,
      "grad_norm": 4.8008128032961395e-06,
      "learning_rate": 0.28062033703135103,
      "loss": 0.0,
      "num_input_tokens_seen": 1832480,
      "step": 6545
    },
    {
      "epoch": 72.77777777777777,
      "grad_norm": 7.0995411078911275e-06,
      "learning_rate": 0.2805913673599337,
      "loss": 0.0,
      "num_input_tokens_seen": 1833872,
      "step": 6550
    },
    {
      "epoch": 72.83333333333333,
      "grad_norm": 2.859287405954092e-06,
      "learning_rate": 0.2805623775496864,
      "loss": 0.0,
      "num_input_tokens_seen": 1835296,
      "step": 6555
    },
    {
      "epoch": 72.88888888888889,
      "grad_norm": 7.243843811011175e-06,
      "learning_rate": 0.2805333676050797,
      "loss": 0.0,
      "num_input_tokens_seen": 1836704,
      "step": 6560
    },
    {
      "epoch": 72.94444444444444,
      "grad_norm": 9.389914339408278e-06,
      "learning_rate": 0.2805043375305873,
      "loss": 0.0,
      "num_input_tokens_seen": 1838112,
      "step": 6565
    },
    {
      "epoch": 73.0,
      "grad_norm": 5.326660357241053e-06,
      "learning_rate": 0.2804752873306861,
      "loss": 0.0,
      "num_input_tokens_seen": 1839536,
      "step": 6570
    },
    {
      "epoch": 73.05555555555556,
      "grad_norm": 9.751098332344554e-06,
      "learning_rate": 0.2804462170098559,
      "loss": 0.0,
      "num_input_tokens_seen": 1840944,
      "step": 6575
    },
    {
      "epoch": 73.11111111111111,
      "grad_norm": 1.6321801012963988e-05,
      "learning_rate": 0.2804171265725797,
      "loss": 0.0,
      "num_input_tokens_seen": 1842352,
      "step": 6580
    },
    {
      "epoch": 73.16666666666667,
      "grad_norm": 1.8245181081510964e-06,
      "learning_rate": 0.28038801602334373,
      "loss": 0.0,
      "num_input_tokens_seen": 1843776,
      "step": 6585
    },
    {
      "epoch": 73.22222222222223,
      "grad_norm": 1.7768040834198473e-06,
      "learning_rate": 0.28035888536663717,
      "loss": 0.0,
      "num_input_tokens_seen": 1845152,
      "step": 6590
    },
    {
      "epoch": 73.27777777777777,
      "grad_norm": 3.886676950060064e-06,
      "learning_rate": 0.2803297346069522,
      "loss": 0.0,
      "num_input_tokens_seen": 1846512,
      "step": 6595
    },
    {
      "epoch": 73.33333333333333,
      "grad_norm": 1.5246793736878317e-05,
      "learning_rate": 0.28030056374878437,
      "loss": 0.0,
      "num_input_tokens_seen": 1847888,
      "step": 6600
    },
    {
      "epoch": 73.33333333333333,
      "eval_loss": 0.8694473505020142,
      "eval_runtime": 1.1834,
      "eval_samples_per_second": 33.801,
      "eval_steps_per_second": 16.9,
      "num_input_tokens_seen": 1847888,
      "step": 6600
    },
    {
      "epoch": 73.38888888888889,
      "grad_norm": 1.1862231303894077e-06,
      "learning_rate": 0.2802713727966321,
      "loss": 0.0,
      "num_input_tokens_seen": 1849264,
      "step": 6605
    },
    {
      "epoch": 73.44444444444444,
      "grad_norm": 6.4913010646705516e-06,
      "learning_rate": 0.28024216175499717,
      "loss": 0.0,
      "num_input_tokens_seen": 1850656,
      "step": 6610
    },
    {
      "epoch": 73.5,
      "grad_norm": 3.171878461216693e-06,
      "learning_rate": 0.2802129306283841,
      "loss": 0.0,
      "num_input_tokens_seen": 1852064,
      "step": 6615
    },
    {
      "epoch": 73.55555555555556,
      "grad_norm": 1.882533297248301e-06,
      "learning_rate": 0.28018367942130074,
      "loss": 0.0,
      "num_input_tokens_seen": 1853472,
      "step": 6620
    },
    {
      "epoch": 73.61111111111111,
      "grad_norm": 3.641641114882077e-06,
      "learning_rate": 0.28015440813825804,
      "loss": 0.0,
      "num_input_tokens_seen": 1854832,
      "step": 6625
    },
    {
      "epoch": 73.66666666666667,
      "grad_norm": 2.5382976218679687e-06,
      "learning_rate": 0.28012511678377006,
      "loss": 0.0,
      "num_input_tokens_seen": 1856224,
      "step": 6630
    },
    {
      "epoch": 73.72222222222223,
      "grad_norm": 2.188366124755703e-05,
      "learning_rate": 0.28009580536235373,
      "loss": 0.0,
      "num_input_tokens_seen": 1857648,
      "step": 6635
    },
    {
      "epoch": 73.77777777777777,
      "grad_norm": 8.58437215356389e-06,
      "learning_rate": 0.28006647387852934,
      "loss": 0.0,
      "num_input_tokens_seen": 1859072,
      "step": 6640
    },
    {
      "epoch": 73.83333333333333,
      "grad_norm": 4.912145868729567e-06,
      "learning_rate": 0.28003712233682015,
      "loss": 0.0,
      "num_input_tokens_seen": 1860496,
      "step": 6645
    },
    {
      "epoch": 73.88888888888889,
      "grad_norm": 2.716436711125425e-06,
      "learning_rate": 0.2800077507417526,
      "loss": 0.0,
      "num_input_tokens_seen": 1861920,
      "step": 6650
    },
    {
      "epoch": 73.94444444444444,
      "grad_norm": 7.051854026940418e-06,
      "learning_rate": 0.2799783590978561,
      "loss": 0.0,
      "num_input_tokens_seen": 1863344,
      "step": 6655
    },
    {
      "epoch": 74.0,
      "grad_norm": 1.9110927951260237e-06,
      "learning_rate": 0.2799489474096632,
      "loss": 0.0,
      "num_input_tokens_seen": 1864752,
      "step": 6660
    },
    {
      "epoch": 74.05555555555556,
      "grad_norm": 2.520421048757271e-06,
      "learning_rate": 0.27991951568170953,
      "loss": 0.0,
      "num_input_tokens_seen": 1866176,
      "step": 6665
    },
    {
      "epoch": 74.11111111111111,
      "grad_norm": 1.1654310583253391e-05,
      "learning_rate": 0.2798900639185339,
      "loss": 0.0,
      "num_input_tokens_seen": 1867568,
      "step": 6670
    },
    {
      "epoch": 74.16666666666667,
      "grad_norm": 1.5214562836263212e-06,
      "learning_rate": 0.2798605921246781,
      "loss": 0.0,
      "num_input_tokens_seen": 1868928,
      "step": 6675
    },
    {
      "epoch": 74.22222222222223,
      "grad_norm": 7.286436357389903e-06,
      "learning_rate": 0.2798311003046871,
      "loss": 0.0,
      "num_input_tokens_seen": 1870336,
      "step": 6680
    },
    {
      "epoch": 74.27777777777777,
      "grad_norm": 4.543721388472477e-06,
      "learning_rate": 0.2798015884631089,
      "loss": 0.0,
      "num_input_tokens_seen": 1871744,
      "step": 6685
    },
    {
      "epoch": 74.33333333333333,
      "grad_norm": 3.958848083129851e-06,
      "learning_rate": 0.27977205660449445,
      "loss": 0.0,
      "num_input_tokens_seen": 1873136,
      "step": 6690
    },
    {
      "epoch": 74.38888888888889,
      "grad_norm": 1.7596925317775458e-05,
      "learning_rate": 0.2797425047333981,
      "loss": 0.0,
      "num_input_tokens_seen": 1874528,
      "step": 6695
    },
    {
      "epoch": 74.44444444444444,
      "grad_norm": 6.538552497659111e-06,
      "learning_rate": 0.27971293285437715,
      "loss": 0.0,
      "num_input_tokens_seen": 1875888,
      "step": 6700
    },
    {
      "epoch": 74.5,
      "grad_norm": 6.179192496347241e-06,
      "learning_rate": 0.2796833409719918,
      "loss": 0.0,
      "num_input_tokens_seen": 1877312,
      "step": 6705
    },
    {
      "epoch": 74.55555555555556,
      "grad_norm": 9.471197699895129e-06,
      "learning_rate": 0.27965372909080566,
      "loss": 0.0,
      "num_input_tokens_seen": 1878736,
      "step": 6710
    },
    {
      "epoch": 74.61111111111111,
      "grad_norm": 1.6928368040680652e-06,
      "learning_rate": 0.27962409721538506,
      "loss": 0.0,
      "num_input_tokens_seen": 1880176,
      "step": 6715
    },
    {
      "epoch": 74.66666666666667,
      "grad_norm": 2.6136085580219515e-06,
      "learning_rate": 0.27959444535029976,
      "loss": 0.0,
      "num_input_tokens_seen": 1881568,
      "step": 6720
    },
    {
      "epoch": 74.72222222222223,
      "grad_norm": 3.1395299515679653e-07,
      "learning_rate": 0.27956477350012243,
      "loss": 0.0,
      "num_input_tokens_seen": 1882992,
      "step": 6725
    },
    {
      "epoch": 74.77777777777777,
      "grad_norm": 4.579074811772443e-06,
      "learning_rate": 0.27953508166942875,
      "loss": 0.0,
      "num_input_tokens_seen": 1884352,
      "step": 6730
    },
    {
      "epoch": 74.83333333333333,
      "grad_norm": 8.494669145875378e-07,
      "learning_rate": 0.27950536986279767,
      "loss": 0.0,
      "num_input_tokens_seen": 1885696,
      "step": 6735
    },
    {
      "epoch": 74.88888888888889,
      "grad_norm": 3.363898940733634e-06,
      "learning_rate": 0.2794756380848111,
      "loss": 0.0,
      "num_input_tokens_seen": 1887104,
      "step": 6740
    },
    {
      "epoch": 74.94444444444444,
      "grad_norm": 5.101597707835026e-06,
      "learning_rate": 0.279445886340054,
      "loss": 0.0,
      "num_input_tokens_seen": 1888512,
      "step": 6745
    },
    {
      "epoch": 75.0,
      "grad_norm": 8.559776688343845e-06,
      "learning_rate": 0.27941611463311455,
      "loss": 0.0,
      "num_input_tokens_seen": 1889904,
      "step": 6750
    },
    {
      "epoch": 75.05555555555556,
      "grad_norm": 1.0948797353194095e-06,
      "learning_rate": 0.2793863229685839,
      "loss": 0.0,
      "num_input_tokens_seen": 1891312,
      "step": 6755
    },
    {
      "epoch": 75.11111111111111,
      "grad_norm": 2.3412540031131357e-06,
      "learning_rate": 0.27935651135105627,
      "loss": 0.0,
      "num_input_tokens_seen": 1892704,
      "step": 6760
    },
    {
      "epoch": 75.16666666666667,
      "grad_norm": 8.850597623677459e-06,
      "learning_rate": 0.279326679785129,
      "loss": 0.0,
      "num_input_tokens_seen": 1894112,
      "step": 6765
    },
    {
      "epoch": 75.22222222222223,
      "grad_norm": 3.605514848459279e-06,
      "learning_rate": 0.2792968282754024,
      "loss": 0.0,
      "num_input_tokens_seen": 1895552,
      "step": 6770
    },
    {
      "epoch": 75.27777777777777,
      "grad_norm": 4.126202838961035e-06,
      "learning_rate": 0.2792669568264801,
      "loss": 0.0,
      "num_input_tokens_seen": 1896992,
      "step": 6775
    },
    {
      "epoch": 75.33333333333333,
      "grad_norm": 7.155416028581385e-07,
      "learning_rate": 0.27923706544296856,
      "loss": 0.0,
      "num_input_tokens_seen": 1898384,
      "step": 6780
    },
    {
      "epoch": 75.38888888888889,
      "grad_norm": 3.6120022741670255e-06,
      "learning_rate": 0.2792071541294775,
      "loss": 0.0,
      "num_input_tokens_seen": 1899776,
      "step": 6785
    },
    {
      "epoch": 75.44444444444444,
      "grad_norm": 8.334178346558474e-06,
      "learning_rate": 0.27917722289061947,
      "loss": 0.0,
      "num_input_tokens_seen": 1901168,
      "step": 6790
    },
    {
      "epoch": 75.5,
      "grad_norm": 5.879828677279875e-06,
      "learning_rate": 0.27914727173101034,
      "loss": 0.0,
      "num_input_tokens_seen": 1902592,
      "step": 6795
    },
    {
      "epoch": 75.55555555555556,
      "grad_norm": 4.895067377219675e-06,
      "learning_rate": 0.279117300655269,
      "loss": 0.0,
      "num_input_tokens_seen": 1904000,
      "step": 6800
    },
    {
      "epoch": 75.55555555555556,
      "eval_loss": 0.8714165687561035,
      "eval_runtime": 1.1841,
      "eval_samples_per_second": 33.782,
      "eval_steps_per_second": 16.891,
      "num_input_tokens_seen": 1904000,
      "step": 6800
    },
    {
      "epoch": 75.61111111111111,
      "grad_norm": 2.4616049358883174e-06,
      "learning_rate": 0.2790873096680173,
      "loss": 0.0,
      "num_input_tokens_seen": 1905392,
      "step": 6805
    },
    {
      "epoch": 75.66666666666667,
      "grad_norm": 1.553411834720464e-06,
      "learning_rate": 0.2790572987738802,
      "loss": 0.0,
      "num_input_tokens_seen": 1906736,
      "step": 6810
    },
    {
      "epoch": 75.72222222222223,
      "grad_norm": 8.593145139457192e-06,
      "learning_rate": 0.27902726797748584,
      "loss": 0.0,
      "num_input_tokens_seen": 1908128,
      "step": 6815
    },
    {
      "epoch": 75.77777777777777,
      "grad_norm": 5.254852112557273e-06,
      "learning_rate": 0.2789972172834652,
      "loss": 0.0,
      "num_input_tokens_seen": 1909552,
      "step": 6820
    },
    {
      "epoch": 75.83333333333333,
      "grad_norm": 1.0109237337019295e-05,
      "learning_rate": 0.2789671466964527,
      "loss": 0.0,
      "num_input_tokens_seen": 1910960,
      "step": 6825
    },
    {
      "epoch": 75.88888888888889,
      "grad_norm": 2.824199555107043e-06,
      "learning_rate": 0.2789370562210854,
      "loss": 0.0,
      "num_input_tokens_seen": 1912320,
      "step": 6830
    },
    {
      "epoch": 75.94444444444444,
      "grad_norm": 3.3340941172355087e-06,
      "learning_rate": 0.27890694586200376,
      "loss": 0.0,
      "num_input_tokens_seen": 1913744,
      "step": 6835
    },
    {
      "epoch": 76.0,
      "grad_norm": 1.4868849120830419e-06,
      "learning_rate": 0.2788768156238511,
      "loss": 0.0,
      "num_input_tokens_seen": 1915072,
      "step": 6840
    },
    {
      "epoch": 76.05555555555556,
      "grad_norm": 5.626191978080897e-06,
      "learning_rate": 0.27884666551127385,
      "loss": 0.0,
      "num_input_tokens_seen": 1916480,
      "step": 6845
    },
    {
      "epoch": 76.11111111111111,
      "grad_norm": 5.275685907690786e-06,
      "learning_rate": 0.2788164955289217,
      "loss": 0.0,
      "num_input_tokens_seen": 1917888,
      "step": 6850
    },
    {
      "epoch": 76.16666666666667,
      "grad_norm": 9.729199064167915e-07,
      "learning_rate": 0.27878630568144697,
      "loss": 0.0,
      "num_input_tokens_seen": 1919216,
      "step": 6855
    },
    {
      "epoch": 76.22222222222223,
      "grad_norm": 7.069176263030386e-06,
      "learning_rate": 0.2787560959735056,
      "loss": 0.0,
      "num_input_tokens_seen": 1920624,
      "step": 6860
    },
    {
      "epoch": 76.27777777777777,
      "grad_norm": 1.4895488220645348e-06,
      "learning_rate": 0.27872586640975616,
      "loss": 0.0,
      "num_input_tokens_seen": 1922016,
      "step": 6865
    },
    {
      "epoch": 76.33333333333333,
      "grad_norm": 6.6687330217973795e-06,
      "learning_rate": 0.27869561699486045,
      "loss": 0.0,
      "num_input_tokens_seen": 1923488,
      "step": 6870
    },
    {
      "epoch": 76.38888888888889,
      "grad_norm": 1.0675202247512061e-05,
      "learning_rate": 0.2786653477334833,
      "loss": 0.0,
      "num_input_tokens_seen": 1924880,
      "step": 6875
    },
    {
      "epoch": 76.44444444444444,
      "grad_norm": 2.0302165921748383e-06,
      "learning_rate": 0.2786350586302926,
      "loss": 0.0,
      "num_input_tokens_seen": 1926288,
      "step": 6880
    },
    {
      "epoch": 76.5,
      "grad_norm": 3.3451447052357253e-06,
      "learning_rate": 0.27860474968995935,
      "loss": 0.0,
      "num_input_tokens_seen": 1927616,
      "step": 6885
    },
    {
      "epoch": 76.55555555555556,
      "grad_norm": 6.281901278271107e-06,
      "learning_rate": 0.27857442091715756,
      "loss": 0.0,
      "num_input_tokens_seen": 1929056,
      "step": 6890
    },
    {
      "epoch": 76.61111111111111,
      "grad_norm": 8.22360107122222e-06,
      "learning_rate": 0.27854407231656425,
      "loss": 0.0,
      "num_input_tokens_seen": 1930400,
      "step": 6895
    },
    {
      "epoch": 76.66666666666667,
      "grad_norm": 1.7899154727274436e-06,
      "learning_rate": 0.2785137038928596,
      "loss": 0.0,
      "num_input_tokens_seen": 1931840,
      "step": 6900
    },
    {
      "epoch": 76.72222222222223,
      "grad_norm": 1.5356215499195969e-06,
      "learning_rate": 0.27848331565072687,
      "loss": 0.0,
      "num_input_tokens_seen": 1933216,
      "step": 6905
    },
    {
      "epoch": 76.77777777777777,
      "grad_norm": 5.069851340522291e-06,
      "learning_rate": 0.27845290759485225,
      "loss": 0.0,
      "num_input_tokens_seen": 1934640,
      "step": 6910
    },
    {
      "epoch": 76.83333333333333,
      "grad_norm": 3.960066351282876e-06,
      "learning_rate": 0.278422479729925,
      "loss": 0.0,
      "num_input_tokens_seen": 1936000,
      "step": 6915
    },
    {
      "epoch": 76.88888888888889,
      "grad_norm": 5.520386821444845e-06,
      "learning_rate": 0.2783920320606375,
      "loss": 0.0,
      "num_input_tokens_seen": 1937392,
      "step": 6920
    },
    {
      "epoch": 76.94444444444444,
      "grad_norm": 6.8607837420131546e-06,
      "learning_rate": 0.2783615645916852,
      "loss": 0.0,
      "num_input_tokens_seen": 1938832,
      "step": 6925
    },
    {
      "epoch": 77.0,
      "grad_norm": 8.10754227131838e-06,
      "learning_rate": 0.2783310773277666,
      "loss": 0.0,
      "num_input_tokens_seen": 1940288,
      "step": 6930
    },
    {
      "epoch": 77.05555555555556,
      "grad_norm": 3.202675998181803e-06,
      "learning_rate": 0.2783005702735831,
      "loss": 0.0,
      "num_input_tokens_seen": 1941728,
      "step": 6935
    },
    {
      "epoch": 77.11111111111111,
      "grad_norm": 3.2386071779910708e-06,
      "learning_rate": 0.2782700434338394,
      "loss": 0.0,
      "num_input_tokens_seen": 1943152,
      "step": 6940
    },
    {
      "epoch": 77.16666666666667,
      "grad_norm": 4.969015208189376e-06,
      "learning_rate": 0.278239496813243,
      "loss": 0.0,
      "num_input_tokens_seen": 1944560,
      "step": 6945
    },
    {
      "epoch": 77.22222222222223,
      "grad_norm": 8.886458999768365e-06,
      "learning_rate": 0.27820893041650463,
      "loss": 0.0,
      "num_input_tokens_seen": 1945952,
      "step": 6950
    },
    {
      "epoch": 77.27777777777777,
      "grad_norm": 2.5395950160600478e-06,
      "learning_rate": 0.27817834424833804,
      "loss": 0.0,
      "num_input_tokens_seen": 1947312,
      "step": 6955
    },
    {
      "epoch": 77.33333333333333,
      "grad_norm": 3.621631321948371e-06,
      "learning_rate": 0.27814773831345996,
      "loss": 0.0,
      "num_input_tokens_seen": 1948704,
      "step": 6960
    },
    {
      "epoch": 77.38888888888889,
      "grad_norm": 5.882580353500089e-06,
      "learning_rate": 0.2781171126165902,
      "loss": 0.0,
      "num_input_tokens_seen": 1950128,
      "step": 6965
    },
    {
      "epoch": 77.44444444444444,
      "grad_norm": 7.086828645697096e-06,
      "learning_rate": 0.2780864671624517,
      "loss": 0.0,
      "num_input_tokens_seen": 1951568,
      "step": 6970
    },
    {
      "epoch": 77.5,
      "grad_norm": 6.158517862786539e-06,
      "learning_rate": 0.27805580195577034,
      "loss": 0.0,
      "num_input_tokens_seen": 1953008,
      "step": 6975
    },
    {
      "epoch": 77.55555555555556,
      "grad_norm": 2.168566879845457e-06,
      "learning_rate": 0.2780251170012751,
      "loss": 0.0,
      "num_input_tokens_seen": 1954368,
      "step": 6980
    },
    {
      "epoch": 77.61111111111111,
      "grad_norm": 6.7587443481897935e-06,
      "learning_rate": 0.27799441230369787,
      "loss": 0.0,
      "num_input_tokens_seen": 1955728,
      "step": 6985
    },
    {
      "epoch": 77.66666666666667,
      "grad_norm": 4.393725419049588e-07,
      "learning_rate": 0.27796368786777387,
      "loss": 0.0,
      "num_input_tokens_seen": 1957104,
      "step": 6990
    },
    {
      "epoch": 77.72222222222223,
      "grad_norm": 7.4762774602277204e-06,
      "learning_rate": 0.277932943698241,
      "loss": 0.0,
      "num_input_tokens_seen": 1958528,
      "step": 6995
    },
    {
      "epoch": 77.77777777777777,
      "grad_norm": 4.056567831867142e-06,
      "learning_rate": 0.2779021797998406,
      "loss": 0.0,
      "num_input_tokens_seen": 1959920,
      "step": 7000
    },
    {
      "epoch": 77.77777777777777,
      "eval_loss": 0.8972242474555969,
      "eval_runtime": 1.1837,
      "eval_samples_per_second": 33.793,
      "eval_steps_per_second": 16.896,
      "num_input_tokens_seen": 1959920,
      "step": 7000
    },
    {
      "epoch": 77.83333333333333,
      "grad_norm": 6.304092039499665e-06,
      "learning_rate": 0.2778713961773167,
      "loss": 0.0,
      "num_input_tokens_seen": 1961328,
      "step": 7005
    },
    {
      "epoch": 77.88888888888889,
      "grad_norm": 2.3243590021593263e-06,
      "learning_rate": 0.2778405928354166,
      "loss": 0.0,
      "num_input_tokens_seen": 1962720,
      "step": 7010
    },
    {
      "epoch": 77.94444444444444,
      "grad_norm": 9.217525985150132e-06,
      "learning_rate": 0.27780976977889055,
      "loss": 0.0,
      "num_input_tokens_seen": 1964064,
      "step": 7015
    },
    {
      "epoch": 78.0,
      "grad_norm": 3.6767091842193622e-06,
      "learning_rate": 0.27777892701249185,
      "loss": 0.0,
      "num_input_tokens_seen": 1965472,
      "step": 7020
    },
    {
      "epoch": 78.05555555555556,
      "grad_norm": 1.8204100342700258e-06,
      "learning_rate": 0.2777480645409768,
      "loss": 0.0,
      "num_input_tokens_seen": 1966896,
      "step": 7025
    },
    {
      "epoch": 78.11111111111111,
      "grad_norm": 1.4593496189263533e-06,
      "learning_rate": 0.27771718236910486,
      "loss": 0.0,
      "num_input_tokens_seen": 1968272,
      "step": 7030
    },
    {
      "epoch": 78.16666666666667,
      "grad_norm": 5.154651262273546e-06,
      "learning_rate": 0.27768628050163835,
      "loss": 0.0,
      "num_input_tokens_seen": 1969696,
      "step": 7035
    },
    {
      "epoch": 78.22222222222223,
      "grad_norm": 6.137064247013768e-06,
      "learning_rate": 0.2776553589433428,
      "loss": 0.0,
      "num_input_tokens_seen": 1971136,
      "step": 7040
    },
    {
      "epoch": 78.27777777777777,
      "grad_norm": 8.19653632788686e-06,
      "learning_rate": 0.27762441769898666,
      "loss": 0.0,
      "num_input_tokens_seen": 1972528,
      "step": 7045
    },
    {
      "epoch": 78.33333333333333,
      "grad_norm": 1.175112629425712e-06,
      "learning_rate": 0.2775934567733415,
      "loss": 0.0,
      "num_input_tokens_seen": 1973920,
      "step": 7050
    },
    {
      "epoch": 78.38888888888889,
      "grad_norm": 1.1191184512426844e-06,
      "learning_rate": 0.2775624761711819,
      "loss": 0.0,
      "num_input_tokens_seen": 1975296,
      "step": 7055
    },
    {
      "epoch": 78.44444444444444,
      "grad_norm": 2.5719209588714875e-06,
      "learning_rate": 0.2775314758972854,
      "loss": 0.0,
      "num_input_tokens_seen": 1976656,
      "step": 7060
    },
    {
      "epoch": 78.5,
      "grad_norm": 1.4221945093595423e-05,
      "learning_rate": 0.2775004559564327,
      "loss": 0.0,
      "num_input_tokens_seen": 1978048,
      "step": 7065
    },
    {
      "epoch": 78.55555555555556,
      "grad_norm": 7.967410965648014e-06,
      "learning_rate": 0.2774694163534073,
      "loss": 0.0,
      "num_input_tokens_seen": 1979408,
      "step": 7070
    },
    {
      "epoch": 78.61111111111111,
      "grad_norm": 5.319759566191351e-06,
      "learning_rate": 0.27743835709299614,
      "loss": 0.0,
      "num_input_tokens_seen": 1980800,
      "step": 7075
    },
    {
      "epoch": 78.66666666666667,
      "grad_norm": 6.188789029692998e-06,
      "learning_rate": 0.2774072781799888,
      "loss": 0.0,
      "num_input_tokens_seen": 1982176,
      "step": 7080
    },
    {
      "epoch": 78.72222222222223,
      "grad_norm": 5.021844117436558e-06,
      "learning_rate": 0.27737617961917804,
      "loss": 0.0,
      "num_input_tokens_seen": 1983584,
      "step": 7085
    },
    {
      "epoch": 78.77777777777777,
      "grad_norm": 8.752772373554762e-06,
      "learning_rate": 0.27734506141535964,
      "loss": 0.0,
      "num_input_tokens_seen": 1984976,
      "step": 7090
    },
    {
      "epoch": 78.83333333333333,
      "grad_norm": 7.28816894479678e-06,
      "learning_rate": 0.2773139235733325,
      "loss": 0.0,
      "num_input_tokens_seen": 1986384,
      "step": 7095
    },
    {
      "epoch": 78.88888888888889,
      "grad_norm": 4.017892024421599e-06,
      "learning_rate": 0.2772827660978984,
      "loss": 0.0,
      "num_input_tokens_seen": 1987792,
      "step": 7100
    },
    {
      "epoch": 78.94444444444444,
      "grad_norm": 1.4519520163958077e-06,
      "learning_rate": 0.27725158899386226,
      "loss": 0.0,
      "num_input_tokens_seen": 1989216,
      "step": 7105
    },
    {
      "epoch": 79.0,
      "grad_norm": 5.216769750404637e-06,
      "learning_rate": 0.27722039226603196,
      "loss": 0.0,
      "num_input_tokens_seen": 1990624,
      "step": 7110
    },
    {
      "epoch": 79.05555555555556,
      "grad_norm": 5.292419700708706e-06,
      "learning_rate": 0.2771891759192184,
      "loss": 0.0,
      "num_input_tokens_seen": 1992048,
      "step": 7115
    },
    {
      "epoch": 79.11111111111111,
      "grad_norm": 5.056082841292664e-07,
      "learning_rate": 0.2771579399582355,
      "loss": 0.0,
      "num_input_tokens_seen": 1993440,
      "step": 7120
    },
    {
      "epoch": 79.16666666666667,
      "grad_norm": 5.0942230700457e-06,
      "learning_rate": 0.2771266843879004,
      "loss": 0.0,
      "num_input_tokens_seen": 1994816,
      "step": 7125
    },
    {
      "epoch": 79.22222222222223,
      "grad_norm": 3.1701874831924215e-06,
      "learning_rate": 0.2770954092130329,
      "loss": 0.0,
      "num_input_tokens_seen": 1996224,
      "step": 7130
    },
    {
      "epoch": 79.27777777777777,
      "grad_norm": 5.438195785245625e-06,
      "learning_rate": 0.27706411443845613,
      "loss": 0.0,
      "num_input_tokens_seen": 1997616,
      "step": 7135
    },
    {
      "epoch": 79.33333333333333,
      "grad_norm": 4.55377767138998e-06,
      "learning_rate": 0.27703280006899617,
      "loss": 0.0,
      "num_input_tokens_seen": 1999008,
      "step": 7140
    },
    {
      "epoch": 79.38888888888889,
      "grad_norm": 5.447279249892745e-07,
      "learning_rate": 0.277001466109482,
      "loss": 0.0,
      "num_input_tokens_seen": 2000368,
      "step": 7145
    },
    {
      "epoch": 79.44444444444444,
      "grad_norm": 9.22308572626207e-06,
      "learning_rate": 0.2769701125647458,
      "loss": 0.0,
      "num_input_tokens_seen": 2001824,
      "step": 7150
    },
    {
      "epoch": 79.5,
      "grad_norm": 6.308107003860641e-06,
      "learning_rate": 0.27693873943962266,
      "loss": 0.0,
      "num_input_tokens_seen": 2003200,
      "step": 7155
    },
    {
      "epoch": 79.55555555555556,
      "grad_norm": 8.961037565313745e-06,
      "learning_rate": 0.2769073467389506,
      "loss": 0.0,
      "num_input_tokens_seen": 2004576,
      "step": 7160
    },
    {
      "epoch": 79.61111111111111,
      "grad_norm": 5.590718956227647e-06,
      "learning_rate": 0.2768759344675709,
      "loss": 0.0,
      "num_input_tokens_seen": 2005952,
      "step": 7165
    },
    {
      "epoch": 79.66666666666667,
      "grad_norm": 2.422308170935139e-06,
      "learning_rate": 0.27684450263032767,
      "loss": 0.0,
      "num_input_tokens_seen": 2007344,
      "step": 7170
    },
    {
      "epoch": 79.72222222222223,
      "grad_norm": 3.688151309688692e-06,
      "learning_rate": 0.2768130512320682,
      "loss": 0.0,
      "num_input_tokens_seen": 2008784,
      "step": 7175
    },
    {
      "epoch": 79.77777777777777,
      "grad_norm": 8.728067768970504e-06,
      "learning_rate": 0.27678158027764244,
      "loss": 0.0,
      "num_input_tokens_seen": 2010208,
      "step": 7180
    },
    {
      "epoch": 79.83333333333333,
      "grad_norm": 2.5752865440153982e-06,
      "learning_rate": 0.27675008977190385,
      "loss": 0.0,
      "num_input_tokens_seen": 2011568,
      "step": 7185
    },
    {
      "epoch": 79.88888888888889,
      "grad_norm": 4.269105374987703e-06,
      "learning_rate": 0.2767185797197086,
      "loss": 0.0,
      "num_input_tokens_seen": 2012976,
      "step": 7190
    },
    {
      "epoch": 79.94444444444444,
      "grad_norm": 3.083168166995165e-06,
      "learning_rate": 0.2766870501259159,
      "loss": 0.0,
      "num_input_tokens_seen": 2014384,
      "step": 7195
    },
    {
      "epoch": 80.0,
      "grad_norm": 1.9325120774738025e-06,
      "learning_rate": 0.276655500995388,
      "loss": 0.0,
      "num_input_tokens_seen": 2015792,
      "step": 7200
    },
    {
      "epoch": 80.0,
      "eval_loss": 0.9045764207839966,
      "eval_runtime": 1.1818,
      "eval_samples_per_second": 33.847,
      "eval_steps_per_second": 16.924,
      "num_input_tokens_seen": 2015792,
      "step": 7200
    },
    {
      "epoch": 80.05555555555556,
      "grad_norm": 4.866971721639857e-06,
      "learning_rate": 0.27662393233299015,
      "loss": 0.0,
      "num_input_tokens_seen": 2017184,
      "step": 7205
    },
    {
      "epoch": 80.11111111111111,
      "grad_norm": 6.563696388184326e-06,
      "learning_rate": 0.27659234414359074,
      "loss": 0.0,
      "num_input_tokens_seen": 2018592,
      "step": 7210
    },
    {
      "epoch": 80.16666666666667,
      "grad_norm": 4.5101710384187754e-06,
      "learning_rate": 0.27656073643206097,
      "loss": 0.0,
      "num_input_tokens_seen": 2020000,
      "step": 7215
    },
    {
      "epoch": 80.22222222222223,
      "grad_norm": 7.51202742321766e-06,
      "learning_rate": 0.27652910920327517,
      "loss": 0.0,
      "num_input_tokens_seen": 2021440,
      "step": 7220
    },
    {
      "epoch": 80.27777777777777,
      "grad_norm": 1.5902762697805883e-06,
      "learning_rate": 0.2764974624621107,
      "loss": 0.0,
      "num_input_tokens_seen": 2022832,
      "step": 7225
    },
    {
      "epoch": 80.33333333333333,
      "grad_norm": 3.0314847663248656e-06,
      "learning_rate": 0.2764657962134479,
      "loss": 0.0,
      "num_input_tokens_seen": 2024224,
      "step": 7230
    },
    {
      "epoch": 80.38888888888889,
      "grad_norm": 1.4903860119375167e-06,
      "learning_rate": 0.27643411046217,
      "loss": 0.0,
      "num_input_tokens_seen": 2025632,
      "step": 7235
    },
    {
      "epoch": 80.44444444444444,
      "grad_norm": 5.059404884377727e-06,
      "learning_rate": 0.27640240521316334,
      "loss": 0.0,
      "num_input_tokens_seen": 2027008,
      "step": 7240
    },
    {
      "epoch": 80.5,
      "grad_norm": 5.106260800857854e-07,
      "learning_rate": 0.2763706804713174,
      "loss": 0.0,
      "num_input_tokens_seen": 2028448,
      "step": 7245
    },
    {
      "epoch": 80.55555555555556,
      "grad_norm": 9.301104455516906e-07,
      "learning_rate": 0.2763389362415245,
      "loss": 0.0,
      "num_input_tokens_seen": 2029824,
      "step": 7250
    },
    {
      "epoch": 80.61111111111111,
      "grad_norm": 1.3470765907186433e-06,
      "learning_rate": 0.27630717252867987,
      "loss": 0.0,
      "num_input_tokens_seen": 2031200,
      "step": 7255
    },
    {
      "epoch": 80.66666666666667,
      "grad_norm": 3.826246029348113e-06,
      "learning_rate": 0.276275389337682,
      "loss": 0.0,
      "num_input_tokens_seen": 2032624,
      "step": 7260
    },
    {
      "epoch": 80.72222222222223,
      "grad_norm": 5.408480319601949e-06,
      "learning_rate": 0.2762435866734322,
      "loss": 0.0,
      "num_input_tokens_seen": 2034016,
      "step": 7265
    },
    {
      "epoch": 80.77777777777777,
      "grad_norm": 5.882081495656166e-06,
      "learning_rate": 0.27621176454083485,
      "loss": 0.0,
      "num_input_tokens_seen": 2035440,
      "step": 7270
    },
    {
      "epoch": 80.83333333333333,
      "grad_norm": 3.7139323012524983e-06,
      "learning_rate": 0.2761799229447973,
      "loss": 0.0,
      "num_input_tokens_seen": 2036832,
      "step": 7275
    },
    {
      "epoch": 80.88888888888889,
      "grad_norm": 1.1888682820426766e-06,
      "learning_rate": 0.27614806189023006,
      "loss": 0.0,
      "num_input_tokens_seen": 2038192,
      "step": 7280
    },
    {
      "epoch": 80.94444444444444,
      "grad_norm": 6.516352186736185e-06,
      "learning_rate": 0.27611618138204636,
      "loss": 0.0,
      "num_input_tokens_seen": 2039584,
      "step": 7285
    },
    {
      "epoch": 81.0,
      "grad_norm": 2.064411773972097e-06,
      "learning_rate": 0.2760842814251626,
      "loss": 0.0,
      "num_input_tokens_seen": 2040992,
      "step": 7290
    },
    {
      "epoch": 81.05555555555556,
      "grad_norm": 1.8761942328637815e-06,
      "learning_rate": 0.2760523620244982,
      "loss": 0.0,
      "num_input_tokens_seen": 2042352,
      "step": 7295
    },
    {
      "epoch": 81.11111111111111,
      "grad_norm": 2.43767271967954e-06,
      "learning_rate": 0.27602042318497544,
      "loss": 0.0,
      "num_input_tokens_seen": 2043776,
      "step": 7300
    },
    {
      "epoch": 81.16666666666667,
      "grad_norm": 4.573820660880301e-06,
      "learning_rate": 0.2759884649115198,
      "loss": 0.0,
      "num_input_tokens_seen": 2045168,
      "step": 7305
    },
    {
      "epoch": 81.22222222222223,
      "grad_norm": 8.84137989487499e-06,
      "learning_rate": 0.2759564872090596,
      "loss": 0.0,
      "num_input_tokens_seen": 2046592,
      "step": 7310
    },
    {
      "epoch": 81.27777777777777,
      "grad_norm": 3.413454805922811e-06,
      "learning_rate": 0.2759244900825262,
      "loss": 0.0,
      "num_input_tokens_seen": 2047984,
      "step": 7315
    },
    {
      "epoch": 81.33333333333333,
      "grad_norm": 1.8367650227446575e-06,
      "learning_rate": 0.2758924735368539,
      "loss": 0.0,
      "num_input_tokens_seen": 2049408,
      "step": 7320
    },
    {
      "epoch": 81.38888888888889,
      "grad_norm": 2.5514607386867283e-06,
      "learning_rate": 0.27586043757698014,
      "loss": 0.0,
      "num_input_tokens_seen": 2050800,
      "step": 7325
    },
    {
      "epoch": 81.44444444444444,
      "grad_norm": 1.069715494850243e-06,
      "learning_rate": 0.27582838220784534,
      "loss": 0.0,
      "num_input_tokens_seen": 2052224,
      "step": 7330
    },
    {
      "epoch": 81.5,
      "grad_norm": 4.821566562895896e-06,
      "learning_rate": 0.27579630743439265,
      "loss": 0.0,
      "num_input_tokens_seen": 2053616,
      "step": 7335
    },
    {
      "epoch": 81.55555555555556,
      "grad_norm": 1.980033630388789e-06,
      "learning_rate": 0.2757642132615686,
      "loss": 0.0,
      "num_input_tokens_seen": 2055008,
      "step": 7340
    },
    {
      "epoch": 81.61111111111111,
      "grad_norm": 4.7664070734754205e-06,
      "learning_rate": 0.2757320996943223,
      "loss": 0.0,
      "num_input_tokens_seen": 2056416,
      "step": 7345
    },
    {
      "epoch": 81.66666666666667,
      "grad_norm": 6.261182647904207e-07,
      "learning_rate": 0.2756999667376062,
      "loss": 0.0,
      "num_input_tokens_seen": 2057856,
      "step": 7350
    },
    {
      "epoch": 81.72222222222223,
      "grad_norm": 7.350895430136006e-07,
      "learning_rate": 0.2756678143963756,
      "loss": 0.0,
      "num_input_tokens_seen": 2059248,
      "step": 7355
    },
    {
      "epoch": 81.77777777777777,
      "grad_norm": 1.5895537899268675e-06,
      "learning_rate": 0.2756356426755888,
      "loss": 0.0,
      "num_input_tokens_seen": 2060624,
      "step": 7360
    },
    {
      "epoch": 81.83333333333333,
      "grad_norm": 2.586308482932509e-07,
      "learning_rate": 0.27560345158020705,
      "loss": 0.0,
      "num_input_tokens_seen": 2062000,
      "step": 7365
    },
    {
      "epoch": 81.88888888888889,
      "grad_norm": 5.500627139554126e-06,
      "learning_rate": 0.27557124111519465,
      "loss": 0.0,
      "num_input_tokens_seen": 2063408,
      "step": 7370
    },
    {
      "epoch": 81.94444444444444,
      "grad_norm": 6.090338047215482e-06,
      "learning_rate": 0.27553901128551883,
      "loss": 0.0,
      "num_input_tokens_seen": 2064816,
      "step": 7375
    },
    {
      "epoch": 82.0,
      "grad_norm": 2.6549771519057686e-06,
      "learning_rate": 0.2755067620961498,
      "loss": 0.0,
      "num_input_tokens_seen": 2066240,
      "step": 7380
    },
    {
      "epoch": 82.05555555555556,
      "grad_norm": 5.658846475853352e-06,
      "learning_rate": 0.27547449355206094,
      "loss": 0.0,
      "num_input_tokens_seen": 2067632,
      "step": 7385
    },
    {
      "epoch": 82.11111111111111,
      "grad_norm": 1.711818867988768e-06,
      "learning_rate": 0.2754422056582283,
      "loss": 0.0,
      "num_input_tokens_seen": 2069008,
      "step": 7390
    },
    {
      "epoch": 82.16666666666667,
      "grad_norm": 1.7525447901789448e-06,
      "learning_rate": 0.27540989841963115,
      "loss": 0.0,
      "num_input_tokens_seen": 2070400,
      "step": 7395
    },
    {
      "epoch": 82.22222222222223,
      "grad_norm": 3.269062062827288e-06,
      "learning_rate": 0.27537757184125167,
      "loss": 0.0,
      "num_input_tokens_seen": 2071808,
      "step": 7400
    },
    {
      "epoch": 82.22222222222223,
      "eval_loss": 0.9207562208175659,
      "eval_runtime": 1.1856,
      "eval_samples_per_second": 33.739,
      "eval_steps_per_second": 16.87,
      "num_input_tokens_seen": 2071808,
      "step": 7400
    },
    {
      "epoch": 82.27777777777777,
      "grad_norm": 1.0193289199378341e-06,
      "learning_rate": 0.275345225928075,
      "loss": 0.0,
      "num_input_tokens_seen": 2073216,
      "step": 7405
    },
    {
      "epoch": 82.33333333333333,
      "grad_norm": 4.95802896693931e-06,
      "learning_rate": 0.2753128606850893,
      "loss": 0.0,
      "num_input_tokens_seen": 2074624,
      "step": 7410
    },
    {
      "epoch": 82.38888888888889,
      "grad_norm": 4.3510235627763905e-06,
      "learning_rate": 0.2752804761172858,
      "loss": 0.0,
      "num_input_tokens_seen": 2076000,
      "step": 7415
    },
    {
      "epoch": 82.44444444444444,
      "grad_norm": 6.025321454217192e-06,
      "learning_rate": 0.27524807222965836,
      "loss": 0.0,
      "num_input_tokens_seen": 2077424,
      "step": 7420
    },
    {
      "epoch": 82.5,
      "grad_norm": 1.0395538993179798e-05,
      "learning_rate": 0.27521564902720436,
      "loss": 0.0,
      "num_input_tokens_seen": 2078832,
      "step": 7425
    },
    {
      "epoch": 82.55555555555556,
      "grad_norm": 9.455799840907275e-07,
      "learning_rate": 0.2751832065149236,
      "loss": 0.0,
      "num_input_tokens_seen": 2080240,
      "step": 7430
    },
    {
      "epoch": 82.61111111111111,
      "grad_norm": 1.495848437116365e-06,
      "learning_rate": 0.2751507446978193,
      "loss": 0.0,
      "num_input_tokens_seen": 2081632,
      "step": 7435
    },
    {
      "epoch": 82.66666666666667,
      "grad_norm": 2.148134853996453e-06,
      "learning_rate": 0.2751182635808974,
      "loss": 0.0,
      "num_input_tokens_seen": 2083056,
      "step": 7440
    },
    {
      "epoch": 82.72222222222223,
      "grad_norm": 4.959236434842751e-07,
      "learning_rate": 0.27508576316916694,
      "loss": 0.0,
      "num_input_tokens_seen": 2084416,
      "step": 7445
    },
    {
      "epoch": 82.77777777777777,
      "grad_norm": 2.8839558581239544e-06,
      "learning_rate": 0.2750532434676399,
      "loss": 0.0,
      "num_input_tokens_seen": 2085808,
      "step": 7450
    },
    {
      "epoch": 82.83333333333333,
      "grad_norm": 1.984183882086654e-06,
      "learning_rate": 0.27502070448133115,
      "loss": 0.0,
      "num_input_tokens_seen": 2087216,
      "step": 7455
    },
    {
      "epoch": 82.88888888888889,
      "grad_norm": 3.594393092498649e-06,
      "learning_rate": 0.2749881462152587,
      "loss": 0.0,
      "num_input_tokens_seen": 2088544,
      "step": 7460
    },
    {
      "epoch": 82.94444444444444,
      "grad_norm": 3.427319370530313e-06,
      "learning_rate": 0.2749555686744434,
      "loss": 0.0,
      "num_input_tokens_seen": 2089920,
      "step": 7465
    },
    {
      "epoch": 83.0,
      "grad_norm": 5.963067451375537e-06,
      "learning_rate": 0.2749229718639091,
      "loss": 0.0,
      "num_input_tokens_seen": 2091376,
      "step": 7470
    },
    {
      "epoch": 83.05555555555556,
      "grad_norm": 7.430026585097949e-07,
      "learning_rate": 0.27489035578868265,
      "loss": 0.0,
      "num_input_tokens_seen": 2092784,
      "step": 7475
    },
    {
      "epoch": 83.11111111111111,
      "grad_norm": 1.6374498272853089e-06,
      "learning_rate": 0.2748577204537939,
      "loss": 0.0,
      "num_input_tokens_seen": 2094192,
      "step": 7480
    },
    {
      "epoch": 83.16666666666667,
      "grad_norm": 2.3459651856683195e-06,
      "learning_rate": 0.2748250658642756,
      "loss": 0.0,
      "num_input_tokens_seen": 2095568,
      "step": 7485
    },
    {
      "epoch": 83.22222222222223,
      "grad_norm": 2.640099182826816e-06,
      "learning_rate": 0.2747923920251634,
      "loss": 0.0,
      "num_input_tokens_seen": 2096960,
      "step": 7490
    },
    {
      "epoch": 83.27777777777777,
      "grad_norm": 5.6452458920830395e-06,
      "learning_rate": 0.27475969894149627,
      "loss": 0.0,
      "num_input_tokens_seen": 2098320,
      "step": 7495
    },
    {
      "epoch": 83.33333333333333,
      "grad_norm": 7.827381523384247e-06,
      "learning_rate": 0.2747269866183156,
      "loss": 0.0,
      "num_input_tokens_seen": 2099744,
      "step": 7500
    },
    {
      "epoch": 83.38888888888889,
      "grad_norm": 2.108684782342607e-07,
      "learning_rate": 0.27469425506066625,
      "loss": 0.0,
      "num_input_tokens_seen": 2101168,
      "step": 7505
    },
    {
      "epoch": 83.44444444444444,
      "grad_norm": 4.781537882081466e-06,
      "learning_rate": 0.27466150427359576,
      "loss": 0.0,
      "num_input_tokens_seen": 2102576,
      "step": 7510
    },
    {
      "epoch": 83.5,
      "grad_norm": 1.1090461384810624e-06,
      "learning_rate": 0.2746287342621547,
      "loss": 0.0,
      "num_input_tokens_seen": 2103984,
      "step": 7515
    },
    {
      "epoch": 83.55555555555556,
      "grad_norm": 7.013543950051826e-07,
      "learning_rate": 0.2745959450313966,
      "loss": 0.0,
      "num_input_tokens_seen": 2105392,
      "step": 7520
    },
    {
      "epoch": 83.61111111111111,
      "grad_norm": 4.212501607980812e-06,
      "learning_rate": 0.27456313658637804,
      "loss": 0.0,
      "num_input_tokens_seen": 2106784,
      "step": 7525
    },
    {
      "epoch": 83.66666666666667,
      "grad_norm": 4.97922064823797e-06,
      "learning_rate": 0.27453030893215846,
      "loss": 0.0,
      "num_input_tokens_seen": 2108128,
      "step": 7530
    },
    {
      "epoch": 83.72222222222223,
      "grad_norm": 1.44629746046121e-06,
      "learning_rate": 0.2744974620738003,
      "loss": 0.0,
      "num_input_tokens_seen": 2109536,
      "step": 7535
    },
    {
      "epoch": 83.77777777777777,
      "grad_norm": 1.4059397699384135e-06,
      "learning_rate": 0.27446459601636897,
      "loss": 0.0,
      "num_input_tokens_seen": 2110944,
      "step": 7540
    },
    {
      "epoch": 83.83333333333333,
      "grad_norm": 4.0820500544214156e-06,
      "learning_rate": 0.2744317107649328,
      "loss": 0.0,
      "num_input_tokens_seen": 2112368,
      "step": 7545
    },
    {
      "epoch": 83.88888888888889,
      "grad_norm": 3.534680672601098e-06,
      "learning_rate": 0.2743988063245631,
      "loss": 0.0,
      "num_input_tokens_seen": 2113792,
      "step": 7550
    },
    {
      "epoch": 83.94444444444444,
      "grad_norm": 4.030384275210963e-07,
      "learning_rate": 0.2743658827003342,
      "loss": 0.0,
      "num_input_tokens_seen": 2115168,
      "step": 7555
    },
    {
      "epoch": 84.0,
      "grad_norm": 2.2911913220013957e-06,
      "learning_rate": 0.27433293989732327,
      "loss": 0.0,
      "num_input_tokens_seen": 2116592,
      "step": 7560
    },
    {
      "epoch": 84.05555555555556,
      "grad_norm": 3.9140149965533055e-06,
      "learning_rate": 0.27429997792061056,
      "loss": 0.0,
      "num_input_tokens_seen": 2117984,
      "step": 7565
    },
    {
      "epoch": 84.11111111111111,
      "grad_norm": 1.2913029650007957e-06,
      "learning_rate": 0.27426699677527927,
      "loss": 0.0,
      "num_input_tokens_seen": 2119392,
      "step": 7570
    },
    {
      "epoch": 84.16666666666667,
      "grad_norm": 4.1120060814137105e-06,
      "learning_rate": 0.2742339964664154,
      "loss": 0.0,
      "num_input_tokens_seen": 2120800,
      "step": 7575
    },
    {
      "epoch": 84.22222222222223,
      "grad_norm": 3.7084598716319306e-06,
      "learning_rate": 0.274200976999108,
      "loss": 0.0,
      "num_input_tokens_seen": 2122192,
      "step": 7580
    },
    {
      "epoch": 84.27777777777777,
      "grad_norm": 2.7392038646212313e-06,
      "learning_rate": 0.27416793837844916,
      "loss": 0.0,
      "num_input_tokens_seen": 2123600,
      "step": 7585
    },
    {
      "epoch": 84.33333333333333,
      "grad_norm": 1.7261030507143005e-06,
      "learning_rate": 0.27413488060953384,
      "loss": 0.0,
      "num_input_tokens_seen": 2125056,
      "step": 7590
    },
    {
      "epoch": 84.38888888888889,
      "grad_norm": 1.1130373422929551e-06,
      "learning_rate": 0.27410180369745996,
      "loss": 0.0,
      "num_input_tokens_seen": 2126448,
      "step": 7595
    },
    {
      "epoch": 84.44444444444444,
      "grad_norm": 2.280224180140067e-06,
      "learning_rate": 0.27406870764732844,
      "loss": 0.0,
      "num_input_tokens_seen": 2127808,
      "step": 7600
    },
    {
      "epoch": 84.44444444444444,
      "eval_loss": 0.9379554986953735,
      "eval_runtime": 1.1865,
      "eval_samples_per_second": 33.712,
      "eval_steps_per_second": 16.856,
      "num_input_tokens_seen": 2127808,
      "step": 7600
    },
    {
      "epoch": 84.5,
      "grad_norm": 1.1081963748438284e-05,
      "learning_rate": 0.27403559246424297,
      "loss": 0.0,
      "num_input_tokens_seen": 2129248,
      "step": 7605
    },
    {
      "epoch": 84.55555555555556,
      "grad_norm": 2.9749685381830204e-06,
      "learning_rate": 0.2740024581533105,
      "loss": 0.0,
      "num_input_tokens_seen": 2130688,
      "step": 7610
    },
    {
      "epoch": 84.61111111111111,
      "grad_norm": 3.0056162358960137e-06,
      "learning_rate": 0.2739693047196406,
      "loss": 0.0,
      "num_input_tokens_seen": 2132064,
      "step": 7615
    },
    {
      "epoch": 84.66666666666667,
      "grad_norm": 7.954120633257844e-07,
      "learning_rate": 0.27393613216834606,
      "loss": 0.0,
      "num_input_tokens_seen": 2133408,
      "step": 7620
    },
    {
      "epoch": 84.72222222222223,
      "grad_norm": 1.6979043948595063e-06,
      "learning_rate": 0.2739029405045424,
      "loss": 0.0,
      "num_input_tokens_seen": 2134784,
      "step": 7625
    },
    {
      "epoch": 84.77777777777777,
      "grad_norm": 1.2981480495000142e-06,
      "learning_rate": 0.2738697297333483,
      "loss": 0.0,
      "num_input_tokens_seen": 2136224,
      "step": 7630
    },
    {
      "epoch": 84.83333333333333,
      "grad_norm": 5.115105068398407e-06,
      "learning_rate": 0.2738364998598852,
      "loss": 0.0,
      "num_input_tokens_seen": 2137616,
      "step": 7635
    },
    {
      "epoch": 84.88888888888889,
      "grad_norm": 7.205815109045943e-07,
      "learning_rate": 0.27380325088927765,
      "loss": 0.0,
      "num_input_tokens_seen": 2139040,
      "step": 7640
    },
    {
      "epoch": 84.94444444444444,
      "grad_norm": 1.2706220786640188e-06,
      "learning_rate": 0.27376998282665294,
      "loss": 0.0,
      "num_input_tokens_seen": 2140416,
      "step": 7645
    },
    {
      "epoch": 85.0,
      "grad_norm": 3.001555114678922e-06,
      "learning_rate": 0.27373669567714154,
      "loss": 0.0,
      "num_input_tokens_seen": 2141824,
      "step": 7650
    },
    {
      "epoch": 85.05555555555556,
      "grad_norm": 4.537841050478164e-06,
      "learning_rate": 0.27370338944587663,
      "loss": 0.0,
      "num_input_tokens_seen": 2143248,
      "step": 7655
    },
    {
      "epoch": 85.11111111111111,
      "grad_norm": 1.4562044725607848e-06,
      "learning_rate": 0.27367006413799455,
      "loss": 0.0,
      "num_input_tokens_seen": 2144656,
      "step": 7660
    },
    {
      "epoch": 85.16666666666667,
      "grad_norm": 1.190223088087805e-06,
      "learning_rate": 0.2736367197586345,
      "loss": 0.0,
      "num_input_tokens_seen": 2146080,
      "step": 7665
    },
    {
      "epoch": 85.22222222222223,
      "grad_norm": 1.1619193173828535e-05,
      "learning_rate": 0.2736033563129385,
      "loss": 0.0,
      "num_input_tokens_seen": 2147488,
      "step": 7670
    },
    {
      "epoch": 85.27777777777777,
      "grad_norm": 3.532178652676521e-06,
      "learning_rate": 0.27356997380605164,
      "loss": 0.0,
      "num_input_tokens_seen": 2148864,
      "step": 7675
    },
    {
      "epoch": 85.33333333333333,
      "grad_norm": 3.762387223105179e-06,
      "learning_rate": 0.27353657224312194,
      "loss": 0.0,
      "num_input_tokens_seen": 2150272,
      "step": 7680
    },
    {
      "epoch": 85.38888888888889,
      "grad_norm": 1.7649006167630432e-06,
      "learning_rate": 0.2735031516293004,
      "loss": 0.0,
      "num_input_tokens_seen": 2151664,
      "step": 7685
    },
    {
      "epoch": 85.44444444444444,
      "grad_norm": 3.2117093269334873e-06,
      "learning_rate": 0.2734697119697408,
      "loss": 0.0,
      "num_input_tokens_seen": 2153088,
      "step": 7690
    },
    {
      "epoch": 85.5,
      "grad_norm": 7.09705204826605e-07,
      "learning_rate": 0.27343625326959997,
      "loss": 0.0,
      "num_input_tokens_seen": 2154512,
      "step": 7695
    },
    {
      "epoch": 85.55555555555556,
      "grad_norm": 3.3324104151688516e-06,
      "learning_rate": 0.27340277553403775,
      "loss": 0.0,
      "num_input_tokens_seen": 2155904,
      "step": 7700
    },
    {
      "epoch": 85.61111111111111,
      "grad_norm": 4.4632884055317845e-06,
      "learning_rate": 0.2733692787682167,
      "loss": 0.0,
      "num_input_tokens_seen": 2157264,
      "step": 7705
    },
    {
      "epoch": 85.66666666666667,
      "grad_norm": 2.7329808744980255e-06,
      "learning_rate": 0.27333576297730255,
      "loss": 0.0,
      "num_input_tokens_seen": 2158688,
      "step": 7710
    },
    {
      "epoch": 85.72222222222223,
      "grad_norm": 4.317815637477906e-06,
      "learning_rate": 0.2733022281664638,
      "loss": 0.0,
      "num_input_tokens_seen": 2160096,
      "step": 7715
    },
    {
      "epoch": 85.77777777777777,
      "grad_norm": 1.8035358380075195e-06,
      "learning_rate": 0.273268674340872,
      "loss": 0.0,
      "num_input_tokens_seen": 2161520,
      "step": 7720
    },
    {
      "epoch": 85.83333333333333,
      "grad_norm": 2.8758915959770093e-06,
      "learning_rate": 0.27323510150570146,
      "loss": 0.0,
      "num_input_tokens_seen": 2162928,
      "step": 7725
    },
    {
      "epoch": 85.88888888888889,
      "grad_norm": 1.6780591067799833e-06,
      "learning_rate": 0.27320150966612966,
      "loss": 0.0,
      "num_input_tokens_seen": 2164336,
      "step": 7730
    },
    {
      "epoch": 85.94444444444444,
      "grad_norm": 2.7971600502496585e-07,
      "learning_rate": 0.2731678988273368,
      "loss": 0.0,
      "num_input_tokens_seen": 2165760,
      "step": 7735
    },
    {
      "epoch": 86.0,
      "grad_norm": 2.1381092665251344e-06,
      "learning_rate": 0.27313426899450605,
      "loss": 0.0,
      "num_input_tokens_seen": 2167152,
      "step": 7740
    },
    {
      "epoch": 86.05555555555556,
      "grad_norm": 2.1315024696377805e-06,
      "learning_rate": 0.27310062017282366,
      "loss": 0.0,
      "num_input_tokens_seen": 2168544,
      "step": 7745
    },
    {
      "epoch": 86.11111111111111,
      "grad_norm": 4.4624835027207155e-06,
      "learning_rate": 0.2730669523674787,
      "loss": 0.0,
      "num_input_tokens_seen": 2169904,
      "step": 7750
    },
    {
      "epoch": 86.16666666666667,
      "grad_norm": 2.3826969481888227e-06,
      "learning_rate": 0.2730332655836631,
      "loss": 0.0,
      "num_input_tokens_seen": 2171296,
      "step": 7755
    },
    {
      "epoch": 86.22222222222223,
      "grad_norm": 3.2033378829510184e-06,
      "learning_rate": 0.2729995598265718,
      "loss": 0.0,
      "num_input_tokens_seen": 2172704,
      "step": 7760
    },
    {
      "epoch": 86.27777777777777,
      "grad_norm": 9.285733540309593e-06,
      "learning_rate": 0.2729658351014027,
      "loss": 0.0,
      "num_input_tokens_seen": 2174112,
      "step": 7765
    },
    {
      "epoch": 86.33333333333333,
      "grad_norm": 5.018098363507306e-07,
      "learning_rate": 0.27293209141335656,
      "loss": 0.0,
      "num_input_tokens_seen": 2175520,
      "step": 7770
    },
    {
      "epoch": 86.38888888888889,
      "grad_norm": 1.1597071534197312e-06,
      "learning_rate": 0.27289832876763703,
      "loss": 0.0,
      "num_input_tokens_seen": 2176928,
      "step": 7775
    },
    {
      "epoch": 86.44444444444444,
      "grad_norm": 5.780192964266462e-07,
      "learning_rate": 0.27286454716945074,
      "loss": 0.0,
      "num_input_tokens_seen": 2178320,
      "step": 7780
    },
    {
      "epoch": 86.5,
      "grad_norm": 3.4361278267169837e-07,
      "learning_rate": 0.27283074662400725,
      "loss": 0.0,
      "num_input_tokens_seen": 2179728,
      "step": 7785
    },
    {
      "epoch": 86.55555555555556,
      "grad_norm": 4.497848294704454e-06,
      "learning_rate": 0.2727969271365191,
      "loss": 0.0,
      "num_input_tokens_seen": 2181088,
      "step": 7790
    },
    {
      "epoch": 86.61111111111111,
      "grad_norm": 2.941244247267605e-06,
      "learning_rate": 0.2727630887122016,
      "loss": 0.0,
      "num_input_tokens_seen": 2182480,
      "step": 7795
    },
    {
      "epoch": 86.66666666666667,
      "grad_norm": 6.922204192960635e-06,
      "learning_rate": 0.27272923135627314,
      "loss": 0.0,
      "num_input_tokens_seen": 2183888,
      "step": 7800
    },
    {
      "epoch": 86.66666666666667,
      "eval_loss": 0.9472252726554871,
      "eval_runtime": 1.2334,
      "eval_samples_per_second": 32.43,
      "eval_steps_per_second": 16.215,
      "num_input_tokens_seen": 2183888,
      "step": 7800
    },
    {
      "epoch": 86.72222222222223,
      "grad_norm": 4.887409090770234e-07,
      "learning_rate": 0.2726953550739548,
      "loss": 0.0,
      "num_input_tokens_seen": 2185296,
      "step": 7805
    },
    {
      "epoch": 86.77777777777777,
      "grad_norm": 8.333271352967131e-07,
      "learning_rate": 0.27266145987047086,
      "loss": 0.0,
      "num_input_tokens_seen": 2186672,
      "step": 7810
    },
    {
      "epoch": 86.83333333333333,
      "grad_norm": 7.77917989580601e-07,
      "learning_rate": 0.27262754575104836,
      "loss": 0.0,
      "num_input_tokens_seen": 2188128,
      "step": 7815
    },
    {
      "epoch": 86.88888888888889,
      "grad_norm": 1.1962334838244715e-06,
      "learning_rate": 0.27259361272091726,
      "loss": 0.0,
      "num_input_tokens_seen": 2189536,
      "step": 7820
    },
    {
      "epoch": 86.94444444444444,
      "grad_norm": 5.091992534289602e-07,
      "learning_rate": 0.27255966078531046,
      "loss": 0.0,
      "num_input_tokens_seen": 2190880,
      "step": 7825
    },
    {
      "epoch": 87.0,
      "grad_norm": 1.169265374301176e-06,
      "learning_rate": 0.2725256899494638,
      "loss": 0.0,
      "num_input_tokens_seen": 2192304,
      "step": 7830
    },
    {
      "epoch": 87.05555555555556,
      "grad_norm": 3.3655485367489746e-06,
      "learning_rate": 0.272491700218616,
      "loss": 0.0,
      "num_input_tokens_seen": 2193696,
      "step": 7835
    },
    {
      "epoch": 87.11111111111111,
      "grad_norm": 3.530386948114028e-06,
      "learning_rate": 0.27245769159800876,
      "loss": 0.0,
      "num_input_tokens_seen": 2195104,
      "step": 7840
    },
    {
      "epoch": 87.16666666666667,
      "grad_norm": 4.1963690478041826e-07,
      "learning_rate": 0.2724236640928865,
      "loss": 0.0,
      "num_input_tokens_seen": 2196480,
      "step": 7845
    },
    {
      "epoch": 87.22222222222223,
      "grad_norm": 1.3709018276131246e-06,
      "learning_rate": 0.27238961770849673,
      "loss": 0.0,
      "num_input_tokens_seen": 2197856,
      "step": 7850
    },
    {
      "epoch": 87.27777777777777,
      "grad_norm": 2.2675742457067827e-06,
      "learning_rate": 0.27235555245008997,
      "loss": 0.0,
      "num_input_tokens_seen": 2199248,
      "step": 7855
    },
    {
      "epoch": 87.33333333333333,
      "grad_norm": 3.1590689104632474e-06,
      "learning_rate": 0.2723214683229193,
      "loss": 0.0,
      "num_input_tokens_seen": 2200640,
      "step": 7860
    },
    {
      "epoch": 87.38888888888889,
      "grad_norm": 2.5105653094215086e-06,
      "learning_rate": 0.27228736533224107,
      "loss": 0.0,
      "num_input_tokens_seen": 2202048,
      "step": 7865
    },
    {
      "epoch": 87.44444444444444,
      "grad_norm": 1.9995254660898354e-06,
      "learning_rate": 0.27225324348331437,
      "loss": 0.0,
      "num_input_tokens_seen": 2203472,
      "step": 7870
    },
    {
      "epoch": 87.5,
      "grad_norm": 2.3733864509267733e-06,
      "learning_rate": 0.27221910278140116,
      "loss": 0.0,
      "num_input_tokens_seen": 2204864,
      "step": 7875
    },
    {
      "epoch": 87.55555555555556,
      "grad_norm": 1.7817213802118204e-06,
      "learning_rate": 0.2721849432317664,
      "loss": 0.0,
      "num_input_tokens_seen": 2206288,
      "step": 7880
    },
    {
      "epoch": 87.61111111111111,
      "grad_norm": 2.2128504042484565e-06,
      "learning_rate": 0.2721507648396779,
      "loss": 0.0,
      "num_input_tokens_seen": 2207728,
      "step": 7885
    },
    {
      "epoch": 87.66666666666667,
      "grad_norm": 1.0028576298282132e-06,
      "learning_rate": 0.27211656761040653,
      "loss": 0.0,
      "num_input_tokens_seen": 2209136,
      "step": 7890
    },
    {
      "epoch": 87.72222222222223,
      "grad_norm": 2.6518741833569948e-06,
      "learning_rate": 0.2720823515492257,
      "loss": 0.0,
      "num_input_tokens_seen": 2210528,
      "step": 7895
    },
    {
      "epoch": 87.77777777777777,
      "grad_norm": 1.7873677506941021e-06,
      "learning_rate": 0.27204811666141215,
      "loss": 0.0,
      "num_input_tokens_seen": 2211904,
      "step": 7900
    },
    {
      "epoch": 87.83333333333333,
      "grad_norm": 9.992722880269866e-07,
      "learning_rate": 0.2720138629522452,
      "loss": 0.0,
      "num_input_tokens_seen": 2213264,
      "step": 7905
    },
    {
      "epoch": 87.88888888888889,
      "grad_norm": 4.626728696166538e-06,
      "learning_rate": 0.2719795904270073,
      "loss": 0.0,
      "num_input_tokens_seen": 2214688,
      "step": 7910
    },
    {
      "epoch": 87.94444444444444,
      "grad_norm": 7.387424147964339e-07,
      "learning_rate": 0.2719452990909837,
      "loss": 0.0,
      "num_input_tokens_seen": 2216080,
      "step": 7915
    },
    {
      "epoch": 88.0,
      "grad_norm": 2.3776028683641925e-06,
      "learning_rate": 0.2719109889494625,
      "loss": 0.0,
      "num_input_tokens_seen": 2217488,
      "step": 7920
    },
    {
      "epoch": 88.05555555555556,
      "grad_norm": 1.1097595233877655e-06,
      "learning_rate": 0.27187666000773475,
      "loss": 0.0,
      "num_input_tokens_seen": 2218864,
      "step": 7925
    },
    {
      "epoch": 88.11111111111111,
      "grad_norm": 3.2412447126262123e-06,
      "learning_rate": 0.2718423122710944,
      "loss": 0.0,
      "num_input_tokens_seen": 2220240,
      "step": 7930
    },
    {
      "epoch": 88.16666666666667,
      "grad_norm": 1.5817998928469024e-06,
      "learning_rate": 0.2718079457448384,
      "loss": 0.0,
      "num_input_tokens_seen": 2221616,
      "step": 7935
    },
    {
      "epoch": 88.22222222222223,
      "grad_norm": 1.7814006696426077e-06,
      "learning_rate": 0.27177356043426637,
      "loss": 0.0,
      "num_input_tokens_seen": 2222992,
      "step": 7940
    },
    {
      "epoch": 88.27777777777777,
      "grad_norm": 1.3071380635665264e-06,
      "learning_rate": 0.27173915634468104,
      "loss": 0.0,
      "num_input_tokens_seen": 2224368,
      "step": 7945
    },
    {
      "epoch": 88.33333333333333,
      "grad_norm": 1.8772367411656887e-06,
      "learning_rate": 0.27170473348138796,
      "loss": 0.0,
      "num_input_tokens_seen": 2225776,
      "step": 7950
    },
    {
      "epoch": 88.38888888888889,
      "grad_norm": 2.3286308987735538e-06,
      "learning_rate": 0.27167029184969554,
      "loss": 0.0,
      "num_input_tokens_seen": 2227184,
      "step": 7955
    },
    {
      "epoch": 88.44444444444444,
      "grad_norm": 1.279891421290813e-06,
      "learning_rate": 0.27163583145491504,
      "loss": 0.0,
      "num_input_tokens_seen": 2228608,
      "step": 7960
    },
    {
      "epoch": 88.5,
      "grad_norm": 5.7797724366537295e-06,
      "learning_rate": 0.2716013523023608,
      "loss": 0.0,
      "num_input_tokens_seen": 2230032,
      "step": 7965
    },
    {
      "epoch": 88.55555555555556,
      "grad_norm": 4.086020908289356e-06,
      "learning_rate": 0.27156685439734995,
      "loss": 0.0,
      "num_input_tokens_seen": 2231392,
      "step": 7970
    },
    {
      "epoch": 88.61111111111111,
      "grad_norm": 3.546315156199853e-06,
      "learning_rate": 0.2715323377452024,
      "loss": 0.0,
      "num_input_tokens_seen": 2232816,
      "step": 7975
    },
    {
      "epoch": 88.66666666666667,
      "grad_norm": 1.8270916370966006e-06,
      "learning_rate": 0.2714978023512411,
      "loss": 0.0,
      "num_input_tokens_seen": 2234224,
      "step": 7980
    },
    {
      "epoch": 88.72222222222223,
      "grad_norm": 2.2458771127276123e-06,
      "learning_rate": 0.2714632482207918,
      "loss": 0.0,
      "num_input_tokens_seen": 2235664,
      "step": 7985
    },
    {
      "epoch": 88.77777777777777,
      "grad_norm": 3.233097231714055e-06,
      "learning_rate": 0.2714286753591833,
      "loss": 0.0,
      "num_input_tokens_seen": 2237040,
      "step": 7990
    },
    {
      "epoch": 88.83333333333333,
      "grad_norm": 1.5740595245006261e-06,
      "learning_rate": 0.27139408377174706,
      "loss": 0.0,
      "num_input_tokens_seen": 2238432,
      "step": 7995
    },
    {
      "epoch": 88.88888888888889,
      "grad_norm": 1.3133011123045435e-07,
      "learning_rate": 0.27135947346381756,
      "loss": 0.0,
      "num_input_tokens_seen": 2239840,
      "step": 8000
    },
    {
      "epoch": 88.88888888888889,
      "eval_loss": 0.9389088749885559,
      "eval_runtime": 1.1808,
      "eval_samples_per_second": 33.874,
      "eval_steps_per_second": 16.937,
      "num_input_tokens_seen": 2239840,
      "step": 8000
    },
    {
      "epoch": 88.94444444444444,
      "grad_norm": 6.518417308143398e-07,
      "learning_rate": 0.2713248444407322,
      "loss": 0.0,
      "num_input_tokens_seen": 2241200,
      "step": 8005
    },
    {
      "epoch": 89.0,
      "grad_norm": 2.3614031761098886e-06,
      "learning_rate": 0.27129019670783106,
      "loss": 0.0,
      "num_input_tokens_seen": 2242608,
      "step": 8010
    },
    {
      "epoch": 89.05555555555556,
      "grad_norm": 6.897501862113131e-06,
      "learning_rate": 0.27125553027045746,
      "loss": 0.0,
      "num_input_tokens_seen": 2244016,
      "step": 8015
    },
    {
      "epoch": 89.11111111111111,
      "grad_norm": 1.3505660945156706e-06,
      "learning_rate": 0.2712208451339572,
      "loss": 0.0,
      "num_input_tokens_seen": 2245440,
      "step": 8020
    },
    {
      "epoch": 89.16666666666667,
      "grad_norm": 2.576270844656392e-06,
      "learning_rate": 0.27118614130367935,
      "loss": 0.0,
      "num_input_tokens_seen": 2246832,
      "step": 8025
    },
    {
      "epoch": 89.22222222222223,
      "grad_norm": 1.356253051199019e-06,
      "learning_rate": 0.2711514187849756,
      "loss": 0.0,
      "num_input_tokens_seen": 2248176,
      "step": 8030
    },
    {
      "epoch": 89.27777777777777,
      "grad_norm": 2.8178560569358524e-06,
      "learning_rate": 0.27111667758320057,
      "loss": 0.0,
      "num_input_tokens_seen": 2249568,
      "step": 8035
    },
    {
      "epoch": 89.33333333333333,
      "grad_norm": 2.560038012688892e-07,
      "learning_rate": 0.27108191770371176,
      "loss": 0.0,
      "num_input_tokens_seen": 2250976,
      "step": 8040
    },
    {
      "epoch": 89.38888888888889,
      "grad_norm": 8.09558969194768e-07,
      "learning_rate": 0.2710471391518697,
      "loss": 0.0,
      "num_input_tokens_seen": 2252384,
      "step": 8045
    },
    {
      "epoch": 89.44444444444444,
      "grad_norm": 1.951007106981706e-06,
      "learning_rate": 0.2710123419330375,
      "loss": 0.0,
      "num_input_tokens_seen": 2253792,
      "step": 8050
    },
    {
      "epoch": 89.5,
      "grad_norm": 8.973285048341495e-07,
      "learning_rate": 0.2709775260525816,
      "loss": 0.0,
      "num_input_tokens_seen": 2255168,
      "step": 8055
    },
    {
      "epoch": 89.55555555555556,
      "grad_norm": 1.4383288089447888e-06,
      "learning_rate": 0.27094269151587075,
      "loss": 0.0,
      "num_input_tokens_seen": 2256624,
      "step": 8060
    },
    {
      "epoch": 89.61111111111111,
      "grad_norm": 4.61542867924436e-07,
      "learning_rate": 0.27090783832827703,
      "loss": 0.0,
      "num_input_tokens_seen": 2258016,
      "step": 8065
    },
    {
      "epoch": 89.66666666666667,
      "grad_norm": 1.6156712945303298e-06,
      "learning_rate": 0.2708729664951753,
      "loss": 0.0,
      "num_input_tokens_seen": 2259456,
      "step": 8070
    },
    {
      "epoch": 89.72222222222223,
      "grad_norm": 9.455003464609035e-07,
      "learning_rate": 0.27083807602194304,
      "loss": 0.0,
      "num_input_tokens_seen": 2260880,
      "step": 8075
    },
    {
      "epoch": 89.77777777777777,
      "grad_norm": 2.6816433091880754e-06,
      "learning_rate": 0.270803166913961,
      "loss": 0.0,
      "num_input_tokens_seen": 2262272,
      "step": 8080
    },
    {
      "epoch": 89.83333333333333,
      "grad_norm": 2.8374157068356e-07,
      "learning_rate": 0.27076823917661247,
      "loss": 0.0,
      "num_input_tokens_seen": 2263632,
      "step": 8085
    },
    {
      "epoch": 89.88888888888889,
      "grad_norm": 1.3516536228053155e-06,
      "learning_rate": 0.2707332928152838,
      "loss": 0.0,
      "num_input_tokens_seen": 2265008,
      "step": 8090
    },
    {
      "epoch": 89.94444444444444,
      "grad_norm": 2.7903329282708e-06,
      "learning_rate": 0.2706983278353641,
      "loss": 0.0,
      "num_input_tokens_seen": 2266400,
      "step": 8095
    },
    {
      "epoch": 90.0,
      "grad_norm": 6.311323659247137e-07,
      "learning_rate": 0.27066334424224553,
      "loss": 0.0,
      "num_input_tokens_seen": 2267824,
      "step": 8100
    },
    {
      "epoch": 90.05555555555556,
      "grad_norm": 7.381691489172226e-07,
      "learning_rate": 0.27062834204132297,
      "loss": 0.0,
      "num_input_tokens_seen": 2269232,
      "step": 8105
    },
    {
      "epoch": 90.11111111111111,
      "grad_norm": 6.449372449424118e-07,
      "learning_rate": 0.27059332123799407,
      "loss": 0.0,
      "num_input_tokens_seen": 2270608,
      "step": 8110
    },
    {
      "epoch": 90.16666666666667,
      "grad_norm": 2.2140816327009816e-06,
      "learning_rate": 0.27055828183765956,
      "loss": 0.0,
      "num_input_tokens_seen": 2272048,
      "step": 8115
    },
    {
      "epoch": 90.22222222222223,
      "grad_norm": 3.0331105449477036e-07,
      "learning_rate": 0.270523223845723,
      "loss": 0.0,
      "num_input_tokens_seen": 2273440,
      "step": 8120
    },
    {
      "epoch": 90.27777777777777,
      "grad_norm": 4.314520083426032e-06,
      "learning_rate": 0.2704881472675907,
      "loss": 0.0,
      "num_input_tokens_seen": 2274832,
      "step": 8125
    },
    {
      "epoch": 90.33333333333333,
      "grad_norm": 3.6215755017110496e-07,
      "learning_rate": 0.270453052108672,
      "loss": 0.0,
      "num_input_tokens_seen": 2276256,
      "step": 8130
    },
    {
      "epoch": 90.38888888888889,
      "grad_norm": 4.173045908828499e-06,
      "learning_rate": 0.2704179383743789,
      "loss": 0.0,
      "num_input_tokens_seen": 2277648,
      "step": 8135
    },
    {
      "epoch": 90.44444444444444,
      "grad_norm": 4.046102901611448e-07,
      "learning_rate": 0.27038280607012644,
      "loss": 0.0,
      "num_input_tokens_seen": 2279072,
      "step": 8140
    },
    {
      "epoch": 90.5,
      "grad_norm": 1.2777774145433796e-06,
      "learning_rate": 0.27034765520133247,
      "loss": 0.0,
      "num_input_tokens_seen": 2280464,
      "step": 8145
    },
    {
      "epoch": 90.55555555555556,
      "grad_norm": 1.6942341289905016e-06,
      "learning_rate": 0.2703124857734177,
      "loss": 0.0,
      "num_input_tokens_seen": 2281856,
      "step": 8150
    },
    {
      "epoch": 90.61111111111111,
      "grad_norm": 1.5073359236339456e-06,
      "learning_rate": 0.27027729779180565,
      "loss": 0.0,
      "num_input_tokens_seen": 2283280,
      "step": 8155
    },
    {
      "epoch": 90.66666666666667,
      "grad_norm": 2.234179191873409e-06,
      "learning_rate": 0.27024209126192283,
      "loss": 0.0,
      "num_input_tokens_seen": 2284688,
      "step": 8160
    },
    {
      "epoch": 90.72222222222223,
      "grad_norm": 2.848481472028652e-06,
      "learning_rate": 0.2702068661891984,
      "loss": 0.0,
      "num_input_tokens_seen": 2286080,
      "step": 8165
    },
    {
      "epoch": 90.77777777777777,
      "grad_norm": 3.738178065759712e-06,
      "learning_rate": 0.2701716225790647,
      "loss": 0.0,
      "num_input_tokens_seen": 2287456,
      "step": 8170
    },
    {
      "epoch": 90.83333333333333,
      "grad_norm": 6.754014520993223e-07,
      "learning_rate": 0.27013636043695655,
      "loss": 0.0,
      "num_input_tokens_seen": 2288832,
      "step": 8175
    },
    {
      "epoch": 90.88888888888889,
      "grad_norm": 2.1726500563090667e-06,
      "learning_rate": 0.27010107976831194,
      "loss": 0.0,
      "num_input_tokens_seen": 2290272,
      "step": 8180
    },
    {
      "epoch": 90.94444444444444,
      "grad_norm": 6.837089472355729e-07,
      "learning_rate": 0.2700657805785715,
      "loss": 0.0,
      "num_input_tokens_seen": 2291664,
      "step": 8185
    },
    {
      "epoch": 91.0,
      "grad_norm": 7.949331006784632e-07,
      "learning_rate": 0.2700304628731789,
      "loss": 0.0,
      "num_input_tokens_seen": 2293088,
      "step": 8190
    },
    {
      "epoch": 91.05555555555556,
      "grad_norm": 3.5408863823249703e-06,
      "learning_rate": 0.26999512665758046,
      "loss": 0.0,
      "num_input_tokens_seen": 2294544,
      "step": 8195
    },
    {
      "epoch": 91.11111111111111,
      "grad_norm": 2.5069874709515716e-07,
      "learning_rate": 0.2699597719372256,
      "loss": 0.0,
      "num_input_tokens_seen": 2295888,
      "step": 8200
    },
    {
      "epoch": 91.11111111111111,
      "eval_loss": 0.9593908190727234,
      "eval_runtime": 1.1814,
      "eval_samples_per_second": 33.859,
      "eval_steps_per_second": 16.929,
      "num_input_tokens_seen": 2295888,
      "step": 8200
    },
    {
      "epoch": 91.16666666666667,
      "grad_norm": 4.875285526395601e-07,
      "learning_rate": 0.26992439871756635,
      "loss": 0.0,
      "num_input_tokens_seen": 2297232,
      "step": 8205
    },
    {
      "epoch": 91.22222222222223,
      "grad_norm": 8.821592132335354e-07,
      "learning_rate": 0.2698890070040578,
      "loss": 0.0,
      "num_input_tokens_seen": 2298608,
      "step": 8210
    },
    {
      "epoch": 91.27777777777777,
      "grad_norm": 1.686588234406372e-06,
      "learning_rate": 0.2698535968021577,
      "loss": 0.0,
      "num_input_tokens_seen": 2300016,
      "step": 8215
    },
    {
      "epoch": 91.33333333333333,
      "grad_norm": 1.8826201539923204e-06,
      "learning_rate": 0.26981816811732684,
      "loss": 0.0,
      "num_input_tokens_seen": 2301408,
      "step": 8220
    },
    {
      "epoch": 91.38888888888889,
      "grad_norm": 9.937821232597344e-07,
      "learning_rate": 0.26978272095502875,
      "loss": 0.0,
      "num_input_tokens_seen": 2302816,
      "step": 8225
    },
    {
      "epoch": 91.44444444444444,
      "grad_norm": 3.166654323649709e-06,
      "learning_rate": 0.26974725532072974,
      "loss": 0.0,
      "num_input_tokens_seen": 2304240,
      "step": 8230
    },
    {
      "epoch": 91.5,
      "grad_norm": 1.7143221384685603e-06,
      "learning_rate": 0.26971177121989914,
      "loss": 0.0,
      "num_input_tokens_seen": 2305664,
      "step": 8235
    },
    {
      "epoch": 91.55555555555556,
      "grad_norm": 2.3535385480499826e-06,
      "learning_rate": 0.2696762686580091,
      "loss": 0.0,
      "num_input_tokens_seen": 2307024,
      "step": 8240
    },
    {
      "epoch": 91.61111111111111,
      "grad_norm": 1.4135091532807564e-06,
      "learning_rate": 0.26964074764053436,
      "loss": 0.0,
      "num_input_tokens_seen": 2308416,
      "step": 8245
    },
    {
      "epoch": 91.66666666666667,
      "grad_norm": 1.6121487078635255e-06,
      "learning_rate": 0.2696052081729529,
      "loss": 0.0,
      "num_input_tokens_seen": 2309760,
      "step": 8250
    },
    {
      "epoch": 91.72222222222223,
      "grad_norm": 2.402655354671879e-07,
      "learning_rate": 0.2695696502607453,
      "loss": 0.0,
      "num_input_tokens_seen": 2311184,
      "step": 8255
    },
    {
      "epoch": 91.77777777777777,
      "grad_norm": 1.730612211758853e-06,
      "learning_rate": 0.26953407390939504,
      "loss": 0.0,
      "num_input_tokens_seen": 2312576,
      "step": 8260
    },
    {
      "epoch": 91.83333333333333,
      "grad_norm": 3.242433649575105e-06,
      "learning_rate": 0.26949847912438835,
      "loss": 0.0,
      "num_input_tokens_seen": 2313952,
      "step": 8265
    },
    {
      "epoch": 91.88888888888889,
      "grad_norm": 6.477229135271045e-07,
      "learning_rate": 0.26946286591121454,
      "loss": 0.0,
      "num_input_tokens_seen": 2315360,
      "step": 8270
    },
    {
      "epoch": 91.94444444444444,
      "grad_norm": 1.7810417602959205e-06,
      "learning_rate": 0.2694272342753655,
      "loss": 0.0,
      "num_input_tokens_seen": 2316832,
      "step": 8275
    },
    {
      "epoch": 92.0,
      "grad_norm": 1.5427621065100539e-06,
      "learning_rate": 0.26939158422233617,
      "loss": 0.0,
      "num_input_tokens_seen": 2318256,
      "step": 8280
    },
    {
      "epoch": 92.05555555555556,
      "grad_norm": 4.70249324280303e-06,
      "learning_rate": 0.26935591575762413,
      "loss": 0.0,
      "num_input_tokens_seen": 2319648,
      "step": 8285
    },
    {
      "epoch": 92.11111111111111,
      "grad_norm": 1.0799479923662147e-06,
      "learning_rate": 0.26932022888672996,
      "loss": 0.0,
      "num_input_tokens_seen": 2321056,
      "step": 8290
    },
    {
      "epoch": 92.16666666666667,
      "grad_norm": 2.8881675007141894e-06,
      "learning_rate": 0.26928452361515703,
      "loss": 0.0,
      "num_input_tokens_seen": 2322432,
      "step": 8295
    },
    {
      "epoch": 92.22222222222223,
      "grad_norm": 2.22127550841833e-06,
      "learning_rate": 0.26924879994841155,
      "loss": 0.0,
      "num_input_tokens_seen": 2323840,
      "step": 8300
    },
    {
      "epoch": 92.27777777777777,
      "grad_norm": 7.681259717173816e-07,
      "learning_rate": 0.2692130578920025,
      "loss": 0.0,
      "num_input_tokens_seen": 2325216,
      "step": 8305
    },
    {
      "epoch": 92.33333333333333,
      "grad_norm": 2.9319373879843624e-06,
      "learning_rate": 0.26917729745144187,
      "loss": 0.0,
      "num_input_tokens_seen": 2326608,
      "step": 8310
    },
    {
      "epoch": 92.38888888888889,
      "grad_norm": 1.4827614904788788e-06,
      "learning_rate": 0.2691415186322443,
      "loss": 0.0,
      "num_input_tokens_seen": 2328048,
      "step": 8315
    },
    {
      "epoch": 92.44444444444444,
      "grad_norm": 2.878583018173231e-06,
      "learning_rate": 0.2691057214399273,
      "loss": 0.0,
      "num_input_tokens_seen": 2329440,
      "step": 8320
    },
    {
      "epoch": 92.5,
      "grad_norm": 3.848840151476907e-06,
      "learning_rate": 0.2690699058800113,
      "loss": 0.0,
      "num_input_tokens_seen": 2330832,
      "step": 8325
    },
    {
      "epoch": 92.55555555555556,
      "grad_norm": 1.051172944244172e-06,
      "learning_rate": 0.2690340719580194,
      "loss": 0.0,
      "num_input_tokens_seen": 2332208,
      "step": 8330
    },
    {
      "epoch": 92.61111111111111,
      "grad_norm": 1.027964231070655e-06,
      "learning_rate": 0.2689982196794778,
      "loss": 0.0,
      "num_input_tokens_seen": 2333568,
      "step": 8335
    },
    {
      "epoch": 92.66666666666667,
      "grad_norm": 1.9013165228898288e-06,
      "learning_rate": 0.2689623490499153,
      "loss": 0.0,
      "num_input_tokens_seen": 2334960,
      "step": 8340
    },
    {
      "epoch": 92.72222222222223,
      "grad_norm": 1.2521771850515506e-06,
      "learning_rate": 0.2689264600748636,
      "loss": 0.0,
      "num_input_tokens_seen": 2336368,
      "step": 8345
    },
    {
      "epoch": 92.77777777777777,
      "grad_norm": 2.5126557829935336e-06,
      "learning_rate": 0.26889055275985724,
      "loss": 0.0,
      "num_input_tokens_seen": 2337808,
      "step": 8350
    },
    {
      "epoch": 92.83333333333333,
      "grad_norm": 1.5808878970346996e-06,
      "learning_rate": 0.2688546271104335,
      "loss": 0.0,
      "num_input_tokens_seen": 2339248,
      "step": 8355
    },
    {
      "epoch": 92.88888888888889,
      "grad_norm": 1.0106833769896184e-06,
      "learning_rate": 0.26881868313213275,
      "loss": 0.0,
      "num_input_tokens_seen": 2340640,
      "step": 8360
    },
    {
      "epoch": 92.94444444444444,
      "grad_norm": 6.825649165875802e-07,
      "learning_rate": 0.2687827208304978,
      "loss": 0.0,
      "num_input_tokens_seen": 2342032,
      "step": 8365
    },
    {
      "epoch": 93.0,
      "grad_norm": 1.142017822530761e-06,
      "learning_rate": 0.26874674021107464,
      "loss": 0.0,
      "num_input_tokens_seen": 2343424,
      "step": 8370
    },
    {
      "epoch": 93.05555555555556,
      "grad_norm": 1.7410202417522669e-06,
      "learning_rate": 0.2687107412794118,
      "loss": 0.0,
      "num_input_tokens_seen": 2344848,
      "step": 8375
    },
    {
      "epoch": 93.11111111111111,
      "grad_norm": 3.235126371237129e-07,
      "learning_rate": 0.26867472404106096,
      "loss": 0.0,
      "num_input_tokens_seen": 2346256,
      "step": 8380
    },
    {
      "epoch": 93.16666666666667,
      "grad_norm": 2.3649633931199787e-06,
      "learning_rate": 0.26863868850157624,
      "loss": 0.0,
      "num_input_tokens_seen": 2347696,
      "step": 8385
    },
    {
      "epoch": 93.22222222222223,
      "grad_norm": 8.575153742640396e-07,
      "learning_rate": 0.26860263466651485,
      "loss": 0.0,
      "num_input_tokens_seen": 2349072,
      "step": 8390
    },
    {
      "epoch": 93.27777777777777,
      "grad_norm": 1.1728629942808766e-06,
      "learning_rate": 0.26856656254143674,
      "loss": 0.0,
      "num_input_tokens_seen": 2350448,
      "step": 8395
    },
    {
      "epoch": 93.33333333333333,
      "grad_norm": 8.392950689994905e-07,
      "learning_rate": 0.2685304721319047,
      "loss": 0.0,
      "num_input_tokens_seen": 2351872,
      "step": 8400
    },
    {
      "epoch": 93.33333333333333,
      "eval_loss": 0.9713389277458191,
      "eval_runtime": 1.1826,
      "eval_samples_per_second": 33.825,
      "eval_steps_per_second": 16.912,
      "num_input_tokens_seen": 2351872,
      "step": 8400
    },
    {
      "epoch": 93.38888888888889,
      "grad_norm": 6.117303996688861e-07,
      "learning_rate": 0.2684943634434843,
      "loss": 0.0,
      "num_input_tokens_seen": 2353280,
      "step": 8405
    },
    {
      "epoch": 93.44444444444444,
      "grad_norm": 3.191810719727073e-06,
      "learning_rate": 0.268458236481744,
      "loss": 0.0,
      "num_input_tokens_seen": 2354672,
      "step": 8410
    },
    {
      "epoch": 93.5,
      "grad_norm": 3.0122721454972634e-06,
      "learning_rate": 0.2684220912522549,
      "loss": 0.0,
      "num_input_tokens_seen": 2356080,
      "step": 8415
    },
    {
      "epoch": 93.55555555555556,
      "grad_norm": 2.4759191319390084e-07,
      "learning_rate": 0.2683859277605913,
      "loss": 0.0,
      "num_input_tokens_seen": 2357456,
      "step": 8420
    },
    {
      "epoch": 93.61111111111111,
      "grad_norm": 1.5828542245799326e-06,
      "learning_rate": 0.2683497460123298,
      "loss": 0.0,
      "num_input_tokens_seen": 2358816,
      "step": 8425
    },
    {
      "epoch": 93.66666666666667,
      "grad_norm": 2.6476409402675927e-06,
      "learning_rate": 0.26831354601305013,
      "loss": 0.0,
      "num_input_tokens_seen": 2360224,
      "step": 8430
    },
    {
      "epoch": 93.72222222222223,
      "grad_norm": 8.558862418794888e-07,
      "learning_rate": 0.26827732776833496,
      "loss": 0.0,
      "num_input_tokens_seen": 2361616,
      "step": 8435
    },
    {
      "epoch": 93.77777777777777,
      "grad_norm": 4.637109213945223e-06,
      "learning_rate": 0.26824109128376944,
      "loss": 0.0,
      "num_input_tokens_seen": 2363024,
      "step": 8440
    },
    {
      "epoch": 93.83333333333333,
      "grad_norm": 1.0958158327412093e-06,
      "learning_rate": 0.2682048365649417,
      "loss": 0.0,
      "num_input_tokens_seen": 2364384,
      "step": 8445
    },
    {
      "epoch": 93.88888888888889,
      "grad_norm": 3.6791368529520696e-07,
      "learning_rate": 0.2681685636174428,
      "loss": 0.0,
      "num_input_tokens_seen": 2365792,
      "step": 8450
    },
    {
      "epoch": 93.94444444444444,
      "grad_norm": 1.3133098946127575e-06,
      "learning_rate": 0.2681322724468663,
      "loss": 0.0,
      "num_input_tokens_seen": 2367152,
      "step": 8455
    },
    {
      "epoch": 94.0,
      "grad_norm": 4.440433713170933e-06,
      "learning_rate": 0.2680959630588089,
      "loss": 0.0,
      "num_input_tokens_seen": 2368560,
      "step": 8460
    },
    {
      "epoch": 94.05555555555556,
      "grad_norm": 5.68526957067661e-07,
      "learning_rate": 0.26805963545886985,
      "loss": 0.0,
      "num_input_tokens_seen": 2369952,
      "step": 8465
    },
    {
      "epoch": 94.11111111111111,
      "grad_norm": 1.8134293213734054e-06,
      "learning_rate": 0.26802328965265143,
      "loss": 0.0,
      "num_input_tokens_seen": 2371344,
      "step": 8470
    },
    {
      "epoch": 94.16666666666667,
      "grad_norm": 1.3309443147591082e-06,
      "learning_rate": 0.26798692564575854,
      "loss": 0.0,
      "num_input_tokens_seen": 2372736,
      "step": 8475
    },
    {
      "epoch": 94.22222222222223,
      "grad_norm": 1.4197580640029628e-06,
      "learning_rate": 0.26795054344379904,
      "loss": 0.0,
      "num_input_tokens_seen": 2374096,
      "step": 8480
    },
    {
      "epoch": 94.27777777777777,
      "grad_norm": 1.541812139294052e-06,
      "learning_rate": 0.2679141430523835,
      "loss": 0.0,
      "num_input_tokens_seen": 2375472,
      "step": 8485
    },
    {
      "epoch": 94.33333333333333,
      "grad_norm": 1.5761818303872133e-06,
      "learning_rate": 0.2678777244771252,
      "loss": 0.0,
      "num_input_tokens_seen": 2376880,
      "step": 8490
    },
    {
      "epoch": 94.38888888888889,
      "grad_norm": 2.253195816592779e-06,
      "learning_rate": 0.2678412877236405,
      "loss": 0.0,
      "num_input_tokens_seen": 2378256,
      "step": 8495
    },
    {
      "epoch": 94.44444444444444,
      "grad_norm": 1.5601659697495052e-06,
      "learning_rate": 0.2678048327975484,
      "loss": 0.0,
      "num_input_tokens_seen": 2379648,
      "step": 8500
    },
    {
      "epoch": 94.5,
      "grad_norm": 1.2643292848224519e-06,
      "learning_rate": 0.2677683597044706,
      "loss": 0.0,
      "num_input_tokens_seen": 2381088,
      "step": 8505
    },
    {
      "epoch": 94.55555555555556,
      "grad_norm": 2.5136944259429583e-06,
      "learning_rate": 0.2677318684500318,
      "loss": 0.0,
      "num_input_tokens_seen": 2382464,
      "step": 8510
    },
    {
      "epoch": 94.61111111111111,
      "grad_norm": 2.797235765683581e-06,
      "learning_rate": 0.2676953590398593,
      "loss": 0.0,
      "num_input_tokens_seen": 2383904,
      "step": 8515
    },
    {
      "epoch": 94.66666666666667,
      "grad_norm": 1.635400508348539e-07,
      "learning_rate": 0.2676588314795834,
      "loss": 0.0,
      "num_input_tokens_seen": 2385328,
      "step": 8520
    },
    {
      "epoch": 94.72222222222223,
      "grad_norm": 2.9378952604020014e-07,
      "learning_rate": 0.26762228577483715,
      "loss": 0.0,
      "num_input_tokens_seen": 2386720,
      "step": 8525
    },
    {
      "epoch": 94.77777777777777,
      "grad_norm": 2.2543681552633643e-06,
      "learning_rate": 0.2675857219312563,
      "loss": 0.0,
      "num_input_tokens_seen": 2388144,
      "step": 8530
    },
    {
      "epoch": 94.83333333333333,
      "grad_norm": 1.3258267017590697e-06,
      "learning_rate": 0.2675491399544794,
      "loss": 0.0,
      "num_input_tokens_seen": 2389552,
      "step": 8535
    },
    {
      "epoch": 94.88888888888889,
      "grad_norm": 1.460680209675047e-06,
      "learning_rate": 0.2675125398501479,
      "loss": 0.0,
      "num_input_tokens_seen": 2390960,
      "step": 8540
    },
    {
      "epoch": 94.94444444444444,
      "grad_norm": 1.8119516198566998e-06,
      "learning_rate": 0.26747592162390604,
      "loss": 0.0,
      "num_input_tokens_seen": 2392368,
      "step": 8545
    },
    {
      "epoch": 95.0,
      "grad_norm": 2.8041567929903977e-06,
      "learning_rate": 0.26743928528140076,
      "loss": 0.0,
      "num_input_tokens_seen": 2393808,
      "step": 8550
    },
    {
      "epoch": 95.05555555555556,
      "grad_norm": 1.6338127295512095e-07,
      "learning_rate": 0.26740263082828186,
      "loss": 0.0,
      "num_input_tokens_seen": 2395232,
      "step": 8555
    },
    {
      "epoch": 95.11111111111111,
      "grad_norm": 7.976541951393301e-07,
      "learning_rate": 0.2673659582702019,
      "loss": 0.0,
      "num_input_tokens_seen": 2396640,
      "step": 8560
    },
    {
      "epoch": 95.16666666666667,
      "grad_norm": 8.929137607083248e-07,
      "learning_rate": 0.2673292676128163,
      "loss": 0.0,
      "num_input_tokens_seen": 2398080,
      "step": 8565
    },
    {
      "epoch": 95.22222222222223,
      "grad_norm": 4.3117793779856584e-07,
      "learning_rate": 0.2672925588617831,
      "loss": 0.0,
      "num_input_tokens_seen": 2399456,
      "step": 8570
    },
    {
      "epoch": 95.27777777777777,
      "grad_norm": 1.2900659385195468e-06,
      "learning_rate": 0.2672558320227634,
      "loss": 0.0,
      "num_input_tokens_seen": 2400864,
      "step": 8575
    },
    {
      "epoch": 95.33333333333333,
      "grad_norm": 1.1380976729924441e-06,
      "learning_rate": 0.2672190871014209,
      "loss": 0.0,
      "num_input_tokens_seen": 2402288,
      "step": 8580
    },
    {
      "epoch": 95.38888888888889,
      "grad_norm": 2.3370400867861463e-06,
      "learning_rate": 0.267182324103422,
      "loss": 0.0,
      "num_input_tokens_seen": 2403616,
      "step": 8585
    },
    {
      "epoch": 95.44444444444444,
      "grad_norm": 6.894344437569089e-07,
      "learning_rate": 0.2671455430344362,
      "loss": 0.0,
      "num_input_tokens_seen": 2404992,
      "step": 8590
    },
    {
      "epoch": 95.5,
      "grad_norm": 1.2141193792558624e-06,
      "learning_rate": 0.2671087439001355,
      "loss": 0.0,
      "num_input_tokens_seen": 2406400,
      "step": 8595
    },
    {
      "epoch": 95.55555555555556,
      "grad_norm": 2.2046497178962454e-06,
      "learning_rate": 0.2670719267061948,
      "loss": 0.0,
      "num_input_tokens_seen": 2407824,
      "step": 8600
    },
    {
      "epoch": 95.55555555555556,
      "eval_loss": 0.9810115694999695,
      "eval_runtime": 1.1876,
      "eval_samples_per_second": 33.682,
      "eval_steps_per_second": 16.841,
      "num_input_tokens_seen": 2407824,
      "step": 8600
    },
    {
      "epoch": 95.61111111111111,
      "grad_norm": 1.1735147609215346e-06,
      "learning_rate": 0.2670350914582918,
      "loss": 0.0,
      "num_input_tokens_seen": 2409216,
      "step": 8605
    },
    {
      "epoch": 95.66666666666667,
      "grad_norm": 1.7323134215985192e-06,
      "learning_rate": 0.26699823816210694,
      "loss": 0.0,
      "num_input_tokens_seen": 2410592,
      "step": 8610
    },
    {
      "epoch": 95.72222222222223,
      "grad_norm": 2.7731812224374153e-06,
      "learning_rate": 0.26696136682332344,
      "loss": 0.0,
      "num_input_tokens_seen": 2412000,
      "step": 8615
    },
    {
      "epoch": 95.77777777777777,
      "grad_norm": 1.7324505279248115e-06,
      "learning_rate": 0.2669244774476274,
      "loss": 0.0,
      "num_input_tokens_seen": 2413408,
      "step": 8620
    },
    {
      "epoch": 95.83333333333333,
      "grad_norm": 2.892379598051775e-07,
      "learning_rate": 0.2668875700407075,
      "loss": 0.0,
      "num_input_tokens_seen": 2414800,
      "step": 8625
    },
    {
      "epoch": 95.88888888888889,
      "grad_norm": 9.98541963781463e-07,
      "learning_rate": 0.26685064460825547,
      "loss": 0.0,
      "num_input_tokens_seen": 2416208,
      "step": 8630
    },
    {
      "epoch": 95.94444444444444,
      "grad_norm": 4.095921667612856e-06,
      "learning_rate": 0.26681370115596553,
      "loss": 0.0,
      "num_input_tokens_seen": 2417632,
      "step": 8635
    },
    {
      "epoch": 96.0,
      "grad_norm": 4.796971211362688e-07,
      "learning_rate": 0.26677673968953497,
      "loss": 0.0,
      "num_input_tokens_seen": 2419008,
      "step": 8640
    },
    {
      "epoch": 96.05555555555556,
      "grad_norm": 1.189991166938853e-06,
      "learning_rate": 0.2667397602146636,
      "loss": 0.0,
      "num_input_tokens_seen": 2420432,
      "step": 8645
    },
    {
      "epoch": 96.11111111111111,
      "grad_norm": 1.6830958884384017e-06,
      "learning_rate": 0.2667027627370542,
      "loss": 0.0,
      "num_input_tokens_seen": 2421808,
      "step": 8650
    },
    {
      "epoch": 96.16666666666667,
      "grad_norm": 2.4373630367335863e-06,
      "learning_rate": 0.26666574726241216,
      "loss": 0.0,
      "num_input_tokens_seen": 2423216,
      "step": 8655
    },
    {
      "epoch": 96.22222222222223,
      "grad_norm": 3.951487883568916e-07,
      "learning_rate": 0.2666287137964458,
      "loss": 0.0,
      "num_input_tokens_seen": 2424592,
      "step": 8660
    },
    {
      "epoch": 96.27777777777777,
      "grad_norm": 5.361750368138019e-07,
      "learning_rate": 0.26659166234486614,
      "loss": 0.0,
      "num_input_tokens_seen": 2426048,
      "step": 8665
    },
    {
      "epoch": 96.33333333333333,
      "grad_norm": 3.0341020647028927e-06,
      "learning_rate": 0.2665545929133869,
      "loss": 0.0,
      "num_input_tokens_seen": 2427424,
      "step": 8670
    },
    {
      "epoch": 96.38888888888889,
      "grad_norm": 4.7328160235338146e-07,
      "learning_rate": 0.2665175055077248,
      "loss": 0.0,
      "num_input_tokens_seen": 2428816,
      "step": 8675
    },
    {
      "epoch": 96.44444444444444,
      "grad_norm": 3.060034998725314e-07,
      "learning_rate": 0.2664804001335991,
      "loss": 0.0,
      "num_input_tokens_seen": 2430192,
      "step": 8680
    },
    {
      "epoch": 96.5,
      "grad_norm": 1.6030262486310676e-06,
      "learning_rate": 0.26644327679673185,
      "loss": 0.0,
      "num_input_tokens_seen": 2431584,
      "step": 8685
    },
    {
      "epoch": 96.55555555555556,
      "grad_norm": 2.8460074190661544e-06,
      "learning_rate": 0.26640613550284803,
      "loss": 0.0,
      "num_input_tokens_seen": 2432976,
      "step": 8690
    },
    {
      "epoch": 96.61111111111111,
      "grad_norm": 7.290279313565406e-07,
      "learning_rate": 0.26636897625767525,
      "loss": 0.0,
      "num_input_tokens_seen": 2434368,
      "step": 8695
    },
    {
      "epoch": 96.66666666666667,
      "grad_norm": 2.5605197606637375e-06,
      "learning_rate": 0.266331799066944,
      "loss": 0.0,
      "num_input_tokens_seen": 2435792,
      "step": 8700
    },
    {
      "epoch": 96.72222222222223,
      "grad_norm": 1.4248519164539175e-06,
      "learning_rate": 0.2662946039363874,
      "loss": 0.0,
      "num_input_tokens_seen": 2437216,
      "step": 8705
    },
    {
      "epoch": 96.77777777777777,
      "grad_norm": 6.447358487093879e-07,
      "learning_rate": 0.2662573908717414,
      "loss": 0.0,
      "num_input_tokens_seen": 2438608,
      "step": 8710
    },
    {
      "epoch": 96.83333333333333,
      "grad_norm": 1.937630941029056e-06,
      "learning_rate": 0.2662201598787447,
      "loss": 0.0,
      "num_input_tokens_seen": 2439968,
      "step": 8715
    },
    {
      "epoch": 96.88888888888889,
      "grad_norm": 8.0289947845813e-07,
      "learning_rate": 0.2661829109631389,
      "loss": 0.0,
      "num_input_tokens_seen": 2441392,
      "step": 8720
    },
    {
      "epoch": 96.94444444444444,
      "grad_norm": 1.9265671653556637e-06,
      "learning_rate": 0.26614564413066816,
      "loss": 0.0,
      "num_input_tokens_seen": 2442768,
      "step": 8725
    },
    {
      "epoch": 97.0,
      "grad_norm": 8.490251843795704e-07,
      "learning_rate": 0.2661083593870795,
      "loss": 0.0,
      "num_input_tokens_seen": 2444160,
      "step": 8730
    },
    {
      "epoch": 97.05555555555556,
      "grad_norm": 1.6491924270667369e-06,
      "learning_rate": 0.26607105673812276,
      "loss": 0.0,
      "num_input_tokens_seen": 2445568,
      "step": 8735
    },
    {
      "epoch": 97.11111111111111,
      "grad_norm": 2.2626957161264727e-06,
      "learning_rate": 0.2660337361895504,
      "loss": 0.0,
      "num_input_tokens_seen": 2446976,
      "step": 8740
    },
    {
      "epoch": 97.16666666666667,
      "grad_norm": 1.4913784980308264e-06,
      "learning_rate": 0.26599639774711775,
      "loss": 0.0,
      "num_input_tokens_seen": 2448416,
      "step": 8745
    },
    {
      "epoch": 97.22222222222223,
      "grad_norm": 1.0574590305623133e-06,
      "learning_rate": 0.2659590414165829,
      "loss": 0.0,
      "num_input_tokens_seen": 2449808,
      "step": 8750
    },
    {
      "epoch": 97.27777777777777,
      "grad_norm": 1.6434745475635282e-06,
      "learning_rate": 0.2659216672037066,
      "loss": 0.0,
      "num_input_tokens_seen": 2451216,
      "step": 8755
    },
    {
      "epoch": 97.33333333333333,
      "grad_norm": 2.3267136839422164e-06,
      "learning_rate": 0.26588427511425244,
      "loss": 0.0,
      "num_input_tokens_seen": 2452608,
      "step": 8760
    },
    {
      "epoch": 97.38888888888889,
      "grad_norm": 1.1774837958000717e-06,
      "learning_rate": 0.26584686515398676,
      "loss": 0.0,
      "num_input_tokens_seen": 2454000,
      "step": 8765
    },
    {
      "epoch": 97.44444444444444,
      "grad_norm": 1.053768642123032e-06,
      "learning_rate": 0.2658094373286787,
      "loss": 0.0,
      "num_input_tokens_seen": 2455408,
      "step": 8770
    },
    {
      "epoch": 97.5,
      "grad_norm": 7.651402142982988e-07,
      "learning_rate": 0.2657719916441,
      "loss": 0.0,
      "num_input_tokens_seen": 2456800,
      "step": 8775
    },
    {
      "epoch": 97.55555555555556,
      "grad_norm": 1.591711452419986e-06,
      "learning_rate": 0.2657345281060253,
      "loss": 0.0,
      "num_input_tokens_seen": 2458208,
      "step": 8780
    },
    {
      "epoch": 97.61111111111111,
      "grad_norm": 3.1628712804376846e-07,
      "learning_rate": 0.26569704672023203,
      "loss": 0.0,
      "num_input_tokens_seen": 2459568,
      "step": 8785
    },
    {
      "epoch": 97.66666666666667,
      "grad_norm": 8.445682055935322e-07,
      "learning_rate": 0.26565954749250015,
      "loss": 0.0,
      "num_input_tokens_seen": 2460976,
      "step": 8790
    },
    {
      "epoch": 97.72222222222223,
      "grad_norm": 3.2255043151963037e-06,
      "learning_rate": 0.2656220304286126,
      "loss": 0.0,
      "num_input_tokens_seen": 2462384,
      "step": 8795
    },
    {
      "epoch": 97.77777777777777,
      "grad_norm": 2.8292191700529656e-07,
      "learning_rate": 0.265584495534355,
      "loss": 0.0,
      "num_input_tokens_seen": 2463744,
      "step": 8800
    },
    {
      "epoch": 97.77777777777777,
      "eval_loss": 0.9830455780029297,
      "eval_runtime": 1.1946,
      "eval_samples_per_second": 33.485,
      "eval_steps_per_second": 16.742,
      "num_input_tokens_seen": 2463744,
      "step": 8800
    },
    {
      "epoch": 97.83333333333333,
      "grad_norm": 3.6542309089782066e-07,
      "learning_rate": 0.2655469428155156,
      "loss": 0.0,
      "num_input_tokens_seen": 2465136,
      "step": 8805
    },
    {
      "epoch": 97.88888888888889,
      "grad_norm": 6.218166163307615e-06,
      "learning_rate": 0.2655093722778856,
      "loss": 0.0,
      "num_input_tokens_seen": 2466512,
      "step": 8810
    },
    {
      "epoch": 97.94444444444444,
      "grad_norm": 8.520976848558348e-07,
      "learning_rate": 0.2654717839272588,
      "loss": 0.0,
      "num_input_tokens_seen": 2467904,
      "step": 8815
    },
    {
      "epoch": 98.0,
      "grad_norm": 1.8651670643521356e-06,
      "learning_rate": 0.2654341777694318,
      "loss": 0.0,
      "num_input_tokens_seen": 2469296,
      "step": 8820
    },
    {
      "epoch": 98.05555555555556,
      "grad_norm": 2.329423523406149e-06,
      "learning_rate": 0.265396553810204,
      "loss": 0.0,
      "num_input_tokens_seen": 2470688,
      "step": 8825
    },
    {
      "epoch": 98.11111111111111,
      "grad_norm": 3.7649769524250587e-07,
      "learning_rate": 0.26535891205537737,
      "loss": 0.0,
      "num_input_tokens_seen": 2472080,
      "step": 8830
    },
    {
      "epoch": 98.16666666666667,
      "grad_norm": 8.751069344725693e-07,
      "learning_rate": 0.26532125251075683,
      "loss": 0.0,
      "num_input_tokens_seen": 2473488,
      "step": 8835
    },
    {
      "epoch": 98.22222222222223,
      "grad_norm": 4.090228173936339e-07,
      "learning_rate": 0.26528357518214996,
      "loss": 0.0,
      "num_input_tokens_seen": 2474896,
      "step": 8840
    },
    {
      "epoch": 98.27777777777777,
      "grad_norm": 1.19185051516979e-06,
      "learning_rate": 0.26524588007536704,
      "loss": 0.0,
      "num_input_tokens_seen": 2476272,
      "step": 8845
    },
    {
      "epoch": 98.33333333333333,
      "grad_norm": 6.802375196457433e-07,
      "learning_rate": 0.26520816719622115,
      "loss": 0.0,
      "num_input_tokens_seen": 2477696,
      "step": 8850
    },
    {
      "epoch": 98.38888888888889,
      "grad_norm": 1.1416324241508846e-06,
      "learning_rate": 0.2651704365505281,
      "loss": 0.0,
      "num_input_tokens_seen": 2479040,
      "step": 8855
    },
    {
      "epoch": 98.44444444444444,
      "grad_norm": 4.8148954192583915e-06,
      "learning_rate": 0.26513268814410634,
      "loss": 0.0,
      "num_input_tokens_seen": 2480496,
      "step": 8860
    },
    {
      "epoch": 98.5,
      "grad_norm": 1.0216729151579784e-06,
      "learning_rate": 0.2650949219827773,
      "loss": 0.0,
      "num_input_tokens_seen": 2481888,
      "step": 8865
    },
    {
      "epoch": 98.55555555555556,
      "grad_norm": 2.126146000591689e-06,
      "learning_rate": 0.26505713807236486,
      "loss": 0.0,
      "num_input_tokens_seen": 2483280,
      "step": 8870
    },
    {
      "epoch": 98.61111111111111,
      "grad_norm": 1.8995010577782523e-06,
      "learning_rate": 0.26501933641869585,
      "loss": 0.0,
      "num_input_tokens_seen": 2484704,
      "step": 8875
    },
    {
      "epoch": 98.66666666666667,
      "grad_norm": 3.297467969787249e-07,
      "learning_rate": 0.26498151702759976,
      "loss": 0.0,
      "num_input_tokens_seen": 2486080,
      "step": 8880
    },
    {
      "epoch": 98.72222222222223,
      "grad_norm": 7.048026304801169e-07,
      "learning_rate": 0.2649436799049088,
      "loss": 0.0,
      "num_input_tokens_seen": 2487520,
      "step": 8885
    },
    {
      "epoch": 98.77777777777777,
      "grad_norm": 4.846028218707943e-07,
      "learning_rate": 0.2649058250564579,
      "loss": 0.0,
      "num_input_tokens_seen": 2488944,
      "step": 8890
    },
    {
      "epoch": 98.83333333333333,
      "grad_norm": 2.097989636240527e-06,
      "learning_rate": 0.26486795248808476,
      "loss": 0.0,
      "num_input_tokens_seen": 2490320,
      "step": 8895
    },
    {
      "epoch": 98.88888888888889,
      "grad_norm": 1.2674037179749575e-06,
      "learning_rate": 0.2648300622056298,
      "loss": 0.0,
      "num_input_tokens_seen": 2491728,
      "step": 8900
    },
    {
      "epoch": 98.94444444444444,
      "grad_norm": 2.9051163892290788e-06,
      "learning_rate": 0.2647921542149363,
      "loss": 0.0,
      "num_input_tokens_seen": 2493088,
      "step": 8905
    },
    {
      "epoch": 99.0,
      "grad_norm": 5.003328169550514e-06,
      "learning_rate": 0.26475422852185,
      "loss": 0.0,
      "num_input_tokens_seen": 2494448,
      "step": 8910
    },
    {
      "epoch": 99.05555555555556,
      "grad_norm": 2.6056027309095953e-06,
      "learning_rate": 0.2647162851322196,
      "loss": 0.0,
      "num_input_tokens_seen": 2495888,
      "step": 8915
    },
    {
      "epoch": 99.11111111111111,
      "grad_norm": 1.1543323807927663e-07,
      "learning_rate": 0.2646783240518964,
      "loss": 0.0,
      "num_input_tokens_seen": 2497264,
      "step": 8920
    },
    {
      "epoch": 99.16666666666667,
      "grad_norm": 1.01112789252511e-06,
      "learning_rate": 0.26464034528673447,
      "loss": 0.0,
      "num_input_tokens_seen": 2498624,
      "step": 8925
    },
    {
      "epoch": 99.22222222222223,
      "grad_norm": 8.028870865928184e-07,
      "learning_rate": 0.26460234884259065,
      "loss": 0.0,
      "num_input_tokens_seen": 2500000,
      "step": 8930
    },
    {
      "epoch": 99.27777777777777,
      "grad_norm": 3.4450008001840615e-07,
      "learning_rate": 0.2645643347253245,
      "loss": 0.0,
      "num_input_tokens_seen": 2501392,
      "step": 8935
    },
    {
      "epoch": 99.33333333333333,
      "grad_norm": 8.440702004008926e-07,
      "learning_rate": 0.2645263029407982,
      "loss": 0.0,
      "num_input_tokens_seen": 2502768,
      "step": 8940
    },
    {
      "epoch": 99.38888888888889,
      "grad_norm": 9.937182312569348e-07,
      "learning_rate": 0.2644882534948767,
      "loss": 0.0,
      "num_input_tokens_seen": 2504160,
      "step": 8945
    },
    {
      "epoch": 99.44444444444444,
      "grad_norm": 8.518749154973193e-07,
      "learning_rate": 0.2644501863934278,
      "loss": 0.0,
      "num_input_tokens_seen": 2505552,
      "step": 8950
    },
    {
      "epoch": 99.5,
      "grad_norm": 4.8323668124794494e-06,
      "learning_rate": 0.26441210164232193,
      "loss": 0.0,
      "num_input_tokens_seen": 2506912,
      "step": 8955
    },
    {
      "epoch": 99.55555555555556,
      "grad_norm": 1.4633147884524078e-06,
      "learning_rate": 0.26437399924743216,
      "loss": 0.0,
      "num_input_tokens_seen": 2508384,
      "step": 8960
    },
    {
      "epoch": 99.61111111111111,
      "grad_norm": 1.5134536113237118e-07,
      "learning_rate": 0.26433587921463436,
      "loss": 0.0,
      "num_input_tokens_seen": 2509808,
      "step": 8965
    },
    {
      "epoch": 99.66666666666667,
      "grad_norm": 5.860288752046472e-07,
      "learning_rate": 0.2642977415498072,
      "loss": 0.0,
      "num_input_tokens_seen": 2511216,
      "step": 8970
    },
    {
      "epoch": 99.72222222222223,
      "grad_norm": 5.293400135997217e-07,
      "learning_rate": 0.26425958625883195,
      "loss": 0.0,
      "num_input_tokens_seen": 2512624,
      "step": 8975
    },
    {
      "epoch": 99.77777777777777,
      "grad_norm": 9.553860991218244e-07,
      "learning_rate": 0.2642214133475926,
      "loss": 0.0,
      "num_input_tokens_seen": 2514032,
      "step": 8980
    },
    {
      "epoch": 99.83333333333333,
      "grad_norm": 1.3743151612288784e-06,
      "learning_rate": 0.26418322282197587,
      "loss": 0.0,
      "num_input_tokens_seen": 2515456,
      "step": 8985
    },
    {
      "epoch": 99.88888888888889,
      "grad_norm": 4.142492855407909e-07,
      "learning_rate": 0.2641450146878714,
      "loss": 0.0,
      "num_input_tokens_seen": 2516896,
      "step": 8990
    },
    {
      "epoch": 99.94444444444444,
      "grad_norm": 1.2082824696335592e-07,
      "learning_rate": 0.26410678895117107,
      "loss": 0.0,
      "num_input_tokens_seen": 2518304,
      "step": 8995
    },
    {
      "epoch": 100.0,
      "grad_norm": 1.9347517081769183e-06,
      "learning_rate": 0.26406854561777,
      "loss": 0.0,
      "num_input_tokens_seen": 2519680,
      "step": 9000
    },
    {
      "epoch": 100.0,
      "eval_loss": 1.0046435594558716,
      "eval_runtime": 1.1791,
      "eval_samples_per_second": 33.923,
      "eval_steps_per_second": 16.962,
      "num_input_tokens_seen": 2519680,
      "step": 9000
    },
    {
      "epoch": 100.05555555555556,
      "grad_norm": 1.0565224783931626e-06,
      "learning_rate": 0.26403028469356576,
      "loss": 0.0,
      "num_input_tokens_seen": 2521088,
      "step": 9005
    },
    {
      "epoch": 100.11111111111111,
      "grad_norm": 4.004031097792904e-07,
      "learning_rate": 0.2639920061844585,
      "loss": 0.0,
      "num_input_tokens_seen": 2522512,
      "step": 9010
    },
    {
      "epoch": 100.16666666666667,
      "grad_norm": 8.633990660200652e-07,
      "learning_rate": 0.2639537100963515,
      "loss": 0.0,
      "num_input_tokens_seen": 2523904,
      "step": 9015
    },
    {
      "epoch": 100.22222222222223,
      "grad_norm": 7.712899900980119e-07,
      "learning_rate": 0.26391539643515033,
      "loss": 0.0,
      "num_input_tokens_seen": 2525264,
      "step": 9020
    },
    {
      "epoch": 100.27777777777777,
      "grad_norm": 3.359804452429671e-07,
      "learning_rate": 0.26387706520676346,
      "loss": 0.0,
      "num_input_tokens_seen": 2526704,
      "step": 9025
    },
    {
      "epoch": 100.33333333333333,
      "grad_norm": 3.4637724866115605e-07,
      "learning_rate": 0.26383871641710205,
      "loss": 0.0,
      "num_input_tokens_seen": 2528112,
      "step": 9030
    },
    {
      "epoch": 100.38888888888889,
      "grad_norm": 2.404018459856161e-06,
      "learning_rate": 0.26380035007208,
      "loss": 0.0,
      "num_input_tokens_seen": 2529504,
      "step": 9035
    },
    {
      "epoch": 100.44444444444444,
      "grad_norm": 9.227124309063583e-08,
      "learning_rate": 0.26376196617761394,
      "loss": 0.0,
      "num_input_tokens_seen": 2530880,
      "step": 9040
    },
    {
      "epoch": 100.5,
      "grad_norm": 3.811679789578193e-06,
      "learning_rate": 0.263723564739623,
      "loss": 0.0,
      "num_input_tokens_seen": 2532256,
      "step": 9045
    },
    {
      "epoch": 100.55555555555556,
      "grad_norm": 4.958567387802759e-07,
      "learning_rate": 0.2636851457640293,
      "loss": 0.0,
      "num_input_tokens_seen": 2533616,
      "step": 9050
    },
    {
      "epoch": 100.61111111111111,
      "grad_norm": 2.796979288177681e-07,
      "learning_rate": 0.26364670925675737,
      "loss": 0.0,
      "num_input_tokens_seen": 2535024,
      "step": 9055
    },
    {
      "epoch": 100.66666666666667,
      "grad_norm": 2.2685894691676367e-06,
      "learning_rate": 0.2636082552237347,
      "loss": 0.0,
      "num_input_tokens_seen": 2536432,
      "step": 9060
    },
    {
      "epoch": 100.72222222222223,
      "grad_norm": 1.560948476253543e-06,
      "learning_rate": 0.26356978367089146,
      "loss": 0.0,
      "num_input_tokens_seen": 2537824,
      "step": 9065
    },
    {
      "epoch": 100.77777777777777,
      "grad_norm": 1.5554828678432386e-06,
      "learning_rate": 0.26353129460416036,
      "loss": 0.0,
      "num_input_tokens_seen": 2539232,
      "step": 9070
    },
    {
      "epoch": 100.83333333333333,
      "grad_norm": 2.094375020078587e-07,
      "learning_rate": 0.2634927880294769,
      "loss": 0.0,
      "num_input_tokens_seen": 2540608,
      "step": 9075
    },
    {
      "epoch": 100.88888888888889,
      "grad_norm": 6.043411531209131e-07,
      "learning_rate": 0.26345426395277927,
      "loss": 0.0,
      "num_input_tokens_seen": 2542000,
      "step": 9080
    },
    {
      "epoch": 100.94444444444444,
      "grad_norm": 3.809556119449553e-07,
      "learning_rate": 0.2634157223800084,
      "loss": 0.0,
      "num_input_tokens_seen": 2543408,
      "step": 9085
    },
    {
      "epoch": 101.0,
      "grad_norm": 7.505122994189151e-07,
      "learning_rate": 0.26337716331710787,
      "loss": 0.0,
      "num_input_tokens_seen": 2544800,
      "step": 9090
    },
    {
      "epoch": 101.05555555555556,
      "grad_norm": 4.543039722193498e-06,
      "learning_rate": 0.2633385867700239,
      "loss": 0.0,
      "num_input_tokens_seen": 2546176,
      "step": 9095
    },
    {
      "epoch": 101.11111111111111,
      "grad_norm": 5.642100404656958e-07,
      "learning_rate": 0.2632999927447056,
      "loss": 0.0,
      "num_input_tokens_seen": 2547568,
      "step": 9100
    },
    {
      "epoch": 101.16666666666667,
      "grad_norm": 2.459642018948216e-06,
      "learning_rate": 0.2632613812471046,
      "loss": 0.0,
      "num_input_tokens_seen": 2548992,
      "step": 9105
    },
    {
      "epoch": 101.22222222222223,
      "grad_norm": 3.176352265654714e-07,
      "learning_rate": 0.2632227522831753,
      "loss": 0.0,
      "num_input_tokens_seen": 2550400,
      "step": 9110
    },
    {
      "epoch": 101.27777777777777,
      "grad_norm": 1.9191172668797662e-06,
      "learning_rate": 0.26318410585887475,
      "loss": 0.0,
      "num_input_tokens_seen": 2551776,
      "step": 9115
    },
    {
      "epoch": 101.33333333333333,
      "grad_norm": 1.9343976873642532e-06,
      "learning_rate": 0.2631454419801627,
      "loss": 0.0,
      "num_input_tokens_seen": 2553184,
      "step": 9120
    },
    {
      "epoch": 101.38888888888889,
      "grad_norm": 3.6619300658458087e-07,
      "learning_rate": 0.2631067606530016,
      "loss": 0.0,
      "num_input_tokens_seen": 2554576,
      "step": 9125
    },
    {
      "epoch": 101.44444444444444,
      "grad_norm": 7.976778420015762e-07,
      "learning_rate": 0.2630680618833567,
      "loss": 0.0,
      "num_input_tokens_seen": 2555968,
      "step": 9130
    },
    {
      "epoch": 101.5,
      "grad_norm": 1.1845091876239167e-06,
      "learning_rate": 0.26302934567719566,
      "loss": 0.0,
      "num_input_tokens_seen": 2557376,
      "step": 9135
    },
    {
      "epoch": 101.55555555555556,
      "grad_norm": 4.825228643312585e-07,
      "learning_rate": 0.2629906120404892,
      "loss": 0.0,
      "num_input_tokens_seen": 2558800,
      "step": 9140
    },
    {
      "epoch": 101.61111111111111,
      "grad_norm": 5.125132247485453e-07,
      "learning_rate": 0.26295186097921036,
      "loss": 0.0,
      "num_input_tokens_seen": 2560208,
      "step": 9145
    },
    {
      "epoch": 101.66666666666667,
      "grad_norm": 8.735906362744572e-07,
      "learning_rate": 0.2629130924993351,
      "loss": 0.0,
      "num_input_tokens_seen": 2561648,
      "step": 9150
    },
    {
      "epoch": 101.72222222222223,
      "grad_norm": 4.092292442692269e-07,
      "learning_rate": 0.2628743066068421,
      "loss": 0.0,
      "num_input_tokens_seen": 2563024,
      "step": 9155
    },
    {
      "epoch": 101.77777777777777,
      "grad_norm": 8.461567517770163e-07,
      "learning_rate": 0.26283550330771244,
      "loss": 0.0,
      "num_input_tokens_seen": 2564416,
      "step": 9160
    },
    {
      "epoch": 101.83333333333333,
      "grad_norm": 8.505599566888122e-07,
      "learning_rate": 0.2627966826079303,
      "loss": 0.0,
      "num_input_tokens_seen": 2565856,
      "step": 9165
    },
    {
      "epoch": 101.88888888888889,
      "grad_norm": 2.79363717936576e-07,
      "learning_rate": 0.26275784451348216,
      "loss": 0.0,
      "num_input_tokens_seen": 2567232,
      "step": 9170
    },
    {
      "epoch": 101.94444444444444,
      "grad_norm": 4.492910647968529e-07,
      "learning_rate": 0.2627189890303574,
      "loss": 0.0,
      "num_input_tokens_seen": 2568608,
      "step": 9175
    },
    {
      "epoch": 102.0,
      "grad_norm": 1.271457563234435e-06,
      "learning_rate": 0.262680116164548,
      "loss": 0.0,
      "num_input_tokens_seen": 2569968,
      "step": 9180
    },
    {
      "epoch": 102.05555555555556,
      "grad_norm": 1.0434380328661064e-06,
      "learning_rate": 0.2626412259220487,
      "loss": 0.0,
      "num_input_tokens_seen": 2571392,
      "step": 9185
    },
    {
      "epoch": 102.11111111111111,
      "grad_norm": 1.953791752384859e-06,
      "learning_rate": 0.2626023183088568,
      "loss": 0.0,
      "num_input_tokens_seen": 2572832,
      "step": 9190
    },
    {
      "epoch": 102.16666666666667,
      "grad_norm": 1.3920034689363092e-06,
      "learning_rate": 0.26256339333097234,
      "loss": 0.0,
      "num_input_tokens_seen": 2574208,
      "step": 9195
    },
    {
      "epoch": 102.22222222222223,
      "grad_norm": 4.6495392780343536e-07,
      "learning_rate": 0.2625244509943981,
      "loss": 0.0,
      "num_input_tokens_seen": 2575584,
      "step": 9200
    },
    {
      "epoch": 102.22222222222223,
      "eval_loss": 1.0119785070419312,
      "eval_runtime": 1.188,
      "eval_samples_per_second": 33.671,
      "eval_steps_per_second": 16.835,
      "num_input_tokens_seen": 2575584,
      "step": 9200
    },
    {
      "epoch": 102.27777777777777,
      "grad_norm": 7.751766020192008e-07,
      "learning_rate": 0.2624854913051395,
      "loss": 0.0,
      "num_input_tokens_seen": 2576976,
      "step": 9205
    },
    {
      "epoch": 102.33333333333333,
      "grad_norm": 1.6790526160548325e-06,
      "learning_rate": 0.26244651426920446,
      "loss": 0.0,
      "num_input_tokens_seen": 2578400,
      "step": 9210
    },
    {
      "epoch": 102.38888888888889,
      "grad_norm": 1.8416267266729847e-06,
      "learning_rate": 0.26240751989260386,
      "loss": 0.0,
      "num_input_tokens_seen": 2579824,
      "step": 9215
    },
    {
      "epoch": 102.44444444444444,
      "grad_norm": 3.1082785767466703e-07,
      "learning_rate": 0.2623685081813511,
      "loss": 0.0,
      "num_input_tokens_seen": 2581248,
      "step": 9220
    },
    {
      "epoch": 102.5,
      "grad_norm": 9.104358582590066e-07,
      "learning_rate": 0.2623294791414623,
      "loss": 0.0,
      "num_input_tokens_seen": 2582608,
      "step": 9225
    },
    {
      "epoch": 102.55555555555556,
      "grad_norm": 2.487230176484445e-06,
      "learning_rate": 0.26229043277895614,
      "loss": 0.0,
      "num_input_tokens_seen": 2584064,
      "step": 9230
    },
    {
      "epoch": 102.61111111111111,
      "grad_norm": 9.057557690539397e-07,
      "learning_rate": 0.2622513690998542,
      "loss": 0.0,
      "num_input_tokens_seen": 2585424,
      "step": 9235
    },
    {
      "epoch": 102.66666666666667,
      "grad_norm": 9.34660477014404e-07,
      "learning_rate": 0.26221228811018044,
      "loss": 0.0,
      "num_input_tokens_seen": 2586880,
      "step": 9240
    },
    {
      "epoch": 102.72222222222223,
      "grad_norm": 2.960696974696475e-06,
      "learning_rate": 0.2621731898159617,
      "loss": 0.0,
      "num_input_tokens_seen": 2588240,
      "step": 9245
    },
    {
      "epoch": 102.77777777777777,
      "grad_norm": 1.7080227507904056e-06,
      "learning_rate": 0.26213407422322743,
      "loss": 0.0,
      "num_input_tokens_seen": 2589616,
      "step": 9250
    },
    {
      "epoch": 102.83333333333333,
      "grad_norm": 4.834759579352976e-07,
      "learning_rate": 0.2620949413380098,
      "loss": 0.0,
      "num_input_tokens_seen": 2591008,
      "step": 9255
    },
    {
      "epoch": 102.88888888888889,
      "grad_norm": 5.457042675516277e-07,
      "learning_rate": 0.26205579116634353,
      "loss": 0.0,
      "num_input_tokens_seen": 2592432,
      "step": 9260
    },
    {
      "epoch": 102.94444444444444,
      "grad_norm": 3.354899718033266e-07,
      "learning_rate": 0.26201662371426604,
      "loss": 0.0,
      "num_input_tokens_seen": 2593824,
      "step": 9265
    },
    {
      "epoch": 103.0,
      "grad_norm": 6.390690145963163e-07,
      "learning_rate": 0.2619774389878175,
      "loss": 0.0,
      "num_input_tokens_seen": 2595200,
      "step": 9270
    },
    {
      "epoch": 103.05555555555556,
      "grad_norm": 1.41282737331494e-06,
      "learning_rate": 0.2619382369930407,
      "loss": 0.0,
      "num_input_tokens_seen": 2596576,
      "step": 9275
    },
    {
      "epoch": 103.11111111111111,
      "grad_norm": 1.2034180372211267e-06,
      "learning_rate": 0.261899017735981,
      "loss": 0.0,
      "num_input_tokens_seen": 2597952,
      "step": 9280
    },
    {
      "epoch": 103.16666666666667,
      "grad_norm": 1.0956080132018542e-07,
      "learning_rate": 0.2618597812226866,
      "loss": 0.0,
      "num_input_tokens_seen": 2599376,
      "step": 9285
    },
    {
      "epoch": 103.22222222222223,
      "grad_norm": 4.4725300085701747e-07,
      "learning_rate": 0.2618205274592082,
      "loss": 0.0,
      "num_input_tokens_seen": 2600832,
      "step": 9290
    },
    {
      "epoch": 103.27777777777777,
      "grad_norm": 1.913745109050069e-06,
      "learning_rate": 0.2617812564515992,
      "loss": 0.0,
      "num_input_tokens_seen": 2602240,
      "step": 9295
    },
    {
      "epoch": 103.33333333333333,
      "grad_norm": 4.274219520539191e-07,
      "learning_rate": 0.2617419682059158,
      "loss": 0.0,
      "num_input_tokens_seen": 2603696,
      "step": 9300
    },
    {
      "epoch": 103.38888888888889,
      "grad_norm": 3.9954753106030694e-07,
      "learning_rate": 0.26170266272821663,
      "loss": 0.0,
      "num_input_tokens_seen": 2605088,
      "step": 9305
    },
    {
      "epoch": 103.44444444444444,
      "grad_norm": 2.0284571746742586e-06,
      "learning_rate": 0.26166334002456315,
      "loss": 0.0,
      "num_input_tokens_seen": 2606496,
      "step": 9310
    },
    {
      "epoch": 103.5,
      "grad_norm": 1.1729700872820104e-06,
      "learning_rate": 0.2616240001010194,
      "loss": 0.0,
      "num_input_tokens_seen": 2607920,
      "step": 9315
    },
    {
      "epoch": 103.55555555555556,
      "grad_norm": 7.164462658693083e-07,
      "learning_rate": 0.26158464296365197,
      "loss": 0.0,
      "num_input_tokens_seen": 2609328,
      "step": 9320
    },
    {
      "epoch": 103.61111111111111,
      "grad_norm": 4.3181699993510847e-07,
      "learning_rate": 0.2615452686185304,
      "loss": 0.0,
      "num_input_tokens_seen": 2610720,
      "step": 9325
    },
    {
      "epoch": 103.66666666666667,
      "grad_norm": 1.7569200281286612e-06,
      "learning_rate": 0.26150587707172673,
      "loss": 0.0,
      "num_input_tokens_seen": 2612144,
      "step": 9330
    },
    {
      "epoch": 103.72222222222223,
      "grad_norm": 1.2839960561450425e-07,
      "learning_rate": 0.2614664683293154,
      "loss": 0.0,
      "num_input_tokens_seen": 2613536,
      "step": 9335
    },
    {
      "epoch": 103.77777777777777,
      "grad_norm": 4.5107034907232446e-07,
      "learning_rate": 0.26142704239737397,
      "loss": 0.0,
      "num_input_tokens_seen": 2614944,
      "step": 9340
    },
    {
      "epoch": 103.83333333333333,
      "grad_norm": 9.19044794045476e-07,
      "learning_rate": 0.26138759928198235,
      "loss": 0.0,
      "num_input_tokens_seen": 2616304,
      "step": 9345
    },
    {
      "epoch": 103.88888888888889,
      "grad_norm": 9.948366397338759e-08,
      "learning_rate": 0.26134813898922304,
      "loss": 0.0,
      "num_input_tokens_seen": 2617648,
      "step": 9350
    },
    {
      "epoch": 103.94444444444444,
      "grad_norm": 2.0147931536484975e-06,
      "learning_rate": 0.26130866152518145,
      "loss": 0.0,
      "num_input_tokens_seen": 2619056,
      "step": 9355
    },
    {
      "epoch": 104.0,
      "grad_norm": 6.954398372727155e-07,
      "learning_rate": 0.2612691668959455,
      "loss": 0.0,
      "num_input_tokens_seen": 2620432,
      "step": 9360
    },
    {
      "epoch": 104.05555555555556,
      "grad_norm": 6.147097337816376e-07,
      "learning_rate": 0.2612296551076057,
      "loss": 0.0,
      "num_input_tokens_seen": 2621808,
      "step": 9365
    },
    {
      "epoch": 104.11111111111111,
      "grad_norm": 3.115974323009141e-07,
      "learning_rate": 0.26119012616625525,
      "loss": 0.0,
      "num_input_tokens_seen": 2623264,
      "step": 9370
    },
    {
      "epoch": 104.16666666666667,
      "grad_norm": 1.2502397339630988e-06,
      "learning_rate": 0.26115058007799,
      "loss": 0.0,
      "num_input_tokens_seen": 2624624,
      "step": 9375
    },
    {
      "epoch": 104.22222222222223,
      "grad_norm": 3.4002198390226113e-07,
      "learning_rate": 0.26111101684890864,
      "loss": 0.0,
      "num_input_tokens_seen": 2626064,
      "step": 9380
    },
    {
      "epoch": 104.27777777777777,
      "grad_norm": 1.7096647297876189e-06,
      "learning_rate": 0.26107143648511205,
      "loss": 0.0,
      "num_input_tokens_seen": 2627472,
      "step": 9385
    },
    {
      "epoch": 104.33333333333333,
      "grad_norm": 2.3217223770188866e-06,
      "learning_rate": 0.2610318389927042,
      "loss": 0.0,
      "num_input_tokens_seen": 2628864,
      "step": 9390
    },
    {
      "epoch": 104.38888888888889,
      "grad_norm": 9.77415538727655e-07,
      "learning_rate": 0.26099222437779146,
      "loss": 0.0,
      "num_input_tokens_seen": 2630272,
      "step": 9395
    },
    {
      "epoch": 104.44444444444444,
      "grad_norm": 8.796333190730365e-07,
      "learning_rate": 0.26095259264648285,
      "loss": 0.0,
      "num_input_tokens_seen": 2631680,
      "step": 9400
    },
    {
      "epoch": 104.44444444444444,
      "eval_loss": 1.0306973457336426,
      "eval_runtime": 1.195,
      "eval_samples_per_second": 33.471,
      "eval_steps_per_second": 16.736,
      "num_input_tokens_seen": 2631680,
      "step": 9400
    },
    {
      "epoch": 104.5,
      "grad_norm": 9.28384906728752e-07,
      "learning_rate": 0.2609129438048902,
      "loss": 0.0,
      "num_input_tokens_seen": 2633088,
      "step": 9405
    },
    {
      "epoch": 104.55555555555556,
      "grad_norm": 1.302386294810276e-06,
      "learning_rate": 0.2608732778591278,
      "loss": 0.0,
      "num_input_tokens_seen": 2634480,
      "step": 9410
    },
    {
      "epoch": 104.61111111111111,
      "grad_norm": 7.857657919885241e-07,
      "learning_rate": 0.2608335948153126,
      "loss": 0.0,
      "num_input_tokens_seen": 2635824,
      "step": 9415
    },
    {
      "epoch": 104.66666666666667,
      "grad_norm": 6.436803232645616e-07,
      "learning_rate": 0.26079389467956426,
      "loss": 0.0,
      "num_input_tokens_seen": 2637264,
      "step": 9420
    },
    {
      "epoch": 104.72222222222223,
      "grad_norm": 3.816415414803487e-07,
      "learning_rate": 0.26075417745800505,
      "loss": 0.0,
      "num_input_tokens_seen": 2638688,
      "step": 9425
    },
    {
      "epoch": 104.77777777777777,
      "grad_norm": 6.997242394390923e-07,
      "learning_rate": 0.26071444315675985,
      "loss": 0.0,
      "num_input_tokens_seen": 2640080,
      "step": 9430
    },
    {
      "epoch": 104.83333333333333,
      "grad_norm": 3.396280305878463e-07,
      "learning_rate": 0.2606746917819562,
      "loss": 0.0,
      "num_input_tokens_seen": 2641456,
      "step": 9435
    },
    {
      "epoch": 104.88888888888889,
      "grad_norm": 1.1083035360570648e-06,
      "learning_rate": 0.2606349233397242,
      "loss": 0.0,
      "num_input_tokens_seen": 2642832,
      "step": 9440
    },
    {
      "epoch": 104.94444444444444,
      "grad_norm": 8.038934424803301e-07,
      "learning_rate": 0.26059513783619676,
      "loss": 0.0,
      "num_input_tokens_seen": 2644240,
      "step": 9445
    },
    {
      "epoch": 105.0,
      "grad_norm": 4.427299131748441e-07,
      "learning_rate": 0.26055533527750924,
      "loss": 0.0,
      "num_input_tokens_seen": 2645648,
      "step": 9450
    },
    {
      "epoch": 105.05555555555556,
      "grad_norm": 9.383656447425892e-07,
      "learning_rate": 0.26051551566979964,
      "loss": 0.0,
      "num_input_tokens_seen": 2647056,
      "step": 9455
    },
    {
      "epoch": 105.11111111111111,
      "grad_norm": 1.0026183190348092e-06,
      "learning_rate": 0.26047567901920876,
      "loss": 0.0,
      "num_input_tokens_seen": 2648432,
      "step": 9460
    },
    {
      "epoch": 105.16666666666667,
      "grad_norm": 2.0952509203198133e-06,
      "learning_rate": 0.2604358253318798,
      "loss": 0.0,
      "num_input_tokens_seen": 2649840,
      "step": 9465
    },
    {
      "epoch": 105.22222222222223,
      "grad_norm": 1.035280320138554e-06,
      "learning_rate": 0.26039595461395876,
      "loss": 0.0,
      "num_input_tokens_seen": 2651296,
      "step": 9470
    },
    {
      "epoch": 105.27777777777777,
      "grad_norm": 4.514067200034333e-07,
      "learning_rate": 0.26035606687159424,
      "loss": 0.0,
      "num_input_tokens_seen": 2652672,
      "step": 9475
    },
    {
      "epoch": 105.33333333333333,
      "grad_norm": 5.356334895623149e-07,
      "learning_rate": 0.26031616211093733,
      "loss": 0.0,
      "num_input_tokens_seen": 2654080,
      "step": 9480
    },
    {
      "epoch": 105.38888888888889,
      "grad_norm": 1.1915203685930464e-06,
      "learning_rate": 0.26027624033814195,
      "loss": 0.0,
      "num_input_tokens_seen": 2655504,
      "step": 9485
    },
    {
      "epoch": 105.44444444444444,
      "grad_norm": 3.5283730426272086e-07,
      "learning_rate": 0.2602363015593645,
      "loss": 0.0,
      "num_input_tokens_seen": 2656928,
      "step": 9490
    },
    {
      "epoch": 105.5,
      "grad_norm": 5.5681294952592e-07,
      "learning_rate": 0.26019634578076395,
      "loss": 0.0,
      "num_input_tokens_seen": 2658320,
      "step": 9495
    },
    {
      "epoch": 105.55555555555556,
      "grad_norm": 6.768764251319226e-07,
      "learning_rate": 0.26015637300850214,
      "loss": 0.0,
      "num_input_tokens_seen": 2659696,
      "step": 9500
    },
    {
      "epoch": 105.61111111111111,
      "grad_norm": 1.1273616564722033e-06,
      "learning_rate": 0.26011638324874325,
      "loss": 0.0,
      "num_input_tokens_seen": 2661056,
      "step": 9505
    },
    {
      "epoch": 105.66666666666667,
      "grad_norm": 4.1789573401729285e-07,
      "learning_rate": 0.2600763765076543,
      "loss": 0.0,
      "num_input_tokens_seen": 2662480,
      "step": 9510
    },
    {
      "epoch": 105.72222222222223,
      "grad_norm": 6.28963732651755e-07,
      "learning_rate": 0.2600363527914048,
      "loss": 0.0,
      "num_input_tokens_seen": 2663872,
      "step": 9515
    },
    {
      "epoch": 105.77777777777777,
      "grad_norm": 5.123065989209863e-07,
      "learning_rate": 0.25999631210616686,
      "loss": 0.0,
      "num_input_tokens_seen": 2665264,
      "step": 9520
    },
    {
      "epoch": 105.83333333333333,
      "grad_norm": 4.2672840550039837e-07,
      "learning_rate": 0.25995625445811527,
      "loss": 0.0,
      "num_input_tokens_seen": 2666672,
      "step": 9525
    },
    {
      "epoch": 105.88888888888889,
      "grad_norm": 1.9801811959041515e-06,
      "learning_rate": 0.2599161798534275,
      "loss": 0.0,
      "num_input_tokens_seen": 2668080,
      "step": 9530
    },
    {
      "epoch": 105.94444444444444,
      "grad_norm": 5.859134830643598e-07,
      "learning_rate": 0.25987608829828346,
      "loss": 0.0,
      "num_input_tokens_seen": 2669472,
      "step": 9535
    },
    {
      "epoch": 106.0,
      "grad_norm": 1.689935743343085e-06,
      "learning_rate": 0.25983597979886586,
      "loss": 0.0,
      "num_input_tokens_seen": 2670864,
      "step": 9540
    },
    {
      "epoch": 106.05555555555556,
      "grad_norm": 2.469052788001136e-06,
      "learning_rate": 0.2597958543613599,
      "loss": 0.0,
      "num_input_tokens_seen": 2672288,
      "step": 9545
    },
    {
      "epoch": 106.11111111111111,
      "grad_norm": 8.640936925985443e-07,
      "learning_rate": 0.25975571199195335,
      "loss": 0.0,
      "num_input_tokens_seen": 2673712,
      "step": 9550
    },
    {
      "epoch": 106.16666666666667,
      "grad_norm": 7.126925538614159e-07,
      "learning_rate": 0.25971555269683677,
      "loss": 0.0,
      "num_input_tokens_seen": 2675104,
      "step": 9555
    },
    {
      "epoch": 106.22222222222223,
      "grad_norm": 1.055592861121113e-06,
      "learning_rate": 0.25967537648220324,
      "loss": 0.0,
      "num_input_tokens_seen": 2676464,
      "step": 9560
    },
    {
      "epoch": 106.27777777777777,
      "grad_norm": 1.5716376537966426e-06,
      "learning_rate": 0.2596351833542483,
      "loss": 0.0,
      "num_input_tokens_seen": 2677904,
      "step": 9565
    },
    {
      "epoch": 106.33333333333333,
      "grad_norm": 5.541033942790818e-07,
      "learning_rate": 0.25959497331917036,
      "loss": 0.0,
      "num_input_tokens_seen": 2679280,
      "step": 9570
    },
    {
      "epoch": 106.38888888888889,
      "grad_norm": 4.3816652350869845e-07,
      "learning_rate": 0.2595547463831703,
      "loss": 0.0,
      "num_input_tokens_seen": 2680672,
      "step": 9575
    },
    {
      "epoch": 106.44444444444444,
      "grad_norm": 2.531328107124864e-07,
      "learning_rate": 0.25951450255245156,
      "loss": 0.0,
      "num_input_tokens_seen": 2682064,
      "step": 9580
    },
    {
      "epoch": 106.5,
      "grad_norm": 9.864601224762737e-07,
      "learning_rate": 0.2594742418332203,
      "loss": 0.0,
      "num_input_tokens_seen": 2683488,
      "step": 9585
    },
    {
      "epoch": 106.55555555555556,
      "grad_norm": 6.110478807386244e-07,
      "learning_rate": 0.2594339642316852,
      "loss": 0.0,
      "num_input_tokens_seen": 2684896,
      "step": 9590
    },
    {
      "epoch": 106.61111111111111,
      "grad_norm": 3.1360499974653067e-07,
      "learning_rate": 0.2593936697540576,
      "loss": 0.0,
      "num_input_tokens_seen": 2686272,
      "step": 9595
    },
    {
      "epoch": 106.66666666666667,
      "grad_norm": 1.3139033399056643e-06,
      "learning_rate": 0.2593533584065514,
      "loss": 0.0,
      "num_input_tokens_seen": 2687728,
      "step": 9600
    },
    {
      "epoch": 106.66666666666667,
      "eval_loss": 1.0326528549194336,
      "eval_runtime": 1.1823,
      "eval_samples_per_second": 33.833,
      "eval_steps_per_second": 16.917,
      "num_input_tokens_seen": 2687728,
      "step": 9600
    },
    {
      "epoch": 106.72222222222223,
      "grad_norm": 1.1931612107218825e-06,
      "learning_rate": 0.2593130301953831,
      "loss": 0.0,
      "num_input_tokens_seen": 2689136,
      "step": 9605
    },
    {
      "epoch": 106.77777777777777,
      "grad_norm": 7.059193194436375e-07,
      "learning_rate": 0.2592726851267718,
      "loss": 0.0,
      "num_input_tokens_seen": 2690544,
      "step": 9610
    },
    {
      "epoch": 106.83333333333333,
      "grad_norm": 1.2250757208676077e-06,
      "learning_rate": 0.2592323232069393,
      "loss": 0.0,
      "num_input_tokens_seen": 2691936,
      "step": 9615
    },
    {
      "epoch": 106.88888888888889,
      "grad_norm": 5.615580676021636e-07,
      "learning_rate": 0.25919194444210986,
      "loss": 0.0,
      "num_input_tokens_seen": 2693344,
      "step": 9620
    },
    {
      "epoch": 106.94444444444444,
      "grad_norm": 1.7545446553413058e-06,
      "learning_rate": 0.2591515488385103,
      "loss": 0.0,
      "num_input_tokens_seen": 2694720,
      "step": 9625
    },
    {
      "epoch": 107.0,
      "grad_norm": 6.365569902300194e-07,
      "learning_rate": 0.2591111364023704,
      "loss": 0.0,
      "num_input_tokens_seen": 2696112,
      "step": 9630
    },
    {
      "epoch": 107.05555555555556,
      "grad_norm": 1.104052216760465e-06,
      "learning_rate": 0.259070707139922,
      "loss": 0.0,
      "num_input_tokens_seen": 2697536,
      "step": 9635
    },
    {
      "epoch": 107.11111111111111,
      "grad_norm": 5.325897518559941e-07,
      "learning_rate": 0.25903026105739985,
      "loss": 0.0,
      "num_input_tokens_seen": 2698976,
      "step": 9640
    },
    {
      "epoch": 107.16666666666667,
      "grad_norm": 2.7569337817112682e-06,
      "learning_rate": 0.2589897981610413,
      "loss": 0.0,
      "num_input_tokens_seen": 2700384,
      "step": 9645
    },
    {
      "epoch": 107.22222222222223,
      "grad_norm": 3.6087584476263146e-07,
      "learning_rate": 0.2589493184570863,
      "loss": 0.0,
      "num_input_tokens_seen": 2701792,
      "step": 9650
    },
    {
      "epoch": 107.27777777777777,
      "grad_norm": 1.1044685379602015e-06,
      "learning_rate": 0.25890882195177717,
      "loss": 0.0,
      "num_input_tokens_seen": 2703184,
      "step": 9655
    },
    {
      "epoch": 107.33333333333333,
      "grad_norm": 3.74106576828126e-07,
      "learning_rate": 0.25886830865135907,
      "loss": 0.0,
      "num_input_tokens_seen": 2704560,
      "step": 9660
    },
    {
      "epoch": 107.38888888888889,
      "grad_norm": 9.157464120335135e-08,
      "learning_rate": 0.25882777856207967,
      "loss": 0.0,
      "num_input_tokens_seen": 2705968,
      "step": 9665
    },
    {
      "epoch": 107.44444444444444,
      "grad_norm": 1.2713420574073098e-06,
      "learning_rate": 0.2587872316901892,
      "loss": 0.0,
      "num_input_tokens_seen": 2707376,
      "step": 9670
    },
    {
      "epoch": 107.5,
      "grad_norm": 1.7587806269148132e-06,
      "learning_rate": 0.25874666804194046,
      "loss": 0.0,
      "num_input_tokens_seen": 2708768,
      "step": 9675
    },
    {
      "epoch": 107.55555555555556,
      "grad_norm": 7.42665292818856e-07,
      "learning_rate": 0.258706087623589,
      "loss": 0.0,
      "num_input_tokens_seen": 2710160,
      "step": 9680
    },
    {
      "epoch": 107.61111111111111,
      "grad_norm": 5.747901354880014e-07,
      "learning_rate": 0.25866549044139264,
      "loss": 0.0,
      "num_input_tokens_seen": 2711584,
      "step": 9685
    },
    {
      "epoch": 107.66666666666667,
      "grad_norm": 5.62274635740323e-07,
      "learning_rate": 0.25862487650161214,
      "loss": 0.0,
      "num_input_tokens_seen": 2712960,
      "step": 9690
    },
    {
      "epoch": 107.72222222222223,
      "grad_norm": 6.956273068681185e-07,
      "learning_rate": 0.2585842458105106,
      "loss": 0.0,
      "num_input_tokens_seen": 2714368,
      "step": 9695
    },
    {
      "epoch": 107.77777777777777,
      "grad_norm": 3.1146879564403207e-07,
      "learning_rate": 0.2585435983743538,
      "loss": 0.0,
      "num_input_tokens_seen": 2715760,
      "step": 9700
    },
    {
      "epoch": 107.83333333333333,
      "grad_norm": 3.7016963005953585e-07,
      "learning_rate": 0.2585029341994101,
      "loss": 0.0,
      "num_input_tokens_seen": 2717200,
      "step": 9705
    },
    {
      "epoch": 107.88888888888889,
      "grad_norm": 6.81926280776679e-07,
      "learning_rate": 0.2584622532919504,
      "loss": 0.0,
      "num_input_tokens_seen": 2718624,
      "step": 9710
    },
    {
      "epoch": 107.94444444444444,
      "grad_norm": 2.9974691528877884e-07,
      "learning_rate": 0.2584215556582482,
      "loss": 0.0,
      "num_input_tokens_seen": 2720032,
      "step": 9715
    },
    {
      "epoch": 108.0,
      "grad_norm": 9.268315466215427e-07,
      "learning_rate": 0.25838084130457967,
      "loss": 0.0,
      "num_input_tokens_seen": 2721392,
      "step": 9720
    },
    {
      "epoch": 108.05555555555556,
      "grad_norm": 7.548331950602005e-07,
      "learning_rate": 0.2583401102372234,
      "loss": 0.0,
      "num_input_tokens_seen": 2722784,
      "step": 9725
    },
    {
      "epoch": 108.11111111111111,
      "grad_norm": 2.9006704949097184e-07,
      "learning_rate": 0.2582993624624606,
      "loss": 0.0,
      "num_input_tokens_seen": 2724192,
      "step": 9730
    },
    {
      "epoch": 108.16666666666667,
      "grad_norm": 2.4660910185048124e-06,
      "learning_rate": 0.25825859798657513,
      "loss": 0.0,
      "num_input_tokens_seen": 2725600,
      "step": 9735
    },
    {
      "epoch": 108.22222222222223,
      "grad_norm": 4.1402137185286847e-07,
      "learning_rate": 0.25821781681585343,
      "loss": 0.0,
      "num_input_tokens_seen": 2726992,
      "step": 9740
    },
    {
      "epoch": 108.27777777777777,
      "grad_norm": 7.870704052947985e-07,
      "learning_rate": 0.2581770189565844,
      "loss": 0.0,
      "num_input_tokens_seen": 2728416,
      "step": 9745
    },
    {
      "epoch": 108.33333333333333,
      "grad_norm": 7.345708468164958e-07,
      "learning_rate": 0.25813620441505963,
      "loss": 0.0,
      "num_input_tokens_seen": 2729792,
      "step": 9750
    },
    {
      "epoch": 108.38888888888889,
      "grad_norm": 7.080607815623807e-07,
      "learning_rate": 0.2580953731975732,
      "loss": 0.0,
      "num_input_tokens_seen": 2731200,
      "step": 9755
    },
    {
      "epoch": 108.44444444444444,
      "grad_norm": 1.7897393718158128e-06,
      "learning_rate": 0.2580545253104218,
      "loss": 0.0,
      "num_input_tokens_seen": 2732640,
      "step": 9760
    },
    {
      "epoch": 108.5,
      "grad_norm": 7.431146400449506e-07,
      "learning_rate": 0.2580136607599047,
      "loss": 0.0,
      "num_input_tokens_seen": 2734016,
      "step": 9765
    },
    {
      "epoch": 108.55555555555556,
      "grad_norm": 2.8221847969689406e-07,
      "learning_rate": 0.2579727795523238,
      "loss": 0.0,
      "num_input_tokens_seen": 2735376,
      "step": 9770
    },
    {
      "epoch": 108.61111111111111,
      "grad_norm": 1.9143008103128523e-06,
      "learning_rate": 0.25793188169398334,
      "loss": 0.0,
      "num_input_tokens_seen": 2736800,
      "step": 9775
    },
    {
      "epoch": 108.66666666666667,
      "grad_norm": 5.142039185557223e-07,
      "learning_rate": 0.25789096719119037,
      "loss": 0.0,
      "num_input_tokens_seen": 2738176,
      "step": 9780
    },
    {
      "epoch": 108.72222222222223,
      "grad_norm": 4.2908322939183563e-07,
      "learning_rate": 0.2578500360502544,
      "loss": 0.0,
      "num_input_tokens_seen": 2739552,
      "step": 9785
    },
    {
      "epoch": 108.77777777777777,
      "grad_norm": 1.2990004449875414e-07,
      "learning_rate": 0.2578090882774876,
      "loss": 0.0,
      "num_input_tokens_seen": 2740960,
      "step": 9790
    },
    {
      "epoch": 108.83333333333333,
      "grad_norm": 4.655724410440598e-07,
      "learning_rate": 0.25776812387920456,
      "loss": 0.0,
      "num_input_tokens_seen": 2742368,
      "step": 9795
    },
    {
      "epoch": 108.88888888888889,
      "grad_norm": 5.555381790145475e-07,
      "learning_rate": 0.2577271428617225,
      "loss": 0.0,
      "num_input_tokens_seen": 2743792,
      "step": 9800
    },
    {
      "epoch": 108.88888888888889,
      "eval_loss": 1.0424296855926514,
      "eval_runtime": 1.1835,
      "eval_samples_per_second": 33.799,
      "eval_steps_per_second": 16.899,
      "num_input_tokens_seen": 2743792,
      "step": 9800
    },
    {
      "epoch": 108.94444444444444,
      "grad_norm": 2.226029636176463e-07,
      "learning_rate": 0.25768614523136124,
      "loss": 0.0,
      "num_input_tokens_seen": 2745184,
      "step": 9805
    },
    {
      "epoch": 109.0,
      "grad_norm": 1.5005654177002725e-06,
      "learning_rate": 0.25764513099444314,
      "loss": 0.0,
      "num_input_tokens_seen": 2746592,
      "step": 9810
    },
    {
      "epoch": 109.05555555555556,
      "grad_norm": 1.4120993228061707e-06,
      "learning_rate": 0.25760410015729307,
      "loss": 0.0,
      "num_input_tokens_seen": 2748016,
      "step": 9815
    },
    {
      "epoch": 109.11111111111111,
      "grad_norm": 1.3703208878723672e-06,
      "learning_rate": 0.2575630527262385,
      "loss": 0.0,
      "num_input_tokens_seen": 2749408,
      "step": 9820
    },
    {
      "epoch": 109.16666666666667,
      "grad_norm": 6.741833544765541e-07,
      "learning_rate": 0.25752198870760945,
      "loss": 0.0,
      "num_input_tokens_seen": 2750816,
      "step": 9825
    },
    {
      "epoch": 109.22222222222223,
      "grad_norm": 3.296753732229263e-07,
      "learning_rate": 0.2574809081077386,
      "loss": 0.0,
      "num_input_tokens_seen": 2752224,
      "step": 9830
    },
    {
      "epoch": 109.27777777777777,
      "grad_norm": 3.527796366142866e-07,
      "learning_rate": 0.257439810932961,
      "loss": 0.0,
      "num_input_tokens_seen": 2753616,
      "step": 9835
    },
    {
      "epoch": 109.33333333333333,
      "grad_norm": 1.5266336959030014e-06,
      "learning_rate": 0.2573986971896144,
      "loss": 0.0,
      "num_input_tokens_seen": 2754992,
      "step": 9840
    },
    {
      "epoch": 109.38888888888889,
      "grad_norm": 7.885656714279321e-07,
      "learning_rate": 0.257357566884039,
      "loss": 0.0,
      "num_input_tokens_seen": 2756400,
      "step": 9845
    },
    {
      "epoch": 109.44444444444444,
      "grad_norm": 8.086048524091893e-07,
      "learning_rate": 0.25731642002257765,
      "loss": 0.0,
      "num_input_tokens_seen": 2757760,
      "step": 9850
    },
    {
      "epoch": 109.5,
      "grad_norm": 1.4124088920652866e-06,
      "learning_rate": 0.25727525661157574,
      "loss": 0.0,
      "num_input_tokens_seen": 2759216,
      "step": 9855
    },
    {
      "epoch": 109.55555555555556,
      "grad_norm": 7.226459501907812e-07,
      "learning_rate": 0.2572340766573811,
      "loss": 0.0,
      "num_input_tokens_seen": 2760576,
      "step": 9860
    },
    {
      "epoch": 109.61111111111111,
      "grad_norm": 1.0347726231429988e-07,
      "learning_rate": 0.25719288016634434,
      "loss": 0.0,
      "num_input_tokens_seen": 2761968,
      "step": 9865
    },
    {
      "epoch": 109.66666666666667,
      "grad_norm": 4.072905426255602e-07,
      "learning_rate": 0.25715166714481835,
      "loss": 0.0,
      "num_input_tokens_seen": 2763376,
      "step": 9870
    },
    {
      "epoch": 109.72222222222223,
      "grad_norm": 6.790549491597631e-07,
      "learning_rate": 0.2571104375991587,
      "loss": 0.0,
      "num_input_tokens_seen": 2764768,
      "step": 9875
    },
    {
      "epoch": 109.77777777777777,
      "grad_norm": 7.973404194672185e-07,
      "learning_rate": 0.2570691915357236,
      "loss": 0.0,
      "num_input_tokens_seen": 2766208,
      "step": 9880
    },
    {
      "epoch": 109.83333333333333,
      "grad_norm": 2.1299418051512475e-07,
      "learning_rate": 0.2570279289608736,
      "loss": 0.0,
      "num_input_tokens_seen": 2767616,
      "step": 9885
    },
    {
      "epoch": 109.88888888888889,
      "grad_norm": 3.0277502105491294e-07,
      "learning_rate": 0.256986649880972,
      "loss": 0.0,
      "num_input_tokens_seen": 2769008,
      "step": 9890
    },
    {
      "epoch": 109.94444444444444,
      "grad_norm": 4.1888202417794673e-07,
      "learning_rate": 0.25694535430238447,
      "loss": 0.0,
      "num_input_tokens_seen": 2770416,
      "step": 9895
    },
    {
      "epoch": 110.0,
      "grad_norm": 8.647551794638275e-07,
      "learning_rate": 0.25690404223147933,
      "loss": 0.0,
      "num_input_tokens_seen": 2771824,
      "step": 9900
    },
    {
      "epoch": 110.05555555555556,
      "grad_norm": 8.114118088542455e-08,
      "learning_rate": 0.2568627136746275,
      "loss": 0.0,
      "num_input_tokens_seen": 2773216,
      "step": 9905
    },
    {
      "epoch": 110.11111111111111,
      "grad_norm": 1.2742667365728266e-07,
      "learning_rate": 0.25682136863820226,
      "loss": 0.0,
      "num_input_tokens_seen": 2774608,
      "step": 9910
    },
    {
      "epoch": 110.16666666666667,
      "grad_norm": 3.845676701530465e-07,
      "learning_rate": 0.25678000712857957,
      "loss": 0.0,
      "num_input_tokens_seen": 2776064,
      "step": 9915
    },
    {
      "epoch": 110.22222222222223,
      "grad_norm": 3.492895075396518e-07,
      "learning_rate": 0.2567386291521379,
      "loss": 0.0,
      "num_input_tokens_seen": 2777472,
      "step": 9920
    },
    {
      "epoch": 110.27777777777777,
      "grad_norm": 1.9338606307428563e-06,
      "learning_rate": 0.2566972347152583,
      "loss": 0.0,
      "num_input_tokens_seen": 2778896,
      "step": 9925
    },
    {
      "epoch": 110.33333333333333,
      "grad_norm": 5.057132739239023e-07,
      "learning_rate": 0.2566558238243242,
      "loss": 0.0,
      "num_input_tokens_seen": 2780272,
      "step": 9930
    },
    {
      "epoch": 110.38888888888889,
      "grad_norm": 1.6745413233820727e-07,
      "learning_rate": 0.25661439648572176,
      "loss": 0.0,
      "num_input_tokens_seen": 2781680,
      "step": 9935
    },
    {
      "epoch": 110.44444444444444,
      "grad_norm": 9.435578363081731e-07,
      "learning_rate": 0.25657295270583963,
      "loss": 0.0,
      "num_input_tokens_seen": 2783072,
      "step": 9940
    },
    {
      "epoch": 110.5,
      "grad_norm": 4.931422381559969e-07,
      "learning_rate": 0.25653149249106894,
      "loss": 0.0,
      "num_input_tokens_seen": 2784480,
      "step": 9945
    },
    {
      "epoch": 110.55555555555556,
      "grad_norm": 9.538024414723623e-07,
      "learning_rate": 0.25649001584780323,
      "loss": 0.0,
      "num_input_tokens_seen": 2785904,
      "step": 9950
    },
    {
      "epoch": 110.61111111111111,
      "grad_norm": 9.915364671542193e-07,
      "learning_rate": 0.2564485227824389,
      "loss": 0.0,
      "num_input_tokens_seen": 2787328,
      "step": 9955
    },
    {
      "epoch": 110.66666666666667,
      "grad_norm": 5.927232109570468e-07,
      "learning_rate": 0.25640701330137466,
      "loss": 0.0,
      "num_input_tokens_seen": 2788720,
      "step": 9960
    },
    {
      "epoch": 110.72222222222223,
      "grad_norm": 2.950206123841781e-07,
      "learning_rate": 0.2563654874110117,
      "loss": 0.0,
      "num_input_tokens_seen": 2790160,
      "step": 9965
    },
    {
      "epoch": 110.77777777777777,
      "grad_norm": 2.821637110628217e-07,
      "learning_rate": 0.256323945117754,
      "loss": 0.0,
      "num_input_tokens_seen": 2791552,
      "step": 9970
    },
    {
      "epoch": 110.83333333333333,
      "grad_norm": 3.5674281662068097e-07,
      "learning_rate": 0.2562823864280078,
      "loss": 0.0,
      "num_input_tokens_seen": 2792928,
      "step": 9975
    },
    {
      "epoch": 110.88888888888889,
      "grad_norm": 1.1573478104764945e-06,
      "learning_rate": 0.25624081134818194,
      "loss": 0.0,
      "num_input_tokens_seen": 2794304,
      "step": 9980
    },
    {
      "epoch": 110.94444444444444,
      "grad_norm": 6.157527536743146e-07,
      "learning_rate": 0.2561992198846879,
      "loss": 0.0,
      "num_input_tokens_seen": 2795648,
      "step": 9985
    },
    {
      "epoch": 111.0,
      "grad_norm": 2.5710551199153997e-07,
      "learning_rate": 0.25615761204393955,
      "loss": 0.0,
      "num_input_tokens_seen": 2797056,
      "step": 9990
    },
    {
      "epoch": 111.05555555555556,
      "grad_norm": 2.944701122942206e-07,
      "learning_rate": 0.2561159878323534,
      "loss": 0.0,
      "num_input_tokens_seen": 2798432,
      "step": 9995
    },
    {
      "epoch": 111.11111111111111,
      "grad_norm": 6.853939567008638e-07,
      "learning_rate": 0.2560743472563483,
      "loss": 0.0,
      "num_input_tokens_seen": 2799840,
      "step": 10000
    },
    {
      "epoch": 111.11111111111111,
      "eval_loss": 1.0433018207550049,
      "eval_runtime": 1.1859,
      "eval_samples_per_second": 33.73,
      "eval_steps_per_second": 16.865,
      "num_input_tokens_seen": 2799840,
      "step": 10000
    },
    {
      "epoch": 111.16666666666667,
      "grad_norm": 1.767992557688558e-06,
      "learning_rate": 0.25603269032234593,
      "loss": 0.0,
      "num_input_tokens_seen": 2801232,
      "step": 10005
    },
    {
      "epoch": 111.22222222222223,
      "grad_norm": 7.482703381356259e-07,
      "learning_rate": 0.2559910170367702,
      "loss": 0.0,
      "num_input_tokens_seen": 2802608,
      "step": 10010
    },
    {
      "epoch": 111.27777777777777,
      "grad_norm": 1.6461206087114988e-07,
      "learning_rate": 0.2559493274060477,
      "loss": 0.0,
      "num_input_tokens_seen": 2804032,
      "step": 10015
    },
    {
      "epoch": 111.33333333333333,
      "grad_norm": 1.762852264164394e-07,
      "learning_rate": 0.2559076214366074,
      "loss": 0.0,
      "num_input_tokens_seen": 2805440,
      "step": 10020
    },
    {
      "epoch": 111.38888888888889,
      "grad_norm": 2.4762616135376447e-07,
      "learning_rate": 0.25586589913488106,
      "loss": 0.0,
      "num_input_tokens_seen": 2806864,
      "step": 10025
    },
    {
      "epoch": 111.44444444444444,
      "grad_norm": 3.601155924570776e-07,
      "learning_rate": 0.2558241605073026,
      "loss": 0.0,
      "num_input_tokens_seen": 2808272,
      "step": 10030
    },
    {
      "epoch": 111.5,
      "grad_norm": 1.0951001740977517e-06,
      "learning_rate": 0.25578240556030873,
      "loss": 0.0,
      "num_input_tokens_seen": 2809664,
      "step": 10035
    },
    {
      "epoch": 111.55555555555556,
      "grad_norm": 1.278709532925859e-06,
      "learning_rate": 0.2557406343003386,
      "loss": 0.0,
      "num_input_tokens_seen": 2811072,
      "step": 10040
    },
    {
      "epoch": 111.61111111111111,
      "grad_norm": 9.978715524994186e-07,
      "learning_rate": 0.25569884673383375,
      "loss": 0.0,
      "num_input_tokens_seen": 2812464,
      "step": 10045
    },
    {
      "epoch": 111.66666666666667,
      "grad_norm": 2.745145479821076e-07,
      "learning_rate": 0.25565704286723856,
      "loss": 0.0,
      "num_input_tokens_seen": 2813856,
      "step": 10050
    },
    {
      "epoch": 111.72222222222223,
      "grad_norm": 5.3365848629027823e-08,
      "learning_rate": 0.25561522270699955,
      "loss": 0.0,
      "num_input_tokens_seen": 2815232,
      "step": 10055
    },
    {
      "epoch": 111.77777777777777,
      "grad_norm": 6.682408866254264e-07,
      "learning_rate": 0.25557338625956594,
      "loss": 0.0,
      "num_input_tokens_seen": 2816608,
      "step": 10060
    },
    {
      "epoch": 111.83333333333333,
      "grad_norm": 3.9547228425362846e-07,
      "learning_rate": 0.25553153353138947,
      "loss": 0.0,
      "num_input_tokens_seen": 2818016,
      "step": 10065
    },
    {
      "epoch": 111.88888888888889,
      "grad_norm": 5.730693146688282e-07,
      "learning_rate": 0.2554896645289243,
      "loss": 0.0,
      "num_input_tokens_seen": 2819376,
      "step": 10070
    },
    {
      "epoch": 111.94444444444444,
      "grad_norm": 2.591501470305957e-06,
      "learning_rate": 0.2554477792586272,
      "loss": 0.0,
      "num_input_tokens_seen": 2820752,
      "step": 10075
    },
    {
      "epoch": 112.0,
      "grad_norm": 2.2808631001680624e-06,
      "learning_rate": 0.25540587772695744,
      "loss": 0.0,
      "num_input_tokens_seen": 2822160,
      "step": 10080
    },
    {
      "epoch": 112.05555555555556,
      "grad_norm": 1.3218385674917954e-06,
      "learning_rate": 0.2553639599403767,
      "loss": 0.0,
      "num_input_tokens_seen": 2823520,
      "step": 10085
    },
    {
      "epoch": 112.11111111111111,
      "grad_norm": 7.26604767464778e-08,
      "learning_rate": 0.2553220259053493,
      "loss": 0.0,
      "num_input_tokens_seen": 2824960,
      "step": 10090
    },
    {
      "epoch": 112.16666666666667,
      "grad_norm": 4.554017039026803e-07,
      "learning_rate": 0.2552800756283419,
      "loss": 0.0,
      "num_input_tokens_seen": 2826368,
      "step": 10095
    },
    {
      "epoch": 112.22222222222223,
      "grad_norm": 1.0539118875385611e-06,
      "learning_rate": 0.25523810911582373,
      "loss": 0.0,
      "num_input_tokens_seen": 2827760,
      "step": 10100
    },
    {
      "epoch": 112.27777777777777,
      "grad_norm": 5.74008652165503e-07,
      "learning_rate": 0.25519612637426675,
      "loss": 0.0,
      "num_input_tokens_seen": 2829152,
      "step": 10105
    },
    {
      "epoch": 112.33333333333333,
      "grad_norm": 1.8801563328452175e-07,
      "learning_rate": 0.25515412741014504,
      "loss": 0.0,
      "num_input_tokens_seen": 2830576,
      "step": 10110
    },
    {
      "epoch": 112.38888888888889,
      "grad_norm": 2.4817046551106614e-07,
      "learning_rate": 0.2551121122299355,
      "loss": 0.0,
      "num_input_tokens_seen": 2831968,
      "step": 10115
    },
    {
      "epoch": 112.44444444444444,
      "grad_norm": 1.0945424264718895e-06,
      "learning_rate": 0.2550700808401173,
      "loss": 0.0,
      "num_input_tokens_seen": 2833376,
      "step": 10120
    },
    {
      "epoch": 112.5,
      "grad_norm": 4.0400513512395264e-07,
      "learning_rate": 0.2550280332471722,
      "loss": 0.0,
      "num_input_tokens_seen": 2834752,
      "step": 10125
    },
    {
      "epoch": 112.55555555555556,
      "grad_norm": 5.305831791702076e-07,
      "learning_rate": 0.2549859694575845,
      "loss": 0.0,
      "num_input_tokens_seen": 2836160,
      "step": 10130
    },
    {
      "epoch": 112.61111111111111,
      "grad_norm": 6.754769970029884e-07,
      "learning_rate": 0.254943889477841,
      "loss": 0.0,
      "num_input_tokens_seen": 2837568,
      "step": 10135
    },
    {
      "epoch": 112.66666666666667,
      "grad_norm": 1.2784089165052137e-07,
      "learning_rate": 0.25490179331443097,
      "loss": 0.0,
      "num_input_tokens_seen": 2838928,
      "step": 10140
    },
    {
      "epoch": 112.72222222222223,
      "grad_norm": 2.5157575578305114e-07,
      "learning_rate": 0.25485968097384615,
      "loss": 0.0,
      "num_input_tokens_seen": 2840272,
      "step": 10145
    },
    {
      "epoch": 112.77777777777777,
      "grad_norm": 3.456379431554524e-07,
      "learning_rate": 0.25481755246258075,
      "loss": 0.0,
      "num_input_tokens_seen": 2841712,
      "step": 10150
    },
    {
      "epoch": 112.83333333333333,
      "grad_norm": 4.2422675505804364e-07,
      "learning_rate": 0.2547754077871315,
      "loss": 0.0,
      "num_input_tokens_seen": 2843136,
      "step": 10155
    },
    {
      "epoch": 112.88888888888889,
      "grad_norm": 2.7959438853031315e-07,
      "learning_rate": 0.25473324695399774,
      "loss": 0.0,
      "num_input_tokens_seen": 2844528,
      "step": 10160
    },
    {
      "epoch": 112.94444444444444,
      "grad_norm": 5.81800577492686e-07,
      "learning_rate": 0.25469106996968105,
      "loss": 0.0,
      "num_input_tokens_seen": 2845904,
      "step": 10165
    },
    {
      "epoch": 113.0,
      "grad_norm": 7.517150493185909e-07,
      "learning_rate": 0.2546488768406858,
      "loss": 0.0,
      "num_input_tokens_seen": 2847344,
      "step": 10170
    },
    {
      "epoch": 113.05555555555556,
      "grad_norm": 1.194897436107567e-06,
      "learning_rate": 0.25460666757351863,
      "loss": 0.0,
      "num_input_tokens_seen": 2848736,
      "step": 10175
    },
    {
      "epoch": 113.11111111111111,
      "grad_norm": 6.100178779888665e-07,
      "learning_rate": 0.25456444217468877,
      "loss": 0.0,
      "num_input_tokens_seen": 2850144,
      "step": 10180
    },
    {
      "epoch": 113.16666666666667,
      "grad_norm": 4.923853111904464e-07,
      "learning_rate": 0.25452220065070785,
      "loss": 0.0,
      "num_input_tokens_seen": 2851568,
      "step": 10185
    },
    {
      "epoch": 113.22222222222223,
      "grad_norm": 5.867694881089847e-07,
      "learning_rate": 0.2544799430080901,
      "loss": 0.0,
      "num_input_tokens_seen": 2852976,
      "step": 10190
    },
    {
      "epoch": 113.27777777777777,
      "grad_norm": 1.043743282025389e-06,
      "learning_rate": 0.2544376692533522,
      "loss": 0.0,
      "num_input_tokens_seen": 2854384,
      "step": 10195
    },
    {
      "epoch": 113.33333333333333,
      "grad_norm": 1.6734219343561563e-06,
      "learning_rate": 0.2543953793930132,
      "loss": 0.0,
      "num_input_tokens_seen": 2855808,
      "step": 10200
    },
    {
      "epoch": 113.33333333333333,
      "eval_loss": 1.0505759716033936,
      "eval_runtime": 1.1804,
      "eval_samples_per_second": 33.886,
      "eval_steps_per_second": 16.943,
      "num_input_tokens_seen": 2855808,
      "step": 10200
    },
    {
      "epoch": 113.38888888888889,
      "grad_norm": 6.959807024031761e-07,
      "learning_rate": 0.2543530734335948,
      "loss": 0.0,
      "num_input_tokens_seen": 2857184,
      "step": 10205
    },
    {
      "epoch": 113.44444444444444,
      "grad_norm": 5.043190753895033e-07,
      "learning_rate": 0.2543107513816211,
      "loss": 0.0,
      "num_input_tokens_seen": 2858544,
      "step": 10210
    },
    {
      "epoch": 113.5,
      "grad_norm": 3.2691403362150595e-07,
      "learning_rate": 0.25426841324361865,
      "loss": 0.0,
      "num_input_tokens_seen": 2859936,
      "step": 10215
    },
    {
      "epoch": 113.55555555555556,
      "grad_norm": 6.201186408816284e-08,
      "learning_rate": 0.2542260590261166,
      "loss": 0.0,
      "num_input_tokens_seen": 2861360,
      "step": 10220
    },
    {
      "epoch": 113.61111111111111,
      "grad_norm": 2.6136081032746006e-07,
      "learning_rate": 0.2541836887356465,
      "loss": 0.0,
      "num_input_tokens_seen": 2862752,
      "step": 10225
    },
    {
      "epoch": 113.66666666666667,
      "grad_norm": 2.2570333158000722e-07,
      "learning_rate": 0.2541413023787423,
      "loss": 0.0,
      "num_input_tokens_seen": 2864064,
      "step": 10230
    },
    {
      "epoch": 113.72222222222223,
      "grad_norm": 1.1116180758108385e-06,
      "learning_rate": 0.2540988999619405,
      "loss": 0.0,
      "num_input_tokens_seen": 2865440,
      "step": 10235
    },
    {
      "epoch": 113.77777777777777,
      "grad_norm": 8.491648486597114e-07,
      "learning_rate": 0.25405648149178023,
      "loss": 0.0,
      "num_input_tokens_seen": 2866800,
      "step": 10240
    },
    {
      "epoch": 113.83333333333333,
      "grad_norm": 3.173864797645365e-07,
      "learning_rate": 0.2540140469748028,
      "loss": 0.0,
      "num_input_tokens_seen": 2868208,
      "step": 10245
    },
    {
      "epoch": 113.88888888888889,
      "grad_norm": 4.460548836959788e-07,
      "learning_rate": 0.25397159641755224,
      "loss": 0.0,
      "num_input_tokens_seen": 2869600,
      "step": 10250
    },
    {
      "epoch": 113.94444444444444,
      "grad_norm": 3.156238221890817e-07,
      "learning_rate": 0.2539291298265749,
      "loss": 0.0,
      "num_input_tokens_seen": 2871040,
      "step": 10255
    },
    {
      "epoch": 114.0,
      "grad_norm": 8.354122655873653e-07,
      "learning_rate": 0.2538866472084197,
      "loss": 0.0,
      "num_input_tokens_seen": 2872448,
      "step": 10260
    },
    {
      "epoch": 114.05555555555556,
      "grad_norm": 6.591059786842379e-07,
      "learning_rate": 0.25384414856963794,
      "loss": 0.0,
      "num_input_tokens_seen": 2873840,
      "step": 10265
    },
    {
      "epoch": 114.11111111111111,
      "grad_norm": 1.7807512620038324e-07,
      "learning_rate": 0.25380163391678356,
      "loss": 0.0,
      "num_input_tokens_seen": 2875216,
      "step": 10270
    },
    {
      "epoch": 114.16666666666667,
      "grad_norm": 8.703720482117205e-07,
      "learning_rate": 0.2537591032564127,
      "loss": 0.0,
      "num_input_tokens_seen": 2876656,
      "step": 10275
    },
    {
      "epoch": 114.22222222222223,
      "grad_norm": 3.524573344293458e-07,
      "learning_rate": 0.25371655659508424,
      "loss": 0.0,
      "num_input_tokens_seen": 2878016,
      "step": 10280
    },
    {
      "epoch": 114.27777777777777,
      "grad_norm": 5.037583150624414e-07,
      "learning_rate": 0.25367399393935935,
      "loss": 0.0,
      "num_input_tokens_seen": 2879376,
      "step": 10285
    },
    {
      "epoch": 114.33333333333333,
      "grad_norm": 7.851725172258739e-07,
      "learning_rate": 0.25363141529580174,
      "loss": 0.0,
      "num_input_tokens_seen": 2880768,
      "step": 10290
    },
    {
      "epoch": 114.38888888888889,
      "grad_norm": 1.7165578469757747e-07,
      "learning_rate": 0.2535888206709776,
      "loss": 0.0,
      "num_input_tokens_seen": 2882176,
      "step": 10295
    },
    {
      "epoch": 114.44444444444444,
      "grad_norm": 1.2683140084845945e-06,
      "learning_rate": 0.2535462100714555,
      "loss": 0.0,
      "num_input_tokens_seen": 2883600,
      "step": 10300
    },
    {
      "epoch": 114.5,
      "grad_norm": 5.977835257908737e-07,
      "learning_rate": 0.2535035835038066,
      "loss": 0.0,
      "num_input_tokens_seen": 2884976,
      "step": 10305
    },
    {
      "epoch": 114.55555555555556,
      "grad_norm": 5.691900355486723e-07,
      "learning_rate": 0.2534609409746044,
      "loss": 0.0,
      "num_input_tokens_seen": 2886384,
      "step": 10310
    },
    {
      "epoch": 114.61111111111111,
      "grad_norm": 4.2547958400973585e-07,
      "learning_rate": 0.253418282490425,
      "loss": 0.0,
      "num_input_tokens_seen": 2887776,
      "step": 10315
    },
    {
      "epoch": 114.66666666666667,
      "grad_norm": 6.95201947564783e-07,
      "learning_rate": 0.2533756080578467,
      "loss": 0.0,
      "num_input_tokens_seen": 2889200,
      "step": 10320
    },
    {
      "epoch": 114.72222222222223,
      "grad_norm": 1.6850003703439143e-07,
      "learning_rate": 0.25333291768345056,
      "loss": 0.0,
      "num_input_tokens_seen": 2890624,
      "step": 10325
    },
    {
      "epoch": 114.77777777777777,
      "grad_norm": 2.927781963535381e-07,
      "learning_rate": 0.25329021137381996,
      "loss": 0.0,
      "num_input_tokens_seen": 2892032,
      "step": 10330
    },
    {
      "epoch": 114.83333333333333,
      "grad_norm": 6.003842827340122e-07,
      "learning_rate": 0.25324748913554074,
      "loss": 0.0,
      "num_input_tokens_seen": 2893472,
      "step": 10335
    },
    {
      "epoch": 114.88888888888889,
      "grad_norm": 1.3841464578945306e-06,
      "learning_rate": 0.2532047509752013,
      "loss": 0.0,
      "num_input_tokens_seen": 2894880,
      "step": 10340
    },
    {
      "epoch": 114.94444444444444,
      "grad_norm": 2.0124575712543447e-06,
      "learning_rate": 0.25316199689939217,
      "loss": 0.0,
      "num_input_tokens_seen": 2896288,
      "step": 10345
    },
    {
      "epoch": 115.0,
      "grad_norm": 5.411002916844154e-07,
      "learning_rate": 0.2531192269147068,
      "loss": 0.0,
      "num_input_tokens_seen": 2897648,
      "step": 10350
    },
    {
      "epoch": 115.05555555555556,
      "grad_norm": 3.1439628855878254e-07,
      "learning_rate": 0.2530764410277407,
      "loss": 0.0,
      "num_input_tokens_seen": 2899088,
      "step": 10355
    },
    {
      "epoch": 115.11111111111111,
      "grad_norm": 7.51703964851913e-07,
      "learning_rate": 0.25303363924509203,
      "loss": 0.0,
      "num_input_tokens_seen": 2900448,
      "step": 10360
    },
    {
      "epoch": 115.16666666666667,
      "grad_norm": 3.2957140660982986e-07,
      "learning_rate": 0.25299082157336145,
      "loss": 0.0,
      "num_input_tokens_seen": 2901856,
      "step": 10365
    },
    {
      "epoch": 115.22222222222223,
      "grad_norm": 3.499269212170475e-07,
      "learning_rate": 0.2529479880191519,
      "loss": 0.0,
      "num_input_tokens_seen": 2903216,
      "step": 10370
    },
    {
      "epoch": 115.27777777777777,
      "grad_norm": 3.80689272105883e-07,
      "learning_rate": 0.2529051385890689,
      "loss": 0.0,
      "num_input_tokens_seen": 2904608,
      "step": 10375
    },
    {
      "epoch": 115.33333333333333,
      "grad_norm": 2.7109564371130546e-07,
      "learning_rate": 0.2528622732897203,
      "loss": 0.0,
      "num_input_tokens_seen": 2905984,
      "step": 10380
    },
    {
      "epoch": 115.38888888888889,
      "grad_norm": 3.009908198237099e-07,
      "learning_rate": 0.25281939212771654,
      "loss": 0.0,
      "num_input_tokens_seen": 2907408,
      "step": 10385
    },
    {
      "epoch": 115.44444444444444,
      "grad_norm": 5.482998517436499e-07,
      "learning_rate": 0.2527764951096704,
      "loss": 0.0,
      "num_input_tokens_seen": 2908848,
      "step": 10390
    },
    {
      "epoch": 115.5,
      "grad_norm": 1.258853217223077e-07,
      "learning_rate": 0.2527335822421971,
      "loss": 0.0,
      "num_input_tokens_seen": 2910256,
      "step": 10395
    },
    {
      "epoch": 115.55555555555556,
      "grad_norm": 2.4540739218537055e-07,
      "learning_rate": 0.25269065353191444,
      "loss": 0.0,
      "num_input_tokens_seen": 2911648,
      "step": 10400
    },
    {
      "epoch": 115.55555555555556,
      "eval_loss": 1.0753761529922485,
      "eval_runtime": 1.1804,
      "eval_samples_per_second": 33.886,
      "eval_steps_per_second": 16.943,
      "num_input_tokens_seen": 2911648,
      "step": 10400
    },
    {
      "epoch": 115.61111111111111,
      "grad_norm": 1.4188087789079873e-06,
      "learning_rate": 0.2526477089854425,
      "loss": 0.0,
      "num_input_tokens_seen": 2913056,
      "step": 10405
    },
    {
      "epoch": 115.66666666666667,
      "grad_norm": 1.4927846905266051e-06,
      "learning_rate": 0.25260474860940385,
      "loss": 0.0,
      "num_input_tokens_seen": 2914448,
      "step": 10410
    },
    {
      "epoch": 115.72222222222223,
      "grad_norm": 4.308110135298193e-07,
      "learning_rate": 0.2525617724104236,
      "loss": 0.0,
      "num_input_tokens_seen": 2915856,
      "step": 10415
    },
    {
      "epoch": 115.77777777777777,
      "grad_norm": 2.3479461219721998e-07,
      "learning_rate": 0.25251878039512915,
      "loss": 0.0,
      "num_input_tokens_seen": 2917216,
      "step": 10420
    },
    {
      "epoch": 115.83333333333333,
      "grad_norm": 4.124202632738161e-07,
      "learning_rate": 0.25247577257015047,
      "loss": 0.0,
      "num_input_tokens_seen": 2918624,
      "step": 10425
    },
    {
      "epoch": 115.88888888888889,
      "grad_norm": 2.1868433464078407e-07,
      "learning_rate": 0.2524327489421198,
      "loss": 0.0,
      "num_input_tokens_seen": 2920016,
      "step": 10430
    },
    {
      "epoch": 115.94444444444444,
      "grad_norm": 1.4571101303317846e-07,
      "learning_rate": 0.25238970951767203,
      "loss": 0.0,
      "num_input_tokens_seen": 2921440,
      "step": 10435
    },
    {
      "epoch": 116.0,
      "grad_norm": 1.0130156624654774e-06,
      "learning_rate": 0.25234665430344433,
      "loss": 0.0,
      "num_input_tokens_seen": 2922848,
      "step": 10440
    },
    {
      "epoch": 116.05555555555556,
      "grad_norm": 3.22047526424285e-07,
      "learning_rate": 0.2523035833060764,
      "loss": 0.0,
      "num_input_tokens_seen": 2924272,
      "step": 10445
    },
    {
      "epoch": 116.11111111111111,
      "grad_norm": 1.9379719162770925e-07,
      "learning_rate": 0.2522604965322103,
      "loss": 0.0,
      "num_input_tokens_seen": 2925696,
      "step": 10450
    },
    {
      "epoch": 116.16666666666667,
      "grad_norm": 2.827420928497304e-07,
      "learning_rate": 0.25221739398849047,
      "loss": 0.0,
      "num_input_tokens_seen": 2927104,
      "step": 10455
    },
    {
      "epoch": 116.22222222222223,
      "grad_norm": 3.9937600604389445e-07,
      "learning_rate": 0.252174275681564,
      "loss": 0.0,
      "num_input_tokens_seen": 2928560,
      "step": 10460
    },
    {
      "epoch": 116.27777777777777,
      "grad_norm": 1.6080187492661935e-07,
      "learning_rate": 0.2521311416180802,
      "loss": 0.0,
      "num_input_tokens_seen": 2929952,
      "step": 10465
    },
    {
      "epoch": 116.33333333333333,
      "grad_norm": 5.799353530733242e-08,
      "learning_rate": 0.25208799180469094,
      "loss": 0.0,
      "num_input_tokens_seen": 2931296,
      "step": 10470
    },
    {
      "epoch": 116.38888888888889,
      "grad_norm": 2.8194335754960775e-07,
      "learning_rate": 0.2520448262480504,
      "loss": 0.0,
      "num_input_tokens_seen": 2932672,
      "step": 10475
    },
    {
      "epoch": 116.44444444444444,
      "grad_norm": 2.280565922774258e-07,
      "learning_rate": 0.25200164495481525,
      "loss": 0.0,
      "num_input_tokens_seen": 2934064,
      "step": 10480
    },
    {
      "epoch": 116.5,
      "grad_norm": 1.26475151773775e-06,
      "learning_rate": 0.25195844793164474,
      "loss": 0.0,
      "num_input_tokens_seen": 2935504,
      "step": 10485
    },
    {
      "epoch": 116.55555555555556,
      "grad_norm": 2.992185557104676e-07,
      "learning_rate": 0.2519152351852001,
      "loss": 0.0,
      "num_input_tokens_seen": 2936864,
      "step": 10490
    },
    {
      "epoch": 116.61111111111111,
      "grad_norm": 1.584606224014351e-07,
      "learning_rate": 0.25187200672214555,
      "loss": 0.0,
      "num_input_tokens_seen": 2938256,
      "step": 10495
    },
    {
      "epoch": 116.66666666666667,
      "grad_norm": 2.8425483833416365e-07,
      "learning_rate": 0.2518287625491473,
      "loss": 0.0,
      "num_input_tokens_seen": 2939632,
      "step": 10500
    },
    {
      "epoch": 116.72222222222223,
      "grad_norm": 3.866848317102267e-07,
      "learning_rate": 0.25178550267287425,
      "loss": 0.0,
      "num_input_tokens_seen": 2941056,
      "step": 10505
    },
    {
      "epoch": 116.77777777777777,
      "grad_norm": 6.085247150622308e-07,
      "learning_rate": 0.2517422270999976,
      "loss": 0.0,
      "num_input_tokens_seen": 2942464,
      "step": 10510
    },
    {
      "epoch": 116.83333333333333,
      "grad_norm": 2.0921420684771874e-07,
      "learning_rate": 0.2516989358371909,
      "loss": 0.0,
      "num_input_tokens_seen": 2943920,
      "step": 10515
    },
    {
      "epoch": 116.88888888888889,
      "grad_norm": 5.2261171390455274e-08,
      "learning_rate": 0.25165562889113025,
      "loss": 0.0,
      "num_input_tokens_seen": 2945296,
      "step": 10520
    },
    {
      "epoch": 116.94444444444444,
      "grad_norm": 1.5599457015014195e-07,
      "learning_rate": 0.2516123062684942,
      "loss": 0.0,
      "num_input_tokens_seen": 2946688,
      "step": 10525
    },
    {
      "epoch": 117.0,
      "grad_norm": 5.499478561432625e-07,
      "learning_rate": 0.25156896797596356,
      "loss": 0.0,
      "num_input_tokens_seen": 2948144,
      "step": 10530
    },
    {
      "epoch": 117.05555555555556,
      "grad_norm": 8.553301995561924e-07,
      "learning_rate": 0.2515256140202216,
      "loss": 0.0,
      "num_input_tokens_seen": 2949568,
      "step": 10535
    },
    {
      "epoch": 117.11111111111111,
      "grad_norm": 4.1974973896685697e-07,
      "learning_rate": 0.25148224440795425,
      "loss": 0.0,
      "num_input_tokens_seen": 2950976,
      "step": 10540
    },
    {
      "epoch": 117.16666666666667,
      "grad_norm": 1.1329414917327085e-07,
      "learning_rate": 0.2514388591458494,
      "loss": 0.0,
      "num_input_tokens_seen": 2952368,
      "step": 10545
    },
    {
      "epoch": 117.22222222222223,
      "grad_norm": 1.4093339473220112e-07,
      "learning_rate": 0.2513954582405977,
      "loss": 0.0,
      "num_input_tokens_seen": 2953712,
      "step": 10550
    },
    {
      "epoch": 117.27777777777777,
      "grad_norm": 6.321689056676405e-07,
      "learning_rate": 0.2513520416988922,
      "loss": 0.0,
      "num_input_tokens_seen": 2955104,
      "step": 10555
    },
    {
      "epoch": 117.33333333333333,
      "grad_norm": 7.942433626340062e-07,
      "learning_rate": 0.2513086095274281,
      "loss": 0.0,
      "num_input_tokens_seen": 2956480,
      "step": 10560
    },
    {
      "epoch": 117.38888888888889,
      "grad_norm": 4.978269316779915e-07,
      "learning_rate": 0.25126516173290336,
      "loss": 0.0,
      "num_input_tokens_seen": 2957920,
      "step": 10565
    },
    {
      "epoch": 117.44444444444444,
      "grad_norm": 1.794528827758768e-07,
      "learning_rate": 0.2512216983220181,
      "loss": 0.0,
      "num_input_tokens_seen": 2959328,
      "step": 10570
    },
    {
      "epoch": 117.5,
      "grad_norm": 1.8128652357063402e-07,
      "learning_rate": 0.25117821930147494,
      "loss": 0.0,
      "num_input_tokens_seen": 2960784,
      "step": 10575
    },
    {
      "epoch": 117.55555555555556,
      "grad_norm": 5.00789155921666e-07,
      "learning_rate": 0.2511347246779788,
      "loss": 0.0,
      "num_input_tokens_seen": 2962208,
      "step": 10580
    },
    {
      "epoch": 117.61111111111111,
      "grad_norm": 2.3048674790970836e-07,
      "learning_rate": 0.25109121445823723,
      "loss": 0.0,
      "num_input_tokens_seen": 2963632,
      "step": 10585
    },
    {
      "epoch": 117.66666666666667,
      "grad_norm": 2.558597316237865e-07,
      "learning_rate": 0.25104768864896004,
      "loss": 0.0,
      "num_input_tokens_seen": 2965056,
      "step": 10590
    },
    {
      "epoch": 117.72222222222223,
      "grad_norm": 2.845698929831997e-07,
      "learning_rate": 0.2510041472568594,
      "loss": 0.0,
      "num_input_tokens_seen": 2966480,
      "step": 10595
    },
    {
      "epoch": 117.77777777777777,
      "grad_norm": 2.960302083465649e-07,
      "learning_rate": 0.25096059028864987,
      "loss": 0.0,
      "num_input_tokens_seen": 2967856,
      "step": 10600
    },
    {
      "epoch": 117.77777777777777,
      "eval_loss": 1.0816168785095215,
      "eval_runtime": 1.1823,
      "eval_samples_per_second": 33.831,
      "eval_steps_per_second": 16.916,
      "num_input_tokens_seen": 2967856,
      "step": 10600
    },
    {
      "epoch": 117.83333333333333,
      "grad_norm": 2.7769505095420755e-07,
      "learning_rate": 0.25091701775104863,
      "loss": 0.0,
      "num_input_tokens_seen": 2969232,
      "step": 10605
    },
    {
      "epoch": 117.88888888888889,
      "grad_norm": 1.2957168564753374e-06,
      "learning_rate": 0.250873429650775,
      "loss": 0.0,
      "num_input_tokens_seen": 2970608,
      "step": 10610
    },
    {
      "epoch": 117.94444444444444,
      "grad_norm": 3.5293879818709684e-07,
      "learning_rate": 0.25082982599455095,
      "loss": 0.0,
      "num_input_tokens_seen": 2972000,
      "step": 10615
    },
    {
      "epoch": 118.0,
      "grad_norm": 2.298781396348204e-07,
      "learning_rate": 0.2507862067891006,
      "loss": 0.0,
      "num_input_tokens_seen": 2973360,
      "step": 10620
    },
    {
      "epoch": 118.05555555555556,
      "grad_norm": 6.589667123080289e-07,
      "learning_rate": 0.25074257204115064,
      "loss": 0.0,
      "num_input_tokens_seen": 2974816,
      "step": 10625
    },
    {
      "epoch": 118.11111111111111,
      "grad_norm": 4.759187390845909e-07,
      "learning_rate": 0.25069892175742997,
      "loss": 0.0,
      "num_input_tokens_seen": 2976192,
      "step": 10630
    },
    {
      "epoch": 118.16666666666667,
      "grad_norm": 1.6106821476569166e-07,
      "learning_rate": 0.25065525594467014,
      "loss": 0.0,
      "num_input_tokens_seen": 2977584,
      "step": 10635
    },
    {
      "epoch": 118.22222222222223,
      "grad_norm": 6.43899056740338e-07,
      "learning_rate": 0.2506115746096049,
      "loss": 0.0,
      "num_input_tokens_seen": 2978992,
      "step": 10640
    },
    {
      "epoch": 118.27777777777777,
      "grad_norm": 4.71032024051965e-07,
      "learning_rate": 0.25056787775897055,
      "loss": 0.0,
      "num_input_tokens_seen": 2980400,
      "step": 10645
    },
    {
      "epoch": 118.33333333333333,
      "grad_norm": 5.681368975274381e-07,
      "learning_rate": 0.2505241653995056,
      "loss": 0.0,
      "num_input_tokens_seen": 2981760,
      "step": 10650
    },
    {
      "epoch": 118.38888888888889,
      "grad_norm": 2.4392900854763866e-07,
      "learning_rate": 0.25048043753795113,
      "loss": 0.0,
      "num_input_tokens_seen": 2983168,
      "step": 10655
    },
    {
      "epoch": 118.44444444444444,
      "grad_norm": 1.4030625550276454e-07,
      "learning_rate": 0.2504366941810504,
      "loss": 0.0,
      "num_input_tokens_seen": 2984608,
      "step": 10660
    },
    {
      "epoch": 118.5,
      "grad_norm": 2.2738480254247406e-07,
      "learning_rate": 0.2503929353355493,
      "loss": 0.0,
      "num_input_tokens_seen": 2986000,
      "step": 10665
    },
    {
      "epoch": 118.55555555555556,
      "grad_norm": 6.668410037491412e-07,
      "learning_rate": 0.250349161008196,
      "loss": 0.0,
      "num_input_tokens_seen": 2987408,
      "step": 10670
    },
    {
      "epoch": 118.61111111111111,
      "grad_norm": 8.678050562593853e-07,
      "learning_rate": 0.2503053712057409,
      "loss": 0.0,
      "num_input_tokens_seen": 2988848,
      "step": 10675
    },
    {
      "epoch": 118.66666666666667,
      "grad_norm": 1.264143065782264e-07,
      "learning_rate": 0.25026156593493715,
      "loss": 0.0,
      "num_input_tokens_seen": 2990272,
      "step": 10680
    },
    {
      "epoch": 118.72222222222223,
      "grad_norm": 2.7913793587686087e-07,
      "learning_rate": 0.2502177452025399,
      "loss": 0.0,
      "num_input_tokens_seen": 2991664,
      "step": 10685
    },
    {
      "epoch": 118.77777777777777,
      "grad_norm": 5.850965862919111e-07,
      "learning_rate": 0.25017390901530695,
      "loss": 0.0,
      "num_input_tokens_seen": 2993072,
      "step": 10690
    },
    {
      "epoch": 118.83333333333333,
      "grad_norm": 1.794455215531343e-07,
      "learning_rate": 0.2501300573799984,
      "loss": 0.0,
      "num_input_tokens_seen": 2994416,
      "step": 10695
    },
    {
      "epoch": 118.88888888888889,
      "grad_norm": 4.96861730425735e-07,
      "learning_rate": 0.2500861903033766,
      "loss": 0.0,
      "num_input_tokens_seen": 2995824,
      "step": 10700
    },
    {
      "epoch": 118.94444444444444,
      "grad_norm": 1.8340554674978193e-07,
      "learning_rate": 0.25004230779220654,
      "loss": 0.0,
      "num_input_tokens_seen": 2997232,
      "step": 10705
    },
    {
      "epoch": 119.0,
      "grad_norm": 3.148939242691995e-07,
      "learning_rate": 0.24999840985325542,
      "loss": 0.0,
      "num_input_tokens_seen": 2998624,
      "step": 10710
    },
    {
      "epoch": 119.05555555555556,
      "grad_norm": 2.1615097978155973e-07,
      "learning_rate": 0.24995449649329285,
      "loss": 0.0,
      "num_input_tokens_seen": 3000032,
      "step": 10715
    },
    {
      "epoch": 119.11111111111111,
      "grad_norm": 1.0124650771103916e-06,
      "learning_rate": 0.2499105677190908,
      "loss": 0.0,
      "num_input_tokens_seen": 3001424,
      "step": 10720
    },
    {
      "epoch": 119.16666666666667,
      "grad_norm": 6.033529302840179e-07,
      "learning_rate": 0.24986662353742364,
      "loss": 0.0,
      "num_input_tokens_seen": 3002848,
      "step": 10725
    },
    {
      "epoch": 119.22222222222223,
      "grad_norm": 1.8733693707417842e-07,
      "learning_rate": 0.24982266395506814,
      "loss": 0.0,
      "num_input_tokens_seen": 3004256,
      "step": 10730
    },
    {
      "epoch": 119.27777777777777,
      "grad_norm": 1.7971275383388274e-06,
      "learning_rate": 0.2497786889788034,
      "loss": 0.0,
      "num_input_tokens_seen": 3005632,
      "step": 10735
    },
    {
      "epoch": 119.33333333333333,
      "grad_norm": 8.079763915702642e-07,
      "learning_rate": 0.24973469861541095,
      "loss": 0.0,
      "num_input_tokens_seen": 3007040,
      "step": 10740
    },
    {
      "epoch": 119.38888888888889,
      "grad_norm": 9.790931443376394e-08,
      "learning_rate": 0.24969069287167456,
      "loss": 0.0,
      "num_input_tokens_seen": 3008432,
      "step": 10745
    },
    {
      "epoch": 119.44444444444444,
      "grad_norm": 5.239749043539632e-07,
      "learning_rate": 0.2496466717543806,
      "loss": 0.0,
      "num_input_tokens_seen": 3009776,
      "step": 10750
    },
    {
      "epoch": 119.5,
      "grad_norm": 1.9779710669354245e-07,
      "learning_rate": 0.24960263527031762,
      "loss": 0.0,
      "num_input_tokens_seen": 3011168,
      "step": 10755
    },
    {
      "epoch": 119.55555555555556,
      "grad_norm": 7.608357464050641e-07,
      "learning_rate": 0.24955858342627657,
      "loss": 0.0,
      "num_input_tokens_seen": 3012528,
      "step": 10760
    },
    {
      "epoch": 119.61111111111111,
      "grad_norm": 2.5472886022726016e-07,
      "learning_rate": 0.24951451622905083,
      "loss": 0.0,
      "num_input_tokens_seen": 3013952,
      "step": 10765
    },
    {
      "epoch": 119.66666666666667,
      "grad_norm": 2.5156285232696973e-07,
      "learning_rate": 0.24947043368543612,
      "loss": 0.0,
      "num_input_tokens_seen": 3015360,
      "step": 10770
    },
    {
      "epoch": 119.72222222222223,
      "grad_norm": 7.403734798572259e-07,
      "learning_rate": 0.2494263358022305,
      "loss": 0.0,
      "num_input_tokens_seen": 3016752,
      "step": 10775
    },
    {
      "epoch": 119.77777777777777,
      "grad_norm": 5.082925369492841e-08,
      "learning_rate": 0.24938222258623444,
      "loss": 0.0,
      "num_input_tokens_seen": 3018144,
      "step": 10780
    },
    {
      "epoch": 119.83333333333333,
      "grad_norm": 2.2294298673841695e-07,
      "learning_rate": 0.24933809404425075,
      "loss": 0.0,
      "num_input_tokens_seen": 3019552,
      "step": 10785
    },
    {
      "epoch": 119.88888888888889,
      "grad_norm": 4.688833996624453e-07,
      "learning_rate": 0.24929395018308453,
      "loss": 0.0,
      "num_input_tokens_seen": 3020928,
      "step": 10790
    },
    {
      "epoch": 119.94444444444444,
      "grad_norm": 1.0748379963843036e-06,
      "learning_rate": 0.24924979100954348,
      "loss": 0.0,
      "num_input_tokens_seen": 3022384,
      "step": 10795
    },
    {
      "epoch": 120.0,
      "grad_norm": 3.585847707654466e-07,
      "learning_rate": 0.24920561653043735,
      "loss": 0.0,
      "num_input_tokens_seen": 3023792,
      "step": 10800
    },
    {
      "epoch": 120.0,
      "eval_loss": 1.0875320434570312,
      "eval_runtime": 1.1811,
      "eval_samples_per_second": 33.868,
      "eval_steps_per_second": 16.934,
      "num_input_tokens_seen": 3023792,
      "step": 10800
    },
    {
      "epoch": 120.05555555555556,
      "grad_norm": 3.2006033734433004e-07,
      "learning_rate": 0.24916142675257846,
      "loss": 0.0,
      "num_input_tokens_seen": 3025184,
      "step": 10805
    },
    {
      "epoch": 120.11111111111111,
      "grad_norm": 4.76790404491112e-07,
      "learning_rate": 0.24911722168278144,
      "loss": 0.0,
      "num_input_tokens_seen": 3026560,
      "step": 10810
    },
    {
      "epoch": 120.16666666666667,
      "grad_norm": 3.675916957490699e-07,
      "learning_rate": 0.24907300132786328,
      "loss": 0.0,
      "num_input_tokens_seen": 3028000,
      "step": 10815
    },
    {
      "epoch": 120.22222222222223,
      "grad_norm": 7.503275583076174e-07,
      "learning_rate": 0.24902876569464322,
      "loss": 0.0,
      "num_input_tokens_seen": 3029424,
      "step": 10820
    },
    {
      "epoch": 120.27777777777777,
      "grad_norm": 2.0028979008657188e-07,
      "learning_rate": 0.24898451478994305,
      "loss": 0.0,
      "num_input_tokens_seen": 3030848,
      "step": 10825
    },
    {
      "epoch": 120.33333333333333,
      "grad_norm": 8.951461722972454e-07,
      "learning_rate": 0.2489402486205868,
      "loss": 0.0,
      "num_input_tokens_seen": 3032288,
      "step": 10830
    },
    {
      "epoch": 120.38888888888889,
      "grad_norm": 5.549931643145101e-07,
      "learning_rate": 0.24889596719340085,
      "loss": 0.0,
      "num_input_tokens_seen": 3033728,
      "step": 10835
    },
    {
      "epoch": 120.44444444444444,
      "grad_norm": 1.0266901426803088e-06,
      "learning_rate": 0.24885167051521392,
      "loss": 0.0,
      "num_input_tokens_seen": 3035168,
      "step": 10840
    },
    {
      "epoch": 120.5,
      "grad_norm": 3.561641221949685e-07,
      "learning_rate": 0.24880735859285716,
      "loss": 0.0,
      "num_input_tokens_seen": 3036576,
      "step": 10845
    },
    {
      "epoch": 120.55555555555556,
      "grad_norm": 9.578734534443356e-07,
      "learning_rate": 0.24876303143316406,
      "loss": 0.0,
      "num_input_tokens_seen": 3037984,
      "step": 10850
    },
    {
      "epoch": 120.61111111111111,
      "grad_norm": 2.739849662702909e-07,
      "learning_rate": 0.24871868904297031,
      "loss": 0.0,
      "num_input_tokens_seen": 3039328,
      "step": 10855
    },
    {
      "epoch": 120.66666666666667,
      "grad_norm": 5.126155997459136e-07,
      "learning_rate": 0.24867433142911416,
      "loss": 0.0,
      "num_input_tokens_seen": 3040784,
      "step": 10860
    },
    {
      "epoch": 120.72222222222223,
      "grad_norm": 1.4398281678040803e-07,
      "learning_rate": 0.24862995859843612,
      "loss": 0.0,
      "num_input_tokens_seen": 3042176,
      "step": 10865
    },
    {
      "epoch": 120.77777777777777,
      "grad_norm": 3.3185017400683137e-07,
      "learning_rate": 0.24858557055777897,
      "loss": 0.0,
      "num_input_tokens_seen": 3043552,
      "step": 10870
    },
    {
      "epoch": 120.83333333333333,
      "grad_norm": 2.480961995843245e-07,
      "learning_rate": 0.24854116731398793,
      "loss": 0.0,
      "num_input_tokens_seen": 3044880,
      "step": 10875
    },
    {
      "epoch": 120.88888888888889,
      "grad_norm": 2.3700090423517395e-07,
      "learning_rate": 0.24849674887391052,
      "loss": 0.0,
      "num_input_tokens_seen": 3046256,
      "step": 10880
    },
    {
      "epoch": 120.94444444444444,
      "grad_norm": 2.0715700088658195e-07,
      "learning_rate": 0.2484523152443967,
      "loss": 0.0,
      "num_input_tokens_seen": 3047648,
      "step": 10885
    },
    {
      "epoch": 121.0,
      "grad_norm": 6.048151703907934e-07,
      "learning_rate": 0.24840786643229862,
      "loss": 0.0,
      "num_input_tokens_seen": 3049024,
      "step": 10890
    },
    {
      "epoch": 121.05555555555556,
      "grad_norm": 1.142122755481978e-06,
      "learning_rate": 0.2483634024444709,
      "loss": 0.0,
      "num_input_tokens_seen": 3050416,
      "step": 10895
    },
    {
      "epoch": 121.11111111111111,
      "grad_norm": 3.1626123586647736e-07,
      "learning_rate": 0.24831892328777033,
      "loss": 0.0,
      "num_input_tokens_seen": 3051808,
      "step": 10900
    },
    {
      "epoch": 121.16666666666667,
      "grad_norm": 5.626681058856775e-07,
      "learning_rate": 0.2482744289690563,
      "loss": 0.0,
      "num_input_tokens_seen": 3053216,
      "step": 10905
    },
    {
      "epoch": 121.22222222222223,
      "grad_norm": 4.5186362740423647e-07,
      "learning_rate": 0.2482299194951903,
      "loss": 0.0,
      "num_input_tokens_seen": 3054608,
      "step": 10910
    },
    {
      "epoch": 121.27777777777777,
      "grad_norm": 7.26210771517799e-07,
      "learning_rate": 0.2481853948730363,
      "loss": 0.0,
      "num_input_tokens_seen": 3055984,
      "step": 10915
    },
    {
      "epoch": 121.33333333333333,
      "grad_norm": 5.405734668784135e-07,
      "learning_rate": 0.24814085510946052,
      "loss": 0.0,
      "num_input_tokens_seen": 3057424,
      "step": 10920
    },
    {
      "epoch": 121.38888888888889,
      "grad_norm": 6.57533291814616e-07,
      "learning_rate": 0.24809630021133158,
      "loss": 0.0,
      "num_input_tokens_seen": 3058832,
      "step": 10925
    },
    {
      "epoch": 121.44444444444444,
      "grad_norm": 5.111891709930205e-07,
      "learning_rate": 0.24805173018552037,
      "loss": 0.0,
      "num_input_tokens_seen": 3060240,
      "step": 10930
    },
    {
      "epoch": 121.5,
      "grad_norm": 3.9891301639727317e-07,
      "learning_rate": 0.2480071450389002,
      "loss": 0.0,
      "num_input_tokens_seen": 3061616,
      "step": 10935
    },
    {
      "epoch": 121.55555555555556,
      "grad_norm": 5.890104262107343e-07,
      "learning_rate": 0.24796254477834662,
      "loss": 0.0,
      "num_input_tokens_seen": 3063008,
      "step": 10940
    },
    {
      "epoch": 121.61111111111111,
      "grad_norm": 1.7898210558087158e-07,
      "learning_rate": 0.24791792941073754,
      "loss": 0.0,
      "num_input_tokens_seen": 3064368,
      "step": 10945
    },
    {
      "epoch": 121.66666666666667,
      "grad_norm": 4.467134431251907e-07,
      "learning_rate": 0.2478732989429533,
      "loss": 0.0,
      "num_input_tokens_seen": 3065792,
      "step": 10950
    },
    {
      "epoch": 121.72222222222223,
      "grad_norm": 1.365740160963469e-07,
      "learning_rate": 0.24782865338187632,
      "loss": 0.0,
      "num_input_tokens_seen": 3067216,
      "step": 10955
    },
    {
      "epoch": 121.77777777777777,
      "grad_norm": 3.3912925800905214e-07,
      "learning_rate": 0.2477839927343916,
      "loss": 0.0,
      "num_input_tokens_seen": 3068608,
      "step": 10960
    },
    {
      "epoch": 121.83333333333333,
      "grad_norm": 3.846247693672922e-07,
      "learning_rate": 0.2477393170073864,
      "loss": 0.0,
      "num_input_tokens_seen": 3070016,
      "step": 10965
    },
    {
      "epoch": 121.88888888888889,
      "grad_norm": 2.1847164077826164e-07,
      "learning_rate": 0.2476946262077503,
      "loss": 0.0,
      "num_input_tokens_seen": 3071424,
      "step": 10970
    },
    {
      "epoch": 121.94444444444444,
      "grad_norm": 4.753380267175089e-08,
      "learning_rate": 0.24764992034237507,
      "loss": 0.0,
      "num_input_tokens_seen": 3072848,
      "step": 10975
    },
    {
      "epoch": 122.0,
      "grad_norm": 4.6479172510771605e-07,
      "learning_rate": 0.24760519941815498,
      "loss": 0.0,
      "num_input_tokens_seen": 3074272,
      "step": 10980
    },
    {
      "epoch": 122.05555555555556,
      "grad_norm": 2.5378415102750296e-07,
      "learning_rate": 0.2475604634419866,
      "loss": 0.0,
      "num_input_tokens_seen": 3075664,
      "step": 10985
    },
    {
      "epoch": 122.11111111111111,
      "grad_norm": 6.745245855199755e-07,
      "learning_rate": 0.24751571242076872,
      "loss": 0.0,
      "num_input_tokens_seen": 3077120,
      "step": 10990
    },
    {
      "epoch": 122.16666666666667,
      "grad_norm": 6.068718789720151e-07,
      "learning_rate": 0.2474709463614025,
      "loss": 0.0,
      "num_input_tokens_seen": 3078544,
      "step": 10995
    },
    {
      "epoch": 122.22222222222223,
      "grad_norm": 4.1454072174929024e-07,
      "learning_rate": 0.24742616527079145,
      "loss": 0.0,
      "num_input_tokens_seen": 3079920,
      "step": 11000
    },
    {
      "epoch": 122.22222222222223,
      "eval_loss": 1.1015602350234985,
      "eval_runtime": 1.1853,
      "eval_samples_per_second": 33.746,
      "eval_steps_per_second": 16.873,
      "num_input_tokens_seen": 3079920,
      "step": 11000
    },
    {
      "epoch": 122.27777777777777,
      "grad_norm": 3.989961498973571e-07,
      "learning_rate": 0.24738136915584139,
      "loss": 0.0,
      "num_input_tokens_seen": 3081312,
      "step": 11005
    },
    {
      "epoch": 122.33333333333333,
      "grad_norm": 8.747617812332464e-07,
      "learning_rate": 0.24733655802346047,
      "loss": 0.0,
      "num_input_tokens_seen": 3082720,
      "step": 11010
    },
    {
      "epoch": 122.38888888888889,
      "grad_norm": 2.3323293874000228e-07,
      "learning_rate": 0.24729173188055906,
      "loss": 0.0,
      "num_input_tokens_seen": 3084112,
      "step": 11015
    },
    {
      "epoch": 122.44444444444444,
      "grad_norm": 6.737074897955608e-08,
      "learning_rate": 0.24724689073404996,
      "loss": 0.0,
      "num_input_tokens_seen": 3085456,
      "step": 11020
    },
    {
      "epoch": 122.5,
      "grad_norm": 2.7691169179888675e-07,
      "learning_rate": 0.24720203459084822,
      "loss": 0.0,
      "num_input_tokens_seen": 3086880,
      "step": 11025
    },
    {
      "epoch": 122.55555555555556,
      "grad_norm": 4.2815656797756674e-07,
      "learning_rate": 0.24715716345787123,
      "loss": 0.0,
      "num_input_tokens_seen": 3088304,
      "step": 11030
    },
    {
      "epoch": 122.61111111111111,
      "grad_norm": 4.4305954816081794e-07,
      "learning_rate": 0.2471122773420387,
      "loss": 0.0,
      "num_input_tokens_seen": 3089680,
      "step": 11035
    },
    {
      "epoch": 122.66666666666667,
      "grad_norm": 2.5978491180467245e-07,
      "learning_rate": 0.24706737625027259,
      "loss": 0.0,
      "num_input_tokens_seen": 3091072,
      "step": 11040
    },
    {
      "epoch": 122.72222222222223,
      "grad_norm": 4.777222102347878e-07,
      "learning_rate": 0.24702246018949725,
      "loss": 0.0,
      "num_input_tokens_seen": 3092480,
      "step": 11045
    },
    {
      "epoch": 122.77777777777777,
      "grad_norm": 1.4292679395566665e-07,
      "learning_rate": 0.2469775291666393,
      "loss": 0.0,
      "num_input_tokens_seen": 3093888,
      "step": 11050
    },
    {
      "epoch": 122.83333333333333,
      "grad_norm": 3.8919955613891943e-07,
      "learning_rate": 0.24693258318862765,
      "loss": 0.0,
      "num_input_tokens_seen": 3095296,
      "step": 11055
    },
    {
      "epoch": 122.88888888888889,
      "grad_norm": 8.210481183823504e-08,
      "learning_rate": 0.2468876222623935,
      "loss": 0.0,
      "num_input_tokens_seen": 3096688,
      "step": 11060
    },
    {
      "epoch": 122.94444444444444,
      "grad_norm": 9.19674008059701e-08,
      "learning_rate": 0.2468426463948705,
      "loss": 0.0,
      "num_input_tokens_seen": 3098112,
      "step": 11065
    },
    {
      "epoch": 123.0,
      "grad_norm": 1.0322865762191213e-07,
      "learning_rate": 0.24679765559299438,
      "loss": 0.0,
      "num_input_tokens_seen": 3099536,
      "step": 11070
    },
    {
      "epoch": 123.05555555555556,
      "grad_norm": 1.2455943476652465e-07,
      "learning_rate": 0.24675264986370332,
      "loss": 0.0,
      "num_input_tokens_seen": 3100960,
      "step": 11075
    },
    {
      "epoch": 123.11111111111111,
      "grad_norm": 2.31340720802109e-07,
      "learning_rate": 0.2467076292139378,
      "loss": 0.0,
      "num_input_tokens_seen": 3102336,
      "step": 11080
    },
    {
      "epoch": 123.16666666666667,
      "grad_norm": 6.476901717178407e-07,
      "learning_rate": 0.24666259365064055,
      "loss": 0.0,
      "num_input_tokens_seen": 3103728,
      "step": 11085
    },
    {
      "epoch": 123.22222222222223,
      "grad_norm": 9.481529161803337e-08,
      "learning_rate": 0.24661754318075663,
      "loss": 0.0,
      "num_input_tokens_seen": 3105136,
      "step": 11090
    },
    {
      "epoch": 123.27777777777777,
      "grad_norm": 2.267213261575307e-07,
      "learning_rate": 0.2465724778112334,
      "loss": 0.0,
      "num_input_tokens_seen": 3106544,
      "step": 11095
    },
    {
      "epoch": 123.33333333333333,
      "grad_norm": 9.110200238637844e-08,
      "learning_rate": 0.24652739754902042,
      "loss": 0.0,
      "num_input_tokens_seen": 3107936,
      "step": 11100
    },
    {
      "epoch": 123.38888888888889,
      "grad_norm": 2.131018277395924e-07,
      "learning_rate": 0.24648230240106975,
      "loss": 0.0,
      "num_input_tokens_seen": 3109376,
      "step": 11105
    },
    {
      "epoch": 123.44444444444444,
      "grad_norm": 3.1822213486520923e-07,
      "learning_rate": 0.2464371923743356,
      "loss": 0.0,
      "num_input_tokens_seen": 3110784,
      "step": 11110
    },
    {
      "epoch": 123.5,
      "grad_norm": 6.71150360176398e-07,
      "learning_rate": 0.24639206747577444,
      "loss": 0.0,
      "num_input_tokens_seen": 3112224,
      "step": 11115
    },
    {
      "epoch": 123.55555555555556,
      "grad_norm": 1.0026028718357338e-07,
      "learning_rate": 0.24634692771234515,
      "loss": 0.0,
      "num_input_tokens_seen": 3113648,
      "step": 11120
    },
    {
      "epoch": 123.61111111111111,
      "grad_norm": 1.9273373652595183e-07,
      "learning_rate": 0.2463017730910088,
      "loss": 0.0,
      "num_input_tokens_seen": 3114976,
      "step": 11125
    },
    {
      "epoch": 123.66666666666667,
      "grad_norm": 3.1974016678759654e-07,
      "learning_rate": 0.2462566036187289,
      "loss": 0.0,
      "num_input_tokens_seen": 3116368,
      "step": 11130
    },
    {
      "epoch": 123.72222222222223,
      "grad_norm": 2.1207060285632906e-07,
      "learning_rate": 0.24621141930247106,
      "loss": 0.0,
      "num_input_tokens_seen": 3117760,
      "step": 11135
    },
    {
      "epoch": 123.77777777777777,
      "grad_norm": 4.6788628083049844e-08,
      "learning_rate": 0.2461662201492033,
      "loss": 0.0,
      "num_input_tokens_seen": 3119168,
      "step": 11140
    },
    {
      "epoch": 123.83333333333333,
      "grad_norm": 7.45577835914446e-07,
      "learning_rate": 0.24612100616589586,
      "loss": 0.0,
      "num_input_tokens_seen": 3120544,
      "step": 11145
    },
    {
      "epoch": 123.88888888888889,
      "grad_norm": 2.3690333250669937e-07,
      "learning_rate": 0.24607577735952135,
      "loss": 0.0,
      "num_input_tokens_seen": 3121952,
      "step": 11150
    },
    {
      "epoch": 123.94444444444444,
      "grad_norm": 3.011712408351741e-07,
      "learning_rate": 0.24603053373705464,
      "loss": 0.0,
      "num_input_tokens_seen": 3123312,
      "step": 11155
    },
    {
      "epoch": 124.0,
      "grad_norm": 4.0663005052010703e-07,
      "learning_rate": 0.2459852753054728,
      "loss": 0.0,
      "num_input_tokens_seen": 3124720,
      "step": 11160
    },
    {
      "epoch": 124.05555555555556,
      "grad_norm": 2.61774118825997e-07,
      "learning_rate": 0.24594000207175526,
      "loss": 0.0,
      "num_input_tokens_seen": 3126128,
      "step": 11165
    },
    {
      "epoch": 124.11111111111111,
      "grad_norm": 2.1097821445437148e-07,
      "learning_rate": 0.2458947140428838,
      "loss": 0.0,
      "num_input_tokens_seen": 3127552,
      "step": 11170
    },
    {
      "epoch": 124.16666666666667,
      "grad_norm": 2.652640205269563e-07,
      "learning_rate": 0.24584941122584233,
      "loss": 0.0,
      "num_input_tokens_seen": 3128960,
      "step": 11175
    },
    {
      "epoch": 124.22222222222223,
      "grad_norm": 2.2331893489990762e-07,
      "learning_rate": 0.24580409362761713,
      "loss": 0.0,
      "num_input_tokens_seen": 3130352,
      "step": 11180
    },
    {
      "epoch": 124.27777777777777,
      "grad_norm": 2.7693738502421184e-07,
      "learning_rate": 0.2457587612551967,
      "loss": 0.0,
      "num_input_tokens_seen": 3131712,
      "step": 11185
    },
    {
      "epoch": 124.33333333333333,
      "grad_norm": 2.9665179113180784e-07,
      "learning_rate": 0.24571341411557193,
      "loss": 0.0,
      "num_input_tokens_seen": 3133088,
      "step": 11190
    },
    {
      "epoch": 124.38888888888889,
      "grad_norm": 2.992047996031033e-07,
      "learning_rate": 0.2456680522157359,
      "loss": 0.0,
      "num_input_tokens_seen": 3134512,
      "step": 11195
    },
    {
      "epoch": 124.44444444444444,
      "grad_norm": 6.707306852149486e-07,
      "learning_rate": 0.245622675562684,
      "loss": 0.0,
      "num_input_tokens_seen": 3135904,
      "step": 11200
    },
    {
      "epoch": 124.44444444444444,
      "eval_loss": 1.107730507850647,
      "eval_runtime": 1.1912,
      "eval_samples_per_second": 33.58,
      "eval_steps_per_second": 16.79,
      "num_input_tokens_seen": 3135904,
      "step": 11200
    },
    {
      "epoch": 124.5,
      "grad_norm": 4.936002255817584e-07,
      "learning_rate": 0.24557728416341384,
      "loss": 0.0,
      "num_input_tokens_seen": 3137344,
      "step": 11205
    },
    {
      "epoch": 124.55555555555556,
      "grad_norm": 8.442763714811008e-07,
      "learning_rate": 0.24553187802492538,
      "loss": 0.0,
      "num_input_tokens_seen": 3138752,
      "step": 11210
    },
    {
      "epoch": 124.61111111111111,
      "grad_norm": 1.874692827641411e-07,
      "learning_rate": 0.24548645715422074,
      "loss": 0.0,
      "num_input_tokens_seen": 3140160,
      "step": 11215
    },
    {
      "epoch": 124.66666666666667,
      "grad_norm": 1.4413885196518095e-07,
      "learning_rate": 0.2454410215583045,
      "loss": 0.0,
      "num_input_tokens_seen": 3141536,
      "step": 11220
    },
    {
      "epoch": 124.72222222222223,
      "grad_norm": 9.061695322998276e-07,
      "learning_rate": 0.24539557124418332,
      "loss": 0.0,
      "num_input_tokens_seen": 3142992,
      "step": 11225
    },
    {
      "epoch": 124.77777777777777,
      "grad_norm": 3.4164827411586884e-07,
      "learning_rate": 0.24535010621886624,
      "loss": 0.0,
      "num_input_tokens_seen": 3144384,
      "step": 11230
    },
    {
      "epoch": 124.83333333333333,
      "grad_norm": 1.7917800221312064e-07,
      "learning_rate": 0.2453046264893646,
      "loss": 0.0,
      "num_input_tokens_seen": 3145760,
      "step": 11235
    },
    {
      "epoch": 124.88888888888889,
      "grad_norm": 6.742011464666575e-07,
      "learning_rate": 0.24525913206269184,
      "loss": 0.0,
      "num_input_tokens_seen": 3147152,
      "step": 11240
    },
    {
      "epoch": 124.94444444444444,
      "grad_norm": 2.9175680538173765e-07,
      "learning_rate": 0.2452136229458638,
      "loss": 0.0,
      "num_input_tokens_seen": 3148560,
      "step": 11245
    },
    {
      "epoch": 125.0,
      "grad_norm": 3.1955886470314e-07,
      "learning_rate": 0.24516809914589857,
      "loss": 0.0,
      "num_input_tokens_seen": 3149952,
      "step": 11250
    },
    {
      "epoch": 125.05555555555556,
      "grad_norm": 3.718423897680623e-07,
      "learning_rate": 0.2451225606698165,
      "loss": 0.0,
      "num_input_tokens_seen": 3151344,
      "step": 11255
    },
    {
      "epoch": 125.11111111111111,
      "grad_norm": 5.679371497535612e-07,
      "learning_rate": 0.2450770075246402,
      "loss": 0.0,
      "num_input_tokens_seen": 3152736,
      "step": 11260
    },
    {
      "epoch": 125.16666666666667,
      "grad_norm": 2.928780702404765e-07,
      "learning_rate": 0.24503143971739455,
      "loss": 0.0,
      "num_input_tokens_seen": 3154144,
      "step": 11265
    },
    {
      "epoch": 125.22222222222223,
      "grad_norm": 8.332853695947051e-08,
      "learning_rate": 0.24498585725510663,
      "loss": 0.0,
      "num_input_tokens_seen": 3155536,
      "step": 11270
    },
    {
      "epoch": 125.27777777777777,
      "grad_norm": 2.0938080069754506e-07,
      "learning_rate": 0.24494026014480583,
      "loss": 0.0,
      "num_input_tokens_seen": 3156912,
      "step": 11275
    },
    {
      "epoch": 125.33333333333333,
      "grad_norm": 3.265995189849491e-07,
      "learning_rate": 0.24489464839352387,
      "loss": 0.0,
      "num_input_tokens_seen": 3158304,
      "step": 11280
    },
    {
      "epoch": 125.38888888888889,
      "grad_norm": 9.386237707076361e-07,
      "learning_rate": 0.2448490220082946,
      "loss": 0.0,
      "num_input_tokens_seen": 3159776,
      "step": 11285
    },
    {
      "epoch": 125.44444444444444,
      "grad_norm": 1.5618317661392211e-07,
      "learning_rate": 0.24480338099615415,
      "loss": 0.0,
      "num_input_tokens_seen": 3161136,
      "step": 11290
    },
    {
      "epoch": 125.5,
      "grad_norm": 5.364785238270997e-08,
      "learning_rate": 0.244757725364141,
      "loss": 0.0,
      "num_input_tokens_seen": 3162512,
      "step": 11295
    },
    {
      "epoch": 125.55555555555556,
      "grad_norm": 6.06776779932261e-07,
      "learning_rate": 0.24471205511929583,
      "loss": 0.0,
      "num_input_tokens_seen": 3163920,
      "step": 11300
    },
    {
      "epoch": 125.61111111111111,
      "grad_norm": 1.9795520245224907e-07,
      "learning_rate": 0.24466637026866145,
      "loss": 0.0,
      "num_input_tokens_seen": 3165280,
      "step": 11305
    },
    {
      "epoch": 125.66666666666667,
      "grad_norm": 2.0751548390762764e-07,
      "learning_rate": 0.2446206708192832,
      "loss": 0.0,
      "num_input_tokens_seen": 3166704,
      "step": 11310
    },
    {
      "epoch": 125.72222222222223,
      "grad_norm": 1.4669721792870405e-07,
      "learning_rate": 0.2445749567782084,
      "loss": 0.0,
      "num_input_tokens_seen": 3168064,
      "step": 11315
    },
    {
      "epoch": 125.77777777777777,
      "grad_norm": 4.400278612592956e-07,
      "learning_rate": 0.2445292281524868,
      "loss": 0.0,
      "num_input_tokens_seen": 3169440,
      "step": 11320
    },
    {
      "epoch": 125.83333333333333,
      "grad_norm": 1.302304610817373e-07,
      "learning_rate": 0.24448348494917022,
      "loss": 0.0,
      "num_input_tokens_seen": 3170880,
      "step": 11325
    },
    {
      "epoch": 125.88888888888889,
      "grad_norm": 9.119621324771288e-08,
      "learning_rate": 0.24443772717531295,
      "loss": 0.0,
      "num_input_tokens_seen": 3172256,
      "step": 11330
    },
    {
      "epoch": 125.94444444444444,
      "grad_norm": 1.7806173957524152e-07,
      "learning_rate": 0.24439195483797138,
      "loss": 0.0,
      "num_input_tokens_seen": 3173712,
      "step": 11335
    },
    {
      "epoch": 126.0,
      "grad_norm": 7.69843140346893e-08,
      "learning_rate": 0.24434616794420416,
      "loss": 0.0,
      "num_input_tokens_seen": 3175056,
      "step": 11340
    },
    {
      "epoch": 126.05555555555556,
      "grad_norm": 3.4335036502852745e-07,
      "learning_rate": 0.24430036650107223,
      "loss": 0.0,
      "num_input_tokens_seen": 3176432,
      "step": 11345
    },
    {
      "epoch": 126.11111111111111,
      "grad_norm": 2.988344078858063e-07,
      "learning_rate": 0.2442545505156387,
      "loss": 0.0,
      "num_input_tokens_seen": 3177840,
      "step": 11350
    },
    {
      "epoch": 126.16666666666667,
      "grad_norm": 2.3727824327579583e-07,
      "learning_rate": 0.24420871999496904,
      "loss": 0.0,
      "num_input_tokens_seen": 3179232,
      "step": 11355
    },
    {
      "epoch": 126.22222222222223,
      "grad_norm": 2.1023512886131357e-07,
      "learning_rate": 0.24416287494613084,
      "loss": 0.0,
      "num_input_tokens_seen": 3180672,
      "step": 11360
    },
    {
      "epoch": 126.27777777777777,
      "grad_norm": 4.375467028694402e-07,
      "learning_rate": 0.24411701537619399,
      "loss": 0.0,
      "num_input_tokens_seen": 3182080,
      "step": 11365
    },
    {
      "epoch": 126.33333333333333,
      "grad_norm": 2.1065471855763462e-07,
      "learning_rate": 0.24407114129223062,
      "loss": 0.0,
      "num_input_tokens_seen": 3183472,
      "step": 11370
    },
    {
      "epoch": 126.38888888888889,
      "grad_norm": 3.229838227980508e-07,
      "learning_rate": 0.2440252527013151,
      "loss": 0.0,
      "num_input_tokens_seen": 3184880,
      "step": 11375
    },
    {
      "epoch": 126.44444444444444,
      "grad_norm": 2.0507098952293745e-07,
      "learning_rate": 0.24397934961052403,
      "loss": 0.0,
      "num_input_tokens_seen": 3186272,
      "step": 11380
    },
    {
      "epoch": 126.5,
      "grad_norm": 1.3938885956576996e-07,
      "learning_rate": 0.24393343202693618,
      "loss": 0.0,
      "num_input_tokens_seen": 3187648,
      "step": 11385
    },
    {
      "epoch": 126.55555555555556,
      "grad_norm": 4.9007539359990915e-08,
      "learning_rate": 0.2438874999576327,
      "loss": 0.0,
      "num_input_tokens_seen": 3189040,
      "step": 11390
    },
    {
      "epoch": 126.61111111111111,
      "grad_norm": 2.617898076096026e-07,
      "learning_rate": 0.24384155340969688,
      "loss": 0.0,
      "num_input_tokens_seen": 3190432,
      "step": 11395
    },
    {
      "epoch": 126.66666666666667,
      "grad_norm": 4.208397683669318e-07,
      "learning_rate": 0.24379559239021423,
      "loss": 0.0,
      "num_input_tokens_seen": 3191808,
      "step": 11400
    },
    {
      "epoch": 126.66666666666667,
      "eval_loss": 1.112866997718811,
      "eval_runtime": 1.1833,
      "eval_samples_per_second": 33.805,
      "eval_steps_per_second": 16.902,
      "num_input_tokens_seen": 3191808,
      "step": 11400
    },
    {
      "epoch": 126.72222222222223,
      "grad_norm": 6.481349714704265e-07,
      "learning_rate": 0.2437496169062725,
      "loss": 0.0,
      "num_input_tokens_seen": 3193168,
      "step": 11405
    },
    {
      "epoch": 126.77777777777777,
      "grad_norm": 3.02598579082769e-07,
      "learning_rate": 0.24370362696496176,
      "loss": 0.0,
      "num_input_tokens_seen": 3194576,
      "step": 11410
    },
    {
      "epoch": 126.83333333333333,
      "grad_norm": 6.269845442830047e-08,
      "learning_rate": 0.24365762257337417,
      "loss": 0.0,
      "num_input_tokens_seen": 3196000,
      "step": 11415
    },
    {
      "epoch": 126.88888888888889,
      "grad_norm": 1.9129713280108263e-07,
      "learning_rate": 0.2436116037386042,
      "loss": 0.0,
      "num_input_tokens_seen": 3197376,
      "step": 11420
    },
    {
      "epoch": 126.94444444444444,
      "grad_norm": 1.029991040013556e-06,
      "learning_rate": 0.24356557046774852,
      "loss": 0.0,
      "num_input_tokens_seen": 3198816,
      "step": 11425
    },
    {
      "epoch": 127.0,
      "grad_norm": 1.6534634994513908e-07,
      "learning_rate": 0.24351952276790606,
      "loss": 0.0,
      "num_input_tokens_seen": 3200208,
      "step": 11430
    },
    {
      "epoch": 127.05555555555556,
      "grad_norm": 2.170753816699289e-07,
      "learning_rate": 0.24347346064617797,
      "loss": 0.0,
      "num_input_tokens_seen": 3201584,
      "step": 11435
    },
    {
      "epoch": 127.11111111111111,
      "grad_norm": 3.2989677833938913e-07,
      "learning_rate": 0.24342738410966758,
      "loss": 0.0,
      "num_input_tokens_seen": 3203008,
      "step": 11440
    },
    {
      "epoch": 127.16666666666667,
      "grad_norm": 9.828854530269382e-08,
      "learning_rate": 0.24338129316548046,
      "loss": 0.0,
      "num_input_tokens_seen": 3204384,
      "step": 11445
    },
    {
      "epoch": 127.22222222222223,
      "grad_norm": 4.985859618500399e-07,
      "learning_rate": 0.24333518782072444,
      "loss": 0.0,
      "num_input_tokens_seen": 3205776,
      "step": 11450
    },
    {
      "epoch": 127.27777777777777,
      "grad_norm": 3.541728332834282e-08,
      "learning_rate": 0.24328906808250952,
      "loss": 0.0,
      "num_input_tokens_seen": 3207200,
      "step": 11455
    },
    {
      "epoch": 127.33333333333333,
      "grad_norm": 3.9758464254191495e-07,
      "learning_rate": 0.243242933957948,
      "loss": 0.0,
      "num_input_tokens_seen": 3208576,
      "step": 11460
    },
    {
      "epoch": 127.38888888888889,
      "grad_norm": 1.331515306901565e-07,
      "learning_rate": 0.24319678545415427,
      "loss": 0.0,
      "num_input_tokens_seen": 3209936,
      "step": 11465
    },
    {
      "epoch": 127.44444444444444,
      "grad_norm": 6.536096464060392e-08,
      "learning_rate": 0.24315062257824507,
      "loss": 0.0,
      "num_input_tokens_seen": 3211344,
      "step": 11470
    },
    {
      "epoch": 127.5,
      "grad_norm": 2.2184535453106946e-07,
      "learning_rate": 0.24310444533733921,
      "loss": 0.0,
      "num_input_tokens_seen": 3212720,
      "step": 11475
    },
    {
      "epoch": 127.55555555555556,
      "grad_norm": 2.685052322703996e-07,
      "learning_rate": 0.2430582537385579,
      "loss": 0.0,
      "num_input_tokens_seen": 3214128,
      "step": 11480
    },
    {
      "epoch": 127.61111111111111,
      "grad_norm": 3.1886793294688687e-07,
      "learning_rate": 0.2430120477890244,
      "loss": 0.0,
      "num_input_tokens_seen": 3215488,
      "step": 11485
    },
    {
      "epoch": 127.66666666666667,
      "grad_norm": 1.3957935607322725e-07,
      "learning_rate": 0.24296582749586426,
      "loss": 0.0,
      "num_input_tokens_seen": 3216896,
      "step": 11490
    },
    {
      "epoch": 127.72222222222223,
      "grad_norm": 3.7059598412270134e-07,
      "learning_rate": 0.24291959286620526,
      "loss": 0.0,
      "num_input_tokens_seen": 3218240,
      "step": 11495
    },
    {
      "epoch": 127.77777777777777,
      "grad_norm": 2.902011715377739e-07,
      "learning_rate": 0.24287334390717738,
      "loss": 0.0,
      "num_input_tokens_seen": 3219696,
      "step": 11500
    },
    {
      "epoch": 127.83333333333333,
      "grad_norm": 1.3451592906221777e-07,
      "learning_rate": 0.24282708062591268,
      "loss": 0.0,
      "num_input_tokens_seen": 3221104,
      "step": 11505
    },
    {
      "epoch": 127.88888888888889,
      "grad_norm": 5.291452609412772e-08,
      "learning_rate": 0.24278080302954563,
      "loss": 0.0,
      "num_input_tokens_seen": 3222544,
      "step": 11510
    },
    {
      "epoch": 127.94444444444444,
      "grad_norm": 5.629021870845463e-07,
      "learning_rate": 0.24273451112521283,
      "loss": 0.0,
      "num_input_tokens_seen": 3223968,
      "step": 11515
    },
    {
      "epoch": 128.0,
      "grad_norm": 2.811178774209111e-07,
      "learning_rate": 0.242688204920053,
      "loss": 0.0,
      "num_input_tokens_seen": 3225376,
      "step": 11520
    },
    {
      "epoch": 128.05555555555554,
      "grad_norm": 4.143010698953731e-07,
      "learning_rate": 0.24264188442120715,
      "loss": 0.0,
      "num_input_tokens_seen": 3226752,
      "step": 11525
    },
    {
      "epoch": 128.11111111111111,
      "grad_norm": 1.282118375911523e-07,
      "learning_rate": 0.24259554963581853,
      "loss": 0.0,
      "num_input_tokens_seen": 3228128,
      "step": 11530
    },
    {
      "epoch": 128.16666666666666,
      "grad_norm": 1.1933040866551892e-07,
      "learning_rate": 0.24254920057103257,
      "loss": 0.0,
      "num_input_tokens_seen": 3229520,
      "step": 11535
    },
    {
      "epoch": 128.22222222222223,
      "grad_norm": 3.287185279532423e-07,
      "learning_rate": 0.24250283723399685,
      "loss": 0.0,
      "num_input_tokens_seen": 3230976,
      "step": 11540
    },
    {
      "epoch": 128.27777777777777,
      "grad_norm": 1.926968877796753e-07,
      "learning_rate": 0.24245645963186108,
      "loss": 0.0,
      "num_input_tokens_seen": 3232400,
      "step": 11545
    },
    {
      "epoch": 128.33333333333334,
      "grad_norm": 1.5004303577370592e-07,
      "learning_rate": 0.2424100677717774,
      "loss": 0.0,
      "num_input_tokens_seen": 3233808,
      "step": 11550
    },
    {
      "epoch": 128.38888888888889,
      "grad_norm": 5.010404606764496e-07,
      "learning_rate": 0.24236366166090004,
      "loss": 0.0,
      "num_input_tokens_seen": 3235168,
      "step": 11555
    },
    {
      "epoch": 128.44444444444446,
      "grad_norm": 1.1888059958664599e-07,
      "learning_rate": 0.24231724130638527,
      "loss": 0.0,
      "num_input_tokens_seen": 3236528,
      "step": 11560
    },
    {
      "epoch": 128.5,
      "grad_norm": 3.1855773841016344e-07,
      "learning_rate": 0.2422708067153917,
      "loss": 0.0,
      "num_input_tokens_seen": 3237936,
      "step": 11565
    },
    {
      "epoch": 128.55555555555554,
      "grad_norm": 1.8354268149778363e-07,
      "learning_rate": 0.24222435789508026,
      "loss": 0.0,
      "num_input_tokens_seen": 3239392,
      "step": 11570
    },
    {
      "epoch": 128.61111111111111,
      "grad_norm": 1.2619117342183017e-06,
      "learning_rate": 0.24217789485261387,
      "loss": 0.0,
      "num_input_tokens_seen": 3240800,
      "step": 11575
    },
    {
      "epoch": 128.66666666666666,
      "grad_norm": 2.7560577109397855e-07,
      "learning_rate": 0.2421314175951577,
      "loss": 0.0,
      "num_input_tokens_seen": 3242176,
      "step": 11580
    },
    {
      "epoch": 128.72222222222223,
      "grad_norm": 4.434615448190016e-07,
      "learning_rate": 0.2420849261298791,
      "loss": 0.0,
      "num_input_tokens_seen": 3243600,
      "step": 11585
    },
    {
      "epoch": 128.77777777777777,
      "grad_norm": 1.9904038595086604e-07,
      "learning_rate": 0.24203842046394775,
      "loss": 0.0,
      "num_input_tokens_seen": 3244992,
      "step": 11590
    },
    {
      "epoch": 128.83333333333334,
      "grad_norm": 3.607896701396385e-07,
      "learning_rate": 0.24199190060453535,
      "loss": 0.0,
      "num_input_tokens_seen": 3246400,
      "step": 11595
    },
    {
      "epoch": 128.88888888888889,
      "grad_norm": 3.2251298875962675e-07,
      "learning_rate": 0.2419453665588158,
      "loss": 0.0,
      "num_input_tokens_seen": 3247840,
      "step": 11600
    },
    {
      "epoch": 128.88888888888889,
      "eval_loss": 1.1310853958129883,
      "eval_runtime": 1.1905,
      "eval_samples_per_second": 33.599,
      "eval_steps_per_second": 16.799,
      "num_input_tokens_seen": 3247840,
      "step": 11600
    },
    {
      "epoch": 128.94444444444446,
      "grad_norm": 4.041509384933306e-07,
      "learning_rate": 0.24189881833396523,
      "loss": 0.0,
      "num_input_tokens_seen": 3249232,
      "step": 11605
    },
    {
      "epoch": 129.0,
      "grad_norm": 2.935791769687057e-07,
      "learning_rate": 0.24185225593716203,
      "loss": 0.0,
      "num_input_tokens_seen": 3250624,
      "step": 11610
    },
    {
      "epoch": 129.05555555555554,
      "grad_norm": 2.031480619280046e-07,
      "learning_rate": 0.2418056793755867,
      "loss": 0.0,
      "num_input_tokens_seen": 3252032,
      "step": 11615
    },
    {
      "epoch": 129.11111111111111,
      "grad_norm": 1.7104805749568186e-07,
      "learning_rate": 0.24175908865642187,
      "loss": 0.0,
      "num_input_tokens_seen": 3253408,
      "step": 11620
    },
    {
      "epoch": 129.16666666666666,
      "grad_norm": 8.641200821557504e-08,
      "learning_rate": 0.24171248378685248,
      "loss": 0.0,
      "num_input_tokens_seen": 3254800,
      "step": 11625
    },
    {
      "epoch": 129.22222222222223,
      "grad_norm": 5.988193265693553e-07,
      "learning_rate": 0.24166586477406554,
      "loss": 0.0,
      "num_input_tokens_seen": 3256192,
      "step": 11630
    },
    {
      "epoch": 129.27777777777777,
      "grad_norm": 4.075206732068182e-07,
      "learning_rate": 0.24161923162525034,
      "loss": 0.0,
      "num_input_tokens_seen": 3257552,
      "step": 11635
    },
    {
      "epoch": 129.33333333333334,
      "grad_norm": 3.971499040744675e-08,
      "learning_rate": 0.2415725843475982,
      "loss": 0.0,
      "num_input_tokens_seen": 3258976,
      "step": 11640
    },
    {
      "epoch": 129.38888888888889,
      "grad_norm": 1.9283220353827346e-07,
      "learning_rate": 0.24152592294830286,
      "loss": 0.0,
      "num_input_tokens_seen": 3260384,
      "step": 11645
    },
    {
      "epoch": 129.44444444444446,
      "grad_norm": 1.9166142806170683e-07,
      "learning_rate": 0.24147924743455995,
      "loss": 0.0,
      "num_input_tokens_seen": 3261792,
      "step": 11650
    },
    {
      "epoch": 129.5,
      "grad_norm": 8.035235623538028e-07,
      "learning_rate": 0.24143255781356754,
      "loss": 0.0,
      "num_input_tokens_seen": 3263184,
      "step": 11655
    },
    {
      "epoch": 129.55555555555554,
      "grad_norm": 7.801702395227039e-08,
      "learning_rate": 0.24138585409252566,
      "loss": 0.0,
      "num_input_tokens_seen": 3264560,
      "step": 11660
    },
    {
      "epoch": 129.61111111111111,
      "grad_norm": 8.942969031977555e-08,
      "learning_rate": 0.24133913627863662,
      "loss": 0.0,
      "num_input_tokens_seen": 3265968,
      "step": 11665
    },
    {
      "epoch": 129.66666666666666,
      "grad_norm": 2.8996348078180745e-07,
      "learning_rate": 0.241292404379105,
      "loss": 0.0,
      "num_input_tokens_seen": 3267360,
      "step": 11670
    },
    {
      "epoch": 129.72222222222223,
      "grad_norm": 1.598172900685313e-07,
      "learning_rate": 0.24124565840113735,
      "loss": 0.0,
      "num_input_tokens_seen": 3268768,
      "step": 11675
    },
    {
      "epoch": 129.77777777777777,
      "grad_norm": 2.618617997995898e-07,
      "learning_rate": 0.2411988983519425,
      "loss": 0.0,
      "num_input_tokens_seen": 3270160,
      "step": 11680
    },
    {
      "epoch": 129.83333333333334,
      "grad_norm": 1.6372230504657637e-07,
      "learning_rate": 0.24115212423873145,
      "loss": 0.0,
      "num_input_tokens_seen": 3271536,
      "step": 11685
    },
    {
      "epoch": 129.88888888888889,
      "grad_norm": 1.419889628095916e-07,
      "learning_rate": 0.24110533606871737,
      "loss": 0.0,
      "num_input_tokens_seen": 3272944,
      "step": 11690
    },
    {
      "epoch": 129.94444444444446,
      "grad_norm": 1.221951890784112e-07,
      "learning_rate": 0.24105853384911552,
      "loss": 0.0,
      "num_input_tokens_seen": 3274320,
      "step": 11695
    },
    {
      "epoch": 130.0,
      "grad_norm": 1.3319899494490528e-07,
      "learning_rate": 0.24101171758714346,
      "loss": 0.0,
      "num_input_tokens_seen": 3275712,
      "step": 11700
    },
    {
      "epoch": 130.05555555555554,
      "grad_norm": 6.03995715664496e-08,
      "learning_rate": 0.24096488729002086,
      "loss": 0.0,
      "num_input_tokens_seen": 3277152,
      "step": 11705
    },
    {
      "epoch": 130.11111111111111,
      "grad_norm": 7.30000124349317e-07,
      "learning_rate": 0.24091804296496946,
      "loss": 0.0,
      "num_input_tokens_seen": 3278592,
      "step": 11710
    },
    {
      "epoch": 130.16666666666666,
      "grad_norm": 7.34587004558307e-08,
      "learning_rate": 0.2408711846192133,
      "loss": 0.0,
      "num_input_tokens_seen": 3280016,
      "step": 11715
    },
    {
      "epoch": 130.22222222222223,
      "grad_norm": 1.1473504457626404e-07,
      "learning_rate": 0.24082431225997855,
      "loss": 0.0,
      "num_input_tokens_seen": 3281360,
      "step": 11720
    },
    {
      "epoch": 130.27777777777777,
      "grad_norm": 2.5193222086272726e-07,
      "learning_rate": 0.24077742589449344,
      "loss": 0.0,
      "num_input_tokens_seen": 3282816,
      "step": 11725
    },
    {
      "epoch": 130.33333333333334,
      "grad_norm": 2.520490340884862e-07,
      "learning_rate": 0.24073052552998844,
      "loss": 0.0,
      "num_input_tokens_seen": 3284208,
      "step": 11730
    },
    {
      "epoch": 130.38888888888889,
      "grad_norm": 1.1336183547427936e-07,
      "learning_rate": 0.2406836111736963,
      "loss": 0.0,
      "num_input_tokens_seen": 3285584,
      "step": 11735
    },
    {
      "epoch": 130.44444444444446,
      "grad_norm": 7.146318807826901e-07,
      "learning_rate": 0.2406366828328517,
      "loss": 0.0,
      "num_input_tokens_seen": 3286976,
      "step": 11740
    },
    {
      "epoch": 130.5,
      "grad_norm": 1.9385213079203822e-07,
      "learning_rate": 0.2405897405146915,
      "loss": 0.0,
      "num_input_tokens_seen": 3288352,
      "step": 11745
    },
    {
      "epoch": 130.55555555555554,
      "grad_norm": 2.1036881037161947e-07,
      "learning_rate": 0.240542784226455,
      "loss": 0.0,
      "num_input_tokens_seen": 3289760,
      "step": 11750
    },
    {
      "epoch": 130.61111111111111,
      "grad_norm": 1.0160680830040292e-07,
      "learning_rate": 0.24049581397538328,
      "loss": 0.0,
      "num_input_tokens_seen": 3291200,
      "step": 11755
    },
    {
      "epoch": 130.66666666666666,
      "grad_norm": 5.235296498540265e-07,
      "learning_rate": 0.24044882976871984,
      "loss": 0.0,
      "num_input_tokens_seen": 3292608,
      "step": 11760
    },
    {
      "epoch": 130.72222222222223,
      "grad_norm": 1.0383517690115696e-07,
      "learning_rate": 0.2404018316137102,
      "loss": 0.0,
      "num_input_tokens_seen": 3294032,
      "step": 11765
    },
    {
      "epoch": 130.77777777777777,
      "grad_norm": 2.1019681639700138e-07,
      "learning_rate": 0.24035481951760204,
      "loss": 0.0,
      "num_input_tokens_seen": 3295360,
      "step": 11770
    },
    {
      "epoch": 130.83333333333334,
      "grad_norm": 4.306760956751532e-07,
      "learning_rate": 0.2403077934876452,
      "loss": 0.0,
      "num_input_tokens_seen": 3296768,
      "step": 11775
    },
    {
      "epoch": 130.88888888888889,
      "grad_norm": 2.3037080154608702e-07,
      "learning_rate": 0.2402607535310918,
      "loss": 0.0,
      "num_input_tokens_seen": 3298160,
      "step": 11780
    },
    {
      "epoch": 130.94444444444446,
      "grad_norm": 3.195557667368121e-07,
      "learning_rate": 0.2402136996551959,
      "loss": 0.0,
      "num_input_tokens_seen": 3299536,
      "step": 11785
    },
    {
      "epoch": 131.0,
      "grad_norm": 1.0321143406599731e-07,
      "learning_rate": 0.24016663186721376,
      "loss": 0.0,
      "num_input_tokens_seen": 3300896,
      "step": 11790
    },
    {
      "epoch": 131.05555555555554,
      "grad_norm": 1.2092027645849157e-07,
      "learning_rate": 0.24011955017440395,
      "loss": 0.0,
      "num_input_tokens_seen": 3302272,
      "step": 11795
    },
    {
      "epoch": 131.11111111111111,
      "grad_norm": 4.6651052798551973e-07,
      "learning_rate": 0.24007245458402696,
      "loss": 0.0,
      "num_input_tokens_seen": 3303712,
      "step": 11800
    },
    {
      "epoch": 131.11111111111111,
      "eval_loss": 1.1460902690887451,
      "eval_runtime": 1.1877,
      "eval_samples_per_second": 33.677,
      "eval_steps_per_second": 16.839,
      "num_input_tokens_seen": 3303712,
      "step": 11800
    },
    {
      "epoch": 131.16666666666666,
      "grad_norm": 4.6123869168468445e-08,
      "learning_rate": 0.2400253451033456,
      "loss": 0.0,
      "num_input_tokens_seen": 3305152,
      "step": 11805
    },
    {
      "epoch": 131.22222222222223,
      "grad_norm": 3.175717893100227e-07,
      "learning_rate": 0.23997822173962463,
      "loss": 0.0,
      "num_input_tokens_seen": 3306576,
      "step": 11810
    },
    {
      "epoch": 131.27777777777777,
      "grad_norm": 1.179610080725979e-07,
      "learning_rate": 0.23993108450013118,
      "loss": 0.0,
      "num_input_tokens_seen": 3307984,
      "step": 11815
    },
    {
      "epoch": 131.33333333333334,
      "grad_norm": 9.64876818443372e-08,
      "learning_rate": 0.2398839333921343,
      "loss": 0.0,
      "num_input_tokens_seen": 3309392,
      "step": 11820
    },
    {
      "epoch": 131.38888888888889,
      "grad_norm": 8.200029810723208e-08,
      "learning_rate": 0.23983676842290536,
      "loss": 0.0,
      "num_input_tokens_seen": 3310736,
      "step": 11825
    },
    {
      "epoch": 131.44444444444446,
      "grad_norm": 1.7889801995352173e-07,
      "learning_rate": 0.2397895895997178,
      "loss": 0.0,
      "num_input_tokens_seen": 3312096,
      "step": 11830
    },
    {
      "epoch": 131.5,
      "grad_norm": 1.269523863811628e-07,
      "learning_rate": 0.23974239692984714,
      "loss": 0.0,
      "num_input_tokens_seen": 3313536,
      "step": 11835
    },
    {
      "epoch": 131.55555555555554,
      "grad_norm": 1.0578672515748622e-07,
      "learning_rate": 0.2396951904205711,
      "loss": 0.0,
      "num_input_tokens_seen": 3314944,
      "step": 11840
    },
    {
      "epoch": 131.61111111111111,
      "grad_norm": 1.658602286624955e-07,
      "learning_rate": 0.23964797007916952,
      "loss": 0.0,
      "num_input_tokens_seen": 3316304,
      "step": 11845
    },
    {
      "epoch": 131.66666666666666,
      "grad_norm": 2.0489495966558025e-07,
      "learning_rate": 0.23960073591292436,
      "loss": 0.0,
      "num_input_tokens_seen": 3317680,
      "step": 11850
    },
    {
      "epoch": 131.72222222222223,
      "grad_norm": 2.7096241694835044e-08,
      "learning_rate": 0.2395534879291197,
      "loss": 0.0,
      "num_input_tokens_seen": 3319056,
      "step": 11855
    },
    {
      "epoch": 131.77777777777777,
      "grad_norm": 3.5004663345716835e-07,
      "learning_rate": 0.23950622613504186,
      "loss": 0.0,
      "num_input_tokens_seen": 3320480,
      "step": 11860
    },
    {
      "epoch": 131.83333333333334,
      "grad_norm": 6.428887786569248e-07,
      "learning_rate": 0.2394589505379791,
      "loss": 0.0,
      "num_input_tokens_seen": 3321840,
      "step": 11865
    },
    {
      "epoch": 131.88888888888889,
      "grad_norm": 3.392406426883099e-07,
      "learning_rate": 0.23941166114522197,
      "loss": 0.0,
      "num_input_tokens_seen": 3323248,
      "step": 11870
    },
    {
      "epoch": 131.94444444444446,
      "grad_norm": 3.5497441785992123e-07,
      "learning_rate": 0.23936435796406308,
      "loss": 0.0,
      "num_input_tokens_seen": 3324640,
      "step": 11875
    },
    {
      "epoch": 132.0,
      "grad_norm": 1.7255541706617805e-07,
      "learning_rate": 0.23931704100179715,
      "loss": 0.0,
      "num_input_tokens_seen": 3326064,
      "step": 11880
    },
    {
      "epoch": 132.05555555555554,
      "grad_norm": 1.9648182103537692e-07,
      "learning_rate": 0.2392697102657211,
      "loss": 0.0,
      "num_input_tokens_seen": 3327456,
      "step": 11885
    },
    {
      "epoch": 132.11111111111111,
      "grad_norm": 6.431434229625665e-08,
      "learning_rate": 0.23922236576313388,
      "loss": 0.0,
      "num_input_tokens_seen": 3328928,
      "step": 11890
    },
    {
      "epoch": 132.16666666666666,
      "grad_norm": 3.4379272051410226e-07,
      "learning_rate": 0.2391750075013366,
      "loss": 0.0,
      "num_input_tokens_seen": 3330352,
      "step": 11895
    },
    {
      "epoch": 132.22222222222223,
      "grad_norm": 3.4419494454596133e-07,
      "learning_rate": 0.2391276354876326,
      "loss": 0.0,
      "num_input_tokens_seen": 3331760,
      "step": 11900
    },
    {
      "epoch": 132.27777777777777,
      "grad_norm": 2.569365165072668e-07,
      "learning_rate": 0.23908024972932707,
      "loss": 0.0,
      "num_input_tokens_seen": 3333152,
      "step": 11905
    },
    {
      "epoch": 132.33333333333334,
      "grad_norm": 1.8088456954501453e-07,
      "learning_rate": 0.2390328502337276,
      "loss": 0.0,
      "num_input_tokens_seen": 3334560,
      "step": 11910
    },
    {
      "epoch": 132.38888888888889,
      "grad_norm": 1.1061624860531083e-07,
      "learning_rate": 0.23898543700814376,
      "loss": 0.0,
      "num_input_tokens_seen": 3335952,
      "step": 11915
    },
    {
      "epoch": 132.44444444444446,
      "grad_norm": 5.199819597123678e-08,
      "learning_rate": 0.2389380100598873,
      "loss": 0.0,
      "num_input_tokens_seen": 3337328,
      "step": 11920
    },
    {
      "epoch": 132.5,
      "grad_norm": 2.2758081286156084e-07,
      "learning_rate": 0.23889056939627207,
      "loss": 0.0,
      "num_input_tokens_seen": 3338704,
      "step": 11925
    },
    {
      "epoch": 132.55555555555554,
      "grad_norm": 4.4148936240162584e-07,
      "learning_rate": 0.23884311502461386,
      "loss": 0.0,
      "num_input_tokens_seen": 3340128,
      "step": 11930
    },
    {
      "epoch": 132.61111111111111,
      "grad_norm": 5.118520789437753e-07,
      "learning_rate": 0.23879564695223088,
      "loss": 0.0,
      "num_input_tokens_seen": 3341552,
      "step": 11935
    },
    {
      "epoch": 132.66666666666666,
      "grad_norm": 2.4056340919287322e-08,
      "learning_rate": 0.23874816518644332,
      "loss": 0.0,
      "num_input_tokens_seen": 3342896,
      "step": 11940
    },
    {
      "epoch": 132.72222222222223,
      "grad_norm": 1.3041127999713353e-07,
      "learning_rate": 0.23870066973457335,
      "loss": 0.0,
      "num_input_tokens_seen": 3344256,
      "step": 11945
    },
    {
      "epoch": 132.77777777777777,
      "grad_norm": 1.5821950682948227e-07,
      "learning_rate": 0.23865316060394545,
      "loss": 0.0,
      "num_input_tokens_seen": 3345632,
      "step": 11950
    },
    {
      "epoch": 132.83333333333334,
      "grad_norm": 4.1986666587945365e-07,
      "learning_rate": 0.2386056378018861,
      "loss": 0.0,
      "num_input_tokens_seen": 3347056,
      "step": 11955
    },
    {
      "epoch": 132.88888888888889,
      "grad_norm": 1.2996626708172698e-07,
      "learning_rate": 0.2385581013357239,
      "loss": 0.0,
      "num_input_tokens_seen": 3348480,
      "step": 11960
    },
    {
      "epoch": 132.94444444444446,
      "grad_norm": 1.0717915444047321e-07,
      "learning_rate": 0.23851055121278958,
      "loss": 0.0,
      "num_input_tokens_seen": 3349888,
      "step": 11965
    },
    {
      "epoch": 133.0,
      "grad_norm": 5.963959637256266e-08,
      "learning_rate": 0.23846298744041594,
      "loss": 0.0,
      "num_input_tokens_seen": 3351296,
      "step": 11970
    },
    {
      "epoch": 133.05555555555554,
      "grad_norm": 1.5653870377718704e-07,
      "learning_rate": 0.23841541002593802,
      "loss": 0.0,
      "num_input_tokens_seen": 3352624,
      "step": 11975
    },
    {
      "epoch": 133.11111111111111,
      "grad_norm": 1.4136855952529004e-07,
      "learning_rate": 0.23836781897669276,
      "loss": 0.0,
      "num_input_tokens_seen": 3354032,
      "step": 11980
    },
    {
      "epoch": 133.16666666666666,
      "grad_norm": 6.979013988939187e-08,
      "learning_rate": 0.23832021430001926,
      "loss": 0.0,
      "num_input_tokens_seen": 3355440,
      "step": 11985
    },
    {
      "epoch": 133.22222222222223,
      "grad_norm": 2.1004008488034742e-07,
      "learning_rate": 0.2382725960032588,
      "loss": 0.0,
      "num_input_tokens_seen": 3356848,
      "step": 11990
    },
    {
      "epoch": 133.27777777777777,
      "grad_norm": 2.445603399792162e-07,
      "learning_rate": 0.23822496409375482,
      "loss": 0.0,
      "num_input_tokens_seen": 3358272,
      "step": 11995
    },
    {
      "epoch": 133.33333333333334,
      "grad_norm": 3.0157875130498724e-07,
      "learning_rate": 0.2381773185788526,
      "loss": 0.0,
      "num_input_tokens_seen": 3359680,
      "step": 12000
    },
    {
      "epoch": 133.33333333333334,
      "eval_loss": 1.152418851852417,
      "eval_runtime": 1.1818,
      "eval_samples_per_second": 33.847,
      "eval_steps_per_second": 16.923,
      "num_input_tokens_seen": 3359680,
      "step": 12000
    },
    {
      "epoch": 133.38888888888889,
      "grad_norm": 1.3603629156477837e-07,
      "learning_rate": 0.2381296594658998,
      "loss": 0.0,
      "num_input_tokens_seen": 3361088,
      "step": 12005
    },
    {
      "epoch": 133.44444444444446,
      "grad_norm": 1.1520605625037206e-07,
      "learning_rate": 0.238081986762246,
      "loss": 0.0,
      "num_input_tokens_seen": 3362528,
      "step": 12010
    },
    {
      "epoch": 133.5,
      "grad_norm": 4.6365349248844723e-07,
      "learning_rate": 0.23803430047524293,
      "loss": 0.0,
      "num_input_tokens_seen": 3363920,
      "step": 12015
    },
    {
      "epoch": 133.55555555555554,
      "grad_norm": 2.598004869014403e-07,
      "learning_rate": 0.23798660061224441,
      "loss": 0.0,
      "num_input_tokens_seen": 3365312,
      "step": 12020
    },
    {
      "epoch": 133.61111111111111,
      "grad_norm": 1.5882237391906529e-07,
      "learning_rate": 0.23793888718060632,
      "loss": 0.0,
      "num_input_tokens_seen": 3366736,
      "step": 12025
    },
    {
      "epoch": 133.66666666666666,
      "grad_norm": 3.532028003405685e-08,
      "learning_rate": 0.23789116018768675,
      "loss": 0.0,
      "num_input_tokens_seen": 3368160,
      "step": 12030
    },
    {
      "epoch": 133.72222222222223,
      "grad_norm": 1.7642832972342148e-07,
      "learning_rate": 0.2378434196408458,
      "loss": 0.0,
      "num_input_tokens_seen": 3369584,
      "step": 12035
    },
    {
      "epoch": 133.77777777777777,
      "grad_norm": 4.1791238913901907e-07,
      "learning_rate": 0.23779566554744563,
      "loss": 0.0,
      "num_input_tokens_seen": 3371008,
      "step": 12040
    },
    {
      "epoch": 133.83333333333334,
      "grad_norm": 1.9729888833808218e-07,
      "learning_rate": 0.23774789791485051,
      "loss": 0.0,
      "num_input_tokens_seen": 3372416,
      "step": 12045
    },
    {
      "epoch": 133.88888888888889,
      "grad_norm": 1.018764876903333e-07,
      "learning_rate": 0.2377001167504268,
      "loss": 0.0,
      "num_input_tokens_seen": 3373840,
      "step": 12050
    },
    {
      "epoch": 133.94444444444446,
      "grad_norm": 2.5409766735151607e-08,
      "learning_rate": 0.23765232206154302,
      "loss": 0.0,
      "num_input_tokens_seen": 3375216,
      "step": 12055
    },
    {
      "epoch": 134.0,
      "grad_norm": 1.0445609888165563e-07,
      "learning_rate": 0.23760451385556966,
      "loss": 0.0,
      "num_input_tokens_seen": 3376560,
      "step": 12060
    },
    {
      "epoch": 134.05555555555554,
      "grad_norm": 1.652193191148399e-07,
      "learning_rate": 0.23755669213987932,
      "loss": 0.0,
      "num_input_tokens_seen": 3377968,
      "step": 12065
    },
    {
      "epoch": 134.11111111111111,
      "grad_norm": 2.1792388338326418e-07,
      "learning_rate": 0.23750885692184676,
      "loss": 0.0,
      "num_input_tokens_seen": 3379312,
      "step": 12070
    },
    {
      "epoch": 134.16666666666666,
      "grad_norm": 1.1952693057537545e-07,
      "learning_rate": 0.23746100820884875,
      "loss": 0.0,
      "num_input_tokens_seen": 3380736,
      "step": 12075
    },
    {
      "epoch": 134.22222222222223,
      "grad_norm": 3.0242810566960543e-07,
      "learning_rate": 0.23741314600826421,
      "loss": 0.0,
      "num_input_tokens_seen": 3382144,
      "step": 12080
    },
    {
      "epoch": 134.27777777777777,
      "grad_norm": 1.7134475172042585e-07,
      "learning_rate": 0.23736527032747406,
      "loss": 0.0,
      "num_input_tokens_seen": 3383504,
      "step": 12085
    },
    {
      "epoch": 134.33333333333334,
      "grad_norm": 1.6451464546207717e-07,
      "learning_rate": 0.23731738117386128,
      "loss": 0.0,
      "num_input_tokens_seen": 3384928,
      "step": 12090
    },
    {
      "epoch": 134.38888888888889,
      "grad_norm": 4.4255699549466954e-08,
      "learning_rate": 0.237269478554811,
      "loss": 0.0,
      "num_input_tokens_seen": 3386336,
      "step": 12095
    },
    {
      "epoch": 134.44444444444446,
      "grad_norm": 1.6780192879650713e-07,
      "learning_rate": 0.23722156247771053,
      "loss": 0.0,
      "num_input_tokens_seen": 3387728,
      "step": 12100
    },
    {
      "epoch": 134.5,
      "grad_norm": 3.8871826291142497e-07,
      "learning_rate": 0.23717363294994895,
      "loss": 0.0,
      "num_input_tokens_seen": 3389120,
      "step": 12105
    },
    {
      "epoch": 134.55555555555554,
      "grad_norm": 1.1422225298929334e-07,
      "learning_rate": 0.2371256899789177,
      "loss": 0.0,
      "num_input_tokens_seen": 3390544,
      "step": 12110
    },
    {
      "epoch": 134.61111111111111,
      "grad_norm": 4.6005723675079935e-07,
      "learning_rate": 0.23707773357201017,
      "loss": 0.0,
      "num_input_tokens_seen": 3391920,
      "step": 12115
    },
    {
      "epoch": 134.66666666666666,
      "grad_norm": 1.1317992942849742e-07,
      "learning_rate": 0.2370297637366218,
      "loss": 0.0,
      "num_input_tokens_seen": 3393296,
      "step": 12120
    },
    {
      "epoch": 134.72222222222223,
      "grad_norm": 7.668747770139817e-08,
      "learning_rate": 0.23698178048015026,
      "loss": 0.0,
      "num_input_tokens_seen": 3394720,
      "step": 12125
    },
    {
      "epoch": 134.77777777777777,
      "grad_norm": 1.7081548264741286e-07,
      "learning_rate": 0.236933783809995,
      "loss": 0.0,
      "num_input_tokens_seen": 3396128,
      "step": 12130
    },
    {
      "epoch": 134.83333333333334,
      "grad_norm": 8.98369449942038e-08,
      "learning_rate": 0.23688577373355785,
      "loss": 0.0,
      "num_input_tokens_seen": 3397536,
      "step": 12135
    },
    {
      "epoch": 134.88888888888889,
      "grad_norm": 2.987048617342225e-07,
      "learning_rate": 0.23683775025824247,
      "loss": 0.0,
      "num_input_tokens_seen": 3398928,
      "step": 12140
    },
    {
      "epoch": 134.94444444444446,
      "grad_norm": 5.189899070501269e-07,
      "learning_rate": 0.2367897133914548,
      "loss": 0.0,
      "num_input_tokens_seen": 3400336,
      "step": 12145
    },
    {
      "epoch": 135.0,
      "grad_norm": 1.804001215077733e-07,
      "learning_rate": 0.2367416631406026,
      "loss": 0.0,
      "num_input_tokens_seen": 3401776,
      "step": 12150
    },
    {
      "epoch": 135.05555555555554,
      "grad_norm": 5.3471520544690065e-08,
      "learning_rate": 0.23669359951309588,
      "loss": 0.0,
      "num_input_tokens_seen": 3403184,
      "step": 12155
    },
    {
      "epoch": 135.11111111111111,
      "grad_norm": 2.0571532388657943e-07,
      "learning_rate": 0.23664552251634666,
      "loss": 0.0,
      "num_input_tokens_seen": 3404560,
      "step": 12160
    },
    {
      "epoch": 135.16666666666666,
      "grad_norm": 1.8874796126056026e-07,
      "learning_rate": 0.23659743215776907,
      "loss": 0.0,
      "num_input_tokens_seen": 3406000,
      "step": 12165
    },
    {
      "epoch": 135.22222222222223,
      "grad_norm": 2.0508750253611652e-07,
      "learning_rate": 0.23654932844477908,
      "loss": 0.0,
      "num_input_tokens_seen": 3407392,
      "step": 12170
    },
    {
      "epoch": 135.27777777777777,
      "grad_norm": 2.3701771567630203e-07,
      "learning_rate": 0.23650121138479507,
      "loss": 0.0,
      "num_input_tokens_seen": 3408800,
      "step": 12175
    },
    {
      "epoch": 135.33333333333334,
      "grad_norm": 2.3035447327401926e-07,
      "learning_rate": 0.23645308098523724,
      "loss": 0.0,
      "num_input_tokens_seen": 3410240,
      "step": 12180
    },
    {
      "epoch": 135.38888888888889,
      "grad_norm": 2.140753281310026e-07,
      "learning_rate": 0.23640493725352785,
      "loss": 0.0,
      "num_input_tokens_seen": 3411616,
      "step": 12185
    },
    {
      "epoch": 135.44444444444446,
      "grad_norm": 4.745262458527577e-07,
      "learning_rate": 0.2363567801970913,
      "loss": 0.0,
      "num_input_tokens_seen": 3413040,
      "step": 12190
    },
    {
      "epoch": 135.5,
      "grad_norm": 2.9262918133099447e-07,
      "learning_rate": 0.236308609823354,
      "loss": 0.0,
      "num_input_tokens_seen": 3414432,
      "step": 12195
    },
    {
      "epoch": 135.55555555555554,
      "grad_norm": 9.24417165037994e-08,
      "learning_rate": 0.23626042613974452,
      "loss": 0.0,
      "num_input_tokens_seen": 3415824,
      "step": 12200
    },
    {
      "epoch": 135.55555555555554,
      "eval_loss": 1.152822732925415,
      "eval_runtime": 1.1827,
      "eval_samples_per_second": 33.822,
      "eval_steps_per_second": 16.911,
      "num_input_tokens_seen": 3415824,
      "step": 12200
    },
    {
      "epoch": 135.61111111111111,
      "grad_norm": 2.716221381149353e-08,
      "learning_rate": 0.23621222915369325,
      "loss": 0.0,
      "num_input_tokens_seen": 3417184,
      "step": 12205
    },
    {
      "epoch": 135.66666666666666,
      "grad_norm": 3.2614158840260643e-07,
      "learning_rate": 0.23616401887263283,
      "loss": 0.0,
      "num_input_tokens_seen": 3418576,
      "step": 12210
    },
    {
      "epoch": 135.72222222222223,
      "grad_norm": 7.666294266073237e-08,
      "learning_rate": 0.23611579530399793,
      "loss": 0.0,
      "num_input_tokens_seen": 3419984,
      "step": 12215
    },
    {
      "epoch": 135.77777777777777,
      "grad_norm": 1.0623923429875504e-07,
      "learning_rate": 0.23606755845522517,
      "loss": 0.0,
      "num_input_tokens_seen": 3421360,
      "step": 12220
    },
    {
      "epoch": 135.83333333333334,
      "grad_norm": 4.737337349070003e-07,
      "learning_rate": 0.23601930833375329,
      "loss": 0.0,
      "num_input_tokens_seen": 3422720,
      "step": 12225
    },
    {
      "epoch": 135.88888888888889,
      "grad_norm": 2.150931237565601e-07,
      "learning_rate": 0.23597104494702312,
      "loss": 0.0,
      "num_input_tokens_seen": 3424112,
      "step": 12230
    },
    {
      "epoch": 135.94444444444446,
      "grad_norm": 2.345116598689856e-07,
      "learning_rate": 0.23592276830247744,
      "loss": 0.0,
      "num_input_tokens_seen": 3425488,
      "step": 12235
    },
    {
      "epoch": 136.0,
      "grad_norm": 8.26275652343611e-08,
      "learning_rate": 0.2358744784075611,
      "loss": 0.0,
      "num_input_tokens_seen": 3426912,
      "step": 12240
    },
    {
      "epoch": 136.05555555555554,
      "grad_norm": 8.713589494391272e-08,
      "learning_rate": 0.235826175269721,
      "loss": 0.0,
      "num_input_tokens_seen": 3428304,
      "step": 12245
    },
    {
      "epoch": 136.11111111111111,
      "grad_norm": 4.204979973110312e-07,
      "learning_rate": 0.23577785889640612,
      "loss": 0.0,
      "num_input_tokens_seen": 3429712,
      "step": 12250
    },
    {
      "epoch": 136.16666666666666,
      "grad_norm": 9.246417675967677e-08,
      "learning_rate": 0.23572952929506744,
      "loss": 0.0,
      "num_input_tokens_seen": 3431088,
      "step": 12255
    },
    {
      "epoch": 136.22222222222223,
      "grad_norm": 1.5909135697711463e-07,
      "learning_rate": 0.23568118647315803,
      "loss": 0.0,
      "num_input_tokens_seen": 3432448,
      "step": 12260
    },
    {
      "epoch": 136.27777777777777,
      "grad_norm": 8.825499264730752e-08,
      "learning_rate": 0.23563283043813296,
      "loss": 0.0,
      "num_input_tokens_seen": 3433872,
      "step": 12265
    },
    {
      "epoch": 136.33333333333334,
      "grad_norm": 2.5952317628252786e-07,
      "learning_rate": 0.23558446119744922,
      "loss": 0.0,
      "num_input_tokens_seen": 3435248,
      "step": 12270
    },
    {
      "epoch": 136.38888888888889,
      "grad_norm": 9.638387155064265e-08,
      "learning_rate": 0.23553607875856608,
      "loss": 0.0,
      "num_input_tokens_seen": 3436592,
      "step": 12275
    },
    {
      "epoch": 136.44444444444446,
      "grad_norm": 9.719620663872774e-08,
      "learning_rate": 0.2354876831289447,
      "loss": 0.0,
      "num_input_tokens_seen": 3438016,
      "step": 12280
    },
    {
      "epoch": 136.5,
      "grad_norm": 1.2279333816422877e-07,
      "learning_rate": 0.23543927431604827,
      "loss": 0.0,
      "num_input_tokens_seen": 3439392,
      "step": 12285
    },
    {
      "epoch": 136.55555555555554,
      "grad_norm": 7.761641995784885e-08,
      "learning_rate": 0.23539085232734203,
      "loss": 0.0,
      "num_input_tokens_seen": 3440816,
      "step": 12290
    },
    {
      "epoch": 136.61111111111111,
      "grad_norm": 2.161361862818012e-07,
      "learning_rate": 0.2353424171702933,
      "loss": 0.0,
      "num_input_tokens_seen": 3442208,
      "step": 12295
    },
    {
      "epoch": 136.66666666666666,
      "grad_norm": 1.4788572855195525e-07,
      "learning_rate": 0.23529396885237133,
      "loss": 0.0,
      "num_input_tokens_seen": 3443632,
      "step": 12300
    },
    {
      "epoch": 136.72222222222223,
      "grad_norm": 9.855346405629462e-08,
      "learning_rate": 0.2352455073810475,
      "loss": 0.0,
      "num_input_tokens_seen": 3445040,
      "step": 12305
    },
    {
      "epoch": 136.77777777777777,
      "grad_norm": 1.9162014552875917e-07,
      "learning_rate": 0.23519703276379517,
      "loss": 0.0,
      "num_input_tokens_seen": 3446352,
      "step": 12310
    },
    {
      "epoch": 136.83333333333334,
      "grad_norm": 1.2568037277560506e-07,
      "learning_rate": 0.2351485450080897,
      "loss": 0.0,
      "num_input_tokens_seen": 3447792,
      "step": 12315
    },
    {
      "epoch": 136.88888888888889,
      "grad_norm": 4.291388577826183e-08,
      "learning_rate": 0.2351000441214086,
      "loss": 0.0,
      "num_input_tokens_seen": 3449152,
      "step": 12320
    },
    {
      "epoch": 136.94444444444446,
      "grad_norm": 2.68784589252391e-07,
      "learning_rate": 0.23505153011123125,
      "loss": 0.0,
      "num_input_tokens_seen": 3450576,
      "step": 12325
    },
    {
      "epoch": 137.0,
      "grad_norm": 1.9673322526614356e-07,
      "learning_rate": 0.23500300298503912,
      "loss": 0.0,
      "num_input_tokens_seen": 3451984,
      "step": 12330
    },
    {
      "epoch": 137.05555555555554,
      "grad_norm": 7.113538202929703e-08,
      "learning_rate": 0.23495446275031576,
      "loss": 0.0,
      "num_input_tokens_seen": 3453360,
      "step": 12335
    },
    {
      "epoch": 137.11111111111111,
      "grad_norm": 9.97846285599735e-08,
      "learning_rate": 0.2349059094145466,
      "loss": 0.0,
      "num_input_tokens_seen": 3454736,
      "step": 12340
    },
    {
      "epoch": 137.16666666666666,
      "grad_norm": 1.3445178304039018e-08,
      "learning_rate": 0.2348573429852192,
      "loss": 0.0,
      "num_input_tokens_seen": 3456160,
      "step": 12345
    },
    {
      "epoch": 137.22222222222223,
      "grad_norm": 7.278724467596476e-08,
      "learning_rate": 0.23480876346982313,
      "loss": 0.0,
      "num_input_tokens_seen": 3457536,
      "step": 12350
    },
    {
      "epoch": 137.27777777777777,
      "grad_norm": 3.7563242472060665e-07,
      "learning_rate": 0.23476017087585,
      "loss": 0.0,
      "num_input_tokens_seen": 3458976,
      "step": 12355
    },
    {
      "epoch": 137.33333333333334,
      "grad_norm": 1.4619385524383688e-07,
      "learning_rate": 0.23471156521079334,
      "loss": 0.0,
      "num_input_tokens_seen": 3460336,
      "step": 12360
    },
    {
      "epoch": 137.38888888888889,
      "grad_norm": 8.708541798796432e-08,
      "learning_rate": 0.23466294648214875,
      "loss": 0.0,
      "num_input_tokens_seen": 3461760,
      "step": 12365
    },
    {
      "epoch": 137.44444444444446,
      "grad_norm": 4.0381237909059564e-07,
      "learning_rate": 0.2346143146974139,
      "loss": 0.0,
      "num_input_tokens_seen": 3463200,
      "step": 12370
    },
    {
      "epoch": 137.5,
      "grad_norm": 2.1205173084126727e-07,
      "learning_rate": 0.23456566986408836,
      "loss": 0.0,
      "num_input_tokens_seen": 3464576,
      "step": 12375
    },
    {
      "epoch": 137.55555555555554,
      "grad_norm": 1.286508251041596e-07,
      "learning_rate": 0.23451701198967384,
      "loss": 0.0,
      "num_input_tokens_seen": 3465936,
      "step": 12380
    },
    {
      "epoch": 137.61111111111111,
      "grad_norm": 1.1642880792805954e-07,
      "learning_rate": 0.23446834108167397,
      "loss": 0.0,
      "num_input_tokens_seen": 3467344,
      "step": 12385
    },
    {
      "epoch": 137.66666666666666,
      "grad_norm": 7.748029418053193e-08,
      "learning_rate": 0.23441965714759438,
      "loss": 0.0,
      "num_input_tokens_seen": 3468720,
      "step": 12390
    },
    {
      "epoch": 137.72222222222223,
      "grad_norm": 1.7834241816672147e-07,
      "learning_rate": 0.23437096019494277,
      "loss": 0.0,
      "num_input_tokens_seen": 3470128,
      "step": 12395
    },
    {
      "epoch": 137.77777777777777,
      "grad_norm": 4.931019361720246e-07,
      "learning_rate": 0.23432225023122885,
      "loss": 0.0,
      "num_input_tokens_seen": 3471520,
      "step": 12400
    },
    {
      "epoch": 137.77777777777777,
      "eval_loss": 1.1764440536499023,
      "eval_runtime": 1.1827,
      "eval_samples_per_second": 33.821,
      "eval_steps_per_second": 16.911,
      "num_input_tokens_seen": 3471520,
      "step": 12400
    },
    {
      "epoch": 137.83333333333334,
      "grad_norm": 7.80056268467888e-08,
      "learning_rate": 0.23427352726396428,
      "loss": 0.0,
      "num_input_tokens_seen": 3472944,
      "step": 12405
    },
    {
      "epoch": 137.88888888888889,
      "grad_norm": 2.3592380671288993e-07,
      "learning_rate": 0.2342247913006628,
      "loss": 0.0,
      "num_input_tokens_seen": 3474352,
      "step": 12410
    },
    {
      "epoch": 137.94444444444446,
      "grad_norm": 1.2185552122900845e-07,
      "learning_rate": 0.23417604234883999,
      "loss": 0.0,
      "num_input_tokens_seen": 3475776,
      "step": 12415
    },
    {
      "epoch": 138.0,
      "grad_norm": 2.0808319334264525e-07,
      "learning_rate": 0.23412728041601363,
      "loss": 0.0,
      "num_input_tokens_seen": 3477184,
      "step": 12420
    },
    {
      "epoch": 138.05555555555554,
      "grad_norm": 5.840342396368214e-07,
      "learning_rate": 0.23407850550970347,
      "loss": 0.0,
      "num_input_tokens_seen": 3478608,
      "step": 12425
    },
    {
      "epoch": 138.11111111111111,
      "grad_norm": 1.234718354226061e-07,
      "learning_rate": 0.23402971763743116,
      "loss": 0.0,
      "num_input_tokens_seen": 3479968,
      "step": 12430
    },
    {
      "epoch": 138.16666666666666,
      "grad_norm": 8.466486178804189e-08,
      "learning_rate": 0.23398091680672037,
      "loss": 0.0,
      "num_input_tokens_seen": 3481392,
      "step": 12435
    },
    {
      "epoch": 138.22222222222223,
      "grad_norm": 1.0519466542291411e-07,
      "learning_rate": 0.23393210302509687,
      "loss": 0.0,
      "num_input_tokens_seen": 3482832,
      "step": 12440
    },
    {
      "epoch": 138.27777777777777,
      "grad_norm": 1.6637282840292755e-07,
      "learning_rate": 0.23388327630008832,
      "loss": 0.0,
      "num_input_tokens_seen": 3484192,
      "step": 12445
    },
    {
      "epoch": 138.33333333333334,
      "grad_norm": 3.450498198276364e-08,
      "learning_rate": 0.23383443663922443,
      "loss": 0.0,
      "num_input_tokens_seen": 3485584,
      "step": 12450
    },
    {
      "epoch": 138.38888888888889,
      "grad_norm": 4.389252694636525e-07,
      "learning_rate": 0.23378558405003685,
      "loss": 0.0,
      "num_input_tokens_seen": 3486992,
      "step": 12455
    },
    {
      "epoch": 138.44444444444446,
      "grad_norm": 2.76395184073408e-07,
      "learning_rate": 0.2337367185400593,
      "loss": 0.0,
      "num_input_tokens_seen": 3488368,
      "step": 12460
    },
    {
      "epoch": 138.5,
      "grad_norm": 1.3910120344462484e-07,
      "learning_rate": 0.23368784011682747,
      "loss": 0.0,
      "num_input_tokens_seen": 3489792,
      "step": 12465
    },
    {
      "epoch": 138.55555555555554,
      "grad_norm": 2.0183804849693843e-07,
      "learning_rate": 0.23363894878787902,
      "loss": 0.0,
      "num_input_tokens_seen": 3491200,
      "step": 12470
    },
    {
      "epoch": 138.61111111111111,
      "grad_norm": 2.2095528606769221e-07,
      "learning_rate": 0.23359004456075352,
      "loss": 0.0,
      "num_input_tokens_seen": 3492608,
      "step": 12475
    },
    {
      "epoch": 138.66666666666666,
      "grad_norm": 1.6549478232263937e-07,
      "learning_rate": 0.23354112744299277,
      "loss": 0.0,
      "num_input_tokens_seen": 3494016,
      "step": 12480
    },
    {
      "epoch": 138.72222222222223,
      "grad_norm": 2.88771587975134e-07,
      "learning_rate": 0.2334921974421403,
      "loss": 0.0,
      "num_input_tokens_seen": 3495424,
      "step": 12485
    },
    {
      "epoch": 138.77777777777777,
      "grad_norm": 1.5338056869040884e-07,
      "learning_rate": 0.23344325456574178,
      "loss": 0.0,
      "num_input_tokens_seen": 3496864,
      "step": 12490
    },
    {
      "epoch": 138.83333333333334,
      "grad_norm": 6.068701452477399e-08,
      "learning_rate": 0.23339429882134477,
      "loss": 0.0,
      "num_input_tokens_seen": 3498240,
      "step": 12495
    },
    {
      "epoch": 138.88888888888889,
      "grad_norm": 1.4584905727588193e-07,
      "learning_rate": 0.23334533021649884,
      "loss": 0.0,
      "num_input_tokens_seen": 3499680,
      "step": 12500
    },
    {
      "epoch": 138.94444444444446,
      "grad_norm": 8.482950875077222e-08,
      "learning_rate": 0.23329634875875566,
      "loss": 0.0,
      "num_input_tokens_seen": 3501056,
      "step": 12505
    },
    {
      "epoch": 139.0,
      "grad_norm": 6.288377818464141e-08,
      "learning_rate": 0.23324735445566874,
      "loss": 0.0,
      "num_input_tokens_seen": 3502448,
      "step": 12510
    },
    {
      "epoch": 139.05555555555554,
      "grad_norm": 2.1175063125156157e-07,
      "learning_rate": 0.2331983473147936,
      "loss": 0.0,
      "num_input_tokens_seen": 3503872,
      "step": 12515
    },
    {
      "epoch": 139.11111111111111,
      "grad_norm": 4.791270313830864e-08,
      "learning_rate": 0.23314932734368776,
      "loss": 0.0,
      "num_input_tokens_seen": 3505280,
      "step": 12520
    },
    {
      "epoch": 139.16666666666666,
      "grad_norm": 2.920874919709604e-07,
      "learning_rate": 0.2331002945499107,
      "loss": 0.0,
      "num_input_tokens_seen": 3506672,
      "step": 12525
    },
    {
      "epoch": 139.22222222222223,
      "grad_norm": 1.2332203880305315e-07,
      "learning_rate": 0.23305124894102397,
      "loss": 0.0,
      "num_input_tokens_seen": 3508048,
      "step": 12530
    },
    {
      "epoch": 139.27777777777777,
      "grad_norm": 1.223913130843357e-07,
      "learning_rate": 0.23300219052459092,
      "loss": 0.0,
      "num_input_tokens_seen": 3509408,
      "step": 12535
    },
    {
      "epoch": 139.33333333333334,
      "grad_norm": 1.836818341871549e-07,
      "learning_rate": 0.23295311930817708,
      "loss": 0.0,
      "num_input_tokens_seen": 3510800,
      "step": 12540
    },
    {
      "epoch": 139.38888888888889,
      "grad_norm": 2.474204450209072e-07,
      "learning_rate": 0.23290403529934972,
      "loss": 0.0,
      "num_input_tokens_seen": 3512224,
      "step": 12545
    },
    {
      "epoch": 139.44444444444446,
      "grad_norm": 3.2497137425480105e-08,
      "learning_rate": 0.23285493850567832,
      "loss": 0.0,
      "num_input_tokens_seen": 3513664,
      "step": 12550
    },
    {
      "epoch": 139.5,
      "grad_norm": 4.0818846969159495e-07,
      "learning_rate": 0.23280582893473414,
      "loss": 0.0,
      "num_input_tokens_seen": 3515072,
      "step": 12555
    },
    {
      "epoch": 139.55555555555554,
      "grad_norm": 1.0313839027276117e-07,
      "learning_rate": 0.2327567065940906,
      "loss": 0.0,
      "num_input_tokens_seen": 3516464,
      "step": 12560
    },
    {
      "epoch": 139.61111111111111,
      "grad_norm": 2.8829646225858596e-07,
      "learning_rate": 0.23270757149132285,
      "loss": 0.0,
      "num_input_tokens_seen": 3517824,
      "step": 12565
    },
    {
      "epoch": 139.66666666666666,
      "grad_norm": 1.7433853471970906e-08,
      "learning_rate": 0.23265842363400827,
      "loss": 0.0,
      "num_input_tokens_seen": 3519216,
      "step": 12570
    },
    {
      "epoch": 139.72222222222223,
      "grad_norm": 1.8516701061344065e-07,
      "learning_rate": 0.23260926302972595,
      "loss": 0.0,
      "num_input_tokens_seen": 3520624,
      "step": 12575
    },
    {
      "epoch": 139.77777777777777,
      "grad_norm": 2.132419467670843e-07,
      "learning_rate": 0.2325600896860572,
      "loss": 0.0,
      "num_input_tokens_seen": 3522048,
      "step": 12580
    },
    {
      "epoch": 139.83333333333334,
      "grad_norm": 1.1443565028912417e-07,
      "learning_rate": 0.23251090361058505,
      "loss": 0.0,
      "num_input_tokens_seen": 3523440,
      "step": 12585
    },
    {
      "epoch": 139.88888888888889,
      "grad_norm": 1.293539781954678e-07,
      "learning_rate": 0.23246170481089476,
      "loss": 0.0,
      "num_input_tokens_seen": 3524832,
      "step": 12590
    },
    {
      "epoch": 139.94444444444446,
      "grad_norm": 6.048085765542055e-08,
      "learning_rate": 0.23241249329457317,
      "loss": 0.0,
      "num_input_tokens_seen": 3526224,
      "step": 12595
    },
    {
      "epoch": 140.0,
      "grad_norm": 3.987744037203811e-07,
      "learning_rate": 0.23236326906920957,
      "loss": 0.0,
      "num_input_tokens_seen": 3527664,
      "step": 12600
    },
    {
      "epoch": 140.0,
      "eval_loss": 1.175498366355896,
      "eval_runtime": 1.1941,
      "eval_samples_per_second": 33.498,
      "eval_steps_per_second": 16.749,
      "num_input_tokens_seen": 3527664,
      "step": 12600
    },
    {
      "epoch": 140.05555555555554,
      "grad_norm": 1.1081914408350713e-07,
      "learning_rate": 0.2323140321423948,
      "loss": 0.0,
      "num_input_tokens_seen": 3529040,
      "step": 12605
    },
    {
      "epoch": 140.11111111111111,
      "grad_norm": 2.8417005637493276e-07,
      "learning_rate": 0.23226478252172184,
      "loss": 0.0,
      "num_input_tokens_seen": 3530448,
      "step": 12610
    },
    {
      "epoch": 140.16666666666666,
      "grad_norm": 4.363731420653494e-08,
      "learning_rate": 0.23221552021478561,
      "loss": 0.0,
      "num_input_tokens_seen": 3531824,
      "step": 12615
    },
    {
      "epoch": 140.22222222222223,
      "grad_norm": 4.3902758761760197e-07,
      "learning_rate": 0.232166245229183,
      "loss": 0.0,
      "num_input_tokens_seen": 3533280,
      "step": 12620
    },
    {
      "epoch": 140.27777777777777,
      "grad_norm": 9.370859288537758e-08,
      "learning_rate": 0.2321169575725128,
      "loss": 0.0,
      "num_input_tokens_seen": 3534688,
      "step": 12625
    },
    {
      "epoch": 140.33333333333334,
      "grad_norm": 1.5252599894211016e-07,
      "learning_rate": 0.23206765725237577,
      "loss": 0.0,
      "num_input_tokens_seen": 3536080,
      "step": 12630
    },
    {
      "epoch": 140.38888888888889,
      "grad_norm": 4.5827096784023524e-08,
      "learning_rate": 0.2320183442763747,
      "loss": 0.0,
      "num_input_tokens_seen": 3537424,
      "step": 12635
    },
    {
      "epoch": 140.44444444444446,
      "grad_norm": 1.582444042469433e-07,
      "learning_rate": 0.23196901865211422,
      "loss": 0.0,
      "num_input_tokens_seen": 3538832,
      "step": 12640
    },
    {
      "epoch": 140.5,
      "grad_norm": 2.021686640318876e-08,
      "learning_rate": 0.231919680387201,
      "loss": 0.0,
      "num_input_tokens_seen": 3540256,
      "step": 12645
    },
    {
      "epoch": 140.55555555555554,
      "grad_norm": 9.870834105640824e-08,
      "learning_rate": 0.23187032948924358,
      "loss": 0.0,
      "num_input_tokens_seen": 3541648,
      "step": 12650
    },
    {
      "epoch": 140.61111111111111,
      "grad_norm": 2.861328027847776e-07,
      "learning_rate": 0.23182096596585247,
      "loss": 0.0,
      "num_input_tokens_seen": 3543120,
      "step": 12655
    },
    {
      "epoch": 140.66666666666666,
      "grad_norm": 1.4698102290822135e-07,
      "learning_rate": 0.23177158982464025,
      "loss": 0.0,
      "num_input_tokens_seen": 3544528,
      "step": 12660
    },
    {
      "epoch": 140.72222222222223,
      "grad_norm": 1.6651610224016622e-07,
      "learning_rate": 0.23172220107322122,
      "loss": 0.0,
      "num_input_tokens_seen": 3545904,
      "step": 12665
    },
    {
      "epoch": 140.77777777777777,
      "grad_norm": 2.40353500657875e-07,
      "learning_rate": 0.23167279971921184,
      "loss": 0.0,
      "num_input_tokens_seen": 3547328,
      "step": 12670
    },
    {
      "epoch": 140.83333333333334,
      "grad_norm": 1.7936348228886345e-07,
      "learning_rate": 0.23162338577023034,
      "loss": 0.0,
      "num_input_tokens_seen": 3548720,
      "step": 12675
    },
    {
      "epoch": 140.88888888888889,
      "grad_norm": 1.7641313831973093e-07,
      "learning_rate": 0.23157395923389704,
      "loss": 0.0,
      "num_input_tokens_seen": 3550080,
      "step": 12680
    },
    {
      "epoch": 140.94444444444446,
      "grad_norm": 9.540872270008549e-08,
      "learning_rate": 0.2315245201178341,
      "loss": 0.0,
      "num_input_tokens_seen": 3551488,
      "step": 12685
    },
    {
      "epoch": 141.0,
      "grad_norm": 1.294911129434695e-07,
      "learning_rate": 0.23147506842966564,
      "loss": 0.0,
      "num_input_tokens_seen": 3552864,
      "step": 12690
    },
    {
      "epoch": 141.05555555555554,
      "grad_norm": 2.0918675147640897e-07,
      "learning_rate": 0.23142560417701774,
      "loss": 0.0,
      "num_input_tokens_seen": 3554272,
      "step": 12695
    },
    {
      "epoch": 141.11111111111111,
      "grad_norm": 2.8334517310213414e-07,
      "learning_rate": 0.23137612736751845,
      "loss": 0.0,
      "num_input_tokens_seen": 3555696,
      "step": 12700
    },
    {
      "epoch": 141.16666666666666,
      "grad_norm": 1.1461274596058502e-07,
      "learning_rate": 0.23132663800879766,
      "loss": 0.0,
      "num_input_tokens_seen": 3557104,
      "step": 12705
    },
    {
      "epoch": 141.22222222222223,
      "grad_norm": 2.7824052040159586e-07,
      "learning_rate": 0.2312771361084873,
      "loss": 0.0,
      "num_input_tokens_seen": 3558480,
      "step": 12710
    },
    {
      "epoch": 141.27777777777777,
      "grad_norm": 1.4660692215784366e-07,
      "learning_rate": 0.23122762167422112,
      "loss": 0.0,
      "num_input_tokens_seen": 3559872,
      "step": 12715
    },
    {
      "epoch": 141.33333333333334,
      "grad_norm": 1.7152882492155186e-07,
      "learning_rate": 0.23117809471363493,
      "loss": 0.0,
      "num_input_tokens_seen": 3561280,
      "step": 12720
    },
    {
      "epoch": 141.38888888888889,
      "grad_norm": 9.317610505377161e-08,
      "learning_rate": 0.23112855523436637,
      "loss": 0.0,
      "num_input_tokens_seen": 3562688,
      "step": 12725
    },
    {
      "epoch": 141.44444444444446,
      "grad_norm": 8.626288661162107e-08,
      "learning_rate": 0.23107900324405511,
      "loss": 0.0,
      "num_input_tokens_seen": 3564080,
      "step": 12730
    },
    {
      "epoch": 141.5,
      "grad_norm": 1.5394719810046809e-07,
      "learning_rate": 0.2310294387503426,
      "loss": 0.0,
      "num_input_tokens_seen": 3565440,
      "step": 12735
    },
    {
      "epoch": 141.55555555555554,
      "grad_norm": 1.304453718375953e-07,
      "learning_rate": 0.23097986176087237,
      "loss": 0.0,
      "num_input_tokens_seen": 3566880,
      "step": 12740
    },
    {
      "epoch": 141.61111111111111,
      "grad_norm": 1.6678205838616122e-07,
      "learning_rate": 0.23093027228328986,
      "loss": 0.0,
      "num_input_tokens_seen": 3568288,
      "step": 12745
    },
    {
      "epoch": 141.66666666666666,
      "grad_norm": 1.3388275021952722e-07,
      "learning_rate": 0.23088067032524226,
      "loss": 0.0,
      "num_input_tokens_seen": 3569648,
      "step": 12750
    },
    {
      "epoch": 141.72222222222223,
      "grad_norm": 1.6602236030394124e-07,
      "learning_rate": 0.23083105589437888,
      "loss": 0.0,
      "num_input_tokens_seen": 3571056,
      "step": 12755
    },
    {
      "epoch": 141.77777777777777,
      "grad_norm": 1.3267840870412329e-07,
      "learning_rate": 0.23078142899835094,
      "loss": 0.0,
      "num_input_tokens_seen": 3572464,
      "step": 12760
    },
    {
      "epoch": 141.83333333333334,
      "grad_norm": 6.821549902724655e-08,
      "learning_rate": 0.23073178964481147,
      "loss": 0.0,
      "num_input_tokens_seen": 3573824,
      "step": 12765
    },
    {
      "epoch": 141.88888888888889,
      "grad_norm": 3.931177445792855e-07,
      "learning_rate": 0.2306821378414155,
      "loss": 0.0,
      "num_input_tokens_seen": 3575248,
      "step": 12770
    },
    {
      "epoch": 141.94444444444446,
      "grad_norm": 1.982852069204455e-07,
      "learning_rate": 0.2306324735958199,
      "loss": 0.0,
      "num_input_tokens_seen": 3576672,
      "step": 12775
    },
    {
      "epoch": 142.0,
      "grad_norm": 5.120043411466213e-08,
      "learning_rate": 0.23058279691568362,
      "loss": 0.0,
      "num_input_tokens_seen": 3578144,
      "step": 12780
    },
    {
      "epoch": 142.05555555555554,
      "grad_norm": 1.230984878475283e-07,
      "learning_rate": 0.23053310780866745,
      "loss": 0.0,
      "num_input_tokens_seen": 3579552,
      "step": 12785
    },
    {
      "epoch": 142.11111111111111,
      "grad_norm": 8.781369587040899e-08,
      "learning_rate": 0.23048340628243397,
      "loss": 0.0,
      "num_input_tokens_seen": 3580944,
      "step": 12790
    },
    {
      "epoch": 142.16666666666666,
      "grad_norm": 1.4216716692772025e-07,
      "learning_rate": 0.23043369234464783,
      "loss": 0.0,
      "num_input_tokens_seen": 3582336,
      "step": 12795
    },
    {
      "epoch": 142.22222222222223,
      "grad_norm": 1.5378728335235792e-07,
      "learning_rate": 0.2303839660029755,
      "loss": 0.0,
      "num_input_tokens_seen": 3583696,
      "step": 12800
    },
    {
      "epoch": 142.22222222222223,
      "eval_loss": 1.2023162841796875,
      "eval_runtime": 1.1856,
      "eval_samples_per_second": 33.737,
      "eval_steps_per_second": 16.868,
      "num_input_tokens_seen": 3583696,
      "step": 12800
    },
    {
      "epoch": 142.27777777777777,
      "grad_norm": 1.6481486397879053e-07,
      "learning_rate": 0.23033422726508548,
      "loss": 0.0,
      "num_input_tokens_seen": 3585120,
      "step": 12805
    },
    {
      "epoch": 142.33333333333334,
      "grad_norm": 9.698397462898356e-08,
      "learning_rate": 0.23028447613864808,
      "loss": 0.0,
      "num_input_tokens_seen": 3586496,
      "step": 12810
    },
    {
      "epoch": 142.38888888888889,
      "grad_norm": 1.1295968249669386e-07,
      "learning_rate": 0.2302347126313355,
      "loss": 0.0,
      "num_input_tokens_seen": 3587888,
      "step": 12815
    },
    {
      "epoch": 142.44444444444446,
      "grad_norm": 1.4251507707285782e-07,
      "learning_rate": 0.23018493675082197,
      "loss": 0.0,
      "num_input_tokens_seen": 3589280,
      "step": 12820
    },
    {
      "epoch": 142.5,
      "grad_norm": 1.3990086245030398e-07,
      "learning_rate": 0.2301351485047835,
      "loss": 0.0,
      "num_input_tokens_seen": 3590704,
      "step": 12825
    },
    {
      "epoch": 142.55555555555554,
      "grad_norm": 6.54676526323783e-08,
      "learning_rate": 0.23008534790089813,
      "loss": 0.0,
      "num_input_tokens_seen": 3592096,
      "step": 12830
    },
    {
      "epoch": 142.61111111111111,
      "grad_norm": 2.0544349865758704e-07,
      "learning_rate": 0.2300355349468457,
      "loss": 0.0,
      "num_input_tokens_seen": 3593472,
      "step": 12835
    },
    {
      "epoch": 142.66666666666666,
      "grad_norm": 1.394645323671284e-07,
      "learning_rate": 0.22998570965030793,
      "loss": 0.0,
      "num_input_tokens_seen": 3594880,
      "step": 12840
    },
    {
      "epoch": 142.72222222222223,
      "grad_norm": 1.0924174631554706e-07,
      "learning_rate": 0.22993587201896862,
      "loss": 0.0,
      "num_input_tokens_seen": 3596304,
      "step": 12845
    },
    {
      "epoch": 142.77777777777777,
      "grad_norm": 7.647733468729712e-08,
      "learning_rate": 0.2298860220605133,
      "loss": 0.0,
      "num_input_tokens_seen": 3597696,
      "step": 12850
    },
    {
      "epoch": 142.83333333333334,
      "grad_norm": 4.9154802894690874e-08,
      "learning_rate": 0.22983615978262942,
      "loss": 0.0,
      "num_input_tokens_seen": 3599120,
      "step": 12855
    },
    {
      "epoch": 142.88888888888889,
      "grad_norm": 5.4848836583687444e-08,
      "learning_rate": 0.22978628519300648,
      "loss": 0.0,
      "num_input_tokens_seen": 3600528,
      "step": 12860
    },
    {
      "epoch": 142.94444444444446,
      "grad_norm": 2.1116521509156883e-07,
      "learning_rate": 0.22973639829933568,
      "loss": 0.0,
      "num_input_tokens_seen": 3601888,
      "step": 12865
    },
    {
      "epoch": 143.0,
      "grad_norm": 1.736901253934775e-07,
      "learning_rate": 0.22968649910931027,
      "loss": 0.0,
      "num_input_tokens_seen": 3603312,
      "step": 12870
    },
    {
      "epoch": 143.05555555555554,
      "grad_norm": 2.883282661514386e-07,
      "learning_rate": 0.22963658763062528,
      "loss": 0.0,
      "num_input_tokens_seen": 3604704,
      "step": 12875
    },
    {
      "epoch": 143.11111111111111,
      "grad_norm": 8.147550545345439e-08,
      "learning_rate": 0.22958666387097765,
      "loss": 0.0,
      "num_input_tokens_seen": 3606096,
      "step": 12880
    },
    {
      "epoch": 143.16666666666666,
      "grad_norm": 1.716555289021926e-07,
      "learning_rate": 0.22953672783806633,
      "loss": 0.0,
      "num_input_tokens_seen": 3607440,
      "step": 12885
    },
    {
      "epoch": 143.22222222222223,
      "grad_norm": 7.019098546834357e-08,
      "learning_rate": 0.22948677953959207,
      "loss": 0.0,
      "num_input_tokens_seen": 3608848,
      "step": 12890
    },
    {
      "epoch": 143.27777777777777,
      "grad_norm": 7.349539288270535e-08,
      "learning_rate": 0.2294368189832575,
      "loss": 0.0,
      "num_input_tokens_seen": 3610288,
      "step": 12895
    },
    {
      "epoch": 143.33333333333334,
      "grad_norm": 8.035804199835184e-08,
      "learning_rate": 0.2293868461767672,
      "loss": 0.0,
      "num_input_tokens_seen": 3611664,
      "step": 12900
    },
    {
      "epoch": 143.38888888888889,
      "grad_norm": 1.766930779467657e-07,
      "learning_rate": 0.22933686112782758,
      "loss": 0.0,
      "num_input_tokens_seen": 3613056,
      "step": 12905
    },
    {
      "epoch": 143.44444444444446,
      "grad_norm": 1.5640847550457693e-07,
      "learning_rate": 0.22928686384414698,
      "loss": 0.0,
      "num_input_tokens_seen": 3614480,
      "step": 12910
    },
    {
      "epoch": 143.5,
      "grad_norm": 2.727515777678491e-07,
      "learning_rate": 0.22923685433343552,
      "loss": 0.0,
      "num_input_tokens_seen": 3615888,
      "step": 12915
    },
    {
      "epoch": 143.55555555555554,
      "grad_norm": 7.295468407164662e-08,
      "learning_rate": 0.22918683260340542,
      "loss": 0.0,
      "num_input_tokens_seen": 3617312,
      "step": 12920
    },
    {
      "epoch": 143.61111111111111,
      "grad_norm": 2.0381266097047046e-07,
      "learning_rate": 0.2291367986617706,
      "loss": 0.0,
      "num_input_tokens_seen": 3618752,
      "step": 12925
    },
    {
      "epoch": 143.66666666666666,
      "grad_norm": 2.196159343270665e-08,
      "learning_rate": 0.22908675251624697,
      "loss": 0.0,
      "num_input_tokens_seen": 3620176,
      "step": 12930
    },
    {
      "epoch": 143.72222222222223,
      "grad_norm": 4.425034205723932e-08,
      "learning_rate": 0.22903669417455216,
      "loss": 0.0,
      "num_input_tokens_seen": 3621568,
      "step": 12935
    },
    {
      "epoch": 143.77777777777777,
      "grad_norm": 3.6586772722557726e-08,
      "learning_rate": 0.22898662364440592,
      "loss": 0.0,
      "num_input_tokens_seen": 3623008,
      "step": 12940
    },
    {
      "epoch": 143.83333333333334,
      "grad_norm": 1.2945135097197635e-07,
      "learning_rate": 0.2289365409335297,
      "loss": 0.0,
      "num_input_tokens_seen": 3624400,
      "step": 12945
    },
    {
      "epoch": 143.88888888888889,
      "grad_norm": 1.183473088417486e-07,
      "learning_rate": 0.2288864460496469,
      "loss": 0.0,
      "num_input_tokens_seen": 3625776,
      "step": 12950
    },
    {
      "epoch": 143.94444444444446,
      "grad_norm": 5.748404063865564e-08,
      "learning_rate": 0.22883633900048272,
      "loss": 0.0,
      "num_input_tokens_seen": 3627168,
      "step": 12955
    },
    {
      "epoch": 144.0,
      "grad_norm": 1.7804005381094612e-07,
      "learning_rate": 0.2287862197937644,
      "loss": 0.0,
      "num_input_tokens_seen": 3628544,
      "step": 12960
    },
    {
      "epoch": 144.05555555555554,
      "grad_norm": 3.049227643714403e-07,
      "learning_rate": 0.2287360884372209,
      "loss": 0.0,
      "num_input_tokens_seen": 3629968,
      "step": 12965
    },
    {
      "epoch": 144.11111111111111,
      "grad_norm": 1.9596761546836206e-07,
      "learning_rate": 0.22868594493858307,
      "loss": 0.0,
      "num_input_tokens_seen": 3631344,
      "step": 12970
    },
    {
      "epoch": 144.16666666666666,
      "grad_norm": 1.3400823206666246e-07,
      "learning_rate": 0.2286357893055837,
      "loss": 0.0,
      "num_input_tokens_seen": 3632736,
      "step": 12975
    },
    {
      "epoch": 144.22222222222223,
      "grad_norm": 9.795417810209983e-08,
      "learning_rate": 0.22858562154595746,
      "loss": 0.0,
      "num_input_tokens_seen": 3634144,
      "step": 12980
    },
    {
      "epoch": 144.27777777777777,
      "grad_norm": 9.888911023381297e-08,
      "learning_rate": 0.22853544166744078,
      "loss": 0.0,
      "num_input_tokens_seen": 3635520,
      "step": 12985
    },
    {
      "epoch": 144.33333333333334,
      "grad_norm": 1.661850745904303e-07,
      "learning_rate": 0.22848524967777206,
      "loss": 0.0,
      "num_input_tokens_seen": 3636864,
      "step": 12990
    },
    {
      "epoch": 144.38888888888889,
      "grad_norm": 1.7938840812803392e-07,
      "learning_rate": 0.22843504558469152,
      "loss": 0.0,
      "num_input_tokens_seen": 3638240,
      "step": 12995
    },
    {
      "epoch": 144.44444444444446,
      "grad_norm": 3.79238088044076e-07,
      "learning_rate": 0.2283848293959413,
      "loss": 0.0,
      "num_input_tokens_seen": 3639680,
      "step": 13000
    },
    {
      "epoch": 144.44444444444446,
      "eval_loss": 1.1985673904418945,
      "eval_runtime": 1.1882,
      "eval_samples_per_second": 33.666,
      "eval_steps_per_second": 16.833,
      "num_input_tokens_seen": 3639680,
      "step": 13000
    },
    {
      "epoch": 144.5,
      "grad_norm": 2.52300281999851e-07,
      "learning_rate": 0.22833460111926532,
      "loss": 0.0,
      "num_input_tokens_seen": 3641088,
      "step": 13005
    },
    {
      "epoch": 144.55555555555554,
      "grad_norm": 7.944835545004025e-08,
      "learning_rate": 0.22828436076240946,
      "loss": 0.0,
      "num_input_tokens_seen": 3642464,
      "step": 13010
    },
    {
      "epoch": 144.61111111111111,
      "grad_norm": 1.60293481599183e-07,
      "learning_rate": 0.22823410833312135,
      "loss": 0.0,
      "num_input_tokens_seen": 3643824,
      "step": 13015
    },
    {
      "epoch": 144.66666666666666,
      "grad_norm": 1.9991240662875498e-08,
      "learning_rate": 0.2281838438391506,
      "loss": 0.0,
      "num_input_tokens_seen": 3645232,
      "step": 13020
    },
    {
      "epoch": 144.72222222222223,
      "grad_norm": 5.226141297498543e-08,
      "learning_rate": 0.22813356728824863,
      "loss": 0.0,
      "num_input_tokens_seen": 3646640,
      "step": 13025
    },
    {
      "epoch": 144.77777777777777,
      "grad_norm": 9.228060804389315e-08,
      "learning_rate": 0.2280832786881687,
      "loss": 0.0,
      "num_input_tokens_seen": 3648032,
      "step": 13030
    },
    {
      "epoch": 144.83333333333334,
      "grad_norm": 3.841456219788597e-08,
      "learning_rate": 0.22803297804666592,
      "loss": 0.0,
      "num_input_tokens_seen": 3649456,
      "step": 13035
    },
    {
      "epoch": 144.88888888888889,
      "grad_norm": 5.4462905296759345e-08,
      "learning_rate": 0.22798266537149728,
      "loss": 0.0,
      "num_input_tokens_seen": 3650864,
      "step": 13040
    },
    {
      "epoch": 144.94444444444446,
      "grad_norm": 2.1165982388993143e-07,
      "learning_rate": 0.22793234067042167,
      "loss": 0.0,
      "num_input_tokens_seen": 3652272,
      "step": 13045
    },
    {
      "epoch": 145.0,
      "grad_norm": 1.334252317519713e-07,
      "learning_rate": 0.22788200395119979,
      "loss": 0.0,
      "num_input_tokens_seen": 3653696,
      "step": 13050
    },
    {
      "epoch": 145.05555555555554,
      "grad_norm": 3.014184457583724e-08,
      "learning_rate": 0.2278316552215942,
      "loss": 0.0,
      "num_input_tokens_seen": 3655120,
      "step": 13055
    },
    {
      "epoch": 145.11111111111111,
      "grad_norm": 8.87379911773678e-08,
      "learning_rate": 0.22778129448936918,
      "loss": 0.0,
      "num_input_tokens_seen": 3656512,
      "step": 13060
    },
    {
      "epoch": 145.16666666666666,
      "grad_norm": 6.96676636380289e-08,
      "learning_rate": 0.22773092176229118,
      "loss": 0.0,
      "num_input_tokens_seen": 3657872,
      "step": 13065
    },
    {
      "epoch": 145.22222222222223,
      "grad_norm": 1.735505428257511e-08,
      "learning_rate": 0.22768053704812816,
      "loss": 0.0,
      "num_input_tokens_seen": 3659280,
      "step": 13070
    },
    {
      "epoch": 145.27777777777777,
      "grad_norm": 5.847829953609107e-08,
      "learning_rate": 0.22763014035465018,
      "loss": 0.0,
      "num_input_tokens_seen": 3660720,
      "step": 13075
    },
    {
      "epoch": 145.33333333333334,
      "grad_norm": 2.6497951921555796e-07,
      "learning_rate": 0.22757973168962892,
      "loss": 0.0,
      "num_input_tokens_seen": 3662144,
      "step": 13080
    },
    {
      "epoch": 145.38888888888889,
      "grad_norm": 2.2316329761906673e-07,
      "learning_rate": 0.22752931106083818,
      "loss": 0.0,
      "num_input_tokens_seen": 3663552,
      "step": 13085
    },
    {
      "epoch": 145.44444444444446,
      "grad_norm": 1.4276784554567712e-07,
      "learning_rate": 0.22747887847605341,
      "loss": 0.0,
      "num_input_tokens_seen": 3664944,
      "step": 13090
    },
    {
      "epoch": 145.5,
      "grad_norm": 1.6882006548257777e-07,
      "learning_rate": 0.22742843394305184,
      "loss": 0.0,
      "num_input_tokens_seen": 3666368,
      "step": 13095
    },
    {
      "epoch": 145.55555555555554,
      "grad_norm": 7.485366637638435e-08,
      "learning_rate": 0.22737797746961272,
      "loss": 0.0,
      "num_input_tokens_seen": 3667776,
      "step": 13100
    },
    {
      "epoch": 145.61111111111111,
      "grad_norm": 2.5335788222946576e-07,
      "learning_rate": 0.22732750906351712,
      "loss": 0.0,
      "num_input_tokens_seen": 3669168,
      "step": 13105
    },
    {
      "epoch": 145.66666666666666,
      "grad_norm": 4.129458019974663e-08,
      "learning_rate": 0.22727702873254785,
      "loss": 0.0,
      "num_input_tokens_seen": 3670576,
      "step": 13110
    },
    {
      "epoch": 145.72222222222223,
      "grad_norm": 3.296044610578974e-07,
      "learning_rate": 0.22722653648448968,
      "loss": 0.0,
      "num_input_tokens_seen": 3671968,
      "step": 13115
    },
    {
      "epoch": 145.77777777777777,
      "grad_norm": 1.1588895887371109e-07,
      "learning_rate": 0.22717603232712902,
      "loss": 0.0,
      "num_input_tokens_seen": 3673344,
      "step": 13120
    },
    {
      "epoch": 145.83333333333334,
      "grad_norm": 5.941826231037339e-08,
      "learning_rate": 0.22712551626825436,
      "loss": 0.0,
      "num_input_tokens_seen": 3674752,
      "step": 13125
    },
    {
      "epoch": 145.88888888888889,
      "grad_norm": 1.5818496024166961e-07,
      "learning_rate": 0.2270749883156559,
      "loss": 0.0,
      "num_input_tokens_seen": 3676160,
      "step": 13130
    },
    {
      "epoch": 145.94444444444446,
      "grad_norm": 1.0550711948553726e-07,
      "learning_rate": 0.22702444847712563,
      "loss": 0.0,
      "num_input_tokens_seen": 3677568,
      "step": 13135
    },
    {
      "epoch": 146.0,
      "grad_norm": 9.88394006640192e-08,
      "learning_rate": 0.22697389676045743,
      "loss": 0.0,
      "num_input_tokens_seen": 3678992,
      "step": 13140
    },
    {
      "epoch": 146.05555555555554,
      "grad_norm": 3.46432287301468e-08,
      "learning_rate": 0.22692333317344704,
      "loss": 0.0,
      "num_input_tokens_seen": 3680368,
      "step": 13145
    },
    {
      "epoch": 146.11111111111111,
      "grad_norm": 1.5778128670262959e-07,
      "learning_rate": 0.22687275772389198,
      "loss": 0.0,
      "num_input_tokens_seen": 3681776,
      "step": 13150
    },
    {
      "epoch": 146.16666666666666,
      "grad_norm": 1.479487821143266e-07,
      "learning_rate": 0.22682217041959168,
      "loss": 0.0,
      "num_input_tokens_seen": 3683184,
      "step": 13155
    },
    {
      "epoch": 146.22222222222223,
      "grad_norm": 4.894106453434688e-08,
      "learning_rate": 0.2267715712683473,
      "loss": 0.0,
      "num_input_tokens_seen": 3684640,
      "step": 13160
    },
    {
      "epoch": 146.27777777777777,
      "grad_norm": 8.754884817108177e-08,
      "learning_rate": 0.22672096027796182,
      "loss": 0.0,
      "num_input_tokens_seen": 3686000,
      "step": 13165
    },
    {
      "epoch": 146.33333333333334,
      "grad_norm": 7.867294016250526e-08,
      "learning_rate": 0.22667033745624016,
      "loss": 0.0,
      "num_input_tokens_seen": 3687344,
      "step": 13170
    },
    {
      "epoch": 146.38888888888889,
      "grad_norm": 1.9625687741609e-07,
      "learning_rate": 0.22661970281098895,
      "loss": 0.0,
      "num_input_tokens_seen": 3688720,
      "step": 13175
    },
    {
      "epoch": 146.44444444444446,
      "grad_norm": 9.142667778405666e-08,
      "learning_rate": 0.22656905635001667,
      "loss": 0.0,
      "num_input_tokens_seen": 3690112,
      "step": 13180
    },
    {
      "epoch": 146.5,
      "grad_norm": 8.489084279972303e-08,
      "learning_rate": 0.2265183980811337,
      "loss": 0.0,
      "num_input_tokens_seen": 3691472,
      "step": 13185
    },
    {
      "epoch": 146.55555555555554,
      "grad_norm": 5.376710632276627e-08,
      "learning_rate": 0.22646772801215218,
      "loss": 0.0,
      "num_input_tokens_seen": 3692896,
      "step": 13190
    },
    {
      "epoch": 146.61111111111111,
      "grad_norm": 5.304328709598849e-08,
      "learning_rate": 0.22641704615088598,
      "loss": 0.0,
      "num_input_tokens_seen": 3694320,
      "step": 13195
    },
    {
      "epoch": 146.66666666666666,
      "grad_norm": 2.9906038889748743e-07,
      "learning_rate": 0.22636635250515103,
      "loss": 0.0,
      "num_input_tokens_seen": 3695712,
      "step": 13200
    },
    {
      "epoch": 146.66666666666666,
      "eval_loss": 1.2131414413452148,
      "eval_runtime": 1.1842,
      "eval_samples_per_second": 33.778,
      "eval_steps_per_second": 16.889,
      "num_input_tokens_seen": 3695712,
      "step": 13200
    },
    {
      "epoch": 146.72222222222223,
      "grad_norm": 3.131261223643378e-07,
      "learning_rate": 0.2263156470827648,
      "loss": 0.0,
      "num_input_tokens_seen": 3697088,
      "step": 13205
    },
    {
      "epoch": 146.77777777777777,
      "grad_norm": 8.993485067776419e-08,
      "learning_rate": 0.22626492989154678,
      "loss": 0.0,
      "num_input_tokens_seen": 3698544,
      "step": 13210
    },
    {
      "epoch": 146.83333333333334,
      "grad_norm": 5.622600340871031e-08,
      "learning_rate": 0.22621420093931813,
      "loss": 0.0,
      "num_input_tokens_seen": 3699904,
      "step": 13215
    },
    {
      "epoch": 146.88888888888889,
      "grad_norm": 2.7298121096919203e-08,
      "learning_rate": 0.22616346023390194,
      "loss": 0.0,
      "num_input_tokens_seen": 3701296,
      "step": 13220
    },
    {
      "epoch": 146.94444444444446,
      "grad_norm": 1.7846979005753383e-07,
      "learning_rate": 0.22611270778312306,
      "loss": 0.0,
      "num_input_tokens_seen": 3702656,
      "step": 13225
    },
    {
      "epoch": 147.0,
      "grad_norm": 1.0577976183867577e-07,
      "learning_rate": 0.2260619435948081,
      "loss": 0.0,
      "num_input_tokens_seen": 3704064,
      "step": 13230
    },
    {
      "epoch": 147.05555555555554,
      "grad_norm": 1.2248224834365828e-07,
      "learning_rate": 0.22601116767678567,
      "loss": 0.0,
      "num_input_tokens_seen": 3705440,
      "step": 13235
    },
    {
      "epoch": 147.11111111111111,
      "grad_norm": 1.6983729267394665e-07,
      "learning_rate": 0.2259603800368859,
      "loss": 0.0,
      "num_input_tokens_seen": 3706816,
      "step": 13240
    },
    {
      "epoch": 147.16666666666666,
      "grad_norm": 3.921531899209185e-08,
      "learning_rate": 0.22590958068294098,
      "loss": 0.0,
      "num_input_tokens_seen": 3708192,
      "step": 13245
    },
    {
      "epoch": 147.22222222222223,
      "grad_norm": 8.919175087385156e-08,
      "learning_rate": 0.22585876962278478,
      "loss": 0.0,
      "num_input_tokens_seen": 3709616,
      "step": 13250
    },
    {
      "epoch": 147.27777777777777,
      "grad_norm": 1.1188953408236557e-07,
      "learning_rate": 0.22580794686425298,
      "loss": 0.0,
      "num_input_tokens_seen": 3710992,
      "step": 13255
    },
    {
      "epoch": 147.33333333333334,
      "grad_norm": 1.4923398339306004e-07,
      "learning_rate": 0.22575711241518312,
      "loss": 0.0,
      "num_input_tokens_seen": 3712400,
      "step": 13260
    },
    {
      "epoch": 147.38888888888889,
      "grad_norm": 7.005187541153646e-08,
      "learning_rate": 0.22570626628341453,
      "loss": 0.0,
      "num_input_tokens_seen": 3713824,
      "step": 13265
    },
    {
      "epoch": 147.44444444444446,
      "grad_norm": 2.7147656567194645e-08,
      "learning_rate": 0.22565540847678828,
      "loss": 0.0,
      "num_input_tokens_seen": 3715264,
      "step": 13270
    },
    {
      "epoch": 147.5,
      "grad_norm": 3.112777449132409e-07,
      "learning_rate": 0.2256045390031473,
      "loss": 0.0,
      "num_input_tokens_seen": 3716656,
      "step": 13275
    },
    {
      "epoch": 147.55555555555554,
      "grad_norm": 7.046741501426368e-08,
      "learning_rate": 0.22555365787033627,
      "loss": 0.0,
      "num_input_tokens_seen": 3718064,
      "step": 13280
    },
    {
      "epoch": 147.61111111111111,
      "grad_norm": 1.5298151367915125e-07,
      "learning_rate": 0.22550276508620173,
      "loss": 0.0,
      "num_input_tokens_seen": 3719456,
      "step": 13285
    },
    {
      "epoch": 147.66666666666666,
      "grad_norm": 1.8614235486325015e-08,
      "learning_rate": 0.22545186065859202,
      "loss": 0.0,
      "num_input_tokens_seen": 3720848,
      "step": 13290
    },
    {
      "epoch": 147.72222222222223,
      "grad_norm": 4.809314546605492e-08,
      "learning_rate": 0.2254009445953572,
      "loss": 0.0,
      "num_input_tokens_seen": 3722224,
      "step": 13295
    },
    {
      "epoch": 147.77777777777777,
      "grad_norm": 1.3646868524119782e-07,
      "learning_rate": 0.22535001690434917,
      "loss": 0.0,
      "num_input_tokens_seen": 3723648,
      "step": 13300
    },
    {
      "epoch": 147.83333333333334,
      "grad_norm": 1.6467738817027566e-07,
      "learning_rate": 0.22529907759342163,
      "loss": 0.0,
      "num_input_tokens_seen": 3725024,
      "step": 13305
    },
    {
      "epoch": 147.88888888888889,
      "grad_norm": 3.8974992122575713e-08,
      "learning_rate": 0.22524812667043007,
      "loss": 0.0,
      "num_input_tokens_seen": 3726416,
      "step": 13310
    },
    {
      "epoch": 147.94444444444446,
      "grad_norm": 2.874219831028313e-07,
      "learning_rate": 0.22519716414323177,
      "loss": 0.0,
      "num_input_tokens_seen": 3727840,
      "step": 13315
    },
    {
      "epoch": 148.0,
      "grad_norm": 1.217989193946778e-07,
      "learning_rate": 0.22514619001968567,
      "loss": 0.0,
      "num_input_tokens_seen": 3729264,
      "step": 13320
    },
    {
      "epoch": 148.05555555555554,
      "grad_norm": 3.388012714822253e-08,
      "learning_rate": 0.2250952043076528,
      "loss": 0.0,
      "num_input_tokens_seen": 3730656,
      "step": 13325
    },
    {
      "epoch": 148.11111111111111,
      "grad_norm": 1.4450809260324604e-07,
      "learning_rate": 0.2250442070149957,
      "loss": 0.0,
      "num_input_tokens_seen": 3732048,
      "step": 13330
    },
    {
      "epoch": 148.16666666666666,
      "grad_norm": 7.110109834229661e-08,
      "learning_rate": 0.22499319814957885,
      "loss": 0.0,
      "num_input_tokens_seen": 3733472,
      "step": 13335
    },
    {
      "epoch": 148.22222222222223,
      "grad_norm": 1.5476034320727194e-07,
      "learning_rate": 0.2249421777192684,
      "loss": 0.0,
      "num_input_tokens_seen": 3734848,
      "step": 13340
    },
    {
      "epoch": 148.27777777777777,
      "grad_norm": 6.128428253759921e-08,
      "learning_rate": 0.22489114573193236,
      "loss": 0.0,
      "num_input_tokens_seen": 3736288,
      "step": 13345
    },
    {
      "epoch": 148.33333333333334,
      "grad_norm": 7.984270666838711e-08,
      "learning_rate": 0.2248401021954405,
      "loss": 0.0,
      "num_input_tokens_seen": 3737712,
      "step": 13350
    },
    {
      "epoch": 148.38888888888889,
      "grad_norm": 5.032535455029574e-08,
      "learning_rate": 0.22478904711766443,
      "loss": 0.0,
      "num_input_tokens_seen": 3739120,
      "step": 13355
    },
    {
      "epoch": 148.44444444444446,
      "grad_norm": 7.412777591753184e-08,
      "learning_rate": 0.22473798050647734,
      "loss": 0.0,
      "num_input_tokens_seen": 3740560,
      "step": 13360
    },
    {
      "epoch": 148.5,
      "grad_norm": 1.5903553673979332e-07,
      "learning_rate": 0.22468690236975453,
      "loss": 0.0,
      "num_input_tokens_seen": 3741968,
      "step": 13365
    },
    {
      "epoch": 148.55555555555554,
      "grad_norm": 1.51896642819338e-07,
      "learning_rate": 0.22463581271537272,
      "loss": 0.0,
      "num_input_tokens_seen": 3743312,
      "step": 13370
    },
    {
      "epoch": 148.61111111111111,
      "grad_norm": 9.61409156730042e-08,
      "learning_rate": 0.22458471155121076,
      "loss": 0.0,
      "num_input_tokens_seen": 3744688,
      "step": 13375
    },
    {
      "epoch": 148.66666666666666,
      "grad_norm": 4.1119381677390265e-08,
      "learning_rate": 0.2245335988851489,
      "loss": 0.0,
      "num_input_tokens_seen": 3746080,
      "step": 13380
    },
    {
      "epoch": 148.72222222222223,
      "grad_norm": 1.428864493391302e-07,
      "learning_rate": 0.2244824747250695,
      "loss": 0.0,
      "num_input_tokens_seen": 3747504,
      "step": 13385
    },
    {
      "epoch": 148.77777777777777,
      "grad_norm": 3.520755598174219e-08,
      "learning_rate": 0.22443133907885646,
      "loss": 0.0,
      "num_input_tokens_seen": 3748928,
      "step": 13390
    },
    {
      "epoch": 148.83333333333334,
      "grad_norm": 9.798522881965255e-08,
      "learning_rate": 0.22438019195439557,
      "loss": 0.0,
      "num_input_tokens_seen": 3750320,
      "step": 13395
    },
    {
      "epoch": 148.88888888888889,
      "grad_norm": 1.589970111126604e-07,
      "learning_rate": 0.22432903335957435,
      "loss": 0.0,
      "num_input_tokens_seen": 3751728,
      "step": 13400
    },
    {
      "epoch": 148.88888888888889,
      "eval_loss": 1.2380867004394531,
      "eval_runtime": 1.1848,
      "eval_samples_per_second": 33.76,
      "eval_steps_per_second": 16.88,
      "num_input_tokens_seen": 3751728,
      "step": 13400
    },
    {
      "epoch": 148.94444444444446,
      "grad_norm": 1.529099478148055e-07,
      "learning_rate": 0.22427786330228214,
      "loss": 0.0,
      "num_input_tokens_seen": 3753136,
      "step": 13405
    },
    {
      "epoch": 149.0,
      "grad_norm": 1.0272093931007475e-07,
      "learning_rate": 0.22422668179040997,
      "loss": 0.0,
      "num_input_tokens_seen": 3754544,
      "step": 13410
    },
    {
      "epoch": 149.05555555555554,
      "grad_norm": 2.0054805816016597e-08,
      "learning_rate": 0.2241754888318507,
      "loss": 0.0,
      "num_input_tokens_seen": 3755920,
      "step": 13415
    },
    {
      "epoch": 149.11111111111111,
      "grad_norm": 1.6278484338272392e-07,
      "learning_rate": 0.22412428443449886,
      "loss": 0.0,
      "num_input_tokens_seen": 3757312,
      "step": 13420
    },
    {
      "epoch": 149.16666666666666,
      "grad_norm": 1.1007430344989189e-07,
      "learning_rate": 0.22407306860625087,
      "loss": 0.0,
      "num_input_tokens_seen": 3758720,
      "step": 13425
    },
    {
      "epoch": 149.22222222222223,
      "grad_norm": 5.972827921141288e-08,
      "learning_rate": 0.22402184135500483,
      "loss": 0.0,
      "num_input_tokens_seen": 3760144,
      "step": 13430
    },
    {
      "epoch": 149.27777777777777,
      "grad_norm": 6.390591522631439e-08,
      "learning_rate": 0.22397060268866067,
      "loss": 0.0,
      "num_input_tokens_seen": 3761504,
      "step": 13435
    },
    {
      "epoch": 149.33333333333334,
      "grad_norm": 6.653208828311108e-08,
      "learning_rate": 0.22391935261511994,
      "loss": 0.0,
      "num_input_tokens_seen": 3762912,
      "step": 13440
    },
    {
      "epoch": 149.38888888888889,
      "grad_norm": 3.8551799974584355e-08,
      "learning_rate": 0.22386809114228615,
      "loss": 0.0,
      "num_input_tokens_seen": 3764336,
      "step": 13445
    },
    {
      "epoch": 149.44444444444446,
      "grad_norm": 1.4572250961464306e-07,
      "learning_rate": 0.22381681827806446,
      "loss": 0.0,
      "num_input_tokens_seen": 3765744,
      "step": 13450
    },
    {
      "epoch": 149.5,
      "grad_norm": 4.481218596197323e-08,
      "learning_rate": 0.22376553403036173,
      "loss": 0.0,
      "num_input_tokens_seen": 3767104,
      "step": 13455
    },
    {
      "epoch": 149.55555555555554,
      "grad_norm": 3.2147873696430906e-08,
      "learning_rate": 0.22371423840708662,
      "loss": 0.0,
      "num_input_tokens_seen": 3768512,
      "step": 13460
    },
    {
      "epoch": 149.61111111111111,
      "grad_norm": 3.8047165418220175e-08,
      "learning_rate": 0.22366293141614962,
      "loss": 0.0,
      "num_input_tokens_seen": 3769920,
      "step": 13465
    },
    {
      "epoch": 149.66666666666666,
      "grad_norm": 7.212256036837061e-08,
      "learning_rate": 0.22361161306546287,
      "loss": 0.0,
      "num_input_tokens_seen": 3771328,
      "step": 13470
    },
    {
      "epoch": 149.72222222222223,
      "grad_norm": 4.866582514750917e-08,
      "learning_rate": 0.22356028336294037,
      "loss": 0.0,
      "num_input_tokens_seen": 3772720,
      "step": 13475
    },
    {
      "epoch": 149.77777777777777,
      "grad_norm": 6.925522200162959e-08,
      "learning_rate": 0.2235089423164977,
      "loss": 0.0,
      "num_input_tokens_seen": 3774144,
      "step": 13480
    },
    {
      "epoch": 149.83333333333334,
      "grad_norm": 1.9702918407915604e-08,
      "learning_rate": 0.22345758993405243,
      "loss": 0.0,
      "num_input_tokens_seen": 3775536,
      "step": 13485
    },
    {
      "epoch": 149.88888888888889,
      "grad_norm": 5.9087067683094574e-08,
      "learning_rate": 0.2234062262235236,
      "loss": 0.0,
      "num_input_tokens_seen": 3776912,
      "step": 13490
    },
    {
      "epoch": 149.94444444444446,
      "grad_norm": 7.084820907721223e-08,
      "learning_rate": 0.22335485119283222,
      "loss": 0.0,
      "num_input_tokens_seen": 3778304,
      "step": 13495
    },
    {
      "epoch": 150.0,
      "grad_norm": 7.483336617042369e-08,
      "learning_rate": 0.22330346484990093,
      "loss": 0.0,
      "num_input_tokens_seen": 3779696,
      "step": 13500
    },
    {
      "epoch": 150.05555555555554,
      "grad_norm": 4.4723901027055035e-08,
      "learning_rate": 0.22325206720265425,
      "loss": 0.0,
      "num_input_tokens_seen": 3781056,
      "step": 13505
    },
    {
      "epoch": 150.11111111111111,
      "grad_norm": 2.719704284004365e-08,
      "learning_rate": 0.2232006582590182,
      "loss": 0.0,
      "num_input_tokens_seen": 3782448,
      "step": 13510
    },
    {
      "epoch": 150.16666666666666,
      "grad_norm": 5.344473308355191e-08,
      "learning_rate": 0.22314923802692077,
      "loss": 0.0,
      "num_input_tokens_seen": 3783824,
      "step": 13515
    },
    {
      "epoch": 150.22222222222223,
      "grad_norm": 9.965054914573557e-08,
      "learning_rate": 0.22309780651429156,
      "loss": 0.0,
      "num_input_tokens_seen": 3785216,
      "step": 13520
    },
    {
      "epoch": 150.27777777777777,
      "grad_norm": 6.232453131360671e-08,
      "learning_rate": 0.22304636372906203,
      "loss": 0.0,
      "num_input_tokens_seen": 3786656,
      "step": 13525
    },
    {
      "epoch": 150.33333333333334,
      "grad_norm": 9.02602650398876e-08,
      "learning_rate": 0.22299490967916522,
      "loss": 0.0,
      "num_input_tokens_seen": 3788064,
      "step": 13530
    },
    {
      "epoch": 150.38888888888889,
      "grad_norm": 1.3120416042511351e-07,
      "learning_rate": 0.22294344437253602,
      "loss": 0.0,
      "num_input_tokens_seen": 3789488,
      "step": 13535
    },
    {
      "epoch": 150.44444444444446,
      "grad_norm": 4.8578691291822906e-08,
      "learning_rate": 0.22289196781711101,
      "loss": 0.0,
      "num_input_tokens_seen": 3790848,
      "step": 13540
    },
    {
      "epoch": 150.5,
      "grad_norm": 3.716204162174108e-07,
      "learning_rate": 0.2228404800208286,
      "loss": 0.0,
      "num_input_tokens_seen": 3792224,
      "step": 13545
    },
    {
      "epoch": 150.55555555555554,
      "grad_norm": 1.92164790746574e-07,
      "learning_rate": 0.22278898099162875,
      "loss": 0.0,
      "num_input_tokens_seen": 3793664,
      "step": 13550
    },
    {
      "epoch": 150.61111111111111,
      "grad_norm": 8.27219821530889e-08,
      "learning_rate": 0.22273747073745337,
      "loss": 0.0,
      "num_input_tokens_seen": 3795072,
      "step": 13555
    },
    {
      "epoch": 150.66666666666666,
      "grad_norm": 1.0814073192477736e-07,
      "learning_rate": 0.22268594926624588,
      "loss": 0.0,
      "num_input_tokens_seen": 3796464,
      "step": 13560
    },
    {
      "epoch": 150.72222222222223,
      "grad_norm": 6.886542536221896e-08,
      "learning_rate": 0.22263441658595162,
      "loss": 0.0,
      "num_input_tokens_seen": 3797904,
      "step": 13565
    },
    {
      "epoch": 150.77777777777777,
      "grad_norm": 4.4226759143839445e-08,
      "learning_rate": 0.2225828727045175,
      "loss": 0.0,
      "num_input_tokens_seen": 3799312,
      "step": 13570
    },
    {
      "epoch": 150.83333333333334,
      "grad_norm": 1.9023784147975675e-07,
      "learning_rate": 0.22253131762989228,
      "loss": 0.0,
      "num_input_tokens_seen": 3800736,
      "step": 13575
    },
    {
      "epoch": 150.88888888888889,
      "grad_norm": 1.035723471431993e-07,
      "learning_rate": 0.2224797513700264,
      "loss": 0.0,
      "num_input_tokens_seen": 3802144,
      "step": 13580
    },
    {
      "epoch": 150.94444444444446,
      "grad_norm": 1.5364702221631887e-07,
      "learning_rate": 0.22242817393287204,
      "loss": 0.0,
      "num_input_tokens_seen": 3803520,
      "step": 13585
    },
    {
      "epoch": 151.0,
      "grad_norm": 5.8274753911291555e-08,
      "learning_rate": 0.22237658532638305,
      "loss": 0.0,
      "num_input_tokens_seen": 3804896,
      "step": 13590
    },
    {
      "epoch": 151.05555555555554,
      "grad_norm": 3.299325967986988e-08,
      "learning_rate": 0.22232498555851513,
      "loss": 0.0,
      "num_input_tokens_seen": 3806304,
      "step": 13595
    },
    {
      "epoch": 151.11111111111111,
      "grad_norm": 1.3130912179804e-07,
      "learning_rate": 0.22227337463722546,
      "loss": 0.0,
      "num_input_tokens_seen": 3807744,
      "step": 13600
    },
    {
      "epoch": 151.11111111111111,
      "eval_loss": 1.2480953931808472,
      "eval_runtime": 1.1841,
      "eval_samples_per_second": 33.781,
      "eval_steps_per_second": 16.891,
      "num_input_tokens_seen": 3807744,
      "step": 13600
    },
    {
      "epoch": 151.16666666666666,
      "grad_norm": 1.0107962111760571e-07,
      "learning_rate": 0.2222217525704732,
      "loss": 0.0,
      "num_input_tokens_seen": 3809104,
      "step": 13605
    },
    {
      "epoch": 151.22222222222223,
      "grad_norm": 1.424047582077037e-07,
      "learning_rate": 0.22217011936621908,
      "loss": 0.0,
      "num_input_tokens_seen": 3810480,
      "step": 13610
    },
    {
      "epoch": 151.27777777777777,
      "grad_norm": 6.414534681198347e-08,
      "learning_rate": 0.22211847503242566,
      "loss": 0.0,
      "num_input_tokens_seen": 3811920,
      "step": 13615
    },
    {
      "epoch": 151.33333333333334,
      "grad_norm": 5.51533290149564e-08,
      "learning_rate": 0.22206681957705704,
      "loss": 0.0,
      "num_input_tokens_seen": 3813328,
      "step": 13620
    },
    {
      "epoch": 151.38888888888889,
      "grad_norm": 2.301553436723225e-08,
      "learning_rate": 0.2220151530080792,
      "loss": 0.0,
      "num_input_tokens_seen": 3814752,
      "step": 13625
    },
    {
      "epoch": 151.44444444444446,
      "grad_norm": 1.0928290095080229e-07,
      "learning_rate": 0.2219634753334598,
      "loss": 0.0,
      "num_input_tokens_seen": 3816096,
      "step": 13630
    },
    {
      "epoch": 151.5,
      "grad_norm": 2.0034072178987117e-08,
      "learning_rate": 0.22191178656116817,
      "loss": 0.0,
      "num_input_tokens_seen": 3817488,
      "step": 13635
    },
    {
      "epoch": 151.55555555555554,
      "grad_norm": 1.8333328455355513e-07,
      "learning_rate": 0.2218600866991753,
      "loss": 0.0,
      "num_input_tokens_seen": 3818880,
      "step": 13640
    },
    {
      "epoch": 151.61111111111111,
      "grad_norm": 8.149231689458247e-08,
      "learning_rate": 0.221808375755454,
      "loss": 0.0,
      "num_input_tokens_seen": 3820272,
      "step": 13645
    },
    {
      "epoch": 151.66666666666666,
      "grad_norm": 2.3042169061682216e-07,
      "learning_rate": 0.22175665373797881,
      "loss": 0.0,
      "num_input_tokens_seen": 3821664,
      "step": 13650
    },
    {
      "epoch": 151.72222222222223,
      "grad_norm": 1.7409443842097971e-07,
      "learning_rate": 0.22170492065472583,
      "loss": 0.0,
      "num_input_tokens_seen": 3823072,
      "step": 13655
    },
    {
      "epoch": 151.77777777777777,
      "grad_norm": 6.38723136603403e-08,
      "learning_rate": 0.221653176513673,
      "loss": 0.0,
      "num_input_tokens_seen": 3824464,
      "step": 13660
    },
    {
      "epoch": 151.83333333333334,
      "grad_norm": 1.5043704593153961e-07,
      "learning_rate": 0.2216014213227999,
      "loss": 0.0,
      "num_input_tokens_seen": 3825888,
      "step": 13665
    },
    {
      "epoch": 151.88888888888889,
      "grad_norm": 1.0619233847819487e-07,
      "learning_rate": 0.22154965509008784,
      "loss": 0.0,
      "num_input_tokens_seen": 3827280,
      "step": 13670
    },
    {
      "epoch": 151.94444444444446,
      "grad_norm": 1.3252947894670797e-07,
      "learning_rate": 0.2214978778235198,
      "loss": 0.0,
      "num_input_tokens_seen": 3828720,
      "step": 13675
    },
    {
      "epoch": 152.0,
      "grad_norm": 7.478395502857893e-08,
      "learning_rate": 0.2214460895310805,
      "loss": 0.0,
      "num_input_tokens_seen": 3830096,
      "step": 13680
    },
    {
      "epoch": 152.05555555555554,
      "grad_norm": 9.43068343417508e-08,
      "learning_rate": 0.22139429022075635,
      "loss": 0.0,
      "num_input_tokens_seen": 3831520,
      "step": 13685
    },
    {
      "epoch": 152.11111111111111,
      "grad_norm": 1.4274880300035875e-07,
      "learning_rate": 0.22134247990053546,
      "loss": 0.0,
      "num_input_tokens_seen": 3832864,
      "step": 13690
    },
    {
      "epoch": 152.16666666666666,
      "grad_norm": 1.2493615031416994e-07,
      "learning_rate": 0.2212906585784076,
      "loss": 0.0,
      "num_input_tokens_seen": 3834224,
      "step": 13695
    },
    {
      "epoch": 152.22222222222223,
      "grad_norm": 2.0121863997246692e-07,
      "learning_rate": 0.22123882626236432,
      "loss": 0.0,
      "num_input_tokens_seen": 3835680,
      "step": 13700
    },
    {
      "epoch": 152.27777777777777,
      "grad_norm": 2.505060514579327e-08,
      "learning_rate": 0.2211869829603988,
      "loss": 0.0,
      "num_input_tokens_seen": 3837072,
      "step": 13705
    },
    {
      "epoch": 152.33333333333334,
      "grad_norm": 7.734222151611903e-08,
      "learning_rate": 0.22113512868050592,
      "loss": 0.0,
      "num_input_tokens_seen": 3838480,
      "step": 13710
    },
    {
      "epoch": 152.38888888888889,
      "grad_norm": 1.9132269812871527e-07,
      "learning_rate": 0.2210832634306822,
      "loss": 0.0,
      "num_input_tokens_seen": 3839840,
      "step": 13715
    },
    {
      "epoch": 152.44444444444446,
      "grad_norm": 1.5578598322463222e-07,
      "learning_rate": 0.22103138721892598,
      "loss": 0.0,
      "num_input_tokens_seen": 3841200,
      "step": 13720
    },
    {
      "epoch": 152.5,
      "grad_norm": 3.8022967885353864e-08,
      "learning_rate": 0.22097950005323724,
      "loss": 0.0,
      "num_input_tokens_seen": 3842576,
      "step": 13725
    },
    {
      "epoch": 152.55555555555554,
      "grad_norm": 1.028395644198099e-07,
      "learning_rate": 0.22092760194161762,
      "loss": 0.0,
      "num_input_tokens_seen": 3843968,
      "step": 13730
    },
    {
      "epoch": 152.61111111111111,
      "grad_norm": 5.3522878573630805e-08,
      "learning_rate": 0.2208756928920704,
      "loss": 0.0,
      "num_input_tokens_seen": 3845376,
      "step": 13735
    },
    {
      "epoch": 152.66666666666666,
      "grad_norm": 7.714933758506959e-08,
      "learning_rate": 0.22082377291260072,
      "loss": 0.0,
      "num_input_tokens_seen": 3846816,
      "step": 13740
    },
    {
      "epoch": 152.72222222222223,
      "grad_norm": 7.54552047510515e-08,
      "learning_rate": 0.2207718420112152,
      "loss": 0.0,
      "num_input_tokens_seen": 3848208,
      "step": 13745
    },
    {
      "epoch": 152.77777777777777,
      "grad_norm": 1.0193524957458067e-07,
      "learning_rate": 0.22071990019592228,
      "loss": 0.0,
      "num_input_tokens_seen": 3849600,
      "step": 13750
    },
    {
      "epoch": 152.83333333333334,
      "grad_norm": 1.4095284939230623e-07,
      "learning_rate": 0.22066794747473198,
      "loss": 0.0,
      "num_input_tokens_seen": 3851040,
      "step": 13755
    },
    {
      "epoch": 152.88888888888889,
      "grad_norm": 1.226937058618205e-07,
      "learning_rate": 0.2206159838556562,
      "loss": 0.0,
      "num_input_tokens_seen": 3852432,
      "step": 13760
    },
    {
      "epoch": 152.94444444444446,
      "grad_norm": 9.259940014771928e-08,
      "learning_rate": 0.2205640093467082,
      "loss": 0.0,
      "num_input_tokens_seen": 3853872,
      "step": 13765
    },
    {
      "epoch": 153.0,
      "grad_norm": 6.512091488275473e-08,
      "learning_rate": 0.22051202395590322,
      "loss": 0.0,
      "num_input_tokens_seen": 3855264,
      "step": 13770
    },
    {
      "epoch": 153.05555555555554,
      "grad_norm": 1.1737591876226361e-07,
      "learning_rate": 0.22046002769125808,
      "loss": 0.0,
      "num_input_tokens_seen": 3856656,
      "step": 13775
    },
    {
      "epoch": 153.11111111111111,
      "grad_norm": 7.911482668987446e-08,
      "learning_rate": 0.2204080205607912,
      "loss": 0.0,
      "num_input_tokens_seen": 3858048,
      "step": 13780
    },
    {
      "epoch": 153.16666666666666,
      "grad_norm": 6.145805997448406e-08,
      "learning_rate": 0.22035600257252272,
      "loss": 0.0,
      "num_input_tokens_seen": 3859456,
      "step": 13785
    },
    {
      "epoch": 153.22222222222223,
      "grad_norm": 1.3827609279815078e-07,
      "learning_rate": 0.2203039737344745,
      "loss": 0.0,
      "num_input_tokens_seen": 3860848,
      "step": 13790
    },
    {
      "epoch": 153.27777777777777,
      "grad_norm": 6.835774257751837e-08,
      "learning_rate": 0.22025193405467003,
      "loss": 0.0,
      "num_input_tokens_seen": 3862304,
      "step": 13795
    },
    {
      "epoch": 153.33333333333334,
      "grad_norm": 2.785955111050953e-08,
      "learning_rate": 0.2201998835411345,
      "loss": 0.0,
      "num_input_tokens_seen": 3863664,
      "step": 13800
    },
    {
      "epoch": 153.33333333333334,
      "eval_loss": 1.2522083520889282,
      "eval_runtime": 1.1848,
      "eval_samples_per_second": 33.76,
      "eval_steps_per_second": 16.88,
      "num_input_tokens_seen": 3863664,
      "step": 13800
    },
    {
      "epoch": 153.38888888888889,
      "grad_norm": 9.007133172644899e-08,
      "learning_rate": 0.22014782220189474,
      "loss": 0.0,
      "num_input_tokens_seen": 3865024,
      "step": 13805
    },
    {
      "epoch": 153.44444444444446,
      "grad_norm": 2.8080455294343665e-08,
      "learning_rate": 0.2200957500449793,
      "loss": 0.0,
      "num_input_tokens_seen": 3866448,
      "step": 13810
    },
    {
      "epoch": 153.5,
      "grad_norm": 1.2793853443326952e-07,
      "learning_rate": 0.22004366707841827,
      "loss": 0.0,
      "num_input_tokens_seen": 3867856,
      "step": 13815
    },
    {
      "epoch": 153.55555555555554,
      "grad_norm": 8.896959258208881e-08,
      "learning_rate": 0.21999157331024358,
      "loss": 0.0,
      "num_input_tokens_seen": 3869232,
      "step": 13820
    },
    {
      "epoch": 153.61111111111111,
      "grad_norm": 5.866193930614827e-08,
      "learning_rate": 0.21993946874848871,
      "loss": 0.0,
      "num_input_tokens_seen": 3870640,
      "step": 13825
    },
    {
      "epoch": 153.66666666666666,
      "grad_norm": 9.735685324585575e-08,
      "learning_rate": 0.2198873534011888,
      "loss": 0.0,
      "num_input_tokens_seen": 3872032,
      "step": 13830
    },
    {
      "epoch": 153.72222222222223,
      "grad_norm": 7.015106717744857e-08,
      "learning_rate": 0.2198352272763808,
      "loss": 0.0,
      "num_input_tokens_seen": 3873424,
      "step": 13835
    },
    {
      "epoch": 153.77777777777777,
      "grad_norm": 8.699962705804865e-08,
      "learning_rate": 0.2197830903821031,
      "loss": 0.0,
      "num_input_tokens_seen": 3874800,
      "step": 13840
    },
    {
      "epoch": 153.83333333333334,
      "grad_norm": 5.256273283293922e-08,
      "learning_rate": 0.21973094272639598,
      "loss": 0.0,
      "num_input_tokens_seen": 3876176,
      "step": 13845
    },
    {
      "epoch": 153.88888888888889,
      "grad_norm": 3.00735734981572e-07,
      "learning_rate": 0.21967878431730117,
      "loss": 0.0,
      "num_input_tokens_seen": 3877584,
      "step": 13850
    },
    {
      "epoch": 153.94444444444446,
      "grad_norm": 1.657731161230913e-07,
      "learning_rate": 0.21962661516286217,
      "loss": 0.0,
      "num_input_tokens_seen": 3878944,
      "step": 13855
    },
    {
      "epoch": 154.0,
      "grad_norm": 2.2560024959261682e-08,
      "learning_rate": 0.21957443527112414,
      "loss": 0.0,
      "num_input_tokens_seen": 3880400,
      "step": 13860
    },
    {
      "epoch": 154.05555555555554,
      "grad_norm": 2.893264472447754e-08,
      "learning_rate": 0.21952224465013384,
      "loss": 0.0,
      "num_input_tokens_seen": 3881808,
      "step": 13865
    },
    {
      "epoch": 154.11111111111111,
      "grad_norm": 2.119939601641363e-08,
      "learning_rate": 0.21947004330793976,
      "loss": 0.0,
      "num_input_tokens_seen": 3883264,
      "step": 13870
    },
    {
      "epoch": 154.16666666666666,
      "grad_norm": 6.323953982700914e-08,
      "learning_rate": 0.21941783125259198,
      "loss": 0.0,
      "num_input_tokens_seen": 3884608,
      "step": 13875
    },
    {
      "epoch": 154.22222222222223,
      "grad_norm": 4.950123866365175e-08,
      "learning_rate": 0.21936560849214226,
      "loss": 0.0,
      "num_input_tokens_seen": 3885952,
      "step": 13880
    },
    {
      "epoch": 154.27777777777777,
      "grad_norm": 2.3076935917742958e-07,
      "learning_rate": 0.21931337503464404,
      "loss": 0.0,
      "num_input_tokens_seen": 3887360,
      "step": 13885
    },
    {
      "epoch": 154.33333333333334,
      "grad_norm": 4.153361032877001e-08,
      "learning_rate": 0.21926113088815233,
      "loss": 0.0,
      "num_input_tokens_seen": 3888736,
      "step": 13890
    },
    {
      "epoch": 154.38888888888889,
      "grad_norm": 4.0581014104645874e-08,
      "learning_rate": 0.2192088760607238,
      "loss": 0.0,
      "num_input_tokens_seen": 3890160,
      "step": 13895
    },
    {
      "epoch": 154.44444444444446,
      "grad_norm": 2.667845322434914e-08,
      "learning_rate": 0.2191566105604169,
      "loss": 0.0,
      "num_input_tokens_seen": 3891520,
      "step": 13900
    },
    {
      "epoch": 154.5,
      "grad_norm": 7.060504714218041e-08,
      "learning_rate": 0.21910433439529153,
      "loss": 0.0,
      "num_input_tokens_seen": 3892912,
      "step": 13905
    },
    {
      "epoch": 154.55555555555554,
      "grad_norm": 2.374425633888677e-08,
      "learning_rate": 0.2190520475734094,
      "loss": 0.0,
      "num_input_tokens_seen": 3894320,
      "step": 13910
    },
    {
      "epoch": 154.61111111111111,
      "grad_norm": 3.021150263293748e-08,
      "learning_rate": 0.2189997501028338,
      "loss": 0.0,
      "num_input_tokens_seen": 3895728,
      "step": 13915
    },
    {
      "epoch": 154.66666666666666,
      "grad_norm": 9.571584058676308e-08,
      "learning_rate": 0.2189474419916296,
      "loss": 0.0,
      "num_input_tokens_seen": 3897136,
      "step": 13920
    },
    {
      "epoch": 154.72222222222223,
      "grad_norm": 7.891946296467722e-08,
      "learning_rate": 0.21889512324786342,
      "loss": 0.0,
      "num_input_tokens_seen": 3898560,
      "step": 13925
    },
    {
      "epoch": 154.77777777777777,
      "grad_norm": 5.707377326302776e-08,
      "learning_rate": 0.21884279387960345,
      "loss": 0.0,
      "num_input_tokens_seen": 3899968,
      "step": 13930
    },
    {
      "epoch": 154.83333333333334,
      "grad_norm": 1.4070039355829067e-07,
      "learning_rate": 0.2187904538949195,
      "loss": 0.0,
      "num_input_tokens_seen": 3901360,
      "step": 13935
    },
    {
      "epoch": 154.88888888888889,
      "grad_norm": 1.423885720441831e-07,
      "learning_rate": 0.2187381033018831,
      "loss": 0.0,
      "num_input_tokens_seen": 3902752,
      "step": 13940
    },
    {
      "epoch": 154.94444444444446,
      "grad_norm": 1.9250760985300985e-08,
      "learning_rate": 0.2186857421085673,
      "loss": 0.0,
      "num_input_tokens_seen": 3904128,
      "step": 13945
    },
    {
      "epoch": 155.0,
      "grad_norm": 3.953697103042941e-08,
      "learning_rate": 0.21863337032304697,
      "loss": 0.0,
      "num_input_tokens_seen": 3905552,
      "step": 13950
    },
    {
      "epoch": 155.05555555555554,
      "grad_norm": 4.675404952081408e-08,
      "learning_rate": 0.21858098795339845,
      "loss": 0.0,
      "num_input_tokens_seen": 3906928,
      "step": 13955
    },
    {
      "epoch": 155.11111111111111,
      "grad_norm": 4.0434990467019816e-08,
      "learning_rate": 0.21852859500769975,
      "loss": 0.0,
      "num_input_tokens_seen": 3908256,
      "step": 13960
    },
    {
      "epoch": 155.16666666666666,
      "grad_norm": 2.6356024918072762e-08,
      "learning_rate": 0.21847619149403044,
      "loss": 0.0,
      "num_input_tokens_seen": 3909648,
      "step": 13965
    },
    {
      "epoch": 155.22222222222223,
      "grad_norm": 1.7460903833921293e-08,
      "learning_rate": 0.21842377742047195,
      "loss": 0.0,
      "num_input_tokens_seen": 3911088,
      "step": 13970
    },
    {
      "epoch": 155.27777777777777,
      "grad_norm": 1.7417299602584535e-07,
      "learning_rate": 0.21837135279510705,
      "loss": 0.0,
      "num_input_tokens_seen": 3912528,
      "step": 13975
    },
    {
      "epoch": 155.33333333333334,
      "grad_norm": 6.042615297019438e-08,
      "learning_rate": 0.21831891762602038,
      "loss": 0.0,
      "num_input_tokens_seen": 3913952,
      "step": 13980
    },
    {
      "epoch": 155.38888888888889,
      "grad_norm": 5.915605427730952e-08,
      "learning_rate": 0.21826647192129806,
      "loss": 0.0,
      "num_input_tokens_seen": 3915408,
      "step": 13985
    },
    {
      "epoch": 155.44444444444446,
      "grad_norm": 1.1919922826564289e-07,
      "learning_rate": 0.21821401568902787,
      "loss": 0.0,
      "num_input_tokens_seen": 3916768,
      "step": 13990
    },
    {
      "epoch": 155.5,
      "grad_norm": 1.3743134275046032e-07,
      "learning_rate": 0.21816154893729925,
      "loss": 0.0,
      "num_input_tokens_seen": 3918160,
      "step": 13995
    },
    {
      "epoch": 155.55555555555554,
      "grad_norm": 4.707460377062489e-08,
      "learning_rate": 0.2181090716742032,
      "loss": 0.0,
      "num_input_tokens_seen": 3919584,
      "step": 14000
    },
    {
      "epoch": 155.55555555555554,
      "eval_loss": 1.2714627981185913,
      "eval_runtime": 1.1841,
      "eval_samples_per_second": 33.78,
      "eval_steps_per_second": 16.89,
      "num_input_tokens_seen": 3919584,
      "step": 14000
    },
    {
      "epoch": 155.61111111111111,
      "grad_norm": 2.2592766768525507e-08,
      "learning_rate": 0.21805658390783236,
      "loss": 0.0,
      "num_input_tokens_seen": 3920992,
      "step": 14005
    },
    {
      "epoch": 155.66666666666666,
      "grad_norm": 7.06291132246406e-08,
      "learning_rate": 0.21800408564628107,
      "loss": 0.0,
      "num_input_tokens_seen": 3922384,
      "step": 14010
    },
    {
      "epoch": 155.72222222222223,
      "grad_norm": 2.2021461631993589e-07,
      "learning_rate": 0.21795157689764516,
      "loss": 0.0,
      "num_input_tokens_seen": 3923776,
      "step": 14015
    },
    {
      "epoch": 155.77777777777777,
      "grad_norm": 2.2909516417257692e-07,
      "learning_rate": 0.21789905767002216,
      "loss": 0.0,
      "num_input_tokens_seen": 3925184,
      "step": 14020
    },
    {
      "epoch": 155.83333333333334,
      "grad_norm": 2.2778205988061018e-08,
      "learning_rate": 0.2178465279715112,
      "loss": 0.0,
      "num_input_tokens_seen": 3926560,
      "step": 14025
    },
    {
      "epoch": 155.88888888888889,
      "grad_norm": 6.508969363494543e-08,
      "learning_rate": 0.21779398781021303,
      "loss": 0.0,
      "num_input_tokens_seen": 3927936,
      "step": 14030
    },
    {
      "epoch": 155.94444444444446,
      "grad_norm": 1.1008189915173716e-07,
      "learning_rate": 0.21774143719422998,
      "loss": 0.0,
      "num_input_tokens_seen": 3929344,
      "step": 14035
    },
    {
      "epoch": 156.0,
      "grad_norm": 1.202483588258474e-07,
      "learning_rate": 0.21768887613166601,
      "loss": 0.0,
      "num_input_tokens_seen": 3930784,
      "step": 14040
    },
    {
      "epoch": 156.05555555555554,
      "grad_norm": 7.274015700886594e-08,
      "learning_rate": 0.2176363046306267,
      "loss": 0.0,
      "num_input_tokens_seen": 3932176,
      "step": 14045
    },
    {
      "epoch": 156.11111111111111,
      "grad_norm": 9.714885784717353e-09,
      "learning_rate": 0.21758372269921925,
      "loss": 0.0,
      "num_input_tokens_seen": 3933552,
      "step": 14050
    },
    {
      "epoch": 156.16666666666666,
      "grad_norm": 3.303214413108435e-08,
      "learning_rate": 0.21753113034555244,
      "loss": 0.0,
      "num_input_tokens_seen": 3934912,
      "step": 14055
    },
    {
      "epoch": 156.22222222222223,
      "grad_norm": 6.492412296665862e-08,
      "learning_rate": 0.2174785275777367,
      "loss": 0.0,
      "num_input_tokens_seen": 3936272,
      "step": 14060
    },
    {
      "epoch": 156.27777777777777,
      "grad_norm": 1.8648799482434697e-07,
      "learning_rate": 0.21742591440388404,
      "loss": 0.0,
      "num_input_tokens_seen": 3937712,
      "step": 14065
    },
    {
      "epoch": 156.33333333333334,
      "grad_norm": 9.640684339728978e-08,
      "learning_rate": 0.21737329083210802,
      "loss": 0.0,
      "num_input_tokens_seen": 3939152,
      "step": 14070
    },
    {
      "epoch": 156.38888888888889,
      "grad_norm": 7.473017404890925e-08,
      "learning_rate": 0.2173206568705239,
      "loss": 0.0,
      "num_input_tokens_seen": 3940544,
      "step": 14075
    },
    {
      "epoch": 156.44444444444446,
      "grad_norm": 1.218054563878468e-07,
      "learning_rate": 0.2172680125272485,
      "loss": 0.0,
      "num_input_tokens_seen": 3941952,
      "step": 14080
    },
    {
      "epoch": 156.5,
      "grad_norm": 2.7956792436611977e-08,
      "learning_rate": 0.2172153578104002,
      "loss": 0.0,
      "num_input_tokens_seen": 3943376,
      "step": 14085
    },
    {
      "epoch": 156.55555555555554,
      "grad_norm": 4.526786412384354e-08,
      "learning_rate": 0.21716269272809902,
      "loss": 0.0,
      "num_input_tokens_seen": 3944768,
      "step": 14090
    },
    {
      "epoch": 156.61111111111111,
      "grad_norm": 6.495613291690461e-08,
      "learning_rate": 0.21711001728846666,
      "loss": 0.0,
      "num_input_tokens_seen": 3946160,
      "step": 14095
    },
    {
      "epoch": 156.66666666666666,
      "grad_norm": 4.3349764666800183e-08,
      "learning_rate": 0.21705733149962628,
      "loss": 0.0,
      "num_input_tokens_seen": 3947552,
      "step": 14100
    },
    {
      "epoch": 156.72222222222223,
      "grad_norm": 1.3831439105160825e-07,
      "learning_rate": 0.21700463536970263,
      "loss": 0.0,
      "num_input_tokens_seen": 3948992,
      "step": 14105
    },
    {
      "epoch": 156.77777777777777,
      "grad_norm": 7.751978614578547e-08,
      "learning_rate": 0.21695192890682222,
      "loss": 0.0,
      "num_input_tokens_seen": 3950368,
      "step": 14110
    },
    {
      "epoch": 156.83333333333334,
      "grad_norm": 6.672818386732615e-08,
      "learning_rate": 0.21689921211911298,
      "loss": 0.0,
      "num_input_tokens_seen": 3951824,
      "step": 14115
    },
    {
      "epoch": 156.88888888888889,
      "grad_norm": 1.3773322393717535e-07,
      "learning_rate": 0.21684648501470452,
      "loss": 0.0,
      "num_input_tokens_seen": 3953200,
      "step": 14120
    },
    {
      "epoch": 156.94444444444446,
      "grad_norm": 5.8835514238353426e-08,
      "learning_rate": 0.216793747601728,
      "loss": 0.0,
      "num_input_tokens_seen": 3954592,
      "step": 14125
    },
    {
      "epoch": 157.0,
      "grad_norm": 1.4218092303508456e-07,
      "learning_rate": 0.21674099988831627,
      "loss": 0.0,
      "num_input_tokens_seen": 3956000,
      "step": 14130
    },
    {
      "epoch": 157.05555555555554,
      "grad_norm": 6.268526675512476e-08,
      "learning_rate": 0.21668824188260363,
      "loss": 0.0,
      "num_input_tokens_seen": 3957360,
      "step": 14135
    },
    {
      "epoch": 157.11111111111111,
      "grad_norm": 6.93622226322077e-08,
      "learning_rate": 0.21663547359272606,
      "loss": 0.0,
      "num_input_tokens_seen": 3958736,
      "step": 14140
    },
    {
      "epoch": 157.16666666666666,
      "grad_norm": 1.559631215286572e-07,
      "learning_rate": 0.216582695026821,
      "loss": 0.0,
      "num_input_tokens_seen": 3960112,
      "step": 14145
    },
    {
      "epoch": 157.22222222222223,
      "grad_norm": 3.053881414416537e-08,
      "learning_rate": 0.21652990619302767,
      "loss": 0.0,
      "num_input_tokens_seen": 3961536,
      "step": 14150
    },
    {
      "epoch": 157.27777777777777,
      "grad_norm": 3.4939638737796486e-08,
      "learning_rate": 0.21647710709948673,
      "loss": 0.0,
      "num_input_tokens_seen": 3962944,
      "step": 14155
    },
    {
      "epoch": 157.33333333333334,
      "grad_norm": 7.836003845795858e-08,
      "learning_rate": 0.2164242977543405,
      "loss": 0.0,
      "num_input_tokens_seen": 3964368,
      "step": 14160
    },
    {
      "epoch": 157.38888888888889,
      "grad_norm": 1.0437035768973146e-07,
      "learning_rate": 0.21637147816573277,
      "loss": 0.0,
      "num_input_tokens_seen": 3965728,
      "step": 14165
    },
    {
      "epoch": 157.44444444444446,
      "grad_norm": 5.1801013256636e-08,
      "learning_rate": 0.21631864834180908,
      "loss": 0.0,
      "num_input_tokens_seen": 3967168,
      "step": 14170
    },
    {
      "epoch": 157.5,
      "grad_norm": 4.532374120458371e-08,
      "learning_rate": 0.21626580829071637,
      "loss": 0.0,
      "num_input_tokens_seen": 3968528,
      "step": 14175
    },
    {
      "epoch": 157.55555555555554,
      "grad_norm": 5.551158821504032e-08,
      "learning_rate": 0.21621295802060328,
      "loss": 0.0,
      "num_input_tokens_seen": 3969952,
      "step": 14180
    },
    {
      "epoch": 157.61111111111111,
      "grad_norm": 1.177972777099967e-07,
      "learning_rate": 0.21616009753961996,
      "loss": 0.0,
      "num_input_tokens_seen": 3971328,
      "step": 14185
    },
    {
      "epoch": 157.66666666666666,
      "grad_norm": 5.773213729298732e-08,
      "learning_rate": 0.2161072268559182,
      "loss": 0.0,
      "num_input_tokens_seen": 3972752,
      "step": 14190
    },
    {
      "epoch": 157.72222222222223,
      "grad_norm": 5.677693692973662e-08,
      "learning_rate": 0.21605434597765133,
      "loss": 0.0,
      "num_input_tokens_seen": 3974144,
      "step": 14195
    },
    {
      "epoch": 157.77777777777777,
      "grad_norm": 1.1248992137780078e-07,
      "learning_rate": 0.21600145491297418,
      "loss": 0.0,
      "num_input_tokens_seen": 3975568,
      "step": 14200
    },
    {
      "epoch": 157.77777777777777,
      "eval_loss": 1.2779912948608398,
      "eval_runtime": 1.1926,
      "eval_samples_per_second": 33.539,
      "eval_steps_per_second": 16.77,
      "num_input_tokens_seen": 3975568,
      "step": 14200
    },
    {
      "epoch": 157.83333333333334,
      "grad_norm": 1.545325005736231e-07,
      "learning_rate": 0.21594855367004326,
      "loss": 0.0,
      "num_input_tokens_seen": 3977008,
      "step": 14205
    },
    {
      "epoch": 157.88888888888889,
      "grad_norm": 1.183193063525323e-07,
      "learning_rate": 0.21589564225701663,
      "loss": 0.0,
      "num_input_tokens_seen": 3978432,
      "step": 14210
    },
    {
      "epoch": 157.94444444444446,
      "grad_norm": 9.895973818174753e-09,
      "learning_rate": 0.21584272068205385,
      "loss": 0.0,
      "num_input_tokens_seen": 3979840,
      "step": 14215
    },
    {
      "epoch": 158.0,
      "grad_norm": 1.049703044486705e-07,
      "learning_rate": 0.2157897889533161,
      "loss": 0.0,
      "num_input_tokens_seen": 3981216,
      "step": 14220
    },
    {
      "epoch": 158.05555555555554,
      "grad_norm": 3.1834009206477276e-08,
      "learning_rate": 0.21573684707896612,
      "loss": 0.0,
      "num_input_tokens_seen": 3982608,
      "step": 14225
    },
    {
      "epoch": 158.11111111111111,
      "grad_norm": 5.637069477870682e-08,
      "learning_rate": 0.21568389506716826,
      "loss": 0.0,
      "num_input_tokens_seen": 3983968,
      "step": 14230
    },
    {
      "epoch": 158.16666666666666,
      "grad_norm": 3.847797458433888e-08,
      "learning_rate": 0.21563093292608831,
      "loss": 0.0,
      "num_input_tokens_seen": 3985328,
      "step": 14235
    },
    {
      "epoch": 158.22222222222223,
      "grad_norm": 1.051414333375078e-08,
      "learning_rate": 0.21557796066389376,
      "loss": 0.0,
      "num_input_tokens_seen": 3986720,
      "step": 14240
    },
    {
      "epoch": 158.27777777777777,
      "grad_norm": 1.943580230090447e-08,
      "learning_rate": 0.21552497828875353,
      "loss": 0.0,
      "num_input_tokens_seen": 3988128,
      "step": 14245
    },
    {
      "epoch": 158.33333333333334,
      "grad_norm": 1.0313582521348508e-07,
      "learning_rate": 0.21547198580883828,
      "loss": 0.0,
      "num_input_tokens_seen": 3989536,
      "step": 14250
    },
    {
      "epoch": 158.38888888888889,
      "grad_norm": 2.295739243152184e-08,
      "learning_rate": 0.21541898323232,
      "loss": 0.0,
      "num_input_tokens_seen": 3990944,
      "step": 14255
    },
    {
      "epoch": 158.44444444444446,
      "grad_norm": 6.811976760445759e-08,
      "learning_rate": 0.2153659705673724,
      "loss": 0.0,
      "num_input_tokens_seen": 3992368,
      "step": 14260
    },
    {
      "epoch": 158.5,
      "grad_norm": 1.503957065551731e-07,
      "learning_rate": 0.2153129478221707,
      "loss": 0.0,
      "num_input_tokens_seen": 3993760,
      "step": 14265
    },
    {
      "epoch": 158.55555555555554,
      "grad_norm": 8.045800825584593e-08,
      "learning_rate": 0.21525991500489164,
      "loss": 0.0,
      "num_input_tokens_seen": 3995152,
      "step": 14270
    },
    {
      "epoch": 158.61111111111111,
      "grad_norm": 2.5364876421463123e-08,
      "learning_rate": 0.21520687212371362,
      "loss": 0.0,
      "num_input_tokens_seen": 3996560,
      "step": 14275
    },
    {
      "epoch": 158.66666666666666,
      "grad_norm": 3.201081355541646e-08,
      "learning_rate": 0.21515381918681648,
      "loss": 0.0,
      "num_input_tokens_seen": 3998016,
      "step": 14280
    },
    {
      "epoch": 158.72222222222223,
      "grad_norm": 1.3719646574372746e-07,
      "learning_rate": 0.21510075620238167,
      "loss": 0.0,
      "num_input_tokens_seen": 3999408,
      "step": 14285
    },
    {
      "epoch": 158.77777777777777,
      "grad_norm": 2.2470693750165083e-07,
      "learning_rate": 0.21504768317859208,
      "loss": 0.0,
      "num_input_tokens_seen": 4000832,
      "step": 14290
    },
    {
      "epoch": 158.83333333333334,
      "grad_norm": 2.080055239161993e-08,
      "learning_rate": 0.2149946001236323,
      "loss": 0.0,
      "num_input_tokens_seen": 4002224,
      "step": 14295
    },
    {
      "epoch": 158.88888888888889,
      "grad_norm": 3.9964362485989113e-08,
      "learning_rate": 0.21494150704568848,
      "loss": 0.0,
      "num_input_tokens_seen": 4003632,
      "step": 14300
    },
    {
      "epoch": 158.94444444444446,
      "grad_norm": 6.445945643918094e-08,
      "learning_rate": 0.21488840395294811,
      "loss": 0.0,
      "num_input_tokens_seen": 4005056,
      "step": 14305
    },
    {
      "epoch": 159.0,
      "grad_norm": 2.2150606682203033e-08,
      "learning_rate": 0.21483529085360042,
      "loss": 0.0,
      "num_input_tokens_seen": 4006448,
      "step": 14310
    },
    {
      "epoch": 159.05555555555554,
      "grad_norm": 9.206110007653479e-08,
      "learning_rate": 0.2147821677558361,
      "loss": 0.0,
      "num_input_tokens_seen": 4007840,
      "step": 14315
    },
    {
      "epoch": 159.11111111111111,
      "grad_norm": 8.773947790530201e-09,
      "learning_rate": 0.2147290346678475,
      "loss": 0.0,
      "num_input_tokens_seen": 4009248,
      "step": 14320
    },
    {
      "epoch": 159.16666666666666,
      "grad_norm": 2.6967493127472153e-08,
      "learning_rate": 0.21467589159782827,
      "loss": 0.0,
      "num_input_tokens_seen": 4010640,
      "step": 14325
    },
    {
      "epoch": 159.22222222222223,
      "grad_norm": 3.582972496474213e-08,
      "learning_rate": 0.21462273855397374,
      "loss": 0.0,
      "num_input_tokens_seen": 4012032,
      "step": 14330
    },
    {
      "epoch": 159.27777777777777,
      "grad_norm": 8.664835604577092e-08,
      "learning_rate": 0.21456957554448083,
      "loss": 0.0,
      "num_input_tokens_seen": 4013456,
      "step": 14335
    },
    {
      "epoch": 159.33333333333334,
      "grad_norm": 1.440186849777092e-07,
      "learning_rate": 0.21451640257754795,
      "loss": 0.0,
      "num_input_tokens_seen": 4014816,
      "step": 14340
    },
    {
      "epoch": 159.38888888888889,
      "grad_norm": 4.802893371902428e-08,
      "learning_rate": 0.21446321966137508,
      "loss": 0.0,
      "num_input_tokens_seen": 4016192,
      "step": 14345
    },
    {
      "epoch": 159.44444444444446,
      "grad_norm": 2.1103124581145494e-08,
      "learning_rate": 0.21441002680416354,
      "loss": 0.0,
      "num_input_tokens_seen": 4017600,
      "step": 14350
    },
    {
      "epoch": 159.5,
      "grad_norm": 2.788003961029517e-08,
      "learning_rate": 0.21435682401411654,
      "loss": 0.0,
      "num_input_tokens_seen": 4019008,
      "step": 14355
    },
    {
      "epoch": 159.55555555555554,
      "grad_norm": 3.159112793582608e-08,
      "learning_rate": 0.2143036112994385,
      "loss": 0.0,
      "num_input_tokens_seen": 4020416,
      "step": 14360
    },
    {
      "epoch": 159.61111111111111,
      "grad_norm": 2.5706251349788545e-08,
      "learning_rate": 0.21425038866833548,
      "loss": 0.0,
      "num_input_tokens_seen": 4021808,
      "step": 14365
    },
    {
      "epoch": 159.66666666666666,
      "grad_norm": 7.039343330461634e-08,
      "learning_rate": 0.21419715612901508,
      "loss": 0.0,
      "num_input_tokens_seen": 4023216,
      "step": 14370
    },
    {
      "epoch": 159.72222222222223,
      "grad_norm": 6.924140905084641e-08,
      "learning_rate": 0.21414391368968652,
      "loss": 0.0,
      "num_input_tokens_seen": 4024608,
      "step": 14375
    },
    {
      "epoch": 159.77777777777777,
      "grad_norm": 2.6079380432975086e-08,
      "learning_rate": 0.21409066135856034,
      "loss": 0.0,
      "num_input_tokens_seen": 4026032,
      "step": 14380
    },
    {
      "epoch": 159.83333333333334,
      "grad_norm": 1.629720891571651e-08,
      "learning_rate": 0.21403739914384878,
      "loss": 0.0,
      "num_input_tokens_seen": 4027408,
      "step": 14385
    },
    {
      "epoch": 159.88888888888889,
      "grad_norm": 8.338837886867623e-08,
      "learning_rate": 0.21398412705376554,
      "loss": 0.0,
      "num_input_tokens_seen": 4028800,
      "step": 14390
    },
    {
      "epoch": 159.94444444444446,
      "grad_norm": 1.06669531874104e-07,
      "learning_rate": 0.2139308450965258,
      "loss": 0.0,
      "num_input_tokens_seen": 4030208,
      "step": 14395
    },
    {
      "epoch": 160.0,
      "grad_norm": 4.715409929190173e-08,
      "learning_rate": 0.21387755328034638,
      "loss": 0.0,
      "num_input_tokens_seen": 4031632,
      "step": 14400
    },
    {
      "epoch": 160.0,
      "eval_loss": 1.3001282215118408,
      "eval_runtime": 1.1802,
      "eval_samples_per_second": 33.891,
      "eval_steps_per_second": 16.946,
      "num_input_tokens_seen": 4031632,
      "step": 14400
    },
    {
      "epoch": 160.05555555555554,
      "grad_norm": 3.902930245658354e-08,
      "learning_rate": 0.2138242516134455,
      "loss": 0.0,
      "num_input_tokens_seen": 4032992,
      "step": 14405
    },
    {
      "epoch": 160.11111111111111,
      "grad_norm": 2.0158532265668327e-07,
      "learning_rate": 0.2137709401040429,
      "loss": 0.0,
      "num_input_tokens_seen": 4034416,
      "step": 14410
    },
    {
      "epoch": 160.16666666666666,
      "grad_norm": 2.4870123738196526e-08,
      "learning_rate": 0.21371761876036,
      "loss": 0.0,
      "num_input_tokens_seen": 4035808,
      "step": 14415
    },
    {
      "epoch": 160.22222222222223,
      "grad_norm": 5.9083127723624784e-08,
      "learning_rate": 0.21366428759061956,
      "loss": 0.0,
      "num_input_tokens_seen": 4037184,
      "step": 14420
    },
    {
      "epoch": 160.27777777777777,
      "grad_norm": 5.098076272247454e-08,
      "learning_rate": 0.2136109466030459,
      "loss": 0.0,
      "num_input_tokens_seen": 4038608,
      "step": 14425
    },
    {
      "epoch": 160.33333333333334,
      "grad_norm": 6.101541316638759e-08,
      "learning_rate": 0.2135575958058649,
      "loss": 0.0,
      "num_input_tokens_seen": 4040016,
      "step": 14430
    },
    {
      "epoch": 160.38888888888889,
      "grad_norm": 8.660457240239339e-08,
      "learning_rate": 0.2135042352073039,
      "loss": 0.0,
      "num_input_tokens_seen": 4041408,
      "step": 14435
    },
    {
      "epoch": 160.44444444444446,
      "grad_norm": 4.1779042447842585e-08,
      "learning_rate": 0.2134508648155918,
      "loss": 0.0,
      "num_input_tokens_seen": 4042784,
      "step": 14440
    },
    {
      "epoch": 160.5,
      "grad_norm": 1.8322845463103477e-08,
      "learning_rate": 0.213397484638959,
      "loss": 0.0,
      "num_input_tokens_seen": 4044160,
      "step": 14445
    },
    {
      "epoch": 160.55555555555554,
      "grad_norm": 6.342784075741292e-08,
      "learning_rate": 0.21334409468563728,
      "loss": 0.0,
      "num_input_tokens_seen": 4045520,
      "step": 14450
    },
    {
      "epoch": 160.61111111111111,
      "grad_norm": 5.516614365319583e-08,
      "learning_rate": 0.2132906949638602,
      "loss": 0.0,
      "num_input_tokens_seen": 4046928,
      "step": 14455
    },
    {
      "epoch": 160.66666666666666,
      "grad_norm": 3.280846527786707e-08,
      "learning_rate": 0.21323728548186255,
      "loss": 0.0,
      "num_input_tokens_seen": 4048304,
      "step": 14460
    },
    {
      "epoch": 160.72222222222223,
      "grad_norm": 1.2575355867738836e-08,
      "learning_rate": 0.21318386624788088,
      "loss": 0.0,
      "num_input_tokens_seen": 4049728,
      "step": 14465
    },
    {
      "epoch": 160.77777777777777,
      "grad_norm": 4.7632365607341853e-08,
      "learning_rate": 0.21313043727015288,
      "loss": 0.0,
      "num_input_tokens_seen": 4051136,
      "step": 14470
    },
    {
      "epoch": 160.83333333333334,
      "grad_norm": 1.158095557229899e-07,
      "learning_rate": 0.2130769985569182,
      "loss": 0.0,
      "num_input_tokens_seen": 4052544,
      "step": 14475
    },
    {
      "epoch": 160.88888888888889,
      "grad_norm": 7.809767055277916e-09,
      "learning_rate": 0.21302355011641766,
      "loss": 0.0,
      "num_input_tokens_seen": 4054000,
      "step": 14480
    },
    {
      "epoch": 160.94444444444446,
      "grad_norm": 2.919266250955843e-08,
      "learning_rate": 0.21297009195689365,
      "loss": 0.0,
      "num_input_tokens_seen": 4055408,
      "step": 14485
    },
    {
      "epoch": 161.0,
      "grad_norm": 3.913333301852617e-08,
      "learning_rate": 0.21291662408659015,
      "loss": 0.0,
      "num_input_tokens_seen": 4056816,
      "step": 14490
    },
    {
      "epoch": 161.05555555555554,
      "grad_norm": 2.6532473995644068e-08,
      "learning_rate": 0.21286314651375254,
      "loss": 0.0,
      "num_input_tokens_seen": 4058224,
      "step": 14495
    },
    {
      "epoch": 161.11111111111111,
      "grad_norm": 3.4279562299843747e-08,
      "learning_rate": 0.2128096592466278,
      "loss": 0.0,
      "num_input_tokens_seen": 4059584,
      "step": 14500
    },
    {
      "epoch": 161.16666666666666,
      "grad_norm": 2.2192903514905993e-08,
      "learning_rate": 0.21275616229346428,
      "loss": 0.0,
      "num_input_tokens_seen": 4061008,
      "step": 14505
    },
    {
      "epoch": 161.22222222222223,
      "grad_norm": 7.936474588632336e-08,
      "learning_rate": 0.21270265566251184,
      "loss": 0.0,
      "num_input_tokens_seen": 4062448,
      "step": 14510
    },
    {
      "epoch": 161.27777777777777,
      "grad_norm": 6.062661128680702e-08,
      "learning_rate": 0.21264913936202193,
      "loss": 0.0,
      "num_input_tokens_seen": 4063824,
      "step": 14515
    },
    {
      "epoch": 161.33333333333334,
      "grad_norm": 7.260360490590756e-08,
      "learning_rate": 0.2125956134002475,
      "loss": 0.0,
      "num_input_tokens_seen": 4065248,
      "step": 14520
    },
    {
      "epoch": 161.38888888888889,
      "grad_norm": 6.024067999987892e-08,
      "learning_rate": 0.2125420777854428,
      "loss": 0.0,
      "num_input_tokens_seen": 4066624,
      "step": 14525
    },
    {
      "epoch": 161.44444444444446,
      "grad_norm": 3.967523909409465e-08,
      "learning_rate": 0.21248853252586372,
      "loss": 0.0,
      "num_input_tokens_seen": 4068048,
      "step": 14530
    },
    {
      "epoch": 161.5,
      "grad_norm": 5.535567382253248e-08,
      "learning_rate": 0.21243497762976774,
      "loss": 0.0,
      "num_input_tokens_seen": 4069472,
      "step": 14535
    },
    {
      "epoch": 161.55555555555554,
      "grad_norm": 2.4813250121269448e-08,
      "learning_rate": 0.21238141310541356,
      "loss": 0.0,
      "num_input_tokens_seen": 4070848,
      "step": 14540
    },
    {
      "epoch": 161.61111111111111,
      "grad_norm": 4.754724614031147e-08,
      "learning_rate": 0.21232783896106153,
      "loss": 0.0,
      "num_input_tokens_seen": 4072256,
      "step": 14545
    },
    {
      "epoch": 161.66666666666666,
      "grad_norm": 6.250262885032498e-08,
      "learning_rate": 0.21227425520497345,
      "loss": 0.0,
      "num_input_tokens_seen": 4073632,
      "step": 14550
    },
    {
      "epoch": 161.72222222222223,
      "grad_norm": 4.346664539411904e-08,
      "learning_rate": 0.2122206618454127,
      "loss": 0.0,
      "num_input_tokens_seen": 4075024,
      "step": 14555
    },
    {
      "epoch": 161.77777777777777,
      "grad_norm": 2.3257147319100113e-08,
      "learning_rate": 0.2121670588906439,
      "loss": 0.0,
      "num_input_tokens_seen": 4076400,
      "step": 14560
    },
    {
      "epoch": 161.83333333333334,
      "grad_norm": 2.7263727275794736e-08,
      "learning_rate": 0.21211344634893345,
      "loss": 0.0,
      "num_input_tokens_seen": 4077840,
      "step": 14565
    },
    {
      "epoch": 161.88888888888889,
      "grad_norm": 1.1067185567981142e-07,
      "learning_rate": 0.21205982422854897,
      "loss": 0.0,
      "num_input_tokens_seen": 4079248,
      "step": 14570
    },
    {
      "epoch": 161.94444444444446,
      "grad_norm": 2.640670793141453e-08,
      "learning_rate": 0.21200619253775974,
      "loss": 0.0,
      "num_input_tokens_seen": 4080656,
      "step": 14575
    },
    {
      "epoch": 162.0,
      "grad_norm": 5.6444932283739035e-08,
      "learning_rate": 0.21195255128483637,
      "loss": 0.0,
      "num_input_tokens_seen": 4082032,
      "step": 14580
    },
    {
      "epoch": 162.05555555555554,
      "grad_norm": 1.058327647740498e-08,
      "learning_rate": 0.21189890047805102,
      "loss": 0.0,
      "num_input_tokens_seen": 4083424,
      "step": 14585
    },
    {
      "epoch": 162.11111111111111,
      "grad_norm": 2.4751006577616863e-08,
      "learning_rate": 0.21184524012567735,
      "loss": 0.0,
      "num_input_tokens_seen": 4084768,
      "step": 14590
    },
    {
      "epoch": 162.16666666666666,
      "grad_norm": 1.8503929055668777e-08,
      "learning_rate": 0.2117915702359905,
      "loss": 0.0,
      "num_input_tokens_seen": 4086160,
      "step": 14595
    },
    {
      "epoch": 162.22222222222223,
      "grad_norm": 1.569939378498475e-08,
      "learning_rate": 0.211737890817267,
      "loss": 0.0,
      "num_input_tokens_seen": 4087632,
      "step": 14600
    },
    {
      "epoch": 162.22222222222223,
      "eval_loss": 1.3049266338348389,
      "eval_runtime": 1.1865,
      "eval_samples_per_second": 33.711,
      "eval_steps_per_second": 16.856,
      "num_input_tokens_seen": 4087632,
      "step": 14600
    },
    {
      "epoch": 162.27777777777777,
      "grad_norm": 3.75815432107629e-08,
      "learning_rate": 0.21168420187778483,
      "loss": 0.0,
      "num_input_tokens_seen": 4089008,
      "step": 14605
    },
    {
      "epoch": 162.33333333333334,
      "grad_norm": 2.1373041647620994e-07,
      "learning_rate": 0.21163050342582362,
      "loss": 0.0,
      "num_input_tokens_seen": 4090416,
      "step": 14610
    },
    {
      "epoch": 162.38888888888889,
      "grad_norm": 7.362156395629427e-08,
      "learning_rate": 0.21157679546966426,
      "loss": 0.0,
      "num_input_tokens_seen": 4091824,
      "step": 14615
    },
    {
      "epoch": 162.44444444444446,
      "grad_norm": 1.4176546159205827e-08,
      "learning_rate": 0.2115230780175892,
      "loss": 0.0,
      "num_input_tokens_seen": 4093248,
      "step": 14620
    },
    {
      "epoch": 162.5,
      "grad_norm": 5.847652317925167e-08,
      "learning_rate": 0.21146935107788237,
      "loss": 0.0,
      "num_input_tokens_seen": 4094672,
      "step": 14625
    },
    {
      "epoch": 162.55555555555554,
      "grad_norm": 1.2826133399812534e-07,
      "learning_rate": 0.21141561465882916,
      "loss": 0.0,
      "num_input_tokens_seen": 4096096,
      "step": 14630
    },
    {
      "epoch": 162.61111111111111,
      "grad_norm": 4.205381642918837e-08,
      "learning_rate": 0.21136186876871635,
      "loss": 0.0,
      "num_input_tokens_seen": 4097456,
      "step": 14635
    },
    {
      "epoch": 162.66666666666666,
      "grad_norm": 1.0175473619256081e-07,
      "learning_rate": 0.21130811341583225,
      "loss": 0.0,
      "num_input_tokens_seen": 4098848,
      "step": 14640
    },
    {
      "epoch": 162.72222222222223,
      "grad_norm": 3.401120451940187e-08,
      "learning_rate": 0.21125434860846667,
      "loss": 0.0,
      "num_input_tokens_seen": 4100272,
      "step": 14645
    },
    {
      "epoch": 162.77777777777777,
      "grad_norm": 9.883964935397671e-08,
      "learning_rate": 0.2112005743549107,
      "loss": 0.0,
      "num_input_tokens_seen": 4101696,
      "step": 14650
    },
    {
      "epoch": 162.83333333333334,
      "grad_norm": 1.1018826029385309e-07,
      "learning_rate": 0.21114679066345707,
      "loss": 0.0,
      "num_input_tokens_seen": 4103120,
      "step": 14655
    },
    {
      "epoch": 162.88888888888889,
      "grad_norm": 3.0489161417790456e-08,
      "learning_rate": 0.21109299754239993,
      "loss": 0.0,
      "num_input_tokens_seen": 4104512,
      "step": 14660
    },
    {
      "epoch": 162.94444444444446,
      "grad_norm": 1.4538151127396759e-08,
      "learning_rate": 0.21103919500003482,
      "loss": 0.0,
      "num_input_tokens_seen": 4105920,
      "step": 14665
    },
    {
      "epoch": 163.0,
      "grad_norm": 3.7897439852940806e-08,
      "learning_rate": 0.21098538304465872,
      "loss": 0.0,
      "num_input_tokens_seen": 4107312,
      "step": 14670
    },
    {
      "epoch": 163.05555555555554,
      "grad_norm": 1.1165602131768537e-07,
      "learning_rate": 0.2109315616845702,
      "loss": 0.0,
      "num_input_tokens_seen": 4108768,
      "step": 14675
    },
    {
      "epoch": 163.11111111111111,
      "grad_norm": 8.144697005718626e-08,
      "learning_rate": 0.21087773092806925,
      "loss": 0.0,
      "num_input_tokens_seen": 4110144,
      "step": 14680
    },
    {
      "epoch": 163.16666666666666,
      "grad_norm": 3.950985671963281e-08,
      "learning_rate": 0.21082389078345704,
      "loss": 0.0,
      "num_input_tokens_seen": 4111520,
      "step": 14685
    },
    {
      "epoch": 163.22222222222223,
      "grad_norm": 5.31909947198983e-08,
      "learning_rate": 0.2107700412590365,
      "loss": 0.0,
      "num_input_tokens_seen": 4112944,
      "step": 14690
    },
    {
      "epoch": 163.27777777777777,
      "grad_norm": 6.353555903615415e-08,
      "learning_rate": 0.210716182363112,
      "loss": 0.0,
      "num_input_tokens_seen": 4114384,
      "step": 14695
    },
    {
      "epoch": 163.33333333333334,
      "grad_norm": 4.5416435057177296e-08,
      "learning_rate": 0.2106623141039891,
      "loss": 0.0,
      "num_input_tokens_seen": 4115776,
      "step": 14700
    },
    {
      "epoch": 163.38888888888889,
      "grad_norm": 3.682688287653946e-08,
      "learning_rate": 0.21060843648997507,
      "loss": 0.0,
      "num_input_tokens_seen": 4117152,
      "step": 14705
    },
    {
      "epoch": 163.44444444444446,
      "grad_norm": 6.40119779404813e-08,
      "learning_rate": 0.21055454952937844,
      "loss": 0.0,
      "num_input_tokens_seen": 4118576,
      "step": 14710
    },
    {
      "epoch": 163.5,
      "grad_norm": 7.004383917319501e-08,
      "learning_rate": 0.21050065323050937,
      "loss": 0.0,
      "num_input_tokens_seen": 4119968,
      "step": 14715
    },
    {
      "epoch": 163.55555555555554,
      "grad_norm": 6.486494186219716e-08,
      "learning_rate": 0.21044674760167928,
      "loss": 0.0,
      "num_input_tokens_seen": 4121328,
      "step": 14720
    },
    {
      "epoch": 163.61111111111111,
      "grad_norm": 1.5867017921777915e-08,
      "learning_rate": 0.210392832651201,
      "loss": 0.0,
      "num_input_tokens_seen": 4122736,
      "step": 14725
    },
    {
      "epoch": 163.66666666666666,
      "grad_norm": 4.8995570267607036e-08,
      "learning_rate": 0.210338908387389,
      "loss": 0.0,
      "num_input_tokens_seen": 4124080,
      "step": 14730
    },
    {
      "epoch": 163.72222222222223,
      "grad_norm": 1.053535392259164e-08,
      "learning_rate": 0.21028497481855912,
      "loss": 0.0,
      "num_input_tokens_seen": 4125488,
      "step": 14735
    },
    {
      "epoch": 163.77777777777777,
      "grad_norm": 6.852699385717642e-08,
      "learning_rate": 0.21023103195302847,
      "loss": 0.0,
      "num_input_tokens_seen": 4126896,
      "step": 14740
    },
    {
      "epoch": 163.83333333333334,
      "grad_norm": 1.3050738800757244e-07,
      "learning_rate": 0.21017707979911582,
      "loss": 0.0,
      "num_input_tokens_seen": 4128304,
      "step": 14745
    },
    {
      "epoch": 163.88888888888889,
      "grad_norm": 2.918905650517445e-08,
      "learning_rate": 0.21012311836514122,
      "loss": 0.0,
      "num_input_tokens_seen": 4129680,
      "step": 14750
    },
    {
      "epoch": 163.94444444444446,
      "grad_norm": 7.059342976845073e-08,
      "learning_rate": 0.21006914765942622,
      "loss": 0.0,
      "num_input_tokens_seen": 4131088,
      "step": 14755
    },
    {
      "epoch": 164.0,
      "grad_norm": 6.039707756144708e-08,
      "learning_rate": 0.2100151676902938,
      "loss": 0.0,
      "num_input_tokens_seen": 4132496,
      "step": 14760
    },
    {
      "epoch": 164.05555555555554,
      "grad_norm": 5.458782936784701e-08,
      "learning_rate": 0.2099611784660683,
      "loss": 0.0,
      "num_input_tokens_seen": 4133872,
      "step": 14765
    },
    {
      "epoch": 164.11111111111111,
      "grad_norm": 9.0382869188943e-08,
      "learning_rate": 0.20990717999507552,
      "loss": 0.0,
      "num_input_tokens_seen": 4135248,
      "step": 14770
    },
    {
      "epoch": 164.16666666666666,
      "grad_norm": 3.38965548962733e-08,
      "learning_rate": 0.20985317228564276,
      "loss": 0.0,
      "num_input_tokens_seen": 4136608,
      "step": 14775
    },
    {
      "epoch": 164.22222222222223,
      "grad_norm": 5.379502354685428e-08,
      "learning_rate": 0.20979915534609872,
      "loss": 0.0,
      "num_input_tokens_seen": 4138048,
      "step": 14780
    },
    {
      "epoch": 164.27777777777777,
      "grad_norm": 5.189279050910045e-08,
      "learning_rate": 0.20974512918477342,
      "loss": 0.0,
      "num_input_tokens_seen": 4139456,
      "step": 14785
    },
    {
      "epoch": 164.33333333333334,
      "grad_norm": 3.0044919441252205e-08,
      "learning_rate": 0.2096910938099984,
      "loss": 0.0,
      "num_input_tokens_seen": 4140864,
      "step": 14790
    },
    {
      "epoch": 164.38888888888889,
      "grad_norm": 2.095528017775905e-08,
      "learning_rate": 0.2096370492301066,
      "loss": 0.0,
      "num_input_tokens_seen": 4142272,
      "step": 14795
    },
    {
      "epoch": 164.44444444444446,
      "grad_norm": 2.5419721438879606e-08,
      "learning_rate": 0.2095829954534323,
      "loss": 0.0,
      "num_input_tokens_seen": 4143664,
      "step": 14800
    },
    {
      "epoch": 164.44444444444446,
      "eval_loss": 1.3115466833114624,
      "eval_runtime": 1.1822,
      "eval_samples_per_second": 33.837,
      "eval_steps_per_second": 16.918,
      "num_input_tokens_seen": 4143664,
      "step": 14800
    },
    {
      "epoch": 164.5,
      "grad_norm": 5.644449885267022e-08,
      "learning_rate": 0.2095289324883114,
      "loss": 0.0,
      "num_input_tokens_seen": 4145024,
      "step": 14805
    },
    {
      "epoch": 164.55555555555554,
      "grad_norm": 2.9232042564331095e-08,
      "learning_rate": 0.20947486034308097,
      "loss": 0.0,
      "num_input_tokens_seen": 4146384,
      "step": 14810
    },
    {
      "epoch": 164.61111111111111,
      "grad_norm": 1.1213139572419095e-07,
      "learning_rate": 0.2094207790260797,
      "loss": 0.0,
      "num_input_tokens_seen": 4147824,
      "step": 14815
    },
    {
      "epoch": 164.66666666666666,
      "grad_norm": 3.087896160991477e-08,
      "learning_rate": 0.20936668854564758,
      "loss": 0.0,
      "num_input_tokens_seen": 4149184,
      "step": 14820
    },
    {
      "epoch": 164.72222222222223,
      "grad_norm": 3.6417027615698316e-08,
      "learning_rate": 0.20931258891012602,
      "loss": 0.0,
      "num_input_tokens_seen": 4150592,
      "step": 14825
    },
    {
      "epoch": 164.77777777777777,
      "grad_norm": 2.322318337633078e-08,
      "learning_rate": 0.20925848012785792,
      "loss": 0.0,
      "num_input_tokens_seen": 4152000,
      "step": 14830
    },
    {
      "epoch": 164.83333333333334,
      "grad_norm": 1.4674466086717075e-08,
      "learning_rate": 0.20920436220718747,
      "loss": 0.0,
      "num_input_tokens_seen": 4153408,
      "step": 14835
    },
    {
      "epoch": 164.88888888888889,
      "grad_norm": 3.9692636732979736e-08,
      "learning_rate": 0.20915023515646033,
      "loss": 0.0,
      "num_input_tokens_seen": 4154816,
      "step": 14840
    },
    {
      "epoch": 164.94444444444446,
      "grad_norm": 9.735784800568581e-08,
      "learning_rate": 0.20909609898402368,
      "loss": 0.0,
      "num_input_tokens_seen": 4156208,
      "step": 14845
    },
    {
      "epoch": 165.0,
      "grad_norm": 2.9870882656268805e-08,
      "learning_rate": 0.2090419536982258,
      "loss": 0.0,
      "num_input_tokens_seen": 4157600,
      "step": 14850
    },
    {
      "epoch": 165.05555555555554,
      "grad_norm": 2.1396306948417987e-08,
      "learning_rate": 0.2089877993074168,
      "loss": 0.0,
      "num_input_tokens_seen": 4158992,
      "step": 14855
    },
    {
      "epoch": 165.11111111111111,
      "grad_norm": 6.997359491833777e-08,
      "learning_rate": 0.20893363581994784,
      "loss": 0.0,
      "num_input_tokens_seen": 4160432,
      "step": 14860
    },
    {
      "epoch": 165.16666666666666,
      "grad_norm": 8.568625986526968e-08,
      "learning_rate": 0.2088794632441716,
      "loss": 0.0,
      "num_input_tokens_seen": 4161856,
      "step": 14865
    },
    {
      "epoch": 165.22222222222223,
      "grad_norm": 2.1338740552323543e-08,
      "learning_rate": 0.20882528158844219,
      "loss": 0.0,
      "num_input_tokens_seen": 4163232,
      "step": 14870
    },
    {
      "epoch": 165.27777777777777,
      "grad_norm": 7.537579449490295e-08,
      "learning_rate": 0.20877109086111514,
      "loss": 0.0,
      "num_input_tokens_seen": 4164608,
      "step": 14875
    },
    {
      "epoch": 165.33333333333334,
      "grad_norm": 8.977149690281294e-09,
      "learning_rate": 0.2087168910705473,
      "loss": 0.0,
      "num_input_tokens_seen": 4165984,
      "step": 14880
    },
    {
      "epoch": 165.38888888888889,
      "grad_norm": 4.835321831819783e-08,
      "learning_rate": 0.208662682225097,
      "loss": 0.0,
      "num_input_tokens_seen": 4167360,
      "step": 14885
    },
    {
      "epoch": 165.44444444444446,
      "grad_norm": 4.10676932460774e-08,
      "learning_rate": 0.2086084643331239,
      "loss": 0.0,
      "num_input_tokens_seen": 4168784,
      "step": 14890
    },
    {
      "epoch": 165.5,
      "grad_norm": 1.9143595153536808e-08,
      "learning_rate": 0.20855423740298906,
      "loss": 0.0,
      "num_input_tokens_seen": 4170192,
      "step": 14895
    },
    {
      "epoch": 165.55555555555554,
      "grad_norm": 2.3050544584179988e-08,
      "learning_rate": 0.208500001443055,
      "loss": 0.0,
      "num_input_tokens_seen": 4171600,
      "step": 14900
    },
    {
      "epoch": 165.61111111111111,
      "grad_norm": 1.481333011810193e-08,
      "learning_rate": 0.20844575646168553,
      "loss": 0.0,
      "num_input_tokens_seen": 4172992,
      "step": 14905
    },
    {
      "epoch": 165.66666666666666,
      "grad_norm": 4.1480404888716293e-08,
      "learning_rate": 0.20839150246724594,
      "loss": 0.0,
      "num_input_tokens_seen": 4174384,
      "step": 14910
    },
    {
      "epoch": 165.72222222222223,
      "grad_norm": 3.798312064873244e-08,
      "learning_rate": 0.20833723946810287,
      "loss": 0.0,
      "num_input_tokens_seen": 4175776,
      "step": 14915
    },
    {
      "epoch": 165.77777777777777,
      "grad_norm": 5.0117868966026435e-08,
      "learning_rate": 0.20828296747262437,
      "loss": 0.0,
      "num_input_tokens_seen": 4177168,
      "step": 14920
    },
    {
      "epoch": 165.83333333333334,
      "grad_norm": 7.12597199026277e-08,
      "learning_rate": 0.20822868648917986,
      "loss": 0.0,
      "num_input_tokens_seen": 4178544,
      "step": 14925
    },
    {
      "epoch": 165.88888888888889,
      "grad_norm": 7.374045196684165e-08,
      "learning_rate": 0.20817439652614017,
      "loss": 0.0,
      "num_input_tokens_seen": 4179984,
      "step": 14930
    },
    {
      "epoch": 165.94444444444446,
      "grad_norm": 2.6376445916298508e-08,
      "learning_rate": 0.20812009759187744,
      "loss": 0.0,
      "num_input_tokens_seen": 4181376,
      "step": 14935
    },
    {
      "epoch": 166.0,
      "grad_norm": 4.840223866153792e-08,
      "learning_rate": 0.2080657896947653,
      "loss": 0.0,
      "num_input_tokens_seen": 4182816,
      "step": 14940
    },
    {
      "epoch": 166.05555555555554,
      "grad_norm": 1.1654710618813624e-07,
      "learning_rate": 0.2080114728431787,
      "loss": 0.0,
      "num_input_tokens_seen": 4184208,
      "step": 14945
    },
    {
      "epoch": 166.11111111111111,
      "grad_norm": 1.2184432129913603e-08,
      "learning_rate": 0.20795714704549392,
      "loss": 0.0,
      "num_input_tokens_seen": 4185568,
      "step": 14950
    },
    {
      "epoch": 166.16666666666666,
      "grad_norm": 4.7323645446795126e-08,
      "learning_rate": 0.20790281231008875,
      "loss": 0.0,
      "num_input_tokens_seen": 4186944,
      "step": 14955
    },
    {
      "epoch": 166.22222222222223,
      "grad_norm": 2.9295064152279338e-08,
      "learning_rate": 0.20784846864534226,
      "loss": 0.0,
      "num_input_tokens_seen": 4188336,
      "step": 14960
    },
    {
      "epoch": 166.27777777777777,
      "grad_norm": 2.671826671019062e-08,
      "learning_rate": 0.20779411605963496,
      "loss": 0.0,
      "num_input_tokens_seen": 4189760,
      "step": 14965
    },
    {
      "epoch": 166.33333333333334,
      "grad_norm": 1.8483699903981687e-08,
      "learning_rate": 0.2077397545613487,
      "loss": 0.0,
      "num_input_tokens_seen": 4191104,
      "step": 14970
    },
    {
      "epoch": 166.38888888888889,
      "grad_norm": 4.0437868165099644e-08,
      "learning_rate": 0.20768538415886661,
      "loss": 0.0,
      "num_input_tokens_seen": 4192544,
      "step": 14975
    },
    {
      "epoch": 166.44444444444446,
      "grad_norm": 2.0094727659625278e-08,
      "learning_rate": 0.20763100486057343,
      "loss": 0.0,
      "num_input_tokens_seen": 4193952,
      "step": 14980
    },
    {
      "epoch": 166.5,
      "grad_norm": 2.1336639122182532e-08,
      "learning_rate": 0.20757661667485502,
      "loss": 0.0,
      "num_input_tokens_seen": 4195360,
      "step": 14985
    },
    {
      "epoch": 166.55555555555554,
      "grad_norm": 5.4551112071976604e-08,
      "learning_rate": 0.2075222196100988,
      "loss": 0.0,
      "num_input_tokens_seen": 4196768,
      "step": 14990
    },
    {
      "epoch": 166.61111111111111,
      "grad_norm": 1.1095736773825138e-08,
      "learning_rate": 0.20746781367469344,
      "loss": 0.0,
      "num_input_tokens_seen": 4198176,
      "step": 14995
    },
    {
      "epoch": 166.66666666666666,
      "grad_norm": 4.371738882014142e-08,
      "learning_rate": 0.207413398877029,
      "loss": 0.0,
      "num_input_tokens_seen": 4199552,
      "step": 15000
    },
    {
      "epoch": 166.66666666666666,
      "eval_loss": 1.3476979732513428,
      "eval_runtime": 1.1901,
      "eval_samples_per_second": 33.612,
      "eval_steps_per_second": 16.806,
      "num_input_tokens_seen": 4199552,
      "step": 15000
    },
    {
      "epoch": 166.72222222222223,
      "grad_norm": 8.453718614021e-09,
      "learning_rate": 0.20735897522549698,
      "loss": 0.0,
      "num_input_tokens_seen": 4200960,
      "step": 15005
    },
    {
      "epoch": 166.77777777777777,
      "grad_norm": 6.276381014913568e-08,
      "learning_rate": 0.2073045427284902,
      "loss": 0.0,
      "num_input_tokens_seen": 4202400,
      "step": 15010
    },
    {
      "epoch": 166.83333333333334,
      "grad_norm": 4.065713810064153e-08,
      "learning_rate": 0.2072501013944027,
      "loss": 0.0,
      "num_input_tokens_seen": 4203760,
      "step": 15015
    },
    {
      "epoch": 166.88888888888889,
      "grad_norm": 7.870747964489055e-08,
      "learning_rate": 0.20719565123163017,
      "loss": 0.0,
      "num_input_tokens_seen": 4205120,
      "step": 15020
    },
    {
      "epoch": 166.94444444444446,
      "grad_norm": 2.589156089527478e-08,
      "learning_rate": 0.20714119224856944,
      "loss": 0.0,
      "num_input_tokens_seen": 4206496,
      "step": 15025
    },
    {
      "epoch": 167.0,
      "grad_norm": 1.483545908342876e-08,
      "learning_rate": 0.2070867244536188,
      "loss": 0.0,
      "num_input_tokens_seen": 4207936,
      "step": 15030
    },
    {
      "epoch": 167.05555555555554,
      "grad_norm": 6.947200148488264e-08,
      "learning_rate": 0.20703224785517785,
      "loss": 0.0,
      "num_input_tokens_seen": 4209312,
      "step": 15035
    },
    {
      "epoch": 167.11111111111111,
      "grad_norm": 3.7628684168566906e-08,
      "learning_rate": 0.20697776246164754,
      "loss": 0.0,
      "num_input_tokens_seen": 4210736,
      "step": 15040
    },
    {
      "epoch": 167.16666666666666,
      "grad_norm": 1.0678771644734297e-08,
      "learning_rate": 0.2069232682814303,
      "loss": 0.0,
      "num_input_tokens_seen": 4212112,
      "step": 15045
    },
    {
      "epoch": 167.22222222222223,
      "grad_norm": 3.381869362328871e-08,
      "learning_rate": 0.20686876532292972,
      "loss": 0.0,
      "num_input_tokens_seen": 4213488,
      "step": 15050
    },
    {
      "epoch": 167.27777777777777,
      "grad_norm": 5.881883424763146e-08,
      "learning_rate": 0.20681425359455083,
      "loss": 0.0,
      "num_input_tokens_seen": 4214880,
      "step": 15055
    },
    {
      "epoch": 167.33333333333334,
      "grad_norm": 7.033973048464759e-08,
      "learning_rate": 0.20675973310470008,
      "loss": 0.0,
      "num_input_tokens_seen": 4216288,
      "step": 15060
    },
    {
      "epoch": 167.38888888888889,
      "grad_norm": 1.1731053461971896e-07,
      "learning_rate": 0.2067052038617852,
      "loss": 0.0,
      "num_input_tokens_seen": 4217696,
      "step": 15065
    },
    {
      "epoch": 167.44444444444446,
      "grad_norm": 2.0931222977083053e-08,
      "learning_rate": 0.2066506658742153,
      "loss": 0.0,
      "num_input_tokens_seen": 4219056,
      "step": 15070
    },
    {
      "epoch": 167.5,
      "grad_norm": 3.7938935548709196e-08,
      "learning_rate": 0.20659611915040077,
      "loss": 0.0,
      "num_input_tokens_seen": 4220496,
      "step": 15075
    },
    {
      "epoch": 167.55555555555554,
      "grad_norm": 3.5043544954760364e-08,
      "learning_rate": 0.20654156369875348,
      "loss": 0.0,
      "num_input_tokens_seen": 4221888,
      "step": 15080
    },
    {
      "epoch": 167.61111111111111,
      "grad_norm": 6.243028138896989e-08,
      "learning_rate": 0.20648699952768648,
      "loss": 0.0,
      "num_input_tokens_seen": 4223296,
      "step": 15085
    },
    {
      "epoch": 167.66666666666666,
      "grad_norm": 2.2081641404270158e-08,
      "learning_rate": 0.20643242664561437,
      "loss": 0.0,
      "num_input_tokens_seen": 4224736,
      "step": 15090
    },
    {
      "epoch": 167.72222222222223,
      "grad_norm": 3.711604179557071e-08,
      "learning_rate": 0.20637784506095277,
      "loss": 0.0,
      "num_input_tokens_seen": 4226112,
      "step": 15095
    },
    {
      "epoch": 167.77777777777777,
      "grad_norm": 1.1973482116900414e-07,
      "learning_rate": 0.20632325478211908,
      "loss": 0.0,
      "num_input_tokens_seen": 4227520,
      "step": 15100
    },
    {
      "epoch": 167.83333333333334,
      "grad_norm": 1.54772852312135e-08,
      "learning_rate": 0.20626865581753165,
      "loss": 0.0,
      "num_input_tokens_seen": 4228880,
      "step": 15105
    },
    {
      "epoch": 167.88888888888889,
      "grad_norm": 3.753240918058509e-08,
      "learning_rate": 0.2062140481756104,
      "loss": 0.0,
      "num_input_tokens_seen": 4230320,
      "step": 15110
    },
    {
      "epoch": 167.94444444444446,
      "grad_norm": 1.2434792040494358e-07,
      "learning_rate": 0.20615943186477648,
      "loss": 0.0,
      "num_input_tokens_seen": 4231728,
      "step": 15115
    },
    {
      "epoch": 168.0,
      "grad_norm": 1.318041853437535e-07,
      "learning_rate": 0.20610480689345242,
      "loss": 0.0,
      "num_input_tokens_seen": 4233152,
      "step": 15120
    },
    {
      "epoch": 168.05555555555554,
      "grad_norm": 3.266997694595375e-08,
      "learning_rate": 0.2060501732700621,
      "loss": 0.0,
      "num_input_tokens_seen": 4234544,
      "step": 15125
    },
    {
      "epoch": 168.11111111111111,
      "grad_norm": 4.0566412451426004e-08,
      "learning_rate": 0.20599553100303067,
      "loss": 0.0,
      "num_input_tokens_seen": 4235904,
      "step": 15130
    },
    {
      "epoch": 168.16666666666666,
      "grad_norm": 4.283352694756104e-08,
      "learning_rate": 0.20594088010078465,
      "loss": 0.0,
      "num_input_tokens_seen": 4237280,
      "step": 15135
    },
    {
      "epoch": 168.22222222222223,
      "grad_norm": 2.0857440219401724e-08,
      "learning_rate": 0.20588622057175196,
      "loss": 0.0,
      "num_input_tokens_seen": 4238688,
      "step": 15140
    },
    {
      "epoch": 168.27777777777777,
      "grad_norm": 2.402089904762761e-08,
      "learning_rate": 0.20583155242436177,
      "loss": 0.0,
      "num_input_tokens_seen": 4240112,
      "step": 15145
    },
    {
      "epoch": 168.33333333333334,
      "grad_norm": 1.4320666430478468e-08,
      "learning_rate": 0.20577687566704453,
      "loss": 0.0,
      "num_input_tokens_seen": 4241520,
      "step": 15150
    },
    {
      "epoch": 168.38888888888889,
      "grad_norm": 2.602809523466476e-08,
      "learning_rate": 0.20572219030823213,
      "loss": 0.0,
      "num_input_tokens_seen": 4242912,
      "step": 15155
    },
    {
      "epoch": 168.44444444444446,
      "grad_norm": 4.225562122428528e-08,
      "learning_rate": 0.20566749635635775,
      "loss": 0.0,
      "num_input_tokens_seen": 4244352,
      "step": 15160
    },
    {
      "epoch": 168.5,
      "grad_norm": 7.435131266220196e-08,
      "learning_rate": 0.20561279381985587,
      "loss": 0.0,
      "num_input_tokens_seen": 4245744,
      "step": 15165
    },
    {
      "epoch": 168.55555555555554,
      "grad_norm": 4.434722455926021e-08,
      "learning_rate": 0.2055580827071623,
      "loss": 0.0,
      "num_input_tokens_seen": 4247168,
      "step": 15170
    },
    {
      "epoch": 168.61111111111111,
      "grad_norm": 1.104549962605006e-08,
      "learning_rate": 0.20550336302671418,
      "loss": 0.0,
      "num_input_tokens_seen": 4248560,
      "step": 15175
    },
    {
      "epoch": 168.66666666666666,
      "grad_norm": 1.4249424395984533e-07,
      "learning_rate": 0.20544863478695,
      "loss": 0.0,
      "num_input_tokens_seen": 4249968,
      "step": 15180
    },
    {
      "epoch": 168.72222222222223,
      "grad_norm": 7.697174453369371e-08,
      "learning_rate": 0.20539389799630953,
      "loss": 0.0,
      "num_input_tokens_seen": 4251392,
      "step": 15185
    },
    {
      "epoch": 168.77777777777777,
      "grad_norm": 3.591881281295173e-08,
      "learning_rate": 0.20533915266323388,
      "loss": 0.0,
      "num_input_tokens_seen": 4252736,
      "step": 15190
    },
    {
      "epoch": 168.83333333333334,
      "grad_norm": 2.749846572669412e-08,
      "learning_rate": 0.20528439879616542,
      "loss": 0.0,
      "num_input_tokens_seen": 4254144,
      "step": 15195
    },
    {
      "epoch": 168.88888888888889,
      "grad_norm": 9.079443685777733e-08,
      "learning_rate": 0.20522963640354794,
      "loss": 0.0,
      "num_input_tokens_seen": 4255584,
      "step": 15200
    },
    {
      "epoch": 168.88888888888889,
      "eval_loss": 1.332916498184204,
      "eval_runtime": 1.1807,
      "eval_samples_per_second": 33.879,
      "eval_steps_per_second": 16.94,
      "num_input_tokens_seen": 4255584,
      "step": 15200
    },
    {
      "epoch": 168.94444444444446,
      "grad_norm": 5.8184031814789705e-08,
      "learning_rate": 0.20517486549382644,
      "loss": 0.0,
      "num_input_tokens_seen": 4256992,
      "step": 15205
    },
    {
      "epoch": 169.0,
      "grad_norm": 2.559905176724442e-08,
      "learning_rate": 0.20512008607544735,
      "loss": 0.0,
      "num_input_tokens_seen": 4258384,
      "step": 15210
    },
    {
      "epoch": 169.05555555555554,
      "grad_norm": 2.7331754637316408e-08,
      "learning_rate": 0.20506529815685826,
      "loss": 0.0,
      "num_input_tokens_seen": 4259808,
      "step": 15215
    },
    {
      "epoch": 169.11111111111111,
      "grad_norm": 5.859076424030718e-08,
      "learning_rate": 0.2050105017465082,
      "loss": 0.0,
      "num_input_tokens_seen": 4261216,
      "step": 15220
    },
    {
      "epoch": 169.16666666666666,
      "grad_norm": 2.0900827735204075e-08,
      "learning_rate": 0.20495569685284754,
      "loss": 0.0,
      "num_input_tokens_seen": 4262608,
      "step": 15225
    },
    {
      "epoch": 169.22222222222223,
      "grad_norm": 2.3027297402222757e-08,
      "learning_rate": 0.20490088348432778,
      "loss": 0.0,
      "num_input_tokens_seen": 4264032,
      "step": 15230
    },
    {
      "epoch": 169.27777777777777,
      "grad_norm": 1.2343868149855552e-08,
      "learning_rate": 0.2048460616494018,
      "loss": 0.0,
      "num_input_tokens_seen": 4265424,
      "step": 15235
    },
    {
      "epoch": 169.33333333333334,
      "grad_norm": 2.8611250257881693e-08,
      "learning_rate": 0.2047912313565239,
      "loss": 0.0,
      "num_input_tokens_seen": 4266880,
      "step": 15240
    },
    {
      "epoch": 169.38888888888889,
      "grad_norm": 1.5358768479245555e-08,
      "learning_rate": 0.20473639261414958,
      "loss": 0.0,
      "num_input_tokens_seen": 4268224,
      "step": 15245
    },
    {
      "epoch": 169.44444444444446,
      "grad_norm": 4.220955673872595e-08,
      "learning_rate": 0.2046815454307357,
      "loss": 0.0,
      "num_input_tokens_seen": 4269600,
      "step": 15250
    },
    {
      "epoch": 169.5,
      "grad_norm": 2.6061046654035636e-08,
      "learning_rate": 0.20462668981474028,
      "loss": 0.0,
      "num_input_tokens_seen": 4270992,
      "step": 15255
    },
    {
      "epoch": 169.55555555555554,
      "grad_norm": 9.885238227980153e-08,
      "learning_rate": 0.20457182577462288,
      "loss": 0.0,
      "num_input_tokens_seen": 4272368,
      "step": 15260
    },
    {
      "epoch": 169.61111111111111,
      "grad_norm": 6.393117502057066e-08,
      "learning_rate": 0.2045169533188441,
      "loss": 0.0,
      "num_input_tokens_seen": 4273792,
      "step": 15265
    },
    {
      "epoch": 169.66666666666666,
      "grad_norm": 2.5202034237281623e-08,
      "learning_rate": 0.20446207245586603,
      "loss": 0.0,
      "num_input_tokens_seen": 4275200,
      "step": 15270
    },
    {
      "epoch": 169.72222222222223,
      "grad_norm": 6.709866795517883e-08,
      "learning_rate": 0.20440718319415196,
      "loss": 0.0,
      "num_input_tokens_seen": 4276592,
      "step": 15275
    },
    {
      "epoch": 169.77777777777777,
      "grad_norm": 8.452877864328912e-08,
      "learning_rate": 0.20435228554216653,
      "loss": 0.0,
      "num_input_tokens_seen": 4277952,
      "step": 15280
    },
    {
      "epoch": 169.83333333333334,
      "grad_norm": 2.8728234013897236e-08,
      "learning_rate": 0.20429737950837565,
      "loss": 0.0,
      "num_input_tokens_seen": 4279360,
      "step": 15285
    },
    {
      "epoch": 169.88888888888889,
      "grad_norm": 9.371512277311922e-08,
      "learning_rate": 0.20424246510124647,
      "loss": 0.0,
      "num_input_tokens_seen": 4280752,
      "step": 15290
    },
    {
      "epoch": 169.94444444444446,
      "grad_norm": 5.4263573190382886e-08,
      "learning_rate": 0.20418754232924755,
      "loss": 0.0,
      "num_input_tokens_seen": 4282160,
      "step": 15295
    },
    {
      "epoch": 170.0,
      "grad_norm": 4.1258022775991776e-08,
      "learning_rate": 0.20413261120084863,
      "loss": 0.0,
      "num_input_tokens_seen": 4283584,
      "step": 15300
    },
    {
      "epoch": 170.05555555555554,
      "grad_norm": 1.1106236996738517e-07,
      "learning_rate": 0.2040776717245208,
      "loss": 0.0,
      "num_input_tokens_seen": 4284912,
      "step": 15305
    },
    {
      "epoch": 170.11111111111111,
      "grad_norm": 1.6052220885853785e-08,
      "learning_rate": 0.2040227239087364,
      "loss": 0.0,
      "num_input_tokens_seen": 4286304,
      "step": 15310
    },
    {
      "epoch": 170.16666666666666,
      "grad_norm": 2.7667756086202644e-08,
      "learning_rate": 0.20396776776196904,
      "loss": 0.0,
      "num_input_tokens_seen": 4287696,
      "step": 15315
    },
    {
      "epoch": 170.22222222222223,
      "grad_norm": 9.567814096556049e-09,
      "learning_rate": 0.20391280329269373,
      "loss": 0.0,
      "num_input_tokens_seen": 4289104,
      "step": 15320
    },
    {
      "epoch": 170.27777777777777,
      "grad_norm": 8.25921375735561e-08,
      "learning_rate": 0.20385783050938663,
      "loss": 0.0,
      "num_input_tokens_seen": 4290496,
      "step": 15325
    },
    {
      "epoch": 170.33333333333334,
      "grad_norm": 6.27213410098193e-08,
      "learning_rate": 0.20380284942052526,
      "loss": 0.0,
      "num_input_tokens_seen": 4291872,
      "step": 15330
    },
    {
      "epoch": 170.38888888888889,
      "grad_norm": 5.6649035684586124e-08,
      "learning_rate": 0.2037478600345884,
      "loss": 0.0,
      "num_input_tokens_seen": 4293248,
      "step": 15335
    },
    {
      "epoch": 170.44444444444446,
      "grad_norm": 3.47973738712426e-08,
      "learning_rate": 0.20369286236005604,
      "loss": 0.0,
      "num_input_tokens_seen": 4294640,
      "step": 15340
    },
    {
      "epoch": 170.5,
      "grad_norm": 2.869060367061138e-08,
      "learning_rate": 0.20363785640540957,
      "loss": 0.0,
      "num_input_tokens_seen": 4296064,
      "step": 15345
    },
    {
      "epoch": 170.55555555555554,
      "grad_norm": 1.0656456339575016e-07,
      "learning_rate": 0.2035828421791316,
      "loss": 0.0,
      "num_input_tokens_seen": 4297472,
      "step": 15350
    },
    {
      "epoch": 170.61111111111111,
      "grad_norm": 7.889875064392982e-08,
      "learning_rate": 0.20352781968970599,
      "loss": 0.0,
      "num_input_tokens_seen": 4298912,
      "step": 15355
    },
    {
      "epoch": 170.66666666666666,
      "grad_norm": 2.6078874171275856e-08,
      "learning_rate": 0.2034727889456179,
      "loss": 0.0,
      "num_input_tokens_seen": 4300320,
      "step": 15360
    },
    {
      "epoch": 170.72222222222223,
      "grad_norm": 2.3494941103763267e-08,
      "learning_rate": 0.2034177499553538,
      "loss": 0.0,
      "num_input_tokens_seen": 4301712,
      "step": 15365
    },
    {
      "epoch": 170.77777777777777,
      "grad_norm": 2.126719422790302e-08,
      "learning_rate": 0.2033627027274014,
      "loss": 0.0,
      "num_input_tokens_seen": 4303136,
      "step": 15370
    },
    {
      "epoch": 170.83333333333334,
      "grad_norm": 4.77873740578616e-08,
      "learning_rate": 0.20330764727024955,
      "loss": 0.0,
      "num_input_tokens_seen": 4304512,
      "step": 15375
    },
    {
      "epoch": 170.88888888888889,
      "grad_norm": 4.9475449515057335e-08,
      "learning_rate": 0.20325258359238868,
      "loss": 0.0,
      "num_input_tokens_seen": 4305920,
      "step": 15380
    },
    {
      "epoch": 170.94444444444446,
      "grad_norm": 6.644333438998729e-08,
      "learning_rate": 0.20319751170231018,
      "loss": 0.0,
      "num_input_tokens_seen": 4307312,
      "step": 15385
    },
    {
      "epoch": 171.0,
      "grad_norm": 8.362249559468182e-08,
      "learning_rate": 0.2031424316085068,
      "loss": 0.0,
      "num_input_tokens_seen": 4308752,
      "step": 15390
    },
    {
      "epoch": 171.05555555555554,
      "grad_norm": 1.0376368919651213e-07,
      "learning_rate": 0.20308734331947265,
      "loss": 0.0,
      "num_input_tokens_seen": 4310144,
      "step": 15395
    },
    {
      "epoch": 171.11111111111111,
      "grad_norm": 5.45454987843641e-08,
      "learning_rate": 0.20303224684370305,
      "loss": 0.0,
      "num_input_tokens_seen": 4311504,
      "step": 15400
    },
    {
      "epoch": 171.11111111111111,
      "eval_loss": 1.3378572463989258,
      "eval_runtime": 1.1835,
      "eval_samples_per_second": 33.799,
      "eval_steps_per_second": 16.899,
      "num_input_tokens_seen": 4311504,
      "step": 15400
    },
    {
      "epoch": 171.16666666666666,
      "grad_norm": 1.0035223141358074e-07,
      "learning_rate": 0.20297714218969456,
      "loss": 0.0,
      "num_input_tokens_seen": 4312880,
      "step": 15405
    },
    {
      "epoch": 171.22222222222223,
      "grad_norm": 1.6118812951049222e-08,
      "learning_rate": 0.20292202936594497,
      "loss": 0.0,
      "num_input_tokens_seen": 4314272,
      "step": 15410
    },
    {
      "epoch": 171.27777777777777,
      "grad_norm": 4.337232084594689e-08,
      "learning_rate": 0.2028669083809534,
      "loss": 0.0,
      "num_input_tokens_seen": 4315632,
      "step": 15415
    },
    {
      "epoch": 171.33333333333334,
      "grad_norm": 2.7831832838387527e-08,
      "learning_rate": 0.20281177924322016,
      "loss": 0.0,
      "num_input_tokens_seen": 4317008,
      "step": 15420
    },
    {
      "epoch": 171.38888888888889,
      "grad_norm": 5.9492425208418354e-08,
      "learning_rate": 0.2027566419612469,
      "loss": 0.0,
      "num_input_tokens_seen": 4318448,
      "step": 15425
    },
    {
      "epoch": 171.44444444444446,
      "grad_norm": 3.218032063045939e-08,
      "learning_rate": 0.20270149654353647,
      "loss": 0.0,
      "num_input_tokens_seen": 4319872,
      "step": 15430
    },
    {
      "epoch": 171.5,
      "grad_norm": 4.273226039686051e-08,
      "learning_rate": 0.202646342998593,
      "loss": 0.0,
      "num_input_tokens_seen": 4321264,
      "step": 15435
    },
    {
      "epoch": 171.55555555555554,
      "grad_norm": 3.201951770392952e-08,
      "learning_rate": 0.20259118133492185,
      "loss": 0.0,
      "num_input_tokens_seen": 4322656,
      "step": 15440
    },
    {
      "epoch": 171.61111111111111,
      "grad_norm": 1.792616011186965e-08,
      "learning_rate": 0.20253601156102966,
      "loss": 0.0,
      "num_input_tokens_seen": 4324048,
      "step": 15445
    },
    {
      "epoch": 171.66666666666666,
      "grad_norm": 3.3835057422493264e-08,
      "learning_rate": 0.20248083368542422,
      "loss": 0.0,
      "num_input_tokens_seen": 4325424,
      "step": 15450
    },
    {
      "epoch": 171.72222222222223,
      "grad_norm": 2.4649532193166124e-08,
      "learning_rate": 0.2024256477166147,
      "loss": 0.0,
      "num_input_tokens_seen": 4326848,
      "step": 15455
    },
    {
      "epoch": 171.77777777777777,
      "grad_norm": 9.469397710404337e-09,
      "learning_rate": 0.2023704536631115,
      "loss": 0.0,
      "num_input_tokens_seen": 4328240,
      "step": 15460
    },
    {
      "epoch": 171.83333333333334,
      "grad_norm": 2.5754355092999504e-08,
      "learning_rate": 0.20231525153342625,
      "loss": 0.0,
      "num_input_tokens_seen": 4329616,
      "step": 15465
    },
    {
      "epoch": 171.88888888888889,
      "grad_norm": 3.896475320175341e-08,
      "learning_rate": 0.20226004133607173,
      "loss": 0.0,
      "num_input_tokens_seen": 4330992,
      "step": 15470
    },
    {
      "epoch": 171.94444444444446,
      "grad_norm": 2.5887604948593435e-08,
      "learning_rate": 0.20220482307956214,
      "loss": 0.0,
      "num_input_tokens_seen": 4332400,
      "step": 15475
    },
    {
      "epoch": 172.0,
      "grad_norm": 2.0434480774156327e-08,
      "learning_rate": 0.20214959677241276,
      "loss": 0.0,
      "num_input_tokens_seen": 4333808,
      "step": 15480
    },
    {
      "epoch": 172.05555555555554,
      "grad_norm": 1.8536601587015866e-08,
      "learning_rate": 0.20209436242314022,
      "loss": 0.0,
      "num_input_tokens_seen": 4335216,
      "step": 15485
    },
    {
      "epoch": 172.11111111111111,
      "grad_norm": 6.576097888455479e-08,
      "learning_rate": 0.2020391200402623,
      "loss": 0.0,
      "num_input_tokens_seen": 4336624,
      "step": 15490
    },
    {
      "epoch": 172.16666666666666,
      "grad_norm": 7.49246638065415e-08,
      "learning_rate": 0.2019838696322981,
      "loss": 0.0,
      "num_input_tokens_seen": 4338000,
      "step": 15495
    },
    {
      "epoch": 172.22222222222223,
      "grad_norm": 4.787817431406438e-08,
      "learning_rate": 0.20192861120776798,
      "loss": 0.0,
      "num_input_tokens_seen": 4339408,
      "step": 15500
    },
    {
      "epoch": 172.27777777777777,
      "grad_norm": 1.1761341056626406e-07,
      "learning_rate": 0.20187334477519345,
      "loss": 0.0,
      "num_input_tokens_seen": 4340864,
      "step": 15505
    },
    {
      "epoch": 172.33333333333334,
      "grad_norm": 3.0243690218867414e-08,
      "learning_rate": 0.20181807034309726,
      "loss": 0.0,
      "num_input_tokens_seen": 4342272,
      "step": 15510
    },
    {
      "epoch": 172.38888888888889,
      "grad_norm": 1.5882648085607798e-08,
      "learning_rate": 0.2017627879200034,
      "loss": 0.0,
      "num_input_tokens_seen": 4343680,
      "step": 15515
    },
    {
      "epoch": 172.44444444444446,
      "grad_norm": 1.790406578550119e-08,
      "learning_rate": 0.2017074975144372,
      "loss": 0.0,
      "num_input_tokens_seen": 4345104,
      "step": 15520
    },
    {
      "epoch": 172.5,
      "grad_norm": 1.4228084488365766e-08,
      "learning_rate": 0.20165219913492508,
      "loss": 0.0,
      "num_input_tokens_seen": 4346496,
      "step": 15525
    },
    {
      "epoch": 172.55555555555554,
      "grad_norm": 5.687669357712366e-08,
      "learning_rate": 0.20159689278999468,
      "loss": 0.0,
      "num_input_tokens_seen": 4347872,
      "step": 15530
    },
    {
      "epoch": 172.61111111111111,
      "grad_norm": 4.117570995276765e-08,
      "learning_rate": 0.20154157848817508,
      "loss": 0.0,
      "num_input_tokens_seen": 4349248,
      "step": 15535
    },
    {
      "epoch": 172.66666666666666,
      "grad_norm": 2.523032627266275e-08,
      "learning_rate": 0.20148625623799632,
      "loss": 0.0,
      "num_input_tokens_seen": 4350656,
      "step": 15540
    },
    {
      "epoch": 172.72222222222223,
      "grad_norm": 3.273280313464966e-08,
      "learning_rate": 0.20143092604798984,
      "loss": 0.0,
      "num_input_tokens_seen": 4352032,
      "step": 15545
    },
    {
      "epoch": 172.77777777777777,
      "grad_norm": 8.660330230725322e-09,
      "learning_rate": 0.2013755879266883,
      "loss": 0.0,
      "num_input_tokens_seen": 4353456,
      "step": 15550
    },
    {
      "epoch": 172.83333333333334,
      "grad_norm": 3.350400135104792e-08,
      "learning_rate": 0.20132024188262543,
      "loss": 0.0,
      "num_input_tokens_seen": 4354800,
      "step": 15555
    },
    {
      "epoch": 172.88888888888889,
      "grad_norm": 2.5292957062106325e-08,
      "learning_rate": 0.2012648879243363,
      "loss": 0.0,
      "num_input_tokens_seen": 4356160,
      "step": 15560
    },
    {
      "epoch": 172.94444444444446,
      "grad_norm": 5.933102187327677e-08,
      "learning_rate": 0.20120952606035725,
      "loss": 0.0,
      "num_input_tokens_seen": 4357616,
      "step": 15565
    },
    {
      "epoch": 173.0,
      "grad_norm": 8.491891634321291e-08,
      "learning_rate": 0.20115415629922576,
      "loss": 0.0,
      "num_input_tokens_seen": 4358992,
      "step": 15570
    },
    {
      "epoch": 173.05555555555554,
      "grad_norm": 1.0848974341115536e-07,
      "learning_rate": 0.20109877864948048,
      "loss": 0.0,
      "num_input_tokens_seen": 4360464,
      "step": 15575
    },
    {
      "epoch": 173.11111111111111,
      "grad_norm": 9.627897412656239e-08,
      "learning_rate": 0.20104339311966138,
      "loss": 0.0,
      "num_input_tokens_seen": 4361856,
      "step": 15580
    },
    {
      "epoch": 173.16666666666666,
      "grad_norm": 3.1477643602784156e-08,
      "learning_rate": 0.2009879997183097,
      "loss": 0.0,
      "num_input_tokens_seen": 4363248,
      "step": 15585
    },
    {
      "epoch": 173.22222222222223,
      "grad_norm": 2.689096767483079e-08,
      "learning_rate": 0.20093259845396763,
      "loss": 0.0,
      "num_input_tokens_seen": 4364624,
      "step": 15590
    },
    {
      "epoch": 173.27777777777777,
      "grad_norm": 2.8232664206484515e-08,
      "learning_rate": 0.20087718933517884,
      "loss": 0.0,
      "num_input_tokens_seen": 4366048,
      "step": 15595
    },
    {
      "epoch": 173.33333333333334,
      "grad_norm": 1.501662794112235e-08,
      "learning_rate": 0.20082177237048807,
      "loss": 0.0,
      "num_input_tokens_seen": 4367408,
      "step": 15600
    },
    {
      "epoch": 173.33333333333334,
      "eval_loss": 1.3553335666656494,
      "eval_runtime": 1.1845,
      "eval_samples_per_second": 33.77,
      "eval_steps_per_second": 16.885,
      "num_input_tokens_seen": 4367408,
      "step": 15600
    },
    {
      "epoch": 173.38888888888889,
      "grad_norm": 4.0084668029294335e-08,
      "learning_rate": 0.20076634756844133,
      "loss": 0.0,
      "num_input_tokens_seen": 4368832,
      "step": 15605
    },
    {
      "epoch": 173.44444444444446,
      "grad_norm": 1.2696649065446763e-08,
      "learning_rate": 0.20071091493758586,
      "loss": 0.0,
      "num_input_tokens_seen": 4370224,
      "step": 15610
    },
    {
      "epoch": 173.5,
      "grad_norm": 2.274336985408354e-08,
      "learning_rate": 0.20065547448647003,
      "loss": 0.0,
      "num_input_tokens_seen": 4371648,
      "step": 15615
    },
    {
      "epoch": 173.55555555555554,
      "grad_norm": 3.5263546749320085e-08,
      "learning_rate": 0.20060002622364348,
      "loss": 0.0,
      "num_input_tokens_seen": 4373008,
      "step": 15620
    },
    {
      "epoch": 173.61111111111111,
      "grad_norm": 1.1840832314646832e-08,
      "learning_rate": 0.20054457015765695,
      "loss": 0.0,
      "num_input_tokens_seen": 4374400,
      "step": 15625
    },
    {
      "epoch": 173.66666666666666,
      "grad_norm": 1.4930394698353666e-08,
      "learning_rate": 0.20048910629706254,
      "loss": 0.0,
      "num_input_tokens_seen": 4375808,
      "step": 15630
    },
    {
      "epoch": 173.72222222222223,
      "grad_norm": 2.2125105303416603e-08,
      "learning_rate": 0.20043363465041347,
      "loss": 0.0,
      "num_input_tokens_seen": 4377200,
      "step": 15635
    },
    {
      "epoch": 173.77777777777777,
      "grad_norm": 2.6529274776976308e-08,
      "learning_rate": 0.2003781552262641,
      "loss": 0.0,
      "num_input_tokens_seen": 4378560,
      "step": 15640
    },
    {
      "epoch": 173.83333333333334,
      "grad_norm": 5.526792534737979e-08,
      "learning_rate": 0.20032266803317014,
      "loss": 0.0,
      "num_input_tokens_seen": 4379936,
      "step": 15645
    },
    {
      "epoch": 173.88888888888889,
      "grad_norm": 2.0103914977198656e-08,
      "learning_rate": 0.2002671730796884,
      "loss": 0.0,
      "num_input_tokens_seen": 4381360,
      "step": 15650
    },
    {
      "epoch": 173.94444444444446,
      "grad_norm": 1.8722895234191128e-08,
      "learning_rate": 0.20021167037437684,
      "loss": 0.0,
      "num_input_tokens_seen": 4382784,
      "step": 15655
    },
    {
      "epoch": 174.0,
      "grad_norm": 3.741627807585246e-08,
      "learning_rate": 0.20015615992579472,
      "loss": 0.0,
      "num_input_tokens_seen": 4384176,
      "step": 15660
    },
    {
      "epoch": 174.05555555555554,
      "grad_norm": 1.9685419516690672e-08,
      "learning_rate": 0.20010064174250244,
      "loss": 0.0,
      "num_input_tokens_seen": 4385536,
      "step": 15665
    },
    {
      "epoch": 174.11111111111111,
      "grad_norm": 1.6058860907719463e-08,
      "learning_rate": 0.2000451158330616,
      "loss": 0.0,
      "num_input_tokens_seen": 4386928,
      "step": 15670
    },
    {
      "epoch": 174.16666666666666,
      "grad_norm": 2.0137616019155757e-08,
      "learning_rate": 0.199989582206035,
      "loss": 0.0,
      "num_input_tokens_seen": 4388352,
      "step": 15675
    },
    {
      "epoch": 174.22222222222223,
      "grad_norm": 1.6554961845827165e-08,
      "learning_rate": 0.1999340408699866,
      "loss": 0.0,
      "num_input_tokens_seen": 4389760,
      "step": 15680
    },
    {
      "epoch": 174.27777777777777,
      "grad_norm": 1.3795035336272576e-08,
      "learning_rate": 0.19987849183348155,
      "loss": 0.0,
      "num_input_tokens_seen": 4391136,
      "step": 15685
    },
    {
      "epoch": 174.33333333333334,
      "grad_norm": 4.996470437390599e-08,
      "learning_rate": 0.19982293510508628,
      "loss": 0.0,
      "num_input_tokens_seen": 4392528,
      "step": 15690
    },
    {
      "epoch": 174.38888888888889,
      "grad_norm": 2.460485326594153e-08,
      "learning_rate": 0.19976737069336833,
      "loss": 0.0,
      "num_input_tokens_seen": 4393856,
      "step": 15695
    },
    {
      "epoch": 174.44444444444446,
      "grad_norm": 3.366011469552177e-08,
      "learning_rate": 0.1997117986068964,
      "loss": 0.0,
      "num_input_tokens_seen": 4395232,
      "step": 15700
    },
    {
      "epoch": 174.5,
      "grad_norm": 5.833539162836132e-08,
      "learning_rate": 0.19965621885424037,
      "loss": 0.0,
      "num_input_tokens_seen": 4396688,
      "step": 15705
    },
    {
      "epoch": 174.55555555555554,
      "grad_norm": 6.380091122082376e-08,
      "learning_rate": 0.19960063144397142,
      "loss": 0.0,
      "num_input_tokens_seen": 4398096,
      "step": 15710
    },
    {
      "epoch": 174.61111111111111,
      "grad_norm": 5.1414495771950897e-08,
      "learning_rate": 0.19954503638466176,
      "loss": 0.0,
      "num_input_tokens_seen": 4399520,
      "step": 15715
    },
    {
      "epoch": 174.66666666666666,
      "grad_norm": 5.003634129252532e-08,
      "learning_rate": 0.1994894336848848,
      "loss": 0.0,
      "num_input_tokens_seen": 4400912,
      "step": 15720
    },
    {
      "epoch": 174.72222222222223,
      "grad_norm": 7.045543526373876e-08,
      "learning_rate": 0.1994338233532153,
      "loss": 0.0,
      "num_input_tokens_seen": 4402336,
      "step": 15725
    },
    {
      "epoch": 174.77777777777777,
      "grad_norm": 3.293650507885104e-08,
      "learning_rate": 0.19937820539822904,
      "loss": 0.0,
      "num_input_tokens_seen": 4403712,
      "step": 15730
    },
    {
      "epoch": 174.83333333333334,
      "grad_norm": 5.4017537109984914e-08,
      "learning_rate": 0.199322579828503,
      "loss": 0.0,
      "num_input_tokens_seen": 4405152,
      "step": 15735
    },
    {
      "epoch": 174.88888888888889,
      "grad_norm": 4.2986755488527706e-08,
      "learning_rate": 0.19926694665261527,
      "loss": 0.0,
      "num_input_tokens_seen": 4406544,
      "step": 15740
    },
    {
      "epoch": 174.94444444444446,
      "grad_norm": 9.966069747235906e-09,
      "learning_rate": 0.19921130587914526,
      "loss": 0.0,
      "num_input_tokens_seen": 4408016,
      "step": 15745
    },
    {
      "epoch": 175.0,
      "grad_norm": 1.4330058917266797e-08,
      "learning_rate": 0.19915565751667344,
      "loss": 0.0,
      "num_input_tokens_seen": 4409408,
      "step": 15750
    },
    {
      "epoch": 175.05555555555554,
      "grad_norm": 6.919247397263462e-08,
      "learning_rate": 0.19910000157378152,
      "loss": 0.0,
      "num_input_tokens_seen": 4410848,
      "step": 15755
    },
    {
      "epoch": 175.11111111111111,
      "grad_norm": 7.503474108716546e-08,
      "learning_rate": 0.1990443380590523,
      "loss": 0.0,
      "num_input_tokens_seen": 4412272,
      "step": 15760
    },
    {
      "epoch": 175.16666666666666,
      "grad_norm": 1.5131925934497303e-08,
      "learning_rate": 0.19898866698106984,
      "loss": 0.0,
      "num_input_tokens_seen": 4413632,
      "step": 15765
    },
    {
      "epoch": 175.22222222222223,
      "grad_norm": 6.251375594956698e-08,
      "learning_rate": 0.19893298834841933,
      "loss": 0.0,
      "num_input_tokens_seen": 4415008,
      "step": 15770
    },
    {
      "epoch": 175.27777777777777,
      "grad_norm": 3.5089477989913576e-08,
      "learning_rate": 0.19887730216968705,
      "loss": 0.0,
      "num_input_tokens_seen": 4416400,
      "step": 15775
    },
    {
      "epoch": 175.33333333333334,
      "grad_norm": 1.2213095423874165e-08,
      "learning_rate": 0.19882160845346053,
      "loss": 0.0,
      "num_input_tokens_seen": 4417808,
      "step": 15780
    },
    {
      "epoch": 175.38888888888889,
      "grad_norm": 5.386169021903697e-08,
      "learning_rate": 0.1987659072083285,
      "loss": 0.0,
      "num_input_tokens_seen": 4419184,
      "step": 15785
    },
    {
      "epoch": 175.44444444444446,
      "grad_norm": 7.745109797951955e-08,
      "learning_rate": 0.1987101984428807,
      "loss": 0.0,
      "num_input_tokens_seen": 4420608,
      "step": 15790
    },
    {
      "epoch": 175.5,
      "grad_norm": 5.652589507576522e-08,
      "learning_rate": 0.19865448216570822,
      "loss": 0.0,
      "num_input_tokens_seen": 4422000,
      "step": 15795
    },
    {
      "epoch": 175.55555555555554,
      "grad_norm": 5.171543637771947e-09,
      "learning_rate": 0.19859875838540317,
      "loss": 0.0,
      "num_input_tokens_seen": 4423376,
      "step": 15800
    },
    {
      "epoch": 175.55555555555554,
      "eval_loss": 1.378533959388733,
      "eval_runtime": 1.1834,
      "eval_samples_per_second": 33.801,
      "eval_steps_per_second": 16.9,
      "num_input_tokens_seen": 4423376,
      "step": 15800
    },
    {
      "epoch": 175.61111111111111,
      "grad_norm": 6.153780418571841e-08,
      "learning_rate": 0.1985430271105588,
      "loss": 0.0,
      "num_input_tokens_seen": 4424800,
      "step": 15805
    },
    {
      "epoch": 175.66666666666666,
      "grad_norm": 7.734611529031099e-08,
      "learning_rate": 0.19848728834976961,
      "loss": 0.0,
      "num_input_tokens_seen": 4426208,
      "step": 15810
    },
    {
      "epoch": 175.72222222222223,
      "grad_norm": 1.9200284029352588e-08,
      "learning_rate": 0.19843154211163128,
      "loss": 0.0,
      "num_input_tokens_seen": 4427600,
      "step": 15815
    },
    {
      "epoch": 175.77777777777777,
      "grad_norm": 6.550983755460038e-08,
      "learning_rate": 0.1983757884047405,
      "loss": 0.0,
      "num_input_tokens_seen": 4428976,
      "step": 15820
    },
    {
      "epoch": 175.83333333333334,
      "grad_norm": 4.3161804796909564e-08,
      "learning_rate": 0.1983200272376952,
      "loss": 0.0,
      "num_input_tokens_seen": 4430368,
      "step": 15825
    },
    {
      "epoch": 175.88888888888889,
      "grad_norm": 2.9526479039532205e-08,
      "learning_rate": 0.1982642586190945,
      "loss": 0.0,
      "num_input_tokens_seen": 4431792,
      "step": 15830
    },
    {
      "epoch": 175.94444444444446,
      "grad_norm": 4.910647177780447e-08,
      "learning_rate": 0.1982084825575386,
      "loss": 0.0,
      "num_input_tokens_seen": 4433168,
      "step": 15835
    },
    {
      "epoch": 176.0,
      "grad_norm": 6.128705365426868e-08,
      "learning_rate": 0.19815269906162883,
      "loss": 0.0,
      "num_input_tokens_seen": 4434592,
      "step": 15840
    },
    {
      "epoch": 176.05555555555554,
      "grad_norm": 1.624158763036121e-08,
      "learning_rate": 0.19809690813996775,
      "loss": 0.0,
      "num_input_tokens_seen": 4435984,
      "step": 15845
    },
    {
      "epoch": 176.11111111111111,
      "grad_norm": 5.484577236813948e-09,
      "learning_rate": 0.19804110980115905,
      "loss": 0.0,
      "num_input_tokens_seen": 4437376,
      "step": 15850
    },
    {
      "epoch": 176.16666666666666,
      "grad_norm": 1.089234213935697e-08,
      "learning_rate": 0.19798530405380746,
      "loss": 0.0,
      "num_input_tokens_seen": 4438784,
      "step": 15855
    },
    {
      "epoch": 176.22222222222223,
      "grad_norm": 3.372387880062888e-08,
      "learning_rate": 0.19792949090651893,
      "loss": 0.0,
      "num_input_tokens_seen": 4440224,
      "step": 15860
    },
    {
      "epoch": 176.27777777777777,
      "grad_norm": 2.298168055858696e-08,
      "learning_rate": 0.19787367036790066,
      "loss": 0.0,
      "num_input_tokens_seen": 4441632,
      "step": 15865
    },
    {
      "epoch": 176.33333333333334,
      "grad_norm": 4.449369939152348e-08,
      "learning_rate": 0.19781784244656075,
      "loss": 0.0,
      "num_input_tokens_seen": 4443088,
      "step": 15870
    },
    {
      "epoch": 176.38888888888889,
      "grad_norm": 4.188657598547252e-08,
      "learning_rate": 0.19776200715110864,
      "loss": 0.0,
      "num_input_tokens_seen": 4444496,
      "step": 15875
    },
    {
      "epoch": 176.44444444444446,
      "grad_norm": 1.71613869781595e-08,
      "learning_rate": 0.1977061644901548,
      "loss": 0.0,
      "num_input_tokens_seen": 4445888,
      "step": 15880
    },
    {
      "epoch": 176.5,
      "grad_norm": 3.804679593599758e-08,
      "learning_rate": 0.1976503144723109,
      "loss": 0.0,
      "num_input_tokens_seen": 4447328,
      "step": 15885
    },
    {
      "epoch": 176.55555555555554,
      "grad_norm": 7.732331219756361e-09,
      "learning_rate": 0.19759445710618967,
      "loss": 0.0,
      "num_input_tokens_seen": 4448704,
      "step": 15890
    },
    {
      "epoch": 176.61111111111111,
      "grad_norm": 5.576914219318496e-08,
      "learning_rate": 0.19753859240040508,
      "loss": 0.0,
      "num_input_tokens_seen": 4450128,
      "step": 15895
    },
    {
      "epoch": 176.66666666666666,
      "grad_norm": 1.2982699360009065e-08,
      "learning_rate": 0.1974827203635721,
      "loss": 0.0,
      "num_input_tokens_seen": 4451584,
      "step": 15900
    },
    {
      "epoch": 176.72222222222223,
      "grad_norm": 6.205434033290658e-08,
      "learning_rate": 0.19742684100430694,
      "loss": 0.0,
      "num_input_tokens_seen": 4452944,
      "step": 15905
    },
    {
      "epoch": 176.77777777777777,
      "grad_norm": 2.4104707563310512e-08,
      "learning_rate": 0.19737095433122692,
      "loss": 0.0,
      "num_input_tokens_seen": 4454320,
      "step": 15910
    },
    {
      "epoch": 176.83333333333334,
      "grad_norm": 2.3621545608421002e-08,
      "learning_rate": 0.19731506035295046,
      "loss": 0.0,
      "num_input_tokens_seen": 4455664,
      "step": 15915
    },
    {
      "epoch": 176.88888888888889,
      "grad_norm": 1.401952953727914e-08,
      "learning_rate": 0.19725915907809702,
      "loss": 0.0,
      "num_input_tokens_seen": 4457056,
      "step": 15920
    },
    {
      "epoch": 176.94444444444446,
      "grad_norm": 2.5332697717317387e-08,
      "learning_rate": 0.1972032505152874,
      "loss": 0.0,
      "num_input_tokens_seen": 4458448,
      "step": 15925
    },
    {
      "epoch": 177.0,
      "grad_norm": 1.8517415156793504e-08,
      "learning_rate": 0.19714733467314338,
      "loss": 0.0,
      "num_input_tokens_seen": 4459856,
      "step": 15930
    },
    {
      "epoch": 177.05555555555554,
      "grad_norm": 5.392461233100221e-08,
      "learning_rate": 0.19709141156028784,
      "loss": 0.0,
      "num_input_tokens_seen": 4461264,
      "step": 15935
    },
    {
      "epoch": 177.11111111111111,
      "grad_norm": 4.8424890763953954e-08,
      "learning_rate": 0.1970354811853448,
      "loss": 0.0,
      "num_input_tokens_seen": 4462656,
      "step": 15940
    },
    {
      "epoch": 177.16666666666666,
      "grad_norm": 6.913283101539491e-08,
      "learning_rate": 0.19697954355693953,
      "loss": 0.0,
      "num_input_tokens_seen": 4464080,
      "step": 15945
    },
    {
      "epoch": 177.22222222222223,
      "grad_norm": 5.333270891583197e-08,
      "learning_rate": 0.19692359868369827,
      "loss": 0.0,
      "num_input_tokens_seen": 4465520,
      "step": 15950
    },
    {
      "epoch": 177.27777777777777,
      "grad_norm": 1.398837135013764e-08,
      "learning_rate": 0.1968676465742484,
      "loss": 0.0,
      "num_input_tokens_seen": 4466896,
      "step": 15955
    },
    {
      "epoch": 177.33333333333334,
      "grad_norm": 3.359383171641639e-08,
      "learning_rate": 0.19681168723721845,
      "loss": 0.0,
      "num_input_tokens_seen": 4468336,
      "step": 15960
    },
    {
      "epoch": 177.38888888888889,
      "grad_norm": 1.37751809958786e-08,
      "learning_rate": 0.19675572068123803,
      "loss": 0.0,
      "num_input_tokens_seen": 4469728,
      "step": 15965
    },
    {
      "epoch": 177.44444444444446,
      "grad_norm": 3.372203849494326e-08,
      "learning_rate": 0.19669974691493794,
      "loss": 0.0,
      "num_input_tokens_seen": 4471104,
      "step": 15970
    },
    {
      "epoch": 177.5,
      "grad_norm": 1.578629671428189e-08,
      "learning_rate": 0.19664376594695002,
      "loss": 0.0,
      "num_input_tokens_seen": 4472464,
      "step": 15975
    },
    {
      "epoch": 177.55555555555554,
      "grad_norm": 3.7661799012767005e-08,
      "learning_rate": 0.19658777778590722,
      "loss": 0.0,
      "num_input_tokens_seen": 4473872,
      "step": 15980
    },
    {
      "epoch": 177.61111111111111,
      "grad_norm": 1.0007839001957564e-08,
      "learning_rate": 0.19653178244044364,
      "loss": 0.0,
      "num_input_tokens_seen": 4475264,
      "step": 15985
    },
    {
      "epoch": 177.66666666666666,
      "grad_norm": 4.75856687387477e-09,
      "learning_rate": 0.19647577991919443,
      "loss": 0.0,
      "num_input_tokens_seen": 4476624,
      "step": 15990
    },
    {
      "epoch": 177.72222222222223,
      "grad_norm": 2.452618197423817e-08,
      "learning_rate": 0.1964197702307959,
      "loss": 0.0,
      "num_input_tokens_seen": 4478032,
      "step": 15995
    },
    {
      "epoch": 177.77777777777777,
      "grad_norm": 2.2262835130959502e-08,
      "learning_rate": 0.19636375338388545,
      "loss": 0.0,
      "num_input_tokens_seen": 4479456,
      "step": 16000
    },
    {
      "epoch": 177.77777777777777,
      "eval_loss": 1.3627619743347168,
      "eval_runtime": 1.1813,
      "eval_samples_per_second": 33.86,
      "eval_steps_per_second": 16.93,
      "num_input_tokens_seen": 4479456,
      "step": 16000
    },
    {
      "epoch": 177.83333333333334,
      "grad_norm": 5.7761084804042184e-08,
      "learning_rate": 0.1963077293871016,
      "loss": 0.0,
      "num_input_tokens_seen": 4480816,
      "step": 16005
    },
    {
      "epoch": 177.88888888888889,
      "grad_norm": 1.824905382363795e-08,
      "learning_rate": 0.19625169824908395,
      "loss": 0.0,
      "num_input_tokens_seen": 4482176,
      "step": 16010
    },
    {
      "epoch": 177.94444444444446,
      "grad_norm": 1.0906070713190275e-08,
      "learning_rate": 0.19619565997847319,
      "loss": 0.0,
      "num_input_tokens_seen": 4483600,
      "step": 16015
    },
    {
      "epoch": 178.0,
      "grad_norm": 1.1446227077271942e-08,
      "learning_rate": 0.19613961458391113,
      "loss": 0.0,
      "num_input_tokens_seen": 4485008,
      "step": 16020
    },
    {
      "epoch": 178.05555555555554,
      "grad_norm": 3.45832837922444e-08,
      "learning_rate": 0.19608356207404065,
      "loss": 0.0,
      "num_input_tokens_seen": 4486416,
      "step": 16025
    },
    {
      "epoch": 178.11111111111111,
      "grad_norm": 1.249694481231245e-08,
      "learning_rate": 0.1960275024575058,
      "loss": 0.0,
      "num_input_tokens_seen": 4487840,
      "step": 16030
    },
    {
      "epoch": 178.16666666666666,
      "grad_norm": 1.8853008043606678e-08,
      "learning_rate": 0.19597143574295164,
      "loss": 0.0,
      "num_input_tokens_seen": 4489280,
      "step": 16035
    },
    {
      "epoch": 178.22222222222223,
      "grad_norm": 5.4998938736616765e-08,
      "learning_rate": 0.1959153619390244,
      "loss": 0.0,
      "num_input_tokens_seen": 4490704,
      "step": 16040
    },
    {
      "epoch": 178.27777777777777,
      "grad_norm": 2.3265824822260583e-08,
      "learning_rate": 0.1958592810543713,
      "loss": 0.0,
      "num_input_tokens_seen": 4492096,
      "step": 16045
    },
    {
      "epoch": 178.33333333333334,
      "grad_norm": 2.461731618552676e-08,
      "learning_rate": 0.19580319309764077,
      "loss": 0.0,
      "num_input_tokens_seen": 4493504,
      "step": 16050
    },
    {
      "epoch": 178.38888888888889,
      "grad_norm": 5.2288118723708976e-08,
      "learning_rate": 0.1957470980774823,
      "loss": 0.0,
      "num_input_tokens_seen": 4494912,
      "step": 16055
    },
    {
      "epoch": 178.44444444444446,
      "grad_norm": 5.356047338977987e-08,
      "learning_rate": 0.19569099600254639,
      "loss": 0.0,
      "num_input_tokens_seen": 4496272,
      "step": 16060
    },
    {
      "epoch": 178.5,
      "grad_norm": 4.96950747219671e-08,
      "learning_rate": 0.1956348868814847,
      "loss": 0.0,
      "num_input_tokens_seen": 4497712,
      "step": 16065
    },
    {
      "epoch": 178.55555555555554,
      "grad_norm": 3.866292175302988e-08,
      "learning_rate": 0.19557877072295,
      "loss": 0.0,
      "num_input_tokens_seen": 4499088,
      "step": 16070
    },
    {
      "epoch": 178.61111111111111,
      "grad_norm": 2.8063100288022724e-08,
      "learning_rate": 0.19552264753559603,
      "loss": 0.0,
      "num_input_tokens_seen": 4500480,
      "step": 16075
    },
    {
      "epoch": 178.66666666666666,
      "grad_norm": 3.586762531426757e-08,
      "learning_rate": 0.19546651732807774,
      "loss": 0.0,
      "num_input_tokens_seen": 4501872,
      "step": 16080
    },
    {
      "epoch": 178.72222222222223,
      "grad_norm": 1.4303721762587429e-08,
      "learning_rate": 0.19541038010905112,
      "loss": 0.0,
      "num_input_tokens_seen": 4503264,
      "step": 16085
    },
    {
      "epoch": 178.77777777777777,
      "grad_norm": 1.5186776280984304e-08,
      "learning_rate": 0.19535423588717324,
      "loss": 0.0,
      "num_input_tokens_seen": 4504672,
      "step": 16090
    },
    {
      "epoch": 178.83333333333334,
      "grad_norm": 5.159762039852467e-08,
      "learning_rate": 0.19529808467110224,
      "loss": 0.0,
      "num_input_tokens_seen": 4506016,
      "step": 16095
    },
    {
      "epoch": 178.88888888888889,
      "grad_norm": 1.257190707093514e-08,
      "learning_rate": 0.19524192646949734,
      "loss": 0.0,
      "num_input_tokens_seen": 4507472,
      "step": 16100
    },
    {
      "epoch": 178.94444444444446,
      "grad_norm": 1.8824204417455803e-08,
      "learning_rate": 0.19518576129101878,
      "loss": 0.0,
      "num_input_tokens_seen": 4508848,
      "step": 16105
    },
    {
      "epoch": 179.0,
      "grad_norm": 3.323637542962388e-08,
      "learning_rate": 0.19512958914432804,
      "loss": 0.0,
      "num_input_tokens_seen": 4510240,
      "step": 16110
    },
    {
      "epoch": 179.05555555555554,
      "grad_norm": 1.2944523675173514e-08,
      "learning_rate": 0.1950734100380875,
      "loss": 0.0,
      "num_input_tokens_seen": 4511600,
      "step": 16115
    },
    {
      "epoch": 179.11111111111111,
      "grad_norm": 2.5788912338953196e-08,
      "learning_rate": 0.19501722398096066,
      "loss": 0.0,
      "num_input_tokens_seen": 4512976,
      "step": 16120
    },
    {
      "epoch": 179.16666666666666,
      "grad_norm": 3.979668150577709e-08,
      "learning_rate": 0.1949610309816122,
      "loss": 0.0,
      "num_input_tokens_seen": 4514368,
      "step": 16125
    },
    {
      "epoch": 179.22222222222223,
      "grad_norm": 7.836669979610633e-09,
      "learning_rate": 0.1949048310487078,
      "loss": 0.0,
      "num_input_tokens_seen": 4515760,
      "step": 16130
    },
    {
      "epoch": 179.27777777777777,
      "grad_norm": 1.2886714806370492e-08,
      "learning_rate": 0.19484862419091406,
      "loss": 0.0,
      "num_input_tokens_seen": 4517168,
      "step": 16135
    },
    {
      "epoch": 179.33333333333334,
      "grad_norm": 1.4055196118079039e-08,
      "learning_rate": 0.19479241041689893,
      "loss": 0.0,
      "num_input_tokens_seen": 4518576,
      "step": 16140
    },
    {
      "epoch": 179.38888888888889,
      "grad_norm": 1.3536139320535767e-08,
      "learning_rate": 0.19473618973533116,
      "loss": 0.0,
      "num_input_tokens_seen": 4519968,
      "step": 16145
    },
    {
      "epoch": 179.44444444444446,
      "grad_norm": 1.3073630178439544e-08,
      "learning_rate": 0.19467996215488076,
      "loss": 0.0,
      "num_input_tokens_seen": 4521392,
      "step": 16150
    },
    {
      "epoch": 179.5,
      "grad_norm": 3.496900191635177e-08,
      "learning_rate": 0.1946237276842187,
      "loss": 0.0,
      "num_input_tokens_seen": 4522800,
      "step": 16155
    },
    {
      "epoch": 179.55555555555554,
      "grad_norm": 5.6816080729049645e-08,
      "learning_rate": 0.19456748633201712,
      "loss": 0.0,
      "num_input_tokens_seen": 4524224,
      "step": 16160
    },
    {
      "epoch": 179.61111111111111,
      "grad_norm": 3.424042560595808e-08,
      "learning_rate": 0.194511238106949,
      "loss": 0.0,
      "num_input_tokens_seen": 4525648,
      "step": 16165
    },
    {
      "epoch": 179.66666666666666,
      "grad_norm": 3.2421493045831085e-08,
      "learning_rate": 0.19445498301768863,
      "loss": 0.0,
      "num_input_tokens_seen": 4527040,
      "step": 16170
    },
    {
      "epoch": 179.72222222222223,
      "grad_norm": 2.0465883210363245e-08,
      "learning_rate": 0.19439872107291126,
      "loss": 0.0,
      "num_input_tokens_seen": 4528464,
      "step": 16175
    },
    {
      "epoch": 179.77777777777777,
      "grad_norm": 1.2829578288631183e-08,
      "learning_rate": 0.1943424522812931,
      "loss": 0.0,
      "num_input_tokens_seen": 4529872,
      "step": 16180
    },
    {
      "epoch": 179.83333333333334,
      "grad_norm": 1.6707042860275578e-08,
      "learning_rate": 0.19428617665151157,
      "loss": 0.0,
      "num_input_tokens_seen": 4531248,
      "step": 16185
    },
    {
      "epoch": 179.88888888888889,
      "grad_norm": 1.1680844735906248e-08,
      "learning_rate": 0.19422989419224507,
      "loss": 0.0,
      "num_input_tokens_seen": 4532688,
      "step": 16190
    },
    {
      "epoch": 179.94444444444446,
      "grad_norm": 5.3064184157847194e-08,
      "learning_rate": 0.19417360491217303,
      "loss": 0.0,
      "num_input_tokens_seen": 4534112,
      "step": 16195
    },
    {
      "epoch": 180.0,
      "grad_norm": 2.4678945109712913e-08,
      "learning_rate": 0.19411730881997605,
      "loss": 0.0,
      "num_input_tokens_seen": 4535504,
      "step": 16200
    },
    {
      "epoch": 180.0,
      "eval_loss": 1.393648386001587,
      "eval_runtime": 1.1806,
      "eval_samples_per_second": 33.881,
      "eval_steps_per_second": 16.94,
      "num_input_tokens_seen": 4535504,
      "step": 16200
    },
    {
      "epoch": 180.05555555555554,
      "grad_norm": 2.1266698624344826e-08,
      "learning_rate": 0.1940610059243356,
      "loss": 0.0,
      "num_input_tokens_seen": 4536896,
      "step": 16205
    },
    {
      "epoch": 180.11111111111111,
      "grad_norm": 1.2928902393127828e-08,
      "learning_rate": 0.19400469623393435,
      "loss": 0.0,
      "num_input_tokens_seen": 4538272,
      "step": 16210
    },
    {
      "epoch": 180.16666666666666,
      "grad_norm": 3.49721140935344e-08,
      "learning_rate": 0.1939483797574559,
      "loss": 0.0,
      "num_input_tokens_seen": 4539680,
      "step": 16215
    },
    {
      "epoch": 180.22222222222223,
      "grad_norm": 5.348558218543076e-08,
      "learning_rate": 0.19389205650358504,
      "loss": 0.0,
      "num_input_tokens_seen": 4541104,
      "step": 16220
    },
    {
      "epoch": 180.27777777777777,
      "grad_norm": 1.6187575724302405e-08,
      "learning_rate": 0.19383572648100747,
      "loss": 0.0,
      "num_input_tokens_seen": 4542512,
      "step": 16225
    },
    {
      "epoch": 180.33333333333334,
      "grad_norm": 3.4383774050184e-08,
      "learning_rate": 0.19377938969841,
      "loss": 0.0,
      "num_input_tokens_seen": 4543920,
      "step": 16230
    },
    {
      "epoch": 180.38888888888889,
      "grad_norm": 3.615176424887068e-08,
      "learning_rate": 0.1937230461644805,
      "loss": 0.0,
      "num_input_tokens_seen": 4545296,
      "step": 16235
    },
    {
      "epoch": 180.44444444444446,
      "grad_norm": 2.150899547359586e-08,
      "learning_rate": 0.19366669588790777,
      "loss": 0.0,
      "num_input_tokens_seen": 4546688,
      "step": 16240
    },
    {
      "epoch": 180.5,
      "grad_norm": 5.362747756976205e-08,
      "learning_rate": 0.19361033887738185,
      "loss": 0.0,
      "num_input_tokens_seen": 4548064,
      "step": 16245
    },
    {
      "epoch": 180.55555555555554,
      "grad_norm": 5.3510621711438944e-08,
      "learning_rate": 0.19355397514159361,
      "loss": 0.0,
      "num_input_tokens_seen": 4549472,
      "step": 16250
    },
    {
      "epoch": 180.61111111111111,
      "grad_norm": 3.401916970346974e-08,
      "learning_rate": 0.19349760468923508,
      "loss": 0.0,
      "num_input_tokens_seen": 4550832,
      "step": 16255
    },
    {
      "epoch": 180.66666666666666,
      "grad_norm": 1.5900804228863308e-08,
      "learning_rate": 0.19344122752899925,
      "loss": 0.0,
      "num_input_tokens_seen": 4552240,
      "step": 16260
    },
    {
      "epoch": 180.72222222222223,
      "grad_norm": 5.40704121476665e-08,
      "learning_rate": 0.1933848436695802,
      "loss": 0.0,
      "num_input_tokens_seen": 4553696,
      "step": 16265
    },
    {
      "epoch": 180.77777777777777,
      "grad_norm": 2.3962684281286784e-08,
      "learning_rate": 0.1933284531196731,
      "loss": 0.0,
      "num_input_tokens_seen": 4555088,
      "step": 16270
    },
    {
      "epoch": 180.83333333333334,
      "grad_norm": 3.205429166541762e-08,
      "learning_rate": 0.19327205588797403,
      "loss": 0.0,
      "num_input_tokens_seen": 4556528,
      "step": 16275
    },
    {
      "epoch": 180.88888888888889,
      "grad_norm": 2.1560714102974998e-08,
      "learning_rate": 0.19321565198318014,
      "loss": 0.0,
      "num_input_tokens_seen": 4557920,
      "step": 16280
    },
    {
      "epoch": 180.94444444444446,
      "grad_norm": 1.3191827186176397e-08,
      "learning_rate": 0.1931592414139896,
      "loss": 0.0,
      "num_input_tokens_seen": 4559312,
      "step": 16285
    },
    {
      "epoch": 181.0,
      "grad_norm": 2.077976724024211e-08,
      "learning_rate": 0.19310282418910169,
      "loss": 0.0,
      "num_input_tokens_seen": 4560736,
      "step": 16290
    },
    {
      "epoch": 181.05555555555554,
      "grad_norm": 1.5023022825744192e-08,
      "learning_rate": 0.1930464003172166,
      "loss": 0.0,
      "num_input_tokens_seen": 4562112,
      "step": 16295
    },
    {
      "epoch": 181.11111111111111,
      "grad_norm": 2.8289905529277348e-08,
      "learning_rate": 0.19298996980703567,
      "loss": 0.0,
      "num_input_tokens_seen": 4563536,
      "step": 16300
    },
    {
      "epoch": 181.16666666666666,
      "grad_norm": 4.8450743861394585e-08,
      "learning_rate": 0.19293353266726113,
      "loss": 0.0,
      "num_input_tokens_seen": 4564976,
      "step": 16305
    },
    {
      "epoch": 181.22222222222223,
      "grad_norm": 2.758610584407961e-08,
      "learning_rate": 0.19287708890659633,
      "loss": 0.0,
      "num_input_tokens_seen": 4566352,
      "step": 16310
    },
    {
      "epoch": 181.27777777777777,
      "grad_norm": 6.142965247590837e-08,
      "learning_rate": 0.19282063853374556,
      "loss": 0.0,
      "num_input_tokens_seen": 4567728,
      "step": 16315
    },
    {
      "epoch": 181.33333333333334,
      "grad_norm": 1.2249856240487134e-08,
      "learning_rate": 0.19276418155741423,
      "loss": 0.0,
      "num_input_tokens_seen": 4569104,
      "step": 16320
    },
    {
      "epoch": 181.38888888888889,
      "grad_norm": 1.4006666049226624e-08,
      "learning_rate": 0.19270771798630867,
      "loss": 0.0,
      "num_input_tokens_seen": 4570528,
      "step": 16325
    },
    {
      "epoch": 181.44444444444446,
      "grad_norm": 2.8121098338829142e-08,
      "learning_rate": 0.1926512478291363,
      "loss": 0.0,
      "num_input_tokens_seen": 4571936,
      "step": 16330
    },
    {
      "epoch": 181.5,
      "grad_norm": 6.798015306230809e-08,
      "learning_rate": 0.19259477109460557,
      "loss": 0.0,
      "num_input_tokens_seen": 4573328,
      "step": 16335
    },
    {
      "epoch": 181.55555555555554,
      "grad_norm": 9.55981516170823e-09,
      "learning_rate": 0.19253828779142584,
      "loss": 0.0,
      "num_input_tokens_seen": 4574656,
      "step": 16340
    },
    {
      "epoch": 181.61111111111111,
      "grad_norm": 2.0622382024271246e-08,
      "learning_rate": 0.19248179792830755,
      "loss": 0.0,
      "num_input_tokens_seen": 4576048,
      "step": 16345
    },
    {
      "epoch": 181.66666666666666,
      "grad_norm": 1.3102729568004179e-08,
      "learning_rate": 0.19242530151396217,
      "loss": 0.0,
      "num_input_tokens_seen": 4577456,
      "step": 16350
    },
    {
      "epoch": 181.72222222222223,
      "grad_norm": 4.495798577863752e-08,
      "learning_rate": 0.19236879855710215,
      "loss": 0.0,
      "num_input_tokens_seen": 4578896,
      "step": 16355
    },
    {
      "epoch": 181.77777777777777,
      "grad_norm": 2.5045606477647198e-08,
      "learning_rate": 0.19231228906644096,
      "loss": 0.0,
      "num_input_tokens_seen": 4580320,
      "step": 16360
    },
    {
      "epoch": 181.83333333333334,
      "grad_norm": 9.61970059165651e-09,
      "learning_rate": 0.19225577305069302,
      "loss": 0.0,
      "num_input_tokens_seen": 4581696,
      "step": 16365
    },
    {
      "epoch": 181.88888888888889,
      "grad_norm": 5.089904675514845e-08,
      "learning_rate": 0.1921992505185739,
      "loss": 0.0,
      "num_input_tokens_seen": 4583104,
      "step": 16370
    },
    {
      "epoch": 181.94444444444446,
      "grad_norm": 1.8114864275275977e-08,
      "learning_rate": 0.19214272147880004,
      "loss": 0.0,
      "num_input_tokens_seen": 4584528,
      "step": 16375
    },
    {
      "epoch": 182.0,
      "grad_norm": 2.752621952595291e-08,
      "learning_rate": 0.19208618594008892,
      "loss": 0.0,
      "num_input_tokens_seen": 4585936,
      "step": 16380
    },
    {
      "epoch": 182.05555555555554,
      "grad_norm": 2.1701699992604517e-08,
      "learning_rate": 0.19202964391115904,
      "loss": 0.0,
      "num_input_tokens_seen": 4587296,
      "step": 16385
    },
    {
      "epoch": 182.11111111111111,
      "grad_norm": 1.5822465115888917e-08,
      "learning_rate": 0.1919730954007299,
      "loss": 0.0,
      "num_input_tokens_seen": 4588704,
      "step": 16390
    },
    {
      "epoch": 182.16666666666666,
      "grad_norm": 4.5515097468751264e-08,
      "learning_rate": 0.19191654041752199,
      "loss": 0.0,
      "num_input_tokens_seen": 4590080,
      "step": 16395
    },
    {
      "epoch": 182.22222222222223,
      "grad_norm": 2.0145268564419894e-08,
      "learning_rate": 0.19185997897025678,
      "loss": 0.0,
      "num_input_tokens_seen": 4591504,
      "step": 16400
    },
    {
      "epoch": 182.22222222222223,
      "eval_loss": 1.390751838684082,
      "eval_runtime": 1.1932,
      "eval_samples_per_second": 33.523,
      "eval_steps_per_second": 16.761,
      "num_input_tokens_seen": 4591504,
      "step": 16400
    },
    {
      "epoch": 182.27777777777777,
      "grad_norm": 3.3561651235913814e-08,
      "learning_rate": 0.19180341106765672,
      "loss": 0.0,
      "num_input_tokens_seen": 4592912,
      "step": 16405
    },
    {
      "epoch": 182.33333333333334,
      "grad_norm": 2.148977529259355e-08,
      "learning_rate": 0.19174683671844536,
      "loss": 0.0,
      "num_input_tokens_seen": 4594304,
      "step": 16410
    },
    {
      "epoch": 182.38888888888889,
      "grad_norm": 1.9708478404822927e-08,
      "learning_rate": 0.19169025593134717,
      "loss": 0.0,
      "num_input_tokens_seen": 4595696,
      "step": 16415
    },
    {
      "epoch": 182.44444444444446,
      "grad_norm": 3.707748064130101e-08,
      "learning_rate": 0.19163366871508764,
      "loss": 0.0,
      "num_input_tokens_seen": 4597120,
      "step": 16420
    },
    {
      "epoch": 182.5,
      "grad_norm": 1.7292485665620916e-08,
      "learning_rate": 0.19157707507839317,
      "loss": 0.0,
      "num_input_tokens_seen": 4598512,
      "step": 16425
    },
    {
      "epoch": 182.55555555555554,
      "grad_norm": 4.303345946254922e-08,
      "learning_rate": 0.19152047502999123,
      "loss": 0.0,
      "num_input_tokens_seen": 4599920,
      "step": 16430
    },
    {
      "epoch": 182.61111111111111,
      "grad_norm": 3.194217157442836e-08,
      "learning_rate": 0.19146386857861025,
      "loss": 0.0,
      "num_input_tokens_seen": 4601312,
      "step": 16435
    },
    {
      "epoch": 182.66666666666666,
      "grad_norm": 1.403300764479809e-08,
      "learning_rate": 0.19140725573297968,
      "loss": 0.0,
      "num_input_tokens_seen": 4602672,
      "step": 16440
    },
    {
      "epoch": 182.72222222222223,
      "grad_norm": 1.3964199574445502e-08,
      "learning_rate": 0.19135063650182987,
      "loss": 0.0,
      "num_input_tokens_seen": 4604064,
      "step": 16445
    },
    {
      "epoch": 182.77777777777777,
      "grad_norm": 2.1256136406577752e-08,
      "learning_rate": 0.19129401089389234,
      "loss": 0.0,
      "num_input_tokens_seen": 4605424,
      "step": 16450
    },
    {
      "epoch": 182.83333333333334,
      "grad_norm": 3.567661721604054e-08,
      "learning_rate": 0.19123737891789938,
      "loss": 0.0,
      "num_input_tokens_seen": 4606832,
      "step": 16455
    },
    {
      "epoch": 182.88888888888889,
      "grad_norm": 1.420588979783588e-08,
      "learning_rate": 0.19118074058258439,
      "loss": 0.0,
      "num_input_tokens_seen": 4608240,
      "step": 16460
    },
    {
      "epoch": 182.94444444444446,
      "grad_norm": 6.189436163595019e-08,
      "learning_rate": 0.1911240958966816,
      "loss": 0.0,
      "num_input_tokens_seen": 4609632,
      "step": 16465
    },
    {
      "epoch": 183.0,
      "grad_norm": 2.4403451703847168e-08,
      "learning_rate": 0.19106744486892652,
      "loss": 0.0,
      "num_input_tokens_seen": 4611072,
      "step": 16470
    },
    {
      "epoch": 183.05555555555554,
      "grad_norm": 1.8017225045241503e-08,
      "learning_rate": 0.1910107875080553,
      "loss": 0.0,
      "num_input_tokens_seen": 4612496,
      "step": 16475
    },
    {
      "epoch": 183.11111111111111,
      "grad_norm": 3.1210454665142606e-08,
      "learning_rate": 0.19095412382280533,
      "loss": 0.0,
      "num_input_tokens_seen": 4613920,
      "step": 16480
    },
    {
      "epoch": 183.16666666666666,
      "grad_norm": 2.3170153795604165e-08,
      "learning_rate": 0.19089745382191473,
      "loss": 0.0,
      "num_input_tokens_seen": 4615344,
      "step": 16485
    },
    {
      "epoch": 183.22222222222223,
      "grad_norm": 1.2114457881295948e-08,
      "learning_rate": 0.19084077751412284,
      "loss": 0.0,
      "num_input_tokens_seen": 4616736,
      "step": 16490
    },
    {
      "epoch": 183.27777777777777,
      "grad_norm": 2.395857734427409e-08,
      "learning_rate": 0.19078409490816986,
      "loss": 0.0,
      "num_input_tokens_seen": 4618160,
      "step": 16495
    },
    {
      "epoch": 183.33333333333334,
      "grad_norm": 3.305361317984534e-08,
      "learning_rate": 0.19072740601279686,
      "loss": 0.0,
      "num_input_tokens_seen": 4619568,
      "step": 16500
    },
    {
      "epoch": 183.38888888888889,
      "grad_norm": 1.4698141370672602e-08,
      "learning_rate": 0.19067071083674605,
      "loss": 0.0,
      "num_input_tokens_seen": 4620928,
      "step": 16505
    },
    {
      "epoch": 183.44444444444446,
      "grad_norm": 1.4730507480464894e-08,
      "learning_rate": 0.19061400938876052,
      "loss": 0.0,
      "num_input_tokens_seen": 4622320,
      "step": 16510
    },
    {
      "epoch": 183.5,
      "grad_norm": 2.1417214668417728e-08,
      "learning_rate": 0.1905573016775844,
      "loss": 0.0,
      "num_input_tokens_seen": 4623712,
      "step": 16515
    },
    {
      "epoch": 183.55555555555554,
      "grad_norm": 1.966152218813022e-08,
      "learning_rate": 0.19050058771196263,
      "loss": 0.0,
      "num_input_tokens_seen": 4625152,
      "step": 16520
    },
    {
      "epoch": 183.61111111111111,
      "grad_norm": 1.908666114047719e-08,
      "learning_rate": 0.19044386750064132,
      "loss": 0.0,
      "num_input_tokens_seen": 4626512,
      "step": 16525
    },
    {
      "epoch": 183.66666666666666,
      "grad_norm": 3.265640913241441e-08,
      "learning_rate": 0.19038714105236737,
      "loss": 0.0,
      "num_input_tokens_seen": 4627952,
      "step": 16530
    },
    {
      "epoch": 183.72222222222223,
      "grad_norm": 2.940695686959316e-08,
      "learning_rate": 0.19033040837588874,
      "loss": 0.0,
      "num_input_tokens_seen": 4629360,
      "step": 16535
    },
    {
      "epoch": 183.77777777777777,
      "grad_norm": 1.3151616684581313e-08,
      "learning_rate": 0.1902736694799543,
      "loss": 0.0,
      "num_input_tokens_seen": 4630720,
      "step": 16540
    },
    {
      "epoch": 183.83333333333334,
      "grad_norm": 5.158419469353248e-08,
      "learning_rate": 0.19021692437331392,
      "loss": 0.0,
      "num_input_tokens_seen": 4632112,
      "step": 16545
    },
    {
      "epoch": 183.88888888888889,
      "grad_norm": 3.995370079223903e-08,
      "learning_rate": 0.1901601730647184,
      "loss": 0.0,
      "num_input_tokens_seen": 4633504,
      "step": 16550
    },
    {
      "epoch": 183.94444444444446,
      "grad_norm": 1.4488001021106811e-08,
      "learning_rate": 0.19010341556291954,
      "loss": 0.0,
      "num_input_tokens_seen": 4634896,
      "step": 16555
    },
    {
      "epoch": 184.0,
      "grad_norm": 1.4186321450893047e-08,
      "learning_rate": 0.19004665187667,
      "loss": 0.0,
      "num_input_tokens_seen": 4636288,
      "step": 16560
    },
    {
      "epoch": 184.05555555555554,
      "grad_norm": 1.0087098267774763e-08,
      "learning_rate": 0.1899898820147235,
      "loss": 0.0,
      "num_input_tokens_seen": 4637696,
      "step": 16565
    },
    {
      "epoch": 184.11111111111111,
      "grad_norm": 2.801385967643455e-08,
      "learning_rate": 0.18993310598583465,
      "loss": 0.0,
      "num_input_tokens_seen": 4639072,
      "step": 16570
    },
    {
      "epoch": 184.16666666666666,
      "grad_norm": 6.411762143443411e-08,
      "learning_rate": 0.18987632379875904,
      "loss": 0.0,
      "num_input_tokens_seen": 4640496,
      "step": 16575
    },
    {
      "epoch": 184.22222222222223,
      "grad_norm": 3.4975862206465536e-08,
      "learning_rate": 0.18981953546225314,
      "loss": 0.0,
      "num_input_tokens_seen": 4641872,
      "step": 16580
    },
    {
      "epoch": 184.27777777777777,
      "grad_norm": 1.0790569326957211e-08,
      "learning_rate": 0.18976274098507445,
      "loss": 0.0,
      "num_input_tokens_seen": 4643248,
      "step": 16585
    },
    {
      "epoch": 184.33333333333334,
      "grad_norm": 8.941018592167893e-09,
      "learning_rate": 0.18970594037598146,
      "loss": 0.0,
      "num_input_tokens_seen": 4644608,
      "step": 16590
    },
    {
      "epoch": 184.38888888888889,
      "grad_norm": 3.1075163775540204e-08,
      "learning_rate": 0.1896491336437335,
      "loss": 0.0,
      "num_input_tokens_seen": 4646016,
      "step": 16595
    },
    {
      "epoch": 184.44444444444446,
      "grad_norm": 1.2831257834022836e-08,
      "learning_rate": 0.18959232079709085,
      "loss": 0.0,
      "num_input_tokens_seen": 4647424,
      "step": 16600
    },
    {
      "epoch": 184.44444444444446,
      "eval_loss": 1.4267860651016235,
      "eval_runtime": 1.1849,
      "eval_samples_per_second": 33.757,
      "eval_steps_per_second": 16.878,
      "num_input_tokens_seen": 4647424,
      "step": 16600
    },
    {
      "epoch": 184.5,
      "grad_norm": 3.7580203837705994e-08,
      "learning_rate": 0.18953550184481477,
      "loss": 0.0,
      "num_input_tokens_seen": 4648832,
      "step": 16605
    },
    {
      "epoch": 184.55555555555554,
      "grad_norm": 1.6351012988025104e-08,
      "learning_rate": 0.18947867679566752,
      "loss": 0.0,
      "num_input_tokens_seen": 4650240,
      "step": 16610
    },
    {
      "epoch": 184.61111111111111,
      "grad_norm": 3.012842242355873e-08,
      "learning_rate": 0.18942184565841216,
      "loss": 0.0,
      "num_input_tokens_seen": 4651616,
      "step": 16615
    },
    {
      "epoch": 184.66666666666666,
      "grad_norm": 1.3865007808533392e-08,
      "learning_rate": 0.18936500844181278,
      "loss": 0.0,
      "num_input_tokens_seen": 4653040,
      "step": 16620
    },
    {
      "epoch": 184.72222222222223,
      "grad_norm": 1.4616739818507085e-08,
      "learning_rate": 0.18930816515463436,
      "loss": 0.0,
      "num_input_tokens_seen": 4654432,
      "step": 16625
    },
    {
      "epoch": 184.77777777777777,
      "grad_norm": 2.3354798983632463e-08,
      "learning_rate": 0.18925131580564297,
      "loss": 0.0,
      "num_input_tokens_seen": 4655808,
      "step": 16630
    },
    {
      "epoch": 184.83333333333334,
      "grad_norm": 1.4034239548266214e-08,
      "learning_rate": 0.1891944604036054,
      "loss": 0.0,
      "num_input_tokens_seen": 4657248,
      "step": 16635
    },
    {
      "epoch": 184.88888888888889,
      "grad_norm": 3.141712312526579e-08,
      "learning_rate": 0.1891375989572895,
      "loss": 0.0,
      "num_input_tokens_seen": 4658656,
      "step": 16640
    },
    {
      "epoch": 184.94444444444446,
      "grad_norm": 9.872719530790164e-09,
      "learning_rate": 0.18908073147546398,
      "loss": 0.0,
      "num_input_tokens_seen": 4660064,
      "step": 16645
    },
    {
      "epoch": 185.0,
      "grad_norm": 1.508253610893462e-08,
      "learning_rate": 0.18902385796689858,
      "loss": 0.0,
      "num_input_tokens_seen": 4661424,
      "step": 16650
    },
    {
      "epoch": 185.05555555555554,
      "grad_norm": 7.1007102420139745e-09,
      "learning_rate": 0.18896697844036384,
      "loss": 0.0,
      "num_input_tokens_seen": 4662800,
      "step": 16655
    },
    {
      "epoch": 185.11111111111111,
      "grad_norm": 3.581750718240073e-08,
      "learning_rate": 0.18891009290463137,
      "loss": 0.0,
      "num_input_tokens_seen": 4664208,
      "step": 16660
    },
    {
      "epoch": 185.16666666666666,
      "grad_norm": 2.587174563473127e-08,
      "learning_rate": 0.18885320136847353,
      "loss": 0.0,
      "num_input_tokens_seen": 4665648,
      "step": 16665
    },
    {
      "epoch": 185.22222222222223,
      "grad_norm": 2.0132080891244186e-08,
      "learning_rate": 0.1887963038406639,
      "loss": 0.0,
      "num_input_tokens_seen": 4667024,
      "step": 16670
    },
    {
      "epoch": 185.27777777777777,
      "grad_norm": 2.8480627634053235e-08,
      "learning_rate": 0.18873940032997658,
      "loss": 0.0,
      "num_input_tokens_seen": 4668416,
      "step": 16675
    },
    {
      "epoch": 185.33333333333334,
      "grad_norm": 1.2932977355717412e-08,
      "learning_rate": 0.18868249084518693,
      "loss": 0.0,
      "num_input_tokens_seen": 4669808,
      "step": 16680
    },
    {
      "epoch": 185.38888888888889,
      "grad_norm": 4.587085555840531e-08,
      "learning_rate": 0.18862557539507102,
      "loss": 0.0,
      "num_input_tokens_seen": 4671200,
      "step": 16685
    },
    {
      "epoch": 185.44444444444446,
      "grad_norm": 1.1724019088887871e-08,
      "learning_rate": 0.18856865398840605,
      "loss": 0.0,
      "num_input_tokens_seen": 4672608,
      "step": 16690
    },
    {
      "epoch": 185.5,
      "grad_norm": 1.3370442530913351e-08,
      "learning_rate": 0.18851172663396995,
      "loss": 0.0,
      "num_input_tokens_seen": 4674016,
      "step": 16695
    },
    {
      "epoch": 185.55555555555554,
      "grad_norm": 2.72191140737732e-08,
      "learning_rate": 0.1884547933405416,
      "loss": 0.0,
      "num_input_tokens_seen": 4675408,
      "step": 16700
    },
    {
      "epoch": 185.61111111111111,
      "grad_norm": 1.2365863000241006e-08,
      "learning_rate": 0.1883978541169009,
      "loss": 0.0,
      "num_input_tokens_seen": 4676768,
      "step": 16705
    },
    {
      "epoch": 185.66666666666666,
      "grad_norm": 1.3613563609737866e-08,
      "learning_rate": 0.18834090897182854,
      "loss": 0.0,
      "num_input_tokens_seen": 4678208,
      "step": 16710
    },
    {
      "epoch": 185.72222222222223,
      "grad_norm": 9.189172978096849e-09,
      "learning_rate": 0.1882839579141062,
      "loss": 0.0,
      "num_input_tokens_seen": 4679616,
      "step": 16715
    },
    {
      "epoch": 185.77777777777777,
      "grad_norm": 5.21369862838128e-08,
      "learning_rate": 0.18822700095251646,
      "loss": 0.0,
      "num_input_tokens_seen": 4681056,
      "step": 16720
    },
    {
      "epoch": 185.83333333333334,
      "grad_norm": 2.723957237549257e-08,
      "learning_rate": 0.18817003809584273,
      "loss": 0.0,
      "num_input_tokens_seen": 4682464,
      "step": 16725
    },
    {
      "epoch": 185.88888888888889,
      "grad_norm": 2.9195797779379973e-08,
      "learning_rate": 0.1881130693528695,
      "loss": 0.0,
      "num_input_tokens_seen": 4683824,
      "step": 16730
    },
    {
      "epoch": 185.94444444444446,
      "grad_norm": 2.10577333348283e-08,
      "learning_rate": 0.18805609473238197,
      "loss": 0.0,
      "num_input_tokens_seen": 4685184,
      "step": 16735
    },
    {
      "epoch": 186.0,
      "grad_norm": 1.5501408157092555e-08,
      "learning_rate": 0.18799911424316643,
      "loss": 0.0,
      "num_input_tokens_seen": 4686608,
      "step": 16740
    },
    {
      "epoch": 186.05555555555554,
      "grad_norm": 1.1599524896155344e-08,
      "learning_rate": 0.18794212789400994,
      "loss": 0.0,
      "num_input_tokens_seen": 4687984,
      "step": 16745
    },
    {
      "epoch": 186.11111111111111,
      "grad_norm": 2.3026704099038398e-08,
      "learning_rate": 0.18788513569370052,
      "loss": 0.0,
      "num_input_tokens_seen": 4689376,
      "step": 16750
    },
    {
      "epoch": 186.16666666666666,
      "grad_norm": 2.1611661793485837e-08,
      "learning_rate": 0.1878281376510271,
      "loss": 0.0,
      "num_input_tokens_seen": 4690800,
      "step": 16755
    },
    {
      "epoch": 186.22222222222223,
      "grad_norm": 1.0138821338046e-08,
      "learning_rate": 0.18777113377477941,
      "loss": 0.0,
      "num_input_tokens_seen": 4692192,
      "step": 16760
    },
    {
      "epoch": 186.27777777777777,
      "grad_norm": 1.5083383431147013e-08,
      "learning_rate": 0.1877141240737483,
      "loss": 0.0,
      "num_input_tokens_seen": 4693568,
      "step": 16765
    },
    {
      "epoch": 186.33333333333334,
      "grad_norm": 1.2205170207835181e-08,
      "learning_rate": 0.18765710855672527,
      "loss": 0.0,
      "num_input_tokens_seen": 4694992,
      "step": 16770
    },
    {
      "epoch": 186.38888888888889,
      "grad_norm": 3.26694156171925e-08,
      "learning_rate": 0.18760008723250288,
      "loss": 0.0,
      "num_input_tokens_seen": 4696384,
      "step": 16775
    },
    {
      "epoch": 186.44444444444446,
      "grad_norm": 1.2851717912099048e-08,
      "learning_rate": 0.18754306010987457,
      "loss": 0.0,
      "num_input_tokens_seen": 4697760,
      "step": 16780
    },
    {
      "epoch": 186.5,
      "grad_norm": 2.3964537021470278e-08,
      "learning_rate": 0.18748602719763457,
      "loss": 0.0,
      "num_input_tokens_seen": 4699136,
      "step": 16785
    },
    {
      "epoch": 186.55555555555554,
      "grad_norm": 3.15004449191747e-08,
      "learning_rate": 0.18742898850457804,
      "loss": 0.0,
      "num_input_tokens_seen": 4700512,
      "step": 16790
    },
    {
      "epoch": 186.61111111111111,
      "grad_norm": 7.401340873514073e-09,
      "learning_rate": 0.1873719440395012,
      "loss": 0.0,
      "num_input_tokens_seen": 4701936,
      "step": 16795
    },
    {
      "epoch": 186.66666666666666,
      "grad_norm": 1.2462429310744483e-08,
      "learning_rate": 0.1873148938112009,
      "loss": 0.0,
      "num_input_tokens_seen": 4703376,
      "step": 16800
    },
    {
      "epoch": 186.66666666666666,
      "eval_loss": 1.4217932224273682,
      "eval_runtime": 1.1859,
      "eval_samples_per_second": 33.729,
      "eval_steps_per_second": 16.865,
      "num_input_tokens_seen": 4703376,
      "step": 16800
    },
    {
      "epoch": 186.72222222222223,
      "grad_norm": 2.0408931433735233e-08,
      "learning_rate": 0.18725783782847508,
      "loss": 0.0,
      "num_input_tokens_seen": 4704800,
      "step": 16805
    },
    {
      "epoch": 186.77777777777777,
      "grad_norm": 1.8193027528923267e-08,
      "learning_rate": 0.1872007761001224,
      "loss": 0.0,
      "num_input_tokens_seen": 4706176,
      "step": 16810
    },
    {
      "epoch": 186.83333333333334,
      "grad_norm": 1.135195581980497e-08,
      "learning_rate": 0.1871437086349426,
      "loss": 0.0,
      "num_input_tokens_seen": 4707584,
      "step": 16815
    },
    {
      "epoch": 186.88888888888889,
      "grad_norm": 2.817344046945891e-08,
      "learning_rate": 0.18708663544173615,
      "loss": 0.0,
      "num_input_tokens_seen": 4709024,
      "step": 16820
    },
    {
      "epoch": 186.94444444444446,
      "grad_norm": 4.971862566094387e-08,
      "learning_rate": 0.18702955652930442,
      "loss": 0.0,
      "num_input_tokens_seen": 4710432,
      "step": 16825
    },
    {
      "epoch": 187.0,
      "grad_norm": 2.694315526241553e-08,
      "learning_rate": 0.18697247190644972,
      "loss": 0.0,
      "num_input_tokens_seen": 4711808,
      "step": 16830
    },
    {
      "epoch": 187.05555555555554,
      "grad_norm": 1.8613015129176347e-08,
      "learning_rate": 0.18691538158197527,
      "loss": 0.0,
      "num_input_tokens_seen": 4713184,
      "step": 16835
    },
    {
      "epoch": 187.11111111111111,
      "grad_norm": 2.6637801298079467e-08,
      "learning_rate": 0.1868582855646851,
      "loss": 0.0,
      "num_input_tokens_seen": 4714576,
      "step": 16840
    },
    {
      "epoch": 187.16666666666666,
      "grad_norm": 1.0756949109236302e-08,
      "learning_rate": 0.18680118386338404,
      "loss": 0.0,
      "num_input_tokens_seen": 4715968,
      "step": 16845
    },
    {
      "epoch": 187.22222222222223,
      "grad_norm": 8.398574635748446e-08,
      "learning_rate": 0.18674407648687794,
      "loss": 0.0,
      "num_input_tokens_seen": 4717344,
      "step": 16850
    },
    {
      "epoch": 187.27777777777777,
      "grad_norm": 1.5208062364990838e-08,
      "learning_rate": 0.1866869634439736,
      "loss": 0.0,
      "num_input_tokens_seen": 4718752,
      "step": 16855
    },
    {
      "epoch": 187.33333333333334,
      "grad_norm": 2.246735419930701e-08,
      "learning_rate": 0.18662984474347838,
      "loss": 0.0,
      "num_input_tokens_seen": 4720192,
      "step": 16860
    },
    {
      "epoch": 187.38888888888889,
      "grad_norm": 1.9697253605954756e-08,
      "learning_rate": 0.1865727203942008,
      "loss": 0.0,
      "num_input_tokens_seen": 4721616,
      "step": 16865
    },
    {
      "epoch": 187.44444444444446,
      "grad_norm": 2.530887321938735e-08,
      "learning_rate": 0.1865155904049501,
      "loss": 0.0,
      "num_input_tokens_seen": 4723024,
      "step": 16870
    },
    {
      "epoch": 187.5,
      "grad_norm": 2.198973092504275e-08,
      "learning_rate": 0.1864584547845365,
      "loss": 0.0,
      "num_input_tokens_seen": 4724464,
      "step": 16875
    },
    {
      "epoch": 187.55555555555554,
      "grad_norm": 9.775576792492302e-09,
      "learning_rate": 0.186401313541771,
      "loss": 0.0,
      "num_input_tokens_seen": 4725840,
      "step": 16880
    },
    {
      "epoch": 187.61111111111111,
      "grad_norm": 9.913716958465102e-09,
      "learning_rate": 0.18634416668546552,
      "loss": 0.0,
      "num_input_tokens_seen": 4727264,
      "step": 16885
    },
    {
      "epoch": 187.66666666666666,
      "grad_norm": 2.359237427640437e-08,
      "learning_rate": 0.1862870142244328,
      "loss": 0.0,
      "num_input_tokens_seen": 4728656,
      "step": 16890
    },
    {
      "epoch": 187.72222222222223,
      "grad_norm": 9.625703789595264e-09,
      "learning_rate": 0.1862298561674865,
      "loss": 0.0,
      "num_input_tokens_seen": 4730032,
      "step": 16895
    },
    {
      "epoch": 187.77777777777777,
      "grad_norm": 1.3364688022932114e-08,
      "learning_rate": 0.18617269252344104,
      "loss": 0.0,
      "num_input_tokens_seen": 4731392,
      "step": 16900
    },
    {
      "epoch": 187.83333333333334,
      "grad_norm": 2.013224786878709e-08,
      "learning_rate": 0.18611552330111186,
      "loss": 0.0,
      "num_input_tokens_seen": 4732816,
      "step": 16905
    },
    {
      "epoch": 187.88888888888889,
      "grad_norm": 1.2209541822016945e-08,
      "learning_rate": 0.18605834850931507,
      "loss": 0.0,
      "num_input_tokens_seen": 4734240,
      "step": 16910
    },
    {
      "epoch": 187.94444444444446,
      "grad_norm": 6.054765577800936e-08,
      "learning_rate": 0.18600116815686787,
      "loss": 0.0,
      "num_input_tokens_seen": 4735600,
      "step": 16915
    },
    {
      "epoch": 188.0,
      "grad_norm": 1.496983159654519e-08,
      "learning_rate": 0.1859439822525881,
      "loss": 0.0,
      "num_input_tokens_seen": 4737040,
      "step": 16920
    },
    {
      "epoch": 188.05555555555554,
      "grad_norm": 1.0016797169498659e-08,
      "learning_rate": 0.18588679080529455,
      "loss": 0.0,
      "num_input_tokens_seen": 4738480,
      "step": 16925
    },
    {
      "epoch": 188.11111111111111,
      "grad_norm": 1.2580842145837323e-08,
      "learning_rate": 0.1858295938238069,
      "loss": 0.0,
      "num_input_tokens_seen": 4739936,
      "step": 16930
    },
    {
      "epoch": 188.16666666666666,
      "grad_norm": 2.650889463495787e-08,
      "learning_rate": 0.18577239131694562,
      "loss": 0.0,
      "num_input_tokens_seen": 4741296,
      "step": 16935
    },
    {
      "epoch": 188.22222222222223,
      "grad_norm": 8.674006402031864e-09,
      "learning_rate": 0.18571518329353204,
      "loss": 0.0,
      "num_input_tokens_seen": 4742720,
      "step": 16940
    },
    {
      "epoch": 188.27777777777777,
      "grad_norm": 3.098883638585903e-08,
      "learning_rate": 0.18565796976238838,
      "loss": 0.0,
      "num_input_tokens_seen": 4744128,
      "step": 16945
    },
    {
      "epoch": 188.33333333333334,
      "grad_norm": 1.3622831751547437e-08,
      "learning_rate": 0.18560075073233764,
      "loss": 0.0,
      "num_input_tokens_seen": 4745600,
      "step": 16950
    },
    {
      "epoch": 188.38888888888889,
      "grad_norm": 1.3455979441800991e-08,
      "learning_rate": 0.18554352621220377,
      "loss": 0.0,
      "num_input_tokens_seen": 4746960,
      "step": 16955
    },
    {
      "epoch": 188.44444444444446,
      "grad_norm": 1.2634952639700714e-08,
      "learning_rate": 0.18548629621081153,
      "loss": 0.0,
      "num_input_tokens_seen": 4748352,
      "step": 16960
    },
    {
      "epoch": 188.5,
      "grad_norm": 3.170865880974816e-08,
      "learning_rate": 0.18542906073698645,
      "loss": 0.0,
      "num_input_tokens_seen": 4749728,
      "step": 16965
    },
    {
      "epoch": 188.55555555555554,
      "grad_norm": 1.9552304664216535e-08,
      "learning_rate": 0.18537181979955494,
      "loss": 0.0,
      "num_input_tokens_seen": 4751136,
      "step": 16970
    },
    {
      "epoch": 188.61111111111111,
      "grad_norm": 1.6451588535915107e-08,
      "learning_rate": 0.18531457340734434,
      "loss": 0.0,
      "num_input_tokens_seen": 4752528,
      "step": 16975
    },
    {
      "epoch": 188.66666666666666,
      "grad_norm": 2.1073955025485702e-08,
      "learning_rate": 0.1852573215691827,
      "loss": 0.0,
      "num_input_tokens_seen": 4753968,
      "step": 16980
    },
    {
      "epoch": 188.72222222222223,
      "grad_norm": 8.643226578897156e-09,
      "learning_rate": 0.18520006429389904,
      "loss": 0.0,
      "num_input_tokens_seen": 4755344,
      "step": 16985
    },
    {
      "epoch": 188.77777777777777,
      "grad_norm": 2.5527565838956434e-08,
      "learning_rate": 0.1851428015903231,
      "loss": 0.0,
      "num_input_tokens_seen": 4756752,
      "step": 16990
    },
    {
      "epoch": 188.83333333333334,
      "grad_norm": 1.660074211429219e-08,
      "learning_rate": 0.1850855334672855,
      "loss": 0.0,
      "num_input_tokens_seen": 4758144,
      "step": 16995
    },
    {
      "epoch": 188.88888888888889,
      "grad_norm": 3.480574761738353e-08,
      "learning_rate": 0.1850282599336178,
      "loss": 0.0,
      "num_input_tokens_seen": 4759552,
      "step": 17000
    },
    {
      "epoch": 188.88888888888889,
      "eval_loss": 1.4471523761749268,
      "eval_runtime": 1.1905,
      "eval_samples_per_second": 33.6,
      "eval_steps_per_second": 16.8,
      "num_input_tokens_seen": 4759552,
      "step": 17000
    },
    {
      "epoch": 188.94444444444446,
      "grad_norm": 2.7466645846629945e-08,
      "learning_rate": 0.18497098099815215,
      "loss": 0.0,
      "num_input_tokens_seen": 4760912,
      "step": 17005
    },
    {
      "epoch": 189.0,
      "grad_norm": 2.0113754217732094e-08,
      "learning_rate": 0.18491369666972174,
      "loss": 0.0,
      "num_input_tokens_seen": 4762336,
      "step": 17010
    },
    {
      "epoch": 189.05555555555554,
      "grad_norm": 4.1896718983025494e-08,
      "learning_rate": 0.1848564069571606,
      "loss": 0.0,
      "num_input_tokens_seen": 4763760,
      "step": 17015
    },
    {
      "epoch": 189.11111111111111,
      "grad_norm": 2.415139377376363e-08,
      "learning_rate": 0.18479911186930348,
      "loss": 0.0,
      "num_input_tokens_seen": 4765216,
      "step": 17020
    },
    {
      "epoch": 189.16666666666666,
      "grad_norm": 3.556317906827644e-08,
      "learning_rate": 0.18474181141498597,
      "loss": 0.0,
      "num_input_tokens_seen": 4766640,
      "step": 17025
    },
    {
      "epoch": 189.22222222222223,
      "grad_norm": 3.613998700302545e-08,
      "learning_rate": 0.18468450560304453,
      "loss": 0.0,
      "num_input_tokens_seen": 4768048,
      "step": 17030
    },
    {
      "epoch": 189.27777777777777,
      "grad_norm": 1.585002884496589e-08,
      "learning_rate": 0.1846271944423165,
      "loss": 0.0,
      "num_input_tokens_seen": 4769456,
      "step": 17035
    },
    {
      "epoch": 189.33333333333334,
      "grad_norm": 1.7269805141495453e-08,
      "learning_rate": 0.18456987794163993,
      "loss": 0.0,
      "num_input_tokens_seen": 4770880,
      "step": 17040
    },
    {
      "epoch": 189.38888888888889,
      "grad_norm": 4.1579863108154314e-08,
      "learning_rate": 0.18451255610985373,
      "loss": 0.0,
      "num_input_tokens_seen": 4772304,
      "step": 17045
    },
    {
      "epoch": 189.44444444444446,
      "grad_norm": 4.97331669180312e-08,
      "learning_rate": 0.18445522895579766,
      "loss": 0.0,
      "num_input_tokens_seen": 4773680,
      "step": 17050
    },
    {
      "epoch": 189.5,
      "grad_norm": 1.2918468073053191e-08,
      "learning_rate": 0.1843978964883123,
      "loss": 0.0,
      "num_input_tokens_seen": 4775072,
      "step": 17055
    },
    {
      "epoch": 189.55555555555554,
      "grad_norm": 1.7644479655132272e-08,
      "learning_rate": 0.18434055871623906,
      "loss": 0.0,
      "num_input_tokens_seen": 4776512,
      "step": 17060
    },
    {
      "epoch": 189.61111111111111,
      "grad_norm": 1.5137748832216857e-08,
      "learning_rate": 0.18428321564842007,
      "loss": 0.0,
      "num_input_tokens_seen": 4777904,
      "step": 17065
    },
    {
      "epoch": 189.66666666666666,
      "grad_norm": 1.5782230633476502e-08,
      "learning_rate": 0.18422586729369841,
      "loss": 0.0,
      "num_input_tokens_seen": 4779296,
      "step": 17070
    },
    {
      "epoch": 189.72222222222223,
      "grad_norm": 1.1642844910397798e-08,
      "learning_rate": 0.1841685136609179,
      "loss": 0.0,
      "num_input_tokens_seen": 4780672,
      "step": 17075
    },
    {
      "epoch": 189.77777777777777,
      "grad_norm": 1.713901731648093e-08,
      "learning_rate": 0.18411115475892326,
      "loss": 0.0,
      "num_input_tokens_seen": 4782048,
      "step": 17080
    },
    {
      "epoch": 189.83333333333334,
      "grad_norm": 1.0290758467590422e-08,
      "learning_rate": 0.18405379059655982,
      "loss": 0.0,
      "num_input_tokens_seen": 4783376,
      "step": 17085
    },
    {
      "epoch": 189.88888888888889,
      "grad_norm": 1.3132512854951983e-08,
      "learning_rate": 0.1839964211826739,
      "loss": 0.0,
      "num_input_tokens_seen": 4784800,
      "step": 17090
    },
    {
      "epoch": 189.94444444444446,
      "grad_norm": 1.6913972444854153e-08,
      "learning_rate": 0.18393904652611265,
      "loss": 0.0,
      "num_input_tokens_seen": 4786208,
      "step": 17095
    },
    {
      "epoch": 190.0,
      "grad_norm": 1.5438089917552134e-08,
      "learning_rate": 0.18388166663572392,
      "loss": 0.0,
      "num_input_tokens_seen": 4787584,
      "step": 17100
    },
    {
      "epoch": 190.05555555555554,
      "grad_norm": 1.3787715857915828e-08,
      "learning_rate": 0.18382428152035643,
      "loss": 0.0,
      "num_input_tokens_seen": 4788976,
      "step": 17105
    },
    {
      "epoch": 190.11111111111111,
      "grad_norm": 1.717292974490192e-08,
      "learning_rate": 0.1837668911888596,
      "loss": 0.0,
      "num_input_tokens_seen": 4790400,
      "step": 17110
    },
    {
      "epoch": 190.16666666666666,
      "grad_norm": 4.846056356200279e-08,
      "learning_rate": 0.18370949565008388,
      "loss": 0.0,
      "num_input_tokens_seen": 4791792,
      "step": 17115
    },
    {
      "epoch": 190.22222222222223,
      "grad_norm": 6.422273912676246e-08,
      "learning_rate": 0.1836520949128803,
      "loss": 0.0,
      "num_input_tokens_seen": 4793152,
      "step": 17120
    },
    {
      "epoch": 190.27777777777777,
      "grad_norm": 2.996058512394484e-08,
      "learning_rate": 0.18359468898610076,
      "loss": 0.0,
      "num_input_tokens_seen": 4794576,
      "step": 17125
    },
    {
      "epoch": 190.33333333333334,
      "grad_norm": 8.520647298837503e-09,
      "learning_rate": 0.18353727787859797,
      "loss": 0.0,
      "num_input_tokens_seen": 4795968,
      "step": 17130
    },
    {
      "epoch": 190.38888888888889,
      "grad_norm": 1.0514782822212965e-08,
      "learning_rate": 0.18347986159922552,
      "loss": 0.0,
      "num_input_tokens_seen": 4797408,
      "step": 17135
    },
    {
      "epoch": 190.44444444444446,
      "grad_norm": 2.1377095649199873e-08,
      "learning_rate": 0.1834224401568377,
      "loss": 0.0,
      "num_input_tokens_seen": 4798832,
      "step": 17140
    },
    {
      "epoch": 190.5,
      "grad_norm": 3.4790449632282616e-08,
      "learning_rate": 0.1833650135602896,
      "loss": 0.0,
      "num_input_tokens_seen": 4800240,
      "step": 17145
    },
    {
      "epoch": 190.55555555555554,
      "grad_norm": 2.47494167382456e-08,
      "learning_rate": 0.18330758181843707,
      "loss": 0.0,
      "num_input_tokens_seen": 4801632,
      "step": 17150
    },
    {
      "epoch": 190.61111111111111,
      "grad_norm": 3.8973624327809375e-08,
      "learning_rate": 0.18325014494013686,
      "loss": 0.0,
      "num_input_tokens_seen": 4803040,
      "step": 17155
    },
    {
      "epoch": 190.66666666666666,
      "grad_norm": 1.7400568097514224e-08,
      "learning_rate": 0.18319270293424647,
      "loss": 0.0,
      "num_input_tokens_seen": 4804448,
      "step": 17160
    },
    {
      "epoch": 190.72222222222223,
      "grad_norm": 1.6494212218276516e-08,
      "learning_rate": 0.18313525580962417,
      "loss": 0.0,
      "num_input_tokens_seen": 4805872,
      "step": 17165
    },
    {
      "epoch": 190.77777777777777,
      "grad_norm": 1.6515206979761388e-08,
      "learning_rate": 0.18307780357512896,
      "loss": 0.0,
      "num_input_tokens_seen": 4807264,
      "step": 17170
    },
    {
      "epoch": 190.83333333333334,
      "grad_norm": 1.5375563933162084e-08,
      "learning_rate": 0.1830203462396208,
      "loss": 0.0,
      "num_input_tokens_seen": 4808656,
      "step": 17175
    },
    {
      "epoch": 190.88888888888889,
      "grad_norm": 2.187969805333978e-08,
      "learning_rate": 0.18296288381196033,
      "loss": 0.0,
      "num_input_tokens_seen": 4810032,
      "step": 17180
    },
    {
      "epoch": 190.94444444444446,
      "grad_norm": 2.9184452188246723e-08,
      "learning_rate": 0.1829054163010089,
      "loss": 0.0,
      "num_input_tokens_seen": 4811424,
      "step": 17185
    },
    {
      "epoch": 191.0,
      "grad_norm": 1.7871974122840584e-08,
      "learning_rate": 0.18284794371562874,
      "loss": 0.0,
      "num_input_tokens_seen": 4812784,
      "step": 17190
    },
    {
      "epoch": 191.05555555555554,
      "grad_norm": 4.570212652765804e-08,
      "learning_rate": 0.18279046606468288,
      "loss": 0.0,
      "num_input_tokens_seen": 4814160,
      "step": 17195
    },
    {
      "epoch": 191.11111111111111,
      "grad_norm": 2.332429893669996e-08,
      "learning_rate": 0.1827329833570351,
      "loss": 0.0,
      "num_input_tokens_seen": 4815552,
      "step": 17200
    },
    {
      "epoch": 191.11111111111111,
      "eval_loss": 1.4649169445037842,
      "eval_runtime": 1.1856,
      "eval_samples_per_second": 33.738,
      "eval_steps_per_second": 16.869,
      "num_input_tokens_seen": 4815552,
      "step": 17200
    },
    {
      "epoch": 191.16666666666666,
      "grad_norm": 1.4524861313702786e-08,
      "learning_rate": 0.18267549560154991,
      "loss": 0.0,
      "num_input_tokens_seen": 4816912,
      "step": 17205
    },
    {
      "epoch": 191.22222222222223,
      "grad_norm": 9.36903976622716e-09,
      "learning_rate": 0.18261800280709267,
      "loss": 0.0,
      "num_input_tokens_seen": 4818320,
      "step": 17210
    },
    {
      "epoch": 191.27777777777777,
      "grad_norm": 1.2146910144394951e-08,
      "learning_rate": 0.18256050498252957,
      "loss": 0.0,
      "num_input_tokens_seen": 4819728,
      "step": 17215
    },
    {
      "epoch": 191.33333333333334,
      "grad_norm": 8.396542128252804e-09,
      "learning_rate": 0.18250300213672735,
      "loss": 0.0,
      "num_input_tokens_seen": 4821136,
      "step": 17220
    },
    {
      "epoch": 191.38888888888889,
      "grad_norm": 2.622239847482888e-08,
      "learning_rate": 0.18244549427855378,
      "loss": 0.0,
      "num_input_tokens_seen": 4822544,
      "step": 17225
    },
    {
      "epoch": 191.44444444444446,
      "grad_norm": 1.8479799024362364e-08,
      "learning_rate": 0.1823879814168772,
      "loss": 0.0,
      "num_input_tokens_seen": 4823936,
      "step": 17230
    },
    {
      "epoch": 191.5,
      "grad_norm": 9.759224539607203e-09,
      "learning_rate": 0.18233046356056692,
      "loss": 0.0,
      "num_input_tokens_seen": 4825344,
      "step": 17235
    },
    {
      "epoch": 191.55555555555554,
      "grad_norm": 1.0963398189289819e-08,
      "learning_rate": 0.18227294071849284,
      "loss": 0.0,
      "num_input_tokens_seen": 4826752,
      "step": 17240
    },
    {
      "epoch": 191.61111111111111,
      "grad_norm": 1.605095967249781e-08,
      "learning_rate": 0.18221541289952578,
      "loss": 0.0,
      "num_input_tokens_seen": 4828144,
      "step": 17245
    },
    {
      "epoch": 191.66666666666666,
      "grad_norm": 1.4160803196716643e-08,
      "learning_rate": 0.18215788011253717,
      "loss": 0.0,
      "num_input_tokens_seen": 4829568,
      "step": 17250
    },
    {
      "epoch": 191.72222222222223,
      "grad_norm": 1.3269191079245957e-08,
      "learning_rate": 0.18210034236639935,
      "loss": 0.0,
      "num_input_tokens_seen": 4830896,
      "step": 17255
    },
    {
      "epoch": 191.77777777777777,
      "grad_norm": 2.4725233416234005e-08,
      "learning_rate": 0.1820427996699853,
      "loss": 0.0,
      "num_input_tokens_seen": 4832304,
      "step": 17260
    },
    {
      "epoch": 191.83333333333334,
      "grad_norm": 1.6980845174430215e-08,
      "learning_rate": 0.1819852520321689,
      "loss": 0.0,
      "num_input_tokens_seen": 4833696,
      "step": 17265
    },
    {
      "epoch": 191.88888888888889,
      "grad_norm": 2.3122151304733052e-08,
      "learning_rate": 0.18192769946182466,
      "loss": 0.0,
      "num_input_tokens_seen": 4835152,
      "step": 17270
    },
    {
      "epoch": 191.94444444444446,
      "grad_norm": 8.964256004162507e-09,
      "learning_rate": 0.18187014196782794,
      "loss": 0.0,
      "num_input_tokens_seen": 4836512,
      "step": 17275
    },
    {
      "epoch": 192.0,
      "grad_norm": 2.056965087149365e-08,
      "learning_rate": 0.18181257955905486,
      "loss": 0.0,
      "num_input_tokens_seen": 4837936,
      "step": 17280
    },
    {
      "epoch": 192.05555555555554,
      "grad_norm": 1.2958835782228562e-08,
      "learning_rate": 0.18175501224438217,
      "loss": 0.0,
      "num_input_tokens_seen": 4839312,
      "step": 17285
    },
    {
      "epoch": 192.11111111111111,
      "grad_norm": 3.9547245478388504e-08,
      "learning_rate": 0.18169744003268756,
      "loss": 0.0,
      "num_input_tokens_seen": 4840672,
      "step": 17290
    },
    {
      "epoch": 192.16666666666666,
      "grad_norm": 3.3500313634249324e-08,
      "learning_rate": 0.18163986293284937,
      "loss": 0.0,
      "num_input_tokens_seen": 4842080,
      "step": 17295
    },
    {
      "epoch": 192.22222222222223,
      "grad_norm": 7.387027878280605e-09,
      "learning_rate": 0.18158228095374673,
      "loss": 0.0,
      "num_input_tokens_seen": 4843504,
      "step": 17300
    },
    {
      "epoch": 192.27777777777777,
      "grad_norm": 1.683028116872265e-08,
      "learning_rate": 0.18152469410425945,
      "loss": 0.0,
      "num_input_tokens_seen": 4844912,
      "step": 17305
    },
    {
      "epoch": 192.33333333333334,
      "grad_norm": 1.3139935362005417e-08,
      "learning_rate": 0.18146710239326813,
      "loss": 0.0,
      "num_input_tokens_seen": 4846320,
      "step": 17310
    },
    {
      "epoch": 192.38888888888889,
      "grad_norm": 1.0440564857105983e-08,
      "learning_rate": 0.18140950582965423,
      "loss": 0.0,
      "num_input_tokens_seen": 4847696,
      "step": 17315
    },
    {
      "epoch": 192.44444444444446,
      "grad_norm": 4.690199517654037e-08,
      "learning_rate": 0.1813519044222998,
      "loss": 0.0,
      "num_input_tokens_seen": 4849088,
      "step": 17320
    },
    {
      "epoch": 192.5,
      "grad_norm": 6.681558417653832e-09,
      "learning_rate": 0.18129429818008772,
      "loss": 0.0,
      "num_input_tokens_seen": 4850512,
      "step": 17325
    },
    {
      "epoch": 192.55555555555554,
      "grad_norm": 5.205081254899824e-09,
      "learning_rate": 0.18123668711190163,
      "loss": 0.0,
      "num_input_tokens_seen": 4851904,
      "step": 17330
    },
    {
      "epoch": 192.61111111111111,
      "grad_norm": 7.584842975916217e-09,
      "learning_rate": 0.18117907122662583,
      "loss": 0.0,
      "num_input_tokens_seen": 4853344,
      "step": 17335
    },
    {
      "epoch": 192.66666666666666,
      "grad_norm": 1.6819889481212158e-08,
      "learning_rate": 0.1811214505331454,
      "loss": 0.0,
      "num_input_tokens_seen": 4854768,
      "step": 17340
    },
    {
      "epoch": 192.72222222222223,
      "grad_norm": 2.424889800067831e-08,
      "learning_rate": 0.1810638250403462,
      "loss": 0.0,
      "num_input_tokens_seen": 4856160,
      "step": 17345
    },
    {
      "epoch": 192.77777777777777,
      "grad_norm": 4.803516162610322e-08,
      "learning_rate": 0.1810061947571148,
      "loss": 0.0,
      "num_input_tokens_seen": 4857536,
      "step": 17350
    },
    {
      "epoch": 192.83333333333334,
      "grad_norm": 2.1129075378212292e-08,
      "learning_rate": 0.1809485596923385,
      "loss": 0.0,
      "num_input_tokens_seen": 4858976,
      "step": 17355
    },
    {
      "epoch": 192.88888888888889,
      "grad_norm": 1.2963910833718728e-08,
      "learning_rate": 0.18089091985490546,
      "loss": 0.0,
      "num_input_tokens_seen": 4860384,
      "step": 17360
    },
    {
      "epoch": 192.94444444444446,
      "grad_norm": 9.56357304460198e-09,
      "learning_rate": 0.18083327525370432,
      "loss": 0.0,
      "num_input_tokens_seen": 4861776,
      "step": 17365
    },
    {
      "epoch": 193.0,
      "grad_norm": 2.9150147184964226e-08,
      "learning_rate": 0.18077562589762464,
      "loss": 0.0,
      "num_input_tokens_seen": 4863168,
      "step": 17370
    },
    {
      "epoch": 193.05555555555554,
      "grad_norm": 1.401307425652476e-08,
      "learning_rate": 0.1807179717955567,
      "loss": 0.0,
      "num_input_tokens_seen": 4864544,
      "step": 17375
    },
    {
      "epoch": 193.11111111111111,
      "grad_norm": 1.1903378727140534e-08,
      "learning_rate": 0.1806603129563915,
      "loss": 0.0,
      "num_input_tokens_seen": 4865952,
      "step": 17380
    },
    {
      "epoch": 193.16666666666666,
      "grad_norm": 1.7212311576031425e-08,
      "learning_rate": 0.1806026493890208,
      "loss": 0.0,
      "num_input_tokens_seen": 4867360,
      "step": 17385
    },
    {
      "epoch": 193.22222222222223,
      "grad_norm": 1.8436672633015405e-08,
      "learning_rate": 0.18054498110233688,
      "loss": 0.0,
      "num_input_tokens_seen": 4868784,
      "step": 17390
    },
    {
      "epoch": 193.27777777777777,
      "grad_norm": 2.576272173371308e-08,
      "learning_rate": 0.1804873081052331,
      "loss": 0.0,
      "num_input_tokens_seen": 4870208,
      "step": 17395
    },
    {
      "epoch": 193.33333333333334,
      "grad_norm": 3.032411299841442e-08,
      "learning_rate": 0.18042963040660326,
      "loss": 0.0,
      "num_input_tokens_seen": 4871600,
      "step": 17400
    },
    {
      "epoch": 193.33333333333334,
      "eval_loss": 1.4669480323791504,
      "eval_runtime": 1.186,
      "eval_samples_per_second": 33.725,
      "eval_steps_per_second": 16.863,
      "num_input_tokens_seen": 4871600,
      "step": 17400
    },
    {
      "epoch": 193.38888888888889,
      "grad_norm": 1.6440850458820933e-08,
      "learning_rate": 0.180371948015342,
      "loss": 0.0,
      "num_input_tokens_seen": 4872976,
      "step": 17405
    },
    {
      "epoch": 193.44444444444446,
      "grad_norm": 2.4108523177801544e-08,
      "learning_rate": 0.18031426094034472,
      "loss": 0.0,
      "num_input_tokens_seen": 4874400,
      "step": 17410
    },
    {
      "epoch": 193.5,
      "grad_norm": 2.3559781681115055e-08,
      "learning_rate": 0.18025656919050737,
      "loss": 0.0,
      "num_input_tokens_seen": 4875792,
      "step": 17415
    },
    {
      "epoch": 193.55555555555554,
      "grad_norm": 1.581096142899696e-08,
      "learning_rate": 0.18019887277472688,
      "loss": 0.0,
      "num_input_tokens_seen": 4877200,
      "step": 17420
    },
    {
      "epoch": 193.61111111111111,
      "grad_norm": 2.5782753709790995e-08,
      "learning_rate": 0.18014117170190067,
      "loss": 0.0,
      "num_input_tokens_seen": 4878624,
      "step": 17425
    },
    {
      "epoch": 193.66666666666666,
      "grad_norm": 6.566248877959424e-09,
      "learning_rate": 0.18008346598092703,
      "loss": 0.0,
      "num_input_tokens_seen": 4880048,
      "step": 17430
    },
    {
      "epoch": 193.72222222222223,
      "grad_norm": 1.0513059756078746e-08,
      "learning_rate": 0.18002575562070489,
      "loss": 0.0,
      "num_input_tokens_seen": 4881440,
      "step": 17435
    },
    {
      "epoch": 193.77777777777777,
      "grad_norm": 1.5071270453859142e-08,
      "learning_rate": 0.1799680406301339,
      "loss": 0.0,
      "num_input_tokens_seen": 4882880,
      "step": 17440
    },
    {
      "epoch": 193.83333333333334,
      "grad_norm": 2.05972856548442e-08,
      "learning_rate": 0.17991032101811447,
      "loss": 0.0,
      "num_input_tokens_seen": 4884272,
      "step": 17445
    },
    {
      "epoch": 193.88888888888889,
      "grad_norm": 1.3923663999548808e-08,
      "learning_rate": 0.1798525967935476,
      "loss": 0.0,
      "num_input_tokens_seen": 4885664,
      "step": 17450
    },
    {
      "epoch": 193.94444444444446,
      "grad_norm": 1.7013370268159633e-08,
      "learning_rate": 0.17979486796533517,
      "loss": 0.0,
      "num_input_tokens_seen": 4887072,
      "step": 17455
    },
    {
      "epoch": 194.0,
      "grad_norm": 5.273439018793624e-09,
      "learning_rate": 0.1797371345423797,
      "loss": 0.0,
      "num_input_tokens_seen": 4888464,
      "step": 17460
    },
    {
      "epoch": 194.05555555555554,
      "grad_norm": 1.9346893864735648e-08,
      "learning_rate": 0.17967939653358436,
      "loss": 0.0,
      "num_input_tokens_seen": 4889856,
      "step": 17465
    },
    {
      "epoch": 194.11111111111111,
      "grad_norm": 9.137284706639548e-09,
      "learning_rate": 0.17962165394785315,
      "loss": 0.0,
      "num_input_tokens_seen": 4891216,
      "step": 17470
    },
    {
      "epoch": 194.16666666666666,
      "grad_norm": 8.81153550125191e-09,
      "learning_rate": 0.17956390679409057,
      "loss": 0.0,
      "num_input_tokens_seen": 4892640,
      "step": 17475
    },
    {
      "epoch": 194.22222222222223,
      "grad_norm": 2.128508569398946e-08,
      "learning_rate": 0.1795061550812021,
      "loss": 0.0,
      "num_input_tokens_seen": 4894048,
      "step": 17480
    },
    {
      "epoch": 194.27777777777777,
      "grad_norm": 5.940503200463354e-09,
      "learning_rate": 0.1794483988180937,
      "loss": 0.0,
      "num_input_tokens_seen": 4895472,
      "step": 17485
    },
    {
      "epoch": 194.33333333333334,
      "grad_norm": 2.524623354815958e-08,
      "learning_rate": 0.17939063801367214,
      "loss": 0.0,
      "num_input_tokens_seen": 4896848,
      "step": 17490
    },
    {
      "epoch": 194.38888888888889,
      "grad_norm": 1.8763280706934893e-08,
      "learning_rate": 0.17933287267684483,
      "loss": 0.0,
      "num_input_tokens_seen": 4898224,
      "step": 17495
    },
    {
      "epoch": 194.44444444444446,
      "grad_norm": 1.7495956683433178e-08,
      "learning_rate": 0.17927510281651995,
      "loss": 0.0,
      "num_input_tokens_seen": 4899616,
      "step": 17500
    },
    {
      "epoch": 194.5,
      "grad_norm": 2.614514471588336e-08,
      "learning_rate": 0.17921732844160634,
      "loss": 0.0,
      "num_input_tokens_seen": 4901024,
      "step": 17505
    },
    {
      "epoch": 194.55555555555554,
      "grad_norm": 1.4029772898993542e-08,
      "learning_rate": 0.17915954956101351,
      "loss": 0.0,
      "num_input_tokens_seen": 4902432,
      "step": 17510
    },
    {
      "epoch": 194.61111111111111,
      "grad_norm": 2.3766894230448088e-08,
      "learning_rate": 0.17910176618365165,
      "loss": 0.0,
      "num_input_tokens_seen": 4903872,
      "step": 17515
    },
    {
      "epoch": 194.66666666666666,
      "grad_norm": 9.19189702131007e-09,
      "learning_rate": 0.17904397831843177,
      "loss": 0.0,
      "num_input_tokens_seen": 4905248,
      "step": 17520
    },
    {
      "epoch": 194.72222222222223,
      "grad_norm": 1.3639482432381556e-08,
      "learning_rate": 0.17898618597426547,
      "loss": 0.0,
      "num_input_tokens_seen": 4906656,
      "step": 17525
    },
    {
      "epoch": 194.77777777777777,
      "grad_norm": 2.915759544919183e-08,
      "learning_rate": 0.17892838916006495,
      "loss": 0.0,
      "num_input_tokens_seen": 4908080,
      "step": 17530
    },
    {
      "epoch": 194.83333333333334,
      "grad_norm": 3.8116027667456365e-08,
      "learning_rate": 0.17887058788474333,
      "loss": 0.0,
      "num_input_tokens_seen": 4909488,
      "step": 17535
    },
    {
      "epoch": 194.88888888888889,
      "grad_norm": 9.938597500536162e-09,
      "learning_rate": 0.17881278215721427,
      "loss": 0.0,
      "num_input_tokens_seen": 4910880,
      "step": 17540
    },
    {
      "epoch": 194.94444444444446,
      "grad_norm": 2.3216625066879715e-08,
      "learning_rate": 0.1787549719863921,
      "loss": 0.0,
      "num_input_tokens_seen": 4912224,
      "step": 17545
    },
    {
      "epoch": 195.0,
      "grad_norm": 3.0612699930543386e-08,
      "learning_rate": 0.17869715738119188,
      "loss": 0.0,
      "num_input_tokens_seen": 4913616,
      "step": 17550
    },
    {
      "epoch": 195.05555555555554,
      "grad_norm": 1.2533011073401212e-08,
      "learning_rate": 0.17863933835052936,
      "loss": 0.0,
      "num_input_tokens_seen": 4915024,
      "step": 17555
    },
    {
      "epoch": 195.11111111111111,
      "grad_norm": 1.0926541449407523e-08,
      "learning_rate": 0.17858151490332097,
      "loss": 0.0,
      "num_input_tokens_seen": 4916496,
      "step": 17560
    },
    {
      "epoch": 195.16666666666666,
      "grad_norm": 1.0531126193313867e-08,
      "learning_rate": 0.17852368704848381,
      "loss": 0.0,
      "num_input_tokens_seen": 4917936,
      "step": 17565
    },
    {
      "epoch": 195.22222222222223,
      "grad_norm": 1.2437772589635188e-08,
      "learning_rate": 0.17846585479493565,
      "loss": 0.0,
      "num_input_tokens_seen": 4919392,
      "step": 17570
    },
    {
      "epoch": 195.27777777777777,
      "grad_norm": 5.000574176960981e-09,
      "learning_rate": 0.178408018151595,
      "loss": 0.0,
      "num_input_tokens_seen": 4920752,
      "step": 17575
    },
    {
      "epoch": 195.33333333333334,
      "grad_norm": 1.4833420713955547e-08,
      "learning_rate": 0.17835017712738085,
      "loss": 0.0,
      "num_input_tokens_seen": 4922144,
      "step": 17580
    },
    {
      "epoch": 195.38888888888889,
      "grad_norm": 1.4703841699770237e-08,
      "learning_rate": 0.17829233173121323,
      "loss": 0.0,
      "num_input_tokens_seen": 4923536,
      "step": 17585
    },
    {
      "epoch": 195.44444444444446,
      "grad_norm": 2.063259074702728e-08,
      "learning_rate": 0.17823448197201244,
      "loss": 0.0,
      "num_input_tokens_seen": 4924928,
      "step": 17590
    },
    {
      "epoch": 195.5,
      "grad_norm": 1.7162882670618274e-08,
      "learning_rate": 0.1781766278586997,
      "loss": 0.0,
      "num_input_tokens_seen": 4926288,
      "step": 17595
    },
    {
      "epoch": 195.55555555555554,
      "grad_norm": 1.8650778699225157e-08,
      "learning_rate": 0.1781187694001969,
      "loss": 0.0,
      "num_input_tokens_seen": 4927696,
      "step": 17600
    },
    {
      "epoch": 195.55555555555554,
      "eval_loss": 1.4431090354919434,
      "eval_runtime": 1.1835,
      "eval_samples_per_second": 33.798,
      "eval_steps_per_second": 16.899,
      "num_input_tokens_seen": 4927696,
      "step": 17600
    },
    {
      "epoch": 195.61111111111111,
      "grad_norm": 1.1701049906776007e-08,
      "learning_rate": 0.1780609066054265,
      "loss": 0.0,
      "num_input_tokens_seen": 4929040,
      "step": 17605
    },
    {
      "epoch": 195.66666666666666,
      "grad_norm": 9.42751032795286e-09,
      "learning_rate": 0.17800303948331164,
      "loss": 0.0,
      "num_input_tokens_seen": 4930432,
      "step": 17610
    },
    {
      "epoch": 195.72222222222223,
      "grad_norm": 2.1345153200513778e-08,
      "learning_rate": 0.1779451680427762,
      "loss": 0.0,
      "num_input_tokens_seen": 4931840,
      "step": 17615
    },
    {
      "epoch": 195.77777777777777,
      "grad_norm": 4.5757843736282666e-08,
      "learning_rate": 0.17788729229274464,
      "loss": 0.0,
      "num_input_tokens_seen": 4933216,
      "step": 17620
    },
    {
      "epoch": 195.83333333333334,
      "grad_norm": 5.29021582096334e-09,
      "learning_rate": 0.17782941224214222,
      "loss": 0.0,
      "num_input_tokens_seen": 4934576,
      "step": 17625
    },
    {
      "epoch": 195.88888888888889,
      "grad_norm": 3.3917810782213564e-08,
      "learning_rate": 0.17777152789989464,
      "loss": 0.0,
      "num_input_tokens_seen": 4936016,
      "step": 17630
    },
    {
      "epoch": 195.94444444444446,
      "grad_norm": 1.6334894326064386e-08,
      "learning_rate": 0.17771363927492845,
      "loss": 0.0,
      "num_input_tokens_seen": 4937424,
      "step": 17635
    },
    {
      "epoch": 196.0,
      "grad_norm": 1.2883350386516668e-08,
      "learning_rate": 0.17765574637617085,
      "loss": 0.0,
      "num_input_tokens_seen": 4938816,
      "step": 17640
    },
    {
      "epoch": 196.05555555555554,
      "grad_norm": 1.691940099135536e-08,
      "learning_rate": 0.17759784921254962,
      "loss": 0.0,
      "num_input_tokens_seen": 4940224,
      "step": 17645
    },
    {
      "epoch": 196.11111111111111,
      "grad_norm": 1.2731868004323132e-08,
      "learning_rate": 0.1775399477929932,
      "loss": 0.0,
      "num_input_tokens_seen": 4941584,
      "step": 17650
    },
    {
      "epoch": 196.16666666666666,
      "grad_norm": 9.061269956589513e-09,
      "learning_rate": 0.17748204212643076,
      "loss": 0.0,
      "num_input_tokens_seen": 4942944,
      "step": 17655
    },
    {
      "epoch": 196.22222222222223,
      "grad_norm": 1.7761223602974496e-08,
      "learning_rate": 0.17742413222179204,
      "loss": 0.0,
      "num_input_tokens_seen": 4944384,
      "step": 17660
    },
    {
      "epoch": 196.27777777777777,
      "grad_norm": 2.468671844724213e-08,
      "learning_rate": 0.17736621808800754,
      "loss": 0.0,
      "num_input_tokens_seen": 4945792,
      "step": 17665
    },
    {
      "epoch": 196.33333333333334,
      "grad_norm": 1.0667109862083635e-08,
      "learning_rate": 0.17730829973400827,
      "loss": 0.0,
      "num_input_tokens_seen": 4947200,
      "step": 17670
    },
    {
      "epoch": 196.38888888888889,
      "grad_norm": 1.4803300807386677e-08,
      "learning_rate": 0.17725037716872602,
      "loss": 0.0,
      "num_input_tokens_seen": 4948608,
      "step": 17675
    },
    {
      "epoch": 196.44444444444446,
      "grad_norm": 9.445641602212618e-09,
      "learning_rate": 0.17719245040109313,
      "loss": 0.0,
      "num_input_tokens_seen": 4949984,
      "step": 17680
    },
    {
      "epoch": 196.5,
      "grad_norm": 1.3650602426196201e-08,
      "learning_rate": 0.17713451944004271,
      "loss": 0.0,
      "num_input_tokens_seen": 4951328,
      "step": 17685
    },
    {
      "epoch": 196.55555555555554,
      "grad_norm": 1.3196898684952885e-08,
      "learning_rate": 0.17707658429450843,
      "loss": 0.0,
      "num_input_tokens_seen": 4952720,
      "step": 17690
    },
    {
      "epoch": 196.61111111111111,
      "grad_norm": 1.906184188271709e-08,
      "learning_rate": 0.1770186449734245,
      "loss": 0.0,
      "num_input_tokens_seen": 4954160,
      "step": 17695
    },
    {
      "epoch": 196.66666666666666,
      "grad_norm": 1.7027971921379503e-08,
      "learning_rate": 0.17696070148572599,
      "loss": 0.0,
      "num_input_tokens_seen": 4955568,
      "step": 17700
    },
    {
      "epoch": 196.72222222222223,
      "grad_norm": 1.7683101205534513e-08,
      "learning_rate": 0.17690275384034856,
      "loss": 0.0,
      "num_input_tokens_seen": 4956944,
      "step": 17705
    },
    {
      "epoch": 196.77777777777777,
      "grad_norm": 1.1796895904581106e-08,
      "learning_rate": 0.17684480204622835,
      "loss": 0.0,
      "num_input_tokens_seen": 4958288,
      "step": 17710
    },
    {
      "epoch": 196.83333333333334,
      "grad_norm": 8.883136004556036e-09,
      "learning_rate": 0.1767868461123023,
      "loss": 0.0,
      "num_input_tokens_seen": 4959616,
      "step": 17715
    },
    {
      "epoch": 196.88888888888889,
      "grad_norm": 2.04869312625533e-08,
      "learning_rate": 0.176728886047508,
      "loss": 0.0,
      "num_input_tokens_seen": 4961024,
      "step": 17720
    },
    {
      "epoch": 196.94444444444446,
      "grad_norm": 1.437652308311499e-08,
      "learning_rate": 0.17667092186078362,
      "loss": 0.0,
      "num_input_tokens_seen": 4962448,
      "step": 17725
    },
    {
      "epoch": 197.0,
      "grad_norm": 2.8377877825391806e-08,
      "learning_rate": 0.17661295356106785,
      "loss": 0.0,
      "num_input_tokens_seen": 4963872,
      "step": 17730
    },
    {
      "epoch": 197.05555555555554,
      "grad_norm": 1.3134926035718308e-08,
      "learning_rate": 0.1765549811573002,
      "loss": 0.0,
      "num_input_tokens_seen": 4965280,
      "step": 17735
    },
    {
      "epoch": 197.11111111111111,
      "grad_norm": 8.558406427994214e-09,
      "learning_rate": 0.17649700465842078,
      "loss": 0.0,
      "num_input_tokens_seen": 4966688,
      "step": 17740
    },
    {
      "epoch": 197.16666666666666,
      "grad_norm": 2.3190972697761936e-08,
      "learning_rate": 0.17643902407337023,
      "loss": 0.0,
      "num_input_tokens_seen": 4968064,
      "step": 17745
    },
    {
      "epoch": 197.22222222222223,
      "grad_norm": 7.339486796098527e-09,
      "learning_rate": 0.17638103941108993,
      "loss": 0.0,
      "num_input_tokens_seen": 4969408,
      "step": 17750
    },
    {
      "epoch": 197.27777777777777,
      "grad_norm": 1.404216209976994e-08,
      "learning_rate": 0.1763230506805218,
      "loss": 0.0,
      "num_input_tokens_seen": 4970752,
      "step": 17755
    },
    {
      "epoch": 197.33333333333334,
      "grad_norm": 1.3293036893458066e-08,
      "learning_rate": 0.1762650578906085,
      "loss": 0.0,
      "num_input_tokens_seen": 4972176,
      "step": 17760
    },
    {
      "epoch": 197.38888888888889,
      "grad_norm": 9.27835142050526e-09,
      "learning_rate": 0.1762070610502932,
      "loss": 0.0,
      "num_input_tokens_seen": 4973600,
      "step": 17765
    },
    {
      "epoch": 197.44444444444446,
      "grad_norm": 1.3179354496628548e-08,
      "learning_rate": 0.17614906016851975,
      "loss": 0.0,
      "num_input_tokens_seen": 4974992,
      "step": 17770
    },
    {
      "epoch": 197.5,
      "grad_norm": 2.0632988650959305e-08,
      "learning_rate": 0.17609105525423258,
      "loss": 0.0,
      "num_input_tokens_seen": 4976384,
      "step": 17775
    },
    {
      "epoch": 197.55555555555554,
      "grad_norm": 1.8152872982568624e-08,
      "learning_rate": 0.1760330463163768,
      "loss": 0.0,
      "num_input_tokens_seen": 4977808,
      "step": 17780
    },
    {
      "epoch": 197.61111111111111,
      "grad_norm": 9.008303436530696e-09,
      "learning_rate": 0.17597503336389816,
      "loss": 0.0,
      "num_input_tokens_seen": 4979216,
      "step": 17785
    },
    {
      "epoch": 197.66666666666666,
      "grad_norm": 1.4762314926031195e-08,
      "learning_rate": 0.17591701640574298,
      "loss": 0.0,
      "num_input_tokens_seen": 4980592,
      "step": 17790
    },
    {
      "epoch": 197.72222222222223,
      "grad_norm": 1.4411541293668506e-08,
      "learning_rate": 0.17585899545085815,
      "loss": 0.0,
      "num_input_tokens_seen": 4982016,
      "step": 17795
    },
    {
      "epoch": 197.77777777777777,
      "grad_norm": 2.0593915905919857e-08,
      "learning_rate": 0.17580097050819124,
      "loss": 0.0,
      "num_input_tokens_seen": 4983424,
      "step": 17800
    },
    {
      "epoch": 197.77777777777777,
      "eval_loss": 1.4888417720794678,
      "eval_runtime": 1.1898,
      "eval_samples_per_second": 33.62,
      "eval_steps_per_second": 16.81,
      "num_input_tokens_seen": 4983424,
      "step": 17800
    },
    {
      "epoch": 197.83333333333334,
      "grad_norm": 7.4311112818747915e-09,
      "learning_rate": 0.17574294158669046,
      "loss": 0.0,
      "num_input_tokens_seen": 4984816,
      "step": 17805
    },
    {
      "epoch": 197.88888888888889,
      "grad_norm": 1.1227822227510842e-08,
      "learning_rate": 0.17568490869530456,
      "loss": 0.0,
      "num_input_tokens_seen": 4986240,
      "step": 17810
    },
    {
      "epoch": 197.94444444444446,
      "grad_norm": 4.233206496451203e-08,
      "learning_rate": 0.17562687184298295,
      "loss": 0.0,
      "num_input_tokens_seen": 4987664,
      "step": 17815
    },
    {
      "epoch": 198.0,
      "grad_norm": 2.2621774675712913e-08,
      "learning_rate": 0.1755688310386757,
      "loss": 0.0,
      "num_input_tokens_seen": 4989088,
      "step": 17820
    },
    {
      "epoch": 198.05555555555554,
      "grad_norm": 6.150161713236457e-09,
      "learning_rate": 0.17551078629133335,
      "loss": 0.0,
      "num_input_tokens_seen": 4990496,
      "step": 17825
    },
    {
      "epoch": 198.11111111111111,
      "grad_norm": 9.058360284086575e-09,
      "learning_rate": 0.17545273760990718,
      "loss": 0.0,
      "num_input_tokens_seen": 4991888,
      "step": 17830
    },
    {
      "epoch": 198.16666666666666,
      "grad_norm": 4.327233238399231e-09,
      "learning_rate": 0.17539468500334904,
      "loss": 0.0,
      "num_input_tokens_seen": 4993280,
      "step": 17835
    },
    {
      "epoch": 198.22222222222223,
      "grad_norm": 1.2187978626343465e-08,
      "learning_rate": 0.17533662848061132,
      "loss": 0.0,
      "num_input_tokens_seen": 4994688,
      "step": 17840
    },
    {
      "epoch": 198.27777777777777,
      "grad_norm": 1.2549588923604915e-08,
      "learning_rate": 0.1752785680506471,
      "loss": 0.0,
      "num_input_tokens_seen": 4996112,
      "step": 17845
    },
    {
      "epoch": 198.33333333333334,
      "grad_norm": 3.0723711574864865e-08,
      "learning_rate": 0.17522050372241,
      "loss": 0.0,
      "num_input_tokens_seen": 4997520,
      "step": 17850
    },
    {
      "epoch": 198.38888888888889,
      "grad_norm": 3.412171167838096e-08,
      "learning_rate": 0.17516243550485425,
      "loss": 0.0,
      "num_input_tokens_seen": 4998928,
      "step": 17855
    },
    {
      "epoch": 198.44444444444446,
      "grad_norm": 1.078924150021976e-08,
      "learning_rate": 0.17510436340693478,
      "loss": 0.0,
      "num_input_tokens_seen": 5000288,
      "step": 17860
    },
    {
      "epoch": 198.5,
      "grad_norm": 1.7663079887597632e-08,
      "learning_rate": 0.175046287437607,
      "loss": 0.0,
      "num_input_tokens_seen": 5001712,
      "step": 17865
    },
    {
      "epoch": 198.55555555555554,
      "grad_norm": 1.0840085273855493e-08,
      "learning_rate": 0.17498820760582695,
      "loss": 0.0,
      "num_input_tokens_seen": 5003104,
      "step": 17870
    },
    {
      "epoch": 198.61111111111111,
      "grad_norm": 2.0460204197547682e-08,
      "learning_rate": 0.1749301239205512,
      "loss": 0.0,
      "num_input_tokens_seen": 5004496,
      "step": 17875
    },
    {
      "epoch": 198.66666666666666,
      "grad_norm": 1.3970852030809056e-08,
      "learning_rate": 0.1748720363907371,
      "loss": 0.0,
      "num_input_tokens_seen": 5005936,
      "step": 17880
    },
    {
      "epoch": 198.72222222222223,
      "grad_norm": 1.1038634006865777e-08,
      "learning_rate": 0.17481394502534242,
      "loss": 0.0,
      "num_input_tokens_seen": 5007328,
      "step": 17885
    },
    {
      "epoch": 198.77777777777777,
      "grad_norm": 1.3717102120835989e-08,
      "learning_rate": 0.17475584983332562,
      "loss": 0.0,
      "num_input_tokens_seen": 5008720,
      "step": 17890
    },
    {
      "epoch": 198.83333333333334,
      "grad_norm": 1.8837056359188864e-08,
      "learning_rate": 0.17469775082364558,
      "loss": 0.0,
      "num_input_tokens_seen": 5010112,
      "step": 17895
    },
    {
      "epoch": 198.88888888888889,
      "grad_norm": 1.538425209446359e-08,
      "learning_rate": 0.17463964800526205,
      "loss": 0.0,
      "num_input_tokens_seen": 5011520,
      "step": 17900
    },
    {
      "epoch": 198.94444444444446,
      "grad_norm": 9.293673386423507e-09,
      "learning_rate": 0.17458154138713522,
      "loss": 0.0,
      "num_input_tokens_seen": 5012960,
      "step": 17905
    },
    {
      "epoch": 199.0,
      "grad_norm": 6.661525997486706e-09,
      "learning_rate": 0.17452343097822576,
      "loss": 0.0,
      "num_input_tokens_seen": 5014352,
      "step": 17910
    },
    {
      "epoch": 199.05555555555554,
      "grad_norm": 1.848653496949737e-08,
      "learning_rate": 0.17446531678749497,
      "loss": 0.0,
      "num_input_tokens_seen": 5015728,
      "step": 17915
    },
    {
      "epoch": 199.11111111111111,
      "grad_norm": 1.9359346126179844e-08,
      "learning_rate": 0.17440719882390496,
      "loss": 0.0,
      "num_input_tokens_seen": 5017152,
      "step": 17920
    },
    {
      "epoch": 199.16666666666666,
      "grad_norm": 1.1691143164682671e-08,
      "learning_rate": 0.17434907709641814,
      "loss": 0.0,
      "num_input_tokens_seen": 5018560,
      "step": 17925
    },
    {
      "epoch": 199.22222222222223,
      "grad_norm": 6.795470408604842e-09,
      "learning_rate": 0.17429095161399769,
      "loss": 0.0,
      "num_input_tokens_seen": 5019936,
      "step": 17930
    },
    {
      "epoch": 199.27777777777777,
      "grad_norm": 9.695134473020062e-09,
      "learning_rate": 0.1742328223856072,
      "loss": 0.0,
      "num_input_tokens_seen": 5021344,
      "step": 17935
    },
    {
      "epoch": 199.33333333333334,
      "grad_norm": 1.1034144264954193e-08,
      "learning_rate": 0.174174689420211,
      "loss": 0.0,
      "num_input_tokens_seen": 5022704,
      "step": 17940
    },
    {
      "epoch": 199.38888888888889,
      "grad_norm": 1.646404435007298e-08,
      "learning_rate": 0.1741165527267739,
      "loss": 0.0,
      "num_input_tokens_seen": 5024112,
      "step": 17945
    },
    {
      "epoch": 199.44444444444446,
      "grad_norm": 2.2328020321538133e-08,
      "learning_rate": 0.17405841231426125,
      "loss": 0.0,
      "num_input_tokens_seen": 5025504,
      "step": 17950
    },
    {
      "epoch": 199.5,
      "grad_norm": 2.481208660753964e-08,
      "learning_rate": 0.1740002681916391,
      "loss": 0.0,
      "num_input_tokens_seen": 5026912,
      "step": 17955
    },
    {
      "epoch": 199.55555555555554,
      "grad_norm": 1.3925467889919219e-08,
      "learning_rate": 0.17394212036787401,
      "loss": 0.0,
      "num_input_tokens_seen": 5028304,
      "step": 17960
    },
    {
      "epoch": 199.61111111111111,
      "grad_norm": 2.4852393920582472e-08,
      "learning_rate": 0.1738839688519331,
      "loss": 0.0,
      "num_input_tokens_seen": 5029728,
      "step": 17965
    },
    {
      "epoch": 199.66666666666666,
      "grad_norm": 2.4828748834693215e-08,
      "learning_rate": 0.17382581365278402,
      "loss": 0.0,
      "num_input_tokens_seen": 5031120,
      "step": 17970
    },
    {
      "epoch": 199.72222222222223,
      "grad_norm": 6.248276118725471e-09,
      "learning_rate": 0.17376765477939507,
      "loss": 0.0,
      "num_input_tokens_seen": 5032512,
      "step": 17975
    },
    {
      "epoch": 199.77777777777777,
      "grad_norm": 1.2136207594437565e-08,
      "learning_rate": 0.1737094922407351,
      "loss": 0.0,
      "num_input_tokens_seen": 5033920,
      "step": 17980
    },
    {
      "epoch": 199.83333333333334,
      "grad_norm": 1.0577775988451776e-08,
      "learning_rate": 0.1736513260457734,
      "loss": 0.0,
      "num_input_tokens_seen": 5035312,
      "step": 17985
    },
    {
      "epoch": 199.88888888888889,
      "grad_norm": 6.9860783824537975e-09,
      "learning_rate": 0.17359315620348006,
      "loss": 0.0,
      "num_input_tokens_seen": 5036720,
      "step": 17990
    },
    {
      "epoch": 199.94444444444446,
      "grad_norm": 1.569773111498307e-08,
      "learning_rate": 0.17353498272282547,
      "loss": 0.0,
      "num_input_tokens_seen": 5038112,
      "step": 17995
    },
    {
      "epoch": 200.0,
      "grad_norm": 2.115298158855694e-08,
      "learning_rate": 0.17347680561278087,
      "loss": 0.0,
      "num_input_tokens_seen": 5039536,
      "step": 18000
    },
    {
      "epoch": 200.0,
      "eval_loss": 1.5015560388565063,
      "eval_runtime": 1.1811,
      "eval_samples_per_second": 33.866,
      "eval_steps_per_second": 16.933,
      "num_input_tokens_seen": 5039536,
      "step": 18000
    },
    {
      "epoch": 200.05555555555554,
      "grad_norm": 2.559913170330219e-08,
      "learning_rate": 0.1734186248823178,
      "loss": 0.0,
      "num_input_tokens_seen": 5040944,
      "step": 18005
    },
    {
      "epoch": 200.11111111111111,
      "grad_norm": 1.1470172367467057e-08,
      "learning_rate": 0.17336044054040844,
      "loss": 0.0,
      "num_input_tokens_seen": 5042320,
      "step": 18010
    },
    {
      "epoch": 200.16666666666666,
      "grad_norm": 3.933536518729852e-08,
      "learning_rate": 0.1733022525960256,
      "loss": 0.0,
      "num_input_tokens_seen": 5043728,
      "step": 18015
    },
    {
      "epoch": 200.22222222222223,
      "grad_norm": 1.0642368764024468e-08,
      "learning_rate": 0.1732440610581426,
      "loss": 0.0,
      "num_input_tokens_seen": 5045104,
      "step": 18020
    },
    {
      "epoch": 200.27777777777777,
      "grad_norm": 1.4593513064653507e-08,
      "learning_rate": 0.17318586593573326,
      "loss": 0.0,
      "num_input_tokens_seen": 5046512,
      "step": 18025
    },
    {
      "epoch": 200.33333333333334,
      "grad_norm": 8.257356576280017e-09,
      "learning_rate": 0.17312766723777204,
      "loss": 0.0,
      "num_input_tokens_seen": 5047920,
      "step": 18030
    },
    {
      "epoch": 200.38888888888889,
      "grad_norm": 9.062337547049992e-09,
      "learning_rate": 0.1730694649732339,
      "loss": 0.0,
      "num_input_tokens_seen": 5049328,
      "step": 18035
    },
    {
      "epoch": 200.44444444444446,
      "grad_norm": 1.4577466345144785e-08,
      "learning_rate": 0.17301125915109428,
      "loss": 0.0,
      "num_input_tokens_seen": 5050688,
      "step": 18040
    },
    {
      "epoch": 200.5,
      "grad_norm": 2.8520869221893008e-08,
      "learning_rate": 0.17295304978032938,
      "loss": 0.0,
      "num_input_tokens_seen": 5052080,
      "step": 18045
    },
    {
      "epoch": 200.55555555555554,
      "grad_norm": 1.31742847742089e-08,
      "learning_rate": 0.17289483686991577,
      "loss": 0.0,
      "num_input_tokens_seen": 5053504,
      "step": 18050
    },
    {
      "epoch": 200.61111111111111,
      "grad_norm": 2.4423666644679543e-08,
      "learning_rate": 0.1728366204288306,
      "loss": 0.0,
      "num_input_tokens_seen": 5054864,
      "step": 18055
    },
    {
      "epoch": 200.66666666666666,
      "grad_norm": 1.2100111135282532e-08,
      "learning_rate": 0.17277840046605153,
      "loss": 0.0,
      "num_input_tokens_seen": 5056224,
      "step": 18060
    },
    {
      "epoch": 200.72222222222223,
      "grad_norm": 5.363759658649769e-09,
      "learning_rate": 0.17272017699055686,
      "loss": 0.0,
      "num_input_tokens_seen": 5057600,
      "step": 18065
    },
    {
      "epoch": 200.77777777777777,
      "grad_norm": 1.012854244919481e-08,
      "learning_rate": 0.17266195001132542,
      "loss": 0.0,
      "num_input_tokens_seen": 5058992,
      "step": 18070
    },
    {
      "epoch": 200.83333333333334,
      "grad_norm": 1.0159203256421279e-08,
      "learning_rate": 0.17260371953733647,
      "loss": 0.0,
      "num_input_tokens_seen": 5060432,
      "step": 18075
    },
    {
      "epoch": 200.88888888888889,
      "grad_norm": 1.3043319313510437e-08,
      "learning_rate": 0.1725454855775699,
      "loss": 0.0,
      "num_input_tokens_seen": 5061872,
      "step": 18080
    },
    {
      "epoch": 200.94444444444446,
      "grad_norm": 1.2941312910186298e-08,
      "learning_rate": 0.17248724814100616,
      "loss": 0.0,
      "num_input_tokens_seen": 5063264,
      "step": 18085
    },
    {
      "epoch": 201.0,
      "grad_norm": 3.347856392110771e-08,
      "learning_rate": 0.17242900723662619,
      "loss": 0.0,
      "num_input_tokens_seen": 5064672,
      "step": 18090
    },
    {
      "epoch": 201.05555555555554,
      "grad_norm": 1.0647553061460258e-08,
      "learning_rate": 0.1723707628734114,
      "loss": 0.0,
      "num_input_tokens_seen": 5066080,
      "step": 18095
    },
    {
      "epoch": 201.11111111111111,
      "grad_norm": 1.3547098554056447e-08,
      "learning_rate": 0.1723125150603438,
      "loss": 0.0,
      "num_input_tokens_seen": 5067424,
      "step": 18100
    },
    {
      "epoch": 201.16666666666666,
      "grad_norm": 1.7049442746497334e-08,
      "learning_rate": 0.1722542638064061,
      "loss": 0.0,
      "num_input_tokens_seen": 5068816,
      "step": 18105
    },
    {
      "epoch": 201.22222222222223,
      "grad_norm": 1.283752215641698e-08,
      "learning_rate": 0.17219600912058117,
      "loss": 0.0,
      "num_input_tokens_seen": 5070192,
      "step": 18110
    },
    {
      "epoch": 201.27777777777777,
      "grad_norm": 1.8095004605811482e-08,
      "learning_rate": 0.17213775101185272,
      "loss": 0.0,
      "num_input_tokens_seen": 5071600,
      "step": 18115
    },
    {
      "epoch": 201.33333333333334,
      "grad_norm": 1.776186486779352e-08,
      "learning_rate": 0.17207948948920485,
      "loss": 0.0,
      "num_input_tokens_seen": 5072992,
      "step": 18120
    },
    {
      "epoch": 201.38888888888889,
      "grad_norm": 1.517752323820787e-08,
      "learning_rate": 0.17202122456162228,
      "loss": 0.0,
      "num_input_tokens_seen": 5074368,
      "step": 18125
    },
    {
      "epoch": 201.44444444444446,
      "grad_norm": 2.7967317350885423e-08,
      "learning_rate": 0.17196295623809013,
      "loss": 0.0,
      "num_input_tokens_seen": 5075744,
      "step": 18130
    },
    {
      "epoch": 201.5,
      "grad_norm": 1.228007562303901e-08,
      "learning_rate": 0.1719046845275941,
      "loss": 0.0,
      "num_input_tokens_seen": 5077168,
      "step": 18135
    },
    {
      "epoch": 201.55555555555554,
      "grad_norm": 2.0168332781622667e-08,
      "learning_rate": 0.17184640943912044,
      "loss": 0.0,
      "num_input_tokens_seen": 5078560,
      "step": 18140
    },
    {
      "epoch": 201.61111111111111,
      "grad_norm": 1.1084953399631559e-08,
      "learning_rate": 0.1717881309816559,
      "loss": 0.0,
      "num_input_tokens_seen": 5079968,
      "step": 18145
    },
    {
      "epoch": 201.66666666666666,
      "grad_norm": 4.848834578297101e-08,
      "learning_rate": 0.1717298491641878,
      "loss": 0.0,
      "num_input_tokens_seen": 5081392,
      "step": 18150
    },
    {
      "epoch": 201.72222222222223,
      "grad_norm": 1.3820017130683482e-08,
      "learning_rate": 0.17167156399570385,
      "loss": 0.0,
      "num_input_tokens_seen": 5082784,
      "step": 18155
    },
    {
      "epoch": 201.77777777777777,
      "grad_norm": 9.6356647105722e-09,
      "learning_rate": 0.17161327548519242,
      "loss": 0.0,
      "num_input_tokens_seen": 5084192,
      "step": 18160
    },
    {
      "epoch": 201.83333333333334,
      "grad_norm": 2.4337442283695054e-08,
      "learning_rate": 0.1715549836416423,
      "loss": 0.0,
      "num_input_tokens_seen": 5085584,
      "step": 18165
    },
    {
      "epoch": 201.88888888888889,
      "grad_norm": 1.3444187096922633e-08,
      "learning_rate": 0.17149668847404279,
      "loss": 0.0,
      "num_input_tokens_seen": 5086992,
      "step": 18170
    },
    {
      "epoch": 201.94444444444446,
      "grad_norm": 1.5805708741822855e-08,
      "learning_rate": 0.1714383899913838,
      "loss": 0.0,
      "num_input_tokens_seen": 5088448,
      "step": 18175
    },
    {
      "epoch": 202.0,
      "grad_norm": 1.5464094005324114e-08,
      "learning_rate": 0.17138008820265563,
      "loss": 0.0,
      "num_input_tokens_seen": 5089808,
      "step": 18180
    },
    {
      "epoch": 202.05555555555554,
      "grad_norm": 2.4066144632683972e-08,
      "learning_rate": 0.17132178311684917,
      "loss": 0.0,
      "num_input_tokens_seen": 5091152,
      "step": 18185
    },
    {
      "epoch": 202.11111111111111,
      "grad_norm": 2.0737299877282567e-08,
      "learning_rate": 0.1712634747429559,
      "loss": 0.0,
      "num_input_tokens_seen": 5092544,
      "step": 18190
    },
    {
      "epoch": 202.16666666666666,
      "grad_norm": 1.5727255942010743e-08,
      "learning_rate": 0.17120516308996753,
      "loss": 0.0,
      "num_input_tokens_seen": 5093968,
      "step": 18195
    },
    {
      "epoch": 202.22222222222223,
      "grad_norm": 1.7350636483115522e-08,
      "learning_rate": 0.17114684816687653,
      "loss": 0.0,
      "num_input_tokens_seen": 5095376,
      "step": 18200
    },
    {
      "epoch": 202.22222222222223,
      "eval_loss": 1.4927966594696045,
      "eval_runtime": 1.1863,
      "eval_samples_per_second": 33.719,
      "eval_steps_per_second": 16.859,
      "num_input_tokens_seen": 5095376,
      "step": 18200
    },
    {
      "epoch": 202.27777777777777,
      "grad_norm": 5.292824400981999e-09,
      "learning_rate": 0.17108852998267585,
      "loss": 0.0,
      "num_input_tokens_seen": 5096784,
      "step": 18205
    },
    {
      "epoch": 202.33333333333334,
      "grad_norm": 8.712111920772259e-09,
      "learning_rate": 0.17103020854635878,
      "loss": 0.0,
      "num_input_tokens_seen": 5098160,
      "step": 18210
    },
    {
      "epoch": 202.38888888888889,
      "grad_norm": 1.5347460191605933e-08,
      "learning_rate": 0.1709718838669193,
      "loss": 0.0,
      "num_input_tokens_seen": 5099600,
      "step": 18215
    },
    {
      "epoch": 202.44444444444446,
      "grad_norm": 9.024425651205092e-09,
      "learning_rate": 0.17091355595335173,
      "loss": 0.0,
      "num_input_tokens_seen": 5101008,
      "step": 18220
    },
    {
      "epoch": 202.5,
      "grad_norm": 8.285565122889693e-09,
      "learning_rate": 0.17085522481465107,
      "loss": 0.0,
      "num_input_tokens_seen": 5102464,
      "step": 18225
    },
    {
      "epoch": 202.55555555555554,
      "grad_norm": 1.909755731333007e-08,
      "learning_rate": 0.17079689045981264,
      "loss": 0.0,
      "num_input_tokens_seen": 5103904,
      "step": 18230
    },
    {
      "epoch": 202.61111111111111,
      "grad_norm": 9.660059419047684e-09,
      "learning_rate": 0.17073855289783238,
      "loss": 0.0,
      "num_input_tokens_seen": 5105312,
      "step": 18235
    },
    {
      "epoch": 202.66666666666666,
      "grad_norm": 1.8336674401098207e-08,
      "learning_rate": 0.1706802121377066,
      "loss": 0.0,
      "num_input_tokens_seen": 5106704,
      "step": 18240
    },
    {
      "epoch": 202.72222222222223,
      "grad_norm": 1.710845864977273e-08,
      "learning_rate": 0.17062186818843225,
      "loss": 0.0,
      "num_input_tokens_seen": 5108064,
      "step": 18245
    },
    {
      "epoch": 202.77777777777777,
      "grad_norm": 1.1132653909839973e-08,
      "learning_rate": 0.17056352105900668,
      "loss": 0.0,
      "num_input_tokens_seen": 5109472,
      "step": 18250
    },
    {
      "epoch": 202.83333333333334,
      "grad_norm": 1.155964390875397e-08,
      "learning_rate": 0.17050517075842772,
      "loss": 0.0,
      "num_input_tokens_seen": 5110864,
      "step": 18255
    },
    {
      "epoch": 202.88888888888889,
      "grad_norm": 1.250745729208802e-08,
      "learning_rate": 0.17044681729569375,
      "loss": 0.0,
      "num_input_tokens_seen": 5112224,
      "step": 18260
    },
    {
      "epoch": 202.94444444444446,
      "grad_norm": 2.0326941907455875e-08,
      "learning_rate": 0.17038846067980365,
      "loss": 0.0,
      "num_input_tokens_seen": 5113568,
      "step": 18265
    },
    {
      "epoch": 203.0,
      "grad_norm": 1.8983895344604207e-08,
      "learning_rate": 0.17033010091975664,
      "loss": 0.0,
      "num_input_tokens_seen": 5114960,
      "step": 18270
    },
    {
      "epoch": 203.05555555555554,
      "grad_norm": 3.388788272218335e-08,
      "learning_rate": 0.17027173802455262,
      "loss": 0.0,
      "num_input_tokens_seen": 5116320,
      "step": 18275
    },
    {
      "epoch": 203.11111111111111,
      "grad_norm": 1.2379308245158427e-08,
      "learning_rate": 0.1702133720031918,
      "loss": 0.0,
      "num_input_tokens_seen": 5117728,
      "step": 18280
    },
    {
      "epoch": 203.16666666666666,
      "grad_norm": 1.2941707261404645e-08,
      "learning_rate": 0.17015500286467503,
      "loss": 0.0,
      "num_input_tokens_seen": 5119168,
      "step": 18285
    },
    {
      "epoch": 203.22222222222223,
      "grad_norm": 1.7340578750690838e-08,
      "learning_rate": 0.17009663061800354,
      "loss": 0.0,
      "num_input_tokens_seen": 5120608,
      "step": 18290
    },
    {
      "epoch": 203.27777777777777,
      "grad_norm": 1.4090373312569682e-08,
      "learning_rate": 0.17003825527217903,
      "loss": 0.0,
      "num_input_tokens_seen": 5122000,
      "step": 18295
    },
    {
      "epoch": 203.33333333333334,
      "grad_norm": 7.373400556787146e-09,
      "learning_rate": 0.16997987683620377,
      "loss": 0.0,
      "num_input_tokens_seen": 5123424,
      "step": 18300
    },
    {
      "epoch": 203.38888888888889,
      "grad_norm": 2.2713345870783996e-08,
      "learning_rate": 0.16992149531908043,
      "loss": 0.0,
      "num_input_tokens_seen": 5124864,
      "step": 18305
    },
    {
      "epoch": 203.44444444444446,
      "grad_norm": 2.0974718850652607e-08,
      "learning_rate": 0.16986311072981214,
      "loss": 0.0,
      "num_input_tokens_seen": 5126272,
      "step": 18310
    },
    {
      "epoch": 203.5,
      "grad_norm": 1.1329010618510438e-08,
      "learning_rate": 0.16980472307740255,
      "loss": 0.0,
      "num_input_tokens_seen": 5127680,
      "step": 18315
    },
    {
      "epoch": 203.55555555555554,
      "grad_norm": 1.1354647888595082e-08,
      "learning_rate": 0.1697463323708558,
      "loss": 0.0,
      "num_input_tokens_seen": 5129104,
      "step": 18320
    },
    {
      "epoch": 203.61111111111111,
      "grad_norm": 1.8490245778934877e-08,
      "learning_rate": 0.16968793861917641,
      "loss": 0.0,
      "num_input_tokens_seen": 5130496,
      "step": 18325
    },
    {
      "epoch": 203.66666666666666,
      "grad_norm": 1.2009389038780682e-08,
      "learning_rate": 0.16962954183136952,
      "loss": 0.0,
      "num_input_tokens_seen": 5131904,
      "step": 18330
    },
    {
      "epoch": 203.72222222222223,
      "grad_norm": 1.980298058867902e-08,
      "learning_rate": 0.16957114201644058,
      "loss": 0.0,
      "num_input_tokens_seen": 5133312,
      "step": 18335
    },
    {
      "epoch": 203.77777777777777,
      "grad_norm": 1.304858265882558e-08,
      "learning_rate": 0.16951273918339563,
      "loss": 0.0,
      "num_input_tokens_seen": 5134704,
      "step": 18340
    },
    {
      "epoch": 203.83333333333334,
      "grad_norm": 1.709453023579499e-08,
      "learning_rate": 0.16945433334124105,
      "loss": 0.0,
      "num_input_tokens_seen": 5136096,
      "step": 18345
    },
    {
      "epoch": 203.88888888888889,
      "grad_norm": 1.8922094113804633e-08,
      "learning_rate": 0.1693959244989838,
      "loss": 0.0,
      "num_input_tokens_seen": 5137472,
      "step": 18350
    },
    {
      "epoch": 203.94444444444446,
      "grad_norm": 1.6085101250951084e-08,
      "learning_rate": 0.16933751266563127,
      "loss": 0.0,
      "num_input_tokens_seen": 5138896,
      "step": 18355
    },
    {
      "epoch": 204.0,
      "grad_norm": 1.2412149530405259e-08,
      "learning_rate": 0.16927909785019118,
      "loss": 0.0,
      "num_input_tokens_seen": 5140272,
      "step": 18360
    },
    {
      "epoch": 204.05555555555554,
      "grad_norm": 5.970065775073863e-09,
      "learning_rate": 0.169220680061672,
      "loss": 0.0,
      "num_input_tokens_seen": 5141616,
      "step": 18365
    },
    {
      "epoch": 204.11111111111111,
      "grad_norm": 9.864373318180242e-09,
      "learning_rate": 0.16916225930908244,
      "loss": 0.0,
      "num_input_tokens_seen": 5142976,
      "step": 18370
    },
    {
      "epoch": 204.16666666666666,
      "grad_norm": 6.419380582656231e-09,
      "learning_rate": 0.16910383560143163,
      "loss": 0.0,
      "num_input_tokens_seen": 5144400,
      "step": 18375
    },
    {
      "epoch": 204.22222222222223,
      "grad_norm": 1.2615758215872575e-08,
      "learning_rate": 0.16904540894772935,
      "loss": 0.0,
      "num_input_tokens_seen": 5145808,
      "step": 18380
    },
    {
      "epoch": 204.27777777777777,
      "grad_norm": 2.0431205172144473e-08,
      "learning_rate": 0.16898697935698562,
      "loss": 0.0,
      "num_input_tokens_seen": 5147216,
      "step": 18385
    },
    {
      "epoch": 204.33333333333334,
      "grad_norm": 7.757886777426393e-09,
      "learning_rate": 0.1689285468382111,
      "loss": 0.0,
      "num_input_tokens_seen": 5148624,
      "step": 18390
    },
    {
      "epoch": 204.38888888888889,
      "grad_norm": 8.046371569037092e-09,
      "learning_rate": 0.16887011140041677,
      "loss": 0.0,
      "num_input_tokens_seen": 5150032,
      "step": 18395
    },
    {
      "epoch": 204.44444444444446,
      "grad_norm": 8.642344617726394e-09,
      "learning_rate": 0.1688116730526141,
      "loss": 0.0,
      "num_input_tokens_seen": 5151440,
      "step": 18400
    },
    {
      "epoch": 204.44444444444446,
      "eval_loss": 1.5293112993240356,
      "eval_runtime": 1.1872,
      "eval_samples_per_second": 33.693,
      "eval_steps_per_second": 16.847,
      "num_input_tokens_seen": 5151440,
      "step": 18400
    },
    {
      "epoch": 204.5,
      "grad_norm": 1.2244441016662222e-08,
      "learning_rate": 0.1687532318038151,
      "loss": 0.0,
      "num_input_tokens_seen": 5152864,
      "step": 18405
    },
    {
      "epoch": 204.55555555555554,
      "grad_norm": 6.3339600231415716e-09,
      "learning_rate": 0.16869478766303206,
      "loss": 0.0,
      "num_input_tokens_seen": 5154288,
      "step": 18410
    },
    {
      "epoch": 204.61111111111111,
      "grad_norm": 1.9067989853738254e-08,
      "learning_rate": 0.16863634063927788,
      "loss": 0.0,
      "num_input_tokens_seen": 5155664,
      "step": 18415
    },
    {
      "epoch": 204.66666666666666,
      "grad_norm": 9.611402340681252e-09,
      "learning_rate": 0.16857789074156568,
      "loss": 0.0,
      "num_input_tokens_seen": 5157040,
      "step": 18420
    },
    {
      "epoch": 204.72222222222223,
      "grad_norm": 5.878236564171857e-09,
      "learning_rate": 0.16851943797890928,
      "loss": 0.0,
      "num_input_tokens_seen": 5158464,
      "step": 18425
    },
    {
      "epoch": 204.77777777777777,
      "grad_norm": 1.3569665391344188e-08,
      "learning_rate": 0.16846098236032284,
      "loss": 0.0,
      "num_input_tokens_seen": 5159872,
      "step": 18430
    },
    {
      "epoch": 204.83333333333334,
      "grad_norm": 1.5212156867505655e-08,
      "learning_rate": 0.16840252389482097,
      "loss": 0.0,
      "num_input_tokens_seen": 5161280,
      "step": 18435
    },
    {
      "epoch": 204.88888888888889,
      "grad_norm": 1.328822563095855e-08,
      "learning_rate": 0.16834406259141857,
      "loss": 0.0,
      "num_input_tokens_seen": 5162656,
      "step": 18440
    },
    {
      "epoch": 204.94444444444446,
      "grad_norm": 3.6213997134382225e-08,
      "learning_rate": 0.16828559845913124,
      "loss": 0.0,
      "num_input_tokens_seen": 5164064,
      "step": 18445
    },
    {
      "epoch": 205.0,
      "grad_norm": 7.538502266868363e-09,
      "learning_rate": 0.16822713150697488,
      "loss": 0.0,
      "num_input_tokens_seen": 5165456,
      "step": 18450
    },
    {
      "epoch": 205.05555555555554,
      "grad_norm": 2.4296333833717654e-08,
      "learning_rate": 0.16816866174396575,
      "loss": 0.0,
      "num_input_tokens_seen": 5166880,
      "step": 18455
    },
    {
      "epoch": 205.11111111111111,
      "grad_norm": 1.3142341437344385e-08,
      "learning_rate": 0.16811018917912057,
      "loss": 0.0,
      "num_input_tokens_seen": 5168224,
      "step": 18460
    },
    {
      "epoch": 205.16666666666666,
      "grad_norm": 1.3200711634908657e-08,
      "learning_rate": 0.16805171382145673,
      "loss": 0.0,
      "num_input_tokens_seen": 5169664,
      "step": 18465
    },
    {
      "epoch": 205.22222222222223,
      "grad_norm": 1.1493640705850794e-08,
      "learning_rate": 0.16799323567999175,
      "loss": 0.0,
      "num_input_tokens_seen": 5171136,
      "step": 18470
    },
    {
      "epoch": 205.27777777777777,
      "grad_norm": 1.1456416260102742e-08,
      "learning_rate": 0.16793475476374367,
      "loss": 0.0,
      "num_input_tokens_seen": 5172544,
      "step": 18475
    },
    {
      "epoch": 205.33333333333334,
      "grad_norm": 4.805350783954054e-09,
      "learning_rate": 0.1678762710817311,
      "loss": 0.0,
      "num_input_tokens_seen": 5173920,
      "step": 18480
    },
    {
      "epoch": 205.38888888888889,
      "grad_norm": 1.804652605130741e-08,
      "learning_rate": 0.1678177846429728,
      "loss": 0.0,
      "num_input_tokens_seen": 5175312,
      "step": 18485
    },
    {
      "epoch": 205.44444444444446,
      "grad_norm": 9.200348927151936e-09,
      "learning_rate": 0.16775929545648827,
      "loss": 0.0,
      "num_input_tokens_seen": 5176736,
      "step": 18490
    },
    {
      "epoch": 205.5,
      "grad_norm": 3.113126467724214e-08,
      "learning_rate": 0.16770080353129715,
      "loss": 0.0,
      "num_input_tokens_seen": 5178128,
      "step": 18495
    },
    {
      "epoch": 205.55555555555554,
      "grad_norm": 9.98098492743793e-09,
      "learning_rate": 0.16764230887641968,
      "loss": 0.0,
      "num_input_tokens_seen": 5179520,
      "step": 18500
    },
    {
      "epoch": 205.61111111111111,
      "grad_norm": 6.957331599721783e-09,
      "learning_rate": 0.1675838115008765,
      "loss": 0.0,
      "num_input_tokens_seen": 5180928,
      "step": 18505
    },
    {
      "epoch": 205.66666666666666,
      "grad_norm": 2.8960377207454258e-08,
      "learning_rate": 0.1675253114136886,
      "loss": 0.0,
      "num_input_tokens_seen": 5182272,
      "step": 18510
    },
    {
      "epoch": 205.72222222222223,
      "grad_norm": 1.0159354246752628e-08,
      "learning_rate": 0.16746680862387747,
      "loss": 0.0,
      "num_input_tokens_seen": 5183680,
      "step": 18515
    },
    {
      "epoch": 205.77777777777777,
      "grad_norm": 2.4717438762422717e-08,
      "learning_rate": 0.16740830314046493,
      "loss": 0.0,
      "num_input_tokens_seen": 5185088,
      "step": 18520
    },
    {
      "epoch": 205.83333333333334,
      "grad_norm": 3.295274453307684e-08,
      "learning_rate": 0.1673497949724733,
      "loss": 0.0,
      "num_input_tokens_seen": 5186464,
      "step": 18525
    },
    {
      "epoch": 205.88888888888889,
      "grad_norm": 2.840766377687487e-08,
      "learning_rate": 0.16729128412892522,
      "loss": 0.0,
      "num_input_tokens_seen": 5187840,
      "step": 18530
    },
    {
      "epoch": 205.94444444444446,
      "grad_norm": 1.0433723218739033e-08,
      "learning_rate": 0.16723277061884384,
      "loss": 0.0,
      "num_input_tokens_seen": 5189248,
      "step": 18535
    },
    {
      "epoch": 206.0,
      "grad_norm": 2.7591330109544288e-08,
      "learning_rate": 0.16717425445125267,
      "loss": 0.0,
      "num_input_tokens_seen": 5190656,
      "step": 18540
    },
    {
      "epoch": 206.05555555555554,
      "grad_norm": 1.7690613418608336e-08,
      "learning_rate": 0.16711573563517565,
      "loss": 0.0,
      "num_input_tokens_seen": 5192048,
      "step": 18545
    },
    {
      "epoch": 206.11111111111111,
      "grad_norm": 6.70996813667557e-09,
      "learning_rate": 0.1670572141796371,
      "loss": 0.0,
      "num_input_tokens_seen": 5193440,
      "step": 18550
    },
    {
      "epoch": 206.16666666666666,
      "grad_norm": 7.903016019383813e-09,
      "learning_rate": 0.16699869009366175,
      "loss": 0.0,
      "num_input_tokens_seen": 5194848,
      "step": 18555
    },
    {
      "epoch": 206.22222222222223,
      "grad_norm": 1.085697487468451e-08,
      "learning_rate": 0.1669401633862748,
      "loss": 0.0,
      "num_input_tokens_seen": 5196240,
      "step": 18560
    },
    {
      "epoch": 206.27777777777777,
      "grad_norm": 1.4692941086025257e-08,
      "learning_rate": 0.16688163406650178,
      "loss": 0.0,
      "num_input_tokens_seen": 5197664,
      "step": 18565
    },
    {
      "epoch": 206.33333333333334,
      "grad_norm": 9.863121874786884e-09,
      "learning_rate": 0.1668231021433686,
      "loss": 0.0,
      "num_input_tokens_seen": 5199056,
      "step": 18570
    },
    {
      "epoch": 206.38888888888889,
      "grad_norm": 1.3724379854807012e-08,
      "learning_rate": 0.1667645676259017,
      "loss": 0.0,
      "num_input_tokens_seen": 5200480,
      "step": 18575
    },
    {
      "epoch": 206.44444444444446,
      "grad_norm": 1.430591201057041e-08,
      "learning_rate": 0.1667060305231277,
      "loss": 0.0,
      "num_input_tokens_seen": 5201856,
      "step": 18580
    },
    {
      "epoch": 206.5,
      "grad_norm": 2.170388846423066e-08,
      "learning_rate": 0.16664749084407396,
      "loss": 0.0,
      "num_input_tokens_seen": 5203264,
      "step": 18585
    },
    {
      "epoch": 206.55555555555554,
      "grad_norm": 5.8956537429821765e-09,
      "learning_rate": 0.16658894859776788,
      "loss": 0.0,
      "num_input_tokens_seen": 5204672,
      "step": 18590
    },
    {
      "epoch": 206.61111111111111,
      "grad_norm": 3.850204777222643e-08,
      "learning_rate": 0.16653040379323752,
      "loss": 0.0,
      "num_input_tokens_seen": 5206096,
      "step": 18595
    },
    {
      "epoch": 206.66666666666666,
      "grad_norm": 1.0437882558278488e-08,
      "learning_rate": 0.16647185643951107,
      "loss": 0.0,
      "num_input_tokens_seen": 5207488,
      "step": 18600
    },
    {
      "epoch": 206.66666666666666,
      "eval_loss": 1.5466697216033936,
      "eval_runtime": 1.1811,
      "eval_samples_per_second": 33.866,
      "eval_steps_per_second": 16.933,
      "num_input_tokens_seen": 5207488,
      "step": 18600
    },
    {
      "epoch": 206.72222222222223,
      "grad_norm": 1.0732033928206874e-08,
      "learning_rate": 0.1664133065456174,
      "loss": 0.0,
      "num_input_tokens_seen": 5208864,
      "step": 18605
    },
    {
      "epoch": 206.77777777777777,
      "grad_norm": 1.539343230660961e-08,
      "learning_rate": 0.1663547541205856,
      "loss": 0.0,
      "num_input_tokens_seen": 5210288,
      "step": 18610
    },
    {
      "epoch": 206.83333333333334,
      "grad_norm": 8.691131370142102e-09,
      "learning_rate": 0.16629619917344518,
      "loss": 0.0,
      "num_input_tokens_seen": 5211680,
      "step": 18615
    },
    {
      "epoch": 206.88888888888889,
      "grad_norm": 2.0148824830812373e-08,
      "learning_rate": 0.16623764171322605,
      "loss": 0.0,
      "num_input_tokens_seen": 5213072,
      "step": 18620
    },
    {
      "epoch": 206.94444444444446,
      "grad_norm": 8.394455797144929e-09,
      "learning_rate": 0.1661790817489585,
      "loss": 0.0,
      "num_input_tokens_seen": 5214464,
      "step": 18625
    },
    {
      "epoch": 207.0,
      "grad_norm": 9.719374638450518e-09,
      "learning_rate": 0.16612051928967328,
      "loss": 0.0,
      "num_input_tokens_seen": 5215840,
      "step": 18630
    },
    {
      "epoch": 207.05555555555554,
      "grad_norm": 7.687956049551303e-09,
      "learning_rate": 0.16606195434440138,
      "loss": 0.0,
      "num_input_tokens_seen": 5217232,
      "step": 18635
    },
    {
      "epoch": 207.11111111111111,
      "grad_norm": 1.9208112433943825e-08,
      "learning_rate": 0.16600338692217426,
      "loss": 0.0,
      "num_input_tokens_seen": 5218656,
      "step": 18640
    },
    {
      "epoch": 207.16666666666666,
      "grad_norm": 4.146430754303765e-09,
      "learning_rate": 0.16594481703202374,
      "loss": 0.0,
      "num_input_tokens_seen": 5220032,
      "step": 18645
    },
    {
      "epoch": 207.22222222222223,
      "grad_norm": 6.606369673534118e-09,
      "learning_rate": 0.1658862446829821,
      "loss": 0.0,
      "num_input_tokens_seen": 5221424,
      "step": 18650
    },
    {
      "epoch": 207.27777777777777,
      "grad_norm": 1.9420676622416977e-08,
      "learning_rate": 0.16582766988408187,
      "loss": 0.0,
      "num_input_tokens_seen": 5222880,
      "step": 18655
    },
    {
      "epoch": 207.33333333333334,
      "grad_norm": 2.1585547571589814e-08,
      "learning_rate": 0.16576909264435608,
      "loss": 0.0,
      "num_input_tokens_seen": 5224256,
      "step": 18660
    },
    {
      "epoch": 207.38888888888889,
      "grad_norm": 6.953446707314015e-09,
      "learning_rate": 0.16571051297283798,
      "loss": 0.0,
      "num_input_tokens_seen": 5225664,
      "step": 18665
    },
    {
      "epoch": 207.44444444444446,
      "grad_norm": 1.1134255295530693e-08,
      "learning_rate": 0.16565193087856137,
      "loss": 0.0,
      "num_input_tokens_seen": 5227040,
      "step": 18670
    },
    {
      "epoch": 207.5,
      "grad_norm": 1.9086522584643717e-08,
      "learning_rate": 0.16559334637056033,
      "loss": 0.0,
      "num_input_tokens_seen": 5228480,
      "step": 18675
    },
    {
      "epoch": 207.55555555555554,
      "grad_norm": 1.9634589065731234e-08,
      "learning_rate": 0.16553475945786933,
      "loss": 0.0,
      "num_input_tokens_seen": 5229888,
      "step": 18680
    },
    {
      "epoch": 207.61111111111111,
      "grad_norm": 3.131384218590938e-08,
      "learning_rate": 0.16547617014952318,
      "loss": 0.0,
      "num_input_tokens_seen": 5231296,
      "step": 18685
    },
    {
      "epoch": 207.66666666666666,
      "grad_norm": 1.696684925889258e-08,
      "learning_rate": 0.1654175784545571,
      "loss": 0.0,
      "num_input_tokens_seen": 5232688,
      "step": 18690
    },
    {
      "epoch": 207.72222222222223,
      "grad_norm": 2.3079962829797296e-08,
      "learning_rate": 0.1653589843820067,
      "loss": 0.0,
      "num_input_tokens_seen": 5234096,
      "step": 18695
    },
    {
      "epoch": 207.77777777777777,
      "grad_norm": 1.3433523626815713e-08,
      "learning_rate": 0.1653003879409079,
      "loss": 0.0,
      "num_input_tokens_seen": 5235520,
      "step": 18700
    },
    {
      "epoch": 207.83333333333334,
      "grad_norm": 1.4445307172650246e-08,
      "learning_rate": 0.165241789140297,
      "loss": 0.0,
      "num_input_tokens_seen": 5236928,
      "step": 18705
    },
    {
      "epoch": 207.88888888888889,
      "grad_norm": 1.3577747814963459e-08,
      "learning_rate": 0.16518318798921064,
      "loss": 0.0,
      "num_input_tokens_seen": 5238272,
      "step": 18710
    },
    {
      "epoch": 207.94444444444446,
      "grad_norm": 5.634444466551258e-09,
      "learning_rate": 0.16512458449668593,
      "loss": 0.0,
      "num_input_tokens_seen": 5239680,
      "step": 18715
    },
    {
      "epoch": 208.0,
      "grad_norm": 1.5566065769689885e-08,
      "learning_rate": 0.1650659786717602,
      "loss": 0.0,
      "num_input_tokens_seen": 5241056,
      "step": 18720
    },
    {
      "epoch": 208.05555555555554,
      "grad_norm": 6.015588027707963e-09,
      "learning_rate": 0.1650073705234712,
      "loss": 0.0,
      "num_input_tokens_seen": 5242432,
      "step": 18725
    },
    {
      "epoch": 208.11111111111111,
      "grad_norm": 1.3407419174882307e-08,
      "learning_rate": 0.16494876006085712,
      "loss": 0.0,
      "num_input_tokens_seen": 5243808,
      "step": 18730
    },
    {
      "epoch": 208.16666666666666,
      "grad_norm": 1.4039186702063944e-08,
      "learning_rate": 0.16489014729295634,
      "loss": 0.0,
      "num_input_tokens_seen": 5245152,
      "step": 18735
    },
    {
      "epoch": 208.22222222222223,
      "grad_norm": 8.159723563494481e-09,
      "learning_rate": 0.16483153222880775,
      "loss": 0.0,
      "num_input_tokens_seen": 5246544,
      "step": 18740
    },
    {
      "epoch": 208.27777777777777,
      "grad_norm": 6.853834833009387e-09,
      "learning_rate": 0.16477291487745052,
      "loss": 0.0,
      "num_input_tokens_seen": 5247936,
      "step": 18745
    },
    {
      "epoch": 208.33333333333334,
      "grad_norm": 1.5954658039163405e-08,
      "learning_rate": 0.16471429524792416,
      "loss": 0.0,
      "num_input_tokens_seen": 5249328,
      "step": 18750
    },
    {
      "epoch": 208.38888888888889,
      "grad_norm": 1.6360491628120144e-08,
      "learning_rate": 0.16465567334926856,
      "loss": 0.0,
      "num_input_tokens_seen": 5250784,
      "step": 18755
    },
    {
      "epoch": 208.44444444444446,
      "grad_norm": 1.7966774734645696e-08,
      "learning_rate": 0.16459704919052395,
      "loss": 0.0,
      "num_input_tokens_seen": 5252192,
      "step": 18760
    },
    {
      "epoch": 208.5,
      "grad_norm": 5.809948522284003e-09,
      "learning_rate": 0.16453842278073086,
      "loss": 0.0,
      "num_input_tokens_seen": 5253616,
      "step": 18765
    },
    {
      "epoch": 208.55555555555554,
      "grad_norm": 1.7617640679645774e-08,
      "learning_rate": 0.16447979412893038,
      "loss": 0.0,
      "num_input_tokens_seen": 5254992,
      "step": 18770
    },
    {
      "epoch": 208.61111111111111,
      "grad_norm": 1.0397578797949336e-08,
      "learning_rate": 0.16442116324416367,
      "loss": 0.0,
      "num_input_tokens_seen": 5256368,
      "step": 18775
    },
    {
      "epoch": 208.66666666666666,
      "grad_norm": 1.2535863902485289e-08,
      "learning_rate": 0.1643625301354723,
      "loss": 0.0,
      "num_input_tokens_seen": 5257808,
      "step": 18780
    },
    {
      "epoch": 208.72222222222223,
      "grad_norm": 1.7321752920906874e-08,
      "learning_rate": 0.16430389481189828,
      "loss": 0.0,
      "num_input_tokens_seen": 5259184,
      "step": 18785
    },
    {
      "epoch": 208.77777777777777,
      "grad_norm": 1.7309361055595218e-08,
      "learning_rate": 0.164245257282484,
      "loss": 0.0,
      "num_input_tokens_seen": 5260592,
      "step": 18790
    },
    {
      "epoch": 208.83333333333334,
      "grad_norm": 9.250602950316988e-09,
      "learning_rate": 0.16418661755627195,
      "loss": 0.0,
      "num_input_tokens_seen": 5261952,
      "step": 18795
    },
    {
      "epoch": 208.88888888888889,
      "grad_norm": 7.991043382560292e-09,
      "learning_rate": 0.16412797564230527,
      "loss": 0.0,
      "num_input_tokens_seen": 5263360,
      "step": 18800
    },
    {
      "epoch": 208.88888888888889,
      "eval_loss": 1.5432411432266235,
      "eval_runtime": 1.187,
      "eval_samples_per_second": 33.697,
      "eval_steps_per_second": 16.849,
      "num_input_tokens_seen": 5263360,
      "step": 18800
    },
    {
      "epoch": 208.94444444444446,
      "grad_norm": 9.010289403477145e-09,
      "learning_rate": 0.16406933154962713,
      "loss": 0.0,
      "num_input_tokens_seen": 5264800,
      "step": 18805
    },
    {
      "epoch": 209.0,
      "grad_norm": 4.0506577647647646e-08,
      "learning_rate": 0.16401068528728133,
      "loss": 0.0,
      "num_input_tokens_seen": 5266240,
      "step": 18810
    },
    {
      "epoch": 209.05555555555554,
      "grad_norm": 2.1290924578920567e-08,
      "learning_rate": 0.16395203686431173,
      "loss": 0.0,
      "num_input_tokens_seen": 5267680,
      "step": 18815
    },
    {
      "epoch": 209.11111111111111,
      "grad_norm": 1.671743632414291e-08,
      "learning_rate": 0.16389338628976277,
      "loss": 0.0,
      "num_input_tokens_seen": 5269088,
      "step": 18820
    },
    {
      "epoch": 209.16666666666666,
      "grad_norm": 1.0676033390666362e-08,
      "learning_rate": 0.163834733572679,
      "loss": 0.0,
      "num_input_tokens_seen": 5270464,
      "step": 18825
    },
    {
      "epoch": 209.22222222222223,
      "grad_norm": 1.4746409426891205e-08,
      "learning_rate": 0.16377607872210545,
      "loss": 0.0,
      "num_input_tokens_seen": 5271856,
      "step": 18830
    },
    {
      "epoch": 209.27777777777777,
      "grad_norm": 7.732611884136986e-09,
      "learning_rate": 0.16371742174708748,
      "loss": 0.0,
      "num_input_tokens_seen": 5273280,
      "step": 18835
    },
    {
      "epoch": 209.33333333333334,
      "grad_norm": 7.911548749461872e-09,
      "learning_rate": 0.16365876265667065,
      "loss": 0.0,
      "num_input_tokens_seen": 5274624,
      "step": 18840
    },
    {
      "epoch": 209.38888888888889,
      "grad_norm": 8.570852472189472e-09,
      "learning_rate": 0.163600101459901,
      "loss": 0.0,
      "num_input_tokens_seen": 5276016,
      "step": 18845
    },
    {
      "epoch": 209.44444444444446,
      "grad_norm": 8.509100979381401e-09,
      "learning_rate": 0.16354143816582484,
      "loss": 0.0,
      "num_input_tokens_seen": 5277424,
      "step": 18850
    },
    {
      "epoch": 209.5,
      "grad_norm": 2.2662048237975796e-08,
      "learning_rate": 0.1634827727834887,
      "loss": 0.0,
      "num_input_tokens_seen": 5278864,
      "step": 18855
    },
    {
      "epoch": 209.55555555555554,
      "grad_norm": 1.8259793677088965e-08,
      "learning_rate": 0.16342410532193954,
      "loss": 0.0,
      "num_input_tokens_seen": 5280240,
      "step": 18860
    },
    {
      "epoch": 209.61111111111111,
      "grad_norm": 1.5112494367031104e-08,
      "learning_rate": 0.16336543579022464,
      "loss": 0.0,
      "num_input_tokens_seen": 5281632,
      "step": 18865
    },
    {
      "epoch": 209.66666666666666,
      "grad_norm": 1.4394250236193784e-08,
      "learning_rate": 0.16330676419739157,
      "loss": 0.0,
      "num_input_tokens_seen": 5283040,
      "step": 18870
    },
    {
      "epoch": 209.72222222222223,
      "grad_norm": 2.9138471191458848e-08,
      "learning_rate": 0.1632480905524883,
      "loss": 0.0,
      "num_input_tokens_seen": 5284464,
      "step": 18875
    },
    {
      "epoch": 209.77777777777777,
      "grad_norm": 5.914976952681172e-09,
      "learning_rate": 0.16318941486456293,
      "loss": 0.0,
      "num_input_tokens_seen": 5285824,
      "step": 18880
    },
    {
      "epoch": 209.83333333333334,
      "grad_norm": 6.138734409688595e-09,
      "learning_rate": 0.16313073714266405,
      "loss": 0.0,
      "num_input_tokens_seen": 5287216,
      "step": 18885
    },
    {
      "epoch": 209.88888888888889,
      "grad_norm": 2.0094212516141852e-08,
      "learning_rate": 0.16307205739584052,
      "loss": 0.0,
      "num_input_tokens_seen": 5288576,
      "step": 18890
    },
    {
      "epoch": 209.94444444444446,
      "grad_norm": 9.190574523643136e-09,
      "learning_rate": 0.16301337563314144,
      "loss": 0.0,
      "num_input_tokens_seen": 5290000,
      "step": 18895
    },
    {
      "epoch": 210.0,
      "grad_norm": 1.834735563477352e-08,
      "learning_rate": 0.1629546918636163,
      "loss": 0.0,
      "num_input_tokens_seen": 5291424,
      "step": 18900
    },
    {
      "epoch": 210.05555555555554,
      "grad_norm": 1.989002562652331e-08,
      "learning_rate": 0.16289600609631485,
      "loss": 0.0,
      "num_input_tokens_seen": 5292832,
      "step": 18905
    },
    {
      "epoch": 210.11111111111111,
      "grad_norm": 8.978484622446103e-09,
      "learning_rate": 0.16283731834028722,
      "loss": 0.0,
      "num_input_tokens_seen": 5294240,
      "step": 18910
    },
    {
      "epoch": 210.16666666666666,
      "grad_norm": 1.2268099425227774e-08,
      "learning_rate": 0.16277862860458378,
      "loss": 0.0,
      "num_input_tokens_seen": 5295632,
      "step": 18915
    },
    {
      "epoch": 210.22222222222223,
      "grad_norm": 1.3817251343084536e-08,
      "learning_rate": 0.16271993689825526,
      "loss": 0.0,
      "num_input_tokens_seen": 5297136,
      "step": 18920
    },
    {
      "epoch": 210.27777777777777,
      "grad_norm": 2.0498612585129194e-08,
      "learning_rate": 0.1626612432303526,
      "loss": 0.0,
      "num_input_tokens_seen": 5298528,
      "step": 18925
    },
    {
      "epoch": 210.33333333333334,
      "grad_norm": 2.1323504739712007e-08,
      "learning_rate": 0.1626025476099271,
      "loss": 0.0,
      "num_input_tokens_seen": 5299920,
      "step": 18930
    },
    {
      "epoch": 210.38888888888889,
      "grad_norm": 1.1758364060199256e-08,
      "learning_rate": 0.1625438500460304,
      "loss": 0.0,
      "num_input_tokens_seen": 5301328,
      "step": 18935
    },
    {
      "epoch": 210.44444444444446,
      "grad_norm": 2.5494774291701106e-08,
      "learning_rate": 0.16248515054771442,
      "loss": 0.0,
      "num_input_tokens_seen": 5302688,
      "step": 18940
    },
    {
      "epoch": 210.5,
      "grad_norm": 9.65906554739604e-09,
      "learning_rate": 0.16242644912403123,
      "loss": 0.0,
      "num_input_tokens_seen": 5304064,
      "step": 18945
    },
    {
      "epoch": 210.55555555555554,
      "grad_norm": 4.085686100552266e-08,
      "learning_rate": 0.1623677457840335,
      "loss": 0.0,
      "num_input_tokens_seen": 5305440,
      "step": 18950
    },
    {
      "epoch": 210.61111111111111,
      "grad_norm": 4.731934399870852e-09,
      "learning_rate": 0.16230904053677397,
      "loss": 0.0,
      "num_input_tokens_seen": 5306800,
      "step": 18955
    },
    {
      "epoch": 210.66666666666666,
      "grad_norm": 6.278715769525434e-09,
      "learning_rate": 0.16225033339130568,
      "loss": 0.0,
      "num_input_tokens_seen": 5308192,
      "step": 18960
    },
    {
      "epoch": 210.72222222222223,
      "grad_norm": 9.989387983466713e-09,
      "learning_rate": 0.16219162435668197,
      "loss": 0.0,
      "num_input_tokens_seen": 5309600,
      "step": 18965
    },
    {
      "epoch": 210.77777777777777,
      "grad_norm": 1.2353035039325277e-08,
      "learning_rate": 0.16213291344195666,
      "loss": 0.0,
      "num_input_tokens_seen": 5310960,
      "step": 18970
    },
    {
      "epoch": 210.83333333333334,
      "grad_norm": 2.195685766537281e-08,
      "learning_rate": 0.16207420065618358,
      "loss": 0.0,
      "num_input_tokens_seen": 5312352,
      "step": 18975
    },
    {
      "epoch": 210.88888888888889,
      "grad_norm": 1.2932740212079352e-08,
      "learning_rate": 0.16201548600841706,
      "loss": 0.0,
      "num_input_tokens_seen": 5313776,
      "step": 18980
    },
    {
      "epoch": 210.94444444444446,
      "grad_norm": 5.340226483241395e-09,
      "learning_rate": 0.16195676950771154,
      "loss": 0.0,
      "num_input_tokens_seen": 5315136,
      "step": 18985
    },
    {
      "epoch": 211.0,
      "grad_norm": 1.4552593796679503e-08,
      "learning_rate": 0.16189805116312198,
      "loss": 0.0,
      "num_input_tokens_seen": 5316560,
      "step": 18990
    },
    {
      "epoch": 211.05555555555554,
      "grad_norm": 1.4946532900239617e-08,
      "learning_rate": 0.16183933098370337,
      "loss": 0.0,
      "num_input_tokens_seen": 5317952,
      "step": 18995
    },
    {
      "epoch": 211.11111111111111,
      "grad_norm": 8.5567286589594e-09,
      "learning_rate": 0.16178060897851115,
      "loss": 0.0,
      "num_input_tokens_seen": 5319344,
      "step": 19000
    },
    {
      "epoch": 211.11111111111111,
      "eval_loss": 1.5499582290649414,
      "eval_runtime": 1.201,
      "eval_samples_per_second": 33.305,
      "eval_steps_per_second": 16.653,
      "num_input_tokens_seen": 5319344,
      "step": 19000
    },
    {
      "epoch": 211.16666666666666,
      "grad_norm": 5.704884120660836e-09,
      "learning_rate": 0.16172188515660096,
      "loss": 0.0,
      "num_input_tokens_seen": 5320736,
      "step": 19005
    },
    {
      "epoch": 211.22222222222223,
      "grad_norm": 1.0917226234141708e-08,
      "learning_rate": 0.16166315952702878,
      "loss": 0.0,
      "num_input_tokens_seen": 5322176,
      "step": 19010
    },
    {
      "epoch": 211.27777777777777,
      "grad_norm": 1.1442840452957626e-08,
      "learning_rate": 0.16160443209885084,
      "loss": 0.0,
      "num_input_tokens_seen": 5323552,
      "step": 19015
    },
    {
      "epoch": 211.33333333333334,
      "grad_norm": 7.694093362431431e-09,
      "learning_rate": 0.16154570288112363,
      "loss": 0.0,
      "num_input_tokens_seen": 5324992,
      "step": 19020
    },
    {
      "epoch": 211.38888888888889,
      "grad_norm": 9.082321561493245e-09,
      "learning_rate": 0.16148697188290395,
      "loss": 0.0,
      "num_input_tokens_seen": 5326416,
      "step": 19025
    },
    {
      "epoch": 211.44444444444446,
      "grad_norm": 1.6100415223263553e-08,
      "learning_rate": 0.16142823911324888,
      "loss": 0.0,
      "num_input_tokens_seen": 5327808,
      "step": 19030
    },
    {
      "epoch": 211.5,
      "grad_norm": 9.186241989311839e-09,
      "learning_rate": 0.16136950458121568,
      "loss": 0.0,
      "num_input_tokens_seen": 5329216,
      "step": 19035
    },
    {
      "epoch": 211.55555555555554,
      "grad_norm": 1.9769080594755906e-08,
      "learning_rate": 0.16131076829586205,
      "loss": 0.0,
      "num_input_tokens_seen": 5330624,
      "step": 19040
    },
    {
      "epoch": 211.61111111111111,
      "grad_norm": 2.2789263809386284e-08,
      "learning_rate": 0.1612520302662457,
      "loss": 0.0,
      "num_input_tokens_seen": 5332016,
      "step": 19045
    },
    {
      "epoch": 211.66666666666666,
      "grad_norm": 9.969333802928304e-09,
      "learning_rate": 0.16119329050142497,
      "loss": 0.0,
      "num_input_tokens_seen": 5333424,
      "step": 19050
    },
    {
      "epoch": 211.72222222222223,
      "grad_norm": 1.0026173669075433e-08,
      "learning_rate": 0.16113454901045818,
      "loss": 0.0,
      "num_input_tokens_seen": 5334832,
      "step": 19055
    },
    {
      "epoch": 211.77777777777777,
      "grad_norm": 5.936056535205125e-09,
      "learning_rate": 0.16107580580240397,
      "loss": 0.0,
      "num_input_tokens_seen": 5336208,
      "step": 19060
    },
    {
      "epoch": 211.83333333333334,
      "grad_norm": 7.739800800266039e-09,
      "learning_rate": 0.16101706088632134,
      "loss": 0.0,
      "num_input_tokens_seen": 5337584,
      "step": 19065
    },
    {
      "epoch": 211.88888888888889,
      "grad_norm": 8.531890749452486e-09,
      "learning_rate": 0.16095831427126947,
      "loss": 0.0,
      "num_input_tokens_seen": 5338944,
      "step": 19070
    },
    {
      "epoch": 211.94444444444446,
      "grad_norm": 1.0285472917814786e-08,
      "learning_rate": 0.16089956596630783,
      "loss": 0.0,
      "num_input_tokens_seen": 5340368,
      "step": 19075
    },
    {
      "epoch": 212.0,
      "grad_norm": 1.3745162341649575e-08,
      "learning_rate": 0.16084081598049618,
      "loss": 0.0,
      "num_input_tokens_seen": 5341776,
      "step": 19080
    },
    {
      "epoch": 212.05555555555554,
      "grad_norm": 2.4725240521661362e-08,
      "learning_rate": 0.1607820643228944,
      "loss": 0.0,
      "num_input_tokens_seen": 5343120,
      "step": 19085
    },
    {
      "epoch": 212.11111111111111,
      "grad_norm": 1.1887530071419405e-08,
      "learning_rate": 0.16072331100256285,
      "loss": 0.0,
      "num_input_tokens_seen": 5344496,
      "step": 19090
    },
    {
      "epoch": 212.16666666666666,
      "grad_norm": 1.7038065180940976e-08,
      "learning_rate": 0.16066455602856197,
      "loss": 0.0,
      "num_input_tokens_seen": 5345920,
      "step": 19095
    },
    {
      "epoch": 212.22222222222223,
      "grad_norm": 1.121689763294853e-08,
      "learning_rate": 0.16060579940995257,
      "loss": 0.0,
      "num_input_tokens_seen": 5347312,
      "step": 19100
    },
    {
      "epoch": 212.27777777777777,
      "grad_norm": 1.2398245985423273e-08,
      "learning_rate": 0.16054704115579557,
      "loss": 0.0,
      "num_input_tokens_seen": 5348768,
      "step": 19105
    },
    {
      "epoch": 212.33333333333334,
      "grad_norm": 1.0057352284320586e-08,
      "learning_rate": 0.1604882812751523,
      "loss": 0.0,
      "num_input_tokens_seen": 5350192,
      "step": 19110
    },
    {
      "epoch": 212.38888888888889,
      "grad_norm": 9.461407657340715e-09,
      "learning_rate": 0.16042951977708425,
      "loss": 0.0,
      "num_input_tokens_seen": 5351600,
      "step": 19115
    },
    {
      "epoch": 212.44444444444446,
      "grad_norm": 9.924153054896578e-09,
      "learning_rate": 0.16037075667065318,
      "loss": 0.0,
      "num_input_tokens_seen": 5353040,
      "step": 19120
    },
    {
      "epoch": 212.5,
      "grad_norm": 1.0951623607979855e-08,
      "learning_rate": 0.1603119919649211,
      "loss": 0.0,
      "num_input_tokens_seen": 5354416,
      "step": 19125
    },
    {
      "epoch": 212.55555555555554,
      "grad_norm": 1.621546630303783e-08,
      "learning_rate": 0.16025322566895028,
      "loss": 0.0,
      "num_input_tokens_seen": 5355808,
      "step": 19130
    },
    {
      "epoch": 212.61111111111111,
      "grad_norm": 1.0838606456786692e-08,
      "learning_rate": 0.16019445779180322,
      "loss": 0.0,
      "num_input_tokens_seen": 5357248,
      "step": 19135
    },
    {
      "epoch": 212.66666666666666,
      "grad_norm": 1.6484255738191678e-08,
      "learning_rate": 0.16013568834254271,
      "loss": 0.0,
      "num_input_tokens_seen": 5358656,
      "step": 19140
    },
    {
      "epoch": 212.72222222222223,
      "grad_norm": 4.3403161065214135e-09,
      "learning_rate": 0.1600769173302316,
      "loss": 0.0,
      "num_input_tokens_seen": 5360016,
      "step": 19145
    },
    {
      "epoch": 212.77777777777777,
      "grad_norm": 7.0489227788073094e-09,
      "learning_rate": 0.16001814476393322,
      "loss": 0.0,
      "num_input_tokens_seen": 5361376,
      "step": 19150
    },
    {
      "epoch": 212.83333333333334,
      "grad_norm": 1.507269686840118e-08,
      "learning_rate": 0.15995937065271104,
      "loss": 0.0,
      "num_input_tokens_seen": 5362784,
      "step": 19155
    },
    {
      "epoch": 212.88888888888889,
      "grad_norm": 1.217682932264097e-08,
      "learning_rate": 0.15990059500562873,
      "loss": 0.0,
      "num_input_tokens_seen": 5364176,
      "step": 19160
    },
    {
      "epoch": 212.94444444444446,
      "grad_norm": 2.8534291374171517e-08,
      "learning_rate": 0.15984181783175025,
      "loss": 0.0,
      "num_input_tokens_seen": 5365584,
      "step": 19165
    },
    {
      "epoch": 213.0,
      "grad_norm": 1.913935143704748e-08,
      "learning_rate": 0.1597830391401398,
      "loss": 0.0,
      "num_input_tokens_seen": 5366960,
      "step": 19170
    },
    {
      "epoch": 213.05555555555554,
      "grad_norm": 1.501683577487256e-08,
      "learning_rate": 0.15972425893986178,
      "loss": 0.0,
      "num_input_tokens_seen": 5368320,
      "step": 19175
    },
    {
      "epoch": 213.11111111111111,
      "grad_norm": 1.4429853756325883e-08,
      "learning_rate": 0.15966547723998084,
      "loss": 0.0,
      "num_input_tokens_seen": 5369760,
      "step": 19180
    },
    {
      "epoch": 213.16666666666666,
      "grad_norm": 1.2070421995247216e-08,
      "learning_rate": 0.15960669404956176,
      "loss": 0.0,
      "num_input_tokens_seen": 5371136,
      "step": 19185
    },
    {
      "epoch": 213.22222222222223,
      "grad_norm": 9.887759055970946e-09,
      "learning_rate": 0.1595479093776698,
      "loss": 0.0,
      "num_input_tokens_seen": 5372528,
      "step": 19190
    },
    {
      "epoch": 213.27777777777777,
      "grad_norm": 2.763797013471958e-08,
      "learning_rate": 0.15948912323337022,
      "loss": 0.0,
      "num_input_tokens_seen": 5373888,
      "step": 19195
    },
    {
      "epoch": 213.33333333333334,
      "grad_norm": 1.5306932610315016e-08,
      "learning_rate": 0.1594303356257286,
      "loss": 0.0,
      "num_input_tokens_seen": 5375280,
      "step": 19200
    },
    {
      "epoch": 213.33333333333334,
      "eval_loss": 1.5504299402236938,
      "eval_runtime": 1.1847,
      "eval_samples_per_second": 33.763,
      "eval_steps_per_second": 16.881,
      "num_input_tokens_seen": 5375280,
      "step": 19200
    },
    {
      "epoch": 213.38888888888889,
      "grad_norm": 1.6903387134448167e-08,
      "learning_rate": 0.15937154656381072,
      "loss": 0.0,
      "num_input_tokens_seen": 5376704,
      "step": 19205
    },
    {
      "epoch": 213.44444444444446,
      "grad_norm": 1.1438972435939831e-08,
      "learning_rate": 0.15931275605668258,
      "loss": 0.0,
      "num_input_tokens_seen": 5378080,
      "step": 19210
    },
    {
      "epoch": 213.5,
      "grad_norm": 4.153771548942586e-09,
      "learning_rate": 0.1592539641134104,
      "loss": 0.0,
      "num_input_tokens_seen": 5379504,
      "step": 19215
    },
    {
      "epoch": 213.55555555555554,
      "grad_norm": 9.658817745616943e-09,
      "learning_rate": 0.1591951707430607,
      "loss": 0.0,
      "num_input_tokens_seen": 5380896,
      "step": 19220
    },
    {
      "epoch": 213.61111111111111,
      "grad_norm": 1.6036379335560014e-08,
      "learning_rate": 0.15913637595470007,
      "loss": 0.0,
      "num_input_tokens_seen": 5382304,
      "step": 19225
    },
    {
      "epoch": 213.66666666666666,
      "grad_norm": 1.2694659545786635e-08,
      "learning_rate": 0.15907757975739548,
      "loss": 0.0,
      "num_input_tokens_seen": 5383664,
      "step": 19230
    },
    {
      "epoch": 213.72222222222223,
      "grad_norm": 3.282805494109198e-08,
      "learning_rate": 0.159018782160214,
      "loss": 0.0,
      "num_input_tokens_seen": 5385088,
      "step": 19235
    },
    {
      "epoch": 213.77777777777777,
      "grad_norm": 5.701944694180838e-09,
      "learning_rate": 0.158959983172223,
      "loss": 0.0,
      "num_input_tokens_seen": 5386512,
      "step": 19240
    },
    {
      "epoch": 213.83333333333334,
      "grad_norm": 9.6639825031275e-09,
      "learning_rate": 0.15890118280249,
      "loss": 0.0,
      "num_input_tokens_seen": 5387968,
      "step": 19245
    },
    {
      "epoch": 213.88888888888889,
      "grad_norm": 9.481914808873171e-09,
      "learning_rate": 0.15884238106008275,
      "loss": 0.0,
      "num_input_tokens_seen": 5389392,
      "step": 19250
    },
    {
      "epoch": 213.94444444444446,
      "grad_norm": 1.0470005307183783e-08,
      "learning_rate": 0.15878357795406922,
      "loss": 0.0,
      "num_input_tokens_seen": 5390800,
      "step": 19255
    },
    {
      "epoch": 214.0,
      "grad_norm": 1.6994372131762248e-08,
      "learning_rate": 0.15872477349351757,
      "loss": 0.0,
      "num_input_tokens_seen": 5392192,
      "step": 19260
    },
    {
      "epoch": 214.05555555555554,
      "grad_norm": 1.4243497048482823e-08,
      "learning_rate": 0.15866596768749622,
      "loss": 0.0,
      "num_input_tokens_seen": 5393568,
      "step": 19265
    },
    {
      "epoch": 214.11111111111111,
      "grad_norm": 6.566451382639116e-09,
      "learning_rate": 0.15860716054507373,
      "loss": 0.0,
      "num_input_tokens_seen": 5395008,
      "step": 19270
    },
    {
      "epoch": 214.16666666666666,
      "grad_norm": 7.275806179762867e-09,
      "learning_rate": 0.1585483520753189,
      "loss": 0.0,
      "num_input_tokens_seen": 5396384,
      "step": 19275
    },
    {
      "epoch": 214.22222222222223,
      "grad_norm": 7.2647541315973285e-09,
      "learning_rate": 0.1584895422873008,
      "loss": 0.0,
      "num_input_tokens_seen": 5397744,
      "step": 19280
    },
    {
      "epoch": 214.27777777777777,
      "grad_norm": 1.615894795747863e-08,
      "learning_rate": 0.1584307311900886,
      "loss": 0.0,
      "num_input_tokens_seen": 5399168,
      "step": 19285
    },
    {
      "epoch": 214.33333333333334,
      "grad_norm": 1.858208698024555e-08,
      "learning_rate": 0.1583719187927517,
      "loss": 0.0,
      "num_input_tokens_seen": 5400560,
      "step": 19290
    },
    {
      "epoch": 214.38888888888889,
      "grad_norm": 8.298982834276103e-09,
      "learning_rate": 0.15831310510435967,
      "loss": 0.0,
      "num_input_tokens_seen": 5401984,
      "step": 19295
    },
    {
      "epoch": 214.44444444444446,
      "grad_norm": 7.262933809926153e-09,
      "learning_rate": 0.15825429013398243,
      "loss": 0.0,
      "num_input_tokens_seen": 5403392,
      "step": 19300
    },
    {
      "epoch": 214.5,
      "grad_norm": 1.4738833264971163e-08,
      "learning_rate": 0.15819547389068986,
      "loss": 0.0,
      "num_input_tokens_seen": 5404800,
      "step": 19305
    },
    {
      "epoch": 214.55555555555554,
      "grad_norm": 1.832795959444411e-08,
      "learning_rate": 0.1581366563835522,
      "loss": 0.0,
      "num_input_tokens_seen": 5406208,
      "step": 19310
    },
    {
      "epoch": 214.61111111111111,
      "grad_norm": 9.303336767629844e-09,
      "learning_rate": 0.15807783762163993,
      "loss": 0.0,
      "num_input_tokens_seen": 5407616,
      "step": 19315
    },
    {
      "epoch": 214.66666666666666,
      "grad_norm": 1.6172116090729105e-08,
      "learning_rate": 0.15801901761402365,
      "loss": 0.0,
      "num_input_tokens_seen": 5409040,
      "step": 19320
    },
    {
      "epoch": 214.72222222222223,
      "grad_norm": 1.3556268108061431e-08,
      "learning_rate": 0.157960196369774,
      "loss": 0.0,
      "num_input_tokens_seen": 5410448,
      "step": 19325
    },
    {
      "epoch": 214.77777777777777,
      "grad_norm": 8.568243003992393e-09,
      "learning_rate": 0.157901373897962,
      "loss": 0.0,
      "num_input_tokens_seen": 5411808,
      "step": 19330
    },
    {
      "epoch": 214.83333333333334,
      "grad_norm": 1.389066284218643e-08,
      "learning_rate": 0.15784255020765892,
      "loss": 0.0,
      "num_input_tokens_seen": 5413232,
      "step": 19335
    },
    {
      "epoch": 214.88888888888889,
      "grad_norm": 6.588432466259064e-09,
      "learning_rate": 0.157783725307936,
      "loss": 0.0,
      "num_input_tokens_seen": 5414656,
      "step": 19340
    },
    {
      "epoch": 214.94444444444446,
      "grad_norm": 9.682324275672727e-09,
      "learning_rate": 0.15772489920786484,
      "loss": 0.0,
      "num_input_tokens_seen": 5416080,
      "step": 19345
    },
    {
      "epoch": 215.0,
      "grad_norm": 6.073196168188133e-09,
      "learning_rate": 0.15766607191651713,
      "loss": 0.0,
      "num_input_tokens_seen": 5417472,
      "step": 19350
    },
    {
      "epoch": 215.05555555555554,
      "grad_norm": 1.0689433338484378e-08,
      "learning_rate": 0.1576072434429648,
      "loss": 0.0,
      "num_input_tokens_seen": 5418880,
      "step": 19355
    },
    {
      "epoch": 215.11111111111111,
      "grad_norm": 2.2394795351488028e-08,
      "learning_rate": 0.15754841379627998,
      "loss": 0.0,
      "num_input_tokens_seen": 5420272,
      "step": 19360
    },
    {
      "epoch": 215.16666666666666,
      "grad_norm": 9.06616381968206e-09,
      "learning_rate": 0.15748958298553484,
      "loss": 0.0,
      "num_input_tokens_seen": 5421664,
      "step": 19365
    },
    {
      "epoch": 215.22222222222223,
      "grad_norm": 6.399388574607201e-09,
      "learning_rate": 0.1574307510198019,
      "loss": 0.0,
      "num_input_tokens_seen": 5423072,
      "step": 19370
    },
    {
      "epoch": 215.27777777777777,
      "grad_norm": 5.76096859106201e-09,
      "learning_rate": 0.15737191790815375,
      "loss": 0.0,
      "num_input_tokens_seen": 5424496,
      "step": 19375
    },
    {
      "epoch": 215.33333333333334,
      "grad_norm": 5.9966316356963034e-09,
      "learning_rate": 0.15731308365966323,
      "loss": 0.0,
      "num_input_tokens_seen": 5425904,
      "step": 19380
    },
    {
      "epoch": 215.38888888888889,
      "grad_norm": 7.664108458982355e-09,
      "learning_rate": 0.15725424828340331,
      "loss": 0.0,
      "num_input_tokens_seen": 5427296,
      "step": 19385
    },
    {
      "epoch": 215.44444444444446,
      "grad_norm": 6.912273420311976e-08,
      "learning_rate": 0.15719541178844715,
      "loss": 0.0,
      "num_input_tokens_seen": 5428688,
      "step": 19390
    },
    {
      "epoch": 215.5,
      "grad_norm": 2.04362784472778e-08,
      "learning_rate": 0.15713657418386806,
      "loss": 0.0,
      "num_input_tokens_seen": 5430080,
      "step": 19395
    },
    {
      "epoch": 215.55555555555554,
      "grad_norm": 5.665147018163452e-09,
      "learning_rate": 0.15707773547873957,
      "loss": 0.0,
      "num_input_tokens_seen": 5431520,
      "step": 19400
    },
    {
      "epoch": 215.55555555555554,
      "eval_loss": 1.5738531351089478,
      "eval_runtime": 1.1872,
      "eval_samples_per_second": 33.693,
      "eval_steps_per_second": 16.846,
      "num_input_tokens_seen": 5431520,
      "step": 19400
    },
    {
      "epoch": 215.61111111111111,
      "grad_norm": 1.954767547829306e-08,
      "learning_rate": 0.1570188956821353,
      "loss": 0.0,
      "num_input_tokens_seen": 5432960,
      "step": 19405
    },
    {
      "epoch": 215.66666666666666,
      "grad_norm": 3.0585123766968536e-08,
      "learning_rate": 0.1569600548031291,
      "loss": 0.0,
      "num_input_tokens_seen": 5434352,
      "step": 19410
    },
    {
      "epoch": 215.72222222222223,
      "grad_norm": 5.7330935554489315e-09,
      "learning_rate": 0.156901212850795,
      "loss": 0.0,
      "num_input_tokens_seen": 5435760,
      "step": 19415
    },
    {
      "epoch": 215.77777777777777,
      "grad_norm": 2.0245277454478128e-08,
      "learning_rate": 0.15684236983420716,
      "loss": 0.0,
      "num_input_tokens_seen": 5437168,
      "step": 19420
    },
    {
      "epoch": 215.83333333333334,
      "grad_norm": 8.583660005001548e-09,
      "learning_rate": 0.1567835257624399,
      "loss": 0.0,
      "num_input_tokens_seen": 5438544,
      "step": 19425
    },
    {
      "epoch": 215.88888888888889,
      "grad_norm": 9.621163421513756e-09,
      "learning_rate": 0.1567246806445677,
      "loss": 0.0,
      "num_input_tokens_seen": 5439904,
      "step": 19430
    },
    {
      "epoch": 215.94444444444446,
      "grad_norm": 1.9684112118056873e-08,
      "learning_rate": 0.15666583448966526,
      "loss": 0.0,
      "num_input_tokens_seen": 5441360,
      "step": 19435
    },
    {
      "epoch": 216.0,
      "grad_norm": 4.086417959570099e-08,
      "learning_rate": 0.1566069873068074,
      "loss": 0.0,
      "num_input_tokens_seen": 5442752,
      "step": 19440
    },
    {
      "epoch": 216.05555555555554,
      "grad_norm": 1.1416635636862793e-08,
      "learning_rate": 0.156548139105069,
      "loss": 0.0,
      "num_input_tokens_seen": 5444176,
      "step": 19445
    },
    {
      "epoch": 216.11111111111111,
      "grad_norm": 6.960877207973226e-09,
      "learning_rate": 0.15648928989352529,
      "loss": 0.0,
      "num_input_tokens_seen": 5445584,
      "step": 19450
    },
    {
      "epoch": 216.16666666666666,
      "grad_norm": 2.7620965070696002e-08,
      "learning_rate": 0.15643043968125156,
      "loss": 0.0,
      "num_input_tokens_seen": 5446976,
      "step": 19455
    },
    {
      "epoch": 216.22222222222223,
      "grad_norm": 5.2619344437232485e-09,
      "learning_rate": 0.15637158847732316,
      "loss": 0.0,
      "num_input_tokens_seen": 5448384,
      "step": 19460
    },
    {
      "epoch": 216.27777777777777,
      "grad_norm": 1.4546895243938707e-08,
      "learning_rate": 0.15631273629081582,
      "loss": 0.0,
      "num_input_tokens_seen": 5449808,
      "step": 19465
    },
    {
      "epoch": 216.33333333333334,
      "grad_norm": 2.5919057122791855e-08,
      "learning_rate": 0.15625388313080518,
      "loss": 0.0,
      "num_input_tokens_seen": 5451232,
      "step": 19470
    },
    {
      "epoch": 216.38888888888889,
      "grad_norm": 1.8468476525868027e-08,
      "learning_rate": 0.15619502900636714,
      "loss": 0.0,
      "num_input_tokens_seen": 5452624,
      "step": 19475
    },
    {
      "epoch": 216.44444444444446,
      "grad_norm": 1.1814528910747413e-08,
      "learning_rate": 0.15613617392657783,
      "loss": 0.0,
      "num_input_tokens_seen": 5453968,
      "step": 19480
    },
    {
      "epoch": 216.5,
      "grad_norm": 1.1672054434086476e-08,
      "learning_rate": 0.15607731790051335,
      "loss": 0.0,
      "num_input_tokens_seen": 5455392,
      "step": 19485
    },
    {
      "epoch": 216.55555555555554,
      "grad_norm": 8.631828585237145e-09,
      "learning_rate": 0.15601846093725008,
      "loss": 0.0,
      "num_input_tokens_seen": 5456800,
      "step": 19490
    },
    {
      "epoch": 216.61111111111111,
      "grad_norm": 1.69464176025258e-08,
      "learning_rate": 0.1559596030458645,
      "loss": 0.0,
      "num_input_tokens_seen": 5458192,
      "step": 19495
    },
    {
      "epoch": 216.66666666666666,
      "grad_norm": 1.0672322581228855e-08,
      "learning_rate": 0.1559007442354333,
      "loss": 0.0,
      "num_input_tokens_seen": 5459568,
      "step": 19500
    },
    {
      "epoch": 216.72222222222223,
      "grad_norm": 1.0628965263492773e-08,
      "learning_rate": 0.15584188451503314,
      "loss": 0.0,
      "num_input_tokens_seen": 5460960,
      "step": 19505
    },
    {
      "epoch": 216.77777777777777,
      "grad_norm": 6.580380684795273e-09,
      "learning_rate": 0.15578302389374094,
      "loss": 0.0,
      "num_input_tokens_seen": 5462368,
      "step": 19510
    },
    {
      "epoch": 216.83333333333334,
      "grad_norm": 4.699162392540757e-09,
      "learning_rate": 0.1557241623806338,
      "loss": 0.0,
      "num_input_tokens_seen": 5463792,
      "step": 19515
    },
    {
      "epoch": 216.88888888888889,
      "grad_norm": 2.9207186003077368e-08,
      "learning_rate": 0.15566529998478887,
      "loss": 0.0,
      "num_input_tokens_seen": 5465232,
      "step": 19520
    },
    {
      "epoch": 216.94444444444446,
      "grad_norm": 9.115149524063781e-09,
      "learning_rate": 0.15560643671528354,
      "loss": 0.0,
      "num_input_tokens_seen": 5466640,
      "step": 19525
    },
    {
      "epoch": 217.0,
      "grad_norm": 8.307534216100976e-09,
      "learning_rate": 0.15554757258119514,
      "loss": 0.0,
      "num_input_tokens_seen": 5467984,
      "step": 19530
    },
    {
      "epoch": 217.05555555555554,
      "grad_norm": 1.2793490711260347e-08,
      "learning_rate": 0.1554887075916014,
      "loss": 0.0,
      "num_input_tokens_seen": 5469376,
      "step": 19535
    },
    {
      "epoch": 217.11111111111111,
      "grad_norm": 1.0794797056234984e-08,
      "learning_rate": 0.15542984175558,
      "loss": 0.0,
      "num_input_tokens_seen": 5470720,
      "step": 19540
    },
    {
      "epoch": 217.16666666666666,
      "grad_norm": 1.1001214161865391e-08,
      "learning_rate": 0.1553709750822087,
      "loss": 0.0,
      "num_input_tokens_seen": 5472112,
      "step": 19545
    },
    {
      "epoch": 217.22222222222223,
      "grad_norm": 7.807303248341668e-09,
      "learning_rate": 0.15531210758056554,
      "loss": 0.0,
      "num_input_tokens_seen": 5473520,
      "step": 19550
    },
    {
      "epoch": 217.27777777777777,
      "grad_norm": 5.038467865148277e-09,
      "learning_rate": 0.15525323925972867,
      "loss": 0.0,
      "num_input_tokens_seen": 5474912,
      "step": 19555
    },
    {
      "epoch": 217.33333333333334,
      "grad_norm": 1.539083172019673e-08,
      "learning_rate": 0.15519437012877627,
      "loss": 0.0,
      "num_input_tokens_seen": 5476288,
      "step": 19560
    },
    {
      "epoch": 217.38888888888889,
      "grad_norm": 1.2296712093018414e-08,
      "learning_rate": 0.15513550019678676,
      "loss": 0.0,
      "num_input_tokens_seen": 5477632,
      "step": 19565
    },
    {
      "epoch": 217.44444444444446,
      "grad_norm": 1.55986583649792e-08,
      "learning_rate": 0.15507662947283854,
      "loss": 0.0,
      "num_input_tokens_seen": 5479056,
      "step": 19570
    },
    {
      "epoch": 217.5,
      "grad_norm": 7.125240397698462e-09,
      "learning_rate": 0.15501775796601028,
      "loss": 0.0,
      "num_input_tokens_seen": 5480480,
      "step": 19575
    },
    {
      "epoch": 217.55555555555554,
      "grad_norm": 8.785067784344847e-09,
      "learning_rate": 0.15495888568538066,
      "loss": 0.0,
      "num_input_tokens_seen": 5481904,
      "step": 19580
    },
    {
      "epoch": 217.61111111111111,
      "grad_norm": 2.7327823559630815e-08,
      "learning_rate": 0.1549000126400286,
      "loss": 0.0,
      "num_input_tokens_seen": 5483280,
      "step": 19585
    },
    {
      "epoch": 217.66666666666666,
      "grad_norm": 2.0754452378923816e-08,
      "learning_rate": 0.15484113883903294,
      "loss": 0.0,
      "num_input_tokens_seen": 5484688,
      "step": 19590
    },
    {
      "epoch": 217.72222222222223,
      "grad_norm": 1.2154759865268261e-08,
      "learning_rate": 0.15478226429147288,
      "loss": 0.0,
      "num_input_tokens_seen": 5486064,
      "step": 19595
    },
    {
      "epoch": 217.77777777777777,
      "grad_norm": 2.0329986583078608e-08,
      "learning_rate": 0.15472338900642757,
      "loss": 0.0,
      "num_input_tokens_seen": 5487472,
      "step": 19600
    },
    {
      "epoch": 217.77777777777777,
      "eval_loss": 1.5765345096588135,
      "eval_runtime": 1.184,
      "eval_samples_per_second": 33.782,
      "eval_steps_per_second": 16.891,
      "num_input_tokens_seen": 5487472,
      "step": 19600
    },
    {
      "epoch": 217.83333333333334,
      "grad_norm": 2.153464251364312e-08,
      "learning_rate": 0.15466451299297632,
      "loss": 0.0,
      "num_input_tokens_seen": 5488880,
      "step": 19605
    },
    {
      "epoch": 217.88888888888889,
      "grad_norm": 2.491880302102345e-08,
      "learning_rate": 0.15460563626019852,
      "loss": 0.0,
      "num_input_tokens_seen": 5490304,
      "step": 19610
    },
    {
      "epoch": 217.94444444444446,
      "grad_norm": 8.428300724006021e-09,
      "learning_rate": 0.15454675881717375,
      "loss": 0.0,
      "num_input_tokens_seen": 5491712,
      "step": 19615
    },
    {
      "epoch": 218.0,
      "grad_norm": 1.4595300079633944e-08,
      "learning_rate": 0.1544878806729816,
      "loss": 0.0,
      "num_input_tokens_seen": 5493136,
      "step": 19620
    },
    {
      "epoch": 218.05555555555554,
      "grad_norm": 1.0792450488850136e-08,
      "learning_rate": 0.1544290018367019,
      "loss": 0.0,
      "num_input_tokens_seen": 5494528,
      "step": 19625
    },
    {
      "epoch": 218.11111111111111,
      "grad_norm": 1.957101147809226e-08,
      "learning_rate": 0.15437012231741445,
      "loss": 0.0,
      "num_input_tokens_seen": 5495920,
      "step": 19630
    },
    {
      "epoch": 218.16666666666666,
      "grad_norm": 2.660888398509087e-08,
      "learning_rate": 0.1543112421241992,
      "loss": 0.0,
      "num_input_tokens_seen": 5497296,
      "step": 19635
    },
    {
      "epoch": 218.22222222222223,
      "grad_norm": 1.962751738915358e-08,
      "learning_rate": 0.15425236126613626,
      "loss": 0.0,
      "num_input_tokens_seen": 5498688,
      "step": 19640
    },
    {
      "epoch": 218.27777777777777,
      "grad_norm": 1.0459859645095548e-08,
      "learning_rate": 0.15419347975230577,
      "loss": 0.0,
      "num_input_tokens_seen": 5500096,
      "step": 19645
    },
    {
      "epoch": 218.33333333333334,
      "grad_norm": 1.0768443914344061e-08,
      "learning_rate": 0.154134597591788,
      "loss": 0.0,
      "num_input_tokens_seen": 5501520,
      "step": 19650
    },
    {
      "epoch": 218.38888888888889,
      "grad_norm": 1.2778507141320006e-08,
      "learning_rate": 0.1540757147936633,
      "loss": 0.0,
      "num_input_tokens_seen": 5502928,
      "step": 19655
    },
    {
      "epoch": 218.44444444444446,
      "grad_norm": 9.291756697393794e-09,
      "learning_rate": 0.1540168313670122,
      "loss": 0.0,
      "num_input_tokens_seen": 5504304,
      "step": 19660
    },
    {
      "epoch": 218.5,
      "grad_norm": 4.480413373642023e-09,
      "learning_rate": 0.1539579473209152,
      "loss": 0.0,
      "num_input_tokens_seen": 5505664,
      "step": 19665
    },
    {
      "epoch": 218.55555555555554,
      "grad_norm": 1.6977049099864416e-08,
      "learning_rate": 0.15389906266445294,
      "loss": 0.0,
      "num_input_tokens_seen": 5507088,
      "step": 19670
    },
    {
      "epoch": 218.61111111111111,
      "grad_norm": 2.4046761026852437e-08,
      "learning_rate": 0.15384017740670627,
      "loss": 0.0,
      "num_input_tokens_seen": 5508512,
      "step": 19675
    },
    {
      "epoch": 218.66666666666666,
      "grad_norm": 5.149703330431521e-09,
      "learning_rate": 0.15378129155675602,
      "loss": 0.0,
      "num_input_tokens_seen": 5509952,
      "step": 19680
    },
    {
      "epoch": 218.72222222222223,
      "grad_norm": 1.3984158719893003e-08,
      "learning_rate": 0.15372240512368307,
      "loss": 0.0,
      "num_input_tokens_seen": 5511344,
      "step": 19685
    },
    {
      "epoch": 218.77777777777777,
      "grad_norm": 1.04019504121311e-08,
      "learning_rate": 0.1536635181165684,
      "loss": 0.0,
      "num_input_tokens_seen": 5512720,
      "step": 19690
    },
    {
      "epoch": 218.83333333333334,
      "grad_norm": 6.7969878614349e-09,
      "learning_rate": 0.15360463054449328,
      "loss": 0.0,
      "num_input_tokens_seen": 5514112,
      "step": 19695
    },
    {
      "epoch": 218.88888888888889,
      "grad_norm": 1.1371988684061307e-08,
      "learning_rate": 0.1535457424165388,
      "loss": 0.0,
      "num_input_tokens_seen": 5515568,
      "step": 19700
    },
    {
      "epoch": 218.94444444444446,
      "grad_norm": 8.273500107236487e-09,
      "learning_rate": 0.15348685374178628,
      "loss": 0.0,
      "num_input_tokens_seen": 5516992,
      "step": 19705
    },
    {
      "epoch": 219.0,
      "grad_norm": 1.1982969283508282e-08,
      "learning_rate": 0.1534279645293171,
      "loss": 0.0,
      "num_input_tokens_seen": 5518368,
      "step": 19710
    },
    {
      "epoch": 219.05555555555554,
      "grad_norm": 1.4506412071568775e-08,
      "learning_rate": 0.1533690747882127,
      "loss": 0.0,
      "num_input_tokens_seen": 5519776,
      "step": 19715
    },
    {
      "epoch": 219.11111111111111,
      "grad_norm": 1.0512430925757599e-08,
      "learning_rate": 0.15331018452755465,
      "loss": 0.0,
      "num_input_tokens_seen": 5521216,
      "step": 19720
    },
    {
      "epoch": 219.16666666666666,
      "grad_norm": 1.7499584004099233e-08,
      "learning_rate": 0.15325129375642457,
      "loss": 0.0,
      "num_input_tokens_seen": 5522608,
      "step": 19725
    },
    {
      "epoch": 219.22222222222223,
      "grad_norm": 2.2474148764217716e-08,
      "learning_rate": 0.15319240248390406,
      "loss": 0.0,
      "num_input_tokens_seen": 5524016,
      "step": 19730
    },
    {
      "epoch": 219.27777777777777,
      "grad_norm": 1.1194972060479813e-08,
      "learning_rate": 0.153133510719075,
      "loss": 0.0,
      "num_input_tokens_seen": 5525424,
      "step": 19735
    },
    {
      "epoch": 219.33333333333334,
      "grad_norm": 5.768497679525808e-09,
      "learning_rate": 0.15307461847101922,
      "loss": 0.0,
      "num_input_tokens_seen": 5526816,
      "step": 19740
    },
    {
      "epoch": 219.38888888888889,
      "grad_norm": 1.062130294826602e-08,
      "learning_rate": 0.15301572574881864,
      "loss": 0.0,
      "num_input_tokens_seen": 5528192,
      "step": 19745
    },
    {
      "epoch": 219.44444444444446,
      "grad_norm": 8.368484571974477e-09,
      "learning_rate": 0.15295683256155523,
      "loss": 0.0,
      "num_input_tokens_seen": 5529616,
      "step": 19750
    },
    {
      "epoch": 219.5,
      "grad_norm": 1.221947876217655e-08,
      "learning_rate": 0.15289793891831113,
      "loss": 0.0,
      "num_input_tokens_seen": 5531008,
      "step": 19755
    },
    {
      "epoch": 219.55555555555554,
      "grad_norm": 1.7423873899247155e-08,
      "learning_rate": 0.15283904482816837,
      "loss": 0.0,
      "num_input_tokens_seen": 5532384,
      "step": 19760
    },
    {
      "epoch": 219.61111111111111,
      "grad_norm": 5.012180004371203e-09,
      "learning_rate": 0.15278015030020928,
      "loss": 0.0,
      "num_input_tokens_seen": 5533728,
      "step": 19765
    },
    {
      "epoch": 219.66666666666666,
      "grad_norm": 1.3407103871543313e-08,
      "learning_rate": 0.152721255343516,
      "loss": 0.0,
      "num_input_tokens_seen": 5535152,
      "step": 19770
    },
    {
      "epoch": 219.72222222222223,
      "grad_norm": 1.0538577122076731e-08,
      "learning_rate": 0.15266235996717098,
      "loss": 0.0,
      "num_input_tokens_seen": 5536560,
      "step": 19775
    },
    {
      "epoch": 219.77777777777777,
      "grad_norm": 9.106501330791161e-09,
      "learning_rate": 0.15260346418025664,
      "loss": 0.0,
      "num_input_tokens_seen": 5537936,
      "step": 19780
    },
    {
      "epoch": 219.83333333333334,
      "grad_norm": 8.690703268143807e-09,
      "learning_rate": 0.15254456799185537,
      "loss": 0.0,
      "num_input_tokens_seen": 5539360,
      "step": 19785
    },
    {
      "epoch": 219.88888888888889,
      "grad_norm": 3.1937737787757214e-08,
      "learning_rate": 0.15248567141104974,
      "loss": 0.0,
      "num_input_tokens_seen": 5540784,
      "step": 19790
    },
    {
      "epoch": 219.94444444444446,
      "grad_norm": 8.326757061638546e-09,
      "learning_rate": 0.15242677444692232,
      "loss": 0.0,
      "num_input_tokens_seen": 5542160,
      "step": 19795
    },
    {
      "epoch": 220.0,
      "grad_norm": 8.859582401044008e-09,
      "learning_rate": 0.15236787710855584,
      "loss": 0.0,
      "num_input_tokens_seen": 5543504,
      "step": 19800
    },
    {
      "epoch": 220.0,
      "eval_loss": 1.5910969972610474,
      "eval_runtime": 1.1835,
      "eval_samples_per_second": 33.799,
      "eval_steps_per_second": 16.9,
      "num_input_tokens_seen": 5543504,
      "step": 19800
    },
    {
      "epoch": 220.05555555555554,
      "grad_norm": 1.667303983765578e-08,
      "learning_rate": 0.1523089794050329,
      "loss": 0.0,
      "num_input_tokens_seen": 5544928,
      "step": 19805
    },
    {
      "epoch": 220.11111111111111,
      "grad_norm": 1.4290799654759212e-08,
      "learning_rate": 0.15225008134543633,
      "loss": 0.0,
      "num_input_tokens_seen": 5546352,
      "step": 19810
    },
    {
      "epoch": 220.16666666666666,
      "grad_norm": 1.1628489282600185e-08,
      "learning_rate": 0.15219118293884895,
      "loss": 0.0,
      "num_input_tokens_seen": 5547712,
      "step": 19815
    },
    {
      "epoch": 220.22222222222223,
      "grad_norm": 6.9866117335948275e-09,
      "learning_rate": 0.15213228419435362,
      "loss": 0.0,
      "num_input_tokens_seen": 5549168,
      "step": 19820
    },
    {
      "epoch": 220.27777777777777,
      "grad_norm": 2.3130850124175595e-08,
      "learning_rate": 0.15207338512103327,
      "loss": 0.0,
      "num_input_tokens_seen": 5550576,
      "step": 19825
    },
    {
      "epoch": 220.33333333333334,
      "grad_norm": 1.6349968490203537e-08,
      "learning_rate": 0.1520144857279709,
      "loss": 0.0,
      "num_input_tokens_seen": 5551968,
      "step": 19830
    },
    {
      "epoch": 220.38888888888889,
      "grad_norm": 7.645919453125316e-09,
      "learning_rate": 0.1519555860242495,
      "loss": 0.0,
      "num_input_tokens_seen": 5553376,
      "step": 19835
    },
    {
      "epoch": 220.44444444444446,
      "grad_norm": 5.122305246629821e-09,
      "learning_rate": 0.15189668601895218,
      "loss": 0.0,
      "num_input_tokens_seen": 5554736,
      "step": 19840
    },
    {
      "epoch": 220.5,
      "grad_norm": 1.0359229030143524e-08,
      "learning_rate": 0.151837785721162,
      "loss": 0.0,
      "num_input_tokens_seen": 5556112,
      "step": 19845
    },
    {
      "epoch": 220.55555555555554,
      "grad_norm": 4.18201651086747e-09,
      "learning_rate": 0.15177888513996218,
      "loss": 0.0,
      "num_input_tokens_seen": 5557520,
      "step": 19850
    },
    {
      "epoch": 220.61111111111111,
      "grad_norm": 7.102661570002056e-09,
      "learning_rate": 0.15171998428443592,
      "loss": 0.0,
      "num_input_tokens_seen": 5558944,
      "step": 19855
    },
    {
      "epoch": 220.66666666666666,
      "grad_norm": 1.4717334018143902e-08,
      "learning_rate": 0.1516610831636665,
      "loss": 0.0,
      "num_input_tokens_seen": 5560352,
      "step": 19860
    },
    {
      "epoch": 220.72222222222223,
      "grad_norm": 2.2391715148728508e-08,
      "learning_rate": 0.15160218178673715,
      "loss": 0.0,
      "num_input_tokens_seen": 5561776,
      "step": 19865
    },
    {
      "epoch": 220.77777777777777,
      "grad_norm": 7.405996260700931e-09,
      "learning_rate": 0.15154328016273122,
      "loss": 0.0,
      "num_input_tokens_seen": 5563136,
      "step": 19870
    },
    {
      "epoch": 220.83333333333334,
      "grad_norm": 1.6912956368742016e-08,
      "learning_rate": 0.1514843783007321,
      "loss": 0.0,
      "num_input_tokens_seen": 5564528,
      "step": 19875
    },
    {
      "epoch": 220.88888888888889,
      "grad_norm": 6.1440861287564985e-09,
      "learning_rate": 0.15142547620982322,
      "loss": 0.0,
      "num_input_tokens_seen": 5565888,
      "step": 19880
    },
    {
      "epoch": 220.94444444444446,
      "grad_norm": 1.413400685379429e-08,
      "learning_rate": 0.15136657389908797,
      "loss": 0.0,
      "num_input_tokens_seen": 5567312,
      "step": 19885
    },
    {
      "epoch": 221.0,
      "grad_norm": 4.89723950281018e-09,
      "learning_rate": 0.15130767137760986,
      "loss": 0.0,
      "num_input_tokens_seen": 5568672,
      "step": 19890
    },
    {
      "epoch": 221.05555555555554,
      "grad_norm": 1.7698578602676207e-08,
      "learning_rate": 0.15124876865447243,
      "loss": 0.0,
      "num_input_tokens_seen": 5570096,
      "step": 19895
    },
    {
      "epoch": 221.11111111111111,
      "grad_norm": 6.8222894000768974e-09,
      "learning_rate": 0.15118986573875912,
      "loss": 0.0,
      "num_input_tokens_seen": 5571456,
      "step": 19900
    },
    {
      "epoch": 221.16666666666666,
      "grad_norm": 1.506742997037236e-08,
      "learning_rate": 0.15113096263955358,
      "loss": 0.0,
      "num_input_tokens_seen": 5572848,
      "step": 19905
    },
    {
      "epoch": 221.22222222222223,
      "grad_norm": 5.350951681748484e-09,
      "learning_rate": 0.1510720593659394,
      "loss": 0.0,
      "num_input_tokens_seen": 5574240,
      "step": 19910
    },
    {
      "epoch": 221.27777777777777,
      "grad_norm": 5.8637046329579334e-09,
      "learning_rate": 0.15101315592700015,
      "loss": 0.0,
      "num_input_tokens_seen": 5575616,
      "step": 19915
    },
    {
      "epoch": 221.33333333333334,
      "grad_norm": 2.772152818408813e-08,
      "learning_rate": 0.15095425233181956,
      "loss": 0.0,
      "num_input_tokens_seen": 5577040,
      "step": 19920
    },
    {
      "epoch": 221.38888888888889,
      "grad_norm": 1.0398090388719083e-08,
      "learning_rate": 0.15089534858948128,
      "loss": 0.0,
      "num_input_tokens_seen": 5578432,
      "step": 19925
    },
    {
      "epoch": 221.44444444444446,
      "grad_norm": 5.4733795273875785e-09,
      "learning_rate": 0.15083644470906898,
      "loss": 0.0,
      "num_input_tokens_seen": 5579856,
      "step": 19930
    },
    {
      "epoch": 221.5,
      "grad_norm": 5.462154728519408e-09,
      "learning_rate": 0.1507775406996664,
      "loss": 0.0,
      "num_input_tokens_seen": 5581216,
      "step": 19935
    },
    {
      "epoch": 221.55555555555554,
      "grad_norm": 1.0828277829944e-08,
      "learning_rate": 0.15071863657035725,
      "loss": 0.0,
      "num_input_tokens_seen": 5582656,
      "step": 19940
    },
    {
      "epoch": 221.61111111111111,
      "grad_norm": 7.174923322139648e-09,
      "learning_rate": 0.15065973233022534,
      "loss": 0.0,
      "num_input_tokens_seen": 5584032,
      "step": 19945
    },
    {
      "epoch": 221.66666666666666,
      "grad_norm": 9.568024594841518e-09,
      "learning_rate": 0.15060082798835442,
      "loss": 0.0,
      "num_input_tokens_seen": 5585408,
      "step": 19950
    },
    {
      "epoch": 221.72222222222223,
      "grad_norm": 1.072769162391296e-08,
      "learning_rate": 0.15054192355382823,
      "loss": 0.0,
      "num_input_tokens_seen": 5586848,
      "step": 19955
    },
    {
      "epoch": 221.77777777777777,
      "grad_norm": 1.3775436791263473e-08,
      "learning_rate": 0.15048301903573066,
      "loss": 0.0,
      "num_input_tokens_seen": 5588224,
      "step": 19960
    },
    {
      "epoch": 221.83333333333334,
      "grad_norm": 2.1478033573885114e-08,
      "learning_rate": 0.15042411444314546,
      "loss": 0.0,
      "num_input_tokens_seen": 5589664,
      "step": 19965
    },
    {
      "epoch": 221.88888888888889,
      "grad_norm": 1.4516990276547403e-08,
      "learning_rate": 0.1503652097851565,
      "loss": 0.0,
      "num_input_tokens_seen": 5591056,
      "step": 19970
    },
    {
      "epoch": 221.94444444444446,
      "grad_norm": 2.8179966804486867e-08,
      "learning_rate": 0.15030630507084758,
      "loss": 0.0,
      "num_input_tokens_seen": 5592432,
      "step": 19975
    },
    {
      "epoch": 222.0,
      "grad_norm": 2.1477754685861328e-08,
      "learning_rate": 0.1502474003093026,
      "loss": 0.0,
      "num_input_tokens_seen": 5593824,
      "step": 19980
    },
    {
      "epoch": 222.05555555555554,
      "grad_norm": 1.7642840077769506e-08,
      "learning_rate": 0.15018849550960536,
      "loss": 0.0,
      "num_input_tokens_seen": 5595264,
      "step": 19985
    },
    {
      "epoch": 222.11111111111111,
      "grad_norm": 6.8513124062974384e-09,
      "learning_rate": 0.15012959068083975,
      "loss": 0.0,
      "num_input_tokens_seen": 5596688,
      "step": 19990
    },
    {
      "epoch": 222.16666666666666,
      "grad_norm": 8.492958336603351e-09,
      "learning_rate": 0.1500706858320896,
      "loss": 0.0,
      "num_input_tokens_seen": 5598080,
      "step": 19995
    },
    {
      "epoch": 222.22222222222223,
      "grad_norm": 9.570467085495693e-09,
      "learning_rate": 0.15001178097243886,
      "loss": 0.0,
      "num_input_tokens_seen": 5599440,
      "step": 20000
    },
    {
      "epoch": 222.22222222222223,
      "eval_loss": 1.5940473079681396,
      "eval_runtime": 1.1835,
      "eval_samples_per_second": 33.798,
      "eval_steps_per_second": 16.899,
      "num_input_tokens_seen": 5599440,
      "step": 20000
    },
    {
      "epoch": 222.27777777777777,
      "grad_norm": 2.2403872534937364e-08,
      "learning_rate": 0.1499528761109713,
      "loss": 0.0,
      "num_input_tokens_seen": 5600848,
      "step": 20005
    },
    {
      "epoch": 222.33333333333334,
      "grad_norm": 8.909587734251545e-09,
      "learning_rate": 0.14989397125677087,
      "loss": 0.0,
      "num_input_tokens_seen": 5602240,
      "step": 20010
    },
    {
      "epoch": 222.38888888888889,
      "grad_norm": 1.0055575039302767e-08,
      "learning_rate": 0.14983506641892141,
      "loss": 0.0,
      "num_input_tokens_seen": 5603600,
      "step": 20015
    },
    {
      "epoch": 222.44444444444446,
      "grad_norm": 9.80306680276044e-09,
      "learning_rate": 0.14977616160650672,
      "loss": 0.0,
      "num_input_tokens_seen": 5604992,
      "step": 20020
    },
    {
      "epoch": 222.5,
      "grad_norm": 1.309292230189385e-08,
      "learning_rate": 0.14971725682861076,
      "loss": 0.0,
      "num_input_tokens_seen": 5606384,
      "step": 20025
    },
    {
      "epoch": 222.55555555555554,
      "grad_norm": 7.437688243072671e-09,
      "learning_rate": 0.14965835209431738,
      "loss": 0.0,
      "num_input_tokens_seen": 5607792,
      "step": 20030
    },
    {
      "epoch": 222.61111111111111,
      "grad_norm": 4.822441113105924e-09,
      "learning_rate": 0.14959944741271036,
      "loss": 0.0,
      "num_input_tokens_seen": 5609216,
      "step": 20035
    },
    {
      "epoch": 222.66666666666666,
      "grad_norm": 1.6636967359318078e-08,
      "learning_rate": 0.14954054279287363,
      "loss": 0.0,
      "num_input_tokens_seen": 5610656,
      "step": 20040
    },
    {
      "epoch": 222.72222222222223,
      "grad_norm": 1.5862982039038798e-08,
      "learning_rate": 0.14948163824389094,
      "loss": 0.0,
      "num_input_tokens_seen": 5612064,
      "step": 20045
    },
    {
      "epoch": 222.77777777777777,
      "grad_norm": 6.873119851036336e-09,
      "learning_rate": 0.14942273377484613,
      "loss": 0.0,
      "num_input_tokens_seen": 5613472,
      "step": 20050
    },
    {
      "epoch": 222.83333333333334,
      "grad_norm": 1.4202144349440005e-08,
      "learning_rate": 0.1493638293948231,
      "loss": 0.0,
      "num_input_tokens_seen": 5614816,
      "step": 20055
    },
    {
      "epoch": 222.88888888888889,
      "grad_norm": 8.81746053948973e-09,
      "learning_rate": 0.14930492511290547,
      "loss": 0.0,
      "num_input_tokens_seen": 5616208,
      "step": 20060
    },
    {
      "epoch": 222.94444444444446,
      "grad_norm": 6.870227053923372e-08,
      "learning_rate": 0.14924602093817715,
      "loss": 0.0,
      "num_input_tokens_seen": 5617632,
      "step": 20065
    },
    {
      "epoch": 223.0,
      "grad_norm": 1.4633839917621572e-08,
      "learning_rate": 0.14918711687972194,
      "loss": 0.0,
      "num_input_tokens_seen": 5619024,
      "step": 20070
    },
    {
      "epoch": 223.05555555555554,
      "grad_norm": 8.628030734314507e-09,
      "learning_rate": 0.14912821294662346,
      "loss": 0.0,
      "num_input_tokens_seen": 5620448,
      "step": 20075
    },
    {
      "epoch": 223.11111111111111,
      "grad_norm": 4.202586723067725e-08,
      "learning_rate": 0.14906930914796554,
      "loss": 0.0,
      "num_input_tokens_seen": 5621840,
      "step": 20080
    },
    {
      "epoch": 223.16666666666666,
      "grad_norm": 8.406517260084456e-09,
      "learning_rate": 0.14901040549283182,
      "loss": 0.0,
      "num_input_tokens_seen": 5623280,
      "step": 20085
    },
    {
      "epoch": 223.22222222222223,
      "grad_norm": 6.384274442439164e-09,
      "learning_rate": 0.148951501990306,
      "loss": 0.0,
      "num_input_tokens_seen": 5624672,
      "step": 20090
    },
    {
      "epoch": 223.27777777777777,
      "grad_norm": 1.8432761095255046e-08,
      "learning_rate": 0.14889259864947177,
      "loss": 0.0,
      "num_input_tokens_seen": 5626112,
      "step": 20095
    },
    {
      "epoch": 223.33333333333334,
      "grad_norm": 1.1818516831851866e-08,
      "learning_rate": 0.14883369547941272,
      "loss": 0.0,
      "num_input_tokens_seen": 5627552,
      "step": 20100
    },
    {
      "epoch": 223.38888888888889,
      "grad_norm": 1.1580942427258378e-08,
      "learning_rate": 0.14877479248921247,
      "loss": 0.0,
      "num_input_tokens_seen": 5628944,
      "step": 20105
    },
    {
      "epoch": 223.44444444444446,
      "grad_norm": 7.54280637949023e-09,
      "learning_rate": 0.14871588968795468,
      "loss": 0.0,
      "num_input_tokens_seen": 5630320,
      "step": 20110
    },
    {
      "epoch": 223.5,
      "grad_norm": 1.3654222641434899e-08,
      "learning_rate": 0.1486569870847228,
      "loss": 0.0,
      "num_input_tokens_seen": 5631664,
      "step": 20115
    },
    {
      "epoch": 223.55555555555554,
      "grad_norm": 1.6526287893725566e-08,
      "learning_rate": 0.1485980846886004,
      "loss": 0.0,
      "num_input_tokens_seen": 5633056,
      "step": 20120
    },
    {
      "epoch": 223.61111111111111,
      "grad_norm": 1.0541834960520191e-08,
      "learning_rate": 0.14853918250867096,
      "loss": 0.0,
      "num_input_tokens_seen": 5634448,
      "step": 20125
    },
    {
      "epoch": 223.66666666666666,
      "grad_norm": 9.745737550304057e-09,
      "learning_rate": 0.1484802805540179,
      "loss": 0.0,
      "num_input_tokens_seen": 5635824,
      "step": 20130
    },
    {
      "epoch": 223.72222222222223,
      "grad_norm": 2.43328681648336e-08,
      "learning_rate": 0.14842137883372472,
      "loss": 0.0,
      "num_input_tokens_seen": 5637232,
      "step": 20135
    },
    {
      "epoch": 223.77777777777777,
      "grad_norm": 6.696894594426794e-09,
      "learning_rate": 0.14836247735687474,
      "loss": 0.0,
      "num_input_tokens_seen": 5638640,
      "step": 20140
    },
    {
      "epoch": 223.83333333333334,
      "grad_norm": 8.833170639377386e-09,
      "learning_rate": 0.14830357613255132,
      "loss": 0.0,
      "num_input_tokens_seen": 5640048,
      "step": 20145
    },
    {
      "epoch": 223.88888888888889,
      "grad_norm": 5.739966724149781e-09,
      "learning_rate": 0.1482446751698378,
      "loss": 0.0,
      "num_input_tokens_seen": 5641472,
      "step": 20150
    },
    {
      "epoch": 223.94444444444446,
      "grad_norm": 8.631121595215063e-09,
      "learning_rate": 0.14818577447781744,
      "loss": 0.0,
      "num_input_tokens_seen": 5642880,
      "step": 20155
    },
    {
      "epoch": 224.0,
      "grad_norm": 2.1867709421030668e-08,
      "learning_rate": 0.14812687406557346,
      "loss": 0.0,
      "num_input_tokens_seen": 5644224,
      "step": 20160
    },
    {
      "epoch": 224.05555555555554,
      "grad_norm": 7.392082945756329e-09,
      "learning_rate": 0.14806797394218899,
      "loss": 0.0,
      "num_input_tokens_seen": 5645600,
      "step": 20165
    },
    {
      "epoch": 224.11111111111111,
      "grad_norm": 2.8944597829649865e-08,
      "learning_rate": 0.1480090741167472,
      "loss": 0.0,
      "num_input_tokens_seen": 5647024,
      "step": 20170
    },
    {
      "epoch": 224.16666666666666,
      "grad_norm": 1.3802851306365937e-08,
      "learning_rate": 0.1479501745983313,
      "loss": 0.0,
      "num_input_tokens_seen": 5648448,
      "step": 20175
    },
    {
      "epoch": 224.22222222222223,
      "grad_norm": 7.591692607888945e-09,
      "learning_rate": 0.14789127539602415,
      "loss": 0.0,
      "num_input_tokens_seen": 5649856,
      "step": 20180
    },
    {
      "epoch": 224.27777777777777,
      "grad_norm": 4.327597391551308e-09,
      "learning_rate": 0.14783237651890885,
      "loss": 0.0,
      "num_input_tokens_seen": 5651216,
      "step": 20185
    },
    {
      "epoch": 224.33333333333334,
      "grad_norm": 6.7514007717761615e-09,
      "learning_rate": 0.14777347797606838,
      "loss": 0.0,
      "num_input_tokens_seen": 5652624,
      "step": 20190
    },
    {
      "epoch": 224.38888888888889,
      "grad_norm": 1.486856859855834e-08,
      "learning_rate": 0.14771457977658553,
      "loss": 0.0,
      "num_input_tokens_seen": 5654016,
      "step": 20195
    },
    {
      "epoch": 224.44444444444446,
      "grad_norm": 2.496290107956156e-08,
      "learning_rate": 0.14765568192954326,
      "loss": 0.0,
      "num_input_tokens_seen": 5655424,
      "step": 20200
    },
    {
      "epoch": 224.44444444444446,
      "eval_loss": 1.5977230072021484,
      "eval_runtime": 1.1905,
      "eval_samples_per_second": 33.599,
      "eval_steps_per_second": 16.799,
      "num_input_tokens_seen": 5655424,
      "step": 20200
    },
    {
      "epoch": 224.5,
      "grad_norm": 1.1815238565304753e-08,
      "learning_rate": 0.14759678444402421,
      "loss": 0.0,
      "num_input_tokens_seen": 5656832,
      "step": 20205
    },
    {
      "epoch": 224.55555555555554,
      "grad_norm": 5.168408367950406e-09,
      "learning_rate": 0.14753788732911122,
      "loss": 0.0,
      "num_input_tokens_seen": 5658208,
      "step": 20210
    },
    {
      "epoch": 224.61111111111111,
      "grad_norm": 1.7693187359668627e-08,
      "learning_rate": 0.147478990593887,
      "loss": 0.0,
      "num_input_tokens_seen": 5659568,
      "step": 20215
    },
    {
      "epoch": 224.66666666666666,
      "grad_norm": 1.6662063728745125e-08,
      "learning_rate": 0.14742009424743405,
      "loss": 0.0,
      "num_input_tokens_seen": 5661024,
      "step": 20220
    },
    {
      "epoch": 224.72222222222223,
      "grad_norm": 4.933646380322898e-09,
      "learning_rate": 0.14736119829883504,
      "loss": 0.0,
      "num_input_tokens_seen": 5662416,
      "step": 20225
    },
    {
      "epoch": 224.77777777777777,
      "grad_norm": 4.444971679617993e-08,
      "learning_rate": 0.14730230275717243,
      "loss": 0.0,
      "num_input_tokens_seen": 5663840,
      "step": 20230
    },
    {
      "epoch": 224.83333333333334,
      "grad_norm": 1.532596449749235e-08,
      "learning_rate": 0.14724340763152854,
      "loss": 0.0,
      "num_input_tokens_seen": 5665264,
      "step": 20235
    },
    {
      "epoch": 224.88888888888889,
      "grad_norm": 1.2032462137767652e-08,
      "learning_rate": 0.14718451293098594,
      "loss": 0.0,
      "num_input_tokens_seen": 5666656,
      "step": 20240
    },
    {
      "epoch": 224.94444444444446,
      "grad_norm": 5.483701048802914e-09,
      "learning_rate": 0.14712561866462676,
      "loss": 0.0,
      "num_input_tokens_seen": 5668064,
      "step": 20245
    },
    {
      "epoch": 225.0,
      "grad_norm": 2.287783651411246e-08,
      "learning_rate": 0.1470667248415333,
      "loss": 0.0,
      "num_input_tokens_seen": 5669456,
      "step": 20250
    },
    {
      "epoch": 225.05555555555554,
      "grad_norm": 7.211075736535122e-09,
      "learning_rate": 0.1470078314707878,
      "loss": 0.0,
      "num_input_tokens_seen": 5670800,
      "step": 20255
    },
    {
      "epoch": 225.11111111111111,
      "grad_norm": 1.0337806166660357e-08,
      "learning_rate": 0.14694893856147223,
      "loss": 0.0,
      "num_input_tokens_seen": 5672160,
      "step": 20260
    },
    {
      "epoch": 225.16666666666666,
      "grad_norm": 7.787351208321525e-09,
      "learning_rate": 0.14689004612266868,
      "loss": 0.0,
      "num_input_tokens_seen": 5673568,
      "step": 20265
    },
    {
      "epoch": 225.22222222222223,
      "grad_norm": 2.1358170343432903e-08,
      "learning_rate": 0.14683115416345913,
      "loss": 0.0,
      "num_input_tokens_seen": 5674960,
      "step": 20270
    },
    {
      "epoch": 225.27777777777777,
      "grad_norm": 7.970430537795892e-09,
      "learning_rate": 0.1467722626929254,
      "loss": 0.0,
      "num_input_tokens_seen": 5676352,
      "step": 20275
    },
    {
      "epoch": 225.33333333333334,
      "grad_norm": 1.3424458877864254e-08,
      "learning_rate": 0.14671337172014937,
      "loss": 0.0,
      "num_input_tokens_seen": 5677776,
      "step": 20280
    },
    {
      "epoch": 225.38888888888889,
      "grad_norm": 1.3500711659730769e-08,
      "learning_rate": 0.14665448125421265,
      "loss": 0.0,
      "num_input_tokens_seen": 5679216,
      "step": 20285
    },
    {
      "epoch": 225.44444444444446,
      "grad_norm": 1.0999879229700582e-08,
      "learning_rate": 0.146595591304197,
      "loss": 0.0,
      "num_input_tokens_seen": 5680640,
      "step": 20290
    },
    {
      "epoch": 225.5,
      "grad_norm": 1.256284498651894e-08,
      "learning_rate": 0.14653670187918397,
      "loss": 0.0,
      "num_input_tokens_seen": 5682048,
      "step": 20295
    },
    {
      "epoch": 225.55555555555554,
      "grad_norm": 1.4122341518429948e-08,
      "learning_rate": 0.14647781298825502,
      "loss": 0.0,
      "num_input_tokens_seen": 5683440,
      "step": 20300
    },
    {
      "epoch": 225.61111111111111,
      "grad_norm": 1.5647302120669337e-08,
      "learning_rate": 0.14641892464049153,
      "loss": 0.0,
      "num_input_tokens_seen": 5684816,
      "step": 20305
    },
    {
      "epoch": 225.66666666666666,
      "grad_norm": 1.3105871943253078e-08,
      "learning_rate": 0.14636003684497495,
      "loss": 0.0,
      "num_input_tokens_seen": 5686208,
      "step": 20310
    },
    {
      "epoch": 225.72222222222223,
      "grad_norm": 2.0255239263633484e-08,
      "learning_rate": 0.14630114961078636,
      "loss": 0.0,
      "num_input_tokens_seen": 5687600,
      "step": 20315
    },
    {
      "epoch": 225.77777777777777,
      "grad_norm": 8.993407796253905e-09,
      "learning_rate": 0.14624226294700704,
      "loss": 0.0,
      "num_input_tokens_seen": 5689008,
      "step": 20320
    },
    {
      "epoch": 225.83333333333334,
      "grad_norm": 7.849627614575638e-09,
      "learning_rate": 0.14618337686271793,
      "loss": 0.0,
      "num_input_tokens_seen": 5690416,
      "step": 20325
    },
    {
      "epoch": 225.88888888888889,
      "grad_norm": 1.2018003481273354e-08,
      "learning_rate": 0.1461244913670001,
      "loss": 0.0,
      "num_input_tokens_seen": 5691792,
      "step": 20330
    },
    {
      "epoch": 225.94444444444446,
      "grad_norm": 8.251947569704043e-09,
      "learning_rate": 0.1460656064689344,
      "loss": 0.0,
      "num_input_tokens_seen": 5693200,
      "step": 20335
    },
    {
      "epoch": 226.0,
      "grad_norm": 1.0787084114838308e-08,
      "learning_rate": 0.14600672217760163,
      "loss": 0.0,
      "num_input_tokens_seen": 5694624,
      "step": 20340
    },
    {
      "epoch": 226.05555555555554,
      "grad_norm": 6.063383573007286e-09,
      "learning_rate": 0.14594783850208248,
      "loss": 0.0,
      "num_input_tokens_seen": 5695984,
      "step": 20345
    },
    {
      "epoch": 226.11111111111111,
      "grad_norm": 2.495679929381822e-08,
      "learning_rate": 0.14588895545145758,
      "loss": 0.0,
      "num_input_tokens_seen": 5697344,
      "step": 20350
    },
    {
      "epoch": 226.16666666666666,
      "grad_norm": 2.0161945002428183e-08,
      "learning_rate": 0.14583007303480738,
      "loss": 0.0,
      "num_input_tokens_seen": 5698704,
      "step": 20355
    },
    {
      "epoch": 226.22222222222223,
      "grad_norm": 8.104771964667634e-09,
      "learning_rate": 0.14577119126121235,
      "loss": 0.0,
      "num_input_tokens_seen": 5700096,
      "step": 20360
    },
    {
      "epoch": 226.27777777777777,
      "grad_norm": 1.0833982599933734e-08,
      "learning_rate": 0.14571231013975272,
      "loss": 0.0,
      "num_input_tokens_seen": 5701504,
      "step": 20365
    },
    {
      "epoch": 226.33333333333334,
      "grad_norm": 1.3961624745206791e-08,
      "learning_rate": 0.1456534296795088,
      "loss": 0.0,
      "num_input_tokens_seen": 5702864,
      "step": 20370
    },
    {
      "epoch": 226.38888888888889,
      "grad_norm": 1.1048938652891138e-08,
      "learning_rate": 0.14559454988956066,
      "loss": 0.0,
      "num_input_tokens_seen": 5704304,
      "step": 20375
    },
    {
      "epoch": 226.44444444444446,
      "grad_norm": 2.5236182921162253e-08,
      "learning_rate": 0.1455356707789882,
      "loss": 0.0,
      "num_input_tokens_seen": 5705760,
      "step": 20380
    },
    {
      "epoch": 226.5,
      "grad_norm": 1.1993145143662787e-08,
      "learning_rate": 0.14547679235687147,
      "loss": 0.0,
      "num_input_tokens_seen": 5707168,
      "step": 20385
    },
    {
      "epoch": 226.55555555555554,
      "grad_norm": 1.2086784018094932e-08,
      "learning_rate": 0.14541791463229023,
      "loss": 0.0,
      "num_input_tokens_seen": 5708528,
      "step": 20390
    },
    {
      "epoch": 226.61111111111111,
      "grad_norm": 6.415906916856784e-09,
      "learning_rate": 0.14535903761432406,
      "loss": 0.0,
      "num_input_tokens_seen": 5709920,
      "step": 20395
    },
    {
      "epoch": 226.66666666666666,
      "grad_norm": 8.578255439317672e-09,
      "learning_rate": 0.1453001613120527,
      "loss": 0.0,
      "num_input_tokens_seen": 5711344,
      "step": 20400
    },
    {
      "epoch": 226.66666666666666,
      "eval_loss": 1.6347118616104126,
      "eval_runtime": 1.1979,
      "eval_samples_per_second": 33.392,
      "eval_steps_per_second": 16.696,
      "num_input_tokens_seen": 5711344,
      "step": 20400
    },
    {
      "epoch": 226.72222222222223,
      "grad_norm": 1.4589051744451353e-08,
      "learning_rate": 0.14524128573455547,
      "loss": 0.0,
      "num_input_tokens_seen": 5712688,
      "step": 20405
    },
    {
      "epoch": 226.77777777777777,
      "grad_norm": 1.492688639359585e-08,
      "learning_rate": 0.14518241089091177,
      "loss": 0.0,
      "num_input_tokens_seen": 5714128,
      "step": 20410
    },
    {
      "epoch": 226.83333333333334,
      "grad_norm": 1.5646621775999847e-08,
      "learning_rate": 0.1451235367902009,
      "loss": 0.0,
      "num_input_tokens_seen": 5715520,
      "step": 20415
    },
    {
      "epoch": 226.88888888888889,
      "grad_norm": 8.50294146204078e-09,
      "learning_rate": 0.1450646634415019,
      "loss": 0.0,
      "num_input_tokens_seen": 5716992,
      "step": 20420
    },
    {
      "epoch": 226.94444444444446,
      "grad_norm": 1.4142104376446696e-08,
      "learning_rate": 0.1450057908538938,
      "loss": 0.0,
      "num_input_tokens_seen": 5718416,
      "step": 20425
    },
    {
      "epoch": 227.0,
      "grad_norm": 1.29671331450254e-08,
      "learning_rate": 0.14494691903645557,
      "loss": 0.0,
      "num_input_tokens_seen": 5719840,
      "step": 20430
    },
    {
      "epoch": 227.05555555555554,
      "grad_norm": 5.820478676810126e-08,
      "learning_rate": 0.14488804799826588,
      "loss": 0.0,
      "num_input_tokens_seen": 5721232,
      "step": 20435
    },
    {
      "epoch": 227.11111111111111,
      "grad_norm": 1.620000134039401e-08,
      "learning_rate": 0.14482917774840348,
      "loss": 0.0,
      "num_input_tokens_seen": 5722688,
      "step": 20440
    },
    {
      "epoch": 227.16666666666666,
      "grad_norm": 9.902767494907039e-09,
      "learning_rate": 0.14477030829594684,
      "loss": 0.0,
      "num_input_tokens_seen": 5724080,
      "step": 20445
    },
    {
      "epoch": 227.22222222222223,
      "grad_norm": 2.0628363017749507e-08,
      "learning_rate": 0.14471143964997432,
      "loss": 0.0,
      "num_input_tokens_seen": 5725504,
      "step": 20450
    },
    {
      "epoch": 227.27777777777777,
      "grad_norm": 6.737943536450075e-09,
      "learning_rate": 0.14465257181956434,
      "loss": 0.0,
      "num_input_tokens_seen": 5726896,
      "step": 20455
    },
    {
      "epoch": 227.33333333333334,
      "grad_norm": 1.1180192771576003e-08,
      "learning_rate": 0.1445937048137949,
      "loss": 0.0,
      "num_input_tokens_seen": 5728240,
      "step": 20460
    },
    {
      "epoch": 227.38888888888889,
      "grad_norm": 3.1666608890645875e-08,
      "learning_rate": 0.14453483864174416,
      "loss": 0.0,
      "num_input_tokens_seen": 5729632,
      "step": 20465
    },
    {
      "epoch": 227.44444444444446,
      "grad_norm": 2.9953962865647554e-08,
      "learning_rate": 0.14447597331249,
      "loss": 0.0,
      "num_input_tokens_seen": 5731040,
      "step": 20470
    },
    {
      "epoch": 227.5,
      "grad_norm": 1.3080504679408023e-08,
      "learning_rate": 0.1444171088351102,
      "loss": 0.0,
      "num_input_tokens_seen": 5732464,
      "step": 20475
    },
    {
      "epoch": 227.55555555555554,
      "grad_norm": 9.289066404960522e-09,
      "learning_rate": 0.14435824521868235,
      "loss": 0.0,
      "num_input_tokens_seen": 5733824,
      "step": 20480
    },
    {
      "epoch": 227.61111111111111,
      "grad_norm": 1.2409791416700955e-08,
      "learning_rate": 0.14429938247228397,
      "loss": 0.0,
      "num_input_tokens_seen": 5735232,
      "step": 20485
    },
    {
      "epoch": 227.66666666666666,
      "grad_norm": 6.099782456914227e-09,
      "learning_rate": 0.14424052060499243,
      "loss": 0.0,
      "num_input_tokens_seen": 5736608,
      "step": 20490
    },
    {
      "epoch": 227.72222222222223,
      "grad_norm": 1.2627938694720342e-08,
      "learning_rate": 0.14418165962588506,
      "loss": 0.0,
      "num_input_tokens_seen": 5738032,
      "step": 20495
    },
    {
      "epoch": 227.77777777777777,
      "grad_norm": 1.161677598560118e-08,
      "learning_rate": 0.1441227995440388,
      "loss": 0.0,
      "num_input_tokens_seen": 5739424,
      "step": 20500
    },
    {
      "epoch": 227.83333333333334,
      "grad_norm": 6.217748094172748e-09,
      "learning_rate": 0.14406394036853082,
      "loss": 0.0,
      "num_input_tokens_seen": 5740800,
      "step": 20505
    },
    {
      "epoch": 227.88888888888889,
      "grad_norm": 2.4018573796524834e-08,
      "learning_rate": 0.14400508210843774,
      "loss": 0.0,
      "num_input_tokens_seen": 5742240,
      "step": 20510
    },
    {
      "epoch": 227.94444444444446,
      "grad_norm": 1.3877350824031964e-08,
      "learning_rate": 0.1439462247728364,
      "loss": 0.0,
      "num_input_tokens_seen": 5743616,
      "step": 20515
    },
    {
      "epoch": 228.0,
      "grad_norm": 1.3928501907400914e-08,
      "learning_rate": 0.14388736837080326,
      "loss": 0.0,
      "num_input_tokens_seen": 5745024,
      "step": 20520
    },
    {
      "epoch": 228.05555555555554,
      "grad_norm": 1.2478762911882768e-08,
      "learning_rate": 0.14382851291141469,
      "loss": 0.0,
      "num_input_tokens_seen": 5746448,
      "step": 20525
    },
    {
      "epoch": 228.11111111111111,
      "grad_norm": 6.879865566133958e-09,
      "learning_rate": 0.14376965840374697,
      "loss": 0.0,
      "num_input_tokens_seen": 5747872,
      "step": 20530
    },
    {
      "epoch": 228.16666666666666,
      "grad_norm": 1.3915114394080774e-08,
      "learning_rate": 0.14371080485687632,
      "loss": 0.0,
      "num_input_tokens_seen": 5749264,
      "step": 20535
    },
    {
      "epoch": 228.22222222222223,
      "grad_norm": 1.8038186055946426e-08,
      "learning_rate": 0.1436519522798785,
      "loss": 0.0,
      "num_input_tokens_seen": 5750704,
      "step": 20540
    },
    {
      "epoch": 228.27777777777777,
      "grad_norm": 1.1888026563156018e-08,
      "learning_rate": 0.14359310068182948,
      "loss": 0.0,
      "num_input_tokens_seen": 5752080,
      "step": 20545
    },
    {
      "epoch": 228.33333333333334,
      "grad_norm": 7.087728448595954e-08,
      "learning_rate": 0.14353425007180484,
      "loss": 0.0,
      "num_input_tokens_seen": 5753472,
      "step": 20550
    },
    {
      "epoch": 228.38888888888889,
      "grad_norm": 1.932698090456597e-08,
      "learning_rate": 0.14347540045888005,
      "loss": 0.0,
      "num_input_tokens_seen": 5754880,
      "step": 20555
    },
    {
      "epoch": 228.44444444444446,
      "grad_norm": 3.707222973048374e-08,
      "learning_rate": 0.14341655185213056,
      "loss": 0.0,
      "num_input_tokens_seen": 5756272,
      "step": 20560
    },
    {
      "epoch": 228.5,
      "grad_norm": 4.2259538091116156e-09,
      "learning_rate": 0.14335770426063144,
      "loss": 0.0,
      "num_input_tokens_seen": 5757632,
      "step": 20565
    },
    {
      "epoch": 228.55555555555554,
      "grad_norm": 6.687849829489778e-09,
      "learning_rate": 0.1432988576934578,
      "loss": 0.0,
      "num_input_tokens_seen": 5758976,
      "step": 20570
    },
    {
      "epoch": 228.61111111111111,
      "grad_norm": 9.898337260949575e-09,
      "learning_rate": 0.14324001215968457,
      "loss": 0.0,
      "num_input_tokens_seen": 5760384,
      "step": 20575
    },
    {
      "epoch": 228.66666666666666,
      "grad_norm": 3.65236707544625e-09,
      "learning_rate": 0.14318116766838637,
      "loss": 0.0,
      "num_input_tokens_seen": 5761792,
      "step": 20580
    },
    {
      "epoch": 228.72222222222223,
      "grad_norm": 1.4789316438168498e-08,
      "learning_rate": 0.14312232422863788,
      "loss": 0.0,
      "num_input_tokens_seen": 5763216,
      "step": 20585
    },
    {
      "epoch": 228.77777777777777,
      "grad_norm": 1.9505808523945234e-08,
      "learning_rate": 0.14306348184951334,
      "loss": 0.0,
      "num_input_tokens_seen": 5764576,
      "step": 20590
    },
    {
      "epoch": 228.83333333333334,
      "grad_norm": 1.4393177316662786e-08,
      "learning_rate": 0.1430046405400871,
      "loss": 0.0,
      "num_input_tokens_seen": 5765968,
      "step": 20595
    },
    {
      "epoch": 228.88888888888889,
      "grad_norm": 8.731555034557914e-09,
      "learning_rate": 0.14294580030943324,
      "loss": 0.0,
      "num_input_tokens_seen": 5767376,
      "step": 20600
    },
    {
      "epoch": 228.88888888888889,
      "eval_loss": 1.6275125741958618,
      "eval_runtime": 1.1935,
      "eval_samples_per_second": 33.516,
      "eval_steps_per_second": 16.758,
      "num_input_tokens_seen": 5767376,
      "step": 20600
    },
    {
      "epoch": 228.94444444444446,
      "grad_norm": 1.2420441564131579e-08,
      "learning_rate": 0.14288696116662553,
      "loss": 0.0,
      "num_input_tokens_seen": 5768832,
      "step": 20605
    },
    {
      "epoch": 229.0,
      "grad_norm": 9.211860607649669e-09,
      "learning_rate": 0.1428281231207378,
      "loss": 0.0,
      "num_input_tokens_seen": 5770256,
      "step": 20610
    },
    {
      "epoch": 229.05555555555554,
      "grad_norm": 5.510163436639459e-09,
      "learning_rate": 0.1427692861808437,
      "loss": 0.0,
      "num_input_tokens_seen": 5771632,
      "step": 20615
    },
    {
      "epoch": 229.11111111111111,
      "grad_norm": 5.560316207464666e-09,
      "learning_rate": 0.1427104503560165,
      "loss": 0.0,
      "num_input_tokens_seen": 5773024,
      "step": 20620
    },
    {
      "epoch": 229.16666666666666,
      "grad_norm": 2.7046331396718415e-08,
      "learning_rate": 0.14265161565532947,
      "loss": 0.0,
      "num_input_tokens_seen": 5774464,
      "step": 20625
    },
    {
      "epoch": 229.22222222222223,
      "grad_norm": 1.706299102011144e-08,
      "learning_rate": 0.14259278208785564,
      "loss": 0.0,
      "num_input_tokens_seen": 5775824,
      "step": 20630
    },
    {
      "epoch": 229.27777777777777,
      "grad_norm": 1.9696788200462834e-08,
      "learning_rate": 0.14253394966266789,
      "loss": 0.0,
      "num_input_tokens_seen": 5777232,
      "step": 20635
    },
    {
      "epoch": 229.33333333333334,
      "grad_norm": 7.216746755744907e-09,
      "learning_rate": 0.14247511838883894,
      "loss": 0.0,
      "num_input_tokens_seen": 5778592,
      "step": 20640
    },
    {
      "epoch": 229.38888888888889,
      "grad_norm": 4.740491110766243e-09,
      "learning_rate": 0.14241628827544126,
      "loss": 0.0,
      "num_input_tokens_seen": 5779984,
      "step": 20645
    },
    {
      "epoch": 229.44444444444446,
      "grad_norm": 1.2671375060335777e-08,
      "learning_rate": 0.14235745933154723,
      "loss": 0.0,
      "num_input_tokens_seen": 5781376,
      "step": 20650
    },
    {
      "epoch": 229.5,
      "grad_norm": 9.974422177094766e-09,
      "learning_rate": 0.14229863156622907,
      "loss": 0.0,
      "num_input_tokens_seen": 5782752,
      "step": 20655
    },
    {
      "epoch": 229.55555555555554,
      "grad_norm": 1.9411091400911573e-08,
      "learning_rate": 0.14223980498855868,
      "loss": 0.0,
      "num_input_tokens_seen": 5784176,
      "step": 20660
    },
    {
      "epoch": 229.61111111111111,
      "grad_norm": 2.752136651906767e-08,
      "learning_rate": 0.14218097960760792,
      "loss": 0.0,
      "num_input_tokens_seen": 5785552,
      "step": 20665
    },
    {
      "epoch": 229.66666666666666,
      "grad_norm": 1.5506413930665985e-08,
      "learning_rate": 0.1421221554324483,
      "loss": 0.0,
      "num_input_tokens_seen": 5786960,
      "step": 20670
    },
    {
      "epoch": 229.72222222222223,
      "grad_norm": 8.364513526259998e-09,
      "learning_rate": 0.1420633324721513,
      "loss": 0.0,
      "num_input_tokens_seen": 5788352,
      "step": 20675
    },
    {
      "epoch": 229.77777777777777,
      "grad_norm": 4.366252692733497e-09,
      "learning_rate": 0.14200451073578824,
      "loss": 0.0,
      "num_input_tokens_seen": 5789696,
      "step": 20680
    },
    {
      "epoch": 229.83333333333334,
      "grad_norm": 1.1003574051926535e-08,
      "learning_rate": 0.14194569023243003,
      "loss": 0.0,
      "num_input_tokens_seen": 5791072,
      "step": 20685
    },
    {
      "epoch": 229.88888888888889,
      "grad_norm": 1.4941690551495412e-08,
      "learning_rate": 0.14188687097114766,
      "loss": 0.0,
      "num_input_tokens_seen": 5792528,
      "step": 20690
    },
    {
      "epoch": 229.94444444444446,
      "grad_norm": 7.353174513724525e-09,
      "learning_rate": 0.14182805296101172,
      "loss": 0.0,
      "num_input_tokens_seen": 5793920,
      "step": 20695
    },
    {
      "epoch": 230.0,
      "grad_norm": 7.389926004464087e-09,
      "learning_rate": 0.14176923621109272,
      "loss": 0.0,
      "num_input_tokens_seen": 5795360,
      "step": 20700
    },
    {
      "epoch": 230.05555555555554,
      "grad_norm": 4.491067073786326e-09,
      "learning_rate": 0.14171042073046097,
      "loss": 0.0,
      "num_input_tokens_seen": 5796736,
      "step": 20705
    },
    {
      "epoch": 230.11111111111111,
      "grad_norm": 3.414645277644013e-08,
      "learning_rate": 0.14165160652818642,
      "loss": 0.0,
      "num_input_tokens_seen": 5798144,
      "step": 20710
    },
    {
      "epoch": 230.16666666666666,
      "grad_norm": 3.764736078437636e-09,
      "learning_rate": 0.14159279361333907,
      "loss": 0.0,
      "num_input_tokens_seen": 5799520,
      "step": 20715
    },
    {
      "epoch": 230.22222222222223,
      "grad_norm": 1.3285053945821801e-08,
      "learning_rate": 0.14153398199498868,
      "loss": 0.0,
      "num_input_tokens_seen": 5800896,
      "step": 20720
    },
    {
      "epoch": 230.27777777777777,
      "grad_norm": 1.3614140037532252e-08,
      "learning_rate": 0.14147517168220458,
      "loss": 0.0,
      "num_input_tokens_seen": 5802256,
      "step": 20725
    },
    {
      "epoch": 230.33333333333334,
      "grad_norm": 3.4682617666703663e-08,
      "learning_rate": 0.14141636268405616,
      "loss": 0.0,
      "num_input_tokens_seen": 5803616,
      "step": 20730
    },
    {
      "epoch": 230.38888888888889,
      "grad_norm": 9.166317482822706e-09,
      "learning_rate": 0.14135755500961253,
      "loss": 0.0,
      "num_input_tokens_seen": 5804960,
      "step": 20735
    },
    {
      "epoch": 230.44444444444446,
      "grad_norm": 9.232921094337598e-09,
      "learning_rate": 0.14129874866794245,
      "loss": 0.0,
      "num_input_tokens_seen": 5806368,
      "step": 20740
    },
    {
      "epoch": 230.5,
      "grad_norm": 3.5454313263016957e-08,
      "learning_rate": 0.14123994366811476,
      "loss": 0.0,
      "num_input_tokens_seen": 5807712,
      "step": 20745
    },
    {
      "epoch": 230.55555555555554,
      "grad_norm": 8.165260467762891e-09,
      "learning_rate": 0.14118114001919774,
      "loss": 0.0,
      "num_input_tokens_seen": 5809072,
      "step": 20750
    },
    {
      "epoch": 230.61111111111111,
      "grad_norm": 8.03203992205681e-09,
      "learning_rate": 0.14112233773025978,
      "loss": 0.0,
      "num_input_tokens_seen": 5810480,
      "step": 20755
    },
    {
      "epoch": 230.66666666666666,
      "grad_norm": 9.047753657398516e-09,
      "learning_rate": 0.14106353681036896,
      "loss": 0.0,
      "num_input_tokens_seen": 5811888,
      "step": 20760
    },
    {
      "epoch": 230.72222222222223,
      "grad_norm": 7.417760183869859e-09,
      "learning_rate": 0.14100473726859303,
      "loss": 0.0,
      "num_input_tokens_seen": 5813280,
      "step": 20765
    },
    {
      "epoch": 230.77777777777777,
      "grad_norm": 1.6302889704888912e-08,
      "learning_rate": 0.14094593911399964,
      "loss": 0.0,
      "num_input_tokens_seen": 5814704,
      "step": 20770
    },
    {
      "epoch": 230.83333333333334,
      "grad_norm": 1.5171067957453488e-08,
      "learning_rate": 0.14088714235565625,
      "loss": 0.0,
      "num_input_tokens_seen": 5816144,
      "step": 20775
    },
    {
      "epoch": 230.88888888888889,
      "grad_norm": 1.0689845453271118e-08,
      "learning_rate": 0.14082834700263,
      "loss": 0.0,
      "num_input_tokens_seen": 5817584,
      "step": 20780
    },
    {
      "epoch": 230.94444444444446,
      "grad_norm": 1.339674948752645e-08,
      "learning_rate": 0.14076955306398795,
      "loss": 0.0,
      "num_input_tokens_seen": 5819008,
      "step": 20785
    },
    {
      "epoch": 231.0,
      "grad_norm": 4.6877005388523685e-08,
      "learning_rate": 0.14071076054879675,
      "loss": 0.0,
      "num_input_tokens_seen": 5820432,
      "step": 20790
    },
    {
      "epoch": 231.05555555555554,
      "grad_norm": 1.1605482796994693e-08,
      "learning_rate": 0.14065196946612302,
      "loss": 0.0,
      "num_input_tokens_seen": 5821872,
      "step": 20795
    },
    {
      "epoch": 231.11111111111111,
      "grad_norm": 1.681016925658696e-08,
      "learning_rate": 0.1405931798250331,
      "loss": 0.0,
      "num_input_tokens_seen": 5823264,
      "step": 20800
    },
    {
      "epoch": 231.11111111111111,
      "eval_loss": 1.6913410425186157,
      "eval_runtime": 1.1823,
      "eval_samples_per_second": 33.831,
      "eval_steps_per_second": 16.916,
      "num_input_tokens_seen": 5823264,
      "step": 20800
    },
    {
      "epoch": 231.16666666666666,
      "grad_norm": 1.957968365218221e-08,
      "learning_rate": 0.14053439163459308,
      "loss": 0.0,
      "num_input_tokens_seen": 5824640,
      "step": 20805
    },
    {
      "epoch": 231.22222222222223,
      "grad_norm": 1.1294546631290814e-08,
      "learning_rate": 0.14047560490386876,
      "loss": 0.0,
      "num_input_tokens_seen": 5826000,
      "step": 20810
    },
    {
      "epoch": 231.27777777777777,
      "grad_norm": 1.3238520502056872e-08,
      "learning_rate": 0.14041681964192593,
      "loss": 0.0,
      "num_input_tokens_seen": 5827392,
      "step": 20815
    },
    {
      "epoch": 231.33333333333334,
      "grad_norm": 1.0655937465742227e-08,
      "learning_rate": 0.14035803585782988,
      "loss": 0.0,
      "num_input_tokens_seen": 5828768,
      "step": 20820
    },
    {
      "epoch": 231.38888888888889,
      "grad_norm": 1.6318994155994915e-08,
      "learning_rate": 0.14029925356064593,
      "loss": 0.0,
      "num_input_tokens_seen": 5830160,
      "step": 20825
    },
    {
      "epoch": 231.44444444444446,
      "grad_norm": 1.4624581545774618e-08,
      "learning_rate": 0.1402404727594389,
      "loss": 0.0,
      "num_input_tokens_seen": 5831600,
      "step": 20830
    },
    {
      "epoch": 231.5,
      "grad_norm": 1.1238914687794477e-08,
      "learning_rate": 0.1401816934632737,
      "loss": 0.0,
      "num_input_tokens_seen": 5832992,
      "step": 20835
    },
    {
      "epoch": 231.55555555555554,
      "grad_norm": 2.483266925423777e-08,
      "learning_rate": 0.1401229156812147,
      "loss": 0.0,
      "num_input_tokens_seen": 5834384,
      "step": 20840
    },
    {
      "epoch": 231.61111111111111,
      "grad_norm": 2.1558120621989474e-08,
      "learning_rate": 0.14006413942232626,
      "loss": 0.0,
      "num_input_tokens_seen": 5835776,
      "step": 20845
    },
    {
      "epoch": 231.66666666666666,
      "grad_norm": 1.6710213657233908e-08,
      "learning_rate": 0.14000536469567235,
      "loss": 0.0,
      "num_input_tokens_seen": 5837184,
      "step": 20850
    },
    {
      "epoch": 231.72222222222223,
      "grad_norm": 2.0916200327292245e-08,
      "learning_rate": 0.13994659151031685,
      "loss": 0.0,
      "num_input_tokens_seen": 5838592,
      "step": 20855
    },
    {
      "epoch": 231.77777777777777,
      "grad_norm": 9.896284680621648e-09,
      "learning_rate": 0.13988781987532323,
      "loss": 0.0,
      "num_input_tokens_seen": 5840000,
      "step": 20860
    },
    {
      "epoch": 231.83333333333334,
      "grad_norm": 1.4188134223047655e-08,
      "learning_rate": 0.1398290497997549,
      "loss": 0.0,
      "num_input_tokens_seen": 5841424,
      "step": 20865
    },
    {
      "epoch": 231.88888888888889,
      "grad_norm": 1.5677457554374996e-08,
      "learning_rate": 0.13977028129267488,
      "loss": 0.0,
      "num_input_tokens_seen": 5842816,
      "step": 20870
    },
    {
      "epoch": 231.94444444444446,
      "grad_norm": 8.13265632615412e-09,
      "learning_rate": 0.13971151436314605,
      "loss": 0.0,
      "num_input_tokens_seen": 5844224,
      "step": 20875
    },
    {
      "epoch": 232.0,
      "grad_norm": 9.04430752513008e-09,
      "learning_rate": 0.13965274902023103,
      "loss": 0.0,
      "num_input_tokens_seen": 5845632,
      "step": 20880
    },
    {
      "epoch": 232.05555555555554,
      "grad_norm": 2.8287283626582393e-09,
      "learning_rate": 0.13959398527299208,
      "loss": 0.0,
      "num_input_tokens_seen": 5847040,
      "step": 20885
    },
    {
      "epoch": 232.11111111111111,
      "grad_norm": 2.321424474871492e-08,
      "learning_rate": 0.13953522313049138,
      "loss": 0.0,
      "num_input_tokens_seen": 5848448,
      "step": 20890
    },
    {
      "epoch": 232.16666666666666,
      "grad_norm": 8.747663926556015e-09,
      "learning_rate": 0.13947646260179083,
      "loss": 0.0,
      "num_input_tokens_seen": 5849824,
      "step": 20895
    },
    {
      "epoch": 232.22222222222223,
      "grad_norm": 1.5848156564857163e-08,
      "learning_rate": 0.13941770369595194,
      "loss": 0.0,
      "num_input_tokens_seen": 5851200,
      "step": 20900
    },
    {
      "epoch": 232.27777777777777,
      "grad_norm": 1.2429252294055004e-08,
      "learning_rate": 0.1393589464220362,
      "loss": 0.0,
      "num_input_tokens_seen": 5852624,
      "step": 20905
    },
    {
      "epoch": 232.33333333333334,
      "grad_norm": 8.524109418317494e-09,
      "learning_rate": 0.13930019078910455,
      "loss": 0.0,
      "num_input_tokens_seen": 5854032,
      "step": 20910
    },
    {
      "epoch": 232.38888888888889,
      "grad_norm": 1.2468416521471681e-08,
      "learning_rate": 0.139241436806218,
      "loss": 0.0,
      "num_input_tokens_seen": 5855456,
      "step": 20915
    },
    {
      "epoch": 232.44444444444446,
      "grad_norm": 2.165619861216328e-08,
      "learning_rate": 0.13918268448243712,
      "loss": 0.0,
      "num_input_tokens_seen": 5856880,
      "step": 20920
    },
    {
      "epoch": 232.5,
      "grad_norm": 1.060149124043619e-08,
      "learning_rate": 0.13912393382682217,
      "loss": 0.0,
      "num_input_tokens_seen": 5858256,
      "step": 20925
    },
    {
      "epoch": 232.55555555555554,
      "grad_norm": 2.9787978306217155e-08,
      "learning_rate": 0.1390651848484333,
      "loss": 0.0,
      "num_input_tokens_seen": 5859680,
      "step": 20930
    },
    {
      "epoch": 232.61111111111111,
      "grad_norm": 9.069908379899516e-09,
      "learning_rate": 0.1390064375563304,
      "loss": 0.0,
      "num_input_tokens_seen": 5861040,
      "step": 20935
    },
    {
      "epoch": 232.66666666666666,
      "grad_norm": 8.872013346206131e-09,
      "learning_rate": 0.13894769195957293,
      "loss": 0.0,
      "num_input_tokens_seen": 5862496,
      "step": 20940
    },
    {
      "epoch": 232.72222222222223,
      "grad_norm": 1.0347466883331435e-08,
      "learning_rate": 0.13888894806722032,
      "loss": 0.0,
      "num_input_tokens_seen": 5863872,
      "step": 20945
    },
    {
      "epoch": 232.77777777777777,
      "grad_norm": 2.129586107457726e-08,
      "learning_rate": 0.1388302058883315,
      "loss": 0.0,
      "num_input_tokens_seen": 5865328,
      "step": 20950
    },
    {
      "epoch": 232.83333333333334,
      "grad_norm": 1.2926561154813498e-08,
      "learning_rate": 0.13877146543196528,
      "loss": 0.0,
      "num_input_tokens_seen": 5866720,
      "step": 20955
    },
    {
      "epoch": 232.88888888888889,
      "grad_norm": 1.0403826244953507e-08,
      "learning_rate": 0.13871272670718027,
      "loss": 0.0,
      "num_input_tokens_seen": 5868096,
      "step": 20960
    },
    {
      "epoch": 232.94444444444446,
      "grad_norm": 1.2263859261452126e-08,
      "learning_rate": 0.13865398972303455,
      "loss": 0.0,
      "num_input_tokens_seen": 5869488,
      "step": 20965
    },
    {
      "epoch": 233.0,
      "grad_norm": 2.347120897638888e-08,
      "learning_rate": 0.13859525448858623,
      "loss": 0.0,
      "num_input_tokens_seen": 5870896,
      "step": 20970
    },
    {
      "epoch": 233.05555555555554,
      "grad_norm": 5.780807388333642e-09,
      "learning_rate": 0.13853652101289304,
      "loss": 0.0,
      "num_input_tokens_seen": 5872272,
      "step": 20975
    },
    {
      "epoch": 233.11111111111111,
      "grad_norm": 8.828197728405485e-09,
      "learning_rate": 0.13847778930501234,
      "loss": 0.0,
      "num_input_tokens_seen": 5873632,
      "step": 20980
    },
    {
      "epoch": 233.16666666666666,
      "grad_norm": 1.2386486503146443e-08,
      "learning_rate": 0.1384190593740013,
      "loss": 0.0,
      "num_input_tokens_seen": 5874992,
      "step": 20985
    },
    {
      "epoch": 233.22222222222223,
      "grad_norm": 2.694895684385301e-08,
      "learning_rate": 0.13836033122891686,
      "loss": 0.0,
      "num_input_tokens_seen": 5876368,
      "step": 20990
    },
    {
      "epoch": 233.27777777777777,
      "grad_norm": 7.002150415047481e-09,
      "learning_rate": 0.1383016048788156,
      "loss": 0.0,
      "num_input_tokens_seen": 5877824,
      "step": 20995
    },
    {
      "epoch": 233.33333333333334,
      "grad_norm": 8.160481179686485e-09,
      "learning_rate": 0.13824288033275392,
      "loss": 0.0,
      "num_input_tokens_seen": 5879248,
      "step": 21000
    },
    {
      "epoch": 233.33333333333334,
      "eval_loss": 1.6944057941436768,
      "eval_runtime": 1.1863,
      "eval_samples_per_second": 33.718,
      "eval_steps_per_second": 16.859,
      "num_input_tokens_seen": 5879248,
      "step": 21000
    },
    {
      "epoch": 233.38888888888889,
      "grad_norm": 2.4102629225808414e-08,
      "learning_rate": 0.1381841575997878,
      "loss": 0.0,
      "num_input_tokens_seen": 5880688,
      "step": 21005
    },
    {
      "epoch": 233.44444444444446,
      "grad_norm": 1.1877550498695655e-08,
      "learning_rate": 0.13812543668897306,
      "loss": 0.0,
      "num_input_tokens_seen": 5882080,
      "step": 21010
    },
    {
      "epoch": 233.5,
      "grad_norm": 1.322348008869767e-08,
      "learning_rate": 0.13806671760936526,
      "loss": 0.0,
      "num_input_tokens_seen": 5883472,
      "step": 21015
    },
    {
      "epoch": 233.55555555555554,
      "grad_norm": 2.083348960013609e-08,
      "learning_rate": 0.13800800037001956,
      "loss": 0.0,
      "num_input_tokens_seen": 5884912,
      "step": 21020
    },
    {
      "epoch": 233.61111111111111,
      "grad_norm": 1.2081265765573335e-08,
      "learning_rate": 0.13794928497999087,
      "loss": 0.0,
      "num_input_tokens_seen": 5886288,
      "step": 21025
    },
    {
      "epoch": 233.66666666666666,
      "grad_norm": 1.0755154100650088e-08,
      "learning_rate": 0.1378905714483339,
      "loss": 0.0,
      "num_input_tokens_seen": 5887712,
      "step": 21030
    },
    {
      "epoch": 233.72222222222223,
      "grad_norm": 3.7772043270933864e-08,
      "learning_rate": 0.13783185978410295,
      "loss": 0.0,
      "num_input_tokens_seen": 5889088,
      "step": 21035
    },
    {
      "epoch": 233.77777777777777,
      "grad_norm": 1.0201302025336645e-08,
      "learning_rate": 0.13777314999635218,
      "loss": 0.0,
      "num_input_tokens_seen": 5890512,
      "step": 21040
    },
    {
      "epoch": 233.83333333333334,
      "grad_norm": 8.824740049817592e-09,
      "learning_rate": 0.1377144420941353,
      "loss": 0.0,
      "num_input_tokens_seen": 5891872,
      "step": 21045
    },
    {
      "epoch": 233.88888888888889,
      "grad_norm": 3.8815553438098505e-08,
      "learning_rate": 0.13765573608650586,
      "loss": 0.0,
      "num_input_tokens_seen": 5893264,
      "step": 21050
    },
    {
      "epoch": 233.94444444444446,
      "grad_norm": 1.3117608332890995e-08,
      "learning_rate": 0.13759703198251702,
      "loss": 0.0,
      "num_input_tokens_seen": 5894672,
      "step": 21055
    },
    {
      "epoch": 234.0,
      "grad_norm": 1.3225805339800445e-08,
      "learning_rate": 0.13753832979122174,
      "loss": 0.0,
      "num_input_tokens_seen": 5896096,
      "step": 21060
    },
    {
      "epoch": 234.05555555555554,
      "grad_norm": 1.703144469900053e-08,
      "learning_rate": 0.13747962952167264,
      "loss": 0.0,
      "num_input_tokens_seen": 5897440,
      "step": 21065
    },
    {
      "epoch": 234.11111111111111,
      "grad_norm": 1.4764101052833212e-08,
      "learning_rate": 0.13742093118292192,
      "loss": 0.0,
      "num_input_tokens_seen": 5898848,
      "step": 21070
    },
    {
      "epoch": 234.16666666666666,
      "grad_norm": 1.9961628794362696e-08,
      "learning_rate": 0.13736223478402174,
      "loss": 0.0,
      "num_input_tokens_seen": 5900256,
      "step": 21075
    },
    {
      "epoch": 234.22222222222223,
      "grad_norm": 1.5576439693631983e-08,
      "learning_rate": 0.1373035403340238,
      "loss": 0.0,
      "num_input_tokens_seen": 5901664,
      "step": 21080
    },
    {
      "epoch": 234.27777777777777,
      "grad_norm": 4.855900570532867e-09,
      "learning_rate": 0.13724484784197943,
      "loss": 0.0,
      "num_input_tokens_seen": 5903008,
      "step": 21085
    },
    {
      "epoch": 234.33333333333334,
      "grad_norm": 1.3379639618449346e-08,
      "learning_rate": 0.13718615731693987,
      "loss": 0.0,
      "num_input_tokens_seen": 5904432,
      "step": 21090
    },
    {
      "epoch": 234.38888888888889,
      "grad_norm": 1.465365873087876e-08,
      "learning_rate": 0.13712746876795587,
      "loss": 0.0,
      "num_input_tokens_seen": 5905840,
      "step": 21095
    },
    {
      "epoch": 234.44444444444446,
      "grad_norm": 9.024152980430244e-09,
      "learning_rate": 0.13706878220407792,
      "loss": 0.0,
      "num_input_tokens_seen": 5907264,
      "step": 21100
    },
    {
      "epoch": 234.5,
      "grad_norm": 6.273425157132806e-08,
      "learning_rate": 0.13701009763435631,
      "loss": 0.0,
      "num_input_tokens_seen": 5908640,
      "step": 21105
    },
    {
      "epoch": 234.55555555555554,
      "grad_norm": 3.073092003091915e-08,
      "learning_rate": 0.13695141506784084,
      "loss": 0.0,
      "num_input_tokens_seen": 5910032,
      "step": 21110
    },
    {
      "epoch": 234.61111111111111,
      "grad_norm": 7.59680052198064e-09,
      "learning_rate": 0.13689273451358114,
      "loss": 0.0,
      "num_input_tokens_seen": 5911376,
      "step": 21115
    },
    {
      "epoch": 234.66666666666666,
      "grad_norm": 7.711062011139802e-09,
      "learning_rate": 0.13683405598062653,
      "loss": 0.0,
      "num_input_tokens_seen": 5912800,
      "step": 21120
    },
    {
      "epoch": 234.72222222222223,
      "grad_norm": 1.3861995995512189e-08,
      "learning_rate": 0.1367753794780259,
      "loss": 0.0,
      "num_input_tokens_seen": 5914192,
      "step": 21125
    },
    {
      "epoch": 234.77777777777777,
      "grad_norm": 1.5672069864081095e-08,
      "learning_rate": 0.13671670501482802,
      "loss": 0.0,
      "num_input_tokens_seen": 5915600,
      "step": 21130
    },
    {
      "epoch": 234.83333333333334,
      "grad_norm": 1.8092293885274557e-08,
      "learning_rate": 0.1366580326000811,
      "loss": 0.0,
      "num_input_tokens_seen": 5916928,
      "step": 21135
    },
    {
      "epoch": 234.88888888888889,
      "grad_norm": 1.641408431396485e-08,
      "learning_rate": 0.1365993622428332,
      "loss": 0.0,
      "num_input_tokens_seen": 5918368,
      "step": 21140
    },
    {
      "epoch": 234.94444444444446,
      "grad_norm": 6.763456461555961e-09,
      "learning_rate": 0.13654069395213211,
      "loss": 0.0,
      "num_input_tokens_seen": 5919840,
      "step": 21145
    },
    {
      "epoch": 235.0,
      "grad_norm": 1.6143527403755797e-08,
      "learning_rate": 0.13648202773702509,
      "loss": 0.0,
      "num_input_tokens_seen": 5921216,
      "step": 21150
    },
    {
      "epoch": 235.05555555555554,
      "grad_norm": 5.8314411077731165e-09,
      "learning_rate": 0.13642336360655927,
      "loss": 0.0,
      "num_input_tokens_seen": 5922608,
      "step": 21155
    },
    {
      "epoch": 235.11111111111111,
      "grad_norm": 2.3889992206704846e-08,
      "learning_rate": 0.13636470156978145,
      "loss": 0.0,
      "num_input_tokens_seen": 5924000,
      "step": 21160
    },
    {
      "epoch": 235.16666666666666,
      "grad_norm": 1.8580568195147862e-08,
      "learning_rate": 0.13630604163573798,
      "loss": 0.0,
      "num_input_tokens_seen": 5925376,
      "step": 21165
    },
    {
      "epoch": 235.22222222222223,
      "grad_norm": 7.50924655790186e-09,
      "learning_rate": 0.13624738381347495,
      "loss": 0.0,
      "num_input_tokens_seen": 5926784,
      "step": 21170
    },
    {
      "epoch": 235.27777777777777,
      "grad_norm": 3.1448617932028355e-08,
      "learning_rate": 0.1361887281120382,
      "loss": 0.0,
      "num_input_tokens_seen": 5928240,
      "step": 21175
    },
    {
      "epoch": 235.33333333333334,
      "grad_norm": 1.4159283523440536e-08,
      "learning_rate": 0.13613007454047307,
      "loss": 0.0,
      "num_input_tokens_seen": 5929600,
      "step": 21180
    },
    {
      "epoch": 235.38888888888889,
      "grad_norm": 7.2352750457582715e-09,
      "learning_rate": 0.13607142310782486,
      "loss": 0.0,
      "num_input_tokens_seen": 5930992,
      "step": 21185
    },
    {
      "epoch": 235.44444444444446,
      "grad_norm": 9.001411171993823e-09,
      "learning_rate": 0.13601277382313814,
      "loss": 0.0,
      "num_input_tokens_seen": 5932368,
      "step": 21190
    },
    {
      "epoch": 235.5,
      "grad_norm": 8.350194491413276e-08,
      "learning_rate": 0.1359541266954575,
      "loss": 0.0,
      "num_input_tokens_seen": 5933744,
      "step": 21195
    },
    {
      "epoch": 235.55555555555554,
      "grad_norm": 3.17132098359707e-08,
      "learning_rate": 0.13589548173382707,
      "loss": 0.0,
      "num_input_tokens_seen": 5935168,
      "step": 21200
    },
    {
      "epoch": 235.55555555555554,
      "eval_loss": 1.6750284433364868,
      "eval_runtime": 1.1863,
      "eval_samples_per_second": 33.717,
      "eval_steps_per_second": 16.859,
      "num_input_tokens_seen": 5935168,
      "step": 21200
    },
    {
      "epoch": 235.61111111111111,
      "grad_norm": 3.1808955469614375e-08,
      "learning_rate": 0.1358368389472906,
      "loss": 0.0,
      "num_input_tokens_seen": 5936544,
      "step": 21205
    },
    {
      "epoch": 235.66666666666666,
      "grad_norm": 2.5710519935273624e-08,
      "learning_rate": 0.13577819834489155,
      "loss": 0.0,
      "num_input_tokens_seen": 5937904,
      "step": 21210
    },
    {
      "epoch": 235.72222222222223,
      "grad_norm": 1.049909759132106e-08,
      "learning_rate": 0.135719559935673,
      "loss": 0.0,
      "num_input_tokens_seen": 5939296,
      "step": 21215
    },
    {
      "epoch": 235.77777777777777,
      "grad_norm": 6.3521214954676e-09,
      "learning_rate": 0.13566092372867775,
      "loss": 0.0,
      "num_input_tokens_seen": 5940704,
      "step": 21220
    },
    {
      "epoch": 235.83333333333334,
      "grad_norm": 2.7610973063474376e-08,
      "learning_rate": 0.13560228973294833,
      "loss": 0.0,
      "num_input_tokens_seen": 5942080,
      "step": 21225
    },
    {
      "epoch": 235.88888888888889,
      "grad_norm": 4.847241275030001e-09,
      "learning_rate": 0.13554365795752668,
      "loss": 0.0,
      "num_input_tokens_seen": 5943536,
      "step": 21230
    },
    {
      "epoch": 235.94444444444446,
      "grad_norm": 9.506600839870316e-09,
      "learning_rate": 0.1354850284114547,
      "loss": 0.0,
      "num_input_tokens_seen": 5944912,
      "step": 21235
    },
    {
      "epoch": 236.0,
      "grad_norm": 8.316652255757617e-09,
      "learning_rate": 0.13542640110377374,
      "loss": 0.0,
      "num_input_tokens_seen": 5946352,
      "step": 21240
    },
    {
      "epoch": 236.05555555555554,
      "grad_norm": 1.270350136195475e-08,
      "learning_rate": 0.13536777604352487,
      "loss": 0.0,
      "num_input_tokens_seen": 5947744,
      "step": 21245
    },
    {
      "epoch": 236.11111111111111,
      "grad_norm": 7.902825949201997e-09,
      "learning_rate": 0.13530915323974887,
      "loss": 0.0,
      "num_input_tokens_seen": 5949136,
      "step": 21250
    },
    {
      "epoch": 236.16666666666666,
      "grad_norm": 1.709791064286037e-08,
      "learning_rate": 0.13525053270148596,
      "loss": 0.0,
      "num_input_tokens_seen": 5950544,
      "step": 21255
    },
    {
      "epoch": 236.22222222222223,
      "grad_norm": 4.585614021834772e-08,
      "learning_rate": 0.13519191443777628,
      "loss": 0.0,
      "num_input_tokens_seen": 5951968,
      "step": 21260
    },
    {
      "epoch": 236.27777777777777,
      "grad_norm": 6.732352453298063e-09,
      "learning_rate": 0.13513329845765953,
      "loss": 0.0,
      "num_input_tokens_seen": 5953376,
      "step": 21265
    },
    {
      "epoch": 236.33333333333334,
      "grad_norm": 1.889678280520002e-08,
      "learning_rate": 0.13507468477017495,
      "loss": 0.0,
      "num_input_tokens_seen": 5954816,
      "step": 21270
    },
    {
      "epoch": 236.38888888888889,
      "grad_norm": 2.7909878852483416e-08,
      "learning_rate": 0.13501607338436153,
      "loss": 0.0,
      "num_input_tokens_seen": 5956208,
      "step": 21275
    },
    {
      "epoch": 236.44444444444446,
      "grad_norm": 1.0834567021333896e-08,
      "learning_rate": 0.13495746430925798,
      "loss": 0.0,
      "num_input_tokens_seen": 5957616,
      "step": 21280
    },
    {
      "epoch": 236.5,
      "grad_norm": 2.9654811939394676e-08,
      "learning_rate": 0.13489885755390238,
      "loss": 0.0,
      "num_input_tokens_seen": 5959024,
      "step": 21285
    },
    {
      "epoch": 236.55555555555554,
      "grad_norm": 4.125389452269701e-08,
      "learning_rate": 0.13484025312733275,
      "loss": 0.0,
      "num_input_tokens_seen": 5960400,
      "step": 21290
    },
    {
      "epoch": 236.61111111111111,
      "grad_norm": 2.5288784399890574e-08,
      "learning_rate": 0.13478165103858658,
      "loss": 0.0,
      "num_input_tokens_seen": 5961840,
      "step": 21295
    },
    {
      "epoch": 236.66666666666666,
      "grad_norm": 1.1522716114598097e-08,
      "learning_rate": 0.13472305129670106,
      "loss": 0.0,
      "num_input_tokens_seen": 5963232,
      "step": 21300
    },
    {
      "epoch": 236.72222222222223,
      "grad_norm": 9.02828212190343e-09,
      "learning_rate": 0.13466445391071305,
      "loss": 0.0,
      "num_input_tokens_seen": 5964656,
      "step": 21305
    },
    {
      "epoch": 236.77777777777777,
      "grad_norm": 9.483584584302207e-09,
      "learning_rate": 0.13460585888965895,
      "loss": 0.0,
      "num_input_tokens_seen": 5966080,
      "step": 21310
    },
    {
      "epoch": 236.83333333333334,
      "grad_norm": 1.968933638352155e-08,
      "learning_rate": 0.13454726624257482,
      "loss": 0.0,
      "num_input_tokens_seen": 5967504,
      "step": 21315
    },
    {
      "epoch": 236.88888888888889,
      "grad_norm": 1.0037353170844199e-08,
      "learning_rate": 0.1344886759784965,
      "loss": 0.0,
      "num_input_tokens_seen": 5968896,
      "step": 21320
    },
    {
      "epoch": 236.94444444444446,
      "grad_norm": 1.7636317295455228e-08,
      "learning_rate": 0.13443008810645923,
      "loss": 0.0,
      "num_input_tokens_seen": 5970272,
      "step": 21325
    },
    {
      "epoch": 237.0,
      "grad_norm": 7.945979874079967e-09,
      "learning_rate": 0.13437150263549807,
      "loss": 0.0,
      "num_input_tokens_seen": 5971664,
      "step": 21330
    },
    {
      "epoch": 237.05555555555554,
      "grad_norm": 1.029988450085284e-08,
      "learning_rate": 0.13431291957464755,
      "loss": 0.0,
      "num_input_tokens_seen": 5972992,
      "step": 21335
    },
    {
      "epoch": 237.11111111111111,
      "grad_norm": 1.8730938577959932e-08,
      "learning_rate": 0.13425433893294197,
      "loss": 0.0,
      "num_input_tokens_seen": 5974368,
      "step": 21340
    },
    {
      "epoch": 237.16666666666666,
      "grad_norm": 1.4047213170442774e-08,
      "learning_rate": 0.13419576071941525,
      "loss": 0.0,
      "num_input_tokens_seen": 5975728,
      "step": 21345
    },
    {
      "epoch": 237.22222222222223,
      "grad_norm": 2.7379025269169688e-08,
      "learning_rate": 0.1341371849431008,
      "loss": 0.0,
      "num_input_tokens_seen": 5977152,
      "step": 21350
    },
    {
      "epoch": 237.27777777777777,
      "grad_norm": 1.1263478150169703e-08,
      "learning_rate": 0.13407861161303178,
      "loss": 0.0,
      "num_input_tokens_seen": 5978608,
      "step": 21355
    },
    {
      "epoch": 237.33333333333334,
      "grad_norm": 1.9129407391460518e-08,
      "learning_rate": 0.13402004073824098,
      "loss": 0.0,
      "num_input_tokens_seen": 5979968,
      "step": 21360
    },
    {
      "epoch": 237.38888888888889,
      "grad_norm": 8.864270206743186e-09,
      "learning_rate": 0.13396147232776062,
      "loss": 0.0,
      "num_input_tokens_seen": 5981376,
      "step": 21365
    },
    {
      "epoch": 237.44444444444446,
      "grad_norm": 1.651049075235278e-08,
      "learning_rate": 0.13390290639062288,
      "loss": 0.0,
      "num_input_tokens_seen": 5982816,
      "step": 21370
    },
    {
      "epoch": 237.5,
      "grad_norm": 1.7410282993068904e-08,
      "learning_rate": 0.13384434293585917,
      "loss": 0.0,
      "num_input_tokens_seen": 5984208,
      "step": 21375
    },
    {
      "epoch": 237.55555555555554,
      "grad_norm": 2.0066337924617983e-08,
      "learning_rate": 0.13378578197250088,
      "loss": 0.0,
      "num_input_tokens_seen": 5985616,
      "step": 21380
    },
    {
      "epoch": 237.61111111111111,
      "grad_norm": 1.2565783968909727e-08,
      "learning_rate": 0.13372722350957872,
      "loss": 0.0,
      "num_input_tokens_seen": 5987024,
      "step": 21385
    },
    {
      "epoch": 237.66666666666666,
      "grad_norm": 1.0595763377807543e-08,
      "learning_rate": 0.13366866755612322,
      "loss": 0.0,
      "num_input_tokens_seen": 5988448,
      "step": 21390
    },
    {
      "epoch": 237.72222222222223,
      "grad_norm": 1.6308071337789443e-08,
      "learning_rate": 0.13361011412116436,
      "loss": 0.0,
      "num_input_tokens_seen": 5989856,
      "step": 21395
    },
    {
      "epoch": 237.77777777777777,
      "grad_norm": 4.6340854709114865e-08,
      "learning_rate": 0.13355156321373196,
      "loss": 0.0,
      "num_input_tokens_seen": 5991232,
      "step": 21400
    },
    {
      "epoch": 237.77777777777777,
      "eval_loss": 1.6816015243530273,
      "eval_runtime": 1.1865,
      "eval_samples_per_second": 33.714,
      "eval_steps_per_second": 16.857,
      "num_input_tokens_seen": 5991232,
      "step": 21400
    },
    {
      "epoch": 237.83333333333334,
      "grad_norm": 1.0687550400234613e-08,
      "learning_rate": 0.13349301484285514,
      "loss": 0.0,
      "num_input_tokens_seen": 5992656,
      "step": 21405
    },
    {
      "epoch": 237.88888888888889,
      "grad_norm": 1.8463062190221535e-08,
      "learning_rate": 0.13343446901756295,
      "loss": 0.0,
      "num_input_tokens_seen": 5994032,
      "step": 21410
    },
    {
      "epoch": 237.94444444444446,
      "grad_norm": 1.6265319757735597e-08,
      "learning_rate": 0.13337592574688376,
      "loss": 0.0,
      "num_input_tokens_seen": 5995456,
      "step": 21415
    },
    {
      "epoch": 238.0,
      "grad_norm": 2.6554014098678635e-08,
      "learning_rate": 0.13331738503984572,
      "loss": 0.0,
      "num_input_tokens_seen": 5996896,
      "step": 21420
    },
    {
      "epoch": 238.05555555555554,
      "grad_norm": 2.2748560368768267e-08,
      "learning_rate": 0.1332588469054766,
      "loss": 0.0,
      "num_input_tokens_seen": 5998288,
      "step": 21425
    },
    {
      "epoch": 238.11111111111111,
      "grad_norm": 1.439636765354635e-08,
      "learning_rate": 0.1332003113528036,
      "loss": 0.0,
      "num_input_tokens_seen": 5999712,
      "step": 21430
    },
    {
      "epoch": 238.16666666666666,
      "grad_norm": 1.4706452056145736e-08,
      "learning_rate": 0.13314177839085373,
      "loss": 0.0,
      "num_input_tokens_seen": 6001136,
      "step": 21435
    },
    {
      "epoch": 238.22222222222223,
      "grad_norm": 2.5505073608655948e-08,
      "learning_rate": 0.13308324802865354,
      "loss": 0.0,
      "num_input_tokens_seen": 6002512,
      "step": 21440
    },
    {
      "epoch": 238.27777777777777,
      "grad_norm": 1.442758534864197e-08,
      "learning_rate": 0.13302472027522905,
      "loss": 0.0,
      "num_input_tokens_seen": 6003888,
      "step": 21445
    },
    {
      "epoch": 238.33333333333334,
      "grad_norm": 1.1501089858256819e-08,
      "learning_rate": 0.13296619513960606,
      "loss": 0.0,
      "num_input_tokens_seen": 6005280,
      "step": 21450
    },
    {
      "epoch": 238.38888888888889,
      "grad_norm": 2.662911668949164e-08,
      "learning_rate": 0.1329076726308098,
      "loss": 0.0,
      "num_input_tokens_seen": 6006688,
      "step": 21455
    },
    {
      "epoch": 238.44444444444446,
      "grad_norm": 1.676213123857906e-08,
      "learning_rate": 0.13284915275786519,
      "loss": 0.0,
      "num_input_tokens_seen": 6008096,
      "step": 21460
    },
    {
      "epoch": 238.5,
      "grad_norm": 1.7922470618714215e-08,
      "learning_rate": 0.1327906355297968,
      "loss": 0.0,
      "num_input_tokens_seen": 6009568,
      "step": 21465
    },
    {
      "epoch": 238.55555555555554,
      "grad_norm": 1.4027622619039448e-08,
      "learning_rate": 0.13273212095562867,
      "loss": 0.0,
      "num_input_tokens_seen": 6010992,
      "step": 21470
    },
    {
      "epoch": 238.61111111111111,
      "grad_norm": 2.275758070879874e-08,
      "learning_rate": 0.13267360904438444,
      "loss": 0.0,
      "num_input_tokens_seen": 6012384,
      "step": 21475
    },
    {
      "epoch": 238.66666666666666,
      "grad_norm": 1.3508444141052678e-08,
      "learning_rate": 0.1326150998050875,
      "loss": 0.0,
      "num_input_tokens_seen": 6013776,
      "step": 21480
    },
    {
      "epoch": 238.72222222222223,
      "grad_norm": 1.87162303433297e-08,
      "learning_rate": 0.1325565932467606,
      "loss": 0.0,
      "num_input_tokens_seen": 6015200,
      "step": 21485
    },
    {
      "epoch": 238.77777777777777,
      "grad_norm": 1.4174148965651057e-08,
      "learning_rate": 0.13249808937842628,
      "loss": 0.0,
      "num_input_tokens_seen": 6016624,
      "step": 21490
    },
    {
      "epoch": 238.83333333333334,
      "grad_norm": 1.9830666886377912e-08,
      "learning_rate": 0.1324395882091065,
      "loss": 0.0,
      "num_input_tokens_seen": 6018032,
      "step": 21495
    },
    {
      "epoch": 238.88888888888889,
      "grad_norm": 4.6711292611689714e-08,
      "learning_rate": 0.13238108974782284,
      "loss": 0.0,
      "num_input_tokens_seen": 6019424,
      "step": 21500
    },
    {
      "epoch": 238.94444444444446,
      "grad_norm": 2.5275415538317247e-08,
      "learning_rate": 0.13232259400359664,
      "loss": 0.0,
      "num_input_tokens_seen": 6020832,
      "step": 21505
    },
    {
      "epoch": 239.0,
      "grad_norm": 3.4970351947549716e-08,
      "learning_rate": 0.13226410098544852,
      "loss": 0.0,
      "num_input_tokens_seen": 6022192,
      "step": 21510
    },
    {
      "epoch": 239.05555555555554,
      "grad_norm": 1.8874667162549486e-08,
      "learning_rate": 0.13220561070239892,
      "loss": 0.0,
      "num_input_tokens_seen": 6023616,
      "step": 21515
    },
    {
      "epoch": 239.11111111111111,
      "grad_norm": 1.9234144943425235e-08,
      "learning_rate": 0.13214712316346783,
      "loss": 0.0,
      "num_input_tokens_seen": 6025008,
      "step": 21520
    },
    {
      "epoch": 239.16666666666666,
      "grad_norm": 2.029632995004249e-08,
      "learning_rate": 0.13208863837767465,
      "loss": 0.0,
      "num_input_tokens_seen": 6026368,
      "step": 21525
    },
    {
      "epoch": 239.22222222222223,
      "grad_norm": 1.75890715325977e-08,
      "learning_rate": 0.13203015635403856,
      "loss": 0.0,
      "num_input_tokens_seen": 6027760,
      "step": 21530
    },
    {
      "epoch": 239.27777777777777,
      "grad_norm": 4.031907963053527e-08,
      "learning_rate": 0.13197167710157817,
      "loss": 0.0,
      "num_input_tokens_seen": 6029120,
      "step": 21535
    },
    {
      "epoch": 239.33333333333334,
      "grad_norm": 1.3001982601679174e-08,
      "learning_rate": 0.13191320062931167,
      "loss": 0.0,
      "num_input_tokens_seen": 6030560,
      "step": 21540
    },
    {
      "epoch": 239.38888888888889,
      "grad_norm": 1.1833958701856773e-08,
      "learning_rate": 0.13185472694625702,
      "loss": 0.0,
      "num_input_tokens_seen": 6031952,
      "step": 21545
    },
    {
      "epoch": 239.44444444444446,
      "grad_norm": 5.985195627999929e-08,
      "learning_rate": 0.13179625606143142,
      "loss": 0.0,
      "num_input_tokens_seen": 6033376,
      "step": 21550
    },
    {
      "epoch": 239.5,
      "grad_norm": 1.5572306111266698e-08,
      "learning_rate": 0.13173778798385188,
      "loss": 0.0,
      "num_input_tokens_seen": 6034768,
      "step": 21555
    },
    {
      "epoch": 239.55555555555554,
      "grad_norm": 1.4963960737190973e-08,
      "learning_rate": 0.13167932272253505,
      "loss": 0.0,
      "num_input_tokens_seen": 6036176,
      "step": 21560
    },
    {
      "epoch": 239.61111111111111,
      "grad_norm": 3.484146660071019e-08,
      "learning_rate": 0.1316208602864968,
      "loss": 0.0,
      "num_input_tokens_seen": 6037568,
      "step": 21565
    },
    {
      "epoch": 239.66666666666666,
      "grad_norm": 1.2107917335413276e-08,
      "learning_rate": 0.13156240068475292,
      "loss": 0.0,
      "num_input_tokens_seen": 6038992,
      "step": 21570
    },
    {
      "epoch": 239.72222222222223,
      "grad_norm": 1.0194781019379207e-08,
      "learning_rate": 0.1315039439263185,
      "loss": 0.0,
      "num_input_tokens_seen": 6040384,
      "step": 21575
    },
    {
      "epoch": 239.77777777777777,
      "grad_norm": 1.5492947369466492e-08,
      "learning_rate": 0.13144549002020833,
      "loss": 0.0,
      "num_input_tokens_seen": 6041792,
      "step": 21580
    },
    {
      "epoch": 239.83333333333334,
      "grad_norm": 2.117978326054981e-08,
      "learning_rate": 0.13138703897543688,
      "loss": 0.0,
      "num_input_tokens_seen": 6043168,
      "step": 21585
    },
    {
      "epoch": 239.88888888888889,
      "grad_norm": 2.3713768726452145e-08,
      "learning_rate": 0.1313285908010178,
      "loss": 0.0,
      "num_input_tokens_seen": 6044608,
      "step": 21590
    },
    {
      "epoch": 239.94444444444446,
      "grad_norm": 1.4382912638666312e-08,
      "learning_rate": 0.13127014550596475,
      "loss": 0.0,
      "num_input_tokens_seen": 6045984,
      "step": 21595
    },
    {
      "epoch": 240.0,
      "grad_norm": 7.1526251588238665e-09,
      "learning_rate": 0.1312117030992906,
      "loss": 0.0,
      "num_input_tokens_seen": 6047376,
      "step": 21600
    },
    {
      "epoch": 240.0,
      "eval_loss": 1.6530004739761353,
      "eval_runtime": 1.1789,
      "eval_samples_per_second": 33.931,
      "eval_steps_per_second": 16.966,
      "num_input_tokens_seen": 6047376,
      "step": 21600
    },
    {
      "epoch": 240.05555555555554,
      "grad_norm": 1.6778264111394492e-08,
      "learning_rate": 0.13115326359000795,
      "loss": 0.0,
      "num_input_tokens_seen": 6048816,
      "step": 21605
    },
    {
      "epoch": 240.11111111111111,
      "grad_norm": 4.708616074822203e-08,
      "learning_rate": 0.13109482698712896,
      "loss": 0.0,
      "num_input_tokens_seen": 6050192,
      "step": 21610
    },
    {
      "epoch": 240.16666666666666,
      "grad_norm": 2.4778488594279224e-08,
      "learning_rate": 0.1310363932996651,
      "loss": 0.0,
      "num_input_tokens_seen": 6051600,
      "step": 21615
    },
    {
      "epoch": 240.22222222222223,
      "grad_norm": 1.85969852850576e-08,
      "learning_rate": 0.13097796253662775,
      "loss": 0.0,
      "num_input_tokens_seen": 6052992,
      "step": 21620
    },
    {
      "epoch": 240.27777777777777,
      "grad_norm": 2.2950452205350302e-08,
      "learning_rate": 0.1309195347070277,
      "loss": 0.0,
      "num_input_tokens_seen": 6054384,
      "step": 21625
    },
    {
      "epoch": 240.33333333333334,
      "grad_norm": 2.0123264832250243e-08,
      "learning_rate": 0.13086110981987506,
      "loss": 0.0,
      "num_input_tokens_seen": 6055744,
      "step": 21630
    },
    {
      "epoch": 240.38888888888889,
      "grad_norm": 1.9958667607511416e-08,
      "learning_rate": 0.13080268788417987,
      "loss": 0.0,
      "num_input_tokens_seen": 6057184,
      "step": 21635
    },
    {
      "epoch": 240.44444444444446,
      "grad_norm": 3.892165878482956e-08,
      "learning_rate": 0.1307442689089515,
      "loss": 0.0,
      "num_input_tokens_seen": 6058576,
      "step": 21640
    },
    {
      "epoch": 240.5,
      "grad_norm": 1.5710241996202967e-08,
      "learning_rate": 0.13068585290319873,
      "loss": 0.0,
      "num_input_tokens_seen": 6059968,
      "step": 21645
    },
    {
      "epoch": 240.55555555555554,
      "grad_norm": 3.7178814693561435e-08,
      "learning_rate": 0.13062743987593026,
      "loss": 0.0,
      "num_input_tokens_seen": 6061424,
      "step": 21650
    },
    {
      "epoch": 240.61111111111111,
      "grad_norm": 1.351595990684018e-08,
      "learning_rate": 0.13056902983615395,
      "loss": 0.0,
      "num_input_tokens_seen": 6062800,
      "step": 21655
    },
    {
      "epoch": 240.66666666666666,
      "grad_norm": 5.169271588556512e-08,
      "learning_rate": 0.13051062279287742,
      "loss": 0.0,
      "num_input_tokens_seen": 6064208,
      "step": 21660
    },
    {
      "epoch": 240.72222222222223,
      "grad_norm": 2.6437561473358073e-08,
      "learning_rate": 0.13045221875510782,
      "loss": 0.0,
      "num_input_tokens_seen": 6065616,
      "step": 21665
    },
    {
      "epoch": 240.77777777777777,
      "grad_norm": 5.057762209048633e-08,
      "learning_rate": 0.13039381773185174,
      "loss": 0.0,
      "num_input_tokens_seen": 6067008,
      "step": 21670
    },
    {
      "epoch": 240.83333333333334,
      "grad_norm": 4.073546122640437e-08,
      "learning_rate": 0.1303354197321153,
      "loss": 0.0,
      "num_input_tokens_seen": 6068400,
      "step": 21675
    },
    {
      "epoch": 240.88888888888889,
      "grad_norm": 1.4328737307778283e-08,
      "learning_rate": 0.13027702476490433,
      "loss": 0.0,
      "num_input_tokens_seen": 6069760,
      "step": 21680
    },
    {
      "epoch": 240.94444444444446,
      "grad_norm": 1.949800498834975e-08,
      "learning_rate": 0.1302186328392239,
      "loss": 0.0,
      "num_input_tokens_seen": 6071120,
      "step": 21685
    },
    {
      "epoch": 241.0,
      "grad_norm": 6.050353107411865e-08,
      "learning_rate": 0.130160243964079,
      "loss": 0.0,
      "num_input_tokens_seen": 6072512,
      "step": 21690
    },
    {
      "epoch": 241.05555555555554,
      "grad_norm": 7.075263397382514e-08,
      "learning_rate": 0.13010185814847372,
      "loss": 0.0,
      "num_input_tokens_seen": 6073872,
      "step": 21695
    },
    {
      "epoch": 241.11111111111111,
      "grad_norm": 6.028464838436776e-08,
      "learning_rate": 0.13004347540141192,
      "loss": 0.0,
      "num_input_tokens_seen": 6075280,
      "step": 21700
    },
    {
      "epoch": 241.16666666666666,
      "grad_norm": 5.560232807511056e-08,
      "learning_rate": 0.12998509573189712,
      "loss": 0.0,
      "num_input_tokens_seen": 6076704,
      "step": 21705
    },
    {
      "epoch": 241.22222222222223,
      "grad_norm": 8.322817102168756e-09,
      "learning_rate": 0.12992671914893203,
      "loss": 0.0,
      "num_input_tokens_seen": 6078080,
      "step": 21710
    },
    {
      "epoch": 241.27777777777777,
      "grad_norm": 8.074241719668862e-09,
      "learning_rate": 0.12986834566151909,
      "loss": 0.0,
      "num_input_tokens_seen": 6079504,
      "step": 21715
    },
    {
      "epoch": 241.33333333333334,
      "grad_norm": 2.233727158795773e-08,
      "learning_rate": 0.12980997527866028,
      "loss": 0.0,
      "num_input_tokens_seen": 6080896,
      "step": 21720
    },
    {
      "epoch": 241.38888888888889,
      "grad_norm": 1.1117519349568283e-08,
      "learning_rate": 0.12975160800935692,
      "loss": 0.0,
      "num_input_tokens_seen": 6082304,
      "step": 21725
    },
    {
      "epoch": 241.44444444444446,
      "grad_norm": 4.3169528396447276e-08,
      "learning_rate": 0.12969324386261016,
      "loss": 0.0,
      "num_input_tokens_seen": 6083696,
      "step": 21730
    },
    {
      "epoch": 241.5,
      "grad_norm": 1.130477755850734e-08,
      "learning_rate": 0.12963488284742034,
      "loss": 0.0,
      "num_input_tokens_seen": 6085072,
      "step": 21735
    },
    {
      "epoch": 241.55555555555554,
      "grad_norm": 8.514033922324415e-09,
      "learning_rate": 0.12957652497278752,
      "loss": 0.0,
      "num_input_tokens_seen": 6086464,
      "step": 21740
    },
    {
      "epoch": 241.61111111111111,
      "grad_norm": 1.4345642895818855e-08,
      "learning_rate": 0.12951817024771117,
      "loss": 0.0,
      "num_input_tokens_seen": 6087808,
      "step": 21745
    },
    {
      "epoch": 241.66666666666666,
      "grad_norm": 1.2026310614032809e-08,
      "learning_rate": 0.12945981868119041,
      "loss": 0.0,
      "num_input_tokens_seen": 6089216,
      "step": 21750
    },
    {
      "epoch": 241.72222222222223,
      "grad_norm": 9.982216830906054e-09,
      "learning_rate": 0.12940147028222376,
      "loss": 0.0,
      "num_input_tokens_seen": 6090640,
      "step": 21755
    },
    {
      "epoch": 241.77777777777777,
      "grad_norm": 2.1708963515720825e-08,
      "learning_rate": 0.12934312505980916,
      "loss": 0.0,
      "num_input_tokens_seen": 6092016,
      "step": 21760
    },
    {
      "epoch": 241.83333333333334,
      "grad_norm": 1.7341900360179352e-08,
      "learning_rate": 0.1292847830229443,
      "loss": 0.0,
      "num_input_tokens_seen": 6093456,
      "step": 21765
    },
    {
      "epoch": 241.88888888888889,
      "grad_norm": 5.520810830716982e-08,
      "learning_rate": 0.12922644418062626,
      "loss": 0.0,
      "num_input_tokens_seen": 6094880,
      "step": 21770
    },
    {
      "epoch": 241.94444444444446,
      "grad_norm": 3.314982421898094e-08,
      "learning_rate": 0.1291681085418515,
      "loss": 0.0,
      "num_input_tokens_seen": 6096352,
      "step": 21775
    },
    {
      "epoch": 242.0,
      "grad_norm": 1.1513627384829306e-08,
      "learning_rate": 0.12910977611561628,
      "loss": 0.0,
      "num_input_tokens_seen": 6097712,
      "step": 21780
    },
    {
      "epoch": 242.05555555555554,
      "grad_norm": 1.996653686830996e-08,
      "learning_rate": 0.1290514469109161,
      "loss": 0.0,
      "num_input_tokens_seen": 6099072,
      "step": 21785
    },
    {
      "epoch": 242.11111111111111,
      "grad_norm": 2.0207908235647665e-08,
      "learning_rate": 0.128993120936746,
      "loss": 0.0,
      "num_input_tokens_seen": 6100496,
      "step": 21790
    },
    {
      "epoch": 242.16666666666666,
      "grad_norm": 3.220303668172164e-08,
      "learning_rate": 0.12893479820210071,
      "loss": 0.0,
      "num_input_tokens_seen": 6101888,
      "step": 21795
    },
    {
      "epoch": 242.22222222222223,
      "grad_norm": 1.0042766618312271e-08,
      "learning_rate": 0.1288764787159742,
      "loss": 0.0,
      "num_input_tokens_seen": 6103328,
      "step": 21800
    },
    {
      "epoch": 242.22222222222223,
      "eval_loss": 1.6663007736206055,
      "eval_runtime": 1.1843,
      "eval_samples_per_second": 33.776,
      "eval_steps_per_second": 16.888,
      "num_input_tokens_seen": 6103328,
      "step": 21800
    },
    {
      "epoch": 242.27777777777777,
      "grad_norm": 1.5209169035301784e-08,
      "learning_rate": 0.1288181624873601,
      "loss": 0.0,
      "num_input_tokens_seen": 6104704,
      "step": 21805
    },
    {
      "epoch": 242.33333333333334,
      "grad_norm": 1.709867980537183e-08,
      "learning_rate": 0.12875984952525163,
      "loss": 0.0,
      "num_input_tokens_seen": 6106144,
      "step": 21810
    },
    {
      "epoch": 242.38888888888889,
      "grad_norm": 1.7250902928367395e-08,
      "learning_rate": 0.12870153983864122,
      "loss": 0.0,
      "num_input_tokens_seen": 6107552,
      "step": 21815
    },
    {
      "epoch": 242.44444444444446,
      "grad_norm": 1.7231036153475543e-08,
      "learning_rate": 0.12864323343652104,
      "loss": 0.0,
      "num_input_tokens_seen": 6108912,
      "step": 21820
    },
    {
      "epoch": 242.5,
      "grad_norm": 3.7732622359953893e-08,
      "learning_rate": 0.12858493032788268,
      "loss": 0.0,
      "num_input_tokens_seen": 6110320,
      "step": 21825
    },
    {
      "epoch": 242.55555555555554,
      "grad_norm": 1.2601268473133587e-08,
      "learning_rate": 0.12852663052171714,
      "loss": 0.0,
      "num_input_tokens_seen": 6111760,
      "step": 21830
    },
    {
      "epoch": 242.61111111111111,
      "grad_norm": 1.7943110108831206e-08,
      "learning_rate": 0.12846833402701507,
      "loss": 0.0,
      "num_input_tokens_seen": 6113152,
      "step": 21835
    },
    {
      "epoch": 242.66666666666666,
      "grad_norm": 1.4095673961378452e-08,
      "learning_rate": 0.12841004085276642,
      "loss": 0.0,
      "num_input_tokens_seen": 6114512,
      "step": 21840
    },
    {
      "epoch": 242.72222222222223,
      "grad_norm": 1.8914349197984848e-08,
      "learning_rate": 0.12835175100796076,
      "loss": 0.0,
      "num_input_tokens_seen": 6115888,
      "step": 21845
    },
    {
      "epoch": 242.77777777777777,
      "grad_norm": 1.6269510183519742e-08,
      "learning_rate": 0.12829346450158724,
      "loss": 0.0,
      "num_input_tokens_seen": 6117296,
      "step": 21850
    },
    {
      "epoch": 242.83333333333334,
      "grad_norm": 2.0255319199691257e-08,
      "learning_rate": 0.12823518134263423,
      "loss": 0.0,
      "num_input_tokens_seen": 6118688,
      "step": 21855
    },
    {
      "epoch": 242.88888888888889,
      "grad_norm": 4.1302659070652226e-08,
      "learning_rate": 0.12817690154008973,
      "loss": 0.0,
      "num_input_tokens_seen": 6120096,
      "step": 21860
    },
    {
      "epoch": 242.94444444444446,
      "grad_norm": 1.200237775833557e-08,
      "learning_rate": 0.12811862510294134,
      "loss": 0.0,
      "num_input_tokens_seen": 6121504,
      "step": 21865
    },
    {
      "epoch": 243.0,
      "grad_norm": 1.2104016455793953e-08,
      "learning_rate": 0.12806035204017585,
      "loss": 0.0,
      "num_input_tokens_seen": 6122896,
      "step": 21870
    },
    {
      "epoch": 243.05555555555554,
      "grad_norm": 1.481789446700077e-08,
      "learning_rate": 0.12800208236077987,
      "loss": 0.0,
      "num_input_tokens_seen": 6124304,
      "step": 21875
    },
    {
      "epoch": 243.11111111111111,
      "grad_norm": 1.018173723110749e-08,
      "learning_rate": 0.12794381607373917,
      "loss": 0.0,
      "num_input_tokens_seen": 6125744,
      "step": 21880
    },
    {
      "epoch": 243.16666666666666,
      "grad_norm": 5.3631755037031326e-08,
      "learning_rate": 0.12788555318803924,
      "loss": 0.0,
      "num_input_tokens_seen": 6127168,
      "step": 21885
    },
    {
      "epoch": 243.22222222222223,
      "grad_norm": 9.397284728152044e-09,
      "learning_rate": 0.1278272937126649,
      "loss": 0.0,
      "num_input_tokens_seen": 6128544,
      "step": 21890
    },
    {
      "epoch": 243.27777777777777,
      "grad_norm": 7.054732265032726e-08,
      "learning_rate": 0.1277690376566005,
      "loss": 0.0,
      "num_input_tokens_seen": 6129936,
      "step": 21895
    },
    {
      "epoch": 243.33333333333334,
      "grad_norm": 2.2851315506500214e-08,
      "learning_rate": 0.12771078502882985,
      "loss": 0.0,
      "num_input_tokens_seen": 6131376,
      "step": 21900
    },
    {
      "epoch": 243.38888888888889,
      "grad_norm": 2.5162274042145327e-08,
      "learning_rate": 0.12765253583833633,
      "loss": 0.0,
      "num_input_tokens_seen": 6132784,
      "step": 21905
    },
    {
      "epoch": 243.44444444444446,
      "grad_norm": 1.4663974035045158e-08,
      "learning_rate": 0.12759429009410256,
      "loss": 0.0,
      "num_input_tokens_seen": 6134176,
      "step": 21910
    },
    {
      "epoch": 243.5,
      "grad_norm": 3.49737234728309e-08,
      "learning_rate": 0.12753604780511085,
      "loss": 0.0,
      "num_input_tokens_seen": 6135568,
      "step": 21915
    },
    {
      "epoch": 243.55555555555554,
      "grad_norm": 5.154288018616171e-08,
      "learning_rate": 0.12747780898034283,
      "loss": 0.0,
      "num_input_tokens_seen": 6136960,
      "step": 21920
    },
    {
      "epoch": 243.61111111111111,
      "grad_norm": 3.4995860431763504e-08,
      "learning_rate": 0.12741957362877973,
      "loss": 0.0,
      "num_input_tokens_seen": 6138336,
      "step": 21925
    },
    {
      "epoch": 243.66666666666666,
      "grad_norm": 3.03289766634407e-08,
      "learning_rate": 0.12736134175940214,
      "loss": 0.0,
      "num_input_tokens_seen": 6139744,
      "step": 21930
    },
    {
      "epoch": 243.72222222222223,
      "grad_norm": 3.271421533668217e-08,
      "learning_rate": 0.12730311338119016,
      "loss": 0.0,
      "num_input_tokens_seen": 6141168,
      "step": 21935
    },
    {
      "epoch": 243.77777777777777,
      "grad_norm": 3.536074544285839e-08,
      "learning_rate": 0.12724488850312327,
      "loss": 0.0,
      "num_input_tokens_seen": 6142592,
      "step": 21940
    },
    {
      "epoch": 243.83333333333334,
      "grad_norm": 2.9941961798840566e-08,
      "learning_rate": 0.1271866671341806,
      "loss": 0.0,
      "num_input_tokens_seen": 6143984,
      "step": 21945
    },
    {
      "epoch": 243.88888888888889,
      "grad_norm": 9.177507109825456e-08,
      "learning_rate": 0.12712844928334047,
      "loss": 0.0,
      "num_input_tokens_seen": 6145392,
      "step": 21950
    },
    {
      "epoch": 243.94444444444446,
      "grad_norm": 1.1248985032352721e-07,
      "learning_rate": 0.12707023495958095,
      "loss": 0.0,
      "num_input_tokens_seen": 6146800,
      "step": 21955
    },
    {
      "epoch": 244.0,
      "grad_norm": 1.0275826411998423e-08,
      "learning_rate": 0.12701202417187932,
      "loss": 0.0,
      "num_input_tokens_seen": 6148176,
      "step": 21960
    },
    {
      "epoch": 244.05555555555554,
      "grad_norm": 4.1615226820113094e-08,
      "learning_rate": 0.12695381692921243,
      "loss": 0.0,
      "num_input_tokens_seen": 6149616,
      "step": 21965
    },
    {
      "epoch": 244.11111111111111,
      "grad_norm": 3.6081427623457785e-08,
      "learning_rate": 0.12689561324055665,
      "loss": 0.0,
      "num_input_tokens_seen": 6150992,
      "step": 21970
    },
    {
      "epoch": 244.16666666666666,
      "grad_norm": 2.6267628072673688e-08,
      "learning_rate": 0.12683741311488758,
      "loss": 0.0,
      "num_input_tokens_seen": 6152384,
      "step": 21975
    },
    {
      "epoch": 244.22222222222223,
      "grad_norm": 3.712774443442868e-08,
      "learning_rate": 0.1267792165611805,
      "loss": 0.0,
      "num_input_tokens_seen": 6153792,
      "step": 21980
    },
    {
      "epoch": 244.27777777777777,
      "grad_norm": 1.1431992241739408e-08,
      "learning_rate": 0.1267210235884101,
      "loss": 0.0,
      "num_input_tokens_seen": 6155200,
      "step": 21985
    },
    {
      "epoch": 244.33333333333334,
      "grad_norm": 2.402939358603362e-08,
      "learning_rate": 0.12666283420555033,
      "loss": 0.0,
      "num_input_tokens_seen": 6156576,
      "step": 21990
    },
    {
      "epoch": 244.38888888888889,
      "grad_norm": 6.578583366945168e-08,
      "learning_rate": 0.12660464842157487,
      "loss": 0.0,
      "num_input_tokens_seen": 6158000,
      "step": 21995
    },
    {
      "epoch": 244.44444444444446,
      "grad_norm": 1.4320550079105487e-08,
      "learning_rate": 0.1265464662454566,
      "loss": 0.0,
      "num_input_tokens_seen": 6159376,
      "step": 22000
    },
    {
      "epoch": 244.44444444444446,
      "eval_loss": 1.670799970626831,
      "eval_runtime": 1.1813,
      "eval_samples_per_second": 33.86,
      "eval_steps_per_second": 16.93,
      "num_input_tokens_seen": 6159376,
      "step": 22000
    },
    {
      "epoch": 244.5,
      "grad_norm": 2.8866248058534438e-08,
      "learning_rate": 0.12648828768616793,
      "loss": 0.0,
      "num_input_tokens_seen": 6160800,
      "step": 22005
    },
    {
      "epoch": 244.55555555555554,
      "grad_norm": 2.0746011131222986e-08,
      "learning_rate": 0.12643011275268085,
      "loss": 0.0,
      "num_input_tokens_seen": 6162192,
      "step": 22010
    },
    {
      "epoch": 244.61111111111111,
      "grad_norm": 7.73618591409786e-09,
      "learning_rate": 0.1263719414539665,
      "loss": 0.0,
      "num_input_tokens_seen": 6163600,
      "step": 22015
    },
    {
      "epoch": 244.66666666666666,
      "grad_norm": 1.9579703192107445e-08,
      "learning_rate": 0.1263137737989957,
      "loss": 0.0,
      "num_input_tokens_seen": 6165024,
      "step": 22020
    },
    {
      "epoch": 244.72222222222223,
      "grad_norm": 2.0858804461454383e-08,
      "learning_rate": 0.1262556097967387,
      "loss": 0.0,
      "num_input_tokens_seen": 6166432,
      "step": 22025
    },
    {
      "epoch": 244.77777777777777,
      "grad_norm": 2.9028923265173034e-08,
      "learning_rate": 0.126197449456165,
      "loss": 0.0,
      "num_input_tokens_seen": 6167824,
      "step": 22030
    },
    {
      "epoch": 244.83333333333334,
      "grad_norm": 2.3049285147180854e-08,
      "learning_rate": 0.12613929278624378,
      "loss": 0.0,
      "num_input_tokens_seen": 6169184,
      "step": 22035
    },
    {
      "epoch": 244.88888888888889,
      "grad_norm": 3.8545493907804484e-08,
      "learning_rate": 0.12608113979594343,
      "loss": 0.0,
      "num_input_tokens_seen": 6170592,
      "step": 22040
    },
    {
      "epoch": 244.94444444444446,
      "grad_norm": 3.602905351840491e-08,
      "learning_rate": 0.1260229904942319,
      "loss": 0.0,
      "num_input_tokens_seen": 6171984,
      "step": 22045
    },
    {
      "epoch": 245.0,
      "grad_norm": 1.5666021369042937e-08,
      "learning_rate": 0.12596484489007662,
      "loss": 0.0,
      "num_input_tokens_seen": 6173376,
      "step": 22050
    },
    {
      "epoch": 245.05555555555554,
      "grad_norm": 1.1236847008433415e-08,
      "learning_rate": 0.1259067029924442,
      "loss": 0.0,
      "num_input_tokens_seen": 6174752,
      "step": 22055
    },
    {
      "epoch": 245.11111111111111,
      "grad_norm": 1.752607659000205e-08,
      "learning_rate": 0.12584856481030096,
      "loss": 0.0,
      "num_input_tokens_seen": 6176128,
      "step": 22060
    },
    {
      "epoch": 245.16666666666666,
      "grad_norm": 8.957399266762422e-09,
      "learning_rate": 0.12579043035261261,
      "loss": 0.0,
      "num_input_tokens_seen": 6177504,
      "step": 22065
    },
    {
      "epoch": 245.22222222222223,
      "grad_norm": 5.301474104157933e-08,
      "learning_rate": 0.1257322996283441,
      "loss": 0.0,
      "num_input_tokens_seen": 6178944,
      "step": 22070
    },
    {
      "epoch": 245.27777777777777,
      "grad_norm": 9.879701501347427e-09,
      "learning_rate": 0.12567417264645994,
      "loss": 0.0,
      "num_input_tokens_seen": 6180352,
      "step": 22075
    },
    {
      "epoch": 245.33333333333334,
      "grad_norm": 2.1305201158838827e-08,
      "learning_rate": 0.12561604941592408,
      "loss": 0.0,
      "num_input_tokens_seen": 6181680,
      "step": 22080
    },
    {
      "epoch": 245.38888888888889,
      "grad_norm": 3.1485193119351607e-08,
      "learning_rate": 0.12555792994569978,
      "loss": 0.0,
      "num_input_tokens_seen": 6183088,
      "step": 22085
    },
    {
      "epoch": 245.44444444444446,
      "grad_norm": 1.74551377796206e-08,
      "learning_rate": 0.1254998142447499,
      "loss": 0.0,
      "num_input_tokens_seen": 6184464,
      "step": 22090
    },
    {
      "epoch": 245.5,
      "grad_norm": 9.738860384800319e-09,
      "learning_rate": 0.1254417023220365,
      "loss": 0.0,
      "num_input_tokens_seen": 6185808,
      "step": 22095
    },
    {
      "epoch": 245.55555555555554,
      "grad_norm": 3.92908745538989e-08,
      "learning_rate": 0.12538359418652126,
      "loss": 0.0,
      "num_input_tokens_seen": 6187216,
      "step": 22100
    },
    {
      "epoch": 245.61111111111111,
      "grad_norm": 3.350036337224083e-08,
      "learning_rate": 0.12532548984716513,
      "loss": 0.0,
      "num_input_tokens_seen": 6188592,
      "step": 22105
    },
    {
      "epoch": 245.66666666666666,
      "grad_norm": 1.4022000449642746e-08,
      "learning_rate": 0.12526738931292855,
      "loss": 0.0,
      "num_input_tokens_seen": 6190016,
      "step": 22110
    },
    {
      "epoch": 245.72222222222223,
      "grad_norm": 1.5680694076536383e-08,
      "learning_rate": 0.1252092925927714,
      "loss": 0.0,
      "num_input_tokens_seen": 6191408,
      "step": 22115
    },
    {
      "epoch": 245.77777777777777,
      "grad_norm": 1.814536609856532e-08,
      "learning_rate": 0.12515119969565278,
      "loss": 0.0,
      "num_input_tokens_seen": 6192832,
      "step": 22120
    },
    {
      "epoch": 245.83333333333334,
      "grad_norm": 2.1633338675997038e-08,
      "learning_rate": 0.12509311063053144,
      "loss": 0.0,
      "num_input_tokens_seen": 6194272,
      "step": 22125
    },
    {
      "epoch": 245.88888888888889,
      "grad_norm": 2.7159774873553033e-08,
      "learning_rate": 0.1250350254063655,
      "loss": 0.0,
      "num_input_tokens_seen": 6195696,
      "step": 22130
    },
    {
      "epoch": 245.94444444444446,
      "grad_norm": 3.529894954112933e-08,
      "learning_rate": 0.1249769440321123,
      "loss": 0.0,
      "num_input_tokens_seen": 6197104,
      "step": 22135
    },
    {
      "epoch": 246.0,
      "grad_norm": 2.0576811365913272e-08,
      "learning_rate": 0.12491886651672884,
      "loss": 0.0,
      "num_input_tokens_seen": 6198512,
      "step": 22140
    },
    {
      "epoch": 246.05555555555554,
      "grad_norm": 4.558594923764758e-08,
      "learning_rate": 0.12486079286917139,
      "loss": 0.0,
      "num_input_tokens_seen": 6199888,
      "step": 22145
    },
    {
      "epoch": 246.11111111111111,
      "grad_norm": 1.539947724893409e-08,
      "learning_rate": 0.12480272309839553,
      "loss": 0.0,
      "num_input_tokens_seen": 6201296,
      "step": 22150
    },
    {
      "epoch": 246.16666666666666,
      "grad_norm": 2.122969888773696e-08,
      "learning_rate": 0.12474465721335648,
      "loss": 0.0,
      "num_input_tokens_seen": 6202688,
      "step": 22155
    },
    {
      "epoch": 246.22222222222223,
      "grad_norm": 1.1969396140898425e-08,
      "learning_rate": 0.12468659522300861,
      "loss": 0.0,
      "num_input_tokens_seen": 6204048,
      "step": 22160
    },
    {
      "epoch": 246.27777777777777,
      "grad_norm": 2.8658371675760463e-08,
      "learning_rate": 0.12462853713630584,
      "loss": 0.0,
      "num_input_tokens_seen": 6205488,
      "step": 22165
    },
    {
      "epoch": 246.33333333333334,
      "grad_norm": 4.835838396388681e-08,
      "learning_rate": 0.12457048296220156,
      "loss": 0.0,
      "num_input_tokens_seen": 6206912,
      "step": 22170
    },
    {
      "epoch": 246.38888888888889,
      "grad_norm": 9.545449763948e-09,
      "learning_rate": 0.12451243270964832,
      "loss": 0.0,
      "num_input_tokens_seen": 6208304,
      "step": 22175
    },
    {
      "epoch": 246.44444444444446,
      "grad_norm": 1.3034467727379706e-08,
      "learning_rate": 0.12445438638759827,
      "loss": 0.0,
      "num_input_tokens_seen": 6209728,
      "step": 22180
    },
    {
      "epoch": 246.5,
      "grad_norm": 1.91387030668011e-08,
      "learning_rate": 0.1243963440050029,
      "loss": 0.0,
      "num_input_tokens_seen": 6211168,
      "step": 22185
    },
    {
      "epoch": 246.55555555555554,
      "grad_norm": 2.141946175981957e-08,
      "learning_rate": 0.12433830557081298,
      "loss": 0.0,
      "num_input_tokens_seen": 6212560,
      "step": 22190
    },
    {
      "epoch": 246.61111111111111,
      "grad_norm": 3.83515619262198e-08,
      "learning_rate": 0.12428027109397889,
      "loss": 0.0,
      "num_input_tokens_seen": 6213968,
      "step": 22195
    },
    {
      "epoch": 246.66666666666666,
      "grad_norm": 1.854633957520946e-08,
      "learning_rate": 0.12422224058345015,
      "loss": 0.0,
      "num_input_tokens_seen": 6215360,
      "step": 22200
    },
    {
      "epoch": 246.66666666666666,
      "eval_loss": 1.643697738647461,
      "eval_runtime": 1.1843,
      "eval_samples_per_second": 33.774,
      "eval_steps_per_second": 16.887,
      "num_input_tokens_seen": 6215360,
      "step": 22200
    },
    {
      "epoch": 246.72222222222223,
      "grad_norm": 1.753608458443523e-08,
      "learning_rate": 0.12416421404817583,
      "loss": 0.0,
      "num_input_tokens_seen": 6216784,
      "step": 22205
    },
    {
      "epoch": 246.77777777777777,
      "grad_norm": 2.334325266417636e-08,
      "learning_rate": 0.12410619149710447,
      "loss": 0.0,
      "num_input_tokens_seen": 6218192,
      "step": 22210
    },
    {
      "epoch": 246.83333333333334,
      "grad_norm": 2.72761511155295e-08,
      "learning_rate": 0.12404817293918374,
      "loss": 0.0,
      "num_input_tokens_seen": 6219616,
      "step": 22215
    },
    {
      "epoch": 246.88888888888889,
      "grad_norm": 2.9678014712430922e-08,
      "learning_rate": 0.12399015838336086,
      "loss": 0.0,
      "num_input_tokens_seen": 6220976,
      "step": 22220
    },
    {
      "epoch": 246.94444444444446,
      "grad_norm": 9.924391974891478e-09,
      "learning_rate": 0.12393214783858246,
      "loss": 0.0,
      "num_input_tokens_seen": 6222352,
      "step": 22225
    },
    {
      "epoch": 247.0,
      "grad_norm": 1.2042572272719099e-08,
      "learning_rate": 0.1238741413137944,
      "loss": 0.0,
      "num_input_tokens_seen": 6223728,
      "step": 22230
    },
    {
      "epoch": 247.05555555555554,
      "grad_norm": 1.0071136813394332e-08,
      "learning_rate": 0.12381613881794212,
      "loss": 0.0,
      "num_input_tokens_seen": 6225104,
      "step": 22235
    },
    {
      "epoch": 247.11111111111111,
      "grad_norm": 3.629463307674996e-08,
      "learning_rate": 0.12375814035997022,
      "loss": 0.0,
      "num_input_tokens_seen": 6226464,
      "step": 22240
    },
    {
      "epoch": 247.16666666666666,
      "grad_norm": 2.1063499389128992e-08,
      "learning_rate": 0.12370014594882285,
      "loss": 0.0,
      "num_input_tokens_seen": 6227840,
      "step": 22245
    },
    {
      "epoch": 247.22222222222223,
      "grad_norm": 8.50667625229562e-09,
      "learning_rate": 0.12364215559344356,
      "loss": 0.0,
      "num_input_tokens_seen": 6229232,
      "step": 22250
    },
    {
      "epoch": 247.27777777777777,
      "grad_norm": 9.754636209891032e-09,
      "learning_rate": 0.12358416930277506,
      "loss": 0.0,
      "num_input_tokens_seen": 6230624,
      "step": 22255
    },
    {
      "epoch": 247.33333333333334,
      "grad_norm": 8.134704785334179e-07,
      "learning_rate": 0.1235261870857596,
      "loss": 0.0,
      "num_input_tokens_seen": 6232032,
      "step": 22260
    },
    {
      "epoch": 247.38888888888889,
      "grad_norm": 2.5616705201514378e-08,
      "learning_rate": 0.12346820895133884,
      "loss": 0.0,
      "num_input_tokens_seen": 6233424,
      "step": 22265
    },
    {
      "epoch": 247.44444444444446,
      "grad_norm": 1.4394666791872623e-08,
      "learning_rate": 0.12341023490845361,
      "loss": 0.0,
      "num_input_tokens_seen": 6234800,
      "step": 22270
    },
    {
      "epoch": 247.5,
      "grad_norm": 3.4331655740516e-08,
      "learning_rate": 0.12335226496604437,
      "loss": 0.0,
      "num_input_tokens_seen": 6236208,
      "step": 22275
    },
    {
      "epoch": 247.55555555555554,
      "grad_norm": 2.5578952289606605e-08,
      "learning_rate": 0.12329429913305069,
      "loss": 0.0,
      "num_input_tokens_seen": 6237632,
      "step": 22280
    },
    {
      "epoch": 247.61111111111111,
      "grad_norm": 4.131901576442942e-08,
      "learning_rate": 0.12323633741841171,
      "loss": 0.0,
      "num_input_tokens_seen": 6239072,
      "step": 22285
    },
    {
      "epoch": 247.66666666666666,
      "grad_norm": 6.014667519593786e-08,
      "learning_rate": 0.12317837983106583,
      "loss": 0.0,
      "num_input_tokens_seen": 6240464,
      "step": 22290
    },
    {
      "epoch": 247.72222222222223,
      "grad_norm": 1.4789335978093732e-08,
      "learning_rate": 0.12312042637995087,
      "loss": 0.0,
      "num_input_tokens_seen": 6241840,
      "step": 22295
    },
    {
      "epoch": 247.77777777777777,
      "grad_norm": 3.198913134383474e-08,
      "learning_rate": 0.12306247707400389,
      "loss": 0.0,
      "num_input_tokens_seen": 6243280,
      "step": 22300
    },
    {
      "epoch": 247.83333333333334,
      "grad_norm": 2.372358309798983e-08,
      "learning_rate": 0.12300453192216154,
      "loss": 0.0,
      "num_input_tokens_seen": 6244704,
      "step": 22305
    },
    {
      "epoch": 247.88888888888889,
      "grad_norm": 6.167815058688575e-08,
      "learning_rate": 0.12294659093335956,
      "loss": 0.0,
      "num_input_tokens_seen": 6246128,
      "step": 22310
    },
    {
      "epoch": 247.94444444444446,
      "grad_norm": 1.3217152705635726e-08,
      "learning_rate": 0.12288865411653327,
      "loss": 0.0,
      "num_input_tokens_seen": 6247504,
      "step": 22315
    },
    {
      "epoch": 248.0,
      "grad_norm": 2.9920162347707446e-08,
      "learning_rate": 0.12283072148061717,
      "loss": 0.0,
      "num_input_tokens_seen": 6248896,
      "step": 22320
    },
    {
      "epoch": 248.05555555555554,
      "grad_norm": 1.5522354956942763e-08,
      "learning_rate": 0.12277279303454529,
      "loss": 0.0,
      "num_input_tokens_seen": 6250288,
      "step": 22325
    },
    {
      "epoch": 248.11111111111111,
      "grad_norm": 1.9799140105192237e-08,
      "learning_rate": 0.12271486878725091,
      "loss": 0.0,
      "num_input_tokens_seen": 6251696,
      "step": 22330
    },
    {
      "epoch": 248.16666666666666,
      "grad_norm": 2.1527043259084166e-08,
      "learning_rate": 0.12265694874766658,
      "loss": 0.0,
      "num_input_tokens_seen": 6253056,
      "step": 22335
    },
    {
      "epoch": 248.22222222222223,
      "grad_norm": 1.8235564169799545e-08,
      "learning_rate": 0.12259903292472435,
      "loss": 0.0,
      "num_input_tokens_seen": 6254464,
      "step": 22340
    },
    {
      "epoch": 248.27777777777777,
      "grad_norm": 1.452724873729494e-08,
      "learning_rate": 0.12254112132735567,
      "loss": 0.0,
      "num_input_tokens_seen": 6255872,
      "step": 22345
    },
    {
      "epoch": 248.33333333333334,
      "grad_norm": 1.4295921779705623e-08,
      "learning_rate": 0.12248321396449108,
      "loss": 0.0,
      "num_input_tokens_seen": 6257248,
      "step": 22350
    },
    {
      "epoch": 248.38888888888889,
      "grad_norm": 9.130102007759433e-09,
      "learning_rate": 0.12242531084506075,
      "loss": 0.0,
      "num_input_tokens_seen": 6258608,
      "step": 22355
    },
    {
      "epoch": 248.44444444444446,
      "grad_norm": 1.8086824482566044e-08,
      "learning_rate": 0.122367411977994,
      "loss": 0.0,
      "num_input_tokens_seen": 6260000,
      "step": 22360
    },
    {
      "epoch": 248.5,
      "grad_norm": 1.2736800947266147e-08,
      "learning_rate": 0.12230951737221954,
      "loss": 0.0,
      "num_input_tokens_seen": 6261440,
      "step": 22365
    },
    {
      "epoch": 248.55555555555554,
      "grad_norm": 1.604995247816987e-08,
      "learning_rate": 0.12225162703666555,
      "loss": 0.0,
      "num_input_tokens_seen": 6262896,
      "step": 22370
    },
    {
      "epoch": 248.61111111111111,
      "grad_norm": 2.115168484806418e-08,
      "learning_rate": 0.1221937409802593,
      "loss": 0.0,
      "num_input_tokens_seen": 6264272,
      "step": 22375
    },
    {
      "epoch": 248.66666666666666,
      "grad_norm": 5.010986114939442e-08,
      "learning_rate": 0.12213585921192768,
      "loss": 0.0,
      "num_input_tokens_seen": 6265648,
      "step": 22380
    },
    {
      "epoch": 248.72222222222223,
      "grad_norm": 9.754654861637846e-09,
      "learning_rate": 0.1220779817405967,
      "loss": 0.0,
      "num_input_tokens_seen": 6267040,
      "step": 22385
    },
    {
      "epoch": 248.77777777777777,
      "grad_norm": 1.1079844597361443e-07,
      "learning_rate": 0.12202010857519181,
      "loss": 0.0,
      "num_input_tokens_seen": 6268432,
      "step": 22390
    },
    {
      "epoch": 248.83333333333334,
      "grad_norm": 3.2528177484891785e-08,
      "learning_rate": 0.12196223972463785,
      "loss": 0.0,
      "num_input_tokens_seen": 6269824,
      "step": 22395
    },
    {
      "epoch": 248.88888888888889,
      "grad_norm": 2.3062172616050702e-08,
      "learning_rate": 0.12190437519785885,
      "loss": 0.0,
      "num_input_tokens_seen": 6271232,
      "step": 22400
    },
    {
      "epoch": 248.88888888888889,
      "eval_loss": 1.6692050695419312,
      "eval_runtime": 1.1887,
      "eval_samples_per_second": 33.651,
      "eval_steps_per_second": 16.826,
      "num_input_tokens_seen": 6271232,
      "step": 22400
    },
    {
      "epoch": 248.94444444444446,
      "grad_norm": 2.7323318718686096e-08,
      "learning_rate": 0.12184651500377823,
      "loss": 0.0,
      "num_input_tokens_seen": 6272656,
      "step": 22405
    },
    {
      "epoch": 249.0,
      "grad_norm": 1.2556452766432358e-08,
      "learning_rate": 0.12178865915131885,
      "loss": 0.0,
      "num_input_tokens_seen": 6274048,
      "step": 22410
    },
    {
      "epoch": 249.05555555555554,
      "grad_norm": 1.5429673538847055e-08,
      "learning_rate": 0.1217308076494027,
      "loss": 0.0,
      "num_input_tokens_seen": 6275504,
      "step": 22415
    },
    {
      "epoch": 249.11111111111111,
      "grad_norm": 2.465789172845234e-08,
      "learning_rate": 0.12167296050695134,
      "loss": 0.0,
      "num_input_tokens_seen": 6276880,
      "step": 22420
    },
    {
      "epoch": 249.16666666666666,
      "grad_norm": 7.929629219916023e-08,
      "learning_rate": 0.12161511773288536,
      "loss": 0.0,
      "num_input_tokens_seen": 6278288,
      "step": 22425
    },
    {
      "epoch": 249.22222222222223,
      "grad_norm": 2.707119683975634e-08,
      "learning_rate": 0.121557279336125,
      "loss": 0.0,
      "num_input_tokens_seen": 6279680,
      "step": 22430
    },
    {
      "epoch": 249.27777777777777,
      "grad_norm": 1.032185750204917e-07,
      "learning_rate": 0.12149944532558957,
      "loss": 0.0,
      "num_input_tokens_seen": 6281088,
      "step": 22435
    },
    {
      "epoch": 249.33333333333334,
      "grad_norm": 2.044536984158185e-08,
      "learning_rate": 0.12144161571019785,
      "loss": 0.0,
      "num_input_tokens_seen": 6282480,
      "step": 22440
    },
    {
      "epoch": 249.38888888888889,
      "grad_norm": 1.9995985311993536e-08,
      "learning_rate": 0.12138379049886781,
      "loss": 0.0,
      "num_input_tokens_seen": 6283872,
      "step": 22445
    },
    {
      "epoch": 249.44444444444446,
      "grad_norm": 2.8329836254670226e-08,
      "learning_rate": 0.12132596970051697,
      "loss": 0.0,
      "num_input_tokens_seen": 6285232,
      "step": 22450
    },
    {
      "epoch": 249.5,
      "grad_norm": 1.317864040117911e-08,
      "learning_rate": 0.12126815332406189,
      "loss": 0.0,
      "num_input_tokens_seen": 6286592,
      "step": 22455
    },
    {
      "epoch": 249.55555555555554,
      "grad_norm": 1.9844792475964823e-08,
      "learning_rate": 0.12121034137841868,
      "loss": 0.0,
      "num_input_tokens_seen": 6288000,
      "step": 22460
    },
    {
      "epoch": 249.61111111111111,
      "grad_norm": 6.877652936054801e-08,
      "learning_rate": 0.12115253387250258,
      "loss": 0.0,
      "num_input_tokens_seen": 6289392,
      "step": 22465
    },
    {
      "epoch": 249.66666666666666,
      "grad_norm": 4.0120561095591256e-08,
      "learning_rate": 0.12109473081522831,
      "loss": 0.0,
      "num_input_tokens_seen": 6290800,
      "step": 22470
    },
    {
      "epoch": 249.72222222222223,
      "grad_norm": 2.8369489868396158e-08,
      "learning_rate": 0.12103693221550982,
      "loss": 0.0,
      "num_input_tokens_seen": 6292176,
      "step": 22475
    },
    {
      "epoch": 249.77777777777777,
      "grad_norm": 2.8537961327401717e-08,
      "learning_rate": 0.12097913808226027,
      "loss": 0.0,
      "num_input_tokens_seen": 6293552,
      "step": 22480
    },
    {
      "epoch": 249.83333333333334,
      "grad_norm": 3.805821791047492e-08,
      "learning_rate": 0.12092134842439234,
      "loss": 0.0,
      "num_input_tokens_seen": 6294944,
      "step": 22485
    },
    {
      "epoch": 249.88888888888889,
      "grad_norm": 5.423230575729576e-08,
      "learning_rate": 0.12086356325081798,
      "loss": 0.0,
      "num_input_tokens_seen": 6296384,
      "step": 22490
    },
    {
      "epoch": 249.94444444444446,
      "grad_norm": 5.4977022045932245e-08,
      "learning_rate": 0.12080578257044824,
      "loss": 0.0,
      "num_input_tokens_seen": 6297808,
      "step": 22495
    },
    {
      "epoch": 250.0,
      "grad_norm": 2.4164169332152596e-08,
      "learning_rate": 0.12074800639219378,
      "loss": 0.0,
      "num_input_tokens_seen": 6299216,
      "step": 22500
    },
    {
      "epoch": 250.05555555555554,
      "grad_norm": 3.7081491655044374e-08,
      "learning_rate": 0.12069023472496428,
      "loss": 0.0,
      "num_input_tokens_seen": 6300656,
      "step": 22505
    },
    {
      "epoch": 250.11111111111111,
      "grad_norm": 4.0663941547336435e-08,
      "learning_rate": 0.12063246757766893,
      "loss": 0.0,
      "num_input_tokens_seen": 6302080,
      "step": 22510
    },
    {
      "epoch": 250.16666666666666,
      "grad_norm": 1.8806272095162058e-08,
      "learning_rate": 0.12057470495921618,
      "loss": 0.0,
      "num_input_tokens_seen": 6303456,
      "step": 22515
    },
    {
      "epoch": 250.22222222222223,
      "grad_norm": 9.11168243078464e-08,
      "learning_rate": 0.12051694687851364,
      "loss": 0.0,
      "num_input_tokens_seen": 6304816,
      "step": 22520
    },
    {
      "epoch": 250.27777777777777,
      "grad_norm": 3.804380099836635e-08,
      "learning_rate": 0.12045919334446839,
      "loss": 0.0,
      "num_input_tokens_seen": 6306192,
      "step": 22525
    },
    {
      "epoch": 250.33333333333334,
      "grad_norm": 1.2252399095302735e-08,
      "learning_rate": 0.12040144436598683,
      "loss": 0.0,
      "num_input_tokens_seen": 6307568,
      "step": 22530
    },
    {
      "epoch": 250.38888888888889,
      "grad_norm": 3.82613514204877e-08,
      "learning_rate": 0.12034369995197444,
      "loss": 0.0,
      "num_input_tokens_seen": 6308944,
      "step": 22535
    },
    {
      "epoch": 250.44444444444446,
      "grad_norm": 1.4377713242197387e-08,
      "learning_rate": 0.12028596011133627,
      "loss": 0.0,
      "num_input_tokens_seen": 6310352,
      "step": 22540
    },
    {
      "epoch": 250.5,
      "grad_norm": 1.4537335779607474e-08,
      "learning_rate": 0.12022822485297643,
      "loss": 0.0,
      "num_input_tokens_seen": 6311712,
      "step": 22545
    },
    {
      "epoch": 250.55555555555554,
      "grad_norm": 3.719315699868275e-08,
      "learning_rate": 0.12017049418579843,
      "loss": 0.0,
      "num_input_tokens_seen": 6313184,
      "step": 22550
    },
    {
      "epoch": 250.61111111111111,
      "grad_norm": 1.4158774597206047e-08,
      "learning_rate": 0.12011276811870514,
      "loss": 0.0,
      "num_input_tokens_seen": 6314560,
      "step": 22555
    },
    {
      "epoch": 250.66666666666666,
      "grad_norm": 3.225625988534375e-08,
      "learning_rate": 0.12005504666059852,
      "loss": 0.0,
      "num_input_tokens_seen": 6315984,
      "step": 22560
    },
    {
      "epoch": 250.72222222222223,
      "grad_norm": 2.7562109039536153e-08,
      "learning_rate": 0.11999732982038003,
      "loss": 0.0,
      "num_input_tokens_seen": 6317360,
      "step": 22565
    },
    {
      "epoch": 250.77777777777777,
      "grad_norm": 2.8528795326110412e-08,
      "learning_rate": 0.11993961760695038,
      "loss": 0.0,
      "num_input_tokens_seen": 6318768,
      "step": 22570
    },
    {
      "epoch": 250.83333333333334,
      "grad_norm": 6.099049443264448e-08,
      "learning_rate": 0.11988191002920942,
      "loss": 0.0,
      "num_input_tokens_seen": 6320144,
      "step": 22575
    },
    {
      "epoch": 250.88888888888889,
      "grad_norm": 3.2030765595436606e-08,
      "learning_rate": 0.11982420709605641,
      "loss": 0.0,
      "num_input_tokens_seen": 6321568,
      "step": 22580
    },
    {
      "epoch": 250.94444444444446,
      "grad_norm": 3.0254703631271695e-08,
      "learning_rate": 0.11976650881638991,
      "loss": 0.0,
      "num_input_tokens_seen": 6322960,
      "step": 22585
    },
    {
      "epoch": 251.0,
      "grad_norm": 2.8165761278842183e-08,
      "learning_rate": 0.11970881519910764,
      "loss": 0.0,
      "num_input_tokens_seen": 6324320,
      "step": 22590
    },
    {
      "epoch": 251.05555555555554,
      "grad_norm": 3.2282319040177754e-08,
      "learning_rate": 0.1196511262531068,
      "loss": 0.0,
      "num_input_tokens_seen": 6325760,
      "step": 22595
    },
    {
      "epoch": 251.11111111111111,
      "grad_norm": 2.7965823434783488e-08,
      "learning_rate": 0.11959344198728361,
      "loss": 0.0,
      "num_input_tokens_seen": 6327136,
      "step": 22600
    },
    {
      "epoch": 251.11111111111111,
      "eval_loss": 1.6101179122924805,
      "eval_runtime": 1.1833,
      "eval_samples_per_second": 33.805,
      "eval_steps_per_second": 16.902,
      "num_input_tokens_seen": 6327136,
      "step": 22600
    },
    {
      "epoch": 251.16666666666666,
      "grad_norm": 1.1579877501333158e-08,
      "learning_rate": 0.11953576241053378,
      "loss": 0.0,
      "num_input_tokens_seen": 6328512,
      "step": 22605
    },
    {
      "epoch": 251.22222222222223,
      "grad_norm": 2.6048320833638172e-08,
      "learning_rate": 0.11947808753175228,
      "loss": 0.0,
      "num_input_tokens_seen": 6329904,
      "step": 22610
    },
    {
      "epoch": 251.27777777777777,
      "grad_norm": 8.110811577921595e-09,
      "learning_rate": 0.1194204173598332,
      "loss": 0.0,
      "num_input_tokens_seen": 6331344,
      "step": 22615
    },
    {
      "epoch": 251.33333333333334,
      "grad_norm": 2.1019713969394616e-08,
      "learning_rate": 0.11936275190367007,
      "loss": 0.0,
      "num_input_tokens_seen": 6332768,
      "step": 22620
    },
    {
      "epoch": 251.38888888888889,
      "grad_norm": 1.7622042491893808e-08,
      "learning_rate": 0.11930509117215563,
      "loss": 0.0,
      "num_input_tokens_seen": 6334192,
      "step": 22625
    },
    {
      "epoch": 251.44444444444446,
      "grad_norm": 8.668809670098199e-08,
      "learning_rate": 0.11924743517418179,
      "loss": 0.0,
      "num_input_tokens_seen": 6335568,
      "step": 22630
    },
    {
      "epoch": 251.5,
      "grad_norm": 2.831063028452263e-08,
      "learning_rate": 0.11918978391864,
      "loss": 0.0,
      "num_input_tokens_seen": 6336976,
      "step": 22635
    },
    {
      "epoch": 251.55555555555554,
      "grad_norm": 1.3844845270227779e-08,
      "learning_rate": 0.11913213741442065,
      "loss": 0.0,
      "num_input_tokens_seen": 6338384,
      "step": 22640
    },
    {
      "epoch": 251.61111111111111,
      "grad_norm": 5.971816108285566e-08,
      "learning_rate": 0.11907449567041364,
      "loss": 0.0,
      "num_input_tokens_seen": 6339792,
      "step": 22645
    },
    {
      "epoch": 251.66666666666666,
      "grad_norm": 6.841296595894164e-08,
      "learning_rate": 0.11901685869550803,
      "loss": 0.0,
      "num_input_tokens_seen": 6341184,
      "step": 22650
    },
    {
      "epoch": 251.72222222222223,
      "grad_norm": 2.0775802411776567e-08,
      "learning_rate": 0.1189592264985922,
      "loss": 0.0,
      "num_input_tokens_seen": 6342608,
      "step": 22655
    },
    {
      "epoch": 251.77777777777777,
      "grad_norm": 2.261953468973843e-08,
      "learning_rate": 0.11890159908855373,
      "loss": 0.0,
      "num_input_tokens_seen": 6344048,
      "step": 22660
    },
    {
      "epoch": 251.83333333333334,
      "grad_norm": 5.352667997726712e-08,
      "learning_rate": 0.11884397647427941,
      "loss": 0.0,
      "num_input_tokens_seen": 6345472,
      "step": 22665
    },
    {
      "epoch": 251.88888888888889,
      "grad_norm": 4.015147681002418e-08,
      "learning_rate": 0.11878635866465546,
      "loss": 0.0,
      "num_input_tokens_seen": 6346896,
      "step": 22670
    },
    {
      "epoch": 251.94444444444446,
      "grad_norm": 1.4914766310880623e-08,
      "learning_rate": 0.11872874566856734,
      "loss": 0.0,
      "num_input_tokens_seen": 6348272,
      "step": 22675
    },
    {
      "epoch": 252.0,
      "grad_norm": 2.052066605529035e-08,
      "learning_rate": 0.11867113749489955,
      "loss": 0.0,
      "num_input_tokens_seen": 6349664,
      "step": 22680
    },
    {
      "epoch": 252.05555555555554,
      "grad_norm": 2.3811058014189257e-08,
      "learning_rate": 0.11861353415253607,
      "loss": 0.0,
      "num_input_tokens_seen": 6351056,
      "step": 22685
    },
    {
      "epoch": 252.11111111111111,
      "grad_norm": 2.6747265735593828e-08,
      "learning_rate": 0.11855593565036011,
      "loss": 0.0,
      "num_input_tokens_seen": 6352464,
      "step": 22690
    },
    {
      "epoch": 252.16666666666666,
      "grad_norm": 8.761292491499262e-08,
      "learning_rate": 0.11849834199725394,
      "loss": 0.0,
      "num_input_tokens_seen": 6353840,
      "step": 22695
    },
    {
      "epoch": 252.22222222222223,
      "grad_norm": 7.797442691526157e-08,
      "learning_rate": 0.1184407532020994,
      "loss": 0.0,
      "num_input_tokens_seen": 6355232,
      "step": 22700
    },
    {
      "epoch": 252.27777777777777,
      "grad_norm": 5.323228080555964e-08,
      "learning_rate": 0.11838316927377723,
      "loss": 0.0,
      "num_input_tokens_seen": 6356672,
      "step": 22705
    },
    {
      "epoch": 252.33333333333334,
      "grad_norm": 1.9058413514017047e-08,
      "learning_rate": 0.11832559022116766,
      "loss": 0.0,
      "num_input_tokens_seen": 6358096,
      "step": 22710
    },
    {
      "epoch": 252.38888888888889,
      "grad_norm": 2.5946064852178097e-08,
      "learning_rate": 0.11826801605315022,
      "loss": 0.0,
      "num_input_tokens_seen": 6359520,
      "step": 22715
    },
    {
      "epoch": 252.44444444444446,
      "grad_norm": 2.3122991521518088e-08,
      "learning_rate": 0.1182104467786034,
      "loss": 0.0,
      "num_input_tokens_seen": 6360928,
      "step": 22720
    },
    {
      "epoch": 252.5,
      "grad_norm": 3.882151489165153e-08,
      "learning_rate": 0.1181528824064052,
      "loss": 0.0,
      "num_input_tokens_seen": 6362352,
      "step": 22725
    },
    {
      "epoch": 252.55555555555554,
      "grad_norm": 2.6771450833962263e-08,
      "learning_rate": 0.11809532294543279,
      "loss": 0.0,
      "num_input_tokens_seen": 6363712,
      "step": 22730
    },
    {
      "epoch": 252.61111111111111,
      "grad_norm": 1.5904403127819933e-08,
      "learning_rate": 0.11803776840456245,
      "loss": 0.0,
      "num_input_tokens_seen": 6365136,
      "step": 22735
    },
    {
      "epoch": 252.66666666666666,
      "grad_norm": 1.5206447656623823e-08,
      "learning_rate": 0.11798021879266997,
      "loss": 0.0,
      "num_input_tokens_seen": 6366528,
      "step": 22740
    },
    {
      "epoch": 252.72222222222223,
      "grad_norm": 1.3989508218514857e-08,
      "learning_rate": 0.11792267411863006,
      "loss": 0.0,
      "num_input_tokens_seen": 6367968,
      "step": 22745
    },
    {
      "epoch": 252.77777777777777,
      "grad_norm": 4.836273959085702e-08,
      "learning_rate": 0.1178651343913169,
      "loss": 0.0,
      "num_input_tokens_seen": 6369360,
      "step": 22750
    },
    {
      "epoch": 252.83333333333334,
      "grad_norm": 4.22921679898991e-08,
      "learning_rate": 0.11780759961960392,
      "loss": 0.0,
      "num_input_tokens_seen": 6370752,
      "step": 22755
    },
    {
      "epoch": 252.88888888888889,
      "grad_norm": 2.3921312930497152e-08,
      "learning_rate": 0.1177500698123636,
      "loss": 0.0,
      "num_input_tokens_seen": 6372128,
      "step": 22760
    },
    {
      "epoch": 252.94444444444446,
      "grad_norm": 2.6053678325865803e-08,
      "learning_rate": 0.11769254497846778,
      "loss": 0.0,
      "num_input_tokens_seen": 6373488,
      "step": 22765
    },
    {
      "epoch": 253.0,
      "grad_norm": 2.9099140874677687e-08,
      "learning_rate": 0.11763502512678758,
      "loss": 0.0,
      "num_input_tokens_seen": 6374912,
      "step": 22770
    },
    {
      "epoch": 253.05555555555554,
      "grad_norm": 4.427809585649811e-08,
      "learning_rate": 0.11757751026619315,
      "loss": 0.0,
      "num_input_tokens_seen": 6376352,
      "step": 22775
    },
    {
      "epoch": 253.11111111111111,
      "grad_norm": 2.495612250186241e-08,
      "learning_rate": 0.11752000040555416,
      "loss": 0.0,
      "num_input_tokens_seen": 6377776,
      "step": 22780
    },
    {
      "epoch": 253.16666666666666,
      "grad_norm": 9.537763467903915e-09,
      "learning_rate": 0.11746249555373921,
      "loss": 0.0,
      "num_input_tokens_seen": 6379152,
      "step": 22785
    },
    {
      "epoch": 253.22222222222223,
      "grad_norm": 2.4170960344349623e-08,
      "learning_rate": 0.11740499571961638,
      "loss": 0.0,
      "num_input_tokens_seen": 6380528,
      "step": 22790
    },
    {
      "epoch": 253.27777777777777,
      "grad_norm": 1.966451357304777e-08,
      "learning_rate": 0.11734750091205279,
      "loss": 0.0,
      "num_input_tokens_seen": 6381840,
      "step": 22795
    },
    {
      "epoch": 253.33333333333334,
      "grad_norm": 2.7786871470425467e-08,
      "learning_rate": 0.11729001113991493,
      "loss": 0.0,
      "num_input_tokens_seen": 6383248,
      "step": 22800
    },
    {
      "epoch": 253.33333333333334,
      "eval_loss": 1.6198228597640991,
      "eval_runtime": 1.1894,
      "eval_samples_per_second": 33.631,
      "eval_steps_per_second": 16.815,
      "num_input_tokens_seen": 6383248,
      "step": 22800
    },
    {
      "epoch": 253.38888888888889,
      "grad_norm": 5.973774364065321e-08,
      "learning_rate": 0.11723252641206837,
      "loss": 0.0,
      "num_input_tokens_seen": 6384608,
      "step": 22805
    },
    {
      "epoch": 253.44444444444446,
      "grad_norm": 8.054976241567147e-09,
      "learning_rate": 0.11717504673737808,
      "loss": 0.0,
      "num_input_tokens_seen": 6385968,
      "step": 22810
    },
    {
      "epoch": 253.5,
      "grad_norm": 1.6800262869764993e-07,
      "learning_rate": 0.11711757212470802,
      "loss": 0.0,
      "num_input_tokens_seen": 6387376,
      "step": 22815
    },
    {
      "epoch": 253.55555555555554,
      "grad_norm": 5.114466361533232e-08,
      "learning_rate": 0.11706010258292165,
      "loss": 0.0,
      "num_input_tokens_seen": 6388800,
      "step": 22820
    },
    {
      "epoch": 253.61111111111111,
      "grad_norm": 6.467119817443745e-08,
      "learning_rate": 0.11700263812088131,
      "loss": 0.0,
      "num_input_tokens_seen": 6390176,
      "step": 22825
    },
    {
      "epoch": 253.66666666666666,
      "grad_norm": 3.183610886026145e-08,
      "learning_rate": 0.11694517874744892,
      "loss": 0.0,
      "num_input_tokens_seen": 6391568,
      "step": 22830
    },
    {
      "epoch": 253.72222222222223,
      "grad_norm": 1.875991628708107e-08,
      "learning_rate": 0.11688772447148532,
      "loss": 0.0,
      "num_input_tokens_seen": 6392976,
      "step": 22835
    },
    {
      "epoch": 253.77777777777777,
      "grad_norm": 2.2957017620228726e-08,
      "learning_rate": 0.11683027530185074,
      "loss": 0.0,
      "num_input_tokens_seen": 6394400,
      "step": 22840
    },
    {
      "epoch": 253.83333333333334,
      "grad_norm": 3.411792803831304e-08,
      "learning_rate": 0.11677283124740451,
      "loss": 0.0,
      "num_input_tokens_seen": 6395840,
      "step": 22845
    },
    {
      "epoch": 253.88888888888889,
      "grad_norm": 5.5446115254653705e-08,
      "learning_rate": 0.11671539231700531,
      "loss": 0.0,
      "num_input_tokens_seen": 6397232,
      "step": 22850
    },
    {
      "epoch": 253.94444444444446,
      "grad_norm": 2.606615367994891e-08,
      "learning_rate": 0.11665795851951084,
      "loss": 0.0,
      "num_input_tokens_seen": 6398624,
      "step": 22855
    },
    {
      "epoch": 254.0,
      "grad_norm": 3.1679313394761266e-08,
      "learning_rate": 0.11660052986377825,
      "loss": 0.0,
      "num_input_tokens_seen": 6400048,
      "step": 22860
    },
    {
      "epoch": 254.05555555555554,
      "grad_norm": 6.999548674002654e-08,
      "learning_rate": 0.1165431063586636,
      "loss": 0.0,
      "num_input_tokens_seen": 6401504,
      "step": 22865
    },
    {
      "epoch": 254.11111111111111,
      "grad_norm": 1.5450101642500158e-08,
      "learning_rate": 0.11648568801302245,
      "loss": 0.0,
      "num_input_tokens_seen": 6402896,
      "step": 22870
    },
    {
      "epoch": 254.16666666666666,
      "grad_norm": 1.808683869342076e-08,
      "learning_rate": 0.11642827483570937,
      "loss": 0.0,
      "num_input_tokens_seen": 6404288,
      "step": 22875
    },
    {
      "epoch": 254.22222222222223,
      "grad_norm": 4.621517391001362e-08,
      "learning_rate": 0.11637086683557815,
      "loss": 0.0,
      "num_input_tokens_seen": 6405664,
      "step": 22880
    },
    {
      "epoch": 254.27777777777777,
      "grad_norm": 2.157995737661622e-08,
      "learning_rate": 0.11631346402148188,
      "loss": 0.0,
      "num_input_tokens_seen": 6407072,
      "step": 22885
    },
    {
      "epoch": 254.33333333333334,
      "grad_norm": 1.0411945972066405e-08,
      "learning_rate": 0.11625606640227285,
      "loss": 0.0,
      "num_input_tokens_seen": 6408496,
      "step": 22890
    },
    {
      "epoch": 254.38888888888889,
      "grad_norm": 5.909678790771977e-08,
      "learning_rate": 0.11619867398680238,
      "loss": 0.0,
      "num_input_tokens_seen": 6409888,
      "step": 22895
    },
    {
      "epoch": 254.44444444444446,
      "grad_norm": 4.246587437251037e-08,
      "learning_rate": 0.11614128678392119,
      "loss": 0.0,
      "num_input_tokens_seen": 6411280,
      "step": 22900
    },
    {
      "epoch": 254.5,
      "grad_norm": 3.5249474450438356e-08,
      "learning_rate": 0.11608390480247906,
      "loss": 0.0,
      "num_input_tokens_seen": 6412672,
      "step": 22905
    },
    {
      "epoch": 254.55555555555554,
      "grad_norm": 1.9372381032667363e-08,
      "learning_rate": 0.11602652805132499,
      "loss": 0.0,
      "num_input_tokens_seen": 6414048,
      "step": 22910
    },
    {
      "epoch": 254.61111111111111,
      "grad_norm": 3.243959412202457e-08,
      "learning_rate": 0.11596915653930731,
      "loss": 0.0,
      "num_input_tokens_seen": 6415456,
      "step": 22915
    },
    {
      "epoch": 254.66666666666666,
      "grad_norm": 5.698815286336867e-08,
      "learning_rate": 0.11591179027527328,
      "loss": 0.0,
      "num_input_tokens_seen": 6416832,
      "step": 22920
    },
    {
      "epoch": 254.72222222222223,
      "grad_norm": 6.98047486480391e-08,
      "learning_rate": 0.11585442926806956,
      "loss": 0.0,
      "num_input_tokens_seen": 6418224,
      "step": 22925
    },
    {
      "epoch": 254.77777777777777,
      "grad_norm": 6.392404117150363e-08,
      "learning_rate": 0.11579707352654202,
      "loss": 0.0,
      "num_input_tokens_seen": 6419632,
      "step": 22930
    },
    {
      "epoch": 254.83333333333334,
      "grad_norm": 5.603292763112222e-08,
      "learning_rate": 0.11573972305953548,
      "loss": 0.0,
      "num_input_tokens_seen": 6421088,
      "step": 22935
    },
    {
      "epoch": 254.88888888888889,
      "grad_norm": 1.5926886476336222e-08,
      "learning_rate": 0.11568237787589426,
      "loss": 0.0,
      "num_input_tokens_seen": 6422496,
      "step": 22940
    },
    {
      "epoch": 254.94444444444446,
      "grad_norm": 3.032115714063366e-08,
      "learning_rate": 0.11562503798446161,
      "loss": 0.0,
      "num_input_tokens_seen": 6423824,
      "step": 22945
    },
    {
      "epoch": 255.0,
      "grad_norm": 1.1297502489071576e-08,
      "learning_rate": 0.11556770339408005,
      "loss": 0.0,
      "num_input_tokens_seen": 6425200,
      "step": 22950
    },
    {
      "epoch": 255.05555555555554,
      "grad_norm": 1.349054823407414e-08,
      "learning_rate": 0.1155103741135914,
      "loss": 0.0,
      "num_input_tokens_seen": 6426640,
      "step": 22955
    },
    {
      "epoch": 255.11111111111111,
      "grad_norm": 2.8298826393324816e-08,
      "learning_rate": 0.1154530501518364,
      "loss": 0.0,
      "num_input_tokens_seen": 6428032,
      "step": 22960
    },
    {
      "epoch": 255.16666666666666,
      "grad_norm": 2.0730354322040512e-08,
      "learning_rate": 0.11539573151765523,
      "loss": 0.0,
      "num_input_tokens_seen": 6429440,
      "step": 22965
    },
    {
      "epoch": 255.22222222222223,
      "grad_norm": 2.863450809797996e-08,
      "learning_rate": 0.11533841821988719,
      "loss": 0.0,
      "num_input_tokens_seen": 6430816,
      "step": 22970
    },
    {
      "epoch": 255.27777777777777,
      "grad_norm": 3.651824798112102e-08,
      "learning_rate": 0.11528111026737059,
      "loss": 0.0,
      "num_input_tokens_seen": 6432144,
      "step": 22975
    },
    {
      "epoch": 255.33333333333334,
      "grad_norm": 4.384221696795976e-08,
      "learning_rate": 0.11522380766894312,
      "loss": 0.0,
      "num_input_tokens_seen": 6433520,
      "step": 22980
    },
    {
      "epoch": 255.38888888888889,
      "grad_norm": 3.191911446265294e-08,
      "learning_rate": 0.11516651043344152,
      "loss": 0.0,
      "num_input_tokens_seen": 6434976,
      "step": 22985
    },
    {
      "epoch": 255.44444444444446,
      "grad_norm": 4.4396646359246006e-08,
      "learning_rate": 0.11510921856970172,
      "loss": 0.0,
      "num_input_tokens_seen": 6436384,
      "step": 22990
    },
    {
      "epoch": 255.5,
      "grad_norm": 1.8120934086596208e-08,
      "learning_rate": 0.11505193208655895,
      "loss": 0.0,
      "num_input_tokens_seen": 6437792,
      "step": 22995
    },
    {
      "epoch": 255.55555555555554,
      "grad_norm": 9.035412062985415e-08,
      "learning_rate": 0.11499465099284738,
      "loss": 0.0,
      "num_input_tokens_seen": 6439168,
      "step": 23000
    },
    {
      "epoch": 255.55555555555554,
      "eval_loss": 1.566773772239685,
      "eval_runtime": 1.1971,
      "eval_samples_per_second": 33.413,
      "eval_steps_per_second": 16.706,
      "num_input_tokens_seen": 6439168,
      "step": 23000
    },
    {
      "epoch": 255.61111111111111,
      "grad_norm": 1.2532400006648459e-08,
      "learning_rate": 0.1149373752974006,
      "loss": 0.0,
      "num_input_tokens_seen": 6440576,
      "step": 23005
    },
    {
      "epoch": 255.66666666666666,
      "grad_norm": 2.1673324468451938e-08,
      "learning_rate": 0.11488010500905109,
      "loss": 0.0,
      "num_input_tokens_seen": 6441968,
      "step": 23010
    },
    {
      "epoch": 255.72222222222223,
      "grad_norm": 5.788880343970959e-07,
      "learning_rate": 0.11482284013663077,
      "loss": 0.0,
      "num_input_tokens_seen": 6443408,
      "step": 23015
    },
    {
      "epoch": 255.77777777777777,
      "grad_norm": 1.4159497574439683e-08,
      "learning_rate": 0.11476558068897061,
      "loss": 0.0,
      "num_input_tokens_seen": 6444768,
      "step": 23020
    },
    {
      "epoch": 255.83333333333334,
      "grad_norm": 1.659555834976345e-07,
      "learning_rate": 0.11470832667490061,
      "loss": 0.0,
      "num_input_tokens_seen": 6446160,
      "step": 23025
    },
    {
      "epoch": 255.88888888888889,
      "grad_norm": 1.6069018116127154e-08,
      "learning_rate": 0.11465107810325013,
      "loss": 0.0,
      "num_input_tokens_seen": 6447600,
      "step": 23030
    },
    {
      "epoch": 255.94444444444446,
      "grad_norm": 1.0883755230395309e-08,
      "learning_rate": 0.11459383498284771,
      "loss": 0.0,
      "num_input_tokens_seen": 6449024,
      "step": 23035
    },
    {
      "epoch": 256.0,
      "grad_norm": 3.4075821275791895e-08,
      "learning_rate": 0.11453659732252082,
      "loss": 0.0,
      "num_input_tokens_seen": 6450432,
      "step": 23040
    },
    {
      "epoch": 256.05555555555554,
      "grad_norm": 3.48166118158133e-08,
      "learning_rate": 0.11447936513109633,
      "loss": 0.0,
      "num_input_tokens_seen": 6451856,
      "step": 23045
    },
    {
      "epoch": 256.1111111111111,
      "grad_norm": 1.3651054509011828e-08,
      "learning_rate": 0.11442213841740011,
      "loss": 0.0,
      "num_input_tokens_seen": 6453280,
      "step": 23050
    },
    {
      "epoch": 256.1666666666667,
      "grad_norm": 8.966862807824327e-09,
      "learning_rate": 0.1143649171902572,
      "loss": 0.0,
      "num_input_tokens_seen": 6454688,
      "step": 23055
    },
    {
      "epoch": 256.22222222222223,
      "grad_norm": 1.521096137935274e-08,
      "learning_rate": 0.11430770145849194,
      "loss": 0.0,
      "num_input_tokens_seen": 6456080,
      "step": 23060
    },
    {
      "epoch": 256.27777777777777,
      "grad_norm": 2.3371937274418997e-08,
      "learning_rate": 0.11425049123092756,
      "loss": 0.0,
      "num_input_tokens_seen": 6457536,
      "step": 23065
    },
    {
      "epoch": 256.3333333333333,
      "grad_norm": 9.179588644769865e-09,
      "learning_rate": 0.11419328651638674,
      "loss": 0.0,
      "num_input_tokens_seen": 6458928,
      "step": 23070
    },
    {
      "epoch": 256.3888888888889,
      "grad_norm": 1.9750430624299042e-08,
      "learning_rate": 0.11413608732369115,
      "loss": 0.0,
      "num_input_tokens_seen": 6460336,
      "step": 23075
    },
    {
      "epoch": 256.44444444444446,
      "grad_norm": 1.7947133557072448e-08,
      "learning_rate": 0.11407889366166153,
      "loss": 0.0,
      "num_input_tokens_seen": 6461744,
      "step": 23080
    },
    {
      "epoch": 256.5,
      "grad_norm": 1.2410838579057781e-08,
      "learning_rate": 0.11402170553911797,
      "loss": 0.0,
      "num_input_tokens_seen": 6463184,
      "step": 23085
    },
    {
      "epoch": 256.55555555555554,
      "grad_norm": 1.5108765794025203e-08,
      "learning_rate": 0.11396452296487955,
      "loss": 0.0,
      "num_input_tokens_seen": 6464544,
      "step": 23090
    },
    {
      "epoch": 256.6111111111111,
      "grad_norm": 1.102686653098317e-08,
      "learning_rate": 0.11390734594776449,
      "loss": 0.0,
      "num_input_tokens_seen": 6465936,
      "step": 23095
    },
    {
      "epoch": 256.6666666666667,
      "grad_norm": 9.667642686395084e-09,
      "learning_rate": 0.11385017449659031,
      "loss": 0.0,
      "num_input_tokens_seen": 6467328,
      "step": 23100
    },
    {
      "epoch": 256.72222222222223,
      "grad_norm": 1.4350776567084722e-08,
      "learning_rate": 0.11379300862017344,
      "loss": 0.0,
      "num_input_tokens_seen": 6468704,
      "step": 23105
    },
    {
      "epoch": 256.77777777777777,
      "grad_norm": 1.866436605268973e-08,
      "learning_rate": 0.11373584832732966,
      "loss": 0.0,
      "num_input_tokens_seen": 6470096,
      "step": 23110
    },
    {
      "epoch": 256.8333333333333,
      "grad_norm": 2.1804632766020404e-08,
      "learning_rate": 0.11367869362687386,
      "loss": 0.0,
      "num_input_tokens_seen": 6471488,
      "step": 23115
    },
    {
      "epoch": 256.8888888888889,
      "grad_norm": 9.500342734725109e-09,
      "learning_rate": 0.11362154452761988,
      "loss": 0.0,
      "num_input_tokens_seen": 6472864,
      "step": 23120
    },
    {
      "epoch": 256.94444444444446,
      "grad_norm": 1.3782401886430762e-08,
      "learning_rate": 0.11356440103838095,
      "loss": 0.0,
      "num_input_tokens_seen": 6474272,
      "step": 23125
    },
    {
      "epoch": 257.0,
      "grad_norm": 1.3088576444886257e-08,
      "learning_rate": 0.11350726316796922,
      "loss": 0.0,
      "num_input_tokens_seen": 6475680,
      "step": 23130
    },
    {
      "epoch": 257.05555555555554,
      "grad_norm": 1.1449081682712858e-08,
      "learning_rate": 0.11345013092519607,
      "loss": 0.0,
      "num_input_tokens_seen": 6477088,
      "step": 23135
    },
    {
      "epoch": 257.1111111111111,
      "grad_norm": 1.865805998590986e-08,
      "learning_rate": 0.11339300431887213,
      "loss": 0.0,
      "num_input_tokens_seen": 6478496,
      "step": 23140
    },
    {
      "epoch": 257.1666666666667,
      "grad_norm": 1.2378892577658007e-08,
      "learning_rate": 0.11333588335780687,
      "loss": 0.0,
      "num_input_tokens_seen": 6479904,
      "step": 23145
    },
    {
      "epoch": 257.22222222222223,
      "grad_norm": 1.4037436990577135e-08,
      "learning_rate": 0.11327876805080916,
      "loss": 0.0,
      "num_input_tokens_seen": 6481280,
      "step": 23150
    },
    {
      "epoch": 257.27777777777777,
      "grad_norm": 1.8383005340183445e-08,
      "learning_rate": 0.11322165840668696,
      "loss": 0.0,
      "num_input_tokens_seen": 6482688,
      "step": 23155
    },
    {
      "epoch": 257.3333333333333,
      "grad_norm": 1.6621449105969077e-08,
      "learning_rate": 0.11316455443424717,
      "loss": 0.0,
      "num_input_tokens_seen": 6484096,
      "step": 23160
    },
    {
      "epoch": 257.3888888888889,
      "grad_norm": 1.5490961402520043e-08,
      "learning_rate": 0.11310745614229603,
      "loss": 0.0,
      "num_input_tokens_seen": 6485504,
      "step": 23165
    },
    {
      "epoch": 257.44444444444446,
      "grad_norm": 2.6581286505233948e-08,
      "learning_rate": 0.1130503635396387,
      "loss": 0.0,
      "num_input_tokens_seen": 6486928,
      "step": 23170
    },
    {
      "epoch": 257.5,
      "grad_norm": 9.293599667614671e-09,
      "learning_rate": 0.11299327663507966,
      "loss": 0.0,
      "num_input_tokens_seen": 6488288,
      "step": 23175
    },
    {
      "epoch": 257.55555555555554,
      "grad_norm": 2.371639240550394e-08,
      "learning_rate": 0.11293619543742246,
      "loss": 0.0,
      "num_input_tokens_seen": 6489664,
      "step": 23180
    },
    {
      "epoch": 257.6111111111111,
      "grad_norm": 1.3347287719511769e-08,
      "learning_rate": 0.11287911995546965,
      "loss": 0.0,
      "num_input_tokens_seen": 6491088,
      "step": 23185
    },
    {
      "epoch": 257.6666666666667,
      "grad_norm": 1.683845596289757e-08,
      "learning_rate": 0.11282205019802308,
      "loss": 0.0,
      "num_input_tokens_seen": 6492464,
      "step": 23190
    },
    {
      "epoch": 257.72222222222223,
      "grad_norm": 1.3180487812292085e-08,
      "learning_rate": 0.11276498617388354,
      "loss": 0.0,
      "num_input_tokens_seen": 6493840,
      "step": 23195
    },
    {
      "epoch": 257.77777777777777,
      "grad_norm": 2.0214718787769925e-08,
      "learning_rate": 0.11270792789185109,
      "loss": 0.0,
      "num_input_tokens_seen": 6495280,
      "step": 23200
    },
    {
      "epoch": 257.77777777777777,
      "eval_loss": 1.5762995481491089,
      "eval_runtime": 1.1842,
      "eval_samples_per_second": 33.779,
      "eval_steps_per_second": 16.889,
      "num_input_tokens_seen": 6495280,
      "step": 23200
    },
    {
      "epoch": 257.8333333333333,
      "grad_norm": 1.4534167647184404e-08,
      "learning_rate": 0.11265087536072482,
      "loss": 0.0,
      "num_input_tokens_seen": 6496720,
      "step": 23205
    },
    {
      "epoch": 257.8888888888889,
      "grad_norm": 1.187596332385965e-08,
      "learning_rate": 0.11259382858930288,
      "loss": 0.0,
      "num_input_tokens_seen": 6498144,
      "step": 23210
    },
    {
      "epoch": 257.94444444444446,
      "grad_norm": 1.4469303089015284e-08,
      "learning_rate": 0.11253678758638262,
      "loss": 0.0,
      "num_input_tokens_seen": 6499504,
      "step": 23215
    },
    {
      "epoch": 258.0,
      "grad_norm": 1.4752455257394104e-08,
      "learning_rate": 0.11247975236076059,
      "loss": 0.0,
      "num_input_tokens_seen": 6500912,
      "step": 23220
    },
    {
      "epoch": 258.05555555555554,
      "grad_norm": 9.401459166724635e-09,
      "learning_rate": 0.11242272292123218,
      "loss": 0.0,
      "num_input_tokens_seen": 6502272,
      "step": 23225
    },
    {
      "epoch": 258.1111111111111,
      "grad_norm": 2.1381881154525217e-08,
      "learning_rate": 0.11236569927659217,
      "loss": 0.0,
      "num_input_tokens_seen": 6503632,
      "step": 23230
    },
    {
      "epoch": 258.1666666666667,
      "grad_norm": 1.5059923086369054e-08,
      "learning_rate": 0.11230868143563429,
      "loss": 0.0,
      "num_input_tokens_seen": 6505040,
      "step": 23235
    },
    {
      "epoch": 258.22222222222223,
      "grad_norm": 1.1277403011433762e-08,
      "learning_rate": 0.11225166940715131,
      "loss": 0.0,
      "num_input_tokens_seen": 6506448,
      "step": 23240
    },
    {
      "epoch": 258.27777777777777,
      "grad_norm": 2.3626354206385258e-08,
      "learning_rate": 0.11219466319993537,
      "loss": 0.0,
      "num_input_tokens_seen": 6507888,
      "step": 23245
    },
    {
      "epoch": 258.3333333333333,
      "grad_norm": 9.616401008827324e-09,
      "learning_rate": 0.11213766282277739,
      "loss": 0.0,
      "num_input_tokens_seen": 6509328,
      "step": 23250
    },
    {
      "epoch": 258.3888888888889,
      "grad_norm": 1.2537752169805572e-08,
      "learning_rate": 0.11208066828446761,
      "loss": 0.0,
      "num_input_tokens_seen": 6510704,
      "step": 23255
    },
    {
      "epoch": 258.44444444444446,
      "grad_norm": 1.5236242489891083e-08,
      "learning_rate": 0.11202367959379537,
      "loss": 0.0,
      "num_input_tokens_seen": 6512096,
      "step": 23260
    },
    {
      "epoch": 258.5,
      "grad_norm": 1.3046885349865533e-08,
      "learning_rate": 0.11196669675954894,
      "loss": 0.0,
      "num_input_tokens_seen": 6513456,
      "step": 23265
    },
    {
      "epoch": 258.55555555555554,
      "grad_norm": 1.23607275526183e-08,
      "learning_rate": 0.1119097197905158,
      "loss": 0.0,
      "num_input_tokens_seen": 6514896,
      "step": 23270
    },
    {
      "epoch": 258.6111111111111,
      "grad_norm": 1.8800330181534264e-08,
      "learning_rate": 0.11185274869548259,
      "loss": 0.0,
      "num_input_tokens_seen": 6516336,
      "step": 23275
    },
    {
      "epoch": 258.6666666666667,
      "grad_norm": 4.4424162126688316e-08,
      "learning_rate": 0.11179578348323486,
      "loss": 0.0,
      "num_input_tokens_seen": 6517744,
      "step": 23280
    },
    {
      "epoch": 258.72222222222223,
      "grad_norm": 1.765123514019251e-08,
      "learning_rate": 0.1117388241625575,
      "loss": 0.0,
      "num_input_tokens_seen": 6519120,
      "step": 23285
    },
    {
      "epoch": 258.77777777777777,
      "grad_norm": 2.7843510608249744e-08,
      "learning_rate": 0.11168187074223421,
      "loss": 0.0,
      "num_input_tokens_seen": 6520512,
      "step": 23290
    },
    {
      "epoch": 258.8333333333333,
      "grad_norm": 2.8264127038823972e-08,
      "learning_rate": 0.11162492323104796,
      "loss": 0.0,
      "num_input_tokens_seen": 6521904,
      "step": 23295
    },
    {
      "epoch": 258.8888888888889,
      "grad_norm": 7.430940307528999e-09,
      "learning_rate": 0.11156798163778091,
      "loss": 0.0,
      "num_input_tokens_seen": 6523296,
      "step": 23300
    },
    {
      "epoch": 258.94444444444446,
      "grad_norm": 1.174916786084168e-08,
      "learning_rate": 0.11151104597121399,
      "loss": 0.0,
      "num_input_tokens_seen": 6524672,
      "step": 23305
    },
    {
      "epoch": 259.0,
      "grad_norm": 1.3963502354386037e-08,
      "learning_rate": 0.11145411624012742,
      "loss": 0.0,
      "num_input_tokens_seen": 6526112,
      "step": 23310
    },
    {
      "epoch": 259.05555555555554,
      "grad_norm": 3.013035865251368e-08,
      "learning_rate": 0.11139719245330063,
      "loss": 0.0,
      "num_input_tokens_seen": 6527456,
      "step": 23315
    },
    {
      "epoch": 259.1111111111111,
      "grad_norm": 2.185381298147604e-08,
      "learning_rate": 0.11134027461951179,
      "loss": 0.0,
      "num_input_tokens_seen": 6528848,
      "step": 23320
    },
    {
      "epoch": 259.1666666666667,
      "grad_norm": 1.6980431283286634e-08,
      "learning_rate": 0.11128336274753849,
      "loss": 0.0,
      "num_input_tokens_seen": 6530288,
      "step": 23325
    },
    {
      "epoch": 259.22222222222223,
      "grad_norm": 1.2973572438568226e-08,
      "learning_rate": 0.11122645684615715,
      "loss": 0.0,
      "num_input_tokens_seen": 6531712,
      "step": 23330
    },
    {
      "epoch": 259.27777777777777,
      "grad_norm": 1.8117574995812902e-08,
      "learning_rate": 0.11116955692414345,
      "loss": 0.0,
      "num_input_tokens_seen": 6533104,
      "step": 23335
    },
    {
      "epoch": 259.3333333333333,
      "grad_norm": 2.3206316868140675e-08,
      "learning_rate": 0.11111266299027203,
      "loss": 0.0,
      "num_input_tokens_seen": 6534480,
      "step": 23340
    },
    {
      "epoch": 259.3888888888889,
      "grad_norm": 1.944317595814482e-08,
      "learning_rate": 0.11105577505331668,
      "loss": 0.0,
      "num_input_tokens_seen": 6535872,
      "step": 23345
    },
    {
      "epoch": 259.44444444444446,
      "grad_norm": 1.3215727179272108e-08,
      "learning_rate": 0.11099889312205018,
      "loss": 0.0,
      "num_input_tokens_seen": 6537264,
      "step": 23350
    },
    {
      "epoch": 259.5,
      "grad_norm": 1.9525809591414145e-07,
      "learning_rate": 0.11094201720524455,
      "loss": 0.0,
      "num_input_tokens_seen": 6538688,
      "step": 23355
    },
    {
      "epoch": 259.55555555555554,
      "grad_norm": 1.2701200979847727e-08,
      "learning_rate": 0.11088514731167064,
      "loss": 0.0,
      "num_input_tokens_seen": 6540096,
      "step": 23360
    },
    {
      "epoch": 259.6111111111111,
      "grad_norm": 9.00530139347211e-09,
      "learning_rate": 0.11082828345009862,
      "loss": 0.0,
      "num_input_tokens_seen": 6541504,
      "step": 23365
    },
    {
      "epoch": 259.6666666666667,
      "grad_norm": 1.828649764945567e-08,
      "learning_rate": 0.11077142562929748,
      "loss": 0.0,
      "num_input_tokens_seen": 6542912,
      "step": 23370
    },
    {
      "epoch": 259.72222222222223,
      "grad_norm": 1.0754683366087647e-08,
      "learning_rate": 0.11071457385803554,
      "loss": 0.0,
      "num_input_tokens_seen": 6544336,
      "step": 23375
    },
    {
      "epoch": 259.77777777777777,
      "grad_norm": 1.294921236905111e-08,
      "learning_rate": 0.11065772814508001,
      "loss": 0.0,
      "num_input_tokens_seen": 6545696,
      "step": 23380
    },
    {
      "epoch": 259.8333333333333,
      "grad_norm": 1.4018742611199286e-08,
      "learning_rate": 0.11060088849919715,
      "loss": 0.0,
      "num_input_tokens_seen": 6547024,
      "step": 23385
    },
    {
      "epoch": 259.8888888888889,
      "grad_norm": 1.0387427806790583e-08,
      "learning_rate": 0.11054405492915244,
      "loss": 0.0,
      "num_input_tokens_seen": 6548400,
      "step": 23390
    },
    {
      "epoch": 259.94444444444446,
      "grad_norm": 1.734030874445125e-08,
      "learning_rate": 0.11048722744371031,
      "loss": 0.0,
      "num_input_tokens_seen": 6549824,
      "step": 23395
    },
    {
      "epoch": 260.0,
      "grad_norm": 1.1636701380268732e-08,
      "learning_rate": 0.1104304060516342,
      "loss": 0.0,
      "num_input_tokens_seen": 6551264,
      "step": 23400
    },
    {
      "epoch": 260.0,
      "eval_loss": 1.5500491857528687,
      "eval_runtime": 1.1812,
      "eval_samples_per_second": 33.864,
      "eval_steps_per_second": 16.932,
      "num_input_tokens_seen": 6551264,
      "step": 23400
    },
    {
      "epoch": 260.05555555555554,
      "grad_norm": 2.0792660038182476e-08,
      "learning_rate": 0.11037359076168682,
      "loss": 0.0,
      "num_input_tokens_seen": 6552720,
      "step": 23405
    },
    {
      "epoch": 260.1111111111111,
      "grad_norm": 2.0527334498865457e-08,
      "learning_rate": 0.11031678158262966,
      "loss": 0.0,
      "num_input_tokens_seen": 6554144,
      "step": 23410
    },
    {
      "epoch": 260.1666666666667,
      "grad_norm": 2.644287455666472e-08,
      "learning_rate": 0.11025997852322349,
      "loss": 0.0,
      "num_input_tokens_seen": 6555504,
      "step": 23415
    },
    {
      "epoch": 260.22222222222223,
      "grad_norm": 2.7962572701767385e-08,
      "learning_rate": 0.11020318159222807,
      "loss": 0.0,
      "num_input_tokens_seen": 6556960,
      "step": 23420
    },
    {
      "epoch": 260.27777777777777,
      "grad_norm": 1.168505576742973e-07,
      "learning_rate": 0.1101463907984021,
      "loss": 0.0,
      "num_input_tokens_seen": 6558336,
      "step": 23425
    },
    {
      "epoch": 260.3333333333333,
      "grad_norm": 1.4315734375713873e-08,
      "learning_rate": 0.11008960615050352,
      "loss": 0.0,
      "num_input_tokens_seen": 6559744,
      "step": 23430
    },
    {
      "epoch": 260.3888888888889,
      "grad_norm": 1.8396725920410972e-08,
      "learning_rate": 0.11003282765728925,
      "loss": 0.0,
      "num_input_tokens_seen": 6561152,
      "step": 23435
    },
    {
      "epoch": 260.44444444444446,
      "grad_norm": 1.1173806768738359e-08,
      "learning_rate": 0.10997605532751518,
      "loss": 0.0,
      "num_input_tokens_seen": 6562544,
      "step": 23440
    },
    {
      "epoch": 260.5,
      "grad_norm": 1.1843632741204146e-08,
      "learning_rate": 0.1099192891699364,
      "loss": 0.0,
      "num_input_tokens_seen": 6563888,
      "step": 23445
    },
    {
      "epoch": 260.55555555555554,
      "grad_norm": 1.5890780247218572e-08,
      "learning_rate": 0.10986252919330687,
      "loss": 0.0,
      "num_input_tokens_seen": 6565264,
      "step": 23450
    },
    {
      "epoch": 260.6111111111111,
      "grad_norm": 1.4044489127229554e-08,
      "learning_rate": 0.10980577540637973,
      "loss": 0.0,
      "num_input_tokens_seen": 6566656,
      "step": 23455
    },
    {
      "epoch": 260.6666666666667,
      "grad_norm": 1.7549396602589695e-08,
      "learning_rate": 0.10974902781790719,
      "loss": 0.0,
      "num_input_tokens_seen": 6568048,
      "step": 23460
    },
    {
      "epoch": 260.72222222222223,
      "grad_norm": 1.0809991124460794e-08,
      "learning_rate": 0.10969228643664032,
      "loss": 0.0,
      "num_input_tokens_seen": 6569472,
      "step": 23465
    },
    {
      "epoch": 260.77777777777777,
      "grad_norm": 1.2311430097611265e-08,
      "learning_rate": 0.10963555127132942,
      "loss": 0.0,
      "num_input_tokens_seen": 6570880,
      "step": 23470
    },
    {
      "epoch": 260.8333333333333,
      "grad_norm": 1.8225218667566878e-08,
      "learning_rate": 0.10957882233072382,
      "loss": 0.0,
      "num_input_tokens_seen": 6572304,
      "step": 23475
    },
    {
      "epoch": 260.8888888888889,
      "grad_norm": 2.257083764334311e-08,
      "learning_rate": 0.10952209962357176,
      "loss": 0.0,
      "num_input_tokens_seen": 6573728,
      "step": 23480
    },
    {
      "epoch": 260.94444444444446,
      "grad_norm": 1.1820953993435523e-08,
      "learning_rate": 0.10946538315862062,
      "loss": 0.0,
      "num_input_tokens_seen": 6575120,
      "step": 23485
    },
    {
      "epoch": 261.0,
      "grad_norm": 1.5040569678603788e-08,
      "learning_rate": 0.10940867294461679,
      "loss": 0.0,
      "num_input_tokens_seen": 6576512,
      "step": 23490
    },
    {
      "epoch": 261.05555555555554,
      "grad_norm": 2.985126457133447e-08,
      "learning_rate": 0.10935196899030565,
      "loss": 0.0,
      "num_input_tokens_seen": 6577920,
      "step": 23495
    },
    {
      "epoch": 261.1111111111111,
      "grad_norm": 1.622204059970045e-08,
      "learning_rate": 0.10929527130443177,
      "loss": 0.0,
      "num_input_tokens_seen": 6579312,
      "step": 23500
    },
    {
      "epoch": 261.1666666666667,
      "grad_norm": 1.929165094338714e-08,
      "learning_rate": 0.1092385798957385,
      "loss": 0.0,
      "num_input_tokens_seen": 6580688,
      "step": 23505
    },
    {
      "epoch": 261.22222222222223,
      "grad_norm": 2.1176662201582985e-08,
      "learning_rate": 0.10918189477296848,
      "loss": 0.0,
      "num_input_tokens_seen": 6582080,
      "step": 23510
    },
    {
      "epoch": 261.27777777777777,
      "grad_norm": 9.478201334900405e-09,
      "learning_rate": 0.1091252159448633,
      "loss": 0.0,
      "num_input_tokens_seen": 6583504,
      "step": 23515
    },
    {
      "epoch": 261.3333333333333,
      "grad_norm": 8.5288887063939e-09,
      "learning_rate": 0.10906854342016345,
      "loss": 0.0,
      "num_input_tokens_seen": 6584928,
      "step": 23520
    },
    {
      "epoch": 261.3888888888889,
      "grad_norm": 2.012342115165211e-08,
      "learning_rate": 0.10901187720760858,
      "loss": 0.0,
      "num_input_tokens_seen": 6586336,
      "step": 23525
    },
    {
      "epoch": 261.44444444444446,
      "grad_norm": 1.0745424994240693e-08,
      "learning_rate": 0.10895521731593734,
      "loss": 0.0,
      "num_input_tokens_seen": 6587760,
      "step": 23530
    },
    {
      "epoch": 261.5,
      "grad_norm": 2.4790276498265484e-08,
      "learning_rate": 0.10889856375388733,
      "loss": 0.0,
      "num_input_tokens_seen": 6589168,
      "step": 23535
    },
    {
      "epoch": 261.55555555555554,
      "grad_norm": 3.923072711131681e-08,
      "learning_rate": 0.1088419165301954,
      "loss": 0.0,
      "num_input_tokens_seen": 6590544,
      "step": 23540
    },
    {
      "epoch": 261.6111111111111,
      "grad_norm": 3.472081289146445e-08,
      "learning_rate": 0.1087852756535971,
      "loss": 0.0,
      "num_input_tokens_seen": 6591968,
      "step": 23545
    },
    {
      "epoch": 261.6666666666667,
      "grad_norm": 3.609491727729619e-08,
      "learning_rate": 0.10872864113282725,
      "loss": 0.0,
      "num_input_tokens_seen": 6593440,
      "step": 23550
    },
    {
      "epoch": 261.72222222222223,
      "grad_norm": 2.2353841444555655e-08,
      "learning_rate": 0.10867201297661958,
      "loss": 0.0,
      "num_input_tokens_seen": 6594816,
      "step": 23555
    },
    {
      "epoch": 261.77777777777777,
      "grad_norm": 4.271137399314284e-08,
      "learning_rate": 0.10861539119370689,
      "loss": 0.0,
      "num_input_tokens_seen": 6596192,
      "step": 23560
    },
    {
      "epoch": 261.8333333333333,
      "grad_norm": 2.246223118618218e-07,
      "learning_rate": 0.10855877579282096,
      "loss": 0.0,
      "num_input_tokens_seen": 6597600,
      "step": 23565
    },
    {
      "epoch": 261.8888888888889,
      "grad_norm": 1.8606893803507774e-08,
      "learning_rate": 0.10850216678269252,
      "loss": 0.0,
      "num_input_tokens_seen": 6598976,
      "step": 23570
    },
    {
      "epoch": 261.94444444444446,
      "grad_norm": 1.0610645695408039e-08,
      "learning_rate": 0.10844556417205146,
      "loss": 0.0,
      "num_input_tokens_seen": 6600368,
      "step": 23575
    },
    {
      "epoch": 262.0,
      "grad_norm": 6.287943499216908e-09,
      "learning_rate": 0.10838896796962669,
      "loss": 0.0,
      "num_input_tokens_seen": 6601760,
      "step": 23580
    },
    {
      "epoch": 262.05555555555554,
      "grad_norm": 2.221639938682074e-08,
      "learning_rate": 0.1083323781841459,
      "loss": 0.0,
      "num_input_tokens_seen": 6603152,
      "step": 23585
    },
    {
      "epoch": 262.1111111111111,
      "grad_norm": 2.6406922870592098e-08,
      "learning_rate": 0.10827579482433607,
      "loss": 0.0,
      "num_input_tokens_seen": 6604592,
      "step": 23590
    },
    {
      "epoch": 262.1666666666667,
      "grad_norm": 8.41402947315828e-09,
      "learning_rate": 0.10821921789892304,
      "loss": 0.0,
      "num_input_tokens_seen": 6606032,
      "step": 23595
    },
    {
      "epoch": 262.22222222222223,
      "grad_norm": 9.074542894893511e-09,
      "learning_rate": 0.10816264741663158,
      "loss": 0.0,
      "num_input_tokens_seen": 6607424,
      "step": 23600
    },
    {
      "epoch": 262.22222222222223,
      "eval_loss": 1.5696380138397217,
      "eval_runtime": 1.1834,
      "eval_samples_per_second": 33.802,
      "eval_steps_per_second": 16.901,
      "num_input_tokens_seen": 6607424,
      "step": 23600
    },
    {
      "epoch": 262.27777777777777,
      "grad_norm": 5.031446814740548e-09,
      "learning_rate": 0.10810608338618573,
      "loss": 0.0,
      "num_input_tokens_seen": 6608768,
      "step": 23605
    },
    {
      "epoch": 262.3333333333333,
      "grad_norm": 8.903415782413049e-09,
      "learning_rate": 0.10804952581630821,
      "loss": 0.0,
      "num_input_tokens_seen": 6610176,
      "step": 23610
    },
    {
      "epoch": 262.3888888888889,
      "grad_norm": 2.7095918397890273e-08,
      "learning_rate": 0.10799297471572102,
      "loss": 0.0,
      "num_input_tokens_seen": 6611552,
      "step": 23615
    },
    {
      "epoch": 262.44444444444446,
      "grad_norm": 3.985706342746198e-08,
      "learning_rate": 0.10793643009314507,
      "loss": 0.0,
      "num_input_tokens_seen": 6612944,
      "step": 23620
    },
    {
      "epoch": 262.5,
      "grad_norm": 1.7180203926159265e-08,
      "learning_rate": 0.10787989195730015,
      "loss": 0.0,
      "num_input_tokens_seen": 6614272,
      "step": 23625
    },
    {
      "epoch": 262.55555555555554,
      "grad_norm": 2.1130066585328677e-08,
      "learning_rate": 0.10782336031690525,
      "loss": 0.0,
      "num_input_tokens_seen": 6615680,
      "step": 23630
    },
    {
      "epoch": 262.6111111111111,
      "grad_norm": 1.421024364844925e-08,
      "learning_rate": 0.10776683518067821,
      "loss": 0.0,
      "num_input_tokens_seen": 6617072,
      "step": 23635
    },
    {
      "epoch": 262.6666666666667,
      "grad_norm": 3.5440134382724864e-08,
      "learning_rate": 0.10771031655733587,
      "loss": 0.0,
      "num_input_tokens_seen": 6618464,
      "step": 23640
    },
    {
      "epoch": 262.72222222222223,
      "grad_norm": 2.7586480655372725e-08,
      "learning_rate": 0.10765380445559422,
      "loss": 0.0,
      "num_input_tokens_seen": 6619888,
      "step": 23645
    },
    {
      "epoch": 262.77777777777777,
      "grad_norm": 2.1645226411237672e-07,
      "learning_rate": 0.10759729888416801,
      "loss": 0.0,
      "num_input_tokens_seen": 6621296,
      "step": 23650
    },
    {
      "epoch": 262.8333333333333,
      "grad_norm": 2.625811390544186e-08,
      "learning_rate": 0.10754079985177119,
      "loss": 0.0,
      "num_input_tokens_seen": 6622704,
      "step": 23655
    },
    {
      "epoch": 262.8888888888889,
      "grad_norm": 1.9461198874637375e-08,
      "learning_rate": 0.10748430736711667,
      "loss": 0.0,
      "num_input_tokens_seen": 6624112,
      "step": 23660
    },
    {
      "epoch": 262.94444444444446,
      "grad_norm": 4.5559261252492433e-08,
      "learning_rate": 0.10742782143891623,
      "loss": 0.0,
      "num_input_tokens_seen": 6625504,
      "step": 23665
    },
    {
      "epoch": 263.0,
      "grad_norm": 2.41117898980292e-08,
      "learning_rate": 0.10737134207588069,
      "loss": 0.0,
      "num_input_tokens_seen": 6626880,
      "step": 23670
    },
    {
      "epoch": 263.05555555555554,
      "grad_norm": 4.373929485268491e-08,
      "learning_rate": 0.10731486928671992,
      "loss": 0.0,
      "num_input_tokens_seen": 6628288,
      "step": 23675
    },
    {
      "epoch": 263.1111111111111,
      "grad_norm": 1.8732061235482433e-08,
      "learning_rate": 0.10725840308014269,
      "loss": 0.0,
      "num_input_tokens_seen": 6629648,
      "step": 23680
    },
    {
      "epoch": 263.1666666666667,
      "grad_norm": 4.229239891628822e-08,
      "learning_rate": 0.10720194346485688,
      "loss": 0.0,
      "num_input_tokens_seen": 6631040,
      "step": 23685
    },
    {
      "epoch": 263.22222222222223,
      "grad_norm": 2.750910610416213e-08,
      "learning_rate": 0.10714549044956918,
      "loss": 0.0,
      "num_input_tokens_seen": 6632448,
      "step": 23690
    },
    {
      "epoch": 263.27777777777777,
      "grad_norm": 2.5740050091371813e-08,
      "learning_rate": 0.10708904404298542,
      "loss": 0.0,
      "num_input_tokens_seen": 6633824,
      "step": 23695
    },
    {
      "epoch": 263.3333333333333,
      "grad_norm": 3.535433990009551e-08,
      "learning_rate": 0.1070326042538103,
      "loss": 0.0,
      "num_input_tokens_seen": 6635280,
      "step": 23700
    },
    {
      "epoch": 263.3888888888889,
      "grad_norm": 4.127921471308582e-08,
      "learning_rate": 0.10697617109074758,
      "loss": 0.0,
      "num_input_tokens_seen": 6636656,
      "step": 23705
    },
    {
      "epoch": 263.44444444444446,
      "grad_norm": 1.8916930244472496e-08,
      "learning_rate": 0.10691974456249999,
      "loss": 0.0,
      "num_input_tokens_seen": 6638048,
      "step": 23710
    },
    {
      "epoch": 263.5,
      "grad_norm": 2.055996972671892e-08,
      "learning_rate": 0.10686332467776909,
      "loss": 0.0,
      "num_input_tokens_seen": 6639488,
      "step": 23715
    },
    {
      "epoch": 263.55555555555554,
      "grad_norm": 1.4270707282548756e-08,
      "learning_rate": 0.10680691144525563,
      "loss": 0.0,
      "num_input_tokens_seen": 6640880,
      "step": 23720
    },
    {
      "epoch": 263.6111111111111,
      "grad_norm": 1.1614797124082088e-08,
      "learning_rate": 0.10675050487365928,
      "loss": 0.0,
      "num_input_tokens_seen": 6642288,
      "step": 23725
    },
    {
      "epoch": 263.6666666666667,
      "grad_norm": 1.3696953793385092e-08,
      "learning_rate": 0.10669410497167851,
      "loss": 0.0,
      "num_input_tokens_seen": 6643664,
      "step": 23730
    },
    {
      "epoch": 263.72222222222223,
      "grad_norm": 3.854860963770079e-08,
      "learning_rate": 0.10663771174801102,
      "loss": 0.0,
      "num_input_tokens_seen": 6645056,
      "step": 23735
    },
    {
      "epoch": 263.77777777777777,
      "grad_norm": 2.7665620905281685e-07,
      "learning_rate": 0.10658132521135329,
      "loss": 0.0,
      "num_input_tokens_seen": 6646448,
      "step": 23740
    },
    {
      "epoch": 263.8333333333333,
      "grad_norm": 1.8919752875490303e-08,
      "learning_rate": 0.10652494537040084,
      "loss": 0.0,
      "num_input_tokens_seen": 6647840,
      "step": 23745
    },
    {
      "epoch": 263.8888888888889,
      "grad_norm": 3.1983582005068456e-08,
      "learning_rate": 0.1064685722338482,
      "loss": 0.0,
      "num_input_tokens_seen": 6649248,
      "step": 23750
    },
    {
      "epoch": 263.94444444444446,
      "grad_norm": 3.7971663147118306e-08,
      "learning_rate": 0.10641220581038871,
      "loss": 0.0,
      "num_input_tokens_seen": 6650688,
      "step": 23755
    },
    {
      "epoch": 264.0,
      "grad_norm": 8.79324275615545e-08,
      "learning_rate": 0.10635584610871483,
      "loss": 0.0,
      "num_input_tokens_seen": 6652080,
      "step": 23760
    },
    {
      "epoch": 264.05555555555554,
      "grad_norm": 2.735808024567632e-08,
      "learning_rate": 0.10629949313751803,
      "loss": 0.0,
      "num_input_tokens_seen": 6653472,
      "step": 23765
    },
    {
      "epoch": 264.1111111111111,
      "grad_norm": 3.516443669582259e-08,
      "learning_rate": 0.10624314690548849,
      "loss": 0.0,
      "num_input_tokens_seen": 6654880,
      "step": 23770
    },
    {
      "epoch": 264.1666666666667,
      "grad_norm": 7.554649350538511e-09,
      "learning_rate": 0.1061868074213156,
      "loss": 0.0,
      "num_input_tokens_seen": 6656256,
      "step": 23775
    },
    {
      "epoch": 264.22222222222223,
      "grad_norm": 2.062820136927712e-08,
      "learning_rate": 0.10613047469368765,
      "loss": 0.0,
      "num_input_tokens_seen": 6657664,
      "step": 23780
    },
    {
      "epoch": 264.27777777777777,
      "grad_norm": 5.892865928558422e-08,
      "learning_rate": 0.10607414873129171,
      "loss": 0.0,
      "num_input_tokens_seen": 6659040,
      "step": 23785
    },
    {
      "epoch": 264.3333333333333,
      "grad_norm": 1.587325293428421e-08,
      "learning_rate": 0.10601782954281413,
      "loss": 0.0,
      "num_input_tokens_seen": 6660384,
      "step": 23790
    },
    {
      "epoch": 264.3888888888889,
      "grad_norm": 1.606117763230941e-07,
      "learning_rate": 0.1059615171369399,
      "loss": 0.0,
      "num_input_tokens_seen": 6661792,
      "step": 23795
    },
    {
      "epoch": 264.44444444444446,
      "grad_norm": 1.8037653148894606e-08,
      "learning_rate": 0.10590521152235312,
      "loss": 0.0,
      "num_input_tokens_seen": 6663168,
      "step": 23800
    },
    {
      "epoch": 264.44444444444446,
      "eval_loss": 1.5224888324737549,
      "eval_runtime": 1.1843,
      "eval_samples_per_second": 33.774,
      "eval_steps_per_second": 16.887,
      "num_input_tokens_seen": 6663168,
      "step": 23800
    },
    {
      "epoch": 264.5,
      "grad_norm": 3.1584896476033464e-08,
      "learning_rate": 0.1058489127077369,
      "loss": 0.0,
      "num_input_tokens_seen": 6664608,
      "step": 23805
    },
    {
      "epoch": 264.55555555555554,
      "grad_norm": 4.115236151847057e-08,
      "learning_rate": 0.1057926207017732,
      "loss": 0.0,
      "num_input_tokens_seen": 6665952,
      "step": 23810
    },
    {
      "epoch": 264.6111111111111,
      "grad_norm": 1.6167907901376566e-08,
      "learning_rate": 0.10573633551314285,
      "loss": 0.0,
      "num_input_tokens_seen": 6667376,
      "step": 23815
    },
    {
      "epoch": 264.6666666666667,
      "grad_norm": 1.07660200754367e-08,
      "learning_rate": 0.1056800571505259,
      "loss": 0.0,
      "num_input_tokens_seen": 6668784,
      "step": 23820
    },
    {
      "epoch": 264.72222222222223,
      "grad_norm": 9.8073101639784e-08,
      "learning_rate": 0.10562378562260105,
      "loss": 0.0,
      "num_input_tokens_seen": 6670176,
      "step": 23825
    },
    {
      "epoch": 264.77777777777777,
      "grad_norm": 1.070082955578755e-08,
      "learning_rate": 0.10556752093804615,
      "loss": 0.0,
      "num_input_tokens_seen": 6671584,
      "step": 23830
    },
    {
      "epoch": 264.8333333333333,
      "grad_norm": 5.2756359281147525e-08,
      "learning_rate": 0.10551126310553786,
      "loss": 0.0,
      "num_input_tokens_seen": 6673024,
      "step": 23835
    },
    {
      "epoch": 264.8888888888889,
      "grad_norm": 1.896347967544898e-08,
      "learning_rate": 0.10545501213375187,
      "loss": 0.0,
      "num_input_tokens_seen": 6674448,
      "step": 23840
    },
    {
      "epoch": 264.94444444444446,
      "grad_norm": 6.97658180115468e-08,
      "learning_rate": 0.10539876803136287,
      "loss": 0.0,
      "num_input_tokens_seen": 6675840,
      "step": 23845
    },
    {
      "epoch": 265.0,
      "grad_norm": 2.669495557938717e-08,
      "learning_rate": 0.10534253080704428,
      "loss": 0.0,
      "num_input_tokens_seen": 6677248,
      "step": 23850
    },
    {
      "epoch": 265.05555555555554,
      "grad_norm": 1.0831397112553987e-08,
      "learning_rate": 0.10528630046946862,
      "loss": 0.0,
      "num_input_tokens_seen": 6678608,
      "step": 23855
    },
    {
      "epoch": 265.1111111111111,
      "grad_norm": 3.321275343637353e-08,
      "learning_rate": 0.1052300770273074,
      "loss": 0.0,
      "num_input_tokens_seen": 6680000,
      "step": 23860
    },
    {
      "epoch": 265.1666666666667,
      "grad_norm": 5.8905801125774815e-08,
      "learning_rate": 0.10517386048923086,
      "loss": 0.0,
      "num_input_tokens_seen": 6681376,
      "step": 23865
    },
    {
      "epoch": 265.22222222222223,
      "grad_norm": 2.6252234164303445e-08,
      "learning_rate": 0.10511765086390841,
      "loss": 0.0,
      "num_input_tokens_seen": 6682768,
      "step": 23870
    },
    {
      "epoch": 265.27777777777777,
      "grad_norm": 1.9203191925498686e-08,
      "learning_rate": 0.10506144816000816,
      "loss": 0.0,
      "num_input_tokens_seen": 6684208,
      "step": 23875
    },
    {
      "epoch": 265.3333333333333,
      "grad_norm": 4.108352058551645e-08,
      "learning_rate": 0.10500525238619736,
      "loss": 0.0,
      "num_input_tokens_seen": 6685632,
      "step": 23880
    },
    {
      "epoch": 265.3888888888889,
      "grad_norm": 2.1004941785918163e-08,
      "learning_rate": 0.10494906355114209,
      "loss": 0.0,
      "num_input_tokens_seen": 6687040,
      "step": 23885
    },
    {
      "epoch": 265.44444444444446,
      "grad_norm": 1.8397718903884197e-08,
      "learning_rate": 0.10489288166350737,
      "loss": 0.0,
      "num_input_tokens_seen": 6688480,
      "step": 23890
    },
    {
      "epoch": 265.5,
      "grad_norm": 2.622215511394188e-08,
      "learning_rate": 0.10483670673195711,
      "loss": 0.0,
      "num_input_tokens_seen": 6689872,
      "step": 23895
    },
    {
      "epoch": 265.55555555555554,
      "grad_norm": 2.7250345979723534e-08,
      "learning_rate": 0.10478053876515431,
      "loss": 0.0,
      "num_input_tokens_seen": 6691280,
      "step": 23900
    },
    {
      "epoch": 265.6111111111111,
      "grad_norm": 3.870428599839215e-08,
      "learning_rate": 0.10472437777176061,
      "loss": 0.0,
      "num_input_tokens_seen": 6692640,
      "step": 23905
    },
    {
      "epoch": 265.6666666666667,
      "grad_norm": 8.45673255867041e-08,
      "learning_rate": 0.1046682237604369,
      "loss": 0.0,
      "num_input_tokens_seen": 6694048,
      "step": 23910
    },
    {
      "epoch": 265.72222222222223,
      "grad_norm": 1.955403483577811e-08,
      "learning_rate": 0.1046120767398427,
      "loss": 0.0,
      "num_input_tokens_seen": 6695440,
      "step": 23915
    },
    {
      "epoch": 265.77777777777777,
      "grad_norm": 1.5240463113741498e-08,
      "learning_rate": 0.10455593671863667,
      "loss": 0.0,
      "num_input_tokens_seen": 6696832,
      "step": 23920
    },
    {
      "epoch": 265.8333333333333,
      "grad_norm": 2.987809111232309e-08,
      "learning_rate": 0.1044998037054763,
      "loss": 0.0,
      "num_input_tokens_seen": 6698288,
      "step": 23925
    },
    {
      "epoch": 265.8888888888889,
      "grad_norm": 1.6255878421134184e-08,
      "learning_rate": 0.10444367770901794,
      "loss": 0.0,
      "num_input_tokens_seen": 6699712,
      "step": 23930
    },
    {
      "epoch": 265.94444444444446,
      "grad_norm": 2.036021840012836e-08,
      "learning_rate": 0.10438755873791698,
      "loss": 0.0,
      "num_input_tokens_seen": 6701120,
      "step": 23935
    },
    {
      "epoch": 266.0,
      "grad_norm": 2.3151692118972278e-08,
      "learning_rate": 0.10433144680082775,
      "loss": 0.0,
      "num_input_tokens_seen": 6702544,
      "step": 23940
    },
    {
      "epoch": 266.05555555555554,
      "grad_norm": 2.5748812859660575e-08,
      "learning_rate": 0.10427534190640322,
      "loss": 0.0,
      "num_input_tokens_seen": 6703952,
      "step": 23945
    },
    {
      "epoch": 266.1111111111111,
      "grad_norm": 2.7407132563439518e-08,
      "learning_rate": 0.10421924406329568,
      "loss": 0.0,
      "num_input_tokens_seen": 6705360,
      "step": 23950
    },
    {
      "epoch": 266.1666666666667,
      "grad_norm": 2.0092109309644002e-08,
      "learning_rate": 0.10416315328015598,
      "loss": 0.0,
      "num_input_tokens_seen": 6706752,
      "step": 23955
    },
    {
      "epoch": 266.22222222222223,
      "grad_norm": 1.2020551665159473e-08,
      "learning_rate": 0.10410706956563402,
      "loss": 0.0,
      "num_input_tokens_seen": 6708176,
      "step": 23960
    },
    {
      "epoch": 266.27777777777777,
      "grad_norm": 2.5872312292563038e-08,
      "learning_rate": 0.10405099292837874,
      "loss": 0.0,
      "num_input_tokens_seen": 6709584,
      "step": 23965
    },
    {
      "epoch": 266.3333333333333,
      "grad_norm": 1.8035349214073904e-08,
      "learning_rate": 0.10399492337703771,
      "loss": 0.0,
      "num_input_tokens_seen": 6710912,
      "step": 23970
    },
    {
      "epoch": 266.3888888888889,
      "grad_norm": 3.8724920159438625e-08,
      "learning_rate": 0.10393886092025764,
      "loss": 0.0,
      "num_input_tokens_seen": 6712272,
      "step": 23975
    },
    {
      "epoch": 266.44444444444446,
      "grad_norm": 9.239562004381696e-09,
      "learning_rate": 0.10388280556668412,
      "loss": 0.0,
      "num_input_tokens_seen": 6713648,
      "step": 23980
    },
    {
      "epoch": 266.5,
      "grad_norm": 1.022614313228587e-07,
      "learning_rate": 0.10382675732496145,
      "loss": 0.0,
      "num_input_tokens_seen": 6715040,
      "step": 23985
    },
    {
      "epoch": 266.55555555555554,
      "grad_norm": 1.0053243570951054e-08,
      "learning_rate": 0.10377071620373311,
      "loss": 0.0,
      "num_input_tokens_seen": 6716432,
      "step": 23990
    },
    {
      "epoch": 266.6111111111111,
      "grad_norm": 3.829158146118061e-08,
      "learning_rate": 0.10371468221164128,
      "loss": 0.0,
      "num_input_tokens_seen": 6717808,
      "step": 23995
    },
    {
      "epoch": 266.6666666666667,
      "grad_norm": 7.585522610042972e-08,
      "learning_rate": 0.10365865535732706,
      "loss": 0.0,
      "num_input_tokens_seen": 6719216,
      "step": 24000
    },
    {
      "epoch": 266.6666666666667,
      "eval_loss": 1.5553686618804932,
      "eval_runtime": 1.1824,
      "eval_samples_per_second": 33.83,
      "eval_steps_per_second": 16.915,
      "num_input_tokens_seen": 6719216,
      "step": 24000
    },
    {
      "epoch": 266.72222222222223,
      "grad_norm": 6.495419313523598e-09,
      "learning_rate": 0.10360263564943062,
      "loss": 0.0,
      "num_input_tokens_seen": 6720592,
      "step": 24005
    },
    {
      "epoch": 266.77777777777777,
      "grad_norm": 1.3721853875381385e-08,
      "learning_rate": 0.10354662309659075,
      "loss": 0.0,
      "num_input_tokens_seen": 6722032,
      "step": 24010
    },
    {
      "epoch": 266.8333333333333,
      "grad_norm": 1.4044538865221057e-08,
      "learning_rate": 0.10349061770744537,
      "loss": 0.0,
      "num_input_tokens_seen": 6723456,
      "step": 24015
    },
    {
      "epoch": 266.8888888888889,
      "grad_norm": 1.1879409456128087e-08,
      "learning_rate": 0.10343461949063128,
      "loss": 0.0,
      "num_input_tokens_seen": 6724880,
      "step": 24020
    },
    {
      "epoch": 266.94444444444446,
      "grad_norm": 2.4164855005892605e-08,
      "learning_rate": 0.103378628454784,
      "loss": 0.0,
      "num_input_tokens_seen": 6726304,
      "step": 24025
    },
    {
      "epoch": 267.0,
      "grad_norm": 1.3784221764012727e-08,
      "learning_rate": 0.10332264460853811,
      "loss": 0.0,
      "num_input_tokens_seen": 6727728,
      "step": 24030
    },
    {
      "epoch": 267.05555555555554,
      "grad_norm": 3.6705959161054125e-08,
      "learning_rate": 0.10326666796052701,
      "loss": 0.0,
      "num_input_tokens_seen": 6729120,
      "step": 24035
    },
    {
      "epoch": 267.1111111111111,
      "grad_norm": 4.200050440772429e-08,
      "learning_rate": 0.10321069851938296,
      "loss": 0.0,
      "num_input_tokens_seen": 6730560,
      "step": 24040
    },
    {
      "epoch": 267.1666666666667,
      "grad_norm": 1.5224294713789277e-08,
      "learning_rate": 0.10315473629373724,
      "loss": 0.0,
      "num_input_tokens_seen": 6731952,
      "step": 24045
    },
    {
      "epoch": 267.22222222222223,
      "grad_norm": 1.870404986448193e-08,
      "learning_rate": 0.10309878129221982,
      "loss": 0.0,
      "num_input_tokens_seen": 6733344,
      "step": 24050
    },
    {
      "epoch": 267.27777777777777,
      "grad_norm": 3.05354070917474e-08,
      "learning_rate": 0.10304283352345973,
      "loss": 0.0,
      "num_input_tokens_seen": 6734752,
      "step": 24055
    },
    {
      "epoch": 267.3333333333333,
      "grad_norm": 1.1006516587031001e-07,
      "learning_rate": 0.10298689299608486,
      "loss": 0.0,
      "num_input_tokens_seen": 6736176,
      "step": 24060
    },
    {
      "epoch": 267.3888888888889,
      "grad_norm": 4.60437377114431e-08,
      "learning_rate": 0.10293095971872188,
      "loss": 0.0,
      "num_input_tokens_seen": 6737552,
      "step": 24065
    },
    {
      "epoch": 267.44444444444446,
      "grad_norm": 3.629039468933115e-08,
      "learning_rate": 0.10287503369999645,
      "loss": 0.0,
      "num_input_tokens_seen": 6738944,
      "step": 24070
    },
    {
      "epoch": 267.5,
      "grad_norm": 1.4444890616971406e-08,
      "learning_rate": 0.10281911494853295,
      "loss": 0.0,
      "num_input_tokens_seen": 6740352,
      "step": 24075
    },
    {
      "epoch": 267.55555555555554,
      "grad_norm": 2.0795805966145053e-08,
      "learning_rate": 0.10276320347295485,
      "loss": 0.0,
      "num_input_tokens_seen": 6741760,
      "step": 24080
    },
    {
      "epoch": 267.6111111111111,
      "grad_norm": 1.8039401084024576e-08,
      "learning_rate": 0.10270729928188446,
      "loss": 0.0,
      "num_input_tokens_seen": 6743152,
      "step": 24085
    },
    {
      "epoch": 267.6666666666667,
      "grad_norm": 3.968315098745734e-08,
      "learning_rate": 0.10265140238394276,
      "loss": 0.0,
      "num_input_tokens_seen": 6744608,
      "step": 24090
    },
    {
      "epoch": 267.72222222222223,
      "grad_norm": 3.511865998007124e-08,
      "learning_rate": 0.10259551278774988,
      "loss": 0.0,
      "num_input_tokens_seen": 6746016,
      "step": 24095
    },
    {
      "epoch": 267.77777777777777,
      "grad_norm": 5.960641402680267e-08,
      "learning_rate": 0.10253963050192462,
      "loss": 0.0,
      "num_input_tokens_seen": 6747344,
      "step": 24100
    },
    {
      "epoch": 267.8333333333333,
      "grad_norm": 2.6988223211787954e-08,
      "learning_rate": 0.10248375553508478,
      "loss": 0.0,
      "num_input_tokens_seen": 6748768,
      "step": 24105
    },
    {
      "epoch": 267.8888888888889,
      "grad_norm": 1.5871103542508536e-08,
      "learning_rate": 0.102427887895847,
      "loss": 0.0,
      "num_input_tokens_seen": 6750176,
      "step": 24110
    },
    {
      "epoch": 267.94444444444446,
      "grad_norm": 4.523509744558396e-08,
      "learning_rate": 0.10237202759282668,
      "loss": 0.0,
      "num_input_tokens_seen": 6751600,
      "step": 24115
    },
    {
      "epoch": 268.0,
      "grad_norm": 7.060782536427723e-08,
      "learning_rate": 0.10231617463463821,
      "loss": 0.0,
      "num_input_tokens_seen": 6753008,
      "step": 24120
    },
    {
      "epoch": 268.05555555555554,
      "grad_norm": 1.4772863821121973e-08,
      "learning_rate": 0.10226032902989492,
      "loss": 0.0,
      "num_input_tokens_seen": 6754416,
      "step": 24125
    },
    {
      "epoch": 268.1111111111111,
      "grad_norm": 1.7072038005494505e-08,
      "learning_rate": 0.10220449078720877,
      "loss": 0.0,
      "num_input_tokens_seen": 6755792,
      "step": 24130
    },
    {
      "epoch": 268.1666666666667,
      "grad_norm": 3.246228175157739e-08,
      "learning_rate": 0.1021486599151908,
      "loss": 0.0,
      "num_input_tokens_seen": 6757216,
      "step": 24135
    },
    {
      "epoch": 268.22222222222223,
      "grad_norm": 3.3746406558066155e-08,
      "learning_rate": 0.10209283642245084,
      "loss": 0.0,
      "num_input_tokens_seen": 6758624,
      "step": 24140
    },
    {
      "epoch": 268.27777777777777,
      "grad_norm": 1.7298940946375296e-08,
      "learning_rate": 0.10203702031759748,
      "loss": 0.0,
      "num_input_tokens_seen": 6760032,
      "step": 24145
    },
    {
      "epoch": 268.3333333333333,
      "grad_norm": 3.0799888861565705e-08,
      "learning_rate": 0.1019812116092384,
      "loss": 0.0,
      "num_input_tokens_seen": 6761424,
      "step": 24150
    },
    {
      "epoch": 268.3888888888889,
      "grad_norm": 1.7206846791850694e-07,
      "learning_rate": 0.10192541030597986,
      "loss": 0.0,
      "num_input_tokens_seen": 6762800,
      "step": 24155
    },
    {
      "epoch": 268.44444444444446,
      "grad_norm": 2.4954502464424877e-08,
      "learning_rate": 0.1018696164164272,
      "loss": 0.0,
      "num_input_tokens_seen": 6764192,
      "step": 24160
    },
    {
      "epoch": 268.5,
      "grad_norm": 1.982146180523614e-08,
      "learning_rate": 0.10181382994918459,
      "loss": 0.0,
      "num_input_tokens_seen": 6765616,
      "step": 24165
    },
    {
      "epoch": 268.55555555555554,
      "grad_norm": 3.256841552001788e-08,
      "learning_rate": 0.10175805091285492,
      "loss": 0.0,
      "num_input_tokens_seen": 6766992,
      "step": 24170
    },
    {
      "epoch": 268.6111111111111,
      "grad_norm": 1.0078204049079886e-08,
      "learning_rate": 0.10170227931603999,
      "loss": 0.0,
      "num_input_tokens_seen": 6768352,
      "step": 24175
    },
    {
      "epoch": 268.6666666666667,
      "grad_norm": 3.1037934888900054e-08,
      "learning_rate": 0.10164651516734062,
      "loss": 0.0,
      "num_input_tokens_seen": 6769744,
      "step": 24180
    },
    {
      "epoch": 268.72222222222223,
      "grad_norm": 2.2223981943625404e-07,
      "learning_rate": 0.1015907584753562,
      "loss": 0.0,
      "num_input_tokens_seen": 6771168,
      "step": 24185
    },
    {
      "epoch": 268.77777777777777,
      "grad_norm": 2.4662762498905977e-08,
      "learning_rate": 0.10153500924868523,
      "loss": 0.0,
      "num_input_tokens_seen": 6772512,
      "step": 24190
    },
    {
      "epoch": 268.8333333333333,
      "grad_norm": 3.241555646127381e-08,
      "learning_rate": 0.10147926749592483,
      "loss": 0.0,
      "num_input_tokens_seen": 6773920,
      "step": 24195
    },
    {
      "epoch": 268.8888888888889,
      "grad_norm": 3.8471565488862325e-08,
      "learning_rate": 0.10142353322567112,
      "loss": 0.0,
      "num_input_tokens_seen": 6775344,
      "step": 24200
    },
    {
      "epoch": 268.8888888888889,
      "eval_loss": 1.5901665687561035,
      "eval_runtime": 1.1883,
      "eval_samples_per_second": 33.66,
      "eval_steps_per_second": 16.83,
      "num_input_tokens_seen": 6775344,
      "step": 24200
    },
    {
      "epoch": 268.94444444444446,
      "grad_norm": 2.108806285150422e-08,
      "learning_rate": 0.1013678064465191,
      "loss": 0.0,
      "num_input_tokens_seen": 6776736,
      "step": 24205
    },
    {
      "epoch": 269.0,
      "grad_norm": 1.3406148191563716e-08,
      "learning_rate": 0.10131208716706244,
      "loss": 0.0,
      "num_input_tokens_seen": 6778144,
      "step": 24210
    },
    {
      "epoch": 269.05555555555554,
      "grad_norm": 1.963800855264708e-08,
      "learning_rate": 0.10125637539589379,
      "loss": 0.0,
      "num_input_tokens_seen": 6779552,
      "step": 24215
    },
    {
      "epoch": 269.1111111111111,
      "grad_norm": 2.008994925972729e-08,
      "learning_rate": 0.10120067114160464,
      "loss": 0.0,
      "num_input_tokens_seen": 6780960,
      "step": 24220
    },
    {
      "epoch": 269.1666666666667,
      "grad_norm": 5.497692256994924e-08,
      "learning_rate": 0.10114497441278517,
      "loss": 0.0,
      "num_input_tokens_seen": 6782352,
      "step": 24225
    },
    {
      "epoch": 269.22222222222223,
      "grad_norm": 5.461826901864697e-08,
      "learning_rate": 0.10108928521802468,
      "loss": 0.0,
      "num_input_tokens_seen": 6783696,
      "step": 24230
    },
    {
      "epoch": 269.27777777777777,
      "grad_norm": 3.7611741277032706e-08,
      "learning_rate": 0.101033603565911,
      "loss": 0.0,
      "num_input_tokens_seen": 6785104,
      "step": 24235
    },
    {
      "epoch": 269.3333333333333,
      "grad_norm": 1.3666763720721065e-08,
      "learning_rate": 0.10097792946503102,
      "loss": 0.0,
      "num_input_tokens_seen": 6786496,
      "step": 24240
    },
    {
      "epoch": 269.3888888888889,
      "grad_norm": 3.314392316156045e-08,
      "learning_rate": 0.10092226292397039,
      "loss": 0.0,
      "num_input_tokens_seen": 6787888,
      "step": 24245
    },
    {
      "epoch": 269.44444444444446,
      "grad_norm": 2.601877113761475e-08,
      "learning_rate": 0.10086660395131354,
      "loss": 0.0,
      "num_input_tokens_seen": 6789280,
      "step": 24250
    },
    {
      "epoch": 269.5,
      "grad_norm": 1.8812857049965714e-08,
      "learning_rate": 0.10081095255564385,
      "loss": 0.0,
      "num_input_tokens_seen": 6790656,
      "step": 24255
    },
    {
      "epoch": 269.55555555555554,
      "grad_norm": 1.1110639519529286e-08,
      "learning_rate": 0.10075530874554335,
      "loss": 0.0,
      "num_input_tokens_seen": 6792064,
      "step": 24260
    },
    {
      "epoch": 269.6111111111111,
      "grad_norm": 1.983514685832688e-08,
      "learning_rate": 0.10069967252959311,
      "loss": 0.0,
      "num_input_tokens_seen": 6793472,
      "step": 24265
    },
    {
      "epoch": 269.6666666666667,
      "grad_norm": 1.263739068946279e-08,
      "learning_rate": 0.10064404391637297,
      "loss": 0.0,
      "num_input_tokens_seen": 6794880,
      "step": 24270
    },
    {
      "epoch": 269.72222222222223,
      "grad_norm": 5.778611722462301e-08,
      "learning_rate": 0.10058842291446145,
      "loss": 0.0,
      "num_input_tokens_seen": 6796304,
      "step": 24275
    },
    {
      "epoch": 269.77777777777777,
      "grad_norm": 2.082072292353132e-08,
      "learning_rate": 0.10053280953243608,
      "loss": 0.0,
      "num_input_tokens_seen": 6797696,
      "step": 24280
    },
    {
      "epoch": 269.8333333333333,
      "grad_norm": 1.5802235964201827e-08,
      "learning_rate": 0.10047720377887315,
      "loss": 0.0,
      "num_input_tokens_seen": 6799088,
      "step": 24285
    },
    {
      "epoch": 269.8888888888889,
      "grad_norm": 8.406658480453189e-09,
      "learning_rate": 0.10042160566234767,
      "loss": 0.0,
      "num_input_tokens_seen": 6800480,
      "step": 24290
    },
    {
      "epoch": 269.94444444444446,
      "grad_norm": 2.721608360900518e-08,
      "learning_rate": 0.10036601519143372,
      "loss": 0.0,
      "num_input_tokens_seen": 6801888,
      "step": 24295
    },
    {
      "epoch": 270.0,
      "grad_norm": 2.2526839060788006e-08,
      "learning_rate": 0.1003104323747039,
      "loss": 0.0,
      "num_input_tokens_seen": 6803344,
      "step": 24300
    },
    {
      "epoch": 270.05555555555554,
      "grad_norm": 2.341395877181185e-08,
      "learning_rate": 0.10025485722072984,
      "loss": 0.0,
      "num_input_tokens_seen": 6804736,
      "step": 24305
    },
    {
      "epoch": 270.1111111111111,
      "grad_norm": 2.0753782692395362e-08,
      "learning_rate": 0.10019928973808201,
      "loss": 0.0,
      "num_input_tokens_seen": 6806112,
      "step": 24310
    },
    {
      "epoch": 270.1666666666667,
      "grad_norm": 3.545930837844935e-08,
      "learning_rate": 0.10014372993532945,
      "loss": 0.0,
      "num_input_tokens_seen": 6807488,
      "step": 24315
    },
    {
      "epoch": 270.22222222222223,
      "grad_norm": 1.9378807891712313e-08,
      "learning_rate": 0.1000881778210403,
      "loss": 0.0,
      "num_input_tokens_seen": 6808896,
      "step": 24320
    },
    {
      "epoch": 270.27777777777777,
      "grad_norm": 2.6532212871188676e-08,
      "learning_rate": 0.10003263340378142,
      "loss": 0.0,
      "num_input_tokens_seen": 6810320,
      "step": 24325
    },
    {
      "epoch": 270.3333333333333,
      "grad_norm": 2.457777625863855e-08,
      "learning_rate": 0.09997709669211834,
      "loss": 0.0,
      "num_input_tokens_seen": 6811712,
      "step": 24330
    },
    {
      "epoch": 270.3888888888889,
      "grad_norm": 3.6589529628372475e-08,
      "learning_rate": 0.0999215676946156,
      "loss": 0.0,
      "num_input_tokens_seen": 6813120,
      "step": 24335
    },
    {
      "epoch": 270.44444444444446,
      "grad_norm": 3.5131478171024355e-08,
      "learning_rate": 0.0998660464198364,
      "loss": 0.0,
      "num_input_tokens_seen": 6814528,
      "step": 24340
    },
    {
      "epoch": 270.5,
      "grad_norm": 1.729555698659624e-08,
      "learning_rate": 0.09981053287634288,
      "loss": 0.0,
      "num_input_tokens_seen": 6815904,
      "step": 24345
    },
    {
      "epoch": 270.55555555555554,
      "grad_norm": 2.238937391041418e-08,
      "learning_rate": 0.09975502707269596,
      "loss": 0.0,
      "num_input_tokens_seen": 6817344,
      "step": 24350
    },
    {
      "epoch": 270.6111111111111,
      "grad_norm": 9.174014081736459e-08,
      "learning_rate": 0.09969952901745524,
      "loss": 0.0,
      "num_input_tokens_seen": 6818736,
      "step": 24355
    },
    {
      "epoch": 270.6666666666667,
      "grad_norm": 2.5722751928469734e-08,
      "learning_rate": 0.09964403871917925,
      "loss": 0.0,
      "num_input_tokens_seen": 6820144,
      "step": 24360
    },
    {
      "epoch": 270.72222222222223,
      "grad_norm": 2.6851685319684293e-08,
      "learning_rate": 0.09958855618642536,
      "loss": 0.0,
      "num_input_tokens_seen": 6821504,
      "step": 24365
    },
    {
      "epoch": 270.77777777777777,
      "grad_norm": 4.3423366236083893e-08,
      "learning_rate": 0.09953308142774955,
      "loss": 0.0,
      "num_input_tokens_seen": 6822880,
      "step": 24370
    },
    {
      "epoch": 270.8333333333333,
      "grad_norm": 3.7935294017188426e-08,
      "learning_rate": 0.09947761445170686,
      "loss": 0.0,
      "num_input_tokens_seen": 6824272,
      "step": 24375
    },
    {
      "epoch": 270.8888888888889,
      "grad_norm": 2.4621508387667745e-08,
      "learning_rate": 0.09942215526685086,
      "loss": 0.0,
      "num_input_tokens_seen": 6825680,
      "step": 24380
    },
    {
      "epoch": 270.94444444444446,
      "grad_norm": 7.790748668412562e-08,
      "learning_rate": 0.09936670388173414,
      "loss": 0.0,
      "num_input_tokens_seen": 6827088,
      "step": 24385
    },
    {
      "epoch": 271.0,
      "grad_norm": 2.8820458908285218e-08,
      "learning_rate": 0.09931126030490799,
      "loss": 0.0,
      "num_input_tokens_seen": 6828512,
      "step": 24390
    },
    {
      "epoch": 271.05555555555554,
      "grad_norm": 1.4302344197858474e-08,
      "learning_rate": 0.0992558245449225,
      "loss": 0.0,
      "num_input_tokens_seen": 6829904,
      "step": 24395
    },
    {
      "epoch": 271.1111111111111,
      "grad_norm": 2.3816076222260563e-08,
      "learning_rate": 0.09920039661032651,
      "loss": 0.0,
      "num_input_tokens_seen": 6831344,
      "step": 24400
    },
    {
      "epoch": 271.1111111111111,
      "eval_loss": 1.4872815608978271,
      "eval_runtime": 1.1968,
      "eval_samples_per_second": 33.422,
      "eval_steps_per_second": 16.711,
      "num_input_tokens_seen": 6831344,
      "step": 24400
    },
    {
      "epoch": 271.1666666666667,
      "grad_norm": 7.33189509105614e-08,
      "learning_rate": 0.09914497650966782,
      "loss": 0.0,
      "num_input_tokens_seen": 6832704,
      "step": 24405
    },
    {
      "epoch": 271.22222222222223,
      "grad_norm": 4.19028687304035e-08,
      "learning_rate": 0.09908956425149276,
      "loss": 0.0,
      "num_input_tokens_seen": 6834096,
      "step": 24410
    },
    {
      "epoch": 271.27777777777777,
      "grad_norm": 2.1638053127048806e-08,
      "learning_rate": 0.09903415984434677,
      "loss": 0.0,
      "num_input_tokens_seen": 6835472,
      "step": 24415
    },
    {
      "epoch": 271.3333333333333,
      "grad_norm": 1.8518299782499525e-08,
      "learning_rate": 0.09897876329677373,
      "loss": 0.0,
      "num_input_tokens_seen": 6836848,
      "step": 24420
    },
    {
      "epoch": 271.3888888888889,
      "grad_norm": 1.9442015997128692e-08,
      "learning_rate": 0.09892337461731658,
      "loss": 0.0,
      "num_input_tokens_seen": 6838240,
      "step": 24425
    },
    {
      "epoch": 271.44444444444446,
      "grad_norm": 4.012064636071955e-08,
      "learning_rate": 0.09886799381451693,
      "loss": 0.0,
      "num_input_tokens_seen": 6839584,
      "step": 24430
    },
    {
      "epoch": 271.5,
      "grad_norm": 2.46264431069676e-08,
      "learning_rate": 0.09881262089691521,
      "loss": 0.0,
      "num_input_tokens_seen": 6841008,
      "step": 24435
    },
    {
      "epoch": 271.55555555555554,
      "grad_norm": 5.7448193757636545e-08,
      "learning_rate": 0.09875725587305059,
      "loss": 0.0,
      "num_input_tokens_seen": 6842464,
      "step": 24440
    },
    {
      "epoch": 271.6111111111111,
      "grad_norm": 3.0114080118437414e-08,
      "learning_rate": 0.09870189875146111,
      "loss": 0.0,
      "num_input_tokens_seen": 6843824,
      "step": 24445
    },
    {
      "epoch": 271.6666666666667,
      "grad_norm": 4.2215557272129445e-08,
      "learning_rate": 0.09864654954068346,
      "loss": 0.0,
      "num_input_tokens_seen": 6845248,
      "step": 24450
    },
    {
      "epoch": 271.72222222222223,
      "grad_norm": 2.9501089571226657e-08,
      "learning_rate": 0.09859120824925326,
      "loss": 0.0,
      "num_input_tokens_seen": 6846656,
      "step": 24455
    },
    {
      "epoch": 271.77777777777777,
      "grad_norm": 2.686578781663229e-08,
      "learning_rate": 0.09853587488570474,
      "loss": 0.0,
      "num_input_tokens_seen": 6848048,
      "step": 24460
    },
    {
      "epoch": 271.8333333333333,
      "grad_norm": 2.599830217775434e-08,
      "learning_rate": 0.09848054945857107,
      "loss": 0.0,
      "num_input_tokens_seen": 6849456,
      "step": 24465
    },
    {
      "epoch": 271.8888888888889,
      "grad_norm": 1.3977096813277967e-08,
      "learning_rate": 0.09842523197638416,
      "loss": 0.0,
      "num_input_tokens_seen": 6850928,
      "step": 24470
    },
    {
      "epoch": 271.94444444444446,
      "grad_norm": 5.54812586983644e-08,
      "learning_rate": 0.09836992244767452,
      "loss": 0.0,
      "num_input_tokens_seen": 6852304,
      "step": 24475
    },
    {
      "epoch": 272.0,
      "grad_norm": 9.26537957468554e-09,
      "learning_rate": 0.09831462088097168,
      "loss": 0.0,
      "num_input_tokens_seen": 6853712,
      "step": 24480
    },
    {
      "epoch": 272.05555555555554,
      "grad_norm": 4.4449905090004904e-08,
      "learning_rate": 0.09825932728480385,
      "loss": 0.0,
      "num_input_tokens_seen": 6855120,
      "step": 24485
    },
    {
      "epoch": 272.1111111111111,
      "grad_norm": 3.1196154992585434e-08,
      "learning_rate": 0.09820404166769794,
      "loss": 0.0,
      "num_input_tokens_seen": 6856496,
      "step": 24490
    },
    {
      "epoch": 272.1666666666667,
      "grad_norm": 7.93411274457867e-08,
      "learning_rate": 0.09814876403817978,
      "loss": 0.0,
      "num_input_tokens_seen": 6857872,
      "step": 24495
    },
    {
      "epoch": 272.22222222222223,
      "grad_norm": 3.1294632663048105e-08,
      "learning_rate": 0.09809349440477376,
      "loss": 0.0,
      "num_input_tokens_seen": 6859296,
      "step": 24500
    },
    {
      "epoch": 272.27777777777777,
      "grad_norm": 1.2201071264428265e-08,
      "learning_rate": 0.09803823277600317,
      "loss": 0.0,
      "num_input_tokens_seen": 6860688,
      "step": 24505
    },
    {
      "epoch": 272.3333333333333,
      "grad_norm": 5.7425364019536573e-08,
      "learning_rate": 0.09798297916039014,
      "loss": 0.0,
      "num_input_tokens_seen": 6862048,
      "step": 24510
    },
    {
      "epoch": 272.3888888888889,
      "grad_norm": 2.7285199877269406e-08,
      "learning_rate": 0.09792773356645534,
      "loss": 0.0,
      "num_input_tokens_seen": 6863520,
      "step": 24515
    },
    {
      "epoch": 272.44444444444446,
      "grad_norm": 1.6224250387608663e-08,
      "learning_rate": 0.09787249600271843,
      "loss": 0.0,
      "num_input_tokens_seen": 6864928,
      "step": 24520
    },
    {
      "epoch": 272.5,
      "grad_norm": 8.200013112968918e-09,
      "learning_rate": 0.09781726647769776,
      "loss": 0.0,
      "num_input_tokens_seen": 6866352,
      "step": 24525
    },
    {
      "epoch": 272.55555555555554,
      "grad_norm": 2.1980984143965543e-08,
      "learning_rate": 0.0977620449999103,
      "loss": 0.0,
      "num_input_tokens_seen": 6867744,
      "step": 24530
    },
    {
      "epoch": 272.6111111111111,
      "grad_norm": 1.3115451835687963e-08,
      "learning_rate": 0.09770683157787204,
      "loss": 0.0,
      "num_input_tokens_seen": 6869152,
      "step": 24535
    },
    {
      "epoch": 272.6666666666667,
      "grad_norm": 1.2800424542547262e-07,
      "learning_rate": 0.09765162622009745,
      "loss": 0.0,
      "num_input_tokens_seen": 6870560,
      "step": 24540
    },
    {
      "epoch": 272.72222222222223,
      "grad_norm": 1.629443033834832e-07,
      "learning_rate": 0.09759642893509995,
      "loss": 0.0,
      "num_input_tokens_seen": 6872000,
      "step": 24545
    },
    {
      "epoch": 272.77777777777777,
      "grad_norm": 2.1347291934148416e-08,
      "learning_rate": 0.09754123973139169,
      "loss": 0.0,
      "num_input_tokens_seen": 6873360,
      "step": 24550
    },
    {
      "epoch": 272.8333333333333,
      "grad_norm": 1.5594196156598628e-07,
      "learning_rate": 0.09748605861748345,
      "loss": 0.0,
      "num_input_tokens_seen": 6874736,
      "step": 24555
    },
    {
      "epoch": 272.8888888888889,
      "grad_norm": 6.764046389662326e-08,
      "learning_rate": 0.0974308856018849,
      "loss": 0.0,
      "num_input_tokens_seen": 6876128,
      "step": 24560
    },
    {
      "epoch": 272.94444444444446,
      "grad_norm": 2.921135155986576e-08,
      "learning_rate": 0.09737572069310449,
      "loss": 0.0,
      "num_input_tokens_seen": 6877504,
      "step": 24565
    },
    {
      "epoch": 273.0,
      "grad_norm": 2.1948245887415396e-08,
      "learning_rate": 0.09732056389964922,
      "loss": 0.0,
      "num_input_tokens_seen": 6878928,
      "step": 24570
    },
    {
      "epoch": 273.05555555555554,
      "grad_norm": 1.292578488687468e-08,
      "learning_rate": 0.097265415230025,
      "loss": 0.0,
      "num_input_tokens_seen": 6880336,
      "step": 24575
    },
    {
      "epoch": 273.1111111111111,
      "grad_norm": 1.3917345498271061e-08,
      "learning_rate": 0.09721027469273648,
      "loss": 0.0,
      "num_input_tokens_seen": 6881760,
      "step": 24580
    },
    {
      "epoch": 273.1666666666667,
      "grad_norm": 8.415938879124951e-08,
      "learning_rate": 0.09715514229628695,
      "loss": 0.0,
      "num_input_tokens_seen": 6883184,
      "step": 24585
    },
    {
      "epoch": 273.22222222222223,
      "grad_norm": 1.3976216628464044e-08,
      "learning_rate": 0.09710001804917864,
      "loss": 0.0,
      "num_input_tokens_seen": 6884560,
      "step": 24590
    },
    {
      "epoch": 273.27777777777777,
      "grad_norm": 3.6917843004857787e-08,
      "learning_rate": 0.09704490195991226,
      "loss": 0.0,
      "num_input_tokens_seen": 6885904,
      "step": 24595
    },
    {
      "epoch": 273.3333333333333,
      "grad_norm": 4.196910907694473e-08,
      "learning_rate": 0.09698979403698753,
      "loss": 0.0,
      "num_input_tokens_seen": 6887344,
      "step": 24600
    },
    {
      "epoch": 273.3333333333333,
      "eval_loss": 1.5269778966903687,
      "eval_runtime": 1.1912,
      "eval_samples_per_second": 33.58,
      "eval_steps_per_second": 16.79,
      "num_input_tokens_seen": 6887344,
      "step": 24600
    },
    {
      "epoch": 273.3888888888889,
      "grad_norm": 5.495307675573713e-08,
      "learning_rate": 0.0969346942889027,
      "loss": 0.0,
      "num_input_tokens_seen": 6888752,
      "step": 24605
    },
    {
      "epoch": 273.44444444444446,
      "grad_norm": 4.898716809975667e-08,
      "learning_rate": 0.09687960272415487,
      "loss": 0.0,
      "num_input_tokens_seen": 6890160,
      "step": 24610
    },
    {
      "epoch": 273.5,
      "grad_norm": 2.9744089857786093e-08,
      "learning_rate": 0.0968245193512399,
      "loss": 0.0,
      "num_input_tokens_seen": 6891568,
      "step": 24615
    },
    {
      "epoch": 273.55555555555554,
      "grad_norm": 2.9180423410934964e-08,
      "learning_rate": 0.09676944417865221,
      "loss": 0.0,
      "num_input_tokens_seen": 6893008,
      "step": 24620
    },
    {
      "epoch": 273.6111111111111,
      "grad_norm": 4.2775990749532866e-08,
      "learning_rate": 0.09671437721488517,
      "loss": 0.0,
      "num_input_tokens_seen": 6894384,
      "step": 24625
    },
    {
      "epoch": 273.6666666666667,
      "grad_norm": 2.5754312460435358e-08,
      "learning_rate": 0.09665931846843086,
      "loss": 0.0,
      "num_input_tokens_seen": 6895792,
      "step": 24630
    },
    {
      "epoch": 273.72222222222223,
      "grad_norm": 1.7444335753680207e-08,
      "learning_rate": 0.0966042679477799,
      "loss": 0.0,
      "num_input_tokens_seen": 6897200,
      "step": 24635
    },
    {
      "epoch": 273.77777777777777,
      "grad_norm": 5.724820084651583e-08,
      "learning_rate": 0.09654922566142186,
      "loss": 0.0,
      "num_input_tokens_seen": 6898624,
      "step": 24640
    },
    {
      "epoch": 273.8333333333333,
      "grad_norm": 3.6372934886230723e-08,
      "learning_rate": 0.09649419161784498,
      "loss": 0.0,
      "num_input_tokens_seen": 6900032,
      "step": 24645
    },
    {
      "epoch": 273.8888888888889,
      "grad_norm": 3.655207692077056e-08,
      "learning_rate": 0.09643916582553606,
      "loss": 0.0,
      "num_input_tokens_seen": 6901440,
      "step": 24650
    },
    {
      "epoch": 273.94444444444446,
      "grad_norm": 2.4099097828411686e-08,
      "learning_rate": 0.09638414829298093,
      "loss": 0.0,
      "num_input_tokens_seen": 6902848,
      "step": 24655
    },
    {
      "epoch": 274.0,
      "grad_norm": 2.0116880605769438e-08,
      "learning_rate": 0.09632913902866386,
      "loss": 0.0,
      "num_input_tokens_seen": 6904192,
      "step": 24660
    },
    {
      "epoch": 274.05555555555554,
      "grad_norm": 3.1313145854028335e-08,
      "learning_rate": 0.096274138041068,
      "loss": 0.0,
      "num_input_tokens_seen": 6905600,
      "step": 24665
    },
    {
      "epoch": 274.1111111111111,
      "grad_norm": 5.7028291422511757e-08,
      "learning_rate": 0.09621914533867527,
      "loss": 0.0,
      "num_input_tokens_seen": 6907024,
      "step": 24670
    },
    {
      "epoch": 274.1666666666667,
      "grad_norm": 3.204693044267515e-08,
      "learning_rate": 0.09616416092996616,
      "loss": 0.0,
      "num_input_tokens_seen": 6908448,
      "step": 24675
    },
    {
      "epoch": 274.22222222222223,
      "grad_norm": 8.786638971969296e-08,
      "learning_rate": 0.09610918482342,
      "loss": 0.0,
      "num_input_tokens_seen": 6909856,
      "step": 24680
    },
    {
      "epoch": 274.27777777777777,
      "grad_norm": 2.8427580289758225e-08,
      "learning_rate": 0.09605421702751478,
      "loss": 0.0,
      "num_input_tokens_seen": 6911248,
      "step": 24685
    },
    {
      "epoch": 274.3333333333333,
      "grad_norm": 1.6945993053241182e-08,
      "learning_rate": 0.09599925755072718,
      "loss": 0.0,
      "num_input_tokens_seen": 6912656,
      "step": 24690
    },
    {
      "epoch": 274.3888888888889,
      "grad_norm": 1.8270686297228167e-08,
      "learning_rate": 0.09594430640153273,
      "loss": 0.0,
      "num_input_tokens_seen": 6914096,
      "step": 24695
    },
    {
      "epoch": 274.44444444444446,
      "grad_norm": 1.8814551694390502e-08,
      "learning_rate": 0.09588936358840547,
      "loss": 0.0,
      "num_input_tokens_seen": 6915456,
      "step": 24700
    },
    {
      "epoch": 274.5,
      "grad_norm": 1.6966943405805068e-08,
      "learning_rate": 0.09583442911981836,
      "loss": 0.0,
      "num_input_tokens_seen": 6916848,
      "step": 24705
    },
    {
      "epoch": 274.55555555555554,
      "grad_norm": 3.2021585383290585e-08,
      "learning_rate": 0.09577950300424302,
      "loss": 0.0,
      "num_input_tokens_seen": 6918272,
      "step": 24710
    },
    {
      "epoch": 274.6111111111111,
      "grad_norm": 2.2032240920566437e-08,
      "learning_rate": 0.09572458525014967,
      "loss": 0.0,
      "num_input_tokens_seen": 6919728,
      "step": 24715
    },
    {
      "epoch": 274.6666666666667,
      "grad_norm": 1.826925277725877e-08,
      "learning_rate": 0.0956696758660073,
      "loss": 0.0,
      "num_input_tokens_seen": 6921120,
      "step": 24720
    },
    {
      "epoch": 274.72222222222223,
      "grad_norm": 3.807656767662593e-08,
      "learning_rate": 0.09561477486028373,
      "loss": 0.0,
      "num_input_tokens_seen": 6922448,
      "step": 24725
    },
    {
      "epoch": 274.77777777777777,
      "grad_norm": 9.82525172332771e-09,
      "learning_rate": 0.09555988224144528,
      "loss": 0.0,
      "num_input_tokens_seen": 6923840,
      "step": 24730
    },
    {
      "epoch": 274.8333333333333,
      "grad_norm": 1.511143565835482e-08,
      "learning_rate": 0.09550499801795717,
      "loss": 0.0,
      "num_input_tokens_seen": 6925264,
      "step": 24735
    },
    {
      "epoch": 274.8888888888889,
      "grad_norm": 6.924788920059655e-08,
      "learning_rate": 0.09545012219828314,
      "loss": 0.0,
      "num_input_tokens_seen": 6926640,
      "step": 24740
    },
    {
      "epoch": 274.94444444444446,
      "grad_norm": 2.569373336314129e-08,
      "learning_rate": 0.09539525479088577,
      "loss": 0.0,
      "num_input_tokens_seen": 6928032,
      "step": 24745
    },
    {
      "epoch": 275.0,
      "grad_norm": 2.1860936172402035e-08,
      "learning_rate": 0.0953403958042264,
      "loss": 0.0,
      "num_input_tokens_seen": 6929456,
      "step": 24750
    },
    {
      "epoch": 275.05555555555554,
      "grad_norm": 2.30707115633777e-08,
      "learning_rate": 0.09528554524676484,
      "loss": 0.0,
      "num_input_tokens_seen": 6930880,
      "step": 24755
    },
    {
      "epoch": 275.1111111111111,
      "grad_norm": 2.3642749980012923e-08,
      "learning_rate": 0.09523070312695978,
      "loss": 0.0,
      "num_input_tokens_seen": 6932336,
      "step": 24760
    },
    {
      "epoch": 275.1666666666667,
      "grad_norm": 1.5662465102650458e-08,
      "learning_rate": 0.09517586945326863,
      "loss": 0.0,
      "num_input_tokens_seen": 6933728,
      "step": 24765
    },
    {
      "epoch": 275.22222222222223,
      "grad_norm": 1.1507450992098711e-08,
      "learning_rate": 0.0951210442341473,
      "loss": 0.0,
      "num_input_tokens_seen": 6935200,
      "step": 24770
    },
    {
      "epoch": 275.27777777777777,
      "grad_norm": 1.783128666943412e-08,
      "learning_rate": 0.09506622747805066,
      "loss": 0.0,
      "num_input_tokens_seen": 6936608,
      "step": 24775
    },
    {
      "epoch": 275.3333333333333,
      "grad_norm": 1.0146353979223477e-08,
      "learning_rate": 0.09501141919343203,
      "loss": 0.0,
      "num_input_tokens_seen": 6938048,
      "step": 24780
    },
    {
      "epoch": 275.3888888888889,
      "grad_norm": 1.6660285595548885e-08,
      "learning_rate": 0.09495661938874361,
      "loss": 0.0,
      "num_input_tokens_seen": 6939440,
      "step": 24785
    },
    {
      "epoch": 275.44444444444446,
      "grad_norm": 1.912401259573926e-08,
      "learning_rate": 0.0949018280724362,
      "loss": 0.0,
      "num_input_tokens_seen": 6940784,
      "step": 24790
    },
    {
      "epoch": 275.5,
      "grad_norm": 5.520278989479266e-08,
      "learning_rate": 0.09484704525295934,
      "loss": 0.0,
      "num_input_tokens_seen": 6942208,
      "step": 24795
    },
    {
      "epoch": 275.55555555555554,
      "grad_norm": 2.653113817530084e-08,
      "learning_rate": 0.09479227093876112,
      "loss": 0.0,
      "num_input_tokens_seen": 6943632,
      "step": 24800
    },
    {
      "epoch": 275.55555555555554,
      "eval_loss": 1.6768004894256592,
      "eval_runtime": 1.1832,
      "eval_samples_per_second": 33.806,
      "eval_steps_per_second": 16.903,
      "num_input_tokens_seen": 6943632,
      "step": 24800
    },
    {
      "epoch": 275.6111111111111,
      "grad_norm": 1.2101031288125341e-08,
      "learning_rate": 0.0947375051382886,
      "loss": 0.0,
      "num_input_tokens_seen": 6945024,
      "step": 24805
    },
    {
      "epoch": 275.6666666666667,
      "grad_norm": 1.0633126379389068e-08,
      "learning_rate": 0.09468274785998718,
      "loss": 0.0,
      "num_input_tokens_seen": 6946400,
      "step": 24810
    },
    {
      "epoch": 275.72222222222223,
      "grad_norm": 1.3874339899189181e-08,
      "learning_rate": 0.09462799911230127,
      "loss": 0.0,
      "num_input_tokens_seen": 6947760,
      "step": 24815
    },
    {
      "epoch": 275.77777777777777,
      "grad_norm": 1.6102660538308555e-08,
      "learning_rate": 0.0945732589036737,
      "loss": 0.0,
      "num_input_tokens_seen": 6949152,
      "step": 24820
    },
    {
      "epoch": 275.8333333333333,
      "grad_norm": 1.106963676278383e-08,
      "learning_rate": 0.09451852724254614,
      "loss": 0.0,
      "num_input_tokens_seen": 6950560,
      "step": 24825
    },
    {
      "epoch": 275.8888888888889,
      "grad_norm": 2.6407436237718684e-08,
      "learning_rate": 0.09446380413735894,
      "loss": 0.0,
      "num_input_tokens_seen": 6951952,
      "step": 24830
    },
    {
      "epoch": 275.94444444444446,
      "grad_norm": 1.1926869269984763e-08,
      "learning_rate": 0.09440908959655099,
      "loss": 0.0,
      "num_input_tokens_seen": 6953344,
      "step": 24835
    },
    {
      "epoch": 276.0,
      "grad_norm": 2.3074427701885725e-08,
      "learning_rate": 0.09435438362856004,
      "loss": 0.0,
      "num_input_tokens_seen": 6954752,
      "step": 24840
    },
    {
      "epoch": 276.05555555555554,
      "grad_norm": 1.5485380089330647e-08,
      "learning_rate": 0.0942996862418225,
      "loss": 0.0,
      "num_input_tokens_seen": 6956160,
      "step": 24845
    },
    {
      "epoch": 276.1111111111111,
      "grad_norm": 1.2872915178263611e-08,
      "learning_rate": 0.09424499744477322,
      "loss": 0.0,
      "num_input_tokens_seen": 6957536,
      "step": 24850
    },
    {
      "epoch": 276.1666666666667,
      "grad_norm": 2.2339261107617858e-08,
      "learning_rate": 0.09419031724584608,
      "loss": 0.0,
      "num_input_tokens_seen": 6958960,
      "step": 24855
    },
    {
      "epoch": 276.22222222222223,
      "grad_norm": 1.5752101845123434e-08,
      "learning_rate": 0.09413564565347331,
      "loss": 0.0,
      "num_input_tokens_seen": 6960320,
      "step": 24860
    },
    {
      "epoch": 276.27777777777777,
      "grad_norm": 1.5800816655087147e-08,
      "learning_rate": 0.094080982676086,
      "loss": 0.0,
      "num_input_tokens_seen": 6961696,
      "step": 24865
    },
    {
      "epoch": 276.3333333333333,
      "grad_norm": 3.8722344442021495e-08,
      "learning_rate": 0.09402632832211395,
      "loss": 0.0,
      "num_input_tokens_seen": 6963136,
      "step": 24870
    },
    {
      "epoch": 276.3888888888889,
      "grad_norm": 1.7554311781964316e-08,
      "learning_rate": 0.09397168259998541,
      "loss": 0.0,
      "num_input_tokens_seen": 6964560,
      "step": 24875
    },
    {
      "epoch": 276.44444444444446,
      "grad_norm": 1.3147577249128517e-08,
      "learning_rate": 0.09391704551812759,
      "loss": 0.0,
      "num_input_tokens_seen": 6965952,
      "step": 24880
    },
    {
      "epoch": 276.5,
      "grad_norm": 2.714471136755492e-08,
      "learning_rate": 0.09386241708496605,
      "loss": 0.0,
      "num_input_tokens_seen": 6967344,
      "step": 24885
    },
    {
      "epoch": 276.55555555555554,
      "grad_norm": 1.9733207068384218e-08,
      "learning_rate": 0.09380779730892527,
      "loss": 0.0,
      "num_input_tokens_seen": 6968768,
      "step": 24890
    },
    {
      "epoch": 276.6111111111111,
      "grad_norm": 1.285327844158246e-08,
      "learning_rate": 0.09375318619842836,
      "loss": 0.0,
      "num_input_tokens_seen": 6970128,
      "step": 24895
    },
    {
      "epoch": 276.6666666666667,
      "grad_norm": 2.1203739208885963e-08,
      "learning_rate": 0.09369858376189696,
      "loss": 0.0,
      "num_input_tokens_seen": 6971568,
      "step": 24900
    },
    {
      "epoch": 276.72222222222223,
      "grad_norm": 1.9261563011241378e-08,
      "learning_rate": 0.09364399000775143,
      "loss": 0.0,
      "num_input_tokens_seen": 6972992,
      "step": 24905
    },
    {
      "epoch": 276.77777777777777,
      "grad_norm": 1.0904749814244497e-07,
      "learning_rate": 0.09358940494441093,
      "loss": 0.0,
      "num_input_tokens_seen": 6974368,
      "step": 24910
    },
    {
      "epoch": 276.8333333333333,
      "grad_norm": 2.319904979231069e-08,
      "learning_rate": 0.09353482858029301,
      "loss": 0.0,
      "num_input_tokens_seen": 6975792,
      "step": 24915
    },
    {
      "epoch": 276.8888888888889,
      "grad_norm": 3.888389343842391e-08,
      "learning_rate": 0.09348026092381419,
      "loss": 0.0,
      "num_input_tokens_seen": 6977184,
      "step": 24920
    },
    {
      "epoch": 276.94444444444446,
      "grad_norm": 1.1284068790473611e-08,
      "learning_rate": 0.09342570198338931,
      "loss": 0.0,
      "num_input_tokens_seen": 6978592,
      "step": 24925
    },
    {
      "epoch": 277.0,
      "grad_norm": 5.5947676713685723e-08,
      "learning_rate": 0.0933711517674322,
      "loss": 0.0,
      "num_input_tokens_seen": 6980000,
      "step": 24930
    },
    {
      "epoch": 277.05555555555554,
      "grad_norm": 2.5558669847214333e-08,
      "learning_rate": 0.09331661028435513,
      "loss": 0.0,
      "num_input_tokens_seen": 6981392,
      "step": 24935
    },
    {
      "epoch": 277.1111111111111,
      "grad_norm": 8.572277465646039e-08,
      "learning_rate": 0.09326207754256909,
      "loss": 0.0,
      "num_input_tokens_seen": 6982768,
      "step": 24940
    },
    {
      "epoch": 277.1666666666667,
      "grad_norm": 2.4205441206959222e-08,
      "learning_rate": 0.09320755355048366,
      "loss": 0.0,
      "num_input_tokens_seen": 6984160,
      "step": 24945
    },
    {
      "epoch": 277.22222222222223,
      "grad_norm": 1.037381469615184e-08,
      "learning_rate": 0.09315303831650722,
      "loss": 0.0,
      "num_input_tokens_seen": 6985568,
      "step": 24950
    },
    {
      "epoch": 277.27777777777777,
      "grad_norm": 1.9195610434508126e-08,
      "learning_rate": 0.09309853184904661,
      "loss": 0.0,
      "num_input_tokens_seen": 6986976,
      "step": 24955
    },
    {
      "epoch": 277.3333333333333,
      "grad_norm": 3.737877918297272e-08,
      "learning_rate": 0.09304403415650753,
      "loss": 0.0,
      "num_input_tokens_seen": 6988400,
      "step": 24960
    },
    {
      "epoch": 277.3888888888889,
      "grad_norm": 3.19138422355536e-08,
      "learning_rate": 0.09298954524729405,
      "loss": 0.0,
      "num_input_tokens_seen": 6989792,
      "step": 24965
    },
    {
      "epoch": 277.44444444444446,
      "grad_norm": 1.8102785048768055e-08,
      "learning_rate": 0.09293506512980916,
      "loss": 0.0,
      "num_input_tokens_seen": 6991200,
      "step": 24970
    },
    {
      "epoch": 277.5,
      "grad_norm": 1.45039109611389e-08,
      "learning_rate": 0.0928805938124544,
      "loss": 0.0,
      "num_input_tokens_seen": 6992592,
      "step": 24975
    },
    {
      "epoch": 277.55555555555554,
      "grad_norm": 1.89951752105344e-08,
      "learning_rate": 0.09282613130362982,
      "loss": 0.0,
      "num_input_tokens_seen": 6994016,
      "step": 24980
    },
    {
      "epoch": 277.6111111111111,
      "grad_norm": 1.65229891990748e-08,
      "learning_rate": 0.09277167761173427,
      "loss": 0.0,
      "num_input_tokens_seen": 6995408,
      "step": 24985
    },
    {
      "epoch": 277.6666666666667,
      "grad_norm": 1.1388180354288124e-07,
      "learning_rate": 0.0927172327451653,
      "loss": 0.0,
      "num_input_tokens_seen": 6996864,
      "step": 24990
    },
    {
      "epoch": 277.72222222222223,
      "grad_norm": 5.6438093309907345e-08,
      "learning_rate": 0.09266279671231882,
      "loss": 0.0,
      "num_input_tokens_seen": 6998256,
      "step": 24995
    },
    {
      "epoch": 277.77777777777777,
      "grad_norm": 3.344137411431802e-08,
      "learning_rate": 0.09260836952158967,
      "loss": 0.0,
      "num_input_tokens_seen": 6999632,
      "step": 25000
    },
    {
      "epoch": 277.77777777777777,
      "eval_loss": 1.6875731945037842,
      "eval_runtime": 1.1896,
      "eval_samples_per_second": 33.623,
      "eval_steps_per_second": 16.812,
      "num_input_tokens_seen": 6999632,
      "step": 25000
    },
    {
      "epoch": 277.8333333333333,
      "grad_norm": 2.2064556404188806e-08,
      "learning_rate": 0.09255395118137114,
      "loss": 0.0,
      "num_input_tokens_seen": 7001024,
      "step": 25005
    },
    {
      "epoch": 277.8888888888889,
      "grad_norm": 1.7243241501319062e-08,
      "learning_rate": 0.09249954170005527,
      "loss": 0.0,
      "num_input_tokens_seen": 7002400,
      "step": 25010
    },
    {
      "epoch": 277.94444444444446,
      "grad_norm": 2.2764259810514886e-08,
      "learning_rate": 0.0924451410860327,
      "loss": 0.0,
      "num_input_tokens_seen": 7003824,
      "step": 25015
    },
    {
      "epoch": 278.0,
      "grad_norm": 1.0631127089766323e-08,
      "learning_rate": 0.09239074934769258,
      "loss": 0.0,
      "num_input_tokens_seen": 7005184,
      "step": 25020
    },
    {
      "epoch": 278.05555555555554,
      "grad_norm": 1.442207153701247e-08,
      "learning_rate": 0.09233636649342288,
      "loss": 0.0,
      "num_input_tokens_seen": 7006608,
      "step": 25025
    },
    {
      "epoch": 278.1111111111111,
      "grad_norm": 1.2609890909232035e-08,
      "learning_rate": 0.09228199253161017,
      "loss": 0.0,
      "num_input_tokens_seen": 7008000,
      "step": 25030
    },
    {
      "epoch": 278.1666666666667,
      "grad_norm": 1.6258335122643075e-08,
      "learning_rate": 0.09222762747063949,
      "loss": 0.0,
      "num_input_tokens_seen": 7009424,
      "step": 25035
    },
    {
      "epoch": 278.22222222222223,
      "grad_norm": 2.8747006552976018e-08,
      "learning_rate": 0.09217327131889473,
      "loss": 0.0,
      "num_input_tokens_seen": 7010816,
      "step": 25040
    },
    {
      "epoch": 278.27777777777777,
      "grad_norm": 5.9391598306035576e-09,
      "learning_rate": 0.09211892408475818,
      "loss": 0.0,
      "num_input_tokens_seen": 7012192,
      "step": 25045
    },
    {
      "epoch": 278.3333333333333,
      "grad_norm": 6.166022359366252e-09,
      "learning_rate": 0.09206458577661089,
      "loss": 0.0,
      "num_input_tokens_seen": 7013568,
      "step": 25050
    },
    {
      "epoch": 278.3888888888889,
      "grad_norm": 1.2089746093124631e-08,
      "learning_rate": 0.09201025640283263,
      "loss": 0.0,
      "num_input_tokens_seen": 7014976,
      "step": 25055
    },
    {
      "epoch": 278.44444444444446,
      "grad_norm": 1.7609366409487848e-08,
      "learning_rate": 0.09195593597180148,
      "loss": 0.0,
      "num_input_tokens_seen": 7016384,
      "step": 25060
    },
    {
      "epoch": 278.5,
      "grad_norm": 1.3692313949320578e-08,
      "learning_rate": 0.09190162449189444,
      "loss": 0.0,
      "num_input_tokens_seen": 7017824,
      "step": 25065
    },
    {
      "epoch": 278.55555555555554,
      "grad_norm": 5.883331599676467e-09,
      "learning_rate": 0.09184732197148705,
      "loss": 0.0,
      "num_input_tokens_seen": 7019184,
      "step": 25070
    },
    {
      "epoch": 278.6111111111111,
      "grad_norm": 1.1254185139364381e-08,
      "learning_rate": 0.09179302841895343,
      "loss": 0.0,
      "num_input_tokens_seen": 7020608,
      "step": 25075
    },
    {
      "epoch": 278.6666666666667,
      "grad_norm": 1.316569520071198e-08,
      "learning_rate": 0.09173874384266625,
      "loss": 0.0,
      "num_input_tokens_seen": 7022016,
      "step": 25080
    },
    {
      "epoch": 278.72222222222223,
      "grad_norm": 9.491210484213752e-09,
      "learning_rate": 0.09168446825099695,
      "loss": 0.0,
      "num_input_tokens_seen": 7023408,
      "step": 25085
    },
    {
      "epoch": 278.77777777777777,
      "grad_norm": 3.672607462590349e-08,
      "learning_rate": 0.09163020165231545,
      "loss": 0.0,
      "num_input_tokens_seen": 7024800,
      "step": 25090
    },
    {
      "epoch": 278.8333333333333,
      "grad_norm": 6.475826097585013e-08,
      "learning_rate": 0.09157594405499044,
      "loss": 0.0,
      "num_input_tokens_seen": 7026208,
      "step": 25095
    },
    {
      "epoch": 278.8888888888889,
      "grad_norm": 1.5947399845117616e-08,
      "learning_rate": 0.09152169546738899,
      "loss": 0.0,
      "num_input_tokens_seen": 7027568,
      "step": 25100
    },
    {
      "epoch": 278.94444444444446,
      "grad_norm": 9.076699392096543e-09,
      "learning_rate": 0.09146745589787698,
      "loss": 0.0,
      "num_input_tokens_seen": 7028992,
      "step": 25105
    },
    {
      "epoch": 279.0,
      "grad_norm": 4.880171289300961e-08,
      "learning_rate": 0.09141322535481891,
      "loss": 0.0,
      "num_input_tokens_seen": 7030400,
      "step": 25110
    },
    {
      "epoch": 279.05555555555554,
      "grad_norm": 1.1757336437767663e-08,
      "learning_rate": 0.0913590038465777,
      "loss": 0.0,
      "num_input_tokens_seen": 7031792,
      "step": 25115
    },
    {
      "epoch": 279.1111111111111,
      "grad_norm": 5.9403357788312405e-09,
      "learning_rate": 0.09130479138151505,
      "loss": 0.0,
      "num_input_tokens_seen": 7033136,
      "step": 25120
    },
    {
      "epoch": 279.1666666666667,
      "grad_norm": 1.333845744966311e-08,
      "learning_rate": 0.09125058796799114,
      "loss": 0.0,
      "num_input_tokens_seen": 7034560,
      "step": 25125
    },
    {
      "epoch": 279.22222222222223,
      "grad_norm": 1.4496071898406626e-08,
      "learning_rate": 0.09119639361436485,
      "loss": 0.0,
      "num_input_tokens_seen": 7036016,
      "step": 25130
    },
    {
      "epoch": 279.27777777777777,
      "grad_norm": 1.290994067204565e-08,
      "learning_rate": 0.09114220832899368,
      "loss": 0.0,
      "num_input_tokens_seen": 7037392,
      "step": 25135
    },
    {
      "epoch": 279.3333333333333,
      "grad_norm": 3.90870411592914e-07,
      "learning_rate": 0.0910880321202336,
      "loss": 0.0,
      "num_input_tokens_seen": 7038816,
      "step": 25140
    },
    {
      "epoch": 279.3888888888889,
      "grad_norm": 5.925767254666425e-08,
      "learning_rate": 0.09103386499643933,
      "loss": 0.0,
      "num_input_tokens_seen": 7040192,
      "step": 25145
    },
    {
      "epoch": 279.44444444444446,
      "grad_norm": 2.7712186323469723e-08,
      "learning_rate": 0.09097970696596407,
      "loss": 0.0,
      "num_input_tokens_seen": 7041552,
      "step": 25150
    },
    {
      "epoch": 279.5,
      "grad_norm": 8.303029375156257e-08,
      "learning_rate": 0.09092555803715971,
      "loss": 0.0,
      "num_input_tokens_seen": 7042960,
      "step": 25155
    },
    {
      "epoch": 279.55555555555554,
      "grad_norm": 1.4024445604832181e-08,
      "learning_rate": 0.0908714182183767,
      "loss": 0.0,
      "num_input_tokens_seen": 7044400,
      "step": 25160
    },
    {
      "epoch": 279.6111111111111,
      "grad_norm": 1.1486863904508482e-08,
      "learning_rate": 0.090817287517964,
      "loss": 0.0,
      "num_input_tokens_seen": 7045824,
      "step": 25165
    },
    {
      "epoch": 279.6666666666667,
      "grad_norm": 8.554375874325615e-09,
      "learning_rate": 0.09076316594426931,
      "loss": 0.0,
      "num_input_tokens_seen": 7047200,
      "step": 25170
    },
    {
      "epoch": 279.72222222222223,
      "grad_norm": 5.757269772033169e-09,
      "learning_rate": 0.09070905350563888,
      "loss": 0.0,
      "num_input_tokens_seen": 7048592,
      "step": 25175
    },
    {
      "epoch": 279.77777777777777,
      "grad_norm": 9.333922967869057e-09,
      "learning_rate": 0.09065495021041745,
      "loss": 0.0,
      "num_input_tokens_seen": 7050032,
      "step": 25180
    },
    {
      "epoch": 279.8333333333333,
      "grad_norm": 1.3872666571046466e-08,
      "learning_rate": 0.09060085606694851,
      "loss": 0.0,
      "num_input_tokens_seen": 7051424,
      "step": 25185
    },
    {
      "epoch": 279.8888888888889,
      "grad_norm": 1.6585344653208267e-08,
      "learning_rate": 0.09054677108357405,
      "loss": 0.0,
      "num_input_tokens_seen": 7052864,
      "step": 25190
    },
    {
      "epoch": 279.94444444444446,
      "grad_norm": 1.0241802073096551e-08,
      "learning_rate": 0.09049269526863457,
      "loss": 0.0,
      "num_input_tokens_seen": 7054272,
      "step": 25195
    },
    {
      "epoch": 280.0,
      "grad_norm": 5.8769380473222554e-08,
      "learning_rate": 0.09043862863046935,
      "loss": 0.0,
      "num_input_tokens_seen": 7055664,
      "step": 25200
    },
    {
      "epoch": 280.0,
      "eval_loss": 1.5999171733856201,
      "eval_runtime": 1.1816,
      "eval_samples_per_second": 33.852,
      "eval_steps_per_second": 16.926,
      "num_input_tokens_seen": 7055664,
      "step": 25200
    },
    {
      "epoch": 280.05555555555554,
      "grad_norm": 1.107040681347371e-08,
      "learning_rate": 0.09038457117741602,
      "loss": 0.0,
      "num_input_tokens_seen": 7057072,
      "step": 25205
    },
    {
      "epoch": 280.1111111111111,
      "grad_norm": 1.0241404169164525e-08,
      "learning_rate": 0.09033052291781099,
      "loss": 0.0,
      "num_input_tokens_seen": 7058496,
      "step": 25210
    },
    {
      "epoch": 280.1666666666667,
      "grad_norm": 2.3134695936732896e-08,
      "learning_rate": 0.09027648385998926,
      "loss": 0.0,
      "num_input_tokens_seen": 7059920,
      "step": 25215
    },
    {
      "epoch": 280.22222222222223,
      "grad_norm": 1.2803289095586479e-08,
      "learning_rate": 0.09022245401228417,
      "loss": 0.0,
      "num_input_tokens_seen": 7061360,
      "step": 25220
    },
    {
      "epoch": 280.27777777777777,
      "grad_norm": 2.4743441073837857e-08,
      "learning_rate": 0.09016843338302792,
      "loss": 0.0,
      "num_input_tokens_seen": 7062720,
      "step": 25225
    },
    {
      "epoch": 280.3333333333333,
      "grad_norm": 1.6297102334306146e-08,
      "learning_rate": 0.09011442198055115,
      "loss": 0.0,
      "num_input_tokens_seen": 7064160,
      "step": 25230
    },
    {
      "epoch": 280.3888888888889,
      "grad_norm": 3.002734771939686e-08,
      "learning_rate": 0.09006041981318305,
      "loss": 0.0,
      "num_input_tokens_seen": 7065536,
      "step": 25235
    },
    {
      "epoch": 280.44444444444446,
      "grad_norm": 1.4138591630796782e-08,
      "learning_rate": 0.09000642688925149,
      "loss": 0.0,
      "num_input_tokens_seen": 7066912,
      "step": 25240
    },
    {
      "epoch": 280.5,
      "grad_norm": 1.5755571070030783e-08,
      "learning_rate": 0.0899524432170828,
      "loss": 0.0,
      "num_input_tokens_seen": 7068304,
      "step": 25245
    },
    {
      "epoch": 280.55555555555554,
      "grad_norm": 6.570315491671863e-08,
      "learning_rate": 0.08989846880500196,
      "loss": 0.0,
      "num_input_tokens_seen": 7069680,
      "step": 25250
    },
    {
      "epoch": 280.6111111111111,
      "grad_norm": 2.3355827494242476e-08,
      "learning_rate": 0.08984450366133256,
      "loss": 0.0,
      "num_input_tokens_seen": 7071104,
      "step": 25255
    },
    {
      "epoch": 280.6666666666667,
      "grad_norm": 4.521946195268356e-08,
      "learning_rate": 0.08979054779439664,
      "loss": 0.0,
      "num_input_tokens_seen": 7072544,
      "step": 25260
    },
    {
      "epoch": 280.72222222222223,
      "grad_norm": 2.7119867240799067e-08,
      "learning_rate": 0.08973660121251485,
      "loss": 0.0,
      "num_input_tokens_seen": 7073920,
      "step": 25265
    },
    {
      "epoch": 280.77777777777777,
      "grad_norm": 7.878628593971371e-08,
      "learning_rate": 0.08968266392400655,
      "loss": 0.0,
      "num_input_tokens_seen": 7075296,
      "step": 25270
    },
    {
      "epoch": 280.8333333333333,
      "grad_norm": 2.4396523912173507e-08,
      "learning_rate": 0.0896287359371894,
      "loss": 0.0,
      "num_input_tokens_seen": 7076656,
      "step": 25275
    },
    {
      "epoch": 280.8888888888889,
      "grad_norm": 9.83173986668362e-09,
      "learning_rate": 0.08957481726037989,
      "loss": 0.0,
      "num_input_tokens_seen": 7078032,
      "step": 25280
    },
    {
      "epoch": 280.94444444444446,
      "grad_norm": 9.766772279817815e-09,
      "learning_rate": 0.08952090790189286,
      "loss": 0.0,
      "num_input_tokens_seen": 7079440,
      "step": 25285
    },
    {
      "epoch": 281.0,
      "grad_norm": 3.191434316818231e-08,
      "learning_rate": 0.08946700787004187,
      "loss": 0.0,
      "num_input_tokens_seen": 7080832,
      "step": 25290
    },
    {
      "epoch": 281.05555555555554,
      "grad_norm": 1.698717255749216e-08,
      "learning_rate": 0.08941311717313899,
      "loss": 0.0,
      "num_input_tokens_seen": 7082224,
      "step": 25295
    },
    {
      "epoch": 281.1111111111111,
      "grad_norm": 2.3959312756005602e-08,
      "learning_rate": 0.08935923581949483,
      "loss": 0.0,
      "num_input_tokens_seen": 7083664,
      "step": 25300
    },
    {
      "epoch": 281.1666666666667,
      "grad_norm": 6.451984724265003e-09,
      "learning_rate": 0.0893053638174185,
      "loss": 0.0,
      "num_input_tokens_seen": 7085120,
      "step": 25305
    },
    {
      "epoch": 281.22222222222223,
      "grad_norm": 3.951452853812043e-08,
      "learning_rate": 0.0892515011752179,
      "loss": 0.0,
      "num_input_tokens_seen": 7086528,
      "step": 25310
    },
    {
      "epoch": 281.27777777777777,
      "grad_norm": 2.0275582102158296e-08,
      "learning_rate": 0.08919764790119918,
      "loss": 0.0,
      "num_input_tokens_seen": 7087920,
      "step": 25315
    },
    {
      "epoch": 281.3333333333333,
      "grad_norm": 1.332862442637861e-08,
      "learning_rate": 0.08914380400366727,
      "loss": 0.0,
      "num_input_tokens_seen": 7089312,
      "step": 25320
    },
    {
      "epoch": 281.3888888888889,
      "grad_norm": 1.8195548179278376e-08,
      "learning_rate": 0.08908996949092551,
      "loss": 0.0,
      "num_input_tokens_seen": 7090672,
      "step": 25325
    },
    {
      "epoch": 281.44444444444446,
      "grad_norm": 1.7386669881602757e-08,
      "learning_rate": 0.08903614437127592,
      "loss": 0.0,
      "num_input_tokens_seen": 7092096,
      "step": 25330
    },
    {
      "epoch": 281.5,
      "grad_norm": 6.835930577153704e-08,
      "learning_rate": 0.088982328653019,
      "loss": 0.0,
      "num_input_tokens_seen": 7093472,
      "step": 25335
    },
    {
      "epoch": 281.55555555555554,
      "grad_norm": 9.532948865853541e-07,
      "learning_rate": 0.0889285223444538,
      "loss": 0.0,
      "num_input_tokens_seen": 7094848,
      "step": 25340
    },
    {
      "epoch": 281.6111111111111,
      "grad_norm": 3.805379549248755e-07,
      "learning_rate": 0.08887472545387787,
      "loss": 0.0,
      "num_input_tokens_seen": 7096272,
      "step": 25345
    },
    {
      "epoch": 281.6666666666667,
      "grad_norm": 2.4596044312374943e-08,
      "learning_rate": 0.08882093798958751,
      "loss": 0.0,
      "num_input_tokens_seen": 7097648,
      "step": 25350
    },
    {
      "epoch": 281.72222222222223,
      "grad_norm": 2.016582989483595e-08,
      "learning_rate": 0.08876715995987726,
      "loss": 0.0,
      "num_input_tokens_seen": 7099088,
      "step": 25355
    },
    {
      "epoch": 281.77777777777777,
      "grad_norm": 2.4170457635364073e-08,
      "learning_rate": 0.08871339137304052,
      "loss": 0.0,
      "num_input_tokens_seen": 7100496,
      "step": 25360
    },
    {
      "epoch": 281.8333333333333,
      "grad_norm": 3.066928044859196e-08,
      "learning_rate": 0.0886596322373689,
      "loss": 0.0,
      "num_input_tokens_seen": 7101904,
      "step": 25365
    },
    {
      "epoch": 281.8888888888889,
      "grad_norm": 6.682033415472688e-08,
      "learning_rate": 0.08860588256115293,
      "loss": 0.0,
      "num_input_tokens_seen": 7103296,
      "step": 25370
    },
    {
      "epoch": 281.94444444444446,
      "grad_norm": 3.072559096040095e-08,
      "learning_rate": 0.0885521423526814,
      "loss": 0.0,
      "num_input_tokens_seen": 7104656,
      "step": 25375
    },
    {
      "epoch": 282.0,
      "grad_norm": 4.9042281347055905e-08,
      "learning_rate": 0.08849841162024165,
      "loss": 0.0,
      "num_input_tokens_seen": 7106048,
      "step": 25380
    },
    {
      "epoch": 282.05555555555554,
      "grad_norm": 4.155149468942909e-08,
      "learning_rate": 0.08844469037211973,
      "loss": 0.0,
      "num_input_tokens_seen": 7107472,
      "step": 25385
    },
    {
      "epoch": 282.1111111111111,
      "grad_norm": 1.4877597820373012e-08,
      "learning_rate": 0.08839097861660014,
      "loss": 0.0,
      "num_input_tokens_seen": 7108832,
      "step": 25390
    },
    {
      "epoch": 282.1666666666667,
      "grad_norm": 1.4524855096453848e-08,
      "learning_rate": 0.08833727636196585,
      "loss": 0.0,
      "num_input_tokens_seen": 7110256,
      "step": 25395
    },
    {
      "epoch": 282.22222222222223,
      "grad_norm": 2.0605630979275702e-08,
      "learning_rate": 0.08828358361649848,
      "loss": 0.0,
      "num_input_tokens_seen": 7111664,
      "step": 25400
    },
    {
      "epoch": 282.22222222222223,
      "eval_loss": 1.6702377796173096,
      "eval_runtime": 1.1841,
      "eval_samples_per_second": 33.781,
      "eval_steps_per_second": 16.891,
      "num_input_tokens_seen": 7111664,
      "step": 25400
    },
    {
      "epoch": 282.27777777777777,
      "grad_norm": 2.6683323994802777e-08,
      "learning_rate": 0.08822990038847807,
      "loss": 0.0,
      "num_input_tokens_seen": 7113072,
      "step": 25405
    },
    {
      "epoch": 282.3333333333333,
      "grad_norm": 1.5052901147782904e-08,
      "learning_rate": 0.08817622668618325,
      "loss": 0.0,
      "num_input_tokens_seen": 7114480,
      "step": 25410
    },
    {
      "epoch": 282.3888888888889,
      "grad_norm": 9.614884888264896e-09,
      "learning_rate": 0.08812256251789125,
      "loss": 0.0,
      "num_input_tokens_seen": 7115888,
      "step": 25415
    },
    {
      "epoch": 282.44444444444446,
      "grad_norm": 9.714947957206732e-09,
      "learning_rate": 0.08806890789187766,
      "loss": 0.0,
      "num_input_tokens_seen": 7117280,
      "step": 25420
    },
    {
      "epoch": 282.5,
      "grad_norm": 2.9021046898947134e-08,
      "learning_rate": 0.08801526281641672,
      "loss": 0.0,
      "num_input_tokens_seen": 7118656,
      "step": 25425
    },
    {
      "epoch": 282.55555555555554,
      "grad_norm": 2.124936493430596e-08,
      "learning_rate": 0.0879616272997813,
      "loss": 0.0,
      "num_input_tokens_seen": 7120048,
      "step": 25430
    },
    {
      "epoch": 282.6111111111111,
      "grad_norm": 3.225665068384842e-08,
      "learning_rate": 0.08790800135024247,
      "loss": 0.0,
      "num_input_tokens_seen": 7121440,
      "step": 25435
    },
    {
      "epoch": 282.6666666666667,
      "grad_norm": 1.6655880230587172e-08,
      "learning_rate": 0.08785438497607023,
      "loss": 0.0,
      "num_input_tokens_seen": 7122880,
      "step": 25440
    },
    {
      "epoch": 282.72222222222223,
      "grad_norm": 1.4222165667376885e-08,
      "learning_rate": 0.08780077818553277,
      "loss": 0.0,
      "num_input_tokens_seen": 7124304,
      "step": 25445
    },
    {
      "epoch": 282.77777777777777,
      "grad_norm": 2.7446331429814563e-08,
      "learning_rate": 0.0877471809868969,
      "loss": 0.0,
      "num_input_tokens_seen": 7125696,
      "step": 25450
    },
    {
      "epoch": 282.8333333333333,
      "grad_norm": 2.320079595108382e-08,
      "learning_rate": 0.08769359338842811,
      "loss": 0.0,
      "num_input_tokens_seen": 7127120,
      "step": 25455
    },
    {
      "epoch": 282.8888888888889,
      "grad_norm": 1.3539780852056538e-08,
      "learning_rate": 0.08764001539839016,
      "loss": 0.0,
      "num_input_tokens_seen": 7128496,
      "step": 25460
    },
    {
      "epoch": 282.94444444444446,
      "grad_norm": 3.0487953495139664e-08,
      "learning_rate": 0.08758644702504548,
      "loss": 0.0,
      "num_input_tokens_seen": 7129936,
      "step": 25465
    },
    {
      "epoch": 283.0,
      "grad_norm": 1.073284483510406e-08,
      "learning_rate": 0.0875328882766551,
      "loss": 0.0,
      "num_input_tokens_seen": 7131328,
      "step": 25470
    },
    {
      "epoch": 283.05555555555554,
      "grad_norm": 1.2352363576439984e-08,
      "learning_rate": 0.08747933916147828,
      "loss": 0.0,
      "num_input_tokens_seen": 7132720,
      "step": 25475
    },
    {
      "epoch": 283.1111111111111,
      "grad_norm": 7.06026526131609e-08,
      "learning_rate": 0.0874257996877731,
      "loss": 0.0,
      "num_input_tokens_seen": 7134096,
      "step": 25480
    },
    {
      "epoch": 283.1666666666667,
      "grad_norm": 3.1028093872009777e-08,
      "learning_rate": 0.08737226986379593,
      "loss": 0.0,
      "num_input_tokens_seen": 7135520,
      "step": 25485
    },
    {
      "epoch": 283.22222222222223,
      "grad_norm": 2.2128306298441203e-08,
      "learning_rate": 0.08731874969780173,
      "loss": 0.0,
      "num_input_tokens_seen": 7136944,
      "step": 25490
    },
    {
      "epoch": 283.27777777777777,
      "grad_norm": 2.632102003019554e-08,
      "learning_rate": 0.08726523919804412,
      "loss": 0.0,
      "num_input_tokens_seen": 7138352,
      "step": 25495
    },
    {
      "epoch": 283.3333333333333,
      "grad_norm": 3.0899787617499896e-08,
      "learning_rate": 0.08721173837277492,
      "loss": 0.0,
      "num_input_tokens_seen": 7139744,
      "step": 25500
    },
    {
      "epoch": 283.3888888888889,
      "grad_norm": 1.1211405137601105e-08,
      "learning_rate": 0.08715824723024479,
      "loss": 0.0,
      "num_input_tokens_seen": 7141136,
      "step": 25505
    },
    {
      "epoch": 283.44444444444446,
      "grad_norm": 1.9015747199091493e-08,
      "learning_rate": 0.08710476577870258,
      "loss": 0.0,
      "num_input_tokens_seen": 7142544,
      "step": 25510
    },
    {
      "epoch": 283.5,
      "grad_norm": 7.0314420952399814e-09,
      "learning_rate": 0.08705129402639587,
      "loss": 0.0,
      "num_input_tokens_seen": 7143968,
      "step": 25515
    },
    {
      "epoch": 283.55555555555554,
      "grad_norm": 2.828933354237506e-08,
      "learning_rate": 0.08699783198157078,
      "loss": 0.0,
      "num_input_tokens_seen": 7145328,
      "step": 25520
    },
    {
      "epoch": 283.6111111111111,
      "grad_norm": 1.5880754489216997e-08,
      "learning_rate": 0.08694437965247163,
      "loss": 0.0,
      "num_input_tokens_seen": 7146704,
      "step": 25525
    },
    {
      "epoch": 283.6666666666667,
      "grad_norm": 2.8424947728922234e-08,
      "learning_rate": 0.08689093704734165,
      "loss": 0.0,
      "num_input_tokens_seen": 7148112,
      "step": 25530
    },
    {
      "epoch": 283.72222222222223,
      "grad_norm": 3.1219524743164584e-08,
      "learning_rate": 0.08683750417442222,
      "loss": 0.0,
      "num_input_tokens_seen": 7149520,
      "step": 25535
    },
    {
      "epoch": 283.77777777777777,
      "grad_norm": 2.1838742370050568e-08,
      "learning_rate": 0.08678408104195334,
      "loss": 0.0,
      "num_input_tokens_seen": 7150896,
      "step": 25540
    },
    {
      "epoch": 283.8333333333333,
      "grad_norm": 4.9822013181710645e-08,
      "learning_rate": 0.08673066765817365,
      "loss": 0.0,
      "num_input_tokens_seen": 7152336,
      "step": 25545
    },
    {
      "epoch": 283.8888888888889,
      "grad_norm": 2.8122386197537708e-08,
      "learning_rate": 0.08667726403132005,
      "loss": 0.0,
      "num_input_tokens_seen": 7153728,
      "step": 25550
    },
    {
      "epoch": 283.94444444444446,
      "grad_norm": 2.472248894491713e-08,
      "learning_rate": 0.0866238701696281,
      "loss": 0.0,
      "num_input_tokens_seen": 7155136,
      "step": 25555
    },
    {
      "epoch": 284.0,
      "grad_norm": 7.328306850240551e-08,
      "learning_rate": 0.08657048608133185,
      "loss": 0.0,
      "num_input_tokens_seen": 7156512,
      "step": 25560
    },
    {
      "epoch": 284.05555555555554,
      "grad_norm": 7.82149243150343e-08,
      "learning_rate": 0.08651711177466369,
      "loss": 0.0,
      "num_input_tokens_seen": 7157936,
      "step": 25565
    },
    {
      "epoch": 284.1111111111111,
      "grad_norm": 3.4778427249193555e-08,
      "learning_rate": 0.08646374725785466,
      "loss": 0.0,
      "num_input_tokens_seen": 7159360,
      "step": 25570
    },
    {
      "epoch": 284.1666666666667,
      "grad_norm": 2.8086489578527107e-08,
      "learning_rate": 0.08641039253913434,
      "loss": 0.0,
      "num_input_tokens_seen": 7160704,
      "step": 25575
    },
    {
      "epoch": 284.22222222222223,
      "grad_norm": 8.06799604902153e-09,
      "learning_rate": 0.08635704762673052,
      "loss": 0.0,
      "num_input_tokens_seen": 7162144,
      "step": 25580
    },
    {
      "epoch": 284.27777777777777,
      "grad_norm": 1.0864483535044656e-08,
      "learning_rate": 0.08630371252886981,
      "loss": 0.0,
      "num_input_tokens_seen": 7163536,
      "step": 25585
    },
    {
      "epoch": 284.3333333333333,
      "grad_norm": 1.2512092695260435e-08,
      "learning_rate": 0.08625038725377704,
      "loss": 0.0,
      "num_input_tokens_seen": 7164960,
      "step": 25590
    },
    {
      "epoch": 284.3888888888889,
      "grad_norm": 7.57437845777531e-09,
      "learning_rate": 0.08619707180967566,
      "loss": 0.0,
      "num_input_tokens_seen": 7166320,
      "step": 25595
    },
    {
      "epoch": 284.44444444444446,
      "grad_norm": 1.721418918521067e-08,
      "learning_rate": 0.08614376620478768,
      "loss": 0.0,
      "num_input_tokens_seen": 7167744,
      "step": 25600
    },
    {
      "epoch": 284.44444444444446,
      "eval_loss": 1.662286400794983,
      "eval_runtime": 1.1977,
      "eval_samples_per_second": 33.398,
      "eval_steps_per_second": 16.699,
      "num_input_tokens_seen": 7167744,
      "step": 25600
    },
    {
      "epoch": 284.5,
      "grad_norm": 1.0305538644672652e-08,
      "learning_rate": 0.08609047044733344,
      "loss": 0.0,
      "num_input_tokens_seen": 7169152,
      "step": 25605
    },
    {
      "epoch": 284.55555555555554,
      "grad_norm": 1.4732688846663677e-08,
      "learning_rate": 0.08603718454553168,
      "loss": 0.0,
      "num_input_tokens_seen": 7170560,
      "step": 25610
    },
    {
      "epoch": 284.6111111111111,
      "grad_norm": 1.3890521621817697e-08,
      "learning_rate": 0.08598390850759997,
      "loss": 0.0,
      "num_input_tokens_seen": 7171984,
      "step": 25615
    },
    {
      "epoch": 284.6666666666667,
      "grad_norm": 1.6167080119089405e-08,
      "learning_rate": 0.08593064234175397,
      "loss": 0.0,
      "num_input_tokens_seen": 7173376,
      "step": 25620
    },
    {
      "epoch": 284.72222222222223,
      "grad_norm": 1.801803506396027e-08,
      "learning_rate": 0.08587738605620815,
      "loss": 0.0,
      "num_input_tokens_seen": 7174784,
      "step": 25625
    },
    {
      "epoch": 284.77777777777777,
      "grad_norm": 2.4993008551632556e-08,
      "learning_rate": 0.08582413965917512,
      "loss": 0.0,
      "num_input_tokens_seen": 7176176,
      "step": 25630
    },
    {
      "epoch": 284.8333333333333,
      "grad_norm": 1.8330229778484863e-08,
      "learning_rate": 0.08577090315886628,
      "loss": 0.0,
      "num_input_tokens_seen": 7177584,
      "step": 25635
    },
    {
      "epoch": 284.8888888888889,
      "grad_norm": 2.4624357664038143e-08,
      "learning_rate": 0.08571767656349136,
      "loss": 0.0,
      "num_input_tokens_seen": 7178944,
      "step": 25640
    },
    {
      "epoch": 284.94444444444446,
      "grad_norm": 1.4453395813518455e-08,
      "learning_rate": 0.08566445988125847,
      "loss": 0.0,
      "num_input_tokens_seen": 7180368,
      "step": 25645
    },
    {
      "epoch": 285.0,
      "grad_norm": 1.733711130214033e-08,
      "learning_rate": 0.08561125312037436,
      "loss": 0.0,
      "num_input_tokens_seen": 7181728,
      "step": 25650
    },
    {
      "epoch": 285.05555555555554,
      "grad_norm": 5.664668734084444e-08,
      "learning_rate": 0.08555805628904424,
      "loss": 0.0,
      "num_input_tokens_seen": 7183120,
      "step": 25655
    },
    {
      "epoch": 285.1111111111111,
      "grad_norm": 1.890116330116598e-08,
      "learning_rate": 0.08550486939547161,
      "loss": 0.0,
      "num_input_tokens_seen": 7184528,
      "step": 25660
    },
    {
      "epoch": 285.1666666666667,
      "grad_norm": 1.681114802920547e-08,
      "learning_rate": 0.08545169244785869,
      "loss": 0.0,
      "num_input_tokens_seen": 7185904,
      "step": 25665
    },
    {
      "epoch": 285.22222222222223,
      "grad_norm": 5.2139967010589316e-08,
      "learning_rate": 0.08539852545440589,
      "loss": 0.0,
      "num_input_tokens_seen": 7187344,
      "step": 25670
    },
    {
      "epoch": 285.27777777777777,
      "grad_norm": 2.4297666101347204e-08,
      "learning_rate": 0.08534536842331235,
      "loss": 0.0,
      "num_input_tokens_seen": 7188720,
      "step": 25675
    },
    {
      "epoch": 285.3333333333333,
      "grad_norm": 2.5102950829136716e-08,
      "learning_rate": 0.08529222136277545,
      "loss": 0.0,
      "num_input_tokens_seen": 7190144,
      "step": 25680
    },
    {
      "epoch": 285.3888888888889,
      "grad_norm": 6.530838447815768e-08,
      "learning_rate": 0.08523908428099125,
      "loss": 0.0,
      "num_input_tokens_seen": 7191536,
      "step": 25685
    },
    {
      "epoch": 285.44444444444446,
      "grad_norm": 2.818372202284536e-08,
      "learning_rate": 0.08518595718615402,
      "loss": 0.0,
      "num_input_tokens_seen": 7192912,
      "step": 25690
    },
    {
      "epoch": 285.5,
      "grad_norm": 8.019215869126128e-08,
      "learning_rate": 0.08513284008645675,
      "loss": 0.0,
      "num_input_tokens_seen": 7194304,
      "step": 25695
    },
    {
      "epoch": 285.55555555555554,
      "grad_norm": 2.5187485874766935e-08,
      "learning_rate": 0.08507973299009065,
      "loss": 0.0,
      "num_input_tokens_seen": 7195744,
      "step": 25700
    },
    {
      "epoch": 285.6111111111111,
      "grad_norm": 7.819255642971257e-08,
      "learning_rate": 0.08502663590524563,
      "loss": 0.0,
      "num_input_tokens_seen": 7197120,
      "step": 25705
    },
    {
      "epoch": 285.6666666666667,
      "grad_norm": 2.2346643646642406e-08,
      "learning_rate": 0.08497354884010981,
      "loss": 0.0,
      "num_input_tokens_seen": 7198560,
      "step": 25710
    },
    {
      "epoch": 285.72222222222223,
      "grad_norm": 1.3916156227367082e-08,
      "learning_rate": 0.0849204718028699,
      "loss": 0.0,
      "num_input_tokens_seen": 7199968,
      "step": 25715
    },
    {
      "epoch": 285.77777777777777,
      "grad_norm": 3.311386009841044e-08,
      "learning_rate": 0.08486740480171118,
      "loss": 0.0,
      "num_input_tokens_seen": 7201408,
      "step": 25720
    },
    {
      "epoch": 285.8333333333333,
      "grad_norm": 1.4031612316500741e-08,
      "learning_rate": 0.08481434784481706,
      "loss": 0.0,
      "num_input_tokens_seen": 7202768,
      "step": 25725
    },
    {
      "epoch": 285.8888888888889,
      "grad_norm": 2.4436129564264775e-08,
      "learning_rate": 0.08476130094036968,
      "loss": 0.0,
      "num_input_tokens_seen": 7204128,
      "step": 25730
    },
    {
      "epoch": 285.94444444444446,
      "grad_norm": 1.353325806974226e-08,
      "learning_rate": 0.08470826409654961,
      "loss": 0.0,
      "num_input_tokens_seen": 7205536,
      "step": 25735
    },
    {
      "epoch": 286.0,
      "grad_norm": 2.124575182449462e-08,
      "learning_rate": 0.08465523732153564,
      "loss": 0.0,
      "num_input_tokens_seen": 7206960,
      "step": 25740
    },
    {
      "epoch": 286.05555555555554,
      "grad_norm": 3.309677509832909e-08,
      "learning_rate": 0.08460222062350532,
      "loss": 0.0,
      "num_input_tokens_seen": 7208352,
      "step": 25745
    },
    {
      "epoch": 286.1111111111111,
      "grad_norm": 2.7854696327267447e-08,
      "learning_rate": 0.08454921401063442,
      "loss": 0.0,
      "num_input_tokens_seen": 7209696,
      "step": 25750
    },
    {
      "epoch": 286.1666666666667,
      "grad_norm": 2.7937186786175516e-08,
      "learning_rate": 0.08449621749109716,
      "loss": 0.0,
      "num_input_tokens_seen": 7211120,
      "step": 25755
    },
    {
      "epoch": 286.22222222222223,
      "grad_norm": 1.2351906164553839e-08,
      "learning_rate": 0.08444323107306641,
      "loss": 0.0,
      "num_input_tokens_seen": 7212528,
      "step": 25760
    },
    {
      "epoch": 286.27777777777777,
      "grad_norm": 7.111579236607213e-08,
      "learning_rate": 0.0843902547647132,
      "loss": 0.0,
      "num_input_tokens_seen": 7213920,
      "step": 25765
    },
    {
      "epoch": 286.3333333333333,
      "grad_norm": 8.411700669341826e-09,
      "learning_rate": 0.0843372885742072,
      "loss": 0.0,
      "num_input_tokens_seen": 7215344,
      "step": 25770
    },
    {
      "epoch": 286.3888888888889,
      "grad_norm": 1.9614804003253994e-08,
      "learning_rate": 0.08428433250971652,
      "loss": 0.0,
      "num_input_tokens_seen": 7216752,
      "step": 25775
    },
    {
      "epoch": 286.44444444444446,
      "grad_norm": 2.3463732290451844e-08,
      "learning_rate": 0.08423138657940757,
      "loss": 0.0,
      "num_input_tokens_seen": 7218096,
      "step": 25780
    },
    {
      "epoch": 286.5,
      "grad_norm": 1.4597876685229494e-08,
      "learning_rate": 0.08417845079144536,
      "loss": 0.0,
      "num_input_tokens_seen": 7219520,
      "step": 25785
    },
    {
      "epoch": 286.55555555555554,
      "grad_norm": 1.6189469320693206e-08,
      "learning_rate": 0.08412552515399314,
      "loss": 0.0,
      "num_input_tokens_seen": 7220928,
      "step": 25790
    },
    {
      "epoch": 286.6111111111111,
      "grad_norm": 2.5675721104789773e-08,
      "learning_rate": 0.08407260967521278,
      "loss": 0.0,
      "num_input_tokens_seen": 7222336,
      "step": 25795
    },
    {
      "epoch": 286.6666666666667,
      "grad_norm": 7.652154465631611e-08,
      "learning_rate": 0.08401970436326454,
      "loss": 0.0,
      "num_input_tokens_seen": 7223696,
      "step": 25800
    },
    {
      "epoch": 286.6666666666667,
      "eval_loss": 1.5949755907058716,
      "eval_runtime": 1.1816,
      "eval_samples_per_second": 33.853,
      "eval_steps_per_second": 16.927,
      "num_input_tokens_seen": 7223696,
      "step": 25800
    },
    {
      "epoch": 286.72222222222223,
      "grad_norm": 1.708464480998373e-08,
      "learning_rate": 0.08396680922630702,
      "loss": 0.0,
      "num_input_tokens_seen": 7225088,
      "step": 25805
    },
    {
      "epoch": 286.77777777777777,
      "grad_norm": 1.2967107387851229e-08,
      "learning_rate": 0.08391392427249732,
      "loss": 0.0,
      "num_input_tokens_seen": 7226448,
      "step": 25810
    },
    {
      "epoch": 286.8333333333333,
      "grad_norm": 8.702239995272976e-08,
      "learning_rate": 0.08386104950999107,
      "loss": 0.0,
      "num_input_tokens_seen": 7227872,
      "step": 25815
    },
    {
      "epoch": 286.8888888888889,
      "grad_norm": 3.3712609592839726e-08,
      "learning_rate": 0.0838081849469421,
      "loss": 0.0,
      "num_input_tokens_seen": 7229296,
      "step": 25820
    },
    {
      "epoch": 286.94444444444446,
      "grad_norm": 3.007387050502075e-08,
      "learning_rate": 0.08375533059150281,
      "loss": 0.0,
      "num_input_tokens_seen": 7230704,
      "step": 25825
    },
    {
      "epoch": 287.0,
      "grad_norm": 2.5172289142005866e-08,
      "learning_rate": 0.08370248645182406,
      "loss": 0.0,
      "num_input_tokens_seen": 7232128,
      "step": 25830
    },
    {
      "epoch": 287.05555555555554,
      "grad_norm": 9.219456842401996e-08,
      "learning_rate": 0.083649652536055,
      "loss": 0.0,
      "num_input_tokens_seen": 7233552,
      "step": 25835
    },
    {
      "epoch": 287.1111111111111,
      "grad_norm": 2.405279531103588e-08,
      "learning_rate": 0.08359682885234339,
      "loss": 0.0,
      "num_input_tokens_seen": 7234976,
      "step": 25840
    },
    {
      "epoch": 287.1666666666667,
      "grad_norm": 7.325729001195214e-08,
      "learning_rate": 0.08354401540883516,
      "loss": 0.0,
      "num_input_tokens_seen": 7236352,
      "step": 25845
    },
    {
      "epoch": 287.22222222222223,
      "grad_norm": 2.158351541936554e-08,
      "learning_rate": 0.0834912122136749,
      "loss": 0.0,
      "num_input_tokens_seen": 7237744,
      "step": 25850
    },
    {
      "epoch": 287.27777777777777,
      "grad_norm": 2.2415479250526005e-08,
      "learning_rate": 0.0834384192750056,
      "loss": 0.0,
      "num_input_tokens_seen": 7239152,
      "step": 25855
    },
    {
      "epoch": 287.3333333333333,
      "grad_norm": 1.5851764345597985e-08,
      "learning_rate": 0.08338563660096844,
      "loss": 0.0,
      "num_input_tokens_seen": 7240560,
      "step": 25860
    },
    {
      "epoch": 287.3888888888889,
      "grad_norm": 1.916530223411428e-08,
      "learning_rate": 0.08333286419970329,
      "loss": 0.0,
      "num_input_tokens_seen": 7241984,
      "step": 25865
    },
    {
      "epoch": 287.44444444444446,
      "grad_norm": 4.513086437896163e-08,
      "learning_rate": 0.08328010207934824,
      "loss": 0.0,
      "num_input_tokens_seen": 7243392,
      "step": 25870
    },
    {
      "epoch": 287.5,
      "grad_norm": 1.388645731736915e-08,
      "learning_rate": 0.08322735024803989,
      "loss": 0.0,
      "num_input_tokens_seen": 7244784,
      "step": 25875
    },
    {
      "epoch": 287.55555555555554,
      "grad_norm": 1.9481065649529228e-08,
      "learning_rate": 0.08317460871391331,
      "loss": 0.0,
      "num_input_tokens_seen": 7246176,
      "step": 25880
    },
    {
      "epoch": 287.6111111111111,
      "grad_norm": 1.7212659741971947e-08,
      "learning_rate": 0.08312187748510179,
      "loss": 0.0,
      "num_input_tokens_seen": 7247552,
      "step": 25885
    },
    {
      "epoch": 287.6666666666667,
      "grad_norm": 1.7251368333859318e-08,
      "learning_rate": 0.08306915656973726,
      "loss": 0.0,
      "num_input_tokens_seen": 7248960,
      "step": 25890
    },
    {
      "epoch": 287.72222222222223,
      "grad_norm": 2.7657174328510337e-08,
      "learning_rate": 0.08301644597594988,
      "loss": 0.0,
      "num_input_tokens_seen": 7250368,
      "step": 25895
    },
    {
      "epoch": 287.77777777777777,
      "grad_norm": 7.883360808591533e-08,
      "learning_rate": 0.08296374571186826,
      "loss": 0.0,
      "num_input_tokens_seen": 7251760,
      "step": 25900
    },
    {
      "epoch": 287.8333333333333,
      "grad_norm": 3.950953342268804e-08,
      "learning_rate": 0.08291105578561955,
      "loss": 0.0,
      "num_input_tokens_seen": 7253120,
      "step": 25905
    },
    {
      "epoch": 287.8888888888889,
      "grad_norm": 1.9974838494363212e-07,
      "learning_rate": 0.08285837620532904,
      "loss": 0.0,
      "num_input_tokens_seen": 7254496,
      "step": 25910
    },
    {
      "epoch": 287.94444444444446,
      "grad_norm": 1.7508879679439815e-08,
      "learning_rate": 0.0828057069791207,
      "loss": 0.0,
      "num_input_tokens_seen": 7255904,
      "step": 25915
    },
    {
      "epoch": 288.0,
      "grad_norm": 5.471023882819281e-07,
      "learning_rate": 0.0827530481151168,
      "loss": 0.0,
      "num_input_tokens_seen": 7257296,
      "step": 25920
    },
    {
      "epoch": 288.05555555555554,
      "grad_norm": 1.6703793903616315e-08,
      "learning_rate": 0.08270039962143792,
      "loss": 0.0,
      "num_input_tokens_seen": 7258688,
      "step": 25925
    },
    {
      "epoch": 288.1111111111111,
      "grad_norm": 2.716879166086983e-08,
      "learning_rate": 0.08264776150620314,
      "loss": 0.0,
      "num_input_tokens_seen": 7260064,
      "step": 25930
    },
    {
      "epoch": 288.1666666666667,
      "grad_norm": 3.313143537297947e-08,
      "learning_rate": 0.08259513377753,
      "loss": 0.0,
      "num_input_tokens_seen": 7261472,
      "step": 25935
    },
    {
      "epoch": 288.22222222222223,
      "grad_norm": 2.3479900690404065e-08,
      "learning_rate": 0.08254251644353423,
      "loss": 0.0,
      "num_input_tokens_seen": 7262896,
      "step": 25940
    },
    {
      "epoch": 288.27777777777777,
      "grad_norm": 6.312862410595699e-08,
      "learning_rate": 0.08248990951233022,
      "loss": 0.0,
      "num_input_tokens_seen": 7264288,
      "step": 25945
    },
    {
      "epoch": 288.3333333333333,
      "grad_norm": 3.5392833552805314e-08,
      "learning_rate": 0.08243731299203048,
      "loss": 0.0,
      "num_input_tokens_seen": 7265696,
      "step": 25950
    },
    {
      "epoch": 288.3888888888889,
      "grad_norm": 2.2425702184136753e-08,
      "learning_rate": 0.08238472689074612,
      "loss": 0.0,
      "num_input_tokens_seen": 7267088,
      "step": 25955
    },
    {
      "epoch": 288.44444444444446,
      "grad_norm": 4.763379024552705e-08,
      "learning_rate": 0.08233215121658666,
      "loss": 0.0,
      "num_input_tokens_seen": 7268496,
      "step": 25960
    },
    {
      "epoch": 288.5,
      "grad_norm": 1.9765293401974304e-08,
      "learning_rate": 0.08227958597765982,
      "loss": 0.0,
      "num_input_tokens_seen": 7269888,
      "step": 25965
    },
    {
      "epoch": 288.55555555555554,
      "grad_norm": 2.2995470416731223e-08,
      "learning_rate": 0.08222703118207181,
      "loss": 0.0,
      "num_input_tokens_seen": 7271296,
      "step": 25970
    },
    {
      "epoch": 288.6111111111111,
      "grad_norm": 1.86130399981721e-08,
      "learning_rate": 0.08217448683792734,
      "loss": 0.0,
      "num_input_tokens_seen": 7272720,
      "step": 25975
    },
    {
      "epoch": 288.6666666666667,
      "grad_norm": 2.1645307768380917e-08,
      "learning_rate": 0.08212195295332926,
      "loss": 0.0,
      "num_input_tokens_seen": 7274160,
      "step": 25980
    },
    {
      "epoch": 288.72222222222223,
      "grad_norm": 4.940684306120602e-08,
      "learning_rate": 0.08206942953637915,
      "loss": 0.0,
      "num_input_tokens_seen": 7275552,
      "step": 25985
    },
    {
      "epoch": 288.77777777777777,
      "grad_norm": 1.7590810585943473e-08,
      "learning_rate": 0.08201691659517658,
      "loss": 0.0,
      "num_input_tokens_seen": 7276960,
      "step": 25990
    },
    {
      "epoch": 288.8333333333333,
      "grad_norm": 1.8019461478502308e-08,
      "learning_rate": 0.08196441413781981,
      "loss": 0.0,
      "num_input_tokens_seen": 7278352,
      "step": 25995
    },
    {
      "epoch": 288.8888888888889,
      "grad_norm": 2.7051685336232367e-08,
      "learning_rate": 0.08191192217240544,
      "loss": 0.0,
      "num_input_tokens_seen": 7279760,
      "step": 26000
    },
    {
      "epoch": 288.8888888888889,
      "eval_loss": 1.6426975727081299,
      "eval_runtime": 1.1865,
      "eval_samples_per_second": 33.714,
      "eval_steps_per_second": 16.857,
      "num_input_tokens_seen": 7279760,
      "step": 26000
    },
    {
      "epoch": 288.94444444444446,
      "grad_norm": 1.946239613914713e-08,
      "learning_rate": 0.08185944070702823,
      "loss": 0.0,
      "num_input_tokens_seen": 7281200,
      "step": 26005
    },
    {
      "epoch": 289.0,
      "grad_norm": 9.077303531057623e-08,
      "learning_rate": 0.08180696974978159,
      "loss": 0.0,
      "num_input_tokens_seen": 7282608,
      "step": 26010
    },
    {
      "epoch": 289.05555555555554,
      "grad_norm": 1.5846913115069583e-08,
      "learning_rate": 0.08175450930875724,
      "loss": 0.0,
      "num_input_tokens_seen": 7283984,
      "step": 26015
    },
    {
      "epoch": 289.1111111111111,
      "grad_norm": 2.3136960791703132e-08,
      "learning_rate": 0.08170205939204513,
      "loss": 0.0,
      "num_input_tokens_seen": 7285408,
      "step": 26020
    },
    {
      "epoch": 289.1666666666667,
      "grad_norm": 1.71815219829341e-08,
      "learning_rate": 0.08164962000773379,
      "loss": 0.0,
      "num_input_tokens_seen": 7286816,
      "step": 26025
    },
    {
      "epoch": 289.22222222222223,
      "grad_norm": 1.4892239441621768e-08,
      "learning_rate": 0.08159719116390995,
      "loss": 0.0,
      "num_input_tokens_seen": 7288224,
      "step": 26030
    },
    {
      "epoch": 289.27777777777777,
      "grad_norm": 1.3049862523928368e-08,
      "learning_rate": 0.08154477286865887,
      "loss": 0.0,
      "num_input_tokens_seen": 7289600,
      "step": 26035
    },
    {
      "epoch": 289.3333333333333,
      "grad_norm": 2.0149006019209992e-08,
      "learning_rate": 0.08149236513006404,
      "loss": 0.0,
      "num_input_tokens_seen": 7290976,
      "step": 26040
    },
    {
      "epoch": 289.3888888888889,
      "grad_norm": 1.5501193217914988e-08,
      "learning_rate": 0.08143996795620746,
      "loss": 0.0,
      "num_input_tokens_seen": 7292368,
      "step": 26045
    },
    {
      "epoch": 289.44444444444446,
      "grad_norm": 2.0196569749941773e-08,
      "learning_rate": 0.08138758135516938,
      "loss": 0.0,
      "num_input_tokens_seen": 7293808,
      "step": 26050
    },
    {
      "epoch": 289.5,
      "grad_norm": 1.365544761711135e-07,
      "learning_rate": 0.08133520533502851,
      "loss": 0.0,
      "num_input_tokens_seen": 7295184,
      "step": 26055
    },
    {
      "epoch": 289.55555555555554,
      "grad_norm": 9.439200532312952e-09,
      "learning_rate": 0.08128283990386184,
      "loss": 0.0,
      "num_input_tokens_seen": 7296576,
      "step": 26060
    },
    {
      "epoch": 289.6111111111111,
      "grad_norm": 1.004661953629693e-08,
      "learning_rate": 0.08123048506974488,
      "loss": 0.0,
      "num_input_tokens_seen": 7297968,
      "step": 26065
    },
    {
      "epoch": 289.6666666666667,
      "grad_norm": 7.113614142184588e-09,
      "learning_rate": 0.08117814084075124,
      "loss": 0.0,
      "num_input_tokens_seen": 7299344,
      "step": 26070
    },
    {
      "epoch": 289.72222222222223,
      "grad_norm": 6.583721123831765e-09,
      "learning_rate": 0.08112580722495318,
      "loss": 0.0,
      "num_input_tokens_seen": 7300736,
      "step": 26075
    },
    {
      "epoch": 289.77777777777777,
      "grad_norm": 8.265135242879751e-09,
      "learning_rate": 0.08107348423042122,
      "loss": 0.0,
      "num_input_tokens_seen": 7302128,
      "step": 26080
    },
    {
      "epoch": 289.8333333333333,
      "grad_norm": 1.0324907151471052e-07,
      "learning_rate": 0.08102117186522413,
      "loss": 0.0,
      "num_input_tokens_seen": 7303536,
      "step": 26085
    },
    {
      "epoch": 289.8888888888889,
      "grad_norm": 1.2164856677543412e-08,
      "learning_rate": 0.08096887013742916,
      "loss": 0.0,
      "num_input_tokens_seen": 7304960,
      "step": 26090
    },
    {
      "epoch": 289.94444444444446,
      "grad_norm": 8.889778690956973e-09,
      "learning_rate": 0.08091657905510198,
      "loss": 0.0,
      "num_input_tokens_seen": 7306368,
      "step": 26095
    },
    {
      "epoch": 290.0,
      "grad_norm": 1.8829211967386073e-08,
      "learning_rate": 0.08086429862630642,
      "loss": 0.0,
      "num_input_tokens_seen": 7307760,
      "step": 26100
    },
    {
      "epoch": 290.05555555555554,
      "grad_norm": 8.652305893974699e-08,
      "learning_rate": 0.08081202885910488,
      "loss": 0.0,
      "num_input_tokens_seen": 7309168,
      "step": 26105
    },
    {
      "epoch": 290.1111111111111,
      "grad_norm": 1.8978949967163317e-08,
      "learning_rate": 0.08075976976155795,
      "loss": 0.0,
      "num_input_tokens_seen": 7310624,
      "step": 26110
    },
    {
      "epoch": 290.1666666666667,
      "grad_norm": 1.072339639307529e-08,
      "learning_rate": 0.08070752134172461,
      "loss": 0.0,
      "num_input_tokens_seen": 7312048,
      "step": 26115
    },
    {
      "epoch": 290.22222222222223,
      "grad_norm": 1.1509294850498009e-08,
      "learning_rate": 0.08065528360766229,
      "loss": 0.0,
      "num_input_tokens_seen": 7313456,
      "step": 26120
    },
    {
      "epoch": 290.27777777777777,
      "grad_norm": 9.820499080603895e-09,
      "learning_rate": 0.08060305656742664,
      "loss": 0.0,
      "num_input_tokens_seen": 7314816,
      "step": 26125
    },
    {
      "epoch": 290.3333333333333,
      "grad_norm": 1.5427776389742576e-08,
      "learning_rate": 0.08055084022907182,
      "loss": 0.0,
      "num_input_tokens_seen": 7316208,
      "step": 26130
    },
    {
      "epoch": 290.3888888888889,
      "grad_norm": 1.4506763790222976e-08,
      "learning_rate": 0.08049863460065014,
      "loss": 0.0,
      "num_input_tokens_seen": 7317600,
      "step": 26135
    },
    {
      "epoch": 290.44444444444446,
      "grad_norm": 1.0975726993933677e-08,
      "learning_rate": 0.0804464396902124,
      "loss": 0.0,
      "num_input_tokens_seen": 7318976,
      "step": 26140
    },
    {
      "epoch": 290.5,
      "grad_norm": 3.844453289048033e-08,
      "learning_rate": 0.08039425550580777,
      "loss": 0.0,
      "num_input_tokens_seen": 7320416,
      "step": 26145
    },
    {
      "epoch": 290.55555555555554,
      "grad_norm": 1.3964563549961895e-07,
      "learning_rate": 0.08034208205548363,
      "loss": 0.0,
      "num_input_tokens_seen": 7321824,
      "step": 26150
    },
    {
      "epoch": 290.6111111111111,
      "grad_norm": 2.3858426345668704e-08,
      "learning_rate": 0.08028991934728581,
      "loss": 0.0,
      "num_input_tokens_seen": 7323200,
      "step": 26155
    },
    {
      "epoch": 290.6666666666667,
      "grad_norm": 1.987335629394238e-08,
      "learning_rate": 0.0802377673892585,
      "loss": 0.0,
      "num_input_tokens_seen": 7324576,
      "step": 26160
    },
    {
      "epoch": 290.72222222222223,
      "grad_norm": 2.12705657531842e-08,
      "learning_rate": 0.0801856261894441,
      "loss": 0.0,
      "num_input_tokens_seen": 7326048,
      "step": 26165
    },
    {
      "epoch": 290.77777777777777,
      "grad_norm": 2.096328088896371e-08,
      "learning_rate": 0.08013349575588354,
      "loss": 0.0,
      "num_input_tokens_seen": 7327392,
      "step": 26170
    },
    {
      "epoch": 290.8333333333333,
      "grad_norm": 1.602963983771133e-08,
      "learning_rate": 0.08008137609661586,
      "loss": 0.0,
      "num_input_tokens_seen": 7328800,
      "step": 26175
    },
    {
      "epoch": 290.8888888888889,
      "grad_norm": 2.090054174175293e-08,
      "learning_rate": 0.08002926721967872,
      "loss": 0.0,
      "num_input_tokens_seen": 7330240,
      "step": 26180
    },
    {
      "epoch": 290.94444444444446,
      "grad_norm": 1.913997138558443e-08,
      "learning_rate": 0.07997716913310782,
      "loss": 0.0,
      "num_input_tokens_seen": 7331632,
      "step": 26185
    },
    {
      "epoch": 291.0,
      "grad_norm": 5.697896554579529e-08,
      "learning_rate": 0.07992508184493745,
      "loss": 0.0,
      "num_input_tokens_seen": 7333008,
      "step": 26190
    },
    {
      "epoch": 291.05555555555554,
      "grad_norm": 2.711653834808203e-08,
      "learning_rate": 0.07987300536320001,
      "loss": 0.0,
      "num_input_tokens_seen": 7334384,
      "step": 26195
    },
    {
      "epoch": 291.1111111111111,
      "grad_norm": 1.8584678684874234e-08,
      "learning_rate": 0.07982093969592649,
      "loss": 0.0,
      "num_input_tokens_seen": 7335792,
      "step": 26200
    },
    {
      "epoch": 291.1111111111111,
      "eval_loss": 1.702783226966858,
      "eval_runtime": 1.1922,
      "eval_samples_per_second": 33.551,
      "eval_steps_per_second": 16.775,
      "num_input_tokens_seen": 7335792,
      "step": 26200
    },
    {
      "epoch": 291.1666666666667,
      "grad_norm": 1.8644804811174254e-08,
      "learning_rate": 0.07976888485114592,
      "loss": 0.0,
      "num_input_tokens_seen": 7337120,
      "step": 26205
    },
    {
      "epoch": 291.22222222222223,
      "grad_norm": 1.6680873571317534e-08,
      "learning_rate": 0.07971684083688595,
      "loss": 0.0,
      "num_input_tokens_seen": 7338496,
      "step": 26210
    },
    {
      "epoch": 291.27777777777777,
      "grad_norm": 3.0970930708917876e-08,
      "learning_rate": 0.0796648076611723,
      "loss": 0.0,
      "num_input_tokens_seen": 7339888,
      "step": 26215
    },
    {
      "epoch": 291.3333333333333,
      "grad_norm": 3.8184445827482705e-08,
      "learning_rate": 0.07961278533202922,
      "loss": 0.0,
      "num_input_tokens_seen": 7341328,
      "step": 26220
    },
    {
      "epoch": 291.3888888888889,
      "grad_norm": 2.19976996618243e-08,
      "learning_rate": 0.07956077385747919,
      "loss": 0.0,
      "num_input_tokens_seen": 7342768,
      "step": 26225
    },
    {
      "epoch": 291.44444444444446,
      "grad_norm": 3.3623521744630125e-08,
      "learning_rate": 0.079508773245543,
      "loss": 0.0,
      "num_input_tokens_seen": 7344160,
      "step": 26230
    },
    {
      "epoch": 291.5,
      "grad_norm": 1.5470256187199993e-08,
      "learning_rate": 0.07945678350423982,
      "loss": 0.0,
      "num_input_tokens_seen": 7345536,
      "step": 26235
    },
    {
      "epoch": 291.55555555555554,
      "grad_norm": 2.7764459176182754e-08,
      "learning_rate": 0.07940480464158717,
      "loss": 0.0,
      "num_input_tokens_seen": 7346960,
      "step": 26240
    },
    {
      "epoch": 291.6111111111111,
      "grad_norm": 2.562676826300958e-08,
      "learning_rate": 0.07935283666560076,
      "loss": 0.0,
      "num_input_tokens_seen": 7348320,
      "step": 26245
    },
    {
      "epoch": 291.6666666666667,
      "grad_norm": 1.6110798028989848e-08,
      "learning_rate": 0.07930087958429478,
      "loss": 0.0,
      "num_input_tokens_seen": 7349696,
      "step": 26250
    },
    {
      "epoch": 291.72222222222223,
      "grad_norm": 4.380024165584473e-08,
      "learning_rate": 0.07924893340568159,
      "loss": 0.0,
      "num_input_tokens_seen": 7351120,
      "step": 26255
    },
    {
      "epoch": 291.77777777777777,
      "grad_norm": 1.9265385731159768e-08,
      "learning_rate": 0.07919699813777205,
      "loss": 0.0,
      "num_input_tokens_seen": 7352560,
      "step": 26260
    },
    {
      "epoch": 291.8333333333333,
      "grad_norm": 1.39282974487287e-07,
      "learning_rate": 0.07914507378857515,
      "loss": 0.0,
      "num_input_tokens_seen": 7354000,
      "step": 26265
    },
    {
      "epoch": 291.8888888888889,
      "grad_norm": 2.454732594969755e-08,
      "learning_rate": 0.07909316036609822,
      "loss": 0.0,
      "num_input_tokens_seen": 7355440,
      "step": 26270
    },
    {
      "epoch": 291.94444444444446,
      "grad_norm": 4.8847184075384575e-08,
      "learning_rate": 0.07904125787834704,
      "loss": 0.0,
      "num_input_tokens_seen": 7356864,
      "step": 26275
    },
    {
      "epoch": 292.0,
      "grad_norm": 3.171048490457906e-08,
      "learning_rate": 0.07898936633332569,
      "loss": 0.0,
      "num_input_tokens_seen": 7358272,
      "step": 26280
    },
    {
      "epoch": 292.05555555555554,
      "grad_norm": 1.7901061966085763e-08,
      "learning_rate": 0.07893748573903635,
      "loss": 0.0,
      "num_input_tokens_seen": 7359632,
      "step": 26285
    },
    {
      "epoch": 292.1111111111111,
      "grad_norm": 1.1792218757022965e-08,
      "learning_rate": 0.0788856161034798,
      "loss": 0.0,
      "num_input_tokens_seen": 7361008,
      "step": 26290
    },
    {
      "epoch": 292.1666666666667,
      "grad_norm": 1.1211305661618098e-08,
      "learning_rate": 0.07883375743465487,
      "loss": 0.0,
      "num_input_tokens_seen": 7362400,
      "step": 26295
    },
    {
      "epoch": 292.22222222222223,
      "grad_norm": 1.4120656643967777e-08,
      "learning_rate": 0.07878190974055888,
      "loss": 0.0,
      "num_input_tokens_seen": 7363808,
      "step": 26300
    },
    {
      "epoch": 292.27777777777777,
      "grad_norm": 1.4382017354819254e-08,
      "learning_rate": 0.07873007302918746,
      "loss": 0.0,
      "num_input_tokens_seen": 7365232,
      "step": 26305
    },
    {
      "epoch": 292.3333333333333,
      "grad_norm": 1.6303406624729178e-08,
      "learning_rate": 0.07867824730853433,
      "loss": 0.0,
      "num_input_tokens_seen": 7366672,
      "step": 26310
    },
    {
      "epoch": 292.3888888888889,
      "grad_norm": 7.947084768034074e-09,
      "learning_rate": 0.07862643258659176,
      "loss": 0.0,
      "num_input_tokens_seen": 7368096,
      "step": 26315
    },
    {
      "epoch": 292.44444444444446,
      "grad_norm": 1.4259208924727318e-08,
      "learning_rate": 0.07857462887135026,
      "loss": 0.0,
      "num_input_tokens_seen": 7369472,
      "step": 26320
    },
    {
      "epoch": 292.5,
      "grad_norm": 1.388005976821205e-08,
      "learning_rate": 0.0785228361707986,
      "loss": 0.0,
      "num_input_tokens_seen": 7370896,
      "step": 26325
    },
    {
      "epoch": 292.55555555555554,
      "grad_norm": 2.8945537522417908e-08,
      "learning_rate": 0.07847105449292378,
      "loss": 0.0,
      "num_input_tokens_seen": 7372256,
      "step": 26330
    },
    {
      "epoch": 292.6111111111111,
      "grad_norm": 1.094313706317962e-08,
      "learning_rate": 0.0784192838457113,
      "loss": 0.0,
      "num_input_tokens_seen": 7373680,
      "step": 26335
    },
    {
      "epoch": 292.6666666666667,
      "grad_norm": 1.947931416168558e-08,
      "learning_rate": 0.07836752423714473,
      "loss": 0.0,
      "num_input_tokens_seen": 7375120,
      "step": 26340
    },
    {
      "epoch": 292.72222222222223,
      "grad_norm": 1.734714949463978e-08,
      "learning_rate": 0.07831577567520616,
      "loss": 0.0,
      "num_input_tokens_seen": 7376560,
      "step": 26345
    },
    {
      "epoch": 292.77777777777777,
      "grad_norm": 2.1161739027775184e-08,
      "learning_rate": 0.07826403816787579,
      "loss": 0.0,
      "num_input_tokens_seen": 7377936,
      "step": 26350
    },
    {
      "epoch": 292.8333333333333,
      "grad_norm": 4.273057641057676e-08,
      "learning_rate": 0.0782123117231322,
      "loss": 0.0,
      "num_input_tokens_seen": 7379312,
      "step": 26355
    },
    {
      "epoch": 292.8888888888889,
      "grad_norm": 2.232417806169451e-08,
      "learning_rate": 0.07816059634895237,
      "loss": 0.0,
      "num_input_tokens_seen": 7380688,
      "step": 26360
    },
    {
      "epoch": 292.94444444444446,
      "grad_norm": 1.4568644246537588e-07,
      "learning_rate": 0.0781088920533113,
      "loss": 0.0,
      "num_input_tokens_seen": 7382096,
      "step": 26365
    },
    {
      "epoch": 293.0,
      "grad_norm": 2.012531652439975e-08,
      "learning_rate": 0.07805719884418257,
      "loss": 0.0,
      "num_input_tokens_seen": 7383440,
      "step": 26370
    },
    {
      "epoch": 293.05555555555554,
      "grad_norm": 2.9400538892332406e-08,
      "learning_rate": 0.07800551672953779,
      "loss": 0.0,
      "num_input_tokens_seen": 7384784,
      "step": 26375
    },
    {
      "epoch": 293.1111111111111,
      "grad_norm": 1.4077533805334497e-08,
      "learning_rate": 0.07795384571734709,
      "loss": 0.0,
      "num_input_tokens_seen": 7386208,
      "step": 26380
    },
    {
      "epoch": 293.1666666666667,
      "grad_norm": 2.512604346804892e-08,
      "learning_rate": 0.07790218581557883,
      "loss": 0.0,
      "num_input_tokens_seen": 7387600,
      "step": 26385
    },
    {
      "epoch": 293.22222222222223,
      "grad_norm": 4.957995614063293e-08,
      "learning_rate": 0.07785053703219949,
      "loss": 0.0,
      "num_input_tokens_seen": 7389040,
      "step": 26390
    },
    {
      "epoch": 293.27777777777777,
      "grad_norm": 2.5370754386244698e-08,
      "learning_rate": 0.07779889937517409,
      "loss": 0.0,
      "num_input_tokens_seen": 7390432,
      "step": 26395
    },
    {
      "epoch": 293.3333333333333,
      "grad_norm": 3.115780700113646e-08,
      "learning_rate": 0.0777472728524657,
      "loss": 0.0,
      "num_input_tokens_seen": 7391808,
      "step": 26400
    },
    {
      "epoch": 293.3333333333333,
      "eval_loss": 1.6055381298065186,
      "eval_runtime": 1.1854,
      "eval_samples_per_second": 33.744,
      "eval_steps_per_second": 16.872,
      "num_input_tokens_seen": 7391808,
      "step": 26400
    },
    {
      "epoch": 293.3888888888889,
      "grad_norm": 2.7155923731925213e-08,
      "learning_rate": 0.07769565747203584,
      "loss": 0.0,
      "num_input_tokens_seen": 7393200,
      "step": 26405
    },
    {
      "epoch": 293.44444444444446,
      "grad_norm": 1.6883397790934396e-08,
      "learning_rate": 0.07764405324184427,
      "loss": 0.0,
      "num_input_tokens_seen": 7394640,
      "step": 26410
    },
    {
      "epoch": 293.5,
      "grad_norm": 3.154764272039756e-08,
      "learning_rate": 0.07759246016984889,
      "loss": 0.0,
      "num_input_tokens_seen": 7396016,
      "step": 26415
    },
    {
      "epoch": 293.55555555555554,
      "grad_norm": 1.852495046250624e-08,
      "learning_rate": 0.07754087826400609,
      "loss": 0.0,
      "num_input_tokens_seen": 7397424,
      "step": 26420
    },
    {
      "epoch": 293.6111111111111,
      "grad_norm": 2.3185791064861405e-08,
      "learning_rate": 0.0774893075322705,
      "loss": 0.0,
      "num_input_tokens_seen": 7398816,
      "step": 26425
    },
    {
      "epoch": 293.6666666666667,
      "grad_norm": 2.7721037909600454e-08,
      "learning_rate": 0.07743774798259484,
      "loss": 0.0,
      "num_input_tokens_seen": 7400224,
      "step": 26430
    },
    {
      "epoch": 293.72222222222223,
      "grad_norm": 1.715613962005591e-08,
      "learning_rate": 0.07738619962293032,
      "loss": 0.0,
      "num_input_tokens_seen": 7401632,
      "step": 26435
    },
    {
      "epoch": 293.77777777777777,
      "grad_norm": 2.594961401314322e-08,
      "learning_rate": 0.0773346624612264,
      "loss": 0.0,
      "num_input_tokens_seen": 7403040,
      "step": 26440
    },
    {
      "epoch": 293.8333333333333,
      "grad_norm": 5.293579263820902e-08,
      "learning_rate": 0.07728313650543066,
      "loss": 0.0,
      "num_input_tokens_seen": 7404448,
      "step": 26445
    },
    {
      "epoch": 293.8888888888889,
      "grad_norm": 1.1873713390286866e-07,
      "learning_rate": 0.07723162176348913,
      "loss": 0.0,
      "num_input_tokens_seen": 7405808,
      "step": 26450
    },
    {
      "epoch": 293.94444444444446,
      "grad_norm": 1.5942505982025068e-08,
      "learning_rate": 0.07718011824334593,
      "loss": 0.0,
      "num_input_tokens_seen": 7407232,
      "step": 26455
    },
    {
      "epoch": 294.0,
      "grad_norm": 1.689887518807609e-08,
      "learning_rate": 0.07712862595294363,
      "loss": 0.0,
      "num_input_tokens_seen": 7408640,
      "step": 26460
    },
    {
      "epoch": 294.05555555555554,
      "grad_norm": 2.0068020134544895e-08,
      "learning_rate": 0.07707714490022301,
      "loss": 0.0,
      "num_input_tokens_seen": 7410048,
      "step": 26465
    },
    {
      "epoch": 294.1111111111111,
      "grad_norm": 1.6499287269766683e-08,
      "learning_rate": 0.07702567509312298,
      "loss": 0.0,
      "num_input_tokens_seen": 7411456,
      "step": 26470
    },
    {
      "epoch": 294.1666666666667,
      "grad_norm": 1.5744930692562775e-08,
      "learning_rate": 0.07697421653958098,
      "loss": 0.0,
      "num_input_tokens_seen": 7412912,
      "step": 26475
    },
    {
      "epoch": 294.22222222222223,
      "grad_norm": 1.5406538267370706e-08,
      "learning_rate": 0.07692276924753247,
      "loss": 0.0,
      "num_input_tokens_seen": 7414320,
      "step": 26480
    },
    {
      "epoch": 294.27777777777777,
      "grad_norm": 1.4000271164604783e-07,
      "learning_rate": 0.07687133322491124,
      "loss": 0.0,
      "num_input_tokens_seen": 7415792,
      "step": 26485
    },
    {
      "epoch": 294.3333333333333,
      "grad_norm": 4.058392022443513e-08,
      "learning_rate": 0.07681990847964948,
      "loss": 0.0,
      "num_input_tokens_seen": 7417216,
      "step": 26490
    },
    {
      "epoch": 294.3888888888889,
      "grad_norm": 1.9928496186594202e-08,
      "learning_rate": 0.0767684950196774,
      "loss": 0.0,
      "num_input_tokens_seen": 7418608,
      "step": 26495
    },
    {
      "epoch": 294.44444444444446,
      "grad_norm": 4.566648215131863e-08,
      "learning_rate": 0.0767170928529237,
      "loss": 0.0,
      "num_input_tokens_seen": 7420000,
      "step": 26500
    },
    {
      "epoch": 294.5,
      "grad_norm": 1.5089870686324502e-08,
      "learning_rate": 0.07666570198731526,
      "loss": 0.0,
      "num_input_tokens_seen": 7421376,
      "step": 26505
    },
    {
      "epoch": 294.55555555555554,
      "grad_norm": 1.6252005963224292e-08,
      "learning_rate": 0.07661432243077708,
      "loss": 0.0,
      "num_input_tokens_seen": 7422768,
      "step": 26510
    },
    {
      "epoch": 294.6111111111111,
      "grad_norm": 1.5111058360162133e-07,
      "learning_rate": 0.0765629541912326,
      "loss": 0.0,
      "num_input_tokens_seen": 7424128,
      "step": 26515
    },
    {
      "epoch": 294.6666666666667,
      "grad_norm": 1.8035258619875094e-08,
      "learning_rate": 0.07651159727660352,
      "loss": 0.0,
      "num_input_tokens_seen": 7425504,
      "step": 26520
    },
    {
      "epoch": 294.72222222222223,
      "grad_norm": 8.9092132782298e-08,
      "learning_rate": 0.07646025169480959,
      "loss": 0.0,
      "num_input_tokens_seen": 7426848,
      "step": 26525
    },
    {
      "epoch": 294.77777777777777,
      "grad_norm": 1.1601211014067303e-07,
      "learning_rate": 0.07640891745376908,
      "loss": 0.0,
      "num_input_tokens_seen": 7428240,
      "step": 26530
    },
    {
      "epoch": 294.8333333333333,
      "grad_norm": 1.6233867583537176e-08,
      "learning_rate": 0.07635759456139822,
      "loss": 0.0,
      "num_input_tokens_seen": 7429632,
      "step": 26535
    },
    {
      "epoch": 294.8888888888889,
      "grad_norm": 1.4121284586110505e-08,
      "learning_rate": 0.0763062830256118,
      "loss": 0.0,
      "num_input_tokens_seen": 7431008,
      "step": 26540
    },
    {
      "epoch": 294.94444444444446,
      "grad_norm": 1.660595394525899e-08,
      "learning_rate": 0.07625498285432258,
      "loss": 0.0,
      "num_input_tokens_seen": 7432416,
      "step": 26545
    },
    {
      "epoch": 295.0,
      "grad_norm": 3.745211074601684e-08,
      "learning_rate": 0.07620369405544176,
      "loss": 0.0,
      "num_input_tokens_seen": 7433808,
      "step": 26550
    },
    {
      "epoch": 295.05555555555554,
      "grad_norm": 1.1743794381402495e-08,
      "learning_rate": 0.07615241663687868,
      "loss": 0.0,
      "num_input_tokens_seen": 7435200,
      "step": 26555
    },
    {
      "epoch": 295.1111111111111,
      "grad_norm": 1.1282253353783744e-08,
      "learning_rate": 0.07610115060654106,
      "loss": 0.0,
      "num_input_tokens_seen": 7436608,
      "step": 26560
    },
    {
      "epoch": 295.1666666666667,
      "grad_norm": 2.030060031188441e-08,
      "learning_rate": 0.07604989597233458,
      "loss": 0.0,
      "num_input_tokens_seen": 7438016,
      "step": 26565
    },
    {
      "epoch": 295.22222222222223,
      "grad_norm": 1.4532735015393428e-08,
      "learning_rate": 0.07599865274216352,
      "loss": 0.0,
      "num_input_tokens_seen": 7439376,
      "step": 26570
    },
    {
      "epoch": 295.27777777777777,
      "grad_norm": 8.365533687992865e-08,
      "learning_rate": 0.07594742092393013,
      "loss": 0.0,
      "num_input_tokens_seen": 7440784,
      "step": 26575
    },
    {
      "epoch": 295.3333333333333,
      "grad_norm": 2.9152124270126478e-08,
      "learning_rate": 0.07589620052553503,
      "loss": 0.0,
      "num_input_tokens_seen": 7442176,
      "step": 26580
    },
    {
      "epoch": 295.3888888888889,
      "grad_norm": 1.2952853012393462e-08,
      "learning_rate": 0.0758449915548771,
      "loss": 0.0,
      "num_input_tokens_seen": 7443568,
      "step": 26585
    },
    {
      "epoch": 295.44444444444446,
      "grad_norm": 8.010934138269477e-09,
      "learning_rate": 0.07579379401985332,
      "loss": 0.0,
      "num_input_tokens_seen": 7444992,
      "step": 26590
    },
    {
      "epoch": 295.5,
      "grad_norm": 4.8935117291648567e-08,
      "learning_rate": 0.07574260792835905,
      "loss": 0.0,
      "num_input_tokens_seen": 7446368,
      "step": 26595
    },
    {
      "epoch": 295.55555555555554,
      "grad_norm": 9.82071934885198e-09,
      "learning_rate": 0.07569143328828784,
      "loss": 0.0,
      "num_input_tokens_seen": 7447808,
      "step": 26600
    },
    {
      "epoch": 295.55555555555554,
      "eval_loss": 1.5844130516052246,
      "eval_runtime": 1.1847,
      "eval_samples_per_second": 33.765,
      "eval_steps_per_second": 16.882,
      "num_input_tokens_seen": 7447808,
      "step": 26600
    },
    {
      "epoch": 295.6111111111111,
      "grad_norm": 7.329747919726515e-09,
      "learning_rate": 0.0756402701075314,
      "loss": 0.0,
      "num_input_tokens_seen": 7449200,
      "step": 26605
    },
    {
      "epoch": 295.6666666666667,
      "grad_norm": 3.209103383028378e-08,
      "learning_rate": 0.07558911839397982,
      "loss": 0.0,
      "num_input_tokens_seen": 7450560,
      "step": 26610
    },
    {
      "epoch": 295.72222222222223,
      "grad_norm": 2.4338188353567602e-08,
      "learning_rate": 0.07553797815552123,
      "loss": 0.0,
      "num_input_tokens_seen": 7451952,
      "step": 26615
    },
    {
      "epoch": 295.77777777777777,
      "grad_norm": 1.3233304230197973e-08,
      "learning_rate": 0.07548684940004222,
      "loss": 0.0,
      "num_input_tokens_seen": 7453360,
      "step": 26620
    },
    {
      "epoch": 295.8333333333333,
      "grad_norm": 1.5967506428182787e-08,
      "learning_rate": 0.07543573213542744,
      "loss": 0.0,
      "num_input_tokens_seen": 7454768,
      "step": 26625
    },
    {
      "epoch": 295.8888888888889,
      "grad_norm": 1.9530808970102953e-08,
      "learning_rate": 0.0753846263695597,
      "loss": 0.0,
      "num_input_tokens_seen": 7456176,
      "step": 26630
    },
    {
      "epoch": 295.94444444444446,
      "grad_norm": 1.367977908728335e-08,
      "learning_rate": 0.07533353211032029,
      "loss": 0.0,
      "num_input_tokens_seen": 7457584,
      "step": 26635
    },
    {
      "epoch": 296.0,
      "grad_norm": 1.1793648724278682e-08,
      "learning_rate": 0.07528244936558857,
      "loss": 0.0,
      "num_input_tokens_seen": 7458944,
      "step": 26640
    },
    {
      "epoch": 296.05555555555554,
      "grad_norm": 9.144454971021787e-09,
      "learning_rate": 0.07523137814324206,
      "loss": 0.0,
      "num_input_tokens_seen": 7460352,
      "step": 26645
    },
    {
      "epoch": 296.1111111111111,
      "grad_norm": 4.294682298677799e-08,
      "learning_rate": 0.07518031845115672,
      "loss": 0.0,
      "num_input_tokens_seen": 7461776,
      "step": 26650
    },
    {
      "epoch": 296.1666666666667,
      "grad_norm": 2.459862713521943e-08,
      "learning_rate": 0.07512927029720647,
      "loss": 0.0,
      "num_input_tokens_seen": 7463184,
      "step": 26655
    },
    {
      "epoch": 296.22222222222223,
      "grad_norm": 1.3072353510779067e-07,
      "learning_rate": 0.0750782336892636,
      "loss": 0.0,
      "num_input_tokens_seen": 7464528,
      "step": 26660
    },
    {
      "epoch": 296.27777777777777,
      "grad_norm": 2.8537698426589486e-08,
      "learning_rate": 0.0750272086351987,
      "loss": 0.0,
      "num_input_tokens_seen": 7465904,
      "step": 26665
    },
    {
      "epoch": 296.3333333333333,
      "grad_norm": 1.2177859609607822e-08,
      "learning_rate": 0.07497619514288031,
      "loss": 0.0,
      "num_input_tokens_seen": 7467312,
      "step": 26670
    },
    {
      "epoch": 296.3888888888889,
      "grad_norm": 4.129749697767693e-08,
      "learning_rate": 0.07492519322017545,
      "loss": 0.0,
      "num_input_tokens_seen": 7468736,
      "step": 26675
    },
    {
      "epoch": 296.44444444444446,
      "grad_norm": 1.3527459152840038e-08,
      "learning_rate": 0.0748742028749493,
      "loss": 0.0,
      "num_input_tokens_seen": 7470176,
      "step": 26680
    },
    {
      "epoch": 296.5,
      "grad_norm": 2.753182393178122e-08,
      "learning_rate": 0.0748232241150651,
      "loss": 0.0,
      "num_input_tokens_seen": 7471616,
      "step": 26685
    },
    {
      "epoch": 296.55555555555554,
      "grad_norm": 4.8970544952453565e-08,
      "learning_rate": 0.07477225694838453,
      "loss": 0.0,
      "num_input_tokens_seen": 7472992,
      "step": 26690
    },
    {
      "epoch": 296.6111111111111,
      "grad_norm": 8.779558413607447e-08,
      "learning_rate": 0.07472130138276731,
      "loss": 0.0,
      "num_input_tokens_seen": 7474368,
      "step": 26695
    },
    {
      "epoch": 296.6666666666667,
      "grad_norm": 1.1659770926542024e-08,
      "learning_rate": 0.07467035742607138,
      "loss": 0.0,
      "num_input_tokens_seen": 7475776,
      "step": 26700
    },
    {
      "epoch": 296.72222222222223,
      "grad_norm": 3.4051620190211906e-08,
      "learning_rate": 0.07461942508615303,
      "loss": 0.0,
      "num_input_tokens_seen": 7477120,
      "step": 26705
    },
    {
      "epoch": 296.77777777777777,
      "grad_norm": 9.327648875512295e-09,
      "learning_rate": 0.07456850437086657,
      "loss": 0.0,
      "num_input_tokens_seen": 7478544,
      "step": 26710
    },
    {
      "epoch": 296.8333333333333,
      "grad_norm": 3.184128871680514e-08,
      "learning_rate": 0.07451759528806468,
      "loss": 0.0,
      "num_input_tokens_seen": 7479952,
      "step": 26715
    },
    {
      "epoch": 296.8888888888889,
      "grad_norm": 1.1589246007304155e-08,
      "learning_rate": 0.0744666978455982,
      "loss": 0.0,
      "num_input_tokens_seen": 7481328,
      "step": 26720
    },
    {
      "epoch": 296.94444444444446,
      "grad_norm": 3.070018905759753e-08,
      "learning_rate": 0.07441581205131609,
      "loss": 0.0,
      "num_input_tokens_seen": 7482784,
      "step": 26725
    },
    {
      "epoch": 297.0,
      "grad_norm": 7.137199276030515e-08,
      "learning_rate": 0.07436493791306566,
      "loss": 0.0,
      "num_input_tokens_seen": 7484208,
      "step": 26730
    },
    {
      "epoch": 297.05555555555554,
      "grad_norm": 9.042270221470972e-08,
      "learning_rate": 0.07431407543869223,
      "loss": 0.0,
      "num_input_tokens_seen": 7485600,
      "step": 26735
    },
    {
      "epoch": 297.1111111111111,
      "grad_norm": 3.0366635428435984e-08,
      "learning_rate": 0.0742632246360395,
      "loss": 0.0,
      "num_input_tokens_seen": 7486960,
      "step": 26740
    },
    {
      "epoch": 297.1666666666667,
      "grad_norm": 8.603439027865534e-08,
      "learning_rate": 0.07421238551294934,
      "loss": 0.0,
      "num_input_tokens_seen": 7488304,
      "step": 26745
    },
    {
      "epoch": 297.22222222222223,
      "grad_norm": 3.332888809381984e-08,
      "learning_rate": 0.07416155807726171,
      "loss": 0.0,
      "num_input_tokens_seen": 7489760,
      "step": 26750
    },
    {
      "epoch": 297.27777777777777,
      "grad_norm": 1.1171152891620295e-08,
      "learning_rate": 0.07411074233681492,
      "loss": 0.0,
      "num_input_tokens_seen": 7491136,
      "step": 26755
    },
    {
      "epoch": 297.3333333333333,
      "grad_norm": 2.004606081129623e-08,
      "learning_rate": 0.07405993829944528,
      "loss": 0.0,
      "num_input_tokens_seen": 7492544,
      "step": 26760
    },
    {
      "epoch": 297.3888888888889,
      "grad_norm": 3.402314163736264e-08,
      "learning_rate": 0.07400914597298755,
      "loss": 0.0,
      "num_input_tokens_seen": 7493952,
      "step": 26765
    },
    {
      "epoch": 297.44444444444446,
      "grad_norm": 3.383465596584756e-08,
      "learning_rate": 0.07395836536527445,
      "loss": 0.0,
      "num_input_tokens_seen": 7495376,
      "step": 26770
    },
    {
      "epoch": 297.5,
      "grad_norm": 1.534323246232816e-08,
      "learning_rate": 0.07390759648413696,
      "loss": 0.0,
      "num_input_tokens_seen": 7496752,
      "step": 26775
    },
    {
      "epoch": 297.55555555555554,
      "grad_norm": 4.170204448428194e-08,
      "learning_rate": 0.07385683933740435,
      "loss": 0.0,
      "num_input_tokens_seen": 7498176,
      "step": 26780
    },
    {
      "epoch": 297.6111111111111,
      "grad_norm": 2.042401625601542e-08,
      "learning_rate": 0.07380609393290402,
      "loss": 0.0,
      "num_input_tokens_seen": 7499552,
      "step": 26785
    },
    {
      "epoch": 297.6666666666667,
      "grad_norm": 2.9523572919742946e-08,
      "learning_rate": 0.07375536027846147,
      "loss": 0.0,
      "num_input_tokens_seen": 7500960,
      "step": 26790
    },
    {
      "epoch": 297.72222222222223,
      "grad_norm": 2.5195333819283405e-08,
      "learning_rate": 0.07370463838190057,
      "loss": 0.0,
      "num_input_tokens_seen": 7502384,
      "step": 26795
    },
    {
      "epoch": 297.77777777777777,
      "grad_norm": 1.3731036752062664e-08,
      "learning_rate": 0.07365392825104317,
      "loss": 0.0,
      "num_input_tokens_seen": 7503824,
      "step": 26800
    },
    {
      "epoch": 297.77777777777777,
      "eval_loss": 1.6416435241699219,
      "eval_runtime": 1.1845,
      "eval_samples_per_second": 33.77,
      "eval_steps_per_second": 16.885,
      "num_input_tokens_seen": 7503824,
      "step": 26800
    },
    {
      "epoch": 297.8333333333333,
      "grad_norm": 1.4130180581162222e-08,
      "learning_rate": 0.07360322989370945,
      "loss": 0.0,
      "num_input_tokens_seen": 7505216,
      "step": 26805
    },
    {
      "epoch": 297.8888888888889,
      "grad_norm": 2.5339939924151622e-08,
      "learning_rate": 0.07355254331771781,
      "loss": 0.0,
      "num_input_tokens_seen": 7506608,
      "step": 26810
    },
    {
      "epoch": 297.94444444444446,
      "grad_norm": 9.842731074627409e-09,
      "learning_rate": 0.07350186853088461,
      "loss": 0.0,
      "num_input_tokens_seen": 7508000,
      "step": 26815
    },
    {
      "epoch": 298.0,
      "grad_norm": 2.6145526632603833e-08,
      "learning_rate": 0.07345120554102462,
      "loss": 0.0,
      "num_input_tokens_seen": 7509456,
      "step": 26820
    },
    {
      "epoch": 298.05555555555554,
      "grad_norm": 4.904723738263783e-08,
      "learning_rate": 0.07340055435595079,
      "loss": 0.0,
      "num_input_tokens_seen": 7510784,
      "step": 26825
    },
    {
      "epoch": 298.1111111111111,
      "grad_norm": 1.2277682870376339e-08,
      "learning_rate": 0.07334991498347401,
      "loss": 0.0,
      "num_input_tokens_seen": 7512176,
      "step": 26830
    },
    {
      "epoch": 298.1666666666667,
      "grad_norm": 3.684885641064284e-08,
      "learning_rate": 0.07329928743140365,
      "loss": 0.0,
      "num_input_tokens_seen": 7513568,
      "step": 26835
    },
    {
      "epoch": 298.22222222222223,
      "grad_norm": 1.6238171696159043e-08,
      "learning_rate": 0.07324867170754705,
      "loss": 0.0,
      "num_input_tokens_seen": 7514992,
      "step": 26840
    },
    {
      "epoch": 298.27777777777777,
      "grad_norm": 2.7960536996829433e-08,
      "learning_rate": 0.07319806781970974,
      "loss": 0.0,
      "num_input_tokens_seen": 7516400,
      "step": 26845
    },
    {
      "epoch": 298.3333333333333,
      "grad_norm": 3.042226381921864e-08,
      "learning_rate": 0.07314747577569555,
      "loss": 0.0,
      "num_input_tokens_seen": 7517856,
      "step": 26850
    },
    {
      "epoch": 298.3888888888889,
      "grad_norm": 2.7536218638601895e-08,
      "learning_rate": 0.07309689558330636,
      "loss": 0.0,
      "num_input_tokens_seen": 7519232,
      "step": 26855
    },
    {
      "epoch": 298.44444444444446,
      "grad_norm": 1.9104893667076794e-08,
      "learning_rate": 0.0730463272503423,
      "loss": 0.0,
      "num_input_tokens_seen": 7520672,
      "step": 26860
    },
    {
      "epoch": 298.5,
      "grad_norm": 7.865244455729226e-09,
      "learning_rate": 0.07299577078460168,
      "loss": 0.0,
      "num_input_tokens_seen": 7522080,
      "step": 26865
    },
    {
      "epoch": 298.55555555555554,
      "grad_norm": 4.53368151909217e-08,
      "learning_rate": 0.07294522619388083,
      "loss": 0.0,
      "num_input_tokens_seen": 7523488,
      "step": 26870
    },
    {
      "epoch": 298.6111111111111,
      "grad_norm": 1.6027140503638293e-08,
      "learning_rate": 0.07289469348597452,
      "loss": 0.0,
      "num_input_tokens_seen": 7524848,
      "step": 26875
    },
    {
      "epoch": 298.6666666666667,
      "grad_norm": 3.021695604843444e-08,
      "learning_rate": 0.07284417266867535,
      "loss": 0.0,
      "num_input_tokens_seen": 7526224,
      "step": 26880
    },
    {
      "epoch": 298.72222222222223,
      "grad_norm": 3.60172229818545e-08,
      "learning_rate": 0.07279366374977439,
      "loss": 0.0,
      "num_input_tokens_seen": 7527600,
      "step": 26885
    },
    {
      "epoch": 298.77777777777777,
      "grad_norm": 1.1426610768694445e-08,
      "learning_rate": 0.07274316673706074,
      "loss": 0.0,
      "num_input_tokens_seen": 7528992,
      "step": 26890
    },
    {
      "epoch": 298.8333333333333,
      "grad_norm": 1.6987604212204133e-08,
      "learning_rate": 0.07269268163832161,
      "loss": 0.0,
      "num_input_tokens_seen": 7530416,
      "step": 26895
    },
    {
      "epoch": 298.8888888888889,
      "grad_norm": 5.537158287438615e-08,
      "learning_rate": 0.07264220846134248,
      "loss": 0.0,
      "num_input_tokens_seen": 7531792,
      "step": 26900
    },
    {
      "epoch": 298.94444444444446,
      "grad_norm": 3.5288397981503294e-08,
      "learning_rate": 0.07259174721390699,
      "loss": 0.0,
      "num_input_tokens_seen": 7533184,
      "step": 26905
    },
    {
      "epoch": 299.0,
      "grad_norm": 3.067371494580584e-07,
      "learning_rate": 0.07254129790379686,
      "loss": 0.0,
      "num_input_tokens_seen": 7534608,
      "step": 26910
    },
    {
      "epoch": 299.05555555555554,
      "grad_norm": 3.4063205589518475e-08,
      "learning_rate": 0.072490860538792,
      "loss": 0.0,
      "num_input_tokens_seen": 7536000,
      "step": 26915
    },
    {
      "epoch": 299.1111111111111,
      "grad_norm": 2.5703460693193847e-08,
      "learning_rate": 0.07244043512667042,
      "loss": 0.0,
      "num_input_tokens_seen": 7537376,
      "step": 26920
    },
    {
      "epoch": 299.1666666666667,
      "grad_norm": 1.676035132902598e-08,
      "learning_rate": 0.07239002167520843,
      "loss": 0.0,
      "num_input_tokens_seen": 7538784,
      "step": 26925
    },
    {
      "epoch": 299.22222222222223,
      "grad_norm": 2.3127650905507835e-08,
      "learning_rate": 0.07233962019218045,
      "loss": 0.0,
      "num_input_tokens_seen": 7540176,
      "step": 26930
    },
    {
      "epoch": 299.27777777777777,
      "grad_norm": 4.5650448754486206e-08,
      "learning_rate": 0.07228923068535892,
      "loss": 0.0,
      "num_input_tokens_seen": 7541568,
      "step": 26935
    },
    {
      "epoch": 299.3333333333333,
      "grad_norm": 5.2468972171482164e-06,
      "learning_rate": 0.0722388531625146,
      "loss": 0.0,
      "num_input_tokens_seen": 7542992,
      "step": 26940
    },
    {
      "epoch": 299.3888888888889,
      "grad_norm": 2.086002659495989e-08,
      "learning_rate": 0.07218848763141639,
      "loss": 0.0,
      "num_input_tokens_seen": 7544416,
      "step": 26945
    },
    {
      "epoch": 299.44444444444446,
      "grad_norm": 3.579891227900589e-08,
      "learning_rate": 0.07213813409983118,
      "loss": 0.0,
      "num_input_tokens_seen": 7545840,
      "step": 26950
    },
    {
      "epoch": 299.5,
      "grad_norm": 1.0806520833739341e-07,
      "learning_rate": 0.0720877925755242,
      "loss": 0.0,
      "num_input_tokens_seen": 7547264,
      "step": 26955
    },
    {
      "epoch": 299.55555555555554,
      "grad_norm": 6.676416575146504e-08,
      "learning_rate": 0.07203746306625866,
      "loss": 0.0,
      "num_input_tokens_seen": 7548608,
      "step": 26960
    },
    {
      "epoch": 299.6111111111111,
      "grad_norm": 1.5424607369141086e-08,
      "learning_rate": 0.07198714557979606,
      "loss": 0.0,
      "num_input_tokens_seen": 7549984,
      "step": 26965
    },
    {
      "epoch": 299.6666666666667,
      "grad_norm": 1.2794560966256086e-08,
      "learning_rate": 0.07193684012389602,
      "loss": 0.0,
      "num_input_tokens_seen": 7551408,
      "step": 26970
    },
    {
      "epoch": 299.72222222222223,
      "grad_norm": 1.6661285684449467e-08,
      "learning_rate": 0.07188654670631621,
      "loss": 0.0,
      "num_input_tokens_seen": 7552800,
      "step": 26975
    },
    {
      "epoch": 299.77777777777777,
      "grad_norm": 1.403164517910227e-08,
      "learning_rate": 0.07183626533481258,
      "loss": 0.0,
      "num_input_tokens_seen": 7554208,
      "step": 26980
    },
    {
      "epoch": 299.8333333333333,
      "grad_norm": 2.0007075107741912e-08,
      "learning_rate": 0.07178599601713909,
      "loss": 0.0,
      "num_input_tokens_seen": 7555648,
      "step": 26985
    },
    {
      "epoch": 299.8888888888889,
      "grad_norm": 9.423978930556132e-09,
      "learning_rate": 0.07173573876104786,
      "loss": 0.0,
      "num_input_tokens_seen": 7557040,
      "step": 26990
    },
    {
      "epoch": 299.94444444444446,
      "grad_norm": 3.6773631251207917e-08,
      "learning_rate": 0.0716854935742893,
      "loss": 0.0,
      "num_input_tokens_seen": 7558448,
      "step": 26995
    },
    {
      "epoch": 300.0,
      "grad_norm": 7.963574688574226e-09,
      "learning_rate": 0.07163526046461174,
      "loss": 0.0,
      "num_input_tokens_seen": 7559856,
      "step": 27000
    },
    {
      "epoch": 300.0,
      "eval_loss": 1.7238719463348389,
      "eval_runtime": 1.1916,
      "eval_samples_per_second": 33.569,
      "eval_steps_per_second": 16.785,
      "num_input_tokens_seen": 7559856,
      "step": 27000
    },
    {
      "epoch": 300.05555555555554,
      "grad_norm": 7.447572780705514e-09,
      "learning_rate": 0.07158503943976181,
      "loss": 0.0,
      "num_input_tokens_seen": 7561312,
      "step": 27005
    },
    {
      "epoch": 300.1111111111111,
      "grad_norm": 1.0594630062144006e-08,
      "learning_rate": 0.07153483050748427,
      "loss": 0.0,
      "num_input_tokens_seen": 7562688,
      "step": 27010
    },
    {
      "epoch": 300.1666666666667,
      "grad_norm": 6.941302643781455e-09,
      "learning_rate": 0.07148463367552188,
      "loss": 0.0,
      "num_input_tokens_seen": 7564112,
      "step": 27015
    },
    {
      "epoch": 300.22222222222223,
      "grad_norm": 7.230700926896816e-09,
      "learning_rate": 0.07143444895161565,
      "loss": 0.0,
      "num_input_tokens_seen": 7565504,
      "step": 27020
    },
    {
      "epoch": 300.27777777777777,
      "grad_norm": 8.55264215005036e-09,
      "learning_rate": 0.07138427634350476,
      "loss": 0.0,
      "num_input_tokens_seen": 7566928,
      "step": 27025
    },
    {
      "epoch": 300.3333333333333,
      "grad_norm": 1.295516849353362e-08,
      "learning_rate": 0.07133411585892636,
      "loss": 0.0,
      "num_input_tokens_seen": 7568352,
      "step": 27030
    },
    {
      "epoch": 300.3888888888889,
      "grad_norm": 7.730370121805663e-09,
      "learning_rate": 0.07128396750561593,
      "loss": 0.0,
      "num_input_tokens_seen": 7569792,
      "step": 27035
    },
    {
      "epoch": 300.44444444444446,
      "grad_norm": 7.0610721714103875e-09,
      "learning_rate": 0.07123383129130685,
      "loss": 0.0,
      "num_input_tokens_seen": 7571232,
      "step": 27040
    },
    {
      "epoch": 300.5,
      "grad_norm": 8.231621606569206e-09,
      "learning_rate": 0.07118370722373084,
      "loss": 0.0,
      "num_input_tokens_seen": 7572624,
      "step": 27045
    },
    {
      "epoch": 300.55555555555554,
      "grad_norm": 7.158987624933388e-09,
      "learning_rate": 0.07113359531061769,
      "loss": 0.0,
      "num_input_tokens_seen": 7574000,
      "step": 27050
    },
    {
      "epoch": 300.6111111111111,
      "grad_norm": 6.390402429445885e-09,
      "learning_rate": 0.07108349555969525,
      "loss": 0.0,
      "num_input_tokens_seen": 7575392,
      "step": 27055
    },
    {
      "epoch": 300.6666666666667,
      "grad_norm": 2.2042494052243455e-08,
      "learning_rate": 0.07103340797868944,
      "loss": 0.0,
      "num_input_tokens_seen": 7576784,
      "step": 27060
    },
    {
      "epoch": 300.72222222222223,
      "grad_norm": 9.945638979047544e-09,
      "learning_rate": 0.07098333257532453,
      "loss": 0.0,
      "num_input_tokens_seen": 7578176,
      "step": 27065
    },
    {
      "epoch": 300.77777777777777,
      "grad_norm": 9.838388770333495e-09,
      "learning_rate": 0.07093326935732269,
      "loss": 0.0,
      "num_input_tokens_seen": 7579568,
      "step": 27070
    },
    {
      "epoch": 300.8333333333333,
      "grad_norm": 6.393742424393167e-09,
      "learning_rate": 0.0708832183324044,
      "loss": 0.0,
      "num_input_tokens_seen": 7581008,
      "step": 27075
    },
    {
      "epoch": 300.8888888888889,
      "grad_norm": 2.976012858368904e-08,
      "learning_rate": 0.07083317950828799,
      "loss": 0.0,
      "num_input_tokens_seen": 7582368,
      "step": 27080
    },
    {
      "epoch": 300.94444444444446,
      "grad_norm": 6.724648393685584e-09,
      "learning_rate": 0.0707831528926902,
      "loss": 0.0,
      "num_input_tokens_seen": 7583744,
      "step": 27085
    },
    {
      "epoch": 301.0,
      "grad_norm": 5.700343308490119e-09,
      "learning_rate": 0.07073313849332578,
      "loss": 0.0,
      "num_input_tokens_seen": 7585184,
      "step": 27090
    },
    {
      "epoch": 301.05555555555554,
      "grad_norm": 1.2157464368556248e-08,
      "learning_rate": 0.07068313631790749,
      "loss": 0.0,
      "num_input_tokens_seen": 7586608,
      "step": 27095
    },
    {
      "epoch": 301.1111111111111,
      "grad_norm": 3.748383825552537e-09,
      "learning_rate": 0.07063314637414632,
      "loss": 0.0,
      "num_input_tokens_seen": 7588032,
      "step": 27100
    },
    {
      "epoch": 301.1666666666667,
      "grad_norm": 9.105717957424986e-09,
      "learning_rate": 0.07058316866975144,
      "loss": 0.0,
      "num_input_tokens_seen": 7589408,
      "step": 27105
    },
    {
      "epoch": 301.22222222222223,
      "grad_norm": 9.129374589633699e-09,
      "learning_rate": 0.0705332032124299,
      "loss": 0.0,
      "num_input_tokens_seen": 7590816,
      "step": 27110
    },
    {
      "epoch": 301.27777777777777,
      "grad_norm": 7.346831587540237e-09,
      "learning_rate": 0.0704832500098871,
      "loss": 0.0,
      "num_input_tokens_seen": 7592176,
      "step": 27115
    },
    {
      "epoch": 301.3333333333333,
      "grad_norm": 2.7279606129582135e-08,
      "learning_rate": 0.07043330906982641,
      "loss": 0.0,
      "num_input_tokens_seen": 7593600,
      "step": 27120
    },
    {
      "epoch": 301.3888888888889,
      "grad_norm": 7.249100431039324e-09,
      "learning_rate": 0.07038338039994936,
      "loss": 0.0,
      "num_input_tokens_seen": 7595008,
      "step": 27125
    },
    {
      "epoch": 301.44444444444446,
      "grad_norm": 5.2411930795415174e-08,
      "learning_rate": 0.07033346400795562,
      "loss": 0.0,
      "num_input_tokens_seen": 7596448,
      "step": 27130
    },
    {
      "epoch": 301.5,
      "grad_norm": 8.440793841657523e-09,
      "learning_rate": 0.07028355990154282,
      "loss": 0.0,
      "num_input_tokens_seen": 7597872,
      "step": 27135
    },
    {
      "epoch": 301.55555555555554,
      "grad_norm": 4.718534007963626e-09,
      "learning_rate": 0.07023366808840685,
      "loss": 0.0,
      "num_input_tokens_seen": 7599232,
      "step": 27140
    },
    {
      "epoch": 301.6111111111111,
      "grad_norm": 2.5160328931406184e-08,
      "learning_rate": 0.07018378857624172,
      "loss": 0.0,
      "num_input_tokens_seen": 7600576,
      "step": 27145
    },
    {
      "epoch": 301.6666666666667,
      "grad_norm": 3.9802108275921455e-09,
      "learning_rate": 0.0701339213727394,
      "loss": 0.0,
      "num_input_tokens_seen": 7601968,
      "step": 27150
    },
    {
      "epoch": 301.72222222222223,
      "grad_norm": 7.98050692196739e-09,
      "learning_rate": 0.07008406648559008,
      "loss": 0.0,
      "num_input_tokens_seen": 7603360,
      "step": 27155
    },
    {
      "epoch": 301.77777777777777,
      "grad_norm": 2.1907105463014886e-08,
      "learning_rate": 0.07003422392248196,
      "loss": 0.0,
      "num_input_tokens_seen": 7604768,
      "step": 27160
    },
    {
      "epoch": 301.8333333333333,
      "grad_norm": 8.57154081046474e-09,
      "learning_rate": 0.06998439369110142,
      "loss": 0.0,
      "num_input_tokens_seen": 7606176,
      "step": 27165
    },
    {
      "epoch": 301.8888888888889,
      "grad_norm": 4.272283860018433e-09,
      "learning_rate": 0.06993457579913295,
      "loss": 0.0,
      "num_input_tokens_seen": 7607584,
      "step": 27170
    },
    {
      "epoch": 301.94444444444446,
      "grad_norm": 6.814711461800016e-09,
      "learning_rate": 0.06988477025425903,
      "loss": 0.0,
      "num_input_tokens_seen": 7608976,
      "step": 27175
    },
    {
      "epoch": 302.0,
      "grad_norm": 1.2989770148408297e-08,
      "learning_rate": 0.06983497706416032,
      "loss": 0.0,
      "num_input_tokens_seen": 7610368,
      "step": 27180
    },
    {
      "epoch": 302.05555555555554,
      "grad_norm": 2.5825666938317227e-08,
      "learning_rate": 0.0697851962365156,
      "loss": 0.0,
      "num_input_tokens_seen": 7611776,
      "step": 27185
    },
    {
      "epoch": 302.1111111111111,
      "grad_norm": 6.362762317024817e-09,
      "learning_rate": 0.06973542777900163,
      "loss": 0.0,
      "num_input_tokens_seen": 7613136,
      "step": 27190
    },
    {
      "epoch": 302.1666666666667,
      "grad_norm": 5.791559232193322e-09,
      "learning_rate": 0.06968567169929342,
      "loss": 0.0,
      "num_input_tokens_seen": 7614496,
      "step": 27195
    },
    {
      "epoch": 302.22222222222223,
      "grad_norm": 5.569010141925901e-09,
      "learning_rate": 0.06963592800506392,
      "loss": 0.0,
      "num_input_tokens_seen": 7615904,
      "step": 27200
    },
    {
      "epoch": 302.22222222222223,
      "eval_loss": 1.6795727014541626,
      "eval_runtime": 1.1838,
      "eval_samples_per_second": 33.789,
      "eval_steps_per_second": 16.894,
      "num_input_tokens_seen": 7615904,
      "step": 27200
    },
    {
      "epoch": 302.27777777777777,
      "grad_norm": 1.9891590596898823e-08,
      "learning_rate": 0.06958619670398417,
      "loss": 0.0,
      "num_input_tokens_seen": 7617328,
      "step": 27205
    },
    {
      "epoch": 302.3333333333333,
      "grad_norm": 1.695716456140417e-08,
      "learning_rate": 0.0695364778037235,
      "loss": 0.0,
      "num_input_tokens_seen": 7618784,
      "step": 27210
    },
    {
      "epoch": 302.3888888888889,
      "grad_norm": 1.0798724581206898e-08,
      "learning_rate": 0.06948677131194907,
      "loss": 0.0,
      "num_input_tokens_seen": 7620144,
      "step": 27215
    },
    {
      "epoch": 302.44444444444446,
      "grad_norm": 5.343653075584598e-09,
      "learning_rate": 0.06943707723632629,
      "loss": 0.0,
      "num_input_tokens_seen": 7621520,
      "step": 27220
    },
    {
      "epoch": 302.5,
      "grad_norm": 1.1566879898339266e-08,
      "learning_rate": 0.06938739558451867,
      "loss": 0.0,
      "num_input_tokens_seen": 7622928,
      "step": 27225
    },
    {
      "epoch": 302.55555555555554,
      "grad_norm": 3.584893804031708e-08,
      "learning_rate": 0.06933772636418763,
      "loss": 0.0,
      "num_input_tokens_seen": 7624304,
      "step": 27230
    },
    {
      "epoch": 302.6111111111111,
      "grad_norm": 6.890801262926516e-09,
      "learning_rate": 0.06928806958299293,
      "loss": 0.0,
      "num_input_tokens_seen": 7625728,
      "step": 27235
    },
    {
      "epoch": 302.6666666666667,
      "grad_norm": 7.881674868315258e-09,
      "learning_rate": 0.06923842524859211,
      "loss": 0.0,
      "num_input_tokens_seen": 7627120,
      "step": 27240
    },
    {
      "epoch": 302.72222222222223,
      "grad_norm": 9.193986905131624e-09,
      "learning_rate": 0.06918879336864105,
      "loss": 0.0,
      "num_input_tokens_seen": 7628544,
      "step": 27245
    },
    {
      "epoch": 302.77777777777777,
      "grad_norm": 9.181566618110537e-09,
      "learning_rate": 0.06913917395079362,
      "loss": 0.0,
      "num_input_tokens_seen": 7629936,
      "step": 27250
    },
    {
      "epoch": 302.8333333333333,
      "grad_norm": 8.182508892673468e-09,
      "learning_rate": 0.0690895670027017,
      "loss": 0.0,
      "num_input_tokens_seen": 7631344,
      "step": 27255
    },
    {
      "epoch": 302.8888888888889,
      "grad_norm": 6.074652780796441e-09,
      "learning_rate": 0.06903997253201531,
      "loss": 0.0,
      "num_input_tokens_seen": 7632704,
      "step": 27260
    },
    {
      "epoch": 302.94444444444446,
      "grad_norm": 6.8593593027799216e-09,
      "learning_rate": 0.06899039054638263,
      "loss": 0.0,
      "num_input_tokens_seen": 7634128,
      "step": 27265
    },
    {
      "epoch": 303.0,
      "grad_norm": 6.129056817627543e-09,
      "learning_rate": 0.06894082105344976,
      "loss": 0.0,
      "num_input_tokens_seen": 7635536,
      "step": 27270
    },
    {
      "epoch": 303.05555555555554,
      "grad_norm": 8.555312902558398e-09,
      "learning_rate": 0.06889126406086087,
      "loss": 0.0,
      "num_input_tokens_seen": 7636928,
      "step": 27275
    },
    {
      "epoch": 303.1111111111111,
      "grad_norm": 1.6243948408600772e-08,
      "learning_rate": 0.0688417195762584,
      "loss": 0.0,
      "num_input_tokens_seen": 7638304,
      "step": 27280
    },
    {
      "epoch": 303.1666666666667,
      "grad_norm": 1.2547566541343258e-08,
      "learning_rate": 0.06879218760728262,
      "loss": 0.0,
      "num_input_tokens_seen": 7639696,
      "step": 27285
    },
    {
      "epoch": 303.22222222222223,
      "grad_norm": 9.17092446428569e-09,
      "learning_rate": 0.06874266816157207,
      "loss": 0.0,
      "num_input_tokens_seen": 7641072,
      "step": 27290
    },
    {
      "epoch": 303.27777777777777,
      "grad_norm": 1.4613374510474841e-08,
      "learning_rate": 0.06869316124676321,
      "loss": 0.0,
      "num_input_tokens_seen": 7642448,
      "step": 27295
    },
    {
      "epoch": 303.3333333333333,
      "grad_norm": 1.3336595827695419e-08,
      "learning_rate": 0.06864366687049062,
      "loss": 0.0,
      "num_input_tokens_seen": 7643856,
      "step": 27300
    },
    {
      "epoch": 303.3888888888889,
      "grad_norm": 1.0006355743996664e-08,
      "learning_rate": 0.06859418504038704,
      "loss": 0.0,
      "num_input_tokens_seen": 7645264,
      "step": 27305
    },
    {
      "epoch": 303.44444444444446,
      "grad_norm": 1.1573549230092794e-08,
      "learning_rate": 0.06854471576408311,
      "loss": 0.0,
      "num_input_tokens_seen": 7646672,
      "step": 27310
    },
    {
      "epoch": 303.5,
      "grad_norm": 3.5965118883041214e-08,
      "learning_rate": 0.06849525904920767,
      "loss": 0.0,
      "num_input_tokens_seen": 7648080,
      "step": 27315
    },
    {
      "epoch": 303.55555555555554,
      "grad_norm": 1.2153027029171426e-08,
      "learning_rate": 0.06844581490338748,
      "loss": 0.0,
      "num_input_tokens_seen": 7649504,
      "step": 27320
    },
    {
      "epoch": 303.6111111111111,
      "grad_norm": 1.1922661080632224e-08,
      "learning_rate": 0.06839638333424752,
      "loss": 0.0,
      "num_input_tokens_seen": 7650912,
      "step": 27325
    },
    {
      "epoch": 303.6666666666667,
      "grad_norm": 3.1552254142752645e-08,
      "learning_rate": 0.06834696434941082,
      "loss": 0.0,
      "num_input_tokens_seen": 7652336,
      "step": 27330
    },
    {
      "epoch": 303.72222222222223,
      "grad_norm": 4.787918328474916e-08,
      "learning_rate": 0.06829755795649824,
      "loss": 0.0,
      "num_input_tokens_seen": 7653744,
      "step": 27335
    },
    {
      "epoch": 303.77777777777777,
      "grad_norm": 4.153524812977594e-08,
      "learning_rate": 0.06824816416312904,
      "loss": 0.0,
      "num_input_tokens_seen": 7655184,
      "step": 27340
    },
    {
      "epoch": 303.8333333333333,
      "grad_norm": 1.3951223287733683e-08,
      "learning_rate": 0.06819878297692027,
      "loss": 0.0,
      "num_input_tokens_seen": 7656608,
      "step": 27345
    },
    {
      "epoch": 303.8888888888889,
      "grad_norm": 2.7665850055313967e-08,
      "learning_rate": 0.0681494144054871,
      "loss": 0.0,
      "num_input_tokens_seen": 7657984,
      "step": 27350
    },
    {
      "epoch": 303.94444444444446,
      "grad_norm": 8.400855122658868e-09,
      "learning_rate": 0.06810005845644286,
      "loss": 0.0,
      "num_input_tokens_seen": 7659376,
      "step": 27355
    },
    {
      "epoch": 304.0,
      "grad_norm": 1.1514551978564214e-08,
      "learning_rate": 0.06805071513739878,
      "loss": 0.0,
      "num_input_tokens_seen": 7660800,
      "step": 27360
    },
    {
      "epoch": 304.05555555555554,
      "grad_norm": 1.4774171219755772e-08,
      "learning_rate": 0.06800138445596428,
      "loss": 0.0,
      "num_input_tokens_seen": 7662224,
      "step": 27365
    },
    {
      "epoch": 304.1111111111111,
      "grad_norm": 1.576591301954977e-08,
      "learning_rate": 0.06795206641974678,
      "loss": 0.0,
      "num_input_tokens_seen": 7663648,
      "step": 27370
    },
    {
      "epoch": 304.1666666666667,
      "grad_norm": 1.222323930960556e-07,
      "learning_rate": 0.06790276103635169,
      "loss": 0.0,
      "num_input_tokens_seen": 7665024,
      "step": 27375
    },
    {
      "epoch": 304.22222222222223,
      "grad_norm": 1.4069610365652352e-08,
      "learning_rate": 0.0678534683133826,
      "loss": 0.0,
      "num_input_tokens_seen": 7666448,
      "step": 27380
    },
    {
      "epoch": 304.27777777777777,
      "grad_norm": 1.9926703842543247e-08,
      "learning_rate": 0.06780418825844095,
      "loss": 0.0,
      "num_input_tokens_seen": 7667840,
      "step": 27385
    },
    {
      "epoch": 304.3333333333333,
      "grad_norm": 3.022481109837827e-08,
      "learning_rate": 0.0677549208791264,
      "loss": 0.0,
      "num_input_tokens_seen": 7669232,
      "step": 27390
    },
    {
      "epoch": 304.3888888888889,
      "grad_norm": 5.788875512280356e-08,
      "learning_rate": 0.06770566618303668,
      "loss": 0.0,
      "num_input_tokens_seen": 7670608,
      "step": 27395
    },
    {
      "epoch": 304.44444444444446,
      "grad_norm": 2.844071289587191e-08,
      "learning_rate": 0.06765642417776736,
      "loss": 0.0,
      "num_input_tokens_seen": 7672000,
      "step": 27400
    },
    {
      "epoch": 304.44444444444446,
      "eval_loss": 1.5742164850234985,
      "eval_runtime": 1.1881,
      "eval_samples_per_second": 33.669,
      "eval_steps_per_second": 16.834,
      "num_input_tokens_seen": 7672000,
      "step": 27400
    },
    {
      "epoch": 304.5,
      "grad_norm": 9.334510053804479e-09,
      "learning_rate": 0.0676071948709122,
      "loss": 0.0,
      "num_input_tokens_seen": 7673360,
      "step": 27405
    },
    {
      "epoch": 304.55555555555554,
      "grad_norm": 1.84094997024431e-08,
      "learning_rate": 0.06755797827006307,
      "loss": 0.0,
      "num_input_tokens_seen": 7674720,
      "step": 27410
    },
    {
      "epoch": 304.6111111111111,
      "grad_norm": 7.213093766722523e-08,
      "learning_rate": 0.06750877438280974,
      "loss": 0.0,
      "num_input_tokens_seen": 7676144,
      "step": 27415
    },
    {
      "epoch": 304.6666666666667,
      "grad_norm": 8.752129687650267e-09,
      "learning_rate": 0.06745958321673998,
      "loss": 0.0,
      "num_input_tokens_seen": 7677568,
      "step": 27420
    },
    {
      "epoch": 304.72222222222223,
      "grad_norm": 1.7797745499592565e-08,
      "learning_rate": 0.0674104047794398,
      "loss": 0.0,
      "num_input_tokens_seen": 7678992,
      "step": 27425
    },
    {
      "epoch": 304.77777777777777,
      "grad_norm": 1.2871976373673988e-08,
      "learning_rate": 0.06736123907849303,
      "loss": 0.0,
      "num_input_tokens_seen": 7680384,
      "step": 27430
    },
    {
      "epoch": 304.8333333333333,
      "grad_norm": 1.1349239770197528e-08,
      "learning_rate": 0.06731208612148178,
      "loss": 0.0,
      "num_input_tokens_seen": 7681760,
      "step": 27435
    },
    {
      "epoch": 304.8888888888889,
      "grad_norm": 1.3844505097893034e-08,
      "learning_rate": 0.0672629459159859,
      "loss": 0.0,
      "num_input_tokens_seen": 7683168,
      "step": 27440
    },
    {
      "epoch": 304.94444444444446,
      "grad_norm": 2.7103135735728756e-08,
      "learning_rate": 0.0672138184695835,
      "loss": 0.0,
      "num_input_tokens_seen": 7684576,
      "step": 27445
    },
    {
      "epoch": 305.0,
      "grad_norm": 2.5946038206825506e-08,
      "learning_rate": 0.0671647037898507,
      "loss": 0.0,
      "num_input_tokens_seen": 7685984,
      "step": 27450
    },
    {
      "epoch": 305.05555555555554,
      "grad_norm": 2.7099918753492602e-08,
      "learning_rate": 0.0671156018843615,
      "loss": 0.0,
      "num_input_tokens_seen": 7687376,
      "step": 27455
    },
    {
      "epoch": 305.1111111111111,
      "grad_norm": 1.4964482986101757e-08,
      "learning_rate": 0.06706651276068812,
      "loss": 0.0,
      "num_input_tokens_seen": 7688816,
      "step": 27460
    },
    {
      "epoch": 305.1666666666667,
      "grad_norm": 1.6656462875630496e-08,
      "learning_rate": 0.06701743642640064,
      "loss": 0.0,
      "num_input_tokens_seen": 7690224,
      "step": 27465
    },
    {
      "epoch": 305.22222222222223,
      "grad_norm": 2.1209725531434742e-08,
      "learning_rate": 0.06696837288906729,
      "loss": 0.0,
      "num_input_tokens_seen": 7691616,
      "step": 27470
    },
    {
      "epoch": 305.27777777777777,
      "grad_norm": 2.6592811508407976e-08,
      "learning_rate": 0.06691932215625432,
      "loss": 0.0,
      "num_input_tokens_seen": 7692992,
      "step": 27475
    },
    {
      "epoch": 305.3333333333333,
      "grad_norm": 2.2591709836206064e-08,
      "learning_rate": 0.06687028423552589,
      "loss": 0.0,
      "num_input_tokens_seen": 7694384,
      "step": 27480
    },
    {
      "epoch": 305.3888888888889,
      "grad_norm": 1.0715543652395354e-07,
      "learning_rate": 0.06682125913444435,
      "loss": 0.0,
      "num_input_tokens_seen": 7695824,
      "step": 27485
    },
    {
      "epoch": 305.44444444444446,
      "grad_norm": 1.7415453967828398e-08,
      "learning_rate": 0.0667722468605699,
      "loss": 0.0,
      "num_input_tokens_seen": 7697216,
      "step": 27490
    },
    {
      "epoch": 305.5,
      "grad_norm": 1.67912084236832e-08,
      "learning_rate": 0.06672324742146094,
      "loss": 0.0,
      "num_input_tokens_seen": 7698608,
      "step": 27495
    },
    {
      "epoch": 305.55555555555554,
      "grad_norm": 4.318809487813269e-08,
      "learning_rate": 0.06667426082467373,
      "loss": 0.0,
      "num_input_tokens_seen": 7699968,
      "step": 27500
    },
    {
      "epoch": 305.6111111111111,
      "grad_norm": 1.4174097451302714e-08,
      "learning_rate": 0.0666252870777626,
      "loss": 0.0,
      "num_input_tokens_seen": 7701360,
      "step": 27505
    },
    {
      "epoch": 305.6666666666667,
      "grad_norm": 4.120082053304941e-08,
      "learning_rate": 0.06657632618827995,
      "loss": 0.0,
      "num_input_tokens_seen": 7702752,
      "step": 27510
    },
    {
      "epoch": 305.72222222222223,
      "grad_norm": 2.786162234258427e-08,
      "learning_rate": 0.06652737816377623,
      "loss": 0.0,
      "num_input_tokens_seen": 7704128,
      "step": 27515
    },
    {
      "epoch": 305.77777777777777,
      "grad_norm": 2.5305361361915857e-08,
      "learning_rate": 0.06647844301179971,
      "loss": 0.0,
      "num_input_tokens_seen": 7705520,
      "step": 27520
    },
    {
      "epoch": 305.8333333333333,
      "grad_norm": 5.4585491682246357e-08,
      "learning_rate": 0.06642952073989689,
      "loss": 0.0,
      "num_input_tokens_seen": 7706928,
      "step": 27525
    },
    {
      "epoch": 305.8888888888889,
      "grad_norm": 5.9442658795205716e-08,
      "learning_rate": 0.06638061135561223,
      "loss": 0.0,
      "num_input_tokens_seen": 7708336,
      "step": 27530
    },
    {
      "epoch": 305.94444444444446,
      "grad_norm": 2.2528000798160974e-08,
      "learning_rate": 0.06633171486648808,
      "loss": 0.0,
      "num_input_tokens_seen": 7709728,
      "step": 27535
    },
    {
      "epoch": 306.0,
      "grad_norm": 3.728497333099767e-08,
      "learning_rate": 0.06628283128006499,
      "loss": 0.0,
      "num_input_tokens_seen": 7711104,
      "step": 27540
    },
    {
      "epoch": 306.05555555555554,
      "grad_norm": 1.994737175436967e-08,
      "learning_rate": 0.0662339606038813,
      "loss": 0.0,
      "num_input_tokens_seen": 7712512,
      "step": 27545
    },
    {
      "epoch": 306.1111111111111,
      "grad_norm": 8.333869061516452e-08,
      "learning_rate": 0.06618510284547358,
      "loss": 0.0,
      "num_input_tokens_seen": 7713936,
      "step": 27550
    },
    {
      "epoch": 306.1666666666667,
      "grad_norm": 1.71105583035569e-08,
      "learning_rate": 0.06613625801237633,
      "loss": 0.0,
      "num_input_tokens_seen": 7715312,
      "step": 27555
    },
    {
      "epoch": 306.22222222222223,
      "grad_norm": 2.661768405687326e-08,
      "learning_rate": 0.066087426112122,
      "loss": 0.0,
      "num_input_tokens_seen": 7716656,
      "step": 27560
    },
    {
      "epoch": 306.27777777777777,
      "grad_norm": 3.498352185715703e-08,
      "learning_rate": 0.06603860715224101,
      "loss": 0.0,
      "num_input_tokens_seen": 7718064,
      "step": 27565
    },
    {
      "epoch": 306.3333333333333,
      "grad_norm": 1.3080786231967068e-07,
      "learning_rate": 0.06598980114026198,
      "loss": 0.0,
      "num_input_tokens_seen": 7719456,
      "step": 27570
    },
    {
      "epoch": 306.3888888888889,
      "grad_norm": 1.9847780308168694e-08,
      "learning_rate": 0.06594100808371128,
      "loss": 0.0,
      "num_input_tokens_seen": 7720864,
      "step": 27575
    },
    {
      "epoch": 306.44444444444446,
      "grad_norm": 2.15183568741395e-08,
      "learning_rate": 0.06589222799011357,
      "loss": 0.0,
      "num_input_tokens_seen": 7722240,
      "step": 27580
    },
    {
      "epoch": 306.5,
      "grad_norm": 3.623643252126385e-08,
      "learning_rate": 0.0658434608669912,
      "loss": 0.0,
      "num_input_tokens_seen": 7723648,
      "step": 27585
    },
    {
      "epoch": 306.55555555555554,
      "grad_norm": 3.82701657031248e-08,
      "learning_rate": 0.06579470672186473,
      "loss": 0.0,
      "num_input_tokens_seen": 7725040,
      "step": 27590
    },
    {
      "epoch": 306.6111111111111,
      "grad_norm": 7.250644529221972e-08,
      "learning_rate": 0.06574596556225275,
      "loss": 0.0,
      "num_input_tokens_seen": 7726400,
      "step": 27595
    },
    {
      "epoch": 306.6666666666667,
      "grad_norm": 4.8914326811200226e-08,
      "learning_rate": 0.06569723739567161,
      "loss": 0.0,
      "num_input_tokens_seen": 7727808,
      "step": 27600
    },
    {
      "epoch": 306.6666666666667,
      "eval_loss": 1.6184145212173462,
      "eval_runtime": 1.1823,
      "eval_samples_per_second": 33.833,
      "eval_steps_per_second": 16.917,
      "num_input_tokens_seen": 7727808,
      "step": 27600
    },
    {
      "epoch": 306.72222222222223,
      "grad_norm": 1.9933024120177834e-08,
      "learning_rate": 0.06564852222963588,
      "loss": 0.0,
      "num_input_tokens_seen": 7729200,
      "step": 27605
    },
    {
      "epoch": 306.77777777777777,
      "grad_norm": 4.417160326397607e-08,
      "learning_rate": 0.06559982007165813,
      "loss": 0.0,
      "num_input_tokens_seen": 7730640,
      "step": 27610
    },
    {
      "epoch": 306.8333333333333,
      "grad_norm": 4.335975134495129e-08,
      "learning_rate": 0.06555113092924868,
      "loss": 0.0,
      "num_input_tokens_seen": 7732016,
      "step": 27615
    },
    {
      "epoch": 306.8888888888889,
      "grad_norm": 2.98186471070494e-08,
      "learning_rate": 0.06550245480991615,
      "loss": 0.0,
      "num_input_tokens_seen": 7733440,
      "step": 27620
    },
    {
      "epoch": 306.94444444444446,
      "grad_norm": 2.9144047175577725e-08,
      "learning_rate": 0.0654537917211669,
      "loss": 0.0,
      "num_input_tokens_seen": 7734832,
      "step": 27625
    },
    {
      "epoch": 307.0,
      "grad_norm": 2.346454408552745e-08,
      "learning_rate": 0.0654051416705055,
      "loss": 0.0,
      "num_input_tokens_seen": 7736224,
      "step": 27630
    },
    {
      "epoch": 307.05555555555554,
      "grad_norm": 2.632697793103489e-08,
      "learning_rate": 0.06535650466543427,
      "loss": 0.0,
      "num_input_tokens_seen": 7737616,
      "step": 27635
    },
    {
      "epoch": 307.1111111111111,
      "grad_norm": 1.2720232867025061e-08,
      "learning_rate": 0.0653078807134538,
      "loss": 0.0,
      "num_input_tokens_seen": 7739040,
      "step": 27640
    },
    {
      "epoch": 307.1666666666667,
      "grad_norm": 2.9508735011063436e-08,
      "learning_rate": 0.06525926982206236,
      "loss": 0.0,
      "num_input_tokens_seen": 7740464,
      "step": 27645
    },
    {
      "epoch": 307.22222222222223,
      "grad_norm": 1.397808659930888e-07,
      "learning_rate": 0.06521067199875648,
      "loss": 0.0,
      "num_input_tokens_seen": 7741872,
      "step": 27650
    },
    {
      "epoch": 307.27777777777777,
      "grad_norm": 6.631483984165243e-08,
      "learning_rate": 0.06516208725103047,
      "loss": 0.0,
      "num_input_tokens_seen": 7743264,
      "step": 27655
    },
    {
      "epoch": 307.3333333333333,
      "grad_norm": 2.35679440407921e-08,
      "learning_rate": 0.06511351558637678,
      "loss": 0.0,
      "num_input_tokens_seen": 7744672,
      "step": 27660
    },
    {
      "epoch": 307.3888888888889,
      "grad_norm": 2.552251565646202e-08,
      "learning_rate": 0.06506495701228569,
      "loss": 0.0,
      "num_input_tokens_seen": 7746048,
      "step": 27665
    },
    {
      "epoch": 307.44444444444446,
      "grad_norm": 2.3289844719442954e-08,
      "learning_rate": 0.06501641153624559,
      "loss": 0.0,
      "num_input_tokens_seen": 7747456,
      "step": 27670
    },
    {
      "epoch": 307.5,
      "grad_norm": 2.8094227388919535e-08,
      "learning_rate": 0.06496787916574286,
      "loss": 0.0,
      "num_input_tokens_seen": 7748864,
      "step": 27675
    },
    {
      "epoch": 307.55555555555554,
      "grad_norm": 1.948722427869143e-08,
      "learning_rate": 0.06491935990826168,
      "loss": 0.0,
      "num_input_tokens_seen": 7750272,
      "step": 27680
    },
    {
      "epoch": 307.6111111111111,
      "grad_norm": 1.737919852473624e-08,
      "learning_rate": 0.0648708537712844,
      "loss": 0.0,
      "num_input_tokens_seen": 7751616,
      "step": 27685
    },
    {
      "epoch": 307.6666666666667,
      "grad_norm": 1.875751109992052e-08,
      "learning_rate": 0.06482236076229132,
      "loss": 0.0,
      "num_input_tokens_seen": 7753024,
      "step": 27690
    },
    {
      "epoch": 307.72222222222223,
      "grad_norm": 1.953659456432888e-08,
      "learning_rate": 0.06477388088876056,
      "loss": 0.0,
      "num_input_tokens_seen": 7754400,
      "step": 27695
    },
    {
      "epoch": 307.77777777777777,
      "grad_norm": 1.9605057133276205e-08,
      "learning_rate": 0.06472541415816846,
      "loss": 0.0,
      "num_input_tokens_seen": 7755840,
      "step": 27700
    },
    {
      "epoch": 307.8333333333333,
      "grad_norm": 1.848410313698423e-08,
      "learning_rate": 0.06467696057798909,
      "loss": 0.0,
      "num_input_tokens_seen": 7757248,
      "step": 27705
    },
    {
      "epoch": 307.8888888888889,
      "grad_norm": 5.151243698264807e-08,
      "learning_rate": 0.0646285201556946,
      "loss": 0.0,
      "num_input_tokens_seen": 7758640,
      "step": 27710
    },
    {
      "epoch": 307.94444444444446,
      "grad_norm": 8.246811944445653e-08,
      "learning_rate": 0.06458009289875521,
      "loss": 0.0,
      "num_input_tokens_seen": 7759968,
      "step": 27715
    },
    {
      "epoch": 308.0,
      "grad_norm": 1.7160090237666736e-08,
      "learning_rate": 0.0645316788146389,
      "loss": 0.0,
      "num_input_tokens_seen": 7761408,
      "step": 27720
    },
    {
      "epoch": 308.05555555555554,
      "grad_norm": 1.7132954610588058e-08,
      "learning_rate": 0.06448327791081175,
      "loss": 0.0,
      "num_input_tokens_seen": 7762816,
      "step": 27725
    },
    {
      "epoch": 308.1111111111111,
      "grad_norm": 3.078633525888108e-08,
      "learning_rate": 0.0644348901947379,
      "loss": 0.0,
      "num_input_tokens_seen": 7764208,
      "step": 27730
    },
    {
      "epoch": 308.1666666666667,
      "grad_norm": 5.8122903823232264e-08,
      "learning_rate": 0.06438651567387917,
      "loss": 0.0,
      "num_input_tokens_seen": 7765584,
      "step": 27735
    },
    {
      "epoch": 308.22222222222223,
      "grad_norm": 1.750735556527161e-08,
      "learning_rate": 0.0643381543556957,
      "loss": 0.0,
      "num_input_tokens_seen": 7766976,
      "step": 27740
    },
    {
      "epoch": 308.27777777777777,
      "grad_norm": 2.364128093290674e-08,
      "learning_rate": 0.06428980624764526,
      "loss": 0.0,
      "num_input_tokens_seen": 7768336,
      "step": 27745
    },
    {
      "epoch": 308.3333333333333,
      "grad_norm": 1.5347872306392674e-08,
      "learning_rate": 0.06424147135718378,
      "loss": 0.0,
      "num_input_tokens_seen": 7769776,
      "step": 27750
    },
    {
      "epoch": 308.3888888888889,
      "grad_norm": 1.9999622224986524e-07,
      "learning_rate": 0.06419314969176519,
      "loss": 0.0,
      "num_input_tokens_seen": 7771168,
      "step": 27755
    },
    {
      "epoch": 308.44444444444446,
      "grad_norm": 3.898389522305479e-08,
      "learning_rate": 0.06414484125884118,
      "loss": 0.0,
      "num_input_tokens_seen": 7772544,
      "step": 27760
    },
    {
      "epoch": 308.5,
      "grad_norm": 1.610723288081317e-08,
      "learning_rate": 0.06409654606586157,
      "loss": 0.0,
      "num_input_tokens_seen": 7773984,
      "step": 27765
    },
    {
      "epoch": 308.55555555555554,
      "grad_norm": 1.112851766293943e-08,
      "learning_rate": 0.06404826412027415,
      "loss": 0.0,
      "num_input_tokens_seen": 7775408,
      "step": 27770
    },
    {
      "epoch": 308.6111111111111,
      "grad_norm": 4.175320711397035e-08,
      "learning_rate": 0.06399999542952453,
      "loss": 0.0,
      "num_input_tokens_seen": 7776784,
      "step": 27775
    },
    {
      "epoch": 308.6666666666667,
      "grad_norm": 3.4960105921300055e-08,
      "learning_rate": 0.0639517400010563,
      "loss": 0.0,
      "num_input_tokens_seen": 7778192,
      "step": 27780
    },
    {
      "epoch": 308.72222222222223,
      "grad_norm": 4.8514955608425225e-08,
      "learning_rate": 0.06390349784231118,
      "loss": 0.0,
      "num_input_tokens_seen": 7779632,
      "step": 27785
    },
    {
      "epoch": 308.77777777777777,
      "grad_norm": 2.0782481513492712e-08,
      "learning_rate": 0.06385526896072859,
      "loss": 0.0,
      "num_input_tokens_seen": 7781008,
      "step": 27790
    },
    {
      "epoch": 308.8333333333333,
      "grad_norm": 2.601352200315432e-08,
      "learning_rate": 0.06380705336374613,
      "loss": 0.0,
      "num_input_tokens_seen": 7782384,
      "step": 27795
    },
    {
      "epoch": 308.8888888888889,
      "grad_norm": 2.417094435713807e-08,
      "learning_rate": 0.06375885105879918,
      "loss": 0.0,
      "num_input_tokens_seen": 7783744,
      "step": 27800
    },
    {
      "epoch": 308.8888888888889,
      "eval_loss": 1.5990965366363525,
      "eval_runtime": 1.1841,
      "eval_samples_per_second": 33.782,
      "eval_steps_per_second": 16.891,
      "num_input_tokens_seen": 7783744,
      "step": 27800
    },
    {
      "epoch": 308.94444444444446,
      "grad_norm": 1.5464603819737022e-08,
      "learning_rate": 0.06371066205332115,
      "loss": 0.0,
      "num_input_tokens_seen": 7785152,
      "step": 27805
    },
    {
      "epoch": 309.0,
      "grad_norm": 2.3227988421581358e-08,
      "learning_rate": 0.06366248635474347,
      "loss": 0.0,
      "num_input_tokens_seen": 7786560,
      "step": 27810
    },
    {
      "epoch": 309.05555555555554,
      "grad_norm": 1.604794341858451e-08,
      "learning_rate": 0.06361432397049532,
      "loss": 0.0,
      "num_input_tokens_seen": 7787952,
      "step": 27815
    },
    {
      "epoch": 309.1111111111111,
      "grad_norm": 2.6257390928208224e-08,
      "learning_rate": 0.06356617490800408,
      "loss": 0.0,
      "num_input_tokens_seen": 7789376,
      "step": 27820
    },
    {
      "epoch": 309.1666666666667,
      "grad_norm": 3.726098896095209e-08,
      "learning_rate": 0.06351803917469478,
      "loss": 0.0,
      "num_input_tokens_seen": 7790800,
      "step": 27825
    },
    {
      "epoch": 309.22222222222223,
      "grad_norm": 1.8770879961493847e-08,
      "learning_rate": 0.06346991677799067,
      "loss": 0.0,
      "num_input_tokens_seen": 7792192,
      "step": 27830
    },
    {
      "epoch": 309.27777777777777,
      "grad_norm": 3.881547527839757e-08,
      "learning_rate": 0.06342180772531283,
      "loss": 0.0,
      "num_input_tokens_seen": 7793584,
      "step": 27835
    },
    {
      "epoch": 309.3333333333333,
      "grad_norm": 2.6767748906308952e-08,
      "learning_rate": 0.06337371202408021,
      "loss": 0.0,
      "num_input_tokens_seen": 7795024,
      "step": 27840
    },
    {
      "epoch": 309.3888888888889,
      "grad_norm": 2.0718941229347365e-08,
      "learning_rate": 0.06332562968170984,
      "loss": 0.0,
      "num_input_tokens_seen": 7796432,
      "step": 27845
    },
    {
      "epoch": 309.44444444444446,
      "grad_norm": 4.569534439724521e-08,
      "learning_rate": 0.06327756070561656,
      "loss": 0.0,
      "num_input_tokens_seen": 7797824,
      "step": 27850
    },
    {
      "epoch": 309.5,
      "grad_norm": 2.824639366849624e-08,
      "learning_rate": 0.06322950510321329,
      "loss": 0.0,
      "num_input_tokens_seen": 7799200,
      "step": 27855
    },
    {
      "epoch": 309.55555555555554,
      "grad_norm": 2.3170867891053604e-08,
      "learning_rate": 0.06318146288191076,
      "loss": 0.0,
      "num_input_tokens_seen": 7800576,
      "step": 27860
    },
    {
      "epoch": 309.6111111111111,
      "grad_norm": 2.1916269687949352e-08,
      "learning_rate": 0.06313343404911763,
      "loss": 0.0,
      "num_input_tokens_seen": 7801936,
      "step": 27865
    },
    {
      "epoch": 309.6666666666667,
      "grad_norm": 4.708287093535546e-08,
      "learning_rate": 0.0630854186122406,
      "loss": 0.0,
      "num_input_tokens_seen": 7803312,
      "step": 27870
    },
    {
      "epoch": 309.72222222222223,
      "grad_norm": 1.4305383899682056e-07,
      "learning_rate": 0.06303741657868431,
      "loss": 0.0,
      "num_input_tokens_seen": 7804736,
      "step": 27875
    },
    {
      "epoch": 309.77777777777777,
      "grad_norm": 1.4592196784235512e-08,
      "learning_rate": 0.06298942795585115,
      "loss": 0.0,
      "num_input_tokens_seen": 7806144,
      "step": 27880
    },
    {
      "epoch": 309.8333333333333,
      "grad_norm": 5.6767920142419825e-08,
      "learning_rate": 0.06294145275114167,
      "loss": 0.0,
      "num_input_tokens_seen": 7807536,
      "step": 27885
    },
    {
      "epoch": 309.8888888888889,
      "grad_norm": 1.807987715096715e-08,
      "learning_rate": 0.06289349097195428,
      "loss": 0.0,
      "num_input_tokens_seen": 7808944,
      "step": 27890
    },
    {
      "epoch": 309.94444444444446,
      "grad_norm": 3.051701824574593e-08,
      "learning_rate": 0.06284554262568516,
      "loss": 0.0,
      "num_input_tokens_seen": 7810336,
      "step": 27895
    },
    {
      "epoch": 310.0,
      "grad_norm": 4.43669847527417e-08,
      "learning_rate": 0.06279760771972868,
      "loss": 0.0,
      "num_input_tokens_seen": 7811744,
      "step": 27900
    },
    {
      "epoch": 310.05555555555554,
      "grad_norm": 6.844600619615449e-08,
      "learning_rate": 0.06274968626147688,
      "loss": 0.0,
      "num_input_tokens_seen": 7813104,
      "step": 27905
    },
    {
      "epoch": 310.1111111111111,
      "grad_norm": 2.8262839180115407e-08,
      "learning_rate": 0.06270177825831993,
      "loss": 0.0,
      "num_input_tokens_seen": 7814496,
      "step": 27910
    },
    {
      "epoch": 310.1666666666667,
      "grad_norm": 3.150947591734621e-08,
      "learning_rate": 0.06265388371764587,
      "loss": 0.0,
      "num_input_tokens_seen": 7815888,
      "step": 27915
    },
    {
      "epoch": 310.22222222222223,
      "grad_norm": 6.917904471492875e-08,
      "learning_rate": 0.0626060026468406,
      "loss": 0.0,
      "num_input_tokens_seen": 7817328,
      "step": 27920
    },
    {
      "epoch": 310.27777777777777,
      "grad_norm": 1.3987866864795251e-08,
      "learning_rate": 0.06255813505328794,
      "loss": 0.0,
      "num_input_tokens_seen": 7818752,
      "step": 27925
    },
    {
      "epoch": 310.3333333333333,
      "grad_norm": 7.07933125454474e-08,
      "learning_rate": 0.06251028094436978,
      "loss": 0.0,
      "num_input_tokens_seen": 7820176,
      "step": 27930
    },
    {
      "epoch": 310.3888888888889,
      "grad_norm": 3.5136277887204415e-08,
      "learning_rate": 0.06246244032746568,
      "loss": 0.0,
      "num_input_tokens_seen": 7821568,
      "step": 27935
    },
    {
      "epoch": 310.44444444444446,
      "grad_norm": 3.059752984313491e-08,
      "learning_rate": 0.06241461320995342,
      "loss": 0.0,
      "num_input_tokens_seen": 7823024,
      "step": 27940
    },
    {
      "epoch": 310.5,
      "grad_norm": 2.3387192626955766e-08,
      "learning_rate": 0.062366799599208426,
      "loss": 0.0,
      "num_input_tokens_seen": 7824400,
      "step": 27945
    },
    {
      "epoch": 310.55555555555554,
      "grad_norm": 4.372873618763151e-08,
      "learning_rate": 0.06231899950260418,
      "loss": 0.0,
      "num_input_tokens_seen": 7825792,
      "step": 27950
    },
    {
      "epoch": 310.6111111111111,
      "grad_norm": 1.8748528063383674e-08,
      "learning_rate": 0.06227121292751214,
      "loss": 0.0,
      "num_input_tokens_seen": 7827168,
      "step": 27955
    },
    {
      "epoch": 310.6666666666667,
      "grad_norm": 1.1268735278235908e-08,
      "learning_rate": 0.062223439881301496,
      "loss": 0.0,
      "num_input_tokens_seen": 7828624,
      "step": 27960
    },
    {
      "epoch": 310.72222222222223,
      "grad_norm": 2.0924641574993075e-08,
      "learning_rate": 0.06217568037133948,
      "loss": 0.0,
      "num_input_tokens_seen": 7830000,
      "step": 27965
    },
    {
      "epoch": 310.77777777777777,
      "grad_norm": 1.8806019852490863e-08,
      "learning_rate": 0.06212793440499126,
      "loss": 0.0,
      "num_input_tokens_seen": 7831424,
      "step": 27970
    },
    {
      "epoch": 310.8333333333333,
      "grad_norm": 1.4327622466225876e-07,
      "learning_rate": 0.062080201989619783,
      "loss": 0.0,
      "num_input_tokens_seen": 7832848,
      "step": 27975
    },
    {
      "epoch": 310.8888888888889,
      "grad_norm": 2.4982400148587658e-08,
      "learning_rate": 0.062032483132586094,
      "loss": 0.0,
      "num_input_tokens_seen": 7834224,
      "step": 27980
    },
    {
      "epoch": 310.94444444444446,
      "grad_norm": 2.9859474892646176e-08,
      "learning_rate": 0.0619847778412489,
      "loss": 0.0,
      "num_input_tokens_seen": 7835600,
      "step": 27985
    },
    {
      "epoch": 311.0,
      "grad_norm": 2.6550734943953103e-08,
      "learning_rate": 0.06193708612296509,
      "loss": 0.0,
      "num_input_tokens_seen": 7837008,
      "step": 27990
    },
    {
      "epoch": 311.05555555555554,
      "grad_norm": 3.249182256581662e-08,
      "learning_rate": 0.06188940798508923,
      "loss": 0.0,
      "num_input_tokens_seen": 7838416,
      "step": 27995
    },
    {
      "epoch": 311.1111111111111,
      "grad_norm": 2.5944951076439793e-08,
      "learning_rate": 0.06184174343497397,
      "loss": 0.0,
      "num_input_tokens_seen": 7839808,
      "step": 28000
    },
    {
      "epoch": 311.1111111111111,
      "eval_loss": 1.5417873859405518,
      "eval_runtime": 1.1843,
      "eval_samples_per_second": 33.775,
      "eval_steps_per_second": 16.888,
      "num_input_tokens_seen": 7839808,
      "step": 28000
    },
    {
      "epoch": 311.1666666666667,
      "grad_norm": 2.8341951008314936e-08,
      "learning_rate": 0.061794092479969726,
      "loss": 0.0,
      "num_input_tokens_seen": 7841184,
      "step": 28005
    },
    {
      "epoch": 311.22222222222223,
      "grad_norm": 3.075674115393667e-08,
      "learning_rate": 0.06174645512742485,
      "loss": 0.0,
      "num_input_tokens_seen": 7842576,
      "step": 28010
    },
    {
      "epoch": 311.27777777777777,
      "grad_norm": 6.167407207158249e-08,
      "learning_rate": 0.06169883138468565,
      "loss": 0.0,
      "num_input_tokens_seen": 7844016,
      "step": 28015
    },
    {
      "epoch": 311.3333333333333,
      "grad_norm": 1.9649688098866136e-08,
      "learning_rate": 0.06165122125909637,
      "loss": 0.0,
      "num_input_tokens_seen": 7845376,
      "step": 28020
    },
    {
      "epoch": 311.3888888888889,
      "grad_norm": 5.954426640641941e-08,
      "learning_rate": 0.061603624757998965,
      "loss": 0.0,
      "num_input_tokens_seen": 7846768,
      "step": 28025
    },
    {
      "epoch": 311.44444444444446,
      "grad_norm": 1.4642266954467686e-08,
      "learning_rate": 0.0615560418887335,
      "loss": 0.0,
      "num_input_tokens_seen": 7848192,
      "step": 28030
    },
    {
      "epoch": 311.5,
      "grad_norm": 4.1260072691784444e-08,
      "learning_rate": 0.06150847265863787,
      "loss": 0.0,
      "num_input_tokens_seen": 7849600,
      "step": 28035
    },
    {
      "epoch": 311.55555555555554,
      "grad_norm": 2.1152260387680144e-08,
      "learning_rate": 0.061460917075047757,
      "loss": 0.0,
      "num_input_tokens_seen": 7851024,
      "step": 28040
    },
    {
      "epoch": 311.6111111111111,
      "grad_norm": 2.532140541688932e-08,
      "learning_rate": 0.06141337514529694,
      "loss": 0.0,
      "num_input_tokens_seen": 7852432,
      "step": 28045
    },
    {
      "epoch": 311.6666666666667,
      "grad_norm": 1.704619911890859e-08,
      "learning_rate": 0.06136584687671687,
      "loss": 0.0,
      "num_input_tokens_seen": 7853824,
      "step": 28050
    },
    {
      "epoch": 311.72222222222223,
      "grad_norm": 1.818741957038128e-08,
      "learning_rate": 0.061318332276637064,
      "loss": 0.0,
      "num_input_tokens_seen": 7855216,
      "step": 28055
    },
    {
      "epoch": 311.77777777777777,
      "grad_norm": 3.198927700509557e-08,
      "learning_rate": 0.06127083135238491,
      "loss": 0.0,
      "num_input_tokens_seen": 7856624,
      "step": 28060
    },
    {
      "epoch": 311.8333333333333,
      "grad_norm": 1.4306920981255189e-08,
      "learning_rate": 0.06122334411128555,
      "loss": 0.0,
      "num_input_tokens_seen": 7858016,
      "step": 28065
    },
    {
      "epoch": 311.8888888888889,
      "grad_norm": 1.3601016313202763e-08,
      "learning_rate": 0.06117587056066223,
      "loss": 0.0,
      "num_input_tokens_seen": 7859424,
      "step": 28070
    },
    {
      "epoch": 311.94444444444446,
      "grad_norm": 3.81721960707182e-08,
      "learning_rate": 0.06112841070783589,
      "loss": 0.0,
      "num_input_tokens_seen": 7860800,
      "step": 28075
    },
    {
      "epoch": 312.0,
      "grad_norm": 1.8640889720700216e-08,
      "learning_rate": 0.061080964560125406,
      "loss": 0.0,
      "num_input_tokens_seen": 7862176,
      "step": 28080
    },
    {
      "epoch": 312.05555555555554,
      "grad_norm": 1.8263071055457658e-08,
      "learning_rate": 0.06103353212484766,
      "loss": 0.0,
      "num_input_tokens_seen": 7863568,
      "step": 28085
    },
    {
      "epoch": 312.1111111111111,
      "grad_norm": 2.913813723637304e-08,
      "learning_rate": 0.06098611340931722,
      "loss": 0.0,
      "num_input_tokens_seen": 7864944,
      "step": 28090
    },
    {
      "epoch": 312.1666666666667,
      "grad_norm": 3.0730223699038106e-08,
      "learning_rate": 0.06093870842084672,
      "loss": 0.0,
      "num_input_tokens_seen": 7866336,
      "step": 28095
    },
    {
      "epoch": 312.22222222222223,
      "grad_norm": 3.1420690049799305e-08,
      "learning_rate": 0.06089131716674666,
      "loss": 0.0,
      "num_input_tokens_seen": 7867744,
      "step": 28100
    },
    {
      "epoch": 312.27777777777777,
      "grad_norm": 1.7708176258679487e-08,
      "learning_rate": 0.060843939654325226,
      "loss": 0.0,
      "num_input_tokens_seen": 7869152,
      "step": 28105
    },
    {
      "epoch": 312.3333333333333,
      "grad_norm": 8.955633035157007e-08,
      "learning_rate": 0.06079657589088873,
      "loss": 0.0,
      "num_input_tokens_seen": 7870560,
      "step": 28110
    },
    {
      "epoch": 312.3888888888889,
      "grad_norm": 2.032769863546946e-08,
      "learning_rate": 0.06074922588374126,
      "loss": 0.0,
      "num_input_tokens_seen": 7871968,
      "step": 28115
    },
    {
      "epoch": 312.44444444444446,
      "grad_norm": 1.3158279799085904e-08,
      "learning_rate": 0.06070188964018472,
      "loss": 0.0,
      "num_input_tokens_seen": 7873376,
      "step": 28120
    },
    {
      "epoch": 312.5,
      "grad_norm": 6.915425387887808e-08,
      "learning_rate": 0.06065456716751902,
      "loss": 0.0,
      "num_input_tokens_seen": 7874736,
      "step": 28125
    },
    {
      "epoch": 312.55555555555554,
      "grad_norm": 3.1098949193619774e-08,
      "learning_rate": 0.06060725847304182,
      "loss": 0.0,
      "num_input_tokens_seen": 7876096,
      "step": 28130
    },
    {
      "epoch": 312.6111111111111,
      "grad_norm": 2.4758636030242087e-08,
      "learning_rate": 0.06055996356404877,
      "loss": 0.0,
      "num_input_tokens_seen": 7877536,
      "step": 28135
    },
    {
      "epoch": 312.6666666666667,
      "grad_norm": 2.057119452558709e-08,
      "learning_rate": 0.06051268244783327,
      "loss": 0.0,
      "num_input_tokens_seen": 7878928,
      "step": 28140
    },
    {
      "epoch": 312.72222222222223,
      "grad_norm": 1.6595443241840258e-08,
      "learning_rate": 0.06046541513168676,
      "loss": 0.0,
      "num_input_tokens_seen": 7880320,
      "step": 28145
    },
    {
      "epoch": 312.77777777777777,
      "grad_norm": 1.447641864160687e-07,
      "learning_rate": 0.060418161622898356,
      "loss": 0.0,
      "num_input_tokens_seen": 7881760,
      "step": 28150
    },
    {
      "epoch": 312.8333333333333,
      "grad_norm": 4.0316816551921875e-08,
      "learning_rate": 0.06037092192875521,
      "loss": 0.0,
      "num_input_tokens_seen": 7883168,
      "step": 28155
    },
    {
      "epoch": 312.8888888888889,
      "grad_norm": 4.2477179107436314e-08,
      "learning_rate": 0.060323696056542225,
      "loss": 0.0,
      "num_input_tokens_seen": 7884592,
      "step": 28160
    },
    {
      "epoch": 312.94444444444446,
      "grad_norm": 6.329586454967284e-08,
      "learning_rate": 0.06027648401354229,
      "loss": 0.0,
      "num_input_tokens_seen": 7886032,
      "step": 28165
    },
    {
      "epoch": 313.0,
      "grad_norm": 2.0055482607972408e-08,
      "learning_rate": 0.06022928580703601,
      "loss": 0.0,
      "num_input_tokens_seen": 7887424,
      "step": 28170
    },
    {
      "epoch": 313.05555555555554,
      "grad_norm": 2.3938905968634572e-08,
      "learning_rate": 0.060182101444301986,
      "loss": 0.0,
      "num_input_tokens_seen": 7888816,
      "step": 28175
    },
    {
      "epoch": 313.1111111111111,
      "grad_norm": 2.0014677915014545e-08,
      "learning_rate": 0.06013493093261669,
      "loss": 0.0,
      "num_input_tokens_seen": 7890192,
      "step": 28180
    },
    {
      "epoch": 313.1666666666667,
      "grad_norm": 2.282792799235267e-08,
      "learning_rate": 0.06008777427925432,
      "loss": 0.0,
      "num_input_tokens_seen": 7891632,
      "step": 28185
    },
    {
      "epoch": 313.22222222222223,
      "grad_norm": 1.7578535960183217e-08,
      "learning_rate": 0.06004063149148705,
      "loss": 0.0,
      "num_input_tokens_seen": 7893056,
      "step": 28190
    },
    {
      "epoch": 313.27777777777777,
      "grad_norm": 2.4266650910931276e-08,
      "learning_rate": 0.05999350257658497,
      "loss": 0.0,
      "num_input_tokens_seen": 7894448,
      "step": 28195
    },
    {
      "epoch": 313.3333333333333,
      "grad_norm": 1.8610748497849272e-08,
      "learning_rate": 0.05994638754181582,
      "loss": 0.0,
      "num_input_tokens_seen": 7895872,
      "step": 28200
    },
    {
      "epoch": 313.3333333333333,
      "eval_loss": 1.616999864578247,
      "eval_runtime": 1.189,
      "eval_samples_per_second": 33.643,
      "eval_steps_per_second": 16.821,
      "num_input_tokens_seen": 7895872,
      "step": 28200
    },
    {
      "epoch": 313.3888888888889,
      "grad_norm": 4.575001710804827e-08,
      "learning_rate": 0.059899286394445445,
      "loss": 0.0,
      "num_input_tokens_seen": 7897264,
      "step": 28205
    },
    {
      "epoch": 313.44444444444446,
      "grad_norm": 5.549745196731237e-08,
      "learning_rate": 0.059852199141737346,
      "loss": 0.0,
      "num_input_tokens_seen": 7898656,
      "step": 28210
    },
    {
      "epoch": 313.5,
      "grad_norm": 1.631342456676066e-07,
      "learning_rate": 0.05980512579095304,
      "loss": 0.0,
      "num_input_tokens_seen": 7900048,
      "step": 28215
    },
    {
      "epoch": 313.55555555555554,
      "grad_norm": 2.7698643378926135e-08,
      "learning_rate": 0.05975806634935181,
      "loss": 0.0,
      "num_input_tokens_seen": 7901472,
      "step": 28220
    },
    {
      "epoch": 313.6111111111111,
      "grad_norm": 3.569673623360359e-08,
      "learning_rate": 0.05971102082419076,
      "loss": 0.0,
      "num_input_tokens_seen": 7902880,
      "step": 28225
    },
    {
      "epoch": 313.6666666666667,
      "grad_norm": 3.354173827574414e-08,
      "learning_rate": 0.05966398922272492,
      "loss": 0.0,
      "num_input_tokens_seen": 7904288,
      "step": 28230
    },
    {
      "epoch": 313.72222222222223,
      "grad_norm": 2.81645267108388e-08,
      "learning_rate": 0.059616971552207236,
      "loss": 0.0,
      "num_input_tokens_seen": 7905696,
      "step": 28235
    },
    {
      "epoch": 313.77777777777777,
      "grad_norm": 5.588930918065671e-08,
      "learning_rate": 0.059569967819888305,
      "loss": 0.0,
      "num_input_tokens_seen": 7907072,
      "step": 28240
    },
    {
      "epoch": 313.8333333333333,
      "grad_norm": 1.9821301933120594e-08,
      "learning_rate": 0.05952297803301681,
      "loss": 0.0,
      "num_input_tokens_seen": 7908480,
      "step": 28245
    },
    {
      "epoch": 313.8888888888889,
      "grad_norm": 5.383945733683504e-08,
      "learning_rate": 0.059476002198839056,
      "loss": 0.0,
      "num_input_tokens_seen": 7909824,
      "step": 28250
    },
    {
      "epoch": 313.94444444444446,
      "grad_norm": 2.1855839804629795e-08,
      "learning_rate": 0.05942904032459935,
      "loss": 0.0,
      "num_input_tokens_seen": 7911184,
      "step": 28255
    },
    {
      "epoch": 314.0,
      "grad_norm": 2.7534564850384413e-08,
      "learning_rate": 0.05938209241753987,
      "loss": 0.0,
      "num_input_tokens_seen": 7912528,
      "step": 28260
    },
    {
      "epoch": 314.05555555555554,
      "grad_norm": 5.7106994688638224e-08,
      "learning_rate": 0.05933515848490046,
      "loss": 0.0,
      "num_input_tokens_seen": 7913936,
      "step": 28265
    },
    {
      "epoch": 314.1111111111111,
      "grad_norm": 3.977360663043328e-08,
      "learning_rate": 0.059288238533918985,
      "loss": 0.0,
      "num_input_tokens_seen": 7915328,
      "step": 28270
    },
    {
      "epoch": 314.1666666666667,
      "grad_norm": 3.673390125413789e-08,
      "learning_rate": 0.05924133257183113,
      "loss": 0.0,
      "num_input_tokens_seen": 7916688,
      "step": 28275
    },
    {
      "epoch": 314.22222222222223,
      "grad_norm": 4.2364362684566004e-08,
      "learning_rate": 0.059194440605870285,
      "loss": 0.0,
      "num_input_tokens_seen": 7918128,
      "step": 28280
    },
    {
      "epoch": 314.27777777777777,
      "grad_norm": 4.5241538515483626e-08,
      "learning_rate": 0.059147562643267884,
      "loss": 0.0,
      "num_input_tokens_seen": 7919536,
      "step": 28285
    },
    {
      "epoch": 314.3333333333333,
      "grad_norm": 1.0374950676350636e-07,
      "learning_rate": 0.059100698691253055,
      "loss": 0.0,
      "num_input_tokens_seen": 7920896,
      "step": 28290
    },
    {
      "epoch": 314.3888888888889,
      "grad_norm": 2.445838376274878e-08,
      "learning_rate": 0.05905384875705273,
      "loss": 0.0,
      "num_input_tokens_seen": 7922304,
      "step": 28295
    },
    {
      "epoch": 314.44444444444446,
      "grad_norm": 2.816144650807928e-08,
      "learning_rate": 0.05900701284789189,
      "loss": 0.0,
      "num_input_tokens_seen": 7923744,
      "step": 28300
    },
    {
      "epoch": 314.5,
      "grad_norm": 4.105207196403171e-08,
      "learning_rate": 0.058960190970993115,
      "loss": 0.0,
      "num_input_tokens_seen": 7925152,
      "step": 28305
    },
    {
      "epoch": 314.55555555555554,
      "grad_norm": 3.620871780185553e-08,
      "learning_rate": 0.058913383133576955,
      "loss": 0.0,
      "num_input_tokens_seen": 7926544,
      "step": 28310
    },
    {
      "epoch": 314.6111111111111,
      "grad_norm": 3.064866760382756e-08,
      "learning_rate": 0.05886658934286185,
      "loss": 0.0,
      "num_input_tokens_seen": 7927936,
      "step": 28315
    },
    {
      "epoch": 314.6666666666667,
      "grad_norm": 4.1338918066458064e-08,
      "learning_rate": 0.058819809606063846,
      "loss": 0.0,
      "num_input_tokens_seen": 7929312,
      "step": 28320
    },
    {
      "epoch": 314.72222222222223,
      "grad_norm": 4.672231668223503e-08,
      "learning_rate": 0.05877304393039711,
      "loss": 0.0,
      "num_input_tokens_seen": 7930688,
      "step": 28325
    },
    {
      "epoch": 314.77777777777777,
      "grad_norm": 1.4610873400044966e-08,
      "learning_rate": 0.05872629232307338,
      "loss": 0.0,
      "num_input_tokens_seen": 7932144,
      "step": 28330
    },
    {
      "epoch": 314.8333333333333,
      "grad_norm": 3.09820542554462e-08,
      "learning_rate": 0.05867955479130239,
      "loss": 0.0,
      "num_input_tokens_seen": 7933536,
      "step": 28335
    },
    {
      "epoch": 314.8888888888889,
      "grad_norm": 2.6785121676198287e-08,
      "learning_rate": 0.058632831342291705,
      "loss": 0.0,
      "num_input_tokens_seen": 7934896,
      "step": 28340
    },
    {
      "epoch": 314.94444444444446,
      "grad_norm": 3.224454658834475e-08,
      "learning_rate": 0.05858612198324655,
      "loss": 0.0,
      "num_input_tokens_seen": 7936336,
      "step": 28345
    },
    {
      "epoch": 315.0,
      "grad_norm": 2.1747347034306586e-08,
      "learning_rate": 0.05853942672137025,
      "loss": 0.0,
      "num_input_tokens_seen": 7937744,
      "step": 28350
    },
    {
      "epoch": 315.05555555555554,
      "grad_norm": 2.3414258976117708e-08,
      "learning_rate": 0.05849274556386363,
      "loss": 0.0,
      "num_input_tokens_seen": 7939104,
      "step": 28355
    },
    {
      "epoch": 315.1111111111111,
      "grad_norm": 4.566855338339337e-08,
      "learning_rate": 0.05844607851792567,
      "loss": 0.0,
      "num_input_tokens_seen": 7940496,
      "step": 28360
    },
    {
      "epoch": 315.1666666666667,
      "grad_norm": 3.1386008458866854e-08,
      "learning_rate": 0.058399425590752924,
      "loss": 0.0,
      "num_input_tokens_seen": 7941888,
      "step": 28365
    },
    {
      "epoch": 315.22222222222223,
      "grad_norm": 7.476852914578558e-08,
      "learning_rate": 0.05835278678953985,
      "loss": 0.0,
      "num_input_tokens_seen": 7943280,
      "step": 28370
    },
    {
      "epoch": 315.27777777777777,
      "grad_norm": 6.528627238822082e-08,
      "learning_rate": 0.05830616212147874,
      "loss": 0.0,
      "num_input_tokens_seen": 7944688,
      "step": 28375
    },
    {
      "epoch": 315.3333333333333,
      "grad_norm": 3.300997164501496e-08,
      "learning_rate": 0.058259551593759784,
      "loss": 0.0,
      "num_input_tokens_seen": 7946064,
      "step": 28380
    },
    {
      "epoch": 315.3888888888889,
      "grad_norm": 2.035245927345386e-08,
      "learning_rate": 0.058212955213570804,
      "loss": 0.0,
      "num_input_tokens_seen": 7947472,
      "step": 28385
    },
    {
      "epoch": 315.44444444444446,
      "grad_norm": 7.354814357540818e-08,
      "learning_rate": 0.0581663729880976,
      "loss": 0.0,
      "num_input_tokens_seen": 7948880,
      "step": 28390
    },
    {
      "epoch": 315.5,
      "grad_norm": 4.6093095562582675e-08,
      "learning_rate": 0.05811980492452379,
      "loss": 0.0,
      "num_input_tokens_seen": 7950288,
      "step": 28395
    },
    {
      "epoch": 315.55555555555554,
      "grad_norm": 1.9570672193935934e-08,
      "learning_rate": 0.058073251030030644,
      "loss": 0.0,
      "num_input_tokens_seen": 7951664,
      "step": 28400
    },
    {
      "epoch": 315.55555555555554,
      "eval_loss": 1.6390682458877563,
      "eval_runtime": 1.1836,
      "eval_samples_per_second": 33.795,
      "eval_steps_per_second": 16.897,
      "num_input_tokens_seen": 7951664,
      "step": 28400
    },
    {
      "epoch": 315.6111111111111,
      "grad_norm": 7.223938780498429e-08,
      "learning_rate": 0.05802671131179747,
      "loss": 0.0,
      "num_input_tokens_seen": 7953120,
      "step": 28405
    },
    {
      "epoch": 315.6666666666667,
      "grad_norm": 2.137189092366043e-08,
      "learning_rate": 0.057980185777001154,
      "loss": 0.0,
      "num_input_tokens_seen": 7954544,
      "step": 28410
    },
    {
      "epoch": 315.72222222222223,
      "grad_norm": 2.7282771597469946e-08,
      "learning_rate": 0.057933674432816606,
      "loss": 0.0,
      "num_input_tokens_seen": 7955936,
      "step": 28415
    },
    {
      "epoch": 315.77777777777777,
      "grad_norm": 2.64344066636113e-08,
      "learning_rate": 0.05788717728641648,
      "loss": 0.0,
      "num_input_tokens_seen": 7957328,
      "step": 28420
    },
    {
      "epoch": 315.8333333333333,
      "grad_norm": 1.5940225139843278e-08,
      "learning_rate": 0.057840694344971126,
      "loss": 0.0,
      "num_input_tokens_seen": 7958736,
      "step": 28425
    },
    {
      "epoch": 315.8888888888889,
      "grad_norm": 2.5458321672999773e-08,
      "learning_rate": 0.0577942256156489,
      "loss": 0.0,
      "num_input_tokens_seen": 7960128,
      "step": 28430
    },
    {
      "epoch": 315.94444444444446,
      "grad_norm": 3.218197619503371e-08,
      "learning_rate": 0.057747771105615804,
      "loss": 0.0,
      "num_input_tokens_seen": 7961536,
      "step": 28435
    },
    {
      "epoch": 316.0,
      "grad_norm": 5.9488542092367425e-08,
      "learning_rate": 0.05770133082203568,
      "loss": 0.0,
      "num_input_tokens_seen": 7962928,
      "step": 28440
    },
    {
      "epoch": 316.05555555555554,
      "grad_norm": 2.4812484511471666e-08,
      "learning_rate": 0.0576549047720703,
      "loss": 0.0,
      "num_input_tokens_seen": 7964336,
      "step": 28445
    },
    {
      "epoch": 316.1111111111111,
      "grad_norm": 4.9859480100167275e-08,
      "learning_rate": 0.05760849296287902,
      "loss": 0.0,
      "num_input_tokens_seen": 7965728,
      "step": 28450
    },
    {
      "epoch": 316.1666666666667,
      "grad_norm": 2.3370452240101258e-08,
      "learning_rate": 0.05756209540161919,
      "loss": 0.0,
      "num_input_tokens_seen": 7967152,
      "step": 28455
    },
    {
      "epoch": 316.22222222222223,
      "grad_norm": 2.1331839406002473e-08,
      "learning_rate": 0.05751571209544595,
      "loss": 0.0,
      "num_input_tokens_seen": 7968512,
      "step": 28460
    },
    {
      "epoch": 316.27777777777777,
      "grad_norm": 4.107700846134321e-08,
      "learning_rate": 0.057469343051512085,
      "loss": 0.0,
      "num_input_tokens_seen": 7969952,
      "step": 28465
    },
    {
      "epoch": 316.3333333333333,
      "grad_norm": 6.280087205823293e-08,
      "learning_rate": 0.057422988276968324,
      "loss": 0.0,
      "num_input_tokens_seen": 7971392,
      "step": 28470
    },
    {
      "epoch": 316.3888888888889,
      "grad_norm": 3.964353822993871e-08,
      "learning_rate": 0.05737664777896323,
      "loss": 0.0,
      "num_input_tokens_seen": 7972800,
      "step": 28475
    },
    {
      "epoch": 316.44444444444446,
      "grad_norm": 5.447662942970055e-08,
      "learning_rate": 0.057330321564642975,
      "loss": 0.0,
      "num_input_tokens_seen": 7974208,
      "step": 28480
    },
    {
      "epoch": 316.5,
      "grad_norm": 6.04562302441991e-08,
      "learning_rate": 0.05728400964115174,
      "loss": 0.0,
      "num_input_tokens_seen": 7975584,
      "step": 28485
    },
    {
      "epoch": 316.55555555555554,
      "grad_norm": 6.303199739932097e-08,
      "learning_rate": 0.057237712015631305,
      "loss": 0.0,
      "num_input_tokens_seen": 7977008,
      "step": 28490
    },
    {
      "epoch": 316.6111111111111,
      "grad_norm": 1.229022785764755e-07,
      "learning_rate": 0.057191428695221425,
      "loss": 0.0,
      "num_input_tokens_seen": 7978352,
      "step": 28495
    },
    {
      "epoch": 316.6666666666667,
      "grad_norm": 1.5814070053465912e-08,
      "learning_rate": 0.05714515968705958,
      "loss": 0.0,
      "num_input_tokens_seen": 7979744,
      "step": 28500
    },
    {
      "epoch": 316.72222222222223,
      "grad_norm": 1.7334954804937297e-08,
      "learning_rate": 0.05709890499828099,
      "loss": 0.0,
      "num_input_tokens_seen": 7981120,
      "step": 28505
    },
    {
      "epoch": 316.77777777777777,
      "grad_norm": 2.07918766648163e-08,
      "learning_rate": 0.05705266463601868,
      "loss": 0.0,
      "num_input_tokens_seen": 7982480,
      "step": 28510
    },
    {
      "epoch": 316.8333333333333,
      "grad_norm": 1.4498543698948652e-08,
      "learning_rate": 0.057006438607403565,
      "loss": 0.0,
      "num_input_tokens_seen": 7983872,
      "step": 28515
    },
    {
      "epoch": 316.8888888888889,
      "grad_norm": 4.2104041142465576e-08,
      "learning_rate": 0.056960226919564205,
      "loss": 0.0,
      "num_input_tokens_seen": 7985328,
      "step": 28520
    },
    {
      "epoch": 316.94444444444446,
      "grad_norm": 8.366019699224125e-08,
      "learning_rate": 0.05691402957962713,
      "loss": 0.0,
      "num_input_tokens_seen": 7986704,
      "step": 28525
    },
    {
      "epoch": 317.0,
      "grad_norm": 3.7328508284417694e-08,
      "learning_rate": 0.05686784659471642,
      "loss": 0.0,
      "num_input_tokens_seen": 7988096,
      "step": 28530
    },
    {
      "epoch": 317.05555555555554,
      "grad_norm": 3.254827163345908e-08,
      "learning_rate": 0.056821677971954136,
      "loss": 0.0,
      "num_input_tokens_seen": 7989472,
      "step": 28535
    },
    {
      "epoch": 317.1111111111111,
      "grad_norm": 2.3861327136387445e-08,
      "learning_rate": 0.05677552371846012,
      "loss": 0.0,
      "num_input_tokens_seen": 7990864,
      "step": 28540
    },
    {
      "epoch": 317.1666666666667,
      "grad_norm": 2.242731511614693e-08,
      "learning_rate": 0.05672938384135182,
      "loss": 0.0,
      "num_input_tokens_seen": 7992224,
      "step": 28545
    },
    {
      "epoch": 317.22222222222223,
      "grad_norm": 2.410243205019924e-08,
      "learning_rate": 0.05668325834774465,
      "loss": 0.0,
      "num_input_tokens_seen": 7993632,
      "step": 28550
    },
    {
      "epoch": 317.27777777777777,
      "grad_norm": 1.4517308244421656e-08,
      "learning_rate": 0.05663714724475177,
      "loss": 0.0,
      "num_input_tokens_seen": 7995008,
      "step": 28555
    },
    {
      "epoch": 317.3333333333333,
      "grad_norm": 3.881370247427185e-08,
      "learning_rate": 0.05659105053948403,
      "loss": 0.0,
      "num_input_tokens_seen": 7996432,
      "step": 28560
    },
    {
      "epoch": 317.3888888888889,
      "grad_norm": 3.5485566485249365e-08,
      "learning_rate": 0.056544968239050176,
      "loss": 0.0,
      "num_input_tokens_seen": 7997840,
      "step": 28565
    },
    {
      "epoch": 317.44444444444446,
      "grad_norm": 5.480101705757079e-08,
      "learning_rate": 0.056498900350556616,
      "loss": 0.0,
      "num_input_tokens_seen": 7999200,
      "step": 28570
    },
    {
      "epoch": 317.5,
      "grad_norm": 1.3474844351435422e-08,
      "learning_rate": 0.05645284688110766,
      "loss": 0.0,
      "num_input_tokens_seen": 8000560,
      "step": 28575
    },
    {
      "epoch": 317.55555555555554,
      "grad_norm": 2.7036048066975127e-08,
      "learning_rate": 0.05640680783780532,
      "loss": 0.0,
      "num_input_tokens_seen": 8002032,
      "step": 28580
    },
    {
      "epoch": 317.6111111111111,
      "grad_norm": 4.3247609937679954e-08,
      "learning_rate": 0.056360783227749324,
      "loss": 0.0,
      "num_input_tokens_seen": 8003424,
      "step": 28585
    },
    {
      "epoch": 317.6666666666667,
      "grad_norm": 1.9505419501797405e-08,
      "learning_rate": 0.05631477305803728,
      "loss": 0.0,
      "num_input_tokens_seen": 8004848,
      "step": 28590
    },
    {
      "epoch": 317.72222222222223,
      "grad_norm": 1.6914027511916174e-08,
      "learning_rate": 0.05626877733576462,
      "loss": 0.0,
      "num_input_tokens_seen": 8006320,
      "step": 28595
    },
    {
      "epoch": 317.77777777777777,
      "grad_norm": 1.354617040760786e-08,
      "learning_rate": 0.05622279606802435,
      "loss": 0.0,
      "num_input_tokens_seen": 8007744,
      "step": 28600
    },
    {
      "epoch": 317.77777777777777,
      "eval_loss": 1.6249862909317017,
      "eval_runtime": 1.1873,
      "eval_samples_per_second": 33.691,
      "eval_steps_per_second": 16.846,
      "num_input_tokens_seen": 8007744,
      "step": 28600
    },
    {
      "epoch": 317.8333333333333,
      "grad_norm": 2.9091417275139975e-08,
      "learning_rate": 0.05617682926190744,
      "loss": 0.0,
      "num_input_tokens_seen": 8009168,
      "step": 28605
    },
    {
      "epoch": 317.8888888888889,
      "grad_norm": 1.6839555527781158e-08,
      "learning_rate": 0.05613087692450248,
      "loss": 0.0,
      "num_input_tokens_seen": 8010544,
      "step": 28610
    },
    {
      "epoch": 317.94444444444446,
      "grad_norm": 3.951064897478318e-08,
      "learning_rate": 0.05608493906289592,
      "loss": 0.0,
      "num_input_tokens_seen": 8011936,
      "step": 28615
    },
    {
      "epoch": 318.0,
      "grad_norm": 3.1802674271830256e-08,
      "learning_rate": 0.05603901568417201,
      "loss": 0.0,
      "num_input_tokens_seen": 8013328,
      "step": 28620
    },
    {
      "epoch": 318.05555555555554,
      "grad_norm": 1.754712997126262e-08,
      "learning_rate": 0.055993106795412625,
      "loss": 0.0,
      "num_input_tokens_seen": 8014736,
      "step": 28625
    },
    {
      "epoch": 318.1111111111111,
      "grad_norm": 2.7861936757744843e-08,
      "learning_rate": 0.05594721240369759,
      "loss": 0.0,
      "num_input_tokens_seen": 8016160,
      "step": 28630
    },
    {
      "epoch": 318.1666666666667,
      "grad_norm": 3.346840315998634e-08,
      "learning_rate": 0.055901332516104296,
      "loss": 0.0,
      "num_input_tokens_seen": 8017536,
      "step": 28635
    },
    {
      "epoch": 318.22222222222223,
      "grad_norm": 1.7141100983053548e-08,
      "learning_rate": 0.05585546713970804,
      "loss": 0.0,
      "num_input_tokens_seen": 8018928,
      "step": 28640
    },
    {
      "epoch": 318.27777777777777,
      "grad_norm": 2.8381691663526e-08,
      "learning_rate": 0.05580961628158189,
      "loss": 0.0,
      "num_input_tokens_seen": 8020368,
      "step": 28645
    },
    {
      "epoch": 318.3333333333333,
      "grad_norm": 2.252244257761049e-08,
      "learning_rate": 0.05576377994879659,
      "loss": 0.0,
      "num_input_tokens_seen": 8021712,
      "step": 28650
    },
    {
      "epoch": 318.3888888888889,
      "grad_norm": 7.319089689872271e-08,
      "learning_rate": 0.05571795814842063,
      "loss": 0.0,
      "num_input_tokens_seen": 8023104,
      "step": 28655
    },
    {
      "epoch": 318.44444444444446,
      "grad_norm": 7.008563329691242e-08,
      "learning_rate": 0.05567215088752037,
      "loss": 0.0,
      "num_input_tokens_seen": 8024512,
      "step": 28660
    },
    {
      "epoch": 318.5,
      "grad_norm": 5.5551026889588684e-08,
      "learning_rate": 0.05562635817315981,
      "loss": 0.0,
      "num_input_tokens_seen": 8025952,
      "step": 28665
    },
    {
      "epoch": 318.55555555555554,
      "grad_norm": 2.648274133321138e-08,
      "learning_rate": 0.05558058001240083,
      "loss": 0.0,
      "num_input_tokens_seen": 8027312,
      "step": 28670
    },
    {
      "epoch": 318.6111111111111,
      "grad_norm": 3.5701280154398773e-08,
      "learning_rate": 0.055534816412302915,
      "loss": 0.0,
      "num_input_tokens_seen": 8028720,
      "step": 28675
    },
    {
      "epoch": 318.6666666666667,
      "grad_norm": 2.19062403772341e-08,
      "learning_rate": 0.055489067379923436,
      "loss": 0.0,
      "num_input_tokens_seen": 8030160,
      "step": 28680
    },
    {
      "epoch": 318.72222222222223,
      "grad_norm": 1.9397528916442752e-08,
      "learning_rate": 0.055443332922317505,
      "loss": 0.0,
      "num_input_tokens_seen": 8031552,
      "step": 28685
    },
    {
      "epoch": 318.77777777777777,
      "grad_norm": 3.168872808601009e-08,
      "learning_rate": 0.055397613046537876,
      "loss": 0.0,
      "num_input_tokens_seen": 8032944,
      "step": 28690
    },
    {
      "epoch": 318.8333333333333,
      "grad_norm": 1.4941100801024731e-07,
      "learning_rate": 0.055351907759635145,
      "loss": 0.0,
      "num_input_tokens_seen": 8034352,
      "step": 28695
    },
    {
      "epoch": 318.8888888888889,
      "grad_norm": 1.4139668103041458e-08,
      "learning_rate": 0.05530621706865772,
      "loss": 0.0,
      "num_input_tokens_seen": 8035808,
      "step": 28700
    },
    {
      "epoch": 318.94444444444446,
      "grad_norm": 1.7579193212213795e-08,
      "learning_rate": 0.055260540980651564,
      "loss": 0.0,
      "num_input_tokens_seen": 8037152,
      "step": 28705
    },
    {
      "epoch": 319.0,
      "grad_norm": 1.9245335991513457e-08,
      "learning_rate": 0.05521487950266062,
      "loss": 0.0,
      "num_input_tokens_seen": 8038512,
      "step": 28710
    },
    {
      "epoch": 319.05555555555554,
      "grad_norm": 4.518395613217763e-08,
      "learning_rate": 0.055169232641726344,
      "loss": 0.0,
      "num_input_tokens_seen": 8039888,
      "step": 28715
    },
    {
      "epoch": 319.1111111111111,
      "grad_norm": 3.722522023963393e-08,
      "learning_rate": 0.055123600404888166,
      "loss": 0.0,
      "num_input_tokens_seen": 8041280,
      "step": 28720
    },
    {
      "epoch": 319.1666666666667,
      "grad_norm": 2.283539402014867e-08,
      "learning_rate": 0.05507798279918309,
      "loss": 0.0,
      "num_input_tokens_seen": 8042656,
      "step": 28725
    },
    {
      "epoch": 319.22222222222223,
      "grad_norm": 2.8090401116287467e-08,
      "learning_rate": 0.0550323798316459,
      "loss": 0.0,
      "num_input_tokens_seen": 8044048,
      "step": 28730
    },
    {
      "epoch": 319.27777777777777,
      "grad_norm": 6.621413461971315e-08,
      "learning_rate": 0.05498679150930916,
      "loss": 0.0,
      "num_input_tokens_seen": 8045440,
      "step": 28735
    },
    {
      "epoch": 319.3333333333333,
      "grad_norm": 5.830500882098022e-08,
      "learning_rate": 0.05494121783920323,
      "loss": 0.0,
      "num_input_tokens_seen": 8046848,
      "step": 28740
    },
    {
      "epoch": 319.3888888888889,
      "grad_norm": 2.1220706969415915e-08,
      "learning_rate": 0.05489565882835605,
      "loss": 0.0,
      "num_input_tokens_seen": 8048256,
      "step": 28745
    },
    {
      "epoch": 319.44444444444446,
      "grad_norm": 6.383681494526172e-08,
      "learning_rate": 0.05485011448379348,
      "loss": 0.0,
      "num_input_tokens_seen": 8049664,
      "step": 28750
    },
    {
      "epoch": 319.5,
      "grad_norm": 1.7459999668290038e-08,
      "learning_rate": 0.05480458481253893,
      "loss": 0.0,
      "num_input_tokens_seen": 8051056,
      "step": 28755
    },
    {
      "epoch": 319.55555555555554,
      "grad_norm": 3.5096110906351896e-08,
      "learning_rate": 0.054759069821613715,
      "loss": 0.0,
      "num_input_tokens_seen": 8052480,
      "step": 28760
    },
    {
      "epoch": 319.6111111111111,
      "grad_norm": 2.660950926269834e-08,
      "learning_rate": 0.05471356951803683,
      "loss": 0.0,
      "num_input_tokens_seen": 8053856,
      "step": 28765
    },
    {
      "epoch": 319.6666666666667,
      "grad_norm": 5.65026709864469e-08,
      "learning_rate": 0.054668083908824945,
      "loss": 0.0,
      "num_input_tokens_seen": 8055232,
      "step": 28770
    },
    {
      "epoch": 319.72222222222223,
      "grad_norm": 4.4285403788535405e-08,
      "learning_rate": 0.054622613000992526,
      "loss": 0.0,
      "num_input_tokens_seen": 8056624,
      "step": 28775
    },
    {
      "epoch": 319.77777777777777,
      "grad_norm": 4.978719303494472e-08,
      "learning_rate": 0.05457715680155182,
      "loss": 0.0,
      "num_input_tokens_seen": 8057984,
      "step": 28780
    },
    {
      "epoch": 319.8333333333333,
      "grad_norm": 1.7111632999444737e-08,
      "learning_rate": 0.05453171531751265,
      "loss": 0.0,
      "num_input_tokens_seen": 8059392,
      "step": 28785
    },
    {
      "epoch": 319.8888888888889,
      "grad_norm": 1.2835960738755148e-08,
      "learning_rate": 0.05448628855588276,
      "loss": 0.0,
      "num_input_tokens_seen": 8060800,
      "step": 28790
    },
    {
      "epoch": 319.94444444444446,
      "grad_norm": 2.0171944115077167e-08,
      "learning_rate": 0.05444087652366746,
      "loss": 0.0,
      "num_input_tokens_seen": 8062224,
      "step": 28795
    },
    {
      "epoch": 320.0,
      "grad_norm": 1.3016260957954273e-08,
      "learning_rate": 0.05439547922786984,
      "loss": 0.0,
      "num_input_tokens_seen": 8063616,
      "step": 28800
    },
    {
      "epoch": 320.0,
      "eval_loss": 1.6387169361114502,
      "eval_runtime": 1.1806,
      "eval_samples_per_second": 33.881,
      "eval_steps_per_second": 16.94,
      "num_input_tokens_seen": 8063616,
      "step": 28800
    },
    {
      "epoch": 320.05555555555554,
      "grad_norm": 2.6745370362846188e-08,
      "learning_rate": 0.0543500966754908,
      "loss": 0.0,
      "num_input_tokens_seen": 8065024,
      "step": 28805
    },
    {
      "epoch": 320.1111111111111,
      "grad_norm": 7.092295106758684e-08,
      "learning_rate": 0.05430472887352882,
      "loss": 0.0,
      "num_input_tokens_seen": 8066416,
      "step": 28810
    },
    {
      "epoch": 320.1666666666667,
      "grad_norm": 5.483752474333414e-08,
      "learning_rate": 0.05425937582898023,
      "loss": 0.0,
      "num_input_tokens_seen": 8067856,
      "step": 28815
    },
    {
      "epoch": 320.22222222222223,
      "grad_norm": 4.543948861623903e-08,
      "learning_rate": 0.054214037548839085,
      "loss": 0.0,
      "num_input_tokens_seen": 8069232,
      "step": 28820
    },
    {
      "epoch": 320.27777777777777,
      "grad_norm": 3.9467895618372495e-08,
      "learning_rate": 0.05416871404009703,
      "loss": 0.0,
      "num_input_tokens_seen": 8070624,
      "step": 28825
    },
    {
      "epoch": 320.3333333333333,
      "grad_norm": 3.4227618073146004e-08,
      "learning_rate": 0.054123405309743605,
      "loss": 0.0,
      "num_input_tokens_seen": 8071984,
      "step": 28830
    },
    {
      "epoch": 320.3888888888889,
      "grad_norm": 5.2090566526885596e-08,
      "learning_rate": 0.0540781113647659,
      "loss": 0.0,
      "num_input_tokens_seen": 8073360,
      "step": 28835
    },
    {
      "epoch": 320.44444444444446,
      "grad_norm": 3.2009534578492094e-08,
      "learning_rate": 0.054032832212148836,
      "loss": 0.0,
      "num_input_tokens_seen": 8074784,
      "step": 28840
    },
    {
      "epoch": 320.5,
      "grad_norm": 5.137183123338218e-08,
      "learning_rate": 0.0539875678588751,
      "loss": 0.0,
      "num_input_tokens_seen": 8076160,
      "step": 28845
    },
    {
      "epoch": 320.55555555555554,
      "grad_norm": 8.505063675556812e-08,
      "learning_rate": 0.05394231831192492,
      "loss": 0.0,
      "num_input_tokens_seen": 8077600,
      "step": 28850
    },
    {
      "epoch": 320.6111111111111,
      "grad_norm": 1.9601671397140308e-08,
      "learning_rate": 0.05389708357827639,
      "loss": 0.0,
      "num_input_tokens_seen": 8079040,
      "step": 28855
    },
    {
      "epoch": 320.6666666666667,
      "grad_norm": 1.2146457173400904e-08,
      "learning_rate": 0.05385186366490533,
      "loss": 0.0,
      "num_input_tokens_seen": 8080400,
      "step": 28860
    },
    {
      "epoch": 320.72222222222223,
      "grad_norm": 9.862747063493771e-09,
      "learning_rate": 0.053806658578785166,
      "loss": 0.0,
      "num_input_tokens_seen": 8081824,
      "step": 28865
    },
    {
      "epoch": 320.77777777777777,
      "grad_norm": 1.0577345221918222e-08,
      "learning_rate": 0.05376146832688705,
      "loss": 0.0,
      "num_input_tokens_seen": 8083216,
      "step": 28870
    },
    {
      "epoch": 320.8333333333333,
      "grad_norm": 1.1188352466717788e-08,
      "learning_rate": 0.053716292916179964,
      "loss": 0.0,
      "num_input_tokens_seen": 8084640,
      "step": 28875
    },
    {
      "epoch": 320.8888888888889,
      "grad_norm": 1.5403045949824445e-08,
      "learning_rate": 0.05367113235363045,
      "loss": 0.0,
      "num_input_tokens_seen": 8086016,
      "step": 28880
    },
    {
      "epoch": 320.94444444444446,
      "grad_norm": 1.699720719727793e-08,
      "learning_rate": 0.05362598664620289,
      "loss": 0.0,
      "num_input_tokens_seen": 8087392,
      "step": 28885
    },
    {
      "epoch": 321.0,
      "grad_norm": 1.3000931176065933e-07,
      "learning_rate": 0.053580855800859285,
      "loss": 0.0,
      "num_input_tokens_seen": 8088784,
      "step": 28890
    },
    {
      "epoch": 321.05555555555554,
      "grad_norm": 3.755144817318978e-08,
      "learning_rate": 0.05353573982455938,
      "loss": 0.0,
      "num_input_tokens_seen": 8090144,
      "step": 28895
    },
    {
      "epoch": 321.1111111111111,
      "grad_norm": 5.56389387895706e-08,
      "learning_rate": 0.053490638724260686,
      "loss": 0.0,
      "num_input_tokens_seen": 8091536,
      "step": 28900
    },
    {
      "epoch": 321.1666666666667,
      "grad_norm": 1.7785062311759248e-08,
      "learning_rate": 0.05344555250691827,
      "loss": 0.0,
      "num_input_tokens_seen": 8092928,
      "step": 28905
    },
    {
      "epoch": 321.22222222222223,
      "grad_norm": 1.675854832683399e-08,
      "learning_rate": 0.053400481179485086,
      "loss": 0.0,
      "num_input_tokens_seen": 8094336,
      "step": 28910
    },
    {
      "epoch": 321.27777777777777,
      "grad_norm": 5.1512209608972626e-08,
      "learning_rate": 0.05335542474891159,
      "loss": 0.0,
      "num_input_tokens_seen": 8095792,
      "step": 28915
    },
    {
      "epoch": 321.3333333333333,
      "grad_norm": 2.50653222622077e-08,
      "learning_rate": 0.053310383222146124,
      "loss": 0.0,
      "num_input_tokens_seen": 8097216,
      "step": 28920
    },
    {
      "epoch": 321.3888888888889,
      "grad_norm": 3.197027353962767e-08,
      "learning_rate": 0.053265356606134684,
      "loss": 0.0,
      "num_input_tokens_seen": 8098608,
      "step": 28925
    },
    {
      "epoch": 321.44444444444446,
      "grad_norm": 2.299314161291477e-08,
      "learning_rate": 0.053220344907820856,
      "loss": 0.0,
      "num_input_tokens_seen": 8100000,
      "step": 28930
    },
    {
      "epoch": 321.5,
      "grad_norm": 1.633203616790979e-08,
      "learning_rate": 0.05317534813414608,
      "loss": 0.0,
      "num_input_tokens_seen": 8101360,
      "step": 28935
    },
    {
      "epoch": 321.55555555555554,
      "grad_norm": 5.99879328433417e-08,
      "learning_rate": 0.05313036629204942,
      "loss": 0.0,
      "num_input_tokens_seen": 8102736,
      "step": 28940
    },
    {
      "epoch": 321.6111111111111,
      "grad_norm": 3.097011713748543e-08,
      "learning_rate": 0.05308539938846756,
      "loss": 0.0,
      "num_input_tokens_seen": 8104176,
      "step": 28945
    },
    {
      "epoch": 321.6666666666667,
      "grad_norm": 3.062526943153898e-08,
      "learning_rate": 0.05304044743033507,
      "loss": 0.0,
      "num_input_tokens_seen": 8105616,
      "step": 28950
    },
    {
      "epoch": 321.72222222222223,
      "grad_norm": 6.081819492465002e-08,
      "learning_rate": 0.05299551042458401,
      "loss": 0.0,
      "num_input_tokens_seen": 8106992,
      "step": 28955
    },
    {
      "epoch": 321.77777777777777,
      "grad_norm": 3.7387302143088164e-08,
      "learning_rate": 0.052950588378144266,
      "loss": 0.0,
      "num_input_tokens_seen": 8108416,
      "step": 28960
    },
    {
      "epoch": 321.8333333333333,
      "grad_norm": 2.4685514077305015e-08,
      "learning_rate": 0.052905681297943465,
      "loss": 0.0,
      "num_input_tokens_seen": 8109856,
      "step": 28965
    },
    {
      "epoch": 321.8888888888889,
      "grad_norm": 3.910069423795903e-08,
      "learning_rate": 0.0528607891909067,
      "loss": 0.0,
      "num_input_tokens_seen": 8111248,
      "step": 28970
    },
    {
      "epoch": 321.94444444444446,
      "grad_norm": 5.7416595922177294e-08,
      "learning_rate": 0.05281591206395697,
      "loss": 0.0,
      "num_input_tokens_seen": 8112640,
      "step": 28975
    },
    {
      "epoch": 322.0,
      "grad_norm": 1.335427324278271e-08,
      "learning_rate": 0.05277104992401496,
      "loss": 0.0,
      "num_input_tokens_seen": 8114000,
      "step": 28980
    },
    {
      "epoch": 322.05555555555554,
      "grad_norm": 1.839700125572108e-08,
      "learning_rate": 0.05272620277799884,
      "loss": 0.0,
      "num_input_tokens_seen": 8115424,
      "step": 28985
    },
    {
      "epoch": 322.1111111111111,
      "grad_norm": 4.097406502978629e-08,
      "learning_rate": 0.05268137063282473,
      "loss": 0.0,
      "num_input_tokens_seen": 8116800,
      "step": 28990
    },
    {
      "epoch": 322.1666666666667,
      "grad_norm": 2.9308692361951216e-08,
      "learning_rate": 0.0526365534954062,
      "loss": 0.0,
      "num_input_tokens_seen": 8118192,
      "step": 28995
    },
    {
      "epoch": 322.22222222222223,
      "grad_norm": 1.7453380962706433e-08,
      "learning_rate": 0.052591751372654656,
      "loss": 0.0,
      "num_input_tokens_seen": 8119520,
      "step": 29000
    },
    {
      "epoch": 322.22222222222223,
      "eval_loss": 1.6151145696640015,
      "eval_runtime": 1.1903,
      "eval_samples_per_second": 33.605,
      "eval_steps_per_second": 16.802,
      "num_input_tokens_seen": 8119520,
      "step": 29000
    },
    {
      "epoch": 322.27777777777777,
      "grad_norm": 2.3440982488409645e-08,
      "learning_rate": 0.05254696427147921,
      "loss": 0.0,
      "num_input_tokens_seen": 8120944,
      "step": 29005
    },
    {
      "epoch": 322.3333333333333,
      "grad_norm": 3.803391379619825e-08,
      "learning_rate": 0.052502192198786546,
      "loss": 0.0,
      "num_input_tokens_seen": 8122384,
      "step": 29010
    },
    {
      "epoch": 322.3888888888889,
      "grad_norm": 2.812824284603721e-08,
      "learning_rate": 0.05245743516148103,
      "loss": 0.0,
      "num_input_tokens_seen": 8123808,
      "step": 29015
    },
    {
      "epoch": 322.44444444444446,
      "grad_norm": 2.61639829801652e-08,
      "learning_rate": 0.05241269316646486,
      "loss": 0.0,
      "num_input_tokens_seen": 8125200,
      "step": 29020
    },
    {
      "epoch": 322.5,
      "grad_norm": 1.946882655090576e-08,
      "learning_rate": 0.052367966220637725,
      "loss": 0.0,
      "num_input_tokens_seen": 8126560,
      "step": 29025
    },
    {
      "epoch": 322.55555555555554,
      "grad_norm": 9.604195838619489e-08,
      "learning_rate": 0.05232325433089716,
      "loss": 0.0,
      "num_input_tokens_seen": 8127968,
      "step": 29030
    },
    {
      "epoch": 322.6111111111111,
      "grad_norm": 4.949975007662033e-08,
      "learning_rate": 0.052278557504138214,
      "loss": 0.0,
      "num_input_tokens_seen": 8129328,
      "step": 29035
    },
    {
      "epoch": 322.6666666666667,
      "grad_norm": 2.7218053588740077e-08,
      "learning_rate": 0.05223387574725372,
      "loss": 0.0,
      "num_input_tokens_seen": 8130688,
      "step": 29040
    },
    {
      "epoch": 322.72222222222223,
      "grad_norm": 1.500889723615728e-08,
      "learning_rate": 0.05218920906713428,
      "loss": 0.0,
      "num_input_tokens_seen": 8132096,
      "step": 29045
    },
    {
      "epoch": 322.77777777777777,
      "grad_norm": 1.321665337172817e-07,
      "learning_rate": 0.05214455747066789,
      "loss": 0.0,
      "num_input_tokens_seen": 8133536,
      "step": 29050
    },
    {
      "epoch": 322.8333333333333,
      "grad_norm": 3.826833605558022e-08,
      "learning_rate": 0.05209992096474048,
      "loss": 0.0,
      "num_input_tokens_seen": 8134960,
      "step": 29055
    },
    {
      "epoch": 322.8888888888889,
      "grad_norm": 7.846893623764117e-08,
      "learning_rate": 0.05205529955623559,
      "loss": 0.0,
      "num_input_tokens_seen": 8136384,
      "step": 29060
    },
    {
      "epoch": 322.94444444444446,
      "grad_norm": 6.998113377676418e-08,
      "learning_rate": 0.052010693252034314,
      "loss": 0.0,
      "num_input_tokens_seen": 8137776,
      "step": 29065
    },
    {
      "epoch": 323.0,
      "grad_norm": 8.381869776030726e-08,
      "learning_rate": 0.0519661020590156,
      "loss": 0.0,
      "num_input_tokens_seen": 8139152,
      "step": 29070
    },
    {
      "epoch": 323.05555555555554,
      "grad_norm": 2.0367634689932856e-08,
      "learning_rate": 0.05192152598405586,
      "loss": 0.0,
      "num_input_tokens_seen": 8140544,
      "step": 29075
    },
    {
      "epoch": 323.1111111111111,
      "grad_norm": 2.9447841498608796e-08,
      "learning_rate": 0.05187696503402941,
      "loss": 0.0,
      "num_input_tokens_seen": 8141952,
      "step": 29080
    },
    {
      "epoch": 323.1666666666667,
      "grad_norm": 3.0350228996667283e-08,
      "learning_rate": 0.05183241921580798,
      "loss": 0.0,
      "num_input_tokens_seen": 8143376,
      "step": 29085
    },
    {
      "epoch": 323.22222222222223,
      "grad_norm": 3.118860902873166e-08,
      "learning_rate": 0.051787888536261206,
      "loss": 0.0,
      "num_input_tokens_seen": 8144736,
      "step": 29090
    },
    {
      "epoch": 323.27777777777777,
      "grad_norm": 1.7293791643169243e-07,
      "learning_rate": 0.051743373002256184,
      "loss": 0.0,
      "num_input_tokens_seen": 8146144,
      "step": 29095
    },
    {
      "epoch": 323.3333333333333,
      "grad_norm": 4.292940047889715e-08,
      "learning_rate": 0.05169887262065787,
      "loss": 0.0,
      "num_input_tokens_seen": 8147536,
      "step": 29100
    },
    {
      "epoch": 323.3888888888889,
      "grad_norm": 1.8119733269372773e-08,
      "learning_rate": 0.051654387398328665,
      "loss": 0.0,
      "num_input_tokens_seen": 8148928,
      "step": 29105
    },
    {
      "epoch": 323.44444444444446,
      "grad_norm": 1.8896498588105715e-08,
      "learning_rate": 0.05160991734212888,
      "loss": 0.0,
      "num_input_tokens_seen": 8150304,
      "step": 29110
    },
    {
      "epoch": 323.5,
      "grad_norm": 1.72244742913108e-08,
      "learning_rate": 0.051565462458916224,
      "loss": 0.0,
      "num_input_tokens_seen": 8151712,
      "step": 29115
    },
    {
      "epoch": 323.55555555555554,
      "grad_norm": 4.8044764611177015e-08,
      "learning_rate": 0.05152102275554627,
      "loss": 0.0,
      "num_input_tokens_seen": 8153104,
      "step": 29120
    },
    {
      "epoch": 323.6111111111111,
      "grad_norm": 6.245783623626266e-08,
      "learning_rate": 0.05147659823887222,
      "loss": 0.0,
      "num_input_tokens_seen": 8154496,
      "step": 29125
    },
    {
      "epoch": 323.6666666666667,
      "grad_norm": 1.3204352455886692e-07,
      "learning_rate": 0.05143218891574479,
      "loss": 0.0,
      "num_input_tokens_seen": 8155936,
      "step": 29130
    },
    {
      "epoch": 323.72222222222223,
      "grad_norm": 4.762162220117716e-08,
      "learning_rate": 0.0513877947930125,
      "loss": 0.0,
      "num_input_tokens_seen": 8157312,
      "step": 29135
    },
    {
      "epoch": 323.77777777777777,
      "grad_norm": 1.5889497717580525e-08,
      "learning_rate": 0.051343415877521566,
      "loss": 0.0,
      "num_input_tokens_seen": 8158720,
      "step": 29140
    },
    {
      "epoch": 323.8333333333333,
      "grad_norm": 2.5179700102739844e-08,
      "learning_rate": 0.051299052176115634,
      "loss": 0.0,
      "num_input_tokens_seen": 8160144,
      "step": 29145
    },
    {
      "epoch": 323.8888888888889,
      "grad_norm": 2.7499874377667766e-08,
      "learning_rate": 0.051254703695636256,
      "loss": 0.0,
      "num_input_tokens_seen": 8161536,
      "step": 29150
    },
    {
      "epoch": 323.94444444444446,
      "grad_norm": 4.585539059576149e-08,
      "learning_rate": 0.05121037044292249,
      "loss": 0.0,
      "num_input_tokens_seen": 8162976,
      "step": 29155
    },
    {
      "epoch": 324.0,
      "grad_norm": 4.411736398424182e-08,
      "learning_rate": 0.05116605242481101,
      "loss": 0.0,
      "num_input_tokens_seen": 8164384,
      "step": 29160
    },
    {
      "epoch": 324.05555555555554,
      "grad_norm": 4.154448163262714e-08,
      "learning_rate": 0.05112174964813634,
      "loss": 0.0,
      "num_input_tokens_seen": 8165760,
      "step": 29165
    },
    {
      "epoch": 324.1111111111111,
      "grad_norm": 2.166668444658626e-08,
      "learning_rate": 0.05107746211973038,
      "loss": 0.0,
      "num_input_tokens_seen": 8167168,
      "step": 29170
    },
    {
      "epoch": 324.1666666666667,
      "grad_norm": 3.66274157670432e-08,
      "learning_rate": 0.05103318984642291,
      "loss": 0.0,
      "num_input_tokens_seen": 8168544,
      "step": 29175
    },
    {
      "epoch": 324.22222222222223,
      "grad_norm": 4.467856129508618e-08,
      "learning_rate": 0.05098893283504131,
      "loss": 0.0,
      "num_input_tokens_seen": 8169952,
      "step": 29180
    },
    {
      "epoch": 324.27777777777777,
      "grad_norm": 3.795584291310661e-08,
      "learning_rate": 0.050944691092410475,
      "loss": 0.0,
      "num_input_tokens_seen": 8171344,
      "step": 29185
    },
    {
      "epoch": 324.3333333333333,
      "grad_norm": 1.9677770524140215e-08,
      "learning_rate": 0.05090046462535313,
      "loss": 0.0,
      "num_input_tokens_seen": 8172832,
      "step": 29190
    },
    {
      "epoch": 324.3888888888889,
      "grad_norm": 1.6736336760914128e-08,
      "learning_rate": 0.050856253440689454,
      "loss": 0.0,
      "num_input_tokens_seen": 8174208,
      "step": 29195
    },
    {
      "epoch": 324.44444444444446,
      "grad_norm": 1.2266292515050736e-07,
      "learning_rate": 0.050812057545237405,
      "loss": 0.0,
      "num_input_tokens_seen": 8175584,
      "step": 29200
    },
    {
      "epoch": 324.44444444444446,
      "eval_loss": 1.621985673904419,
      "eval_runtime": 1.1824,
      "eval_samples_per_second": 33.83,
      "eval_steps_per_second": 16.915,
      "num_input_tokens_seen": 8175584,
      "step": 29200
    },
    {
      "epoch": 324.5,
      "grad_norm": 1.271996730167757e-08,
      "learning_rate": 0.0507678769458126,
      "loss": 0.0,
      "num_input_tokens_seen": 8176976,
      "step": 29205
    },
    {
      "epoch": 324.55555555555554,
      "grad_norm": 6.742534708337189e-08,
      "learning_rate": 0.050723711649228155,
      "loss": 0.0,
      "num_input_tokens_seen": 8178368,
      "step": 29210
    },
    {
      "epoch": 324.6111111111111,
      "grad_norm": 3.733261522143039e-08,
      "learning_rate": 0.05067956166229496,
      "loss": 0.0,
      "num_input_tokens_seen": 8179760,
      "step": 29215
    },
    {
      "epoch": 324.6666666666667,
      "grad_norm": 7.497476417483995e-08,
      "learning_rate": 0.05063542699182155,
      "loss": 0.0,
      "num_input_tokens_seen": 8181152,
      "step": 29220
    },
    {
      "epoch": 324.72222222222223,
      "grad_norm": 3.8664643398078624e-07,
      "learning_rate": 0.050591307644613996,
      "loss": 0.0,
      "num_input_tokens_seen": 8182576,
      "step": 29225
    },
    {
      "epoch": 324.77777777777777,
      "grad_norm": 2.585846914371359e-08,
      "learning_rate": 0.05054720362747599,
      "loss": 0.0,
      "num_input_tokens_seen": 8183968,
      "step": 29230
    },
    {
      "epoch": 324.8333333333333,
      "grad_norm": 2.281815092430861e-08,
      "learning_rate": 0.050503114947209035,
      "loss": 0.0,
      "num_input_tokens_seen": 8185344,
      "step": 29235
    },
    {
      "epoch": 324.8888888888889,
      "grad_norm": 4.2258385235527385e-08,
      "learning_rate": 0.05045904161061207,
      "loss": 0.0,
      "num_input_tokens_seen": 8186752,
      "step": 29240
    },
    {
      "epoch": 324.94444444444446,
      "grad_norm": 3.129899894815935e-08,
      "learning_rate": 0.05041498362448185,
      "loss": 0.0,
      "num_input_tokens_seen": 8188208,
      "step": 29245
    },
    {
      "epoch": 325.0,
      "grad_norm": 1.161746894240423e-07,
      "learning_rate": 0.05037094099561256,
      "loss": 0.0,
      "num_input_tokens_seen": 8189616,
      "step": 29250
    },
    {
      "epoch": 325.05555555555554,
      "grad_norm": 3.497918754646889e-08,
      "learning_rate": 0.05032691373079624,
      "loss": 0.0,
      "num_input_tokens_seen": 8191056,
      "step": 29255
    },
    {
      "epoch": 325.1111111111111,
      "grad_norm": 4.378687634698508e-08,
      "learning_rate": 0.05028290183682234,
      "loss": 0.0,
      "num_input_tokens_seen": 8192416,
      "step": 29260
    },
    {
      "epoch": 325.1666666666667,
      "grad_norm": 1.812448147120449e-08,
      "learning_rate": 0.050238905320478096,
      "loss": 0.0,
      "num_input_tokens_seen": 8193824,
      "step": 29265
    },
    {
      "epoch": 325.22222222222223,
      "grad_norm": 3.810315973851175e-08,
      "learning_rate": 0.05019492418854838,
      "loss": 0.0,
      "num_input_tokens_seen": 8195216,
      "step": 29270
    },
    {
      "epoch": 325.27777777777777,
      "grad_norm": 2.2273408006867612e-08,
      "learning_rate": 0.05015095844781554,
      "loss": 0.0,
      "num_input_tokens_seen": 8196624,
      "step": 29275
    },
    {
      "epoch": 325.3333333333333,
      "grad_norm": 1.0550925111374454e-07,
      "learning_rate": 0.05010700810505968,
      "loss": 0.0,
      "num_input_tokens_seen": 8198016,
      "step": 29280
    },
    {
      "epoch": 325.3888888888889,
      "grad_norm": 4.311739942863824e-08,
      "learning_rate": 0.05006307316705856,
      "loss": 0.0,
      "num_input_tokens_seen": 8199456,
      "step": 29285
    },
    {
      "epoch": 325.44444444444446,
      "grad_norm": 3.2646561010096775e-08,
      "learning_rate": 0.0500191536405874,
      "loss": 0.0,
      "num_input_tokens_seen": 8200864,
      "step": 29290
    },
    {
      "epoch": 325.5,
      "grad_norm": 3.355562938622825e-08,
      "learning_rate": 0.04997524953241922,
      "loss": 0.0,
      "num_input_tokens_seen": 8202304,
      "step": 29295
    },
    {
      "epoch": 325.55555555555554,
      "grad_norm": 3.202049825290487e-08,
      "learning_rate": 0.049931360849324556,
      "loss": 0.0,
      "num_input_tokens_seen": 8203712,
      "step": 29300
    },
    {
      "epoch": 325.6111111111111,
      "grad_norm": 1.5249804619088536e-07,
      "learning_rate": 0.04988748759807155,
      "loss": 0.0,
      "num_input_tokens_seen": 8205104,
      "step": 29305
    },
    {
      "epoch": 325.6666666666667,
      "grad_norm": 3.315092556022137e-08,
      "learning_rate": 0.0498436297854261,
      "loss": 0.0,
      "num_input_tokens_seen": 8206496,
      "step": 29310
    },
    {
      "epoch": 325.72222222222223,
      "grad_norm": 3.677436311022575e-08,
      "learning_rate": 0.04979978741815152,
      "loss": 0.0,
      "num_input_tokens_seen": 8207888,
      "step": 29315
    },
    {
      "epoch": 325.77777777777777,
      "grad_norm": 3.193241937538005e-08,
      "learning_rate": 0.04975596050300891,
      "loss": 0.0,
      "num_input_tokens_seen": 8209296,
      "step": 29320
    },
    {
      "epoch": 325.8333333333333,
      "grad_norm": 2.7756309251003586e-08,
      "learning_rate": 0.049712149046757005,
      "loss": 0.0,
      "num_input_tokens_seen": 8210704,
      "step": 29325
    },
    {
      "epoch": 325.8888888888889,
      "grad_norm": 4.4451297753766994e-08,
      "learning_rate": 0.04966835305615194,
      "loss": 0.0,
      "num_input_tokens_seen": 8212112,
      "step": 29330
    },
    {
      "epoch": 325.94444444444446,
      "grad_norm": 2.076355976043942e-08,
      "learning_rate": 0.049624572537947755,
      "loss": 0.0,
      "num_input_tokens_seen": 8213504,
      "step": 29335
    },
    {
      "epoch": 326.0,
      "grad_norm": 7.185555261912668e-08,
      "learning_rate": 0.04958080749889582,
      "loss": 0.0,
      "num_input_tokens_seen": 8214896,
      "step": 29340
    },
    {
      "epoch": 326.05555555555554,
      "grad_norm": 8.135020834743045e-08,
      "learning_rate": 0.049537057945745304,
      "loss": 0.0,
      "num_input_tokens_seen": 8216272,
      "step": 29345
    },
    {
      "epoch": 326.1111111111111,
      "grad_norm": 3.481568100482946e-08,
      "learning_rate": 0.049493323885243,
      "loss": 0.0,
      "num_input_tokens_seen": 8217648,
      "step": 29350
    },
    {
      "epoch": 326.1666666666667,
      "grad_norm": 3.4753430355749515e-08,
      "learning_rate": 0.04944960532413318,
      "loss": 0.0,
      "num_input_tokens_seen": 8219088,
      "step": 29355
    },
    {
      "epoch": 326.22222222222223,
      "grad_norm": 4.470190972938326e-08,
      "learning_rate": 0.049405902269157774,
      "loss": 0.0,
      "num_input_tokens_seen": 8220480,
      "step": 29360
    },
    {
      "epoch": 326.27777777777777,
      "grad_norm": 4.212135351622237e-08,
      "learning_rate": 0.04936221472705646,
      "loss": 0.0,
      "num_input_tokens_seen": 8221888,
      "step": 29365
    },
    {
      "epoch": 326.3333333333333,
      "grad_norm": 1.6519294376848848e-08,
      "learning_rate": 0.04931854270456632,
      "loss": 0.0,
      "num_input_tokens_seen": 8223328,
      "step": 29370
    },
    {
      "epoch": 326.3888888888889,
      "grad_norm": 6.141803066128659e-09,
      "learning_rate": 0.049274886208422075,
      "loss": 0.0,
      "num_input_tokens_seen": 8224688,
      "step": 29375
    },
    {
      "epoch": 326.44444444444446,
      "grad_norm": 8.256287209462698e-09,
      "learning_rate": 0.049231245245356235,
      "loss": 0.0,
      "num_input_tokens_seen": 8226128,
      "step": 29380
    },
    {
      "epoch": 326.5,
      "grad_norm": 1.0749096723827734e-08,
      "learning_rate": 0.049187619822098655,
      "loss": 0.0,
      "num_input_tokens_seen": 8227568,
      "step": 29385
    },
    {
      "epoch": 326.55555555555554,
      "grad_norm": 7.625258646726252e-09,
      "learning_rate": 0.04914400994537705,
      "loss": 0.0,
      "num_input_tokens_seen": 8228944,
      "step": 29390
    },
    {
      "epoch": 326.6111111111111,
      "grad_norm": 5.6094817679763764e-09,
      "learning_rate": 0.049100415621916485,
      "loss": 0.0,
      "num_input_tokens_seen": 8230352,
      "step": 29395
    },
    {
      "epoch": 326.6666666666667,
      "grad_norm": 7.889795483606576e-09,
      "learning_rate": 0.04905683685843981,
      "loss": 0.0,
      "num_input_tokens_seen": 8231760,
      "step": 29400
    },
    {
      "epoch": 326.6666666666667,
      "eval_loss": 1.6851398944854736,
      "eval_runtime": 1.1838,
      "eval_samples_per_second": 33.79,
      "eval_steps_per_second": 16.895,
      "num_input_tokens_seen": 8231760,
      "step": 29400
    },
    {
      "epoch": 326.72222222222223,
      "grad_norm": 1.216717304686199e-08,
      "learning_rate": 0.049013273661667495,
      "loss": 0.0,
      "num_input_tokens_seen": 8233120,
      "step": 29405
    },
    {
      "epoch": 326.77777777777777,
      "grad_norm": 5.759322352361096e-09,
      "learning_rate": 0.048969726038317396,
      "loss": 0.0,
      "num_input_tokens_seen": 8234480,
      "step": 29410
    },
    {
      "epoch": 326.8333333333333,
      "grad_norm": 1.0617539203394699e-07,
      "learning_rate": 0.048926193995105206,
      "loss": 0.0,
      "num_input_tokens_seen": 8235872,
      "step": 29415
    },
    {
      "epoch": 326.8888888888889,
      "grad_norm": 2.3617516831109242e-08,
      "learning_rate": 0.048882677538744035,
      "loss": 0.0,
      "num_input_tokens_seen": 8237280,
      "step": 29420
    },
    {
      "epoch": 326.94444444444446,
      "grad_norm": 2.5709239181992416e-08,
      "learning_rate": 0.048839176675944715,
      "loss": 0.0,
      "num_input_tokens_seen": 8238672,
      "step": 29425
    },
    {
      "epoch": 327.0,
      "grad_norm": 1.7441736943624164e-08,
      "learning_rate": 0.04879569141341566,
      "loss": 0.0,
      "num_input_tokens_seen": 8240048,
      "step": 29430
    },
    {
      "epoch": 327.05555555555554,
      "grad_norm": 1.8116699251891077e-08,
      "learning_rate": 0.04875222175786274,
      "loss": 0.0,
      "num_input_tokens_seen": 8241424,
      "step": 29435
    },
    {
      "epoch": 327.1111111111111,
      "grad_norm": 1.406698046935162e-08,
      "learning_rate": 0.04870876771598966,
      "loss": 0.0,
      "num_input_tokens_seen": 8242864,
      "step": 29440
    },
    {
      "epoch": 327.1666666666667,
      "grad_norm": 1.0747640999397845e-08,
      "learning_rate": 0.04866532929449744,
      "loss": 0.0,
      "num_input_tokens_seen": 8244256,
      "step": 29445
    },
    {
      "epoch": 327.22222222222223,
      "grad_norm": 1.10979216927376e-08,
      "learning_rate": 0.048621906500084945,
      "loss": 0.0,
      "num_input_tokens_seen": 8245696,
      "step": 29450
    },
    {
      "epoch": 327.27777777777777,
      "grad_norm": 2.4695115286021974e-08,
      "learning_rate": 0.04857849933944845,
      "loss": 0.0,
      "num_input_tokens_seen": 8247072,
      "step": 29455
    },
    {
      "epoch": 327.3333333333333,
      "grad_norm": 4.172580503336576e-08,
      "learning_rate": 0.048535107819281866,
      "loss": 0.0,
      "num_input_tokens_seen": 8248480,
      "step": 29460
    },
    {
      "epoch": 327.3888888888889,
      "grad_norm": 2.9265843082271203e-08,
      "learning_rate": 0.04849173194627675,
      "loss": 0.0,
      "num_input_tokens_seen": 8249872,
      "step": 29465
    },
    {
      "epoch": 327.44444444444446,
      "grad_norm": 2.4015289312728783e-08,
      "learning_rate": 0.04844837172712223,
      "loss": 0.0,
      "num_input_tokens_seen": 8251248,
      "step": 29470
    },
    {
      "epoch": 327.5,
      "grad_norm": 3.93601879977723e-08,
      "learning_rate": 0.04840502716850494,
      "loss": 0.0,
      "num_input_tokens_seen": 8252672,
      "step": 29475
    },
    {
      "epoch": 327.55555555555554,
      "grad_norm": 3.977134355181988e-08,
      "learning_rate": 0.04836169827710916,
      "loss": 0.0,
      "num_input_tokens_seen": 8254080,
      "step": 29480
    },
    {
      "epoch": 327.6111111111111,
      "grad_norm": 3.893893563144957e-08,
      "learning_rate": 0.04831838505961684,
      "loss": 0.0,
      "num_input_tokens_seen": 8255504,
      "step": 29485
    },
    {
      "epoch": 327.6666666666667,
      "grad_norm": 2.7021423321116345e-08,
      "learning_rate": 0.048275087522707295,
      "loss": 0.0,
      "num_input_tokens_seen": 8256912,
      "step": 29490
    },
    {
      "epoch": 327.72222222222223,
      "grad_norm": 3.491048161663457e-08,
      "learning_rate": 0.04823180567305766,
      "loss": 0.0,
      "num_input_tokens_seen": 8258288,
      "step": 29495
    },
    {
      "epoch": 327.77777777777777,
      "grad_norm": 2.3103368107513234e-08,
      "learning_rate": 0.04818853951734244,
      "loss": 0.0,
      "num_input_tokens_seen": 8259680,
      "step": 29500
    },
    {
      "epoch": 327.8333333333333,
      "grad_norm": 3.6999772135004605e-08,
      "learning_rate": 0.04814528906223387,
      "loss": 0.0,
      "num_input_tokens_seen": 8261072,
      "step": 29505
    },
    {
      "epoch": 327.8888888888889,
      "grad_norm": 1.0533023697689714e-07,
      "learning_rate": 0.04810205431440177,
      "loss": 0.0,
      "num_input_tokens_seen": 8262448,
      "step": 29510
    },
    {
      "epoch": 327.94444444444446,
      "grad_norm": 3.11989758472464e-08,
      "learning_rate": 0.04805883528051341,
      "loss": 0.0,
      "num_input_tokens_seen": 8263888,
      "step": 29515
    },
    {
      "epoch": 328.0,
      "grad_norm": 3.29801679299635e-08,
      "learning_rate": 0.048015631967233685,
      "loss": 0.0,
      "num_input_tokens_seen": 8265328,
      "step": 29520
    },
    {
      "epoch": 328.05555555555554,
      "grad_norm": 2.6506175032636747e-08,
      "learning_rate": 0.04797244438122517,
      "loss": 0.0,
      "num_input_tokens_seen": 8266720,
      "step": 29525
    },
    {
      "epoch": 328.1111111111111,
      "grad_norm": 1.1375346886666193e-08,
      "learning_rate": 0.04792927252914784,
      "loss": 0.0,
      "num_input_tokens_seen": 8268128,
      "step": 29530
    },
    {
      "epoch": 328.1666666666667,
      "grad_norm": 3.4980725871491813e-08,
      "learning_rate": 0.04788611641765944,
      "loss": 0.0,
      "num_input_tokens_seen": 8269552,
      "step": 29535
    },
    {
      "epoch": 328.22222222222223,
      "grad_norm": 2.5792440183636245e-08,
      "learning_rate": 0.04784297605341508,
      "loss": 0.0,
      "num_input_tokens_seen": 8270960,
      "step": 29540
    },
    {
      "epoch": 328.27777777777777,
      "grad_norm": 2.2236177343870622e-08,
      "learning_rate": 0.04779985144306761,
      "loss": 0.0,
      "num_input_tokens_seen": 8272384,
      "step": 29545
    },
    {
      "epoch": 328.3333333333333,
      "grad_norm": 1.4998516206787826e-08,
      "learning_rate": 0.047756742593267405,
      "loss": 0.0,
      "num_input_tokens_seen": 8273792,
      "step": 29550
    },
    {
      "epoch": 328.3888888888889,
      "grad_norm": 5.9386827899743366e-08,
      "learning_rate": 0.047713649510662315,
      "loss": 0.0,
      "num_input_tokens_seen": 8275184,
      "step": 29555
    },
    {
      "epoch": 328.44444444444446,
      "grad_norm": 2.1358109947300363e-08,
      "learning_rate": 0.04767057220189789,
      "loss": 0.0,
      "num_input_tokens_seen": 8276576,
      "step": 29560
    },
    {
      "epoch": 328.5,
      "grad_norm": 4.119362628784984e-08,
      "learning_rate": 0.04762751067361722,
      "loss": 0.0,
      "num_input_tokens_seen": 8278000,
      "step": 29565
    },
    {
      "epoch": 328.55555555555554,
      "grad_norm": 3.89551360058249e-08,
      "learning_rate": 0.04758446493246086,
      "loss": 0.0,
      "num_input_tokens_seen": 8279392,
      "step": 29570
    },
    {
      "epoch": 328.6111111111111,
      "grad_norm": 4.028985145509978e-08,
      "learning_rate": 0.047541434985067084,
      "loss": 0.0,
      "num_input_tokens_seen": 8280768,
      "step": 29575
    },
    {
      "epoch": 328.6666666666667,
      "grad_norm": 1.622562990633014e-07,
      "learning_rate": 0.047498420838071556,
      "loss": 0.0,
      "num_input_tokens_seen": 8282176,
      "step": 29580
    },
    {
      "epoch": 328.72222222222223,
      "grad_norm": 2.8360082282574695e-08,
      "learning_rate": 0.04745542249810772,
      "loss": 0.0,
      "num_input_tokens_seen": 8283584,
      "step": 29585
    },
    {
      "epoch": 328.77777777777777,
      "grad_norm": 3.7450913481507087e-08,
      "learning_rate": 0.047412439971806324,
      "loss": 0.0,
      "num_input_tokens_seen": 8284944,
      "step": 29590
    },
    {
      "epoch": 328.8333333333333,
      "grad_norm": 6.974216404387334e-08,
      "learning_rate": 0.04736947326579592,
      "loss": 0.0,
      "num_input_tokens_seen": 8286352,
      "step": 29595
    },
    {
      "epoch": 328.8888888888889,
      "grad_norm": 2.6420995169473827e-08,
      "learning_rate": 0.04732652238670245,
      "loss": 0.0,
      "num_input_tokens_seen": 8287696,
      "step": 29600
    },
    {
      "epoch": 328.8888888888889,
      "eval_loss": 1.6862049102783203,
      "eval_runtime": 1.1965,
      "eval_samples_per_second": 33.43,
      "eval_steps_per_second": 16.715,
      "num_input_tokens_seen": 8287696,
      "step": 29600
    },
    {
      "epoch": 328.94444444444446,
      "grad_norm": 3.008856808150995e-08,
      "learning_rate": 0.04728358734114952,
      "loss": 0.0,
      "num_input_tokens_seen": 8289120,
      "step": 29605
    },
    {
      "epoch": 329.0,
      "grad_norm": 2.5492376209967915e-08,
      "learning_rate": 0.04724066813575821,
      "loss": 0.0,
      "num_input_tokens_seen": 8290560,
      "step": 29610
    },
    {
      "epoch": 329.05555555555554,
      "grad_norm": 3.0745276546895184e-08,
      "learning_rate": 0.04719776477714729,
      "loss": 0.0,
      "num_input_tokens_seen": 8291968,
      "step": 29615
    },
    {
      "epoch": 329.1111111111111,
      "grad_norm": 9.364315189941408e-08,
      "learning_rate": 0.047154877271932856,
      "loss": 0.0,
      "num_input_tokens_seen": 8293376,
      "step": 29620
    },
    {
      "epoch": 329.1666666666667,
      "grad_norm": 4.718028279171449e-08,
      "learning_rate": 0.0471120056267288,
      "loss": 0.0,
      "num_input_tokens_seen": 8294720,
      "step": 29625
    },
    {
      "epoch": 329.22222222222223,
      "grad_norm": 4.0878084917039814e-08,
      "learning_rate": 0.047069149848146495,
      "loss": 0.0,
      "num_input_tokens_seen": 8296160,
      "step": 29630
    },
    {
      "epoch": 329.27777777777777,
      "grad_norm": 1.933747384441631e-08,
      "learning_rate": 0.04702630994279473,
      "loss": 0.0,
      "num_input_tokens_seen": 8297520,
      "step": 29635
    },
    {
      "epoch": 329.3333333333333,
      "grad_norm": 1.9156037467382703e-07,
      "learning_rate": 0.046983485917280035,
      "loss": 0.0,
      "num_input_tokens_seen": 8298896,
      "step": 29640
    },
    {
      "epoch": 329.3888888888889,
      "grad_norm": 9.444414139636592e-09,
      "learning_rate": 0.04694067777820644,
      "loss": 0.0,
      "num_input_tokens_seen": 8300320,
      "step": 29645
    },
    {
      "epoch": 329.44444444444446,
      "grad_norm": 4.0013528490590033e-08,
      "learning_rate": 0.046897885532175415,
      "loss": 0.0,
      "num_input_tokens_seen": 8301680,
      "step": 29650
    },
    {
      "epoch": 329.5,
      "grad_norm": 3.608365872764807e-08,
      "learning_rate": 0.04685510918578613,
      "loss": 0.0,
      "num_input_tokens_seen": 8303104,
      "step": 29655
    },
    {
      "epoch": 329.55555555555554,
      "grad_norm": 3.580091956223441e-08,
      "learning_rate": 0.04681234874563519,
      "loss": 0.0,
      "num_input_tokens_seen": 8304528,
      "step": 29660
    },
    {
      "epoch": 329.6111111111111,
      "grad_norm": 1.8761042497317248e-07,
      "learning_rate": 0.046769604218316836,
      "loss": 0.0,
      "num_input_tokens_seen": 8305888,
      "step": 29665
    },
    {
      "epoch": 329.6666666666667,
      "grad_norm": 1.77743615381587e-08,
      "learning_rate": 0.04672687561042279,
      "loss": 0.0,
      "num_input_tokens_seen": 8307328,
      "step": 29670
    },
    {
      "epoch": 329.72222222222223,
      "grad_norm": 3.024686989760994e-08,
      "learning_rate": 0.046684162928542286,
      "loss": 0.0,
      "num_input_tokens_seen": 8308752,
      "step": 29675
    },
    {
      "epoch": 329.77777777777777,
      "grad_norm": 2.621993289153579e-08,
      "learning_rate": 0.04664146617926222,
      "loss": 0.0,
      "num_input_tokens_seen": 8310160,
      "step": 29680
    },
    {
      "epoch": 329.8333333333333,
      "grad_norm": 5.0461615330732457e-08,
      "learning_rate": 0.046598785369167,
      "loss": 0.0,
      "num_input_tokens_seen": 8311520,
      "step": 29685
    },
    {
      "epoch": 329.8888888888889,
      "grad_norm": 1.3656949704454746e-07,
      "learning_rate": 0.046556120504838434,
      "loss": 0.0,
      "num_input_tokens_seen": 8312944,
      "step": 29690
    },
    {
      "epoch": 329.94444444444446,
      "grad_norm": 5.567318694943424e-08,
      "learning_rate": 0.04651347159285609,
      "loss": 0.0,
      "num_input_tokens_seen": 8314400,
      "step": 29695
    },
    {
      "epoch": 330.0,
      "grad_norm": 1.8347824592979123e-08,
      "learning_rate": 0.04647083863979688,
      "loss": 0.0,
      "num_input_tokens_seen": 8315840,
      "step": 29700
    },
    {
      "epoch": 330.05555555555554,
      "grad_norm": 2.7391658719011502e-08,
      "learning_rate": 0.04642822165223538,
      "loss": 0.0,
      "num_input_tokens_seen": 8317248,
      "step": 29705
    },
    {
      "epoch": 330.1111111111111,
      "grad_norm": 1.2942591887110666e-08,
      "learning_rate": 0.046385620636743716,
      "loss": 0.0,
      "num_input_tokens_seen": 8318592,
      "step": 29710
    },
    {
      "epoch": 330.1666666666667,
      "grad_norm": 3.439040696662232e-08,
      "learning_rate": 0.04634303559989141,
      "loss": 0.0,
      "num_input_tokens_seen": 8320000,
      "step": 29715
    },
    {
      "epoch": 330.22222222222223,
      "grad_norm": 1.2962698470175837e-08,
      "learning_rate": 0.046300466548245635,
      "loss": 0.0,
      "num_input_tokens_seen": 8321392,
      "step": 29720
    },
    {
      "epoch": 330.27777777777777,
      "grad_norm": 6.241160122044676e-08,
      "learning_rate": 0.04625791348837114,
      "loss": 0.0,
      "num_input_tokens_seen": 8322768,
      "step": 29725
    },
    {
      "epoch": 330.3333333333333,
      "grad_norm": 3.398596604142767e-08,
      "learning_rate": 0.046215376426830095,
      "loss": 0.0,
      "num_input_tokens_seen": 8324144,
      "step": 29730
    },
    {
      "epoch": 330.3888888888889,
      "grad_norm": 2.98453599612003e-08,
      "learning_rate": 0.04617285537018219,
      "loss": 0.0,
      "num_input_tokens_seen": 8325584,
      "step": 29735
    },
    {
      "epoch": 330.44444444444446,
      "grad_norm": 4.6276817045054486e-08,
      "learning_rate": 0.046130350324984803,
      "loss": 0.0,
      "num_input_tokens_seen": 8327072,
      "step": 29740
    },
    {
      "epoch": 330.5,
      "grad_norm": 3.7224637594590604e-08,
      "learning_rate": 0.046087861297792666,
      "loss": 0.0,
      "num_input_tokens_seen": 8328448,
      "step": 29745
    },
    {
      "epoch": 330.55555555555554,
      "grad_norm": 2.7088335130542873e-08,
      "learning_rate": 0.0460453882951582,
      "loss": 0.0,
      "num_input_tokens_seen": 8329872,
      "step": 29750
    },
    {
      "epoch": 330.6111111111111,
      "grad_norm": 9.142452483956731e-08,
      "learning_rate": 0.04600293132363119,
      "loss": 0.0,
      "num_input_tokens_seen": 8331280,
      "step": 29755
    },
    {
      "epoch": 330.6666666666667,
      "grad_norm": 2.6923471452278136e-08,
      "learning_rate": 0.045960490389759086,
      "loss": 0.0,
      "num_input_tokens_seen": 8332720,
      "step": 29760
    },
    {
      "epoch": 330.72222222222223,
      "grad_norm": 4.633711014889741e-08,
      "learning_rate": 0.04591806550008685,
      "loss": 0.0,
      "num_input_tokens_seen": 8334112,
      "step": 29765
    },
    {
      "epoch": 330.77777777777777,
      "grad_norm": 5.3755766060703536e-08,
      "learning_rate": 0.045875656661156825,
      "loss": 0.0,
      "num_input_tokens_seen": 8335472,
      "step": 29770
    },
    {
      "epoch": 330.8333333333333,
      "grad_norm": 8.117084604464253e-08,
      "learning_rate": 0.04583326387950911,
      "loss": 0.0,
      "num_input_tokens_seen": 8336832,
      "step": 29775
    },
    {
      "epoch": 330.8888888888889,
      "grad_norm": 3.099671985751229e-08,
      "learning_rate": 0.0457908871616811,
      "loss": 0.0,
      "num_input_tokens_seen": 8338192,
      "step": 29780
    },
    {
      "epoch": 330.94444444444446,
      "grad_norm": 5.84359796107492e-08,
      "learning_rate": 0.04574852651420786,
      "loss": 0.0,
      "num_input_tokens_seen": 8339584,
      "step": 29785
    },
    {
      "epoch": 331.0,
      "grad_norm": 7.25056281680736e-08,
      "learning_rate": 0.045706181943621985,
      "loss": 0.0,
      "num_input_tokens_seen": 8340976,
      "step": 29790
    },
    {
      "epoch": 331.05555555555554,
      "grad_norm": 5.475132169863173e-08,
      "learning_rate": 0.04566385345645344,
      "loss": 0.0,
      "num_input_tokens_seen": 8342352,
      "step": 29795
    },
    {
      "epoch": 331.1111111111111,
      "grad_norm": 9.873397033288711e-08,
      "learning_rate": 0.04562154105922993,
      "loss": 0.0,
      "num_input_tokens_seen": 8343760,
      "step": 29800
    },
    {
      "epoch": 331.1111111111111,
      "eval_loss": 1.6520347595214844,
      "eval_runtime": 1.185,
      "eval_samples_per_second": 33.755,
      "eval_steps_per_second": 16.878,
      "num_input_tokens_seen": 8343760,
      "step": 29800
    },
    {
      "epoch": 331.1666666666667,
      "grad_norm": 4.921031759863581e-08,
      "learning_rate": 0.04557924475847642,
      "loss": 0.0,
      "num_input_tokens_seen": 8345168,
      "step": 29805
    },
    {
      "epoch": 331.22222222222223,
      "grad_norm": 2.5096551325987093e-07,
      "learning_rate": 0.04553696456071567,
      "loss": 0.0,
      "num_input_tokens_seen": 8346576,
      "step": 29810
    },
    {
      "epoch": 331.27777777777777,
      "grad_norm": 2.7212012199129276e-08,
      "learning_rate": 0.045494700472467724,
      "loss": 0.0,
      "num_input_tokens_seen": 8348000,
      "step": 29815
    },
    {
      "epoch": 331.3333333333333,
      "grad_norm": 3.263965098199151e-08,
      "learning_rate": 0.04545245250025024,
      "loss": 0.0,
      "num_input_tokens_seen": 8349392,
      "step": 29820
    },
    {
      "epoch": 331.3888888888889,
      "grad_norm": 2.467158388697044e-08,
      "learning_rate": 0.045410220650578384,
      "loss": 0.0,
      "num_input_tokens_seen": 8350816,
      "step": 29825
    },
    {
      "epoch": 331.44444444444446,
      "grad_norm": 4.2124394639131424e-08,
      "learning_rate": 0.04536800492996492,
      "loss": 0.0,
      "num_input_tokens_seen": 8352208,
      "step": 29830
    },
    {
      "epoch": 331.5,
      "grad_norm": 3.494164104722586e-07,
      "learning_rate": 0.04532580534491994,
      "loss": 0.0,
      "num_input_tokens_seen": 8353584,
      "step": 29835
    },
    {
      "epoch": 331.55555555555554,
      "grad_norm": 6.863962909164911e-08,
      "learning_rate": 0.045283621901951183,
      "loss": 0.0,
      "num_input_tokens_seen": 8354944,
      "step": 29840
    },
    {
      "epoch": 331.6111111111111,
      "grad_norm": 5.66356668230128e-08,
      "learning_rate": 0.04524145460756393,
      "loss": 0.0,
      "num_input_tokens_seen": 8356320,
      "step": 29845
    },
    {
      "epoch": 331.6666666666667,
      "grad_norm": 1.7917583861049025e-08,
      "learning_rate": 0.045199303468260794,
      "loss": 0.0,
      "num_input_tokens_seen": 8357728,
      "step": 29850
    },
    {
      "epoch": 331.72222222222223,
      "grad_norm": 6.474800073874576e-08,
      "learning_rate": 0.04515716849054214,
      "loss": 0.0,
      "num_input_tokens_seen": 8359152,
      "step": 29855
    },
    {
      "epoch": 331.77777777777777,
      "grad_norm": 3.3969780588449794e-07,
      "learning_rate": 0.04511504968090558,
      "loss": 0.0,
      "num_input_tokens_seen": 8360544,
      "step": 29860
    },
    {
      "epoch": 331.8333333333333,
      "grad_norm": 1.833924656580166e-08,
      "learning_rate": 0.04507294704584644,
      "loss": 0.0,
      "num_input_tokens_seen": 8361968,
      "step": 29865
    },
    {
      "epoch": 331.8888888888889,
      "grad_norm": 2.785735553345603e-08,
      "learning_rate": 0.04503086059185749,
      "loss": 0.0,
      "num_input_tokens_seen": 8363376,
      "step": 29870
    },
    {
      "epoch": 331.94444444444446,
      "grad_norm": 8.517350380543576e-08,
      "learning_rate": 0.04498879032542893,
      "loss": 0.0,
      "num_input_tokens_seen": 8364768,
      "step": 29875
    },
    {
      "epoch": 332.0,
      "grad_norm": 3.558246319812497e-08,
      "learning_rate": 0.0449467362530486,
      "loss": 0.0,
      "num_input_tokens_seen": 8366160,
      "step": 29880
    },
    {
      "epoch": 332.05555555555554,
      "grad_norm": 4.286425507871172e-07,
      "learning_rate": 0.04490469838120171,
      "loss": 0.0,
      "num_input_tokens_seen": 8367584,
      "step": 29885
    },
    {
      "epoch": 332.1111111111111,
      "grad_norm": 2.4802249143363042e-08,
      "learning_rate": 0.04486267671637101,
      "loss": 0.0,
      "num_input_tokens_seen": 8368992,
      "step": 29890
    },
    {
      "epoch": 332.1666666666667,
      "grad_norm": 2.5661558211709234e-08,
      "learning_rate": 0.04482067126503683,
      "loss": 0.0,
      "num_input_tokens_seen": 8370384,
      "step": 29895
    },
    {
      "epoch": 332.22222222222223,
      "grad_norm": 1.4752984611732245e-08,
      "learning_rate": 0.04477868203367687,
      "loss": 0.0,
      "num_input_tokens_seen": 8371760,
      "step": 29900
    },
    {
      "epoch": 332.27777777777777,
      "grad_norm": 1.9620955526988837e-08,
      "learning_rate": 0.044736709028766426,
      "loss": 0.0,
      "num_input_tokens_seen": 8373152,
      "step": 29905
    },
    {
      "epoch": 332.3333333333333,
      "grad_norm": 1.6606815478326098e-08,
      "learning_rate": 0.04469475225677832,
      "loss": 0.0,
      "num_input_tokens_seen": 8374576,
      "step": 29910
    },
    {
      "epoch": 332.3888888888889,
      "grad_norm": 1.4170826290182958e-08,
      "learning_rate": 0.04465281172418273,
      "loss": 0.0,
      "num_input_tokens_seen": 8375968,
      "step": 29915
    },
    {
      "epoch": 332.44444444444446,
      "grad_norm": 2.6546382869696572e-08,
      "learning_rate": 0.044610887437447476,
      "loss": 0.0,
      "num_input_tokens_seen": 8377344,
      "step": 29920
    },
    {
      "epoch": 332.5,
      "grad_norm": 3.6262534308662e-08,
      "learning_rate": 0.044568979403037744,
      "loss": 0.0,
      "num_input_tokens_seen": 8378736,
      "step": 29925
    },
    {
      "epoch": 332.55555555555554,
      "grad_norm": 6.677446151570621e-08,
      "learning_rate": 0.04452708762741631,
      "loss": 0.0,
      "num_input_tokens_seen": 8380144,
      "step": 29930
    },
    {
      "epoch": 332.6111111111111,
      "grad_norm": 3.571994255935351e-08,
      "learning_rate": 0.044485212117043475,
      "loss": 0.0,
      "num_input_tokens_seen": 8381536,
      "step": 29935
    },
    {
      "epoch": 332.6666666666667,
      "grad_norm": 2.6614475956421302e-08,
      "learning_rate": 0.04444335287837687,
      "loss": 0.0,
      "num_input_tokens_seen": 8382960,
      "step": 29940
    },
    {
      "epoch": 332.72222222222223,
      "grad_norm": 2.3751031363872244e-08,
      "learning_rate": 0.04440150991787179,
      "loss": 0.0,
      "num_input_tokens_seen": 8384368,
      "step": 29945
    },
    {
      "epoch": 332.77777777777777,
      "grad_norm": 2.9833856274308346e-08,
      "learning_rate": 0.04435968324198088,
      "loss": 0.0,
      "num_input_tokens_seen": 8385760,
      "step": 29950
    },
    {
      "epoch": 332.8333333333333,
      "grad_norm": 9.71505969005193e-08,
      "learning_rate": 0.04431787285715442,
      "loss": 0.0,
      "num_input_tokens_seen": 8387168,
      "step": 29955
    },
    {
      "epoch": 332.8888888888889,
      "grad_norm": 2.1440477837586513e-08,
      "learning_rate": 0.04427607876984004,
      "loss": 0.0,
      "num_input_tokens_seen": 8388560,
      "step": 29960
    },
    {
      "epoch": 332.94444444444446,
      "grad_norm": 3.549448734929683e-08,
      "learning_rate": 0.044234300986482886,
      "loss": 0.0,
      "num_input_tokens_seen": 8389920,
      "step": 29965
    },
    {
      "epoch": 333.0,
      "grad_norm": 4.2313590853382266e-08,
      "learning_rate": 0.04419253951352566,
      "loss": 0.0,
      "num_input_tokens_seen": 8391328,
      "step": 29970
    },
    {
      "epoch": 333.05555555555554,
      "grad_norm": 2.2175305147698054e-08,
      "learning_rate": 0.044150794357408533,
      "loss": 0.0,
      "num_input_tokens_seen": 8392720,
      "step": 29975
    },
    {
      "epoch": 333.1111111111111,
      "grad_norm": 4.689607280283781e-08,
      "learning_rate": 0.044109065524569065,
      "loss": 0.0,
      "num_input_tokens_seen": 8394112,
      "step": 29980
    },
    {
      "epoch": 333.1666666666667,
      "grad_norm": 5.049726681249922e-08,
      "learning_rate": 0.0440673530214424,
      "loss": 0.0,
      "num_input_tokens_seen": 8395504,
      "step": 29985
    },
    {
      "epoch": 333.22222222222223,
      "grad_norm": 5.1591918293070194e-08,
      "learning_rate": 0.04402565685446117,
      "loss": 0.0,
      "num_input_tokens_seen": 8396928,
      "step": 29990
    },
    {
      "epoch": 333.27777777777777,
      "grad_norm": 3.723144104128551e-08,
      "learning_rate": 0.04398397703005536,
      "loss": 0.0,
      "num_input_tokens_seen": 8398320,
      "step": 29995
    },
    {
      "epoch": 333.3333333333333,
      "grad_norm": 2.004131793853503e-08,
      "learning_rate": 0.043942313554652626,
      "loss": 0.0,
      "num_input_tokens_seen": 8399696,
      "step": 30000
    },
    {
      "epoch": 333.3333333333333,
      "eval_loss": 1.6906516551971436,
      "eval_runtime": 1.1827,
      "eval_samples_per_second": 33.821,
      "eval_steps_per_second": 16.91,
      "num_input_tokens_seen": 8399696,
      "step": 30000
    },
    {
      "epoch": 333.3888888888889,
      "grad_norm": 2.646206986867128e-08,
      "learning_rate": 0.0439006664346779,
      "loss": 0.0,
      "num_input_tokens_seen": 8401104,
      "step": 30005
    },
    {
      "epoch": 333.44444444444446,
      "grad_norm": 5.8218653009589616e-08,
      "learning_rate": 0.043859035676553755,
      "loss": 0.0,
      "num_input_tokens_seen": 8402512,
      "step": 30010
    },
    {
      "epoch": 333.5,
      "grad_norm": 3.9644866944854584e-08,
      "learning_rate": 0.043817421286700194,
      "loss": 0.0,
      "num_input_tokens_seen": 8403888,
      "step": 30015
    },
    {
      "epoch": 333.55555555555554,
      "grad_norm": 3.168640105855047e-08,
      "learning_rate": 0.043775823271534585,
      "loss": 0.0,
      "num_input_tokens_seen": 8405312,
      "step": 30020
    },
    {
      "epoch": 333.6111111111111,
      "grad_norm": 2.4987777180740522e-08,
      "learning_rate": 0.04373424163747197,
      "loss": 0.0,
      "num_input_tokens_seen": 8406752,
      "step": 30025
    },
    {
      "epoch": 333.6666666666667,
      "grad_norm": 2.8566280008135436e-08,
      "learning_rate": 0.04369267639092473,
      "loss": 0.0,
      "num_input_tokens_seen": 8408192,
      "step": 30030
    },
    {
      "epoch": 333.72222222222223,
      "grad_norm": 5.846906603323987e-08,
      "learning_rate": 0.04365112753830268,
      "loss": 0.0,
      "num_input_tokens_seen": 8409568,
      "step": 30035
    },
    {
      "epoch": 333.77777777777777,
      "grad_norm": 3.146201876802479e-08,
      "learning_rate": 0.04360959508601327,
      "loss": 0.0,
      "num_input_tokens_seen": 8411008,
      "step": 30040
    },
    {
      "epoch": 333.8333333333333,
      "grad_norm": 4.9612932428999557e-08,
      "learning_rate": 0.04356807904046123,
      "loss": 0.0,
      "num_input_tokens_seen": 8412368,
      "step": 30045
    },
    {
      "epoch": 333.8888888888889,
      "grad_norm": 4.162746236602288e-08,
      "learning_rate": 0.04352657940804892,
      "loss": 0.0,
      "num_input_tokens_seen": 8413744,
      "step": 30050
    },
    {
      "epoch": 333.94444444444446,
      "grad_norm": 1.660524340252323e-08,
      "learning_rate": 0.04348509619517613,
      "loss": 0.0,
      "num_input_tokens_seen": 8415152,
      "step": 30055
    },
    {
      "epoch": 334.0,
      "grad_norm": 2.4871075865462444e-08,
      "learning_rate": 0.04344362940824002,
      "loss": 0.0,
      "num_input_tokens_seen": 8416592,
      "step": 30060
    },
    {
      "epoch": 334.05555555555554,
      "grad_norm": 4.037023870751e-08,
      "learning_rate": 0.04340217905363533,
      "loss": 0.0,
      "num_input_tokens_seen": 8418016,
      "step": 30065
    },
    {
      "epoch": 334.1111111111111,
      "grad_norm": 3.119221787528659e-07,
      "learning_rate": 0.04336074513775425,
      "loss": 0.0,
      "num_input_tokens_seen": 8419408,
      "step": 30070
    },
    {
      "epoch": 334.1666666666667,
      "grad_norm": 2.5552614246748817e-08,
      "learning_rate": 0.04331932766698636,
      "loss": 0.0,
      "num_input_tokens_seen": 8420784,
      "step": 30075
    },
    {
      "epoch": 334.22222222222223,
      "grad_norm": 1.394364659290659e-07,
      "learning_rate": 0.0432779266477188,
      "loss": 0.0,
      "num_input_tokens_seen": 8422192,
      "step": 30080
    },
    {
      "epoch": 334.27777777777777,
      "grad_norm": 2.8300576104811626e-08,
      "learning_rate": 0.04323654208633607,
      "loss": 0.0,
      "num_input_tokens_seen": 8423648,
      "step": 30085
    },
    {
      "epoch": 334.3333333333333,
      "grad_norm": 5.518220902445137e-08,
      "learning_rate": 0.04319517398922024,
      "loss": 0.0,
      "num_input_tokens_seen": 8425056,
      "step": 30090
    },
    {
      "epoch": 334.3888888888889,
      "grad_norm": 6.73251960847665e-08,
      "learning_rate": 0.04315382236275079,
      "loss": 0.0,
      "num_input_tokens_seen": 8426464,
      "step": 30095
    },
    {
      "epoch": 334.44444444444446,
      "grad_norm": 1.0441073783340471e-07,
      "learning_rate": 0.043112487213304664,
      "loss": 0.0,
      "num_input_tokens_seen": 8427872,
      "step": 30100
    },
    {
      "epoch": 334.5,
      "grad_norm": 3.906534118414129e-08,
      "learning_rate": 0.04307116854725618,
      "loss": 0.0,
      "num_input_tokens_seen": 8429280,
      "step": 30105
    },
    {
      "epoch": 334.55555555555554,
      "grad_norm": 2.0554914215153985e-07,
      "learning_rate": 0.043029866370977325,
      "loss": 0.0,
      "num_input_tokens_seen": 8430656,
      "step": 30110
    },
    {
      "epoch": 334.6111111111111,
      "grad_norm": 9.256628885623286e-08,
      "learning_rate": 0.04298858069083728,
      "loss": 0.0,
      "num_input_tokens_seen": 8432048,
      "step": 30115
    },
    {
      "epoch": 334.6666666666667,
      "grad_norm": 1.7537228558239804e-08,
      "learning_rate": 0.04294731151320295,
      "loss": 0.0,
      "num_input_tokens_seen": 8433488,
      "step": 30120
    },
    {
      "epoch": 334.72222222222223,
      "grad_norm": 2.476970273335155e-08,
      "learning_rate": 0.04290605884443841,
      "loss": 0.0,
      "num_input_tokens_seen": 8434800,
      "step": 30125
    },
    {
      "epoch": 334.77777777777777,
      "grad_norm": 7.856268524619736e-08,
      "learning_rate": 0.04286482269090545,
      "loss": 0.0,
      "num_input_tokens_seen": 8436208,
      "step": 30130
    },
    {
      "epoch": 334.8333333333333,
      "grad_norm": 4.2731088001346507e-08,
      "learning_rate": 0.04282360305896323,
      "loss": 0.0,
      "num_input_tokens_seen": 8437632,
      "step": 30135
    },
    {
      "epoch": 334.8888888888889,
      "grad_norm": 2.98926359221241e-08,
      "learning_rate": 0.04278239995496822,
      "loss": 0.0,
      "num_input_tokens_seen": 8439056,
      "step": 30140
    },
    {
      "epoch": 334.94444444444446,
      "grad_norm": 4.5533308679068796e-08,
      "learning_rate": 0.042741213385274514,
      "loss": 0.0,
      "num_input_tokens_seen": 8440480,
      "step": 30145
    },
    {
      "epoch": 335.0,
      "grad_norm": 1.3595776948704952e-08,
      "learning_rate": 0.04270004335623366,
      "loss": 0.0,
      "num_input_tokens_seen": 8441872,
      "step": 30150
    },
    {
      "epoch": 335.05555555555554,
      "grad_norm": 1.314411264274895e-07,
      "learning_rate": 0.04265888987419448,
      "loss": 0.0,
      "num_input_tokens_seen": 8443296,
      "step": 30155
    },
    {
      "epoch": 335.1111111111111,
      "grad_norm": 1.4605933351674594e-08,
      "learning_rate": 0.04261775294550346,
      "loss": 0.0,
      "num_input_tokens_seen": 8444640,
      "step": 30160
    },
    {
      "epoch": 335.1666666666667,
      "grad_norm": 2.1479207745755957e-08,
      "learning_rate": 0.042576632576504354,
      "loss": 0.0,
      "num_input_tokens_seen": 8446048,
      "step": 30165
    },
    {
      "epoch": 335.22222222222223,
      "grad_norm": 2.9581206817397288e-08,
      "learning_rate": 0.0425355287735385,
      "loss": 0.0,
      "num_input_tokens_seen": 8447488,
      "step": 30170
    },
    {
      "epoch": 335.27777777777777,
      "grad_norm": 3.617052612980842e-08,
      "learning_rate": 0.0424944415429446,
      "loss": 0.0,
      "num_input_tokens_seen": 8448912,
      "step": 30175
    },
    {
      "epoch": 335.3333333333333,
      "grad_norm": 4.2657312349092535e-08,
      "learning_rate": 0.04245337089105877,
      "loss": 0.0,
      "num_input_tokens_seen": 8450240,
      "step": 30180
    },
    {
      "epoch": 335.3888888888889,
      "grad_norm": 3.196162978724715e-08,
      "learning_rate": 0.04241231682421467,
      "loss": 0.0,
      "num_input_tokens_seen": 8451632,
      "step": 30185
    },
    {
      "epoch": 335.44444444444446,
      "grad_norm": 1.8533437895484894e-08,
      "learning_rate": 0.04237127934874337,
      "loss": 0.0,
      "num_input_tokens_seen": 8452992,
      "step": 30190
    },
    {
      "epoch": 335.5,
      "grad_norm": 3.6764571831326975e-08,
      "learning_rate": 0.042330258470973305,
      "loss": 0.0,
      "num_input_tokens_seen": 8454400,
      "step": 30195
    },
    {
      "epoch": 335.55555555555554,
      "grad_norm": 3.8247417677439444e-08,
      "learning_rate": 0.042289254197230515,
      "loss": 0.0,
      "num_input_tokens_seen": 8455776,
      "step": 30200
    },
    {
      "epoch": 335.55555555555554,
      "eval_loss": 1.614349603652954,
      "eval_runtime": 1.1923,
      "eval_samples_per_second": 33.549,
      "eval_steps_per_second": 16.775,
      "num_input_tokens_seen": 8455776,
      "step": 30200
    },
    {
      "epoch": 335.6111111111111,
      "grad_norm": 3.5099787965009455e-08,
      "learning_rate": 0.04224826653383823,
      "loss": 0.0,
      "num_input_tokens_seen": 8457232,
      "step": 30205
    },
    {
      "epoch": 335.6666666666667,
      "grad_norm": 8.357630321143006e-08,
      "learning_rate": 0.04220729548711735,
      "loss": 0.0,
      "num_input_tokens_seen": 8458608,
      "step": 30210
    },
    {
      "epoch": 335.72222222222223,
      "grad_norm": 4.8503437710678554e-08,
      "learning_rate": 0.04216634106338616,
      "loss": 0.0,
      "num_input_tokens_seen": 8460016,
      "step": 30215
    },
    {
      "epoch": 335.77777777777777,
      "grad_norm": 6.678611441657267e-08,
      "learning_rate": 0.04212540326896025,
      "loss": 0.0,
      "num_input_tokens_seen": 8461360,
      "step": 30220
    },
    {
      "epoch": 335.8333333333333,
      "grad_norm": 3.2452536657956443e-08,
      "learning_rate": 0.0420844821101528,
      "loss": 0.0,
      "num_input_tokens_seen": 8462800,
      "step": 30225
    },
    {
      "epoch": 335.8888888888889,
      "grad_norm": 5.198549501983507e-08,
      "learning_rate": 0.04204357759327441,
      "loss": 0.0,
      "num_input_tokens_seen": 8464192,
      "step": 30230
    },
    {
      "epoch": 335.94444444444446,
      "grad_norm": 7.134078572335056e-08,
      "learning_rate": 0.042002689724632954,
      "loss": 0.0,
      "num_input_tokens_seen": 8465616,
      "step": 30235
    },
    {
      "epoch": 336.0,
      "grad_norm": 4.302441780623667e-08,
      "learning_rate": 0.04196181851053398,
      "loss": 0.0,
      "num_input_tokens_seen": 8466992,
      "step": 30240
    },
    {
      "epoch": 336.05555555555554,
      "grad_norm": 6.866729762577961e-08,
      "learning_rate": 0.041920963957280295,
      "loss": 0.0,
      "num_input_tokens_seen": 8468416,
      "step": 30245
    },
    {
      "epoch": 336.1111111111111,
      "grad_norm": 1.1952018041938572e-07,
      "learning_rate": 0.04188012607117212,
      "loss": 0.0,
      "num_input_tokens_seen": 8469808,
      "step": 30250
    },
    {
      "epoch": 336.1666666666667,
      "grad_norm": 3.339431486892863e-08,
      "learning_rate": 0.04183930485850725,
      "loss": 0.0,
      "num_input_tokens_seen": 8471216,
      "step": 30255
    },
    {
      "epoch": 336.22222222222223,
      "grad_norm": 2.1577434949904273e-08,
      "learning_rate": 0.04179850032558078,
      "loss": 0.0,
      "num_input_tokens_seen": 8472608,
      "step": 30260
    },
    {
      "epoch": 336.27777777777777,
      "grad_norm": 4.66796379328116e-08,
      "learning_rate": 0.041757712478685295,
      "loss": 0.0,
      "num_input_tokens_seen": 8473984,
      "step": 30265
    },
    {
      "epoch": 336.3333333333333,
      "grad_norm": 5.818407800006753e-08,
      "learning_rate": 0.04171694132411085,
      "loss": 0.0,
      "num_input_tokens_seen": 8475424,
      "step": 30270
    },
    {
      "epoch": 336.3888888888889,
      "grad_norm": 2.6500595140532823e-07,
      "learning_rate": 0.04167618686814479,
      "loss": 0.0,
      "num_input_tokens_seen": 8476848,
      "step": 30275
    },
    {
      "epoch": 336.44444444444446,
      "grad_norm": 2.7949070613431104e-08,
      "learning_rate": 0.041635449117072024,
      "loss": 0.0,
      "num_input_tokens_seen": 8478256,
      "step": 30280
    },
    {
      "epoch": 336.5,
      "grad_norm": 1.654819037355537e-08,
      "learning_rate": 0.04159472807717477,
      "loss": 0.0,
      "num_input_tokens_seen": 8479696,
      "step": 30285
    },
    {
      "epoch": 336.55555555555554,
      "grad_norm": 2.2997754811626692e-08,
      "learning_rate": 0.041554023754732744,
      "loss": 0.0,
      "num_input_tokens_seen": 8481104,
      "step": 30290
    },
    {
      "epoch": 336.6111111111111,
      "grad_norm": 1.1987232539922843e-07,
      "learning_rate": 0.04151333615602311,
      "loss": 0.0,
      "num_input_tokens_seen": 8482496,
      "step": 30295
    },
    {
      "epoch": 336.6666666666667,
      "grad_norm": 3.834363226928872e-08,
      "learning_rate": 0.04147266528732034,
      "loss": 0.0,
      "num_input_tokens_seen": 8483856,
      "step": 30300
    },
    {
      "epoch": 336.72222222222223,
      "grad_norm": 3.249292035434337e-08,
      "learning_rate": 0.0414320111548964,
      "loss": 0.0,
      "num_input_tokens_seen": 8485248,
      "step": 30305
    },
    {
      "epoch": 336.77777777777777,
      "grad_norm": 2.986853075981344e-07,
      "learning_rate": 0.04139137376502076,
      "loss": 0.0,
      "num_input_tokens_seen": 8486624,
      "step": 30310
    },
    {
      "epoch": 336.8333333333333,
      "grad_norm": 6.22194420429878e-08,
      "learning_rate": 0.04135075312396014,
      "loss": 0.0,
      "num_input_tokens_seen": 8487984,
      "step": 30315
    },
    {
      "epoch": 336.8888888888889,
      "grad_norm": 4.7318351903413713e-08,
      "learning_rate": 0.04131014923797875,
      "loss": 0.0,
      "num_input_tokens_seen": 8489392,
      "step": 30320
    },
    {
      "epoch": 336.94444444444446,
      "grad_norm": 2.6695678556620805e-08,
      "learning_rate": 0.04126956211333819,
      "loss": 0.0,
      "num_input_tokens_seen": 8490768,
      "step": 30325
    },
    {
      "epoch": 337.0,
      "grad_norm": 6.283290332476099e-08,
      "learning_rate": 0.041228991756297545,
      "loss": 0.0,
      "num_input_tokens_seen": 8492160,
      "step": 30330
    },
    {
      "epoch": 337.05555555555554,
      "grad_norm": 6.386613904396654e-08,
      "learning_rate": 0.04118843817311332,
      "loss": 0.0,
      "num_input_tokens_seen": 8493584,
      "step": 30335
    },
    {
      "epoch": 337.1111111111111,
      "grad_norm": 4.235554484921522e-08,
      "learning_rate": 0.0411479013700393,
      "loss": 0.0,
      "num_input_tokens_seen": 8494992,
      "step": 30340
    },
    {
      "epoch": 337.1666666666667,
      "grad_norm": 3.821493521627417e-08,
      "learning_rate": 0.0411073813533268,
      "loss": 0.0,
      "num_input_tokens_seen": 8496384,
      "step": 30345
    },
    {
      "epoch": 337.22222222222223,
      "grad_norm": 6.738049762589071e-08,
      "learning_rate": 0.04106687812922456,
      "loss": 0.0,
      "num_input_tokens_seen": 8497792,
      "step": 30350
    },
    {
      "epoch": 337.27777777777777,
      "grad_norm": 2.6132227048947243e-08,
      "learning_rate": 0.041026391703978635,
      "loss": 0.0,
      "num_input_tokens_seen": 8499168,
      "step": 30355
    },
    {
      "epoch": 337.3333333333333,
      "grad_norm": 3.734572118219148e-08,
      "learning_rate": 0.04098592208383259,
      "loss": 0.0,
      "num_input_tokens_seen": 8500544,
      "step": 30360
    },
    {
      "epoch": 337.3888888888889,
      "grad_norm": 5.2717709309035854e-08,
      "learning_rate": 0.040945469275027256,
      "loss": 0.0,
      "num_input_tokens_seen": 8501968,
      "step": 30365
    },
    {
      "epoch": 337.44444444444446,
      "grad_norm": 4.954685195457387e-08,
      "learning_rate": 0.04090503328380104,
      "loss": 0.0,
      "num_input_tokens_seen": 8503360,
      "step": 30370
    },
    {
      "epoch": 337.5,
      "grad_norm": 3.65000687452266e-08,
      "learning_rate": 0.04086461411638971,
      "loss": 0.0,
      "num_input_tokens_seen": 8504752,
      "step": 30375
    },
    {
      "epoch": 337.55555555555554,
      "grad_norm": 4.514644302844317e-08,
      "learning_rate": 0.04082421177902631,
      "loss": 0.0,
      "num_input_tokens_seen": 8506160,
      "step": 30380
    },
    {
      "epoch": 337.6111111111111,
      "grad_norm": 2.829347955923822e-08,
      "learning_rate": 0.04078382627794149,
      "loss": 0.0,
      "num_input_tokens_seen": 8507552,
      "step": 30385
    },
    {
      "epoch": 337.6666666666667,
      "grad_norm": 3.179813745646243e-08,
      "learning_rate": 0.04074345761936316,
      "loss": 0.0,
      "num_input_tokens_seen": 8508960,
      "step": 30390
    },
    {
      "epoch": 337.72222222222223,
      "grad_norm": 3.910303547627336e-08,
      "learning_rate": 0.04070310580951663,
      "loss": 0.0,
      "num_input_tokens_seen": 8510352,
      "step": 30395
    },
    {
      "epoch": 337.77777777777777,
      "grad_norm": 8.096874637431029e-08,
      "learning_rate": 0.040662770854624726,
      "loss": 0.0,
      "num_input_tokens_seen": 8511760,
      "step": 30400
    },
    {
      "epoch": 337.77777777777777,
      "eval_loss": 1.6979000568389893,
      "eval_runtime": 1.1851,
      "eval_samples_per_second": 33.751,
      "eval_steps_per_second": 16.876,
      "num_input_tokens_seen": 8511760,
      "step": 30400
    },
    {
      "epoch": 337.8333333333333,
      "grad_norm": 5.8006829561918494e-08,
      "learning_rate": 0.040622452760907535,
      "loss": 0.0,
      "num_input_tokens_seen": 8513184,
      "step": 30405
    },
    {
      "epoch": 337.8888888888889,
      "grad_norm": 3.1842574799156864e-08,
      "learning_rate": 0.04058215153458265,
      "loss": 0.0,
      "num_input_tokens_seen": 8514560,
      "step": 30410
    },
    {
      "epoch": 337.94444444444446,
      "grad_norm": 4.0411087809388846e-08,
      "learning_rate": 0.04054186718186507,
      "loss": 0.0,
      "num_input_tokens_seen": 8515952,
      "step": 30415
    },
    {
      "epoch": 338.0,
      "grad_norm": 3.763572209436461e-08,
      "learning_rate": 0.04050159970896708,
      "loss": 0.0,
      "num_input_tokens_seen": 8517360,
      "step": 30420
    },
    {
      "epoch": 338.05555555555554,
      "grad_norm": 2.9641139320801813e-08,
      "learning_rate": 0.04046134912209843,
      "loss": 0.0,
      "num_input_tokens_seen": 8518800,
      "step": 30425
    },
    {
      "epoch": 338.1111111111111,
      "grad_norm": 5.767475386164733e-08,
      "learning_rate": 0.040421115427466354,
      "loss": 0.0,
      "num_input_tokens_seen": 8520192,
      "step": 30430
    },
    {
      "epoch": 338.1666666666667,
      "grad_norm": 2.2193189508357136e-08,
      "learning_rate": 0.04038089863127529,
      "loss": 0.0,
      "num_input_tokens_seen": 8521600,
      "step": 30435
    },
    {
      "epoch": 338.22222222222223,
      "grad_norm": 4.879408521674122e-08,
      "learning_rate": 0.04034069873972727,
      "loss": 0.0,
      "num_input_tokens_seen": 8522960,
      "step": 30440
    },
    {
      "epoch": 338.27777777777777,
      "grad_norm": 1.0761603874698267e-07,
      "learning_rate": 0.040300515759021514,
      "loss": 0.0,
      "num_input_tokens_seen": 8524384,
      "step": 30445
    },
    {
      "epoch": 338.3333333333333,
      "grad_norm": 1.138930230126789e-07,
      "learning_rate": 0.04026034969535478,
      "loss": 0.0,
      "num_input_tokens_seen": 8525824,
      "step": 30450
    },
    {
      "epoch": 338.3888888888889,
      "grad_norm": 2.428941137111451e-08,
      "learning_rate": 0.040220200554921266,
      "loss": 0.0,
      "num_input_tokens_seen": 8527216,
      "step": 30455
    },
    {
      "epoch": 338.44444444444446,
      "grad_norm": 3.40466606019163e-08,
      "learning_rate": 0.0401800683439124,
      "loss": 0.0,
      "num_input_tokens_seen": 8528624,
      "step": 30460
    },
    {
      "epoch": 338.5,
      "grad_norm": 4.462345160050063e-08,
      "learning_rate": 0.04013995306851704,
      "loss": 0.0,
      "num_input_tokens_seen": 8530032,
      "step": 30465
    },
    {
      "epoch": 338.55555555555554,
      "grad_norm": 5.111816037128847e-08,
      "learning_rate": 0.040099854734921545,
      "loss": 0.0,
      "num_input_tokens_seen": 8531376,
      "step": 30470
    },
    {
      "epoch": 338.6111111111111,
      "grad_norm": 6.069896585358947e-08,
      "learning_rate": 0.0400597733493095,
      "loss": 0.0,
      "num_input_tokens_seen": 8532736,
      "step": 30475
    },
    {
      "epoch": 338.6666666666667,
      "grad_norm": 6.116898987329478e-08,
      "learning_rate": 0.04001970891786203,
      "loss": 0.0,
      "num_input_tokens_seen": 8534160,
      "step": 30480
    },
    {
      "epoch": 338.72222222222223,
      "grad_norm": 5.003177605544806e-08,
      "learning_rate": 0.03997966144675752,
      "loss": 0.0,
      "num_input_tokens_seen": 8535584,
      "step": 30485
    },
    {
      "epoch": 338.77777777777777,
      "grad_norm": 9.142754464619429e-08,
      "learning_rate": 0.039939630942171796,
      "loss": 0.0,
      "num_input_tokens_seen": 8537024,
      "step": 30490
    },
    {
      "epoch": 338.8333333333333,
      "grad_norm": 9.503107634145636e-08,
      "learning_rate": 0.03989961741027815,
      "loss": 0.0,
      "num_input_tokens_seen": 8538352,
      "step": 30495
    },
    {
      "epoch": 338.8888888888889,
      "grad_norm": 5.760843890811884e-08,
      "learning_rate": 0.03985962085724704,
      "loss": 0.0,
      "num_input_tokens_seen": 8539792,
      "step": 30500
    },
    {
      "epoch": 338.94444444444446,
      "grad_norm": 2.990671177371951e-08,
      "learning_rate": 0.03981964128924656,
      "loss": 0.0,
      "num_input_tokens_seen": 8541184,
      "step": 30505
    },
    {
      "epoch": 339.0,
      "grad_norm": 4.785386309436035e-08,
      "learning_rate": 0.03977967871244197,
      "loss": 0.0,
      "num_input_tokens_seen": 8542576,
      "step": 30510
    },
    {
      "epoch": 339.05555555555554,
      "grad_norm": 3.132100090397216e-08,
      "learning_rate": 0.03973973313299602,
      "loss": 0.0,
      "num_input_tokens_seen": 8543968,
      "step": 30515
    },
    {
      "epoch": 339.1111111111111,
      "grad_norm": 1.395594892983354e-07,
      "learning_rate": 0.0396998045570689,
      "loss": 0.0,
      "num_input_tokens_seen": 8545392,
      "step": 30520
    },
    {
      "epoch": 339.1666666666667,
      "grad_norm": 2.9218176322842737e-08,
      "learning_rate": 0.03965989299081798,
      "loss": 0.0,
      "num_input_tokens_seen": 8546784,
      "step": 30525
    },
    {
      "epoch": 339.22222222222223,
      "grad_norm": 2.5839554496087658e-08,
      "learning_rate": 0.039619998440398235,
      "loss": 0.0,
      "num_input_tokens_seen": 8548192,
      "step": 30530
    },
    {
      "epoch": 339.27777777777777,
      "grad_norm": 2.391172415627807e-08,
      "learning_rate": 0.03958012091196184,
      "loss": 0.0,
      "num_input_tokens_seen": 8549568,
      "step": 30535
    },
    {
      "epoch": 339.3333333333333,
      "grad_norm": 1.891158696309958e-08,
      "learning_rate": 0.039540260411658396,
      "loss": 0.0,
      "num_input_tokens_seen": 8550976,
      "step": 30540
    },
    {
      "epoch": 339.3888888888889,
      "grad_norm": 2.410448196599191e-08,
      "learning_rate": 0.03950041694563496,
      "loss": 0.0,
      "num_input_tokens_seen": 8552368,
      "step": 30545
    },
    {
      "epoch": 339.44444444444446,
      "grad_norm": 6.527386631205445e-08,
      "learning_rate": 0.0394605905200358,
      "loss": 0.0,
      "num_input_tokens_seen": 8553792,
      "step": 30550
    },
    {
      "epoch": 339.5,
      "grad_norm": 3.3328728221704296e-08,
      "learning_rate": 0.03942078114100272,
      "loss": 0.0,
      "num_input_tokens_seen": 8555216,
      "step": 30555
    },
    {
      "epoch": 339.55555555555554,
      "grad_norm": 5.7043315848659404e-08,
      "learning_rate": 0.03938098881467485,
      "loss": 0.0,
      "num_input_tokens_seen": 8556656,
      "step": 30560
    },
    {
      "epoch": 339.6111111111111,
      "grad_norm": 4.416255450223616e-08,
      "learning_rate": 0.039341213547188586,
      "loss": 0.0,
      "num_input_tokens_seen": 8558048,
      "step": 30565
    },
    {
      "epoch": 339.6666666666667,
      "grad_norm": 5.3467616112357064e-08,
      "learning_rate": 0.03930145534467782,
      "loss": 0.0,
      "num_input_tokens_seen": 8559408,
      "step": 30570
    },
    {
      "epoch": 339.72222222222223,
      "grad_norm": 5.152511661776771e-08,
      "learning_rate": 0.0392617142132738,
      "loss": 0.0,
      "num_input_tokens_seen": 8560768,
      "step": 30575
    },
    {
      "epoch": 339.77777777777777,
      "grad_norm": 8.250643190876872e-08,
      "learning_rate": 0.03922199015910504,
      "loss": 0.0,
      "num_input_tokens_seen": 8562208,
      "step": 30580
    },
    {
      "epoch": 339.8333333333333,
      "grad_norm": 8.14341944987973e-08,
      "learning_rate": 0.039182283188297556,
      "loss": 0.0,
      "num_input_tokens_seen": 8563584,
      "step": 30585
    },
    {
      "epoch": 339.8888888888889,
      "grad_norm": 4.5104140866669695e-08,
      "learning_rate": 0.039142593306974595,
      "loss": 0.0,
      "num_input_tokens_seen": 8564976,
      "step": 30590
    },
    {
      "epoch": 339.94444444444446,
      "grad_norm": 3.553936167577376e-08,
      "learning_rate": 0.039102920521256856,
      "loss": 0.0,
      "num_input_tokens_seen": 8566400,
      "step": 30595
    },
    {
      "epoch": 340.0,
      "grad_norm": 5.019966309305346e-08,
      "learning_rate": 0.03906326483726243,
      "loss": 0.0,
      "num_input_tokens_seen": 8567792,
      "step": 30600
    },
    {
      "epoch": 340.0,
      "eval_loss": 1.683437705039978,
      "eval_runtime": 1.1832,
      "eval_samples_per_second": 33.805,
      "eval_steps_per_second": 16.903,
      "num_input_tokens_seen": 8567792,
      "step": 30600
    },
    {
      "epoch": 340.05555555555554,
      "grad_norm": 5.066416264298823e-08,
      "learning_rate": 0.039023626261106704,
      "loss": 0.0,
      "num_input_tokens_seen": 8569168,
      "step": 30605
    },
    {
      "epoch": 340.1111111111111,
      "grad_norm": 3.3357846263015745e-08,
      "learning_rate": 0.03898400479890237,
      "loss": 0.0,
      "num_input_tokens_seen": 8570576,
      "step": 30610
    },
    {
      "epoch": 340.1666666666667,
      "grad_norm": 5.0335412282720426e-08,
      "learning_rate": 0.038944400456759655,
      "loss": 0.0,
      "num_input_tokens_seen": 8572000,
      "step": 30615
    },
    {
      "epoch": 340.22222222222223,
      "grad_norm": 9.633645703388538e-08,
      "learning_rate": 0.038904813240785964,
      "loss": 0.0,
      "num_input_tokens_seen": 8573408,
      "step": 30620
    },
    {
      "epoch": 340.27777777777777,
      "grad_norm": 4.7558017968185595e-08,
      "learning_rate": 0.03886524315708621,
      "loss": 0.0,
      "num_input_tokens_seen": 8574816,
      "step": 30625
    },
    {
      "epoch": 340.3333333333333,
      "grad_norm": 2.4070291715361236e-07,
      "learning_rate": 0.03882569021176255,
      "loss": 0.0,
      "num_input_tokens_seen": 8576208,
      "step": 30630
    },
    {
      "epoch": 340.3888888888889,
      "grad_norm": 1.717729247729949e-08,
      "learning_rate": 0.038786154410914535,
      "loss": 0.0,
      "num_input_tokens_seen": 8577632,
      "step": 30635
    },
    {
      "epoch": 340.44444444444446,
      "grad_norm": 2.4158927303119526e-08,
      "learning_rate": 0.03874663576063917,
      "loss": 0.0,
      "num_input_tokens_seen": 8579056,
      "step": 30640
    },
    {
      "epoch": 340.5,
      "grad_norm": 3.0267976569575694e-08,
      "learning_rate": 0.038707134267030624,
      "loss": 0.0,
      "num_input_tokens_seen": 8580416,
      "step": 30645
    },
    {
      "epoch": 340.55555555555554,
      "grad_norm": 2.9794964717666517e-08,
      "learning_rate": 0.038667649936180555,
      "loss": 0.0,
      "num_input_tokens_seen": 8581824,
      "step": 30650
    },
    {
      "epoch": 340.6111111111111,
      "grad_norm": 4.976530831868331e-08,
      "learning_rate": 0.038628182774178,
      "loss": 0.0,
      "num_input_tokens_seen": 8583200,
      "step": 30655
    },
    {
      "epoch": 340.6666666666667,
      "grad_norm": 7.70519008597148e-08,
      "learning_rate": 0.038588732787109226,
      "loss": 0.0,
      "num_input_tokens_seen": 8584560,
      "step": 30660
    },
    {
      "epoch": 340.72222222222223,
      "grad_norm": 6.101221572407667e-08,
      "learning_rate": 0.03854929998105795,
      "loss": 0.0,
      "num_input_tokens_seen": 8585936,
      "step": 30665
    },
    {
      "epoch": 340.77777777777777,
      "grad_norm": 3.0882347346050665e-08,
      "learning_rate": 0.03850988436210518,
      "loss": 0.0,
      "num_input_tokens_seen": 8587328,
      "step": 30670
    },
    {
      "epoch": 340.8333333333333,
      "grad_norm": 2.2567602897538563e-08,
      "learning_rate": 0.03847048593632933,
      "loss": 0.0,
      "num_input_tokens_seen": 8588688,
      "step": 30675
    },
    {
      "epoch": 340.8888888888889,
      "grad_norm": 5.4084356548855794e-08,
      "learning_rate": 0.038431104709806096,
      "loss": 0.0,
      "num_input_tokens_seen": 8590128,
      "step": 30680
    },
    {
      "epoch": 340.94444444444446,
      "grad_norm": 3.28846283537132e-08,
      "learning_rate": 0.0383917406886086,
      "loss": 0.0,
      "num_input_tokens_seen": 8591504,
      "step": 30685
    },
    {
      "epoch": 341.0,
      "grad_norm": 2.4725919089974013e-08,
      "learning_rate": 0.03835239387880722,
      "loss": 0.0,
      "num_input_tokens_seen": 8592944,
      "step": 30690
    },
    {
      "epoch": 341.05555555555554,
      "grad_norm": 8.440170518042578e-08,
      "learning_rate": 0.03831306428646979,
      "loss": 0.0,
      "num_input_tokens_seen": 8594352,
      "step": 30695
    },
    {
      "epoch": 341.1111111111111,
      "grad_norm": 2.8795534845471593e-08,
      "learning_rate": 0.03827375191766135,
      "loss": 0.0,
      "num_input_tokens_seen": 8595776,
      "step": 30700
    },
    {
      "epoch": 341.1666666666667,
      "grad_norm": 6.967797361312478e-08,
      "learning_rate": 0.03823445677844446,
      "loss": 0.0,
      "num_input_tokens_seen": 8597152,
      "step": 30705
    },
    {
      "epoch": 341.22222222222223,
      "grad_norm": 2.564411829553137e-07,
      "learning_rate": 0.03819517887487881,
      "loss": 0.0,
      "num_input_tokens_seen": 8598608,
      "step": 30710
    },
    {
      "epoch": 341.27777777777777,
      "grad_norm": 2.9086438146919136e-08,
      "learning_rate": 0.03815591821302161,
      "loss": 0.0,
      "num_input_tokens_seen": 8600016,
      "step": 30715
    },
    {
      "epoch": 341.3333333333333,
      "grad_norm": 2.0483737372956057e-08,
      "learning_rate": 0.03811667479892739,
      "loss": 0.0,
      "num_input_tokens_seen": 8601424,
      "step": 30720
    },
    {
      "epoch": 341.3888888888889,
      "grad_norm": 3.977609353000844e-08,
      "learning_rate": 0.03807744863864788,
      "loss": 0.0,
      "num_input_tokens_seen": 8602848,
      "step": 30725
    },
    {
      "epoch": 341.44444444444446,
      "grad_norm": 3.110335100586781e-08,
      "learning_rate": 0.03803823973823229,
      "loss": 0.0,
      "num_input_tokens_seen": 8604256,
      "step": 30730
    },
    {
      "epoch": 341.5,
      "grad_norm": 2.6281416154461112e-08,
      "learning_rate": 0.03799904810372719,
      "loss": 0.0,
      "num_input_tokens_seen": 8605616,
      "step": 30735
    },
    {
      "epoch": 341.55555555555554,
      "grad_norm": 6.122773044126006e-08,
      "learning_rate": 0.03795987374117632,
      "loss": 0.0,
      "num_input_tokens_seen": 8606976,
      "step": 30740
    },
    {
      "epoch": 341.6111111111111,
      "grad_norm": 9.973726378120773e-08,
      "learning_rate": 0.03792071665662093,
      "loss": 0.0,
      "num_input_tokens_seen": 8608400,
      "step": 30745
    },
    {
      "epoch": 341.6666666666667,
      "grad_norm": 3.220997513153634e-08,
      "learning_rate": 0.03788157685609952,
      "loss": 0.0,
      "num_input_tokens_seen": 8609792,
      "step": 30750
    },
    {
      "epoch": 341.72222222222223,
      "grad_norm": 4.829811217632596e-08,
      "learning_rate": 0.037842454345647876,
      "loss": 0.0,
      "num_input_tokens_seen": 8611200,
      "step": 30755
    },
    {
      "epoch": 341.77777777777777,
      "grad_norm": 5.978072437073934e-08,
      "learning_rate": 0.03780334913129929,
      "loss": 0.0,
      "num_input_tokens_seen": 8612592,
      "step": 30760
    },
    {
      "epoch": 341.8333333333333,
      "grad_norm": 9.70426228263932e-08,
      "learning_rate": 0.037764261219084175,
      "loss": 0.0,
      "num_input_tokens_seen": 8613984,
      "step": 30765
    },
    {
      "epoch": 341.8888888888889,
      "grad_norm": 7.679768287971456e-08,
      "learning_rate": 0.037725190615030414,
      "loss": 0.0,
      "num_input_tokens_seen": 8615376,
      "step": 30770
    },
    {
      "epoch": 341.94444444444446,
      "grad_norm": 6.288959752964729e-08,
      "learning_rate": 0.037686137325163224,
      "loss": 0.0,
      "num_input_tokens_seen": 8616752,
      "step": 30775
    },
    {
      "epoch": 342.0,
      "grad_norm": 1.7078993153063493e-07,
      "learning_rate": 0.037647101355505065,
      "loss": 0.0,
      "num_input_tokens_seen": 8618160,
      "step": 30780
    },
    {
      "epoch": 342.05555555555554,
      "grad_norm": 4.412240528495204e-08,
      "learning_rate": 0.03760808271207581,
      "loss": 0.0,
      "num_input_tokens_seen": 8619568,
      "step": 30785
    },
    {
      "epoch": 342.1111111111111,
      "grad_norm": 7.919554434465681e-08,
      "learning_rate": 0.03756908140089258,
      "loss": 0.0,
      "num_input_tokens_seen": 8620928,
      "step": 30790
    },
    {
      "epoch": 342.1666666666667,
      "grad_norm": 2.6982982603840355e-07,
      "learning_rate": 0.03753009742796989,
      "loss": 0.0,
      "num_input_tokens_seen": 8622320,
      "step": 30795
    },
    {
      "epoch": 342.22222222222223,
      "grad_norm": 7.941775947983842e-08,
      "learning_rate": 0.037491130799319615,
      "loss": 0.0,
      "num_input_tokens_seen": 8623728,
      "step": 30800
    },
    {
      "epoch": 342.22222222222223,
      "eval_loss": 1.6585677862167358,
      "eval_runtime": 1.1852,
      "eval_samples_per_second": 33.749,
      "eval_steps_per_second": 16.875,
      "num_input_tokens_seen": 8623728,
      "step": 30800
    },
    {
      "epoch": 342.27777777777777,
      "grad_norm": 6.18006978925223e-08,
      "learning_rate": 0.03745218152095079,
      "loss": 0.0,
      "num_input_tokens_seen": 8625088,
      "step": 30805
    },
    {
      "epoch": 342.3333333333333,
      "grad_norm": 7.121984424429684e-08,
      "learning_rate": 0.037413249598869935,
      "loss": 0.0,
      "num_input_tokens_seen": 8626528,
      "step": 30810
    },
    {
      "epoch": 342.3888888888889,
      "grad_norm": 9.02606842601017e-08,
      "learning_rate": 0.037374335039080886,
      "loss": 0.0,
      "num_input_tokens_seen": 8627920,
      "step": 30815
    },
    {
      "epoch": 342.44444444444446,
      "grad_norm": 2.1393734783714535e-08,
      "learning_rate": 0.037335437847584724,
      "loss": 0.0,
      "num_input_tokens_seen": 8629312,
      "step": 30820
    },
    {
      "epoch": 342.5,
      "grad_norm": 2.827180445308386e-08,
      "learning_rate": 0.03729655803037983,
      "loss": 0.0,
      "num_input_tokens_seen": 8630736,
      "step": 30825
    },
    {
      "epoch": 342.55555555555554,
      "grad_norm": 4.3855791886926454e-08,
      "learning_rate": 0.03725769559346207,
      "loss": 0.0,
      "num_input_tokens_seen": 8632112,
      "step": 30830
    },
    {
      "epoch": 342.6111111111111,
      "grad_norm": 4.116942164955617e-08,
      "learning_rate": 0.03721885054282439,
      "loss": 0.0,
      "num_input_tokens_seen": 8633536,
      "step": 30835
    },
    {
      "epoch": 342.6666666666667,
      "grad_norm": 1.1190086013357359e-07,
      "learning_rate": 0.03718002288445731,
      "loss": 0.0,
      "num_input_tokens_seen": 8634976,
      "step": 30840
    },
    {
      "epoch": 342.72222222222223,
      "grad_norm": 4.058558999986417e-08,
      "learning_rate": 0.03714121262434844,
      "loss": 0.0,
      "num_input_tokens_seen": 8636400,
      "step": 30845
    },
    {
      "epoch": 342.77777777777777,
      "grad_norm": 1.8272689317200275e-07,
      "learning_rate": 0.037102419768482844,
      "loss": 0.0,
      "num_input_tokens_seen": 8637792,
      "step": 30850
    },
    {
      "epoch": 342.8333333333333,
      "grad_norm": 5.468032426847458e-08,
      "learning_rate": 0.03706364432284293,
      "loss": 0.0,
      "num_input_tokens_seen": 8639168,
      "step": 30855
    },
    {
      "epoch": 342.8888888888889,
      "grad_norm": 1.2515444325345015e-07,
      "learning_rate": 0.03702488629340828,
      "loss": 0.0,
      "num_input_tokens_seen": 8640608,
      "step": 30860
    },
    {
      "epoch": 342.94444444444446,
      "grad_norm": 3.039830787088249e-08,
      "learning_rate": 0.036986145686155915,
      "loss": 0.0,
      "num_input_tokens_seen": 8642016,
      "step": 30865
    },
    {
      "epoch": 343.0,
      "grad_norm": 7.232964094328054e-08,
      "learning_rate": 0.036947422507060075,
      "loss": 0.0,
      "num_input_tokens_seen": 8643456,
      "step": 30870
    },
    {
      "epoch": 343.05555555555554,
      "grad_norm": 5.844530903686973e-08,
      "learning_rate": 0.0369087167620924,
      "loss": 0.0,
      "num_input_tokens_seen": 8644880,
      "step": 30875
    },
    {
      "epoch": 343.1111111111111,
      "grad_norm": 4.3706634755835694e-08,
      "learning_rate": 0.03687002845722183,
      "loss": 0.0,
      "num_input_tokens_seen": 8646304,
      "step": 30880
    },
    {
      "epoch": 343.1666666666667,
      "grad_norm": 4.5914081425735276e-08,
      "learning_rate": 0.03683135759841451,
      "loss": 0.0,
      "num_input_tokens_seen": 8647712,
      "step": 30885
    },
    {
      "epoch": 343.22222222222223,
      "grad_norm": 3.794135494672446e-08,
      "learning_rate": 0.03679270419163406,
      "loss": 0.0,
      "num_input_tokens_seen": 8649104,
      "step": 30890
    },
    {
      "epoch": 343.27777777777777,
      "grad_norm": 3.2258327564704814e-08,
      "learning_rate": 0.03675406824284127,
      "loss": 0.0,
      "num_input_tokens_seen": 8650512,
      "step": 30895
    },
    {
      "epoch": 343.3333333333333,
      "grad_norm": 4.330369662852718e-08,
      "learning_rate": 0.03671544975799425,
      "loss": 0.0,
      "num_input_tokens_seen": 8651888,
      "step": 30900
    },
    {
      "epoch": 343.3888888888889,
      "grad_norm": 1.9739832168852445e-07,
      "learning_rate": 0.03667684874304854,
      "loss": 0.0,
      "num_input_tokens_seen": 8653296,
      "step": 30905
    },
    {
      "epoch": 343.44444444444446,
      "grad_norm": 3.975947393541901e-08,
      "learning_rate": 0.03663826520395683,
      "loss": 0.0,
      "num_input_tokens_seen": 8654704,
      "step": 30910
    },
    {
      "epoch": 343.5,
      "grad_norm": 4.941006892522637e-08,
      "learning_rate": 0.03659969914666922,
      "loss": 0.0,
      "num_input_tokens_seen": 8656064,
      "step": 30915
    },
    {
      "epoch": 343.55555555555554,
      "grad_norm": 4.5183078611898964e-08,
      "learning_rate": 0.036561150577133106,
      "loss": 0.0,
      "num_input_tokens_seen": 8657424,
      "step": 30920
    },
    {
      "epoch": 343.6111111111111,
      "grad_norm": 8.194636080816053e-08,
      "learning_rate": 0.036522619501293103,
      "loss": 0.0,
      "num_input_tokens_seen": 8658864,
      "step": 30925
    },
    {
      "epoch": 343.6666666666667,
      "grad_norm": 1.3621311722999963e-07,
      "learning_rate": 0.03648410592509122,
      "loss": 0.0,
      "num_input_tokens_seen": 8660272,
      "step": 30930
    },
    {
      "epoch": 343.72222222222223,
      "grad_norm": 3.7697372334832835e-08,
      "learning_rate": 0.03644560985446676,
      "loss": 0.0,
      "num_input_tokens_seen": 8661664,
      "step": 30935
    },
    {
      "epoch": 343.77777777777777,
      "grad_norm": 3.019745875576518e-08,
      "learning_rate": 0.036407131295356256,
      "loss": 0.0,
      "num_input_tokens_seen": 8663120,
      "step": 30940
    },
    {
      "epoch": 343.8333333333333,
      "grad_norm": 5.190279850353363e-08,
      "learning_rate": 0.03636867025369362,
      "loss": 0.0,
      "num_input_tokens_seen": 8664528,
      "step": 30945
    },
    {
      "epoch": 343.8888888888889,
      "grad_norm": 4.7374058453897305e-08,
      "learning_rate": 0.03633022673540999,
      "loss": 0.0,
      "num_input_tokens_seen": 8665968,
      "step": 30950
    },
    {
      "epoch": 343.94444444444446,
      "grad_norm": 4.6444988299754186e-08,
      "learning_rate": 0.03629180074643385,
      "loss": 0.0,
      "num_input_tokens_seen": 8667360,
      "step": 30955
    },
    {
      "epoch": 344.0,
      "grad_norm": 2.6683508735914074e-08,
      "learning_rate": 0.03625339229269102,
      "loss": 0.0,
      "num_input_tokens_seen": 8668736,
      "step": 30960
    },
    {
      "epoch": 344.05555555555554,
      "grad_norm": 3.300420914342794e-08,
      "learning_rate": 0.036215001380104535,
      "loss": 0.0,
      "num_input_tokens_seen": 8670112,
      "step": 30965
    },
    {
      "epoch": 344.1111111111111,
      "grad_norm": 2.741379212523043e-08,
      "learning_rate": 0.03617662801459471,
      "loss": 0.0,
      "num_input_tokens_seen": 8671520,
      "step": 30970
    },
    {
      "epoch": 344.1666666666667,
      "grad_norm": 4.747646897840241e-08,
      "learning_rate": 0.036138272202079276,
      "loss": 0.0,
      "num_input_tokens_seen": 8672896,
      "step": 30975
    },
    {
      "epoch": 344.22222222222223,
      "grad_norm": 3.400421277888199e-08,
      "learning_rate": 0.036099933948473106,
      "loss": 0.0,
      "num_input_tokens_seen": 8674288,
      "step": 30980
    },
    {
      "epoch": 344.27777777777777,
      "grad_norm": 9.644167420219674e-08,
      "learning_rate": 0.03606161325968851,
      "loss": 0.0,
      "num_input_tokens_seen": 8675696,
      "step": 30985
    },
    {
      "epoch": 344.3333333333333,
      "grad_norm": 9.754283780694095e-08,
      "learning_rate": 0.03602331014163496,
      "loss": 0.0,
      "num_input_tokens_seen": 8677120,
      "step": 30990
    },
    {
      "epoch": 344.3888888888889,
      "grad_norm": 6.269359431598787e-08,
      "learning_rate": 0.035985024600219295,
      "loss": 0.0,
      "num_input_tokens_seen": 8678512,
      "step": 30995
    },
    {
      "epoch": 344.44444444444446,
      "grad_norm": 3.3620466410866356e-08,
      "learning_rate": 0.03594675664134569,
      "loss": 0.0,
      "num_input_tokens_seen": 8679920,
      "step": 31000
    },
    {
      "epoch": 344.44444444444446,
      "eval_loss": 1.6678470373153687,
      "eval_runtime": 1.1844,
      "eval_samples_per_second": 33.772,
      "eval_steps_per_second": 16.886,
      "num_input_tokens_seen": 8679920,
      "step": 31000
    },
    {
      "epoch": 344.5,
      "grad_norm": 3.1315575910184634e-08,
      "learning_rate": 0.03590850627091545,
      "loss": 0.0,
      "num_input_tokens_seen": 8681360,
      "step": 31005
    },
    {
      "epoch": 344.55555555555554,
      "grad_norm": 2.3148736261191516e-08,
      "learning_rate": 0.03587027349482731,
      "loss": 0.0,
      "num_input_tokens_seen": 8682736,
      "step": 31010
    },
    {
      "epoch": 344.6111111111111,
      "grad_norm": 3.104626244976316e-08,
      "learning_rate": 0.035832058318977275,
      "loss": 0.0,
      "num_input_tokens_seen": 8684128,
      "step": 31015
    },
    {
      "epoch": 344.6666666666667,
      "grad_norm": 3.887041089001286e-08,
      "learning_rate": 0.03579386074925853,
      "loss": 0.0,
      "num_input_tokens_seen": 8685536,
      "step": 31020
    },
    {
      "epoch": 344.72222222222223,
      "grad_norm": 3.886085409021689e-08,
      "learning_rate": 0.035755680791561696,
      "loss": 0.0,
      "num_input_tokens_seen": 8686912,
      "step": 31025
    },
    {
      "epoch": 344.77777777777777,
      "grad_norm": 2.4327400538481925e-08,
      "learning_rate": 0.03571751845177454,
      "loss": 0.0,
      "num_input_tokens_seen": 8688336,
      "step": 31030
    },
    {
      "epoch": 344.8333333333333,
      "grad_norm": 2.2383556341765143e-08,
      "learning_rate": 0.03567937373578225,
      "loss": 0.0,
      "num_input_tokens_seen": 8689760,
      "step": 31035
    },
    {
      "epoch": 344.8888888888889,
      "grad_norm": 1.373089997258603e-08,
      "learning_rate": 0.03564124664946711,
      "loss": 0.0,
      "num_input_tokens_seen": 8691152,
      "step": 31040
    },
    {
      "epoch": 344.94444444444446,
      "grad_norm": 2.0125751731825403e-08,
      "learning_rate": 0.035603137198708924,
      "loss": 0.0,
      "num_input_tokens_seen": 8692560,
      "step": 31045
    },
    {
      "epoch": 345.0,
      "grad_norm": 4.5163346840126906e-08,
      "learning_rate": 0.035565045389384514,
      "loss": 0.0,
      "num_input_tokens_seen": 8693984,
      "step": 31050
    },
    {
      "epoch": 345.05555555555554,
      "grad_norm": 2.0252693744282624e-08,
      "learning_rate": 0.03552697122736823,
      "loss": 0.0,
      "num_input_tokens_seen": 8695376,
      "step": 31055
    },
    {
      "epoch": 345.1111111111111,
      "grad_norm": 2.4965169487245475e-08,
      "learning_rate": 0.03548891471853153,
      "loss": 0.0,
      "num_input_tokens_seen": 8696784,
      "step": 31060
    },
    {
      "epoch": 345.1666666666667,
      "grad_norm": 1.243361680280941e-08,
      "learning_rate": 0.03545087586874322,
      "loss": 0.0,
      "num_input_tokens_seen": 8698176,
      "step": 31065
    },
    {
      "epoch": 345.22222222222223,
      "grad_norm": 4.710125978135693e-08,
      "learning_rate": 0.03541285468386935,
      "loss": 0.0,
      "num_input_tokens_seen": 8699616,
      "step": 31070
    },
    {
      "epoch": 345.27777777777777,
      "grad_norm": 2.769555251802558e-08,
      "learning_rate": 0.03537485116977327,
      "loss": 0.0,
      "num_input_tokens_seen": 8701040,
      "step": 31075
    },
    {
      "epoch": 345.3333333333333,
      "grad_norm": 2.1294482621669886e-08,
      "learning_rate": 0.03533686533231565,
      "loss": 0.0,
      "num_input_tokens_seen": 8702448,
      "step": 31080
    },
    {
      "epoch": 345.3888888888889,
      "grad_norm": 3.732277065182643e-08,
      "learning_rate": 0.0352988971773543,
      "loss": 0.0,
      "num_input_tokens_seen": 8703840,
      "step": 31085
    },
    {
      "epoch": 345.44444444444446,
      "grad_norm": 3.743970822256415e-08,
      "learning_rate": 0.03526094671074443,
      "loss": 0.0,
      "num_input_tokens_seen": 8705200,
      "step": 31090
    },
    {
      "epoch": 345.5,
      "grad_norm": 4.4616680128228836e-08,
      "learning_rate": 0.03522301393833852,
      "loss": 0.0,
      "num_input_tokens_seen": 8706592,
      "step": 31095
    },
    {
      "epoch": 345.55555555555554,
      "grad_norm": 3.124053904457469e-08,
      "learning_rate": 0.035185098865986204,
      "loss": 0.0,
      "num_input_tokens_seen": 8707984,
      "step": 31100
    },
    {
      "epoch": 345.6111111111111,
      "grad_norm": 2.3576555818749512e-08,
      "learning_rate": 0.03514720149953453,
      "loss": 0.0,
      "num_input_tokens_seen": 8709360,
      "step": 31105
    },
    {
      "epoch": 345.6666666666667,
      "grad_norm": 1.0052976762153776e-07,
      "learning_rate": 0.03510932184482773,
      "loss": 0.0,
      "num_input_tokens_seen": 8710816,
      "step": 31110
    },
    {
      "epoch": 345.72222222222223,
      "grad_norm": 1.9904874193343858e-08,
      "learning_rate": 0.03507145990770724,
      "loss": 0.0,
      "num_input_tokens_seen": 8712224,
      "step": 31115
    },
    {
      "epoch": 345.77777777777777,
      "grad_norm": 6.629894500065348e-08,
      "learning_rate": 0.035033615694011984,
      "loss": 0.0,
      "num_input_tokens_seen": 8713632,
      "step": 31120
    },
    {
      "epoch": 345.8333333333333,
      "grad_norm": 3.526184499946794e-08,
      "learning_rate": 0.03499578920957788,
      "loss": 0.0,
      "num_input_tokens_seen": 8714992,
      "step": 31125
    },
    {
      "epoch": 345.8888888888889,
      "grad_norm": 5.887214626909554e-08,
      "learning_rate": 0.034957980460238375,
      "loss": 0.0,
      "num_input_tokens_seen": 8716400,
      "step": 31130
    },
    {
      "epoch": 345.94444444444446,
      "grad_norm": 3.404324999678465e-08,
      "learning_rate": 0.03492018945182393,
      "loss": 0.0,
      "num_input_tokens_seen": 8717792,
      "step": 31135
    },
    {
      "epoch": 346.0,
      "grad_norm": 1.9329407408008592e-08,
      "learning_rate": 0.03488241619016247,
      "loss": 0.0,
      "num_input_tokens_seen": 8719184,
      "step": 31140
    },
    {
      "epoch": 346.05555555555554,
      "grad_norm": 1.242270712964455e-07,
      "learning_rate": 0.03484466068107913,
      "loss": 0.0,
      "num_input_tokens_seen": 8720608,
      "step": 31145
    },
    {
      "epoch": 346.1111111111111,
      "grad_norm": 8.961161768183956e-08,
      "learning_rate": 0.034806922930396195,
      "loss": 0.0,
      "num_input_tokens_seen": 8722032,
      "step": 31150
    },
    {
      "epoch": 346.1666666666667,
      "grad_norm": 3.125120784375213e-08,
      "learning_rate": 0.03476920294393337,
      "loss": 0.0,
      "num_input_tokens_seen": 8723472,
      "step": 31155
    },
    {
      "epoch": 346.22222222222223,
      "grad_norm": 8.124681016852264e-08,
      "learning_rate": 0.03473150072750755,
      "loss": 0.0,
      "num_input_tokens_seen": 8724880,
      "step": 31160
    },
    {
      "epoch": 346.27777777777777,
      "grad_norm": 5.620178100684825e-08,
      "learning_rate": 0.03469381628693284,
      "loss": 0.0,
      "num_input_tokens_seen": 8726272,
      "step": 31165
    },
    {
      "epoch": 346.3333333333333,
      "grad_norm": 8.582673416412945e-08,
      "learning_rate": 0.03465614962802072,
      "loss": 0.0,
      "num_input_tokens_seen": 8727712,
      "step": 31170
    },
    {
      "epoch": 346.3888888888889,
      "grad_norm": 4.198184555548323e-08,
      "learning_rate": 0.0346185007565798,
      "loss": 0.0,
      "num_input_tokens_seen": 8729088,
      "step": 31175
    },
    {
      "epoch": 346.44444444444446,
      "grad_norm": 2.6764901406295394e-08,
      "learning_rate": 0.03458086967841609,
      "loss": 0.0,
      "num_input_tokens_seen": 8730480,
      "step": 31180
    },
    {
      "epoch": 346.5,
      "grad_norm": 2.003717192167187e-08,
      "learning_rate": 0.03454325639933266,
      "loss": 0.0,
      "num_input_tokens_seen": 8731888,
      "step": 31185
    },
    {
      "epoch": 346.55555555555554,
      "grad_norm": 2.7382116130070244e-08,
      "learning_rate": 0.03450566092513007,
      "loss": 0.0,
      "num_input_tokens_seen": 8733264,
      "step": 31190
    },
    {
      "epoch": 346.6111111111111,
      "grad_norm": 2.131641352320912e-08,
      "learning_rate": 0.034468083261605914,
      "loss": 0.0,
      "num_input_tokens_seen": 8734624,
      "step": 31195
    },
    {
      "epoch": 346.6666666666667,
      "grad_norm": 3.613546084579866e-08,
      "learning_rate": 0.03443052341455522,
      "loss": 0.0,
      "num_input_tokens_seen": 8736032,
      "step": 31200
    },
    {
      "epoch": 346.6666666666667,
      "eval_loss": 1.713171362876892,
      "eval_runtime": 1.1871,
      "eval_samples_per_second": 33.695,
      "eval_steps_per_second": 16.847,
      "num_input_tokens_seen": 8736032,
      "step": 31200
    },
    {
      "epoch": 346.72222222222223,
      "grad_norm": 1.7536978091925448e-08,
      "learning_rate": 0.0343929813897701,
      "loss": 0.0,
      "num_input_tokens_seen": 8737424,
      "step": 31205
    },
    {
      "epoch": 346.77777777777777,
      "grad_norm": 1.66353146369147e-07,
      "learning_rate": 0.034355457193040125,
      "loss": 0.0,
      "num_input_tokens_seen": 8738784,
      "step": 31210
    },
    {
      "epoch": 346.8333333333333,
      "grad_norm": 7.885880393132538e-08,
      "learning_rate": 0.03431795083015186,
      "loss": 0.0,
      "num_input_tokens_seen": 8740208,
      "step": 31215
    },
    {
      "epoch": 346.8888888888889,
      "grad_norm": 9.380856624829903e-08,
      "learning_rate": 0.03428046230688936,
      "loss": 0.0,
      "num_input_tokens_seen": 8741584,
      "step": 31220
    },
    {
      "epoch": 346.94444444444446,
      "grad_norm": 1.5401842290430068e-07,
      "learning_rate": 0.034242991629033805,
      "loss": 0.0,
      "num_input_tokens_seen": 8742976,
      "step": 31225
    },
    {
      "epoch": 347.0,
      "grad_norm": 5.48149579060464e-08,
      "learning_rate": 0.03420553880236362,
      "loss": 0.0,
      "num_input_tokens_seen": 8744368,
      "step": 31230
    },
    {
      "epoch": 347.05555555555554,
      "grad_norm": 2.7637863553309217e-08,
      "learning_rate": 0.03416810383265449,
      "loss": 0.0,
      "num_input_tokens_seen": 8745760,
      "step": 31235
    },
    {
      "epoch": 347.1111111111111,
      "grad_norm": 1.0236514214057024e-07,
      "learning_rate": 0.03413068672567944,
      "loss": 0.0,
      "num_input_tokens_seen": 8747136,
      "step": 31240
    },
    {
      "epoch": 347.1666666666667,
      "grad_norm": 3.75119455497952e-08,
      "learning_rate": 0.034093287487208565,
      "loss": 0.0,
      "num_input_tokens_seen": 8748528,
      "step": 31245
    },
    {
      "epoch": 347.22222222222223,
      "grad_norm": 4.004640530297365e-08,
      "learning_rate": 0.03405590612300937,
      "loss": 0.0,
      "num_input_tokens_seen": 8749952,
      "step": 31250
    },
    {
      "epoch": 347.27777777777777,
      "grad_norm": 3.7290028842562606e-08,
      "learning_rate": 0.03401854263884646,
      "loss": 0.0,
      "num_input_tokens_seen": 8751392,
      "step": 31255
    },
    {
      "epoch": 347.3333333333333,
      "grad_norm": 5.248995904594267e-08,
      "learning_rate": 0.033981197040481824,
      "loss": 0.0,
      "num_input_tokens_seen": 8752816,
      "step": 31260
    },
    {
      "epoch": 347.3888888888889,
      "grad_norm": 5.098356581356711e-08,
      "learning_rate": 0.03394386933367459,
      "loss": 0.0,
      "num_input_tokens_seen": 8754240,
      "step": 31265
    },
    {
      "epoch": 347.44444444444446,
      "grad_norm": 1.9531270822881197e-07,
      "learning_rate": 0.033906559524181104,
      "loss": 0.0,
      "num_input_tokens_seen": 8755616,
      "step": 31270
    },
    {
      "epoch": 347.5,
      "grad_norm": 7.945955360355583e-08,
      "learning_rate": 0.033869267617755085,
      "loss": 0.0,
      "num_input_tokens_seen": 8756944,
      "step": 31275
    },
    {
      "epoch": 347.55555555555554,
      "grad_norm": 6.380199835120948e-08,
      "learning_rate": 0.0338319936201474,
      "loss": 0.0,
      "num_input_tokens_seen": 8758352,
      "step": 31280
    },
    {
      "epoch": 347.6111111111111,
      "grad_norm": 1.0911660908163867e-08,
      "learning_rate": 0.033794737537106136,
      "loss": 0.0,
      "num_input_tokens_seen": 8759808,
      "step": 31285
    },
    {
      "epoch": 347.6666666666667,
      "grad_norm": 4.14117948821513e-08,
      "learning_rate": 0.03375749937437671,
      "loss": 0.0,
      "num_input_tokens_seen": 8761216,
      "step": 31290
    },
    {
      "epoch": 347.72222222222223,
      "grad_norm": 6.605790758840158e-08,
      "learning_rate": 0.033720279137701634,
      "loss": 0.0,
      "num_input_tokens_seen": 8762624,
      "step": 31295
    },
    {
      "epoch": 347.77777777777777,
      "grad_norm": 5.115130008448432e-08,
      "learning_rate": 0.03368307683282078,
      "loss": 0.0,
      "num_input_tokens_seen": 8764032,
      "step": 31300
    },
    {
      "epoch": 347.8333333333333,
      "grad_norm": 7.086340048090278e-08,
      "learning_rate": 0.033645892465471235,
      "loss": 0.0,
      "num_input_tokens_seen": 8765440,
      "step": 31305
    },
    {
      "epoch": 347.8888888888889,
      "grad_norm": 2.9478206542421503e-08,
      "learning_rate": 0.03360872604138724,
      "loss": 0.0,
      "num_input_tokens_seen": 8766816,
      "step": 31310
    },
    {
      "epoch": 347.94444444444446,
      "grad_norm": 4.241037743213383e-08,
      "learning_rate": 0.03357157756630034,
      "loss": 0.0,
      "num_input_tokens_seen": 8768176,
      "step": 31315
    },
    {
      "epoch": 348.0,
      "grad_norm": 3.114050883823438e-08,
      "learning_rate": 0.033534447045939365,
      "loss": 0.0,
      "num_input_tokens_seen": 8769584,
      "step": 31320
    },
    {
      "epoch": 348.05555555555554,
      "grad_norm": 1.8878614582718e-07,
      "learning_rate": 0.03349733448603026,
      "loss": 0.0,
      "num_input_tokens_seen": 8770928,
      "step": 31325
    },
    {
      "epoch": 348.1111111111111,
      "grad_norm": 8.076574431470362e-08,
      "learning_rate": 0.03346023989229619,
      "loss": 0.0,
      "num_input_tokens_seen": 8772336,
      "step": 31330
    },
    {
      "epoch": 348.1666666666667,
      "grad_norm": 2.7468900043459143e-08,
      "learning_rate": 0.03342316327045769,
      "loss": 0.0,
      "num_input_tokens_seen": 8773728,
      "step": 31335
    },
    {
      "epoch": 348.22222222222223,
      "grad_norm": 1.478207991567615e-07,
      "learning_rate": 0.033386104626232385,
      "loss": 0.0,
      "num_input_tokens_seen": 8775168,
      "step": 31340
    },
    {
      "epoch": 348.27777777777777,
      "grad_norm": 3.277322235817337e-08,
      "learning_rate": 0.03334906396533525,
      "loss": 0.0,
      "num_input_tokens_seen": 8776592,
      "step": 31345
    },
    {
      "epoch": 348.3333333333333,
      "grad_norm": 2.5374619738727233e-08,
      "learning_rate": 0.033312041293478326,
      "loss": 0.0,
      "num_input_tokens_seen": 8777952,
      "step": 31350
    },
    {
      "epoch": 348.3888888888889,
      "grad_norm": 3.509829582526436e-08,
      "learning_rate": 0.03327503661637103,
      "loss": 0.0,
      "num_input_tokens_seen": 8779360,
      "step": 31355
    },
    {
      "epoch": 348.44444444444446,
      "grad_norm": 2.799256115793014e-08,
      "learning_rate": 0.03323804993971998,
      "loss": 0.0,
      "num_input_tokens_seen": 8780768,
      "step": 31360
    },
    {
      "epoch": 348.5,
      "grad_norm": 5.2297984609595005e-08,
      "learning_rate": 0.033201081269228924,
      "loss": 0.0,
      "num_input_tokens_seen": 8782160,
      "step": 31365
    },
    {
      "epoch": 348.55555555555554,
      "grad_norm": 5.981260642329289e-08,
      "learning_rate": 0.03316413061059895,
      "loss": 0.0,
      "num_input_tokens_seen": 8783584,
      "step": 31370
    },
    {
      "epoch": 348.6111111111111,
      "grad_norm": 3.313130392257335e-08,
      "learning_rate": 0.03312719796952827,
      "loss": 0.0,
      "num_input_tokens_seen": 8784960,
      "step": 31375
    },
    {
      "epoch": 348.6666666666667,
      "grad_norm": 3.2386516579663294e-08,
      "learning_rate": 0.03309028335171236,
      "loss": 0.0,
      "num_input_tokens_seen": 8786384,
      "step": 31380
    },
    {
      "epoch": 348.72222222222223,
      "grad_norm": 2.5969587369445435e-08,
      "learning_rate": 0.03305338676284398,
      "loss": 0.0,
      "num_input_tokens_seen": 8787776,
      "step": 31385
    },
    {
      "epoch": 348.77777777777777,
      "grad_norm": 5.6376073587216524e-08,
      "learning_rate": 0.03301650820861296,
      "loss": 0.0,
      "num_input_tokens_seen": 8789120,
      "step": 31390
    },
    {
      "epoch": 348.8333333333333,
      "grad_norm": 5.0226958592247684e-08,
      "learning_rate": 0.03297964769470652,
      "loss": 0.0,
      "num_input_tokens_seen": 8790512,
      "step": 31395
    },
    {
      "epoch": 348.8888888888889,
      "grad_norm": 4.4531503817779594e-08,
      "learning_rate": 0.032942805226808945,
      "loss": 0.0,
      "num_input_tokens_seen": 8791888,
      "step": 31400
    },
    {
      "epoch": 348.8888888888889,
      "eval_loss": 1.733190894126892,
      "eval_runtime": 1.1868,
      "eval_samples_per_second": 33.705,
      "eval_steps_per_second": 16.852,
      "num_input_tokens_seen": 8791888,
      "step": 31400
    },
    {
      "epoch": 348.94444444444446,
      "grad_norm": 2.93238446857913e-08,
      "learning_rate": 0.03290598081060187,
      "loss": 0.0,
      "num_input_tokens_seen": 8793312,
      "step": 31405
    },
    {
      "epoch": 349.0,
      "grad_norm": 2.152475531147502e-08,
      "learning_rate": 0.03286917445176407,
      "loss": 0.0,
      "num_input_tokens_seen": 8794656,
      "step": 31410
    },
    {
      "epoch": 349.05555555555554,
      "grad_norm": 2.1383505099947797e-07,
      "learning_rate": 0.032832386155971456,
      "loss": 0.0,
      "num_input_tokens_seen": 8796016,
      "step": 31415
    },
    {
      "epoch": 349.1111111111111,
      "grad_norm": 4.5320202701759627e-08,
      "learning_rate": 0.032795615928897334,
      "loss": 0.0,
      "num_input_tokens_seen": 8797424,
      "step": 31420
    },
    {
      "epoch": 349.1666666666667,
      "grad_norm": 3.663527081698703e-08,
      "learning_rate": 0.03275886377621215,
      "loss": 0.0,
      "num_input_tokens_seen": 8798848,
      "step": 31425
    },
    {
      "epoch": 349.22222222222223,
      "grad_norm": 3.637587653315677e-08,
      "learning_rate": 0.03272212970358348,
      "loss": 0.0,
      "num_input_tokens_seen": 8800256,
      "step": 31430
    },
    {
      "epoch": 349.27777777777777,
      "grad_norm": 6.301878840986319e-08,
      "learning_rate": 0.032685413716676215,
      "loss": 0.0,
      "num_input_tokens_seen": 8801632,
      "step": 31435
    },
    {
      "epoch": 349.3333333333333,
      "grad_norm": 2.97931741499724e-08,
      "learning_rate": 0.032648715821152474,
      "loss": 0.0,
      "num_input_tokens_seen": 8803040,
      "step": 31440
    },
    {
      "epoch": 349.3888888888889,
      "grad_norm": 9.752589136269307e-08,
      "learning_rate": 0.03261203602267143,
      "loss": 0.0,
      "num_input_tokens_seen": 8804432,
      "step": 31445
    },
    {
      "epoch": 349.44444444444446,
      "grad_norm": 3.7817766695980026e-08,
      "learning_rate": 0.03257537432688966,
      "loss": 0.0,
      "num_input_tokens_seen": 8805824,
      "step": 31450
    },
    {
      "epoch": 349.5,
      "grad_norm": 7.866764661912384e-08,
      "learning_rate": 0.03253873073946077,
      "loss": 0.0,
      "num_input_tokens_seen": 8807216,
      "step": 31455
    },
    {
      "epoch": 349.55555555555554,
      "grad_norm": 1.1896056584248527e-08,
      "learning_rate": 0.03250210526603572,
      "loss": 0.0,
      "num_input_tokens_seen": 8808640,
      "step": 31460
    },
    {
      "epoch": 349.6111111111111,
      "grad_norm": 2.9009790125655854e-08,
      "learning_rate": 0.03246549791226266,
      "loss": 0.0,
      "num_input_tokens_seen": 8810048,
      "step": 31465
    },
    {
      "epoch": 349.6666666666667,
      "grad_norm": 5.0567294351822056e-08,
      "learning_rate": 0.03242890868378679,
      "loss": 0.0,
      "num_input_tokens_seen": 8811472,
      "step": 31470
    },
    {
      "epoch": 349.72222222222223,
      "grad_norm": 5.7994707702846426e-08,
      "learning_rate": 0.03239233758625074,
      "loss": 0.0,
      "num_input_tokens_seen": 8812864,
      "step": 31475
    },
    {
      "epoch": 349.77777777777777,
      "grad_norm": 2.233658591421772e-08,
      "learning_rate": 0.032355784625294204,
      "loss": 0.0,
      "num_input_tokens_seen": 8814272,
      "step": 31480
    },
    {
      "epoch": 349.8333333333333,
      "grad_norm": 1.909702973534877e-08,
      "learning_rate": 0.03231924980655402,
      "loss": 0.0,
      "num_input_tokens_seen": 8815680,
      "step": 31485
    },
    {
      "epoch": 349.8888888888889,
      "grad_norm": 3.303250295516591e-08,
      "learning_rate": 0.032282733135664446,
      "loss": 0.0,
      "num_input_tokens_seen": 8817104,
      "step": 31490
    },
    {
      "epoch": 349.94444444444446,
      "grad_norm": 9.97416265136053e-08,
      "learning_rate": 0.03224623461825669,
      "loss": 0.0,
      "num_input_tokens_seen": 8818496,
      "step": 31495
    },
    {
      "epoch": 350.0,
      "grad_norm": 6.013011244476729e-08,
      "learning_rate": 0.03220975425995937,
      "loss": 0.0,
      "num_input_tokens_seen": 8819888,
      "step": 31500
    },
    {
      "epoch": 350.05555555555554,
      "grad_norm": 4.0719235983033286e-08,
      "learning_rate": 0.032173292066398206,
      "loss": 0.0,
      "num_input_tokens_seen": 8821264,
      "step": 31505
    },
    {
      "epoch": 350.1111111111111,
      "grad_norm": 1.3815082411383628e-07,
      "learning_rate": 0.03213684804319606,
      "loss": 0.0,
      "num_input_tokens_seen": 8822640,
      "step": 31510
    },
    {
      "epoch": 350.1666666666667,
      "grad_norm": 1.3482919314355968e-07,
      "learning_rate": 0.03210042219597312,
      "loss": 0.0,
      "num_input_tokens_seen": 8824048,
      "step": 31515
    },
    {
      "epoch": 350.22222222222223,
      "grad_norm": 5.420897863928076e-08,
      "learning_rate": 0.03206401453034675,
      "loss": 0.0,
      "num_input_tokens_seen": 8825456,
      "step": 31520
    },
    {
      "epoch": 350.27777777777777,
      "grad_norm": 5.3484320972074784e-08,
      "learning_rate": 0.03202762505193136,
      "loss": 0.0,
      "num_input_tokens_seen": 8826864,
      "step": 31525
    },
    {
      "epoch": 350.3333333333333,
      "grad_norm": 1.965696583283716e-08,
      "learning_rate": 0.031991253766338754,
      "loss": 0.0,
      "num_input_tokens_seen": 8828256,
      "step": 31530
    },
    {
      "epoch": 350.3888888888889,
      "grad_norm": 3.55653142491974e-08,
      "learning_rate": 0.03195490067917778,
      "loss": 0.0,
      "num_input_tokens_seen": 8829648,
      "step": 31535
    },
    {
      "epoch": 350.44444444444446,
      "grad_norm": 2.2370510777136587e-08,
      "learning_rate": 0.03191856579605461,
      "loss": 0.0,
      "num_input_tokens_seen": 8831024,
      "step": 31540
    },
    {
      "epoch": 350.5,
      "grad_norm": 4.1765687797123974e-08,
      "learning_rate": 0.031882249122572454,
      "loss": 0.0,
      "num_input_tokens_seen": 8832448,
      "step": 31545
    },
    {
      "epoch": 350.55555555555554,
      "grad_norm": 5.406306868849242e-08,
      "learning_rate": 0.03184595066433188,
      "loss": 0.0,
      "num_input_tokens_seen": 8833856,
      "step": 31550
    },
    {
      "epoch": 350.6111111111111,
      "grad_norm": 1.0613105416723556e-07,
      "learning_rate": 0.03180967042693049,
      "loss": 0.0,
      "num_input_tokens_seen": 8835216,
      "step": 31555
    },
    {
      "epoch": 350.6666666666667,
      "grad_norm": 1.5162697764026234e-07,
      "learning_rate": 0.03177340841596323,
      "loss": 0.0,
      "num_input_tokens_seen": 8836592,
      "step": 31560
    },
    {
      "epoch": 350.72222222222223,
      "grad_norm": 4.0973805681687736e-08,
      "learning_rate": 0.03173716463702209,
      "loss": 0.0,
      "num_input_tokens_seen": 8837984,
      "step": 31565
    },
    {
      "epoch": 350.77777777777777,
      "grad_norm": 6.430245491628739e-08,
      "learning_rate": 0.03170093909569638,
      "loss": 0.0,
      "num_input_tokens_seen": 8839360,
      "step": 31570
    },
    {
      "epoch": 350.8333333333333,
      "grad_norm": 0.0001034514862112701,
      "learning_rate": 0.03166473179757246,
      "loss": 0.0,
      "num_input_tokens_seen": 8840752,
      "step": 31575
    },
    {
      "epoch": 350.8888888888889,
      "grad_norm": 1.8207191487817909e-07,
      "learning_rate": 0.031628542748234005,
      "loss": 0.0,
      "num_input_tokens_seen": 8842160,
      "step": 31580
    },
    {
      "epoch": 350.94444444444446,
      "grad_norm": 9.247685284208274e-08,
      "learning_rate": 0.03159237195326184,
      "loss": 0.0,
      "num_input_tokens_seen": 8843568,
      "step": 31585
    },
    {
      "epoch": 351.0,
      "grad_norm": 2.0574387349370227e-07,
      "learning_rate": 0.031556219418233875,
      "loss": 0.0,
      "num_input_tokens_seen": 8844960,
      "step": 31590
    },
    {
      "epoch": 351.05555555555554,
      "grad_norm": 4.131971138576773e-07,
      "learning_rate": 0.03152008514872533,
      "loss": 0.0,
      "num_input_tokens_seen": 8846320,
      "step": 31595
    },
    {
      "epoch": 351.1111111111111,
      "grad_norm": 2.2359071749633586e-07,
      "learning_rate": 0.03148396915030862,
      "loss": 0.0,
      "num_input_tokens_seen": 8847728,
      "step": 31600
    },
    {
      "epoch": 351.1111111111111,
      "eval_loss": 1.601858139038086,
      "eval_runtime": 1.1943,
      "eval_samples_per_second": 33.493,
      "eval_steps_per_second": 16.746,
      "num_input_tokens_seen": 8847728,
      "step": 31600
    },
    {
      "epoch": 351.1666666666667,
      "grad_norm": 1.5485147741856053e-07,
      "learning_rate": 0.03144787142855318,
      "loss": 0.0,
      "num_input_tokens_seen": 8849184,
      "step": 31605
    },
    {
      "epoch": 351.22222222222223,
      "grad_norm": 1.1950228895329928e-07,
      "learning_rate": 0.031411791989025835,
      "loss": 0.0,
      "num_input_tokens_seen": 8850608,
      "step": 31610
    },
    {
      "epoch": 351.27777777777777,
      "grad_norm": 5.7320569624152995e-08,
      "learning_rate": 0.031375730837290394,
      "loss": 0.0,
      "num_input_tokens_seen": 8852000,
      "step": 31615
    },
    {
      "epoch": 351.3333333333333,
      "grad_norm": 1.0355502411130146e-07,
      "learning_rate": 0.031339687978908015,
      "loss": 0.0,
      "num_input_tokens_seen": 8853408,
      "step": 31620
    },
    {
      "epoch": 351.3888888888889,
      "grad_norm": 1.4329903308407665e-07,
      "learning_rate": 0.03130366341943694,
      "loss": 0.0,
      "num_input_tokens_seen": 8854816,
      "step": 31625
    },
    {
      "epoch": 351.44444444444446,
      "grad_norm": 9.588788429937267e-09,
      "learning_rate": 0.031267657164432555,
      "loss": 0.0,
      "num_input_tokens_seen": 8856208,
      "step": 31630
    },
    {
      "epoch": 351.5,
      "grad_norm": 1.8209055596685175e-08,
      "learning_rate": 0.03123166921944752,
      "loss": 0.0,
      "num_input_tokens_seen": 8857632,
      "step": 31635
    },
    {
      "epoch": 351.55555555555554,
      "grad_norm": 8.75532002453383e-09,
      "learning_rate": 0.031195699590031666,
      "loss": 0.0,
      "num_input_tokens_seen": 8859008,
      "step": 31640
    },
    {
      "epoch": 351.6111111111111,
      "grad_norm": 1.4413153337500262e-08,
      "learning_rate": 0.031159748281731885,
      "loss": 0.0,
      "num_input_tokens_seen": 8860384,
      "step": 31645
    },
    {
      "epoch": 351.6666666666667,
      "grad_norm": 6.344144054537537e-08,
      "learning_rate": 0.031123815300092394,
      "loss": 0.0,
      "num_input_tokens_seen": 8861792,
      "step": 31650
    },
    {
      "epoch": 351.72222222222223,
      "grad_norm": 1.8954278147020887e-08,
      "learning_rate": 0.031087900650654424,
      "loss": 0.0,
      "num_input_tokens_seen": 8863184,
      "step": 31655
    },
    {
      "epoch": 351.77777777777777,
      "grad_norm": 1.0892411417273706e-08,
      "learning_rate": 0.031052004338956534,
      "loss": 0.0,
      "num_input_tokens_seen": 8864608,
      "step": 31660
    },
    {
      "epoch": 351.8333333333333,
      "grad_norm": 3.483300758944097e-08,
      "learning_rate": 0.031016126370534407,
      "loss": 0.0,
      "num_input_tokens_seen": 8865984,
      "step": 31665
    },
    {
      "epoch": 351.8888888888889,
      "grad_norm": 6.782395445270595e-08,
      "learning_rate": 0.030980266750920804,
      "loss": 0.0,
      "num_input_tokens_seen": 8867424,
      "step": 31670
    },
    {
      "epoch": 351.94444444444446,
      "grad_norm": 9.822485225186028e-08,
      "learning_rate": 0.030944425485645747,
      "loss": 0.0,
      "num_input_tokens_seen": 8868832,
      "step": 31675
    },
    {
      "epoch": 352.0,
      "grad_norm": 2.7504414745749273e-08,
      "learning_rate": 0.03090860258023647,
      "loss": 0.0,
      "num_input_tokens_seen": 8870240,
      "step": 31680
    },
    {
      "epoch": 352.05555555555554,
      "grad_norm": 1.095829915698232e-08,
      "learning_rate": 0.030872798040217236,
      "loss": 0.0,
      "num_input_tokens_seen": 8871680,
      "step": 31685
    },
    {
      "epoch": 352.1111111111111,
      "grad_norm": 2.0639052422666282e-07,
      "learning_rate": 0.03083701187110964,
      "loss": 0.0,
      "num_input_tokens_seen": 8873056,
      "step": 31690
    },
    {
      "epoch": 352.1666666666667,
      "grad_norm": 4.981565382422559e-08,
      "learning_rate": 0.030801244078432294,
      "loss": 0.0,
      "num_input_tokens_seen": 8874496,
      "step": 31695
    },
    {
      "epoch": 352.22222222222223,
      "grad_norm": 7.213634489744436e-08,
      "learning_rate": 0.030765494667701024,
      "loss": 0.0,
      "num_input_tokens_seen": 8875904,
      "step": 31700
    },
    {
      "epoch": 352.27777777777777,
      "grad_norm": 1.7317402623007183e-08,
      "learning_rate": 0.030729763644428913,
      "loss": 0.0,
      "num_input_tokens_seen": 8877296,
      "step": 31705
    },
    {
      "epoch": 352.3333333333333,
      "grad_norm": 5.9119500406268344e-08,
      "learning_rate": 0.030694051014126048,
      "loss": 0.0,
      "num_input_tokens_seen": 8878720,
      "step": 31710
    },
    {
      "epoch": 352.3888888888889,
      "grad_norm": 7.690645986713207e-08,
      "learning_rate": 0.030658356782299792,
      "loss": 0.0,
      "num_input_tokens_seen": 8880080,
      "step": 31715
    },
    {
      "epoch": 352.44444444444446,
      "grad_norm": 5.3159496360422054e-08,
      "learning_rate": 0.030622680954454726,
      "loss": 0.0,
      "num_input_tokens_seen": 8881488,
      "step": 31720
    },
    {
      "epoch": 352.5,
      "grad_norm": 7.80273623490757e-08,
      "learning_rate": 0.030587023536092398,
      "loss": 0.0,
      "num_input_tokens_seen": 8882912,
      "step": 31725
    },
    {
      "epoch": 352.55555555555554,
      "grad_norm": 1.6871679164864872e-08,
      "learning_rate": 0.03055138453271171,
      "loss": 0.0,
      "num_input_tokens_seen": 8884320,
      "step": 31730
    },
    {
      "epoch": 352.6111111111111,
      "grad_norm": 1.6655880230587172e-08,
      "learning_rate": 0.03051576394980858,
      "loss": 0.0,
      "num_input_tokens_seen": 8885744,
      "step": 31735
    },
    {
      "epoch": 352.6666666666667,
      "grad_norm": 7.47593418282122e-08,
      "learning_rate": 0.030480161792876187,
      "loss": 0.0,
      "num_input_tokens_seen": 8887104,
      "step": 31740
    },
    {
      "epoch": 352.72222222222223,
      "grad_norm": 8.284408714587244e-09,
      "learning_rate": 0.030444578067404846,
      "loss": 0.0,
      "num_input_tokens_seen": 8888512,
      "step": 31745
    },
    {
      "epoch": 352.77777777777777,
      "grad_norm": 2.5103574330387346e-08,
      "learning_rate": 0.030409012778881975,
      "loss": 0.0,
      "num_input_tokens_seen": 8889904,
      "step": 31750
    },
    {
      "epoch": 352.8333333333333,
      "grad_norm": 7.958631087490176e-09,
      "learning_rate": 0.030373465932792235,
      "loss": 0.0,
      "num_input_tokens_seen": 8891328,
      "step": 31755
    },
    {
      "epoch": 352.8888888888889,
      "grad_norm": 8.631658943158982e-09,
      "learning_rate": 0.030337937534617342,
      "loss": 0.0,
      "num_input_tokens_seen": 8892720,
      "step": 31760
    },
    {
      "epoch": 352.94444444444446,
      "grad_norm": 7.219223441268241e-09,
      "learning_rate": 0.030302427589836277,
      "loss": 0.0,
      "num_input_tokens_seen": 8894112,
      "step": 31765
    },
    {
      "epoch": 353.0,
      "grad_norm": 9.920641197425084e-09,
      "learning_rate": 0.030266936103925095,
      "loss": 0.0,
      "num_input_tokens_seen": 8895488,
      "step": 31770
    },
    {
      "epoch": 353.05555555555554,
      "grad_norm": 5.158289351214762e-09,
      "learning_rate": 0.030231463082356982,
      "loss": 0.0,
      "num_input_tokens_seen": 8896928,
      "step": 31775
    },
    {
      "epoch": 353.1111111111111,
      "grad_norm": 3.590529829011757e-08,
      "learning_rate": 0.030196008530602367,
      "loss": 0.0,
      "num_input_tokens_seen": 8898320,
      "step": 31780
    },
    {
      "epoch": 353.1666666666667,
      "grad_norm": 1.4090295152868748e-08,
      "learning_rate": 0.030160572454128842,
      "loss": 0.0,
      "num_input_tokens_seen": 8899744,
      "step": 31785
    },
    {
      "epoch": 353.22222222222223,
      "grad_norm": 1.644757752217174e-08,
      "learning_rate": 0.03012515485840098,
      "loss": 0.0,
      "num_input_tokens_seen": 8901168,
      "step": 31790
    },
    {
      "epoch": 353.27777777777777,
      "grad_norm": 1.441881369856901e-08,
      "learning_rate": 0.030089755748880734,
      "loss": 0.0,
      "num_input_tokens_seen": 8902544,
      "step": 31795
    },
    {
      "epoch": 353.3333333333333,
      "grad_norm": 5.068708119893017e-08,
      "learning_rate": 0.030054375131027003,
      "loss": 0.0,
      "num_input_tokens_seen": 8903952,
      "step": 31800
    },
    {
      "epoch": 353.3333333333333,
      "eval_loss": 1.6741611957550049,
      "eval_runtime": 1.183,
      "eval_samples_per_second": 33.812,
      "eval_steps_per_second": 16.906,
      "num_input_tokens_seen": 8903952,
      "step": 31800
    },
    {
      "epoch": 353.3888888888889,
      "grad_norm": 8.893806580090313e-09,
      "learning_rate": 0.030019013010295942,
      "loss": 0.0,
      "num_input_tokens_seen": 8905344,
      "step": 31805
    },
    {
      "epoch": 353.44444444444446,
      "grad_norm": 5.80244083892012e-08,
      "learning_rate": 0.029983669392140897,
      "loss": 0.0,
      "num_input_tokens_seen": 8906768,
      "step": 31810
    },
    {
      "epoch": 353.5,
      "grad_norm": 5.25336929513287e-09,
      "learning_rate": 0.029948344282012217,
      "loss": 0.0,
      "num_input_tokens_seen": 8908192,
      "step": 31815
    },
    {
      "epoch": 353.55555555555554,
      "grad_norm": 7.907879506774407e-08,
      "learning_rate": 0.029913037685357507,
      "loss": 0.0,
      "num_input_tokens_seen": 8909568,
      "step": 31820
    },
    {
      "epoch": 353.6111111111111,
      "grad_norm": 6.993527090770613e-09,
      "learning_rate": 0.029877749607621528,
      "loss": 0.0,
      "num_input_tokens_seen": 8910960,
      "step": 31825
    },
    {
      "epoch": 353.6666666666667,
      "grad_norm": 7.443456961908623e-09,
      "learning_rate": 0.029842480054246077,
      "loss": 0.0,
      "num_input_tokens_seen": 8912352,
      "step": 31830
    },
    {
      "epoch": 353.72222222222223,
      "grad_norm": 1.6690398396690398e-08,
      "learning_rate": 0.02980722903067022,
      "loss": 0.0,
      "num_input_tokens_seen": 8913728,
      "step": 31835
    },
    {
      "epoch": 353.77777777777777,
      "grad_norm": 1.7186653877843128e-08,
      "learning_rate": 0.029771996542330113,
      "loss": 0.0,
      "num_input_tokens_seen": 8915136,
      "step": 31840
    },
    {
      "epoch": 353.8333333333333,
      "grad_norm": 1.0420384555231976e-08,
      "learning_rate": 0.029736782594658954,
      "loss": 0.0,
      "num_input_tokens_seen": 8916544,
      "step": 31845
    },
    {
      "epoch": 353.8888888888889,
      "grad_norm": 1.876394506439283e-08,
      "learning_rate": 0.029701587193087284,
      "loss": 0.0,
      "num_input_tokens_seen": 8917872,
      "step": 31850
    },
    {
      "epoch": 353.94444444444446,
      "grad_norm": 2.6869946267993328e-08,
      "learning_rate": 0.0296664103430426,
      "loss": 0.0,
      "num_input_tokens_seen": 8919296,
      "step": 31855
    },
    {
      "epoch": 354.0,
      "grad_norm": 2.748084959591779e-08,
      "learning_rate": 0.029631252049949652,
      "loss": 0.0,
      "num_input_tokens_seen": 8920688,
      "step": 31860
    },
    {
      "epoch": 354.05555555555554,
      "grad_norm": 2.110962249446402e-08,
      "learning_rate": 0.02959611231923031,
      "loss": 0.0,
      "num_input_tokens_seen": 8922080,
      "step": 31865
    },
    {
      "epoch": 354.1111111111111,
      "grad_norm": 4.057907787569093e-08,
      "learning_rate": 0.029560991156303507,
      "loss": 0.0,
      "num_input_tokens_seen": 8923472,
      "step": 31870
    },
    {
      "epoch": 354.1666666666667,
      "grad_norm": 5.753756582294045e-09,
      "learning_rate": 0.02952588856658544,
      "loss": 0.0,
      "num_input_tokens_seen": 8924880,
      "step": 31875
    },
    {
      "epoch": 354.22222222222223,
      "grad_norm": 1.0674461492499177e-07,
      "learning_rate": 0.029490804555489296,
      "loss": 0.0,
      "num_input_tokens_seen": 8926272,
      "step": 31880
    },
    {
      "epoch": 354.27777777777777,
      "grad_norm": 2.994010817047865e-09,
      "learning_rate": 0.029455739128425484,
      "loss": 0.0,
      "num_input_tokens_seen": 8927664,
      "step": 31885
    },
    {
      "epoch": 354.3333333333333,
      "grad_norm": 1.2445431352148262e-08,
      "learning_rate": 0.029420692290801607,
      "loss": 0.0,
      "num_input_tokens_seen": 8929056,
      "step": 31890
    },
    {
      "epoch": 354.3888888888889,
      "grad_norm": 1.9142948559647266e-08,
      "learning_rate": 0.02938566404802223,
      "loss": 0.0,
      "num_input_tokens_seen": 8930496,
      "step": 31895
    },
    {
      "epoch": 354.44444444444446,
      "grad_norm": 5.327578822544865e-09,
      "learning_rate": 0.029350654405489195,
      "loss": 0.0,
      "num_input_tokens_seen": 8931888,
      "step": 31900
    },
    {
      "epoch": 354.5,
      "grad_norm": 1.5119859142487257e-08,
      "learning_rate": 0.02931566336860145,
      "loss": 0.0,
      "num_input_tokens_seen": 8933264,
      "step": 31905
    },
    {
      "epoch": 354.55555555555554,
      "grad_norm": 1.8670920809427116e-08,
      "learning_rate": 0.02928069094275505,
      "loss": 0.0,
      "num_input_tokens_seen": 8934640,
      "step": 31910
    },
    {
      "epoch": 354.6111111111111,
      "grad_norm": 9.2634842019379e-09,
      "learning_rate": 0.02924573713334314,
      "loss": 0.0,
      "num_input_tokens_seen": 8936080,
      "step": 31915
    },
    {
      "epoch": 354.6666666666667,
      "grad_norm": 9.46061984308244e-09,
      "learning_rate": 0.02921080194575603,
      "loss": 0.0,
      "num_input_tokens_seen": 8937520,
      "step": 31920
    },
    {
      "epoch": 354.72222222222223,
      "grad_norm": 3.270492499041211e-08,
      "learning_rate": 0.029175885385381177,
      "loss": 0.0,
      "num_input_tokens_seen": 8938896,
      "step": 31925
    },
    {
      "epoch": 354.77777777777777,
      "grad_norm": 9.733930994570983e-09,
      "learning_rate": 0.029140987457603223,
      "loss": 0.0,
      "num_input_tokens_seen": 8940272,
      "step": 31930
    },
    {
      "epoch": 354.8333333333333,
      "grad_norm": 3.2537180061353865e-08,
      "learning_rate": 0.029106108167803763,
      "loss": 0.0,
      "num_input_tokens_seen": 8941680,
      "step": 31935
    },
    {
      "epoch": 354.8888888888889,
      "grad_norm": 2.8504940630114106e-08,
      "learning_rate": 0.029071247521361674,
      "loss": 0.0,
      "num_input_tokens_seen": 8943056,
      "step": 31940
    },
    {
      "epoch": 354.94444444444446,
      "grad_norm": 8.428290954043405e-09,
      "learning_rate": 0.029036405523652945,
      "loss": 0.0,
      "num_input_tokens_seen": 8944496,
      "step": 31945
    },
    {
      "epoch": 355.0,
      "grad_norm": 5.408450931554398e-08,
      "learning_rate": 0.029001582180050577,
      "loss": 0.0,
      "num_input_tokens_seen": 8945936,
      "step": 31950
    },
    {
      "epoch": 355.05555555555554,
      "grad_norm": 1.1792687715228567e-08,
      "learning_rate": 0.02896677749592482,
      "loss": 0.0,
      "num_input_tokens_seen": 8947344,
      "step": 31955
    },
    {
      "epoch": 355.1111111111111,
      "grad_norm": 1.3349480632030009e-08,
      "learning_rate": 0.028931991476642938,
      "loss": 0.0,
      "num_input_tokens_seen": 8948752,
      "step": 31960
    },
    {
      "epoch": 355.1666666666667,
      "grad_norm": 3.521513392001907e-08,
      "learning_rate": 0.028897224127569412,
      "loss": 0.0,
      "num_input_tokens_seen": 8950160,
      "step": 31965
    },
    {
      "epoch": 355.22222222222223,
      "grad_norm": 1.597878096504246e-08,
      "learning_rate": 0.028862475454065832,
      "loss": 0.0,
      "num_input_tokens_seen": 8951568,
      "step": 31970
    },
    {
      "epoch": 355.27777777777777,
      "grad_norm": 3.2064260580000337e-08,
      "learning_rate": 0.028827745461490806,
      "loss": 0.0,
      "num_input_tokens_seen": 8952944,
      "step": 31975
    },
    {
      "epoch": 355.3333333333333,
      "grad_norm": 8.226893832841142e-09,
      "learning_rate": 0.028793034155200212,
      "loss": 0.0,
      "num_input_tokens_seen": 8954368,
      "step": 31980
    },
    {
      "epoch": 355.3888888888889,
      "grad_norm": 7.387294331806515e-09,
      "learning_rate": 0.028758341540546944,
      "loss": 0.0,
      "num_input_tokens_seen": 8955776,
      "step": 31985
    },
    {
      "epoch": 355.44444444444446,
      "grad_norm": 5.79049919124941e-09,
      "learning_rate": 0.02872366762288098,
      "loss": 0.0,
      "num_input_tokens_seen": 8957120,
      "step": 31990
    },
    {
      "epoch": 355.5,
      "grad_norm": 1.4639042866804175e-08,
      "learning_rate": 0.028689012407549567,
      "loss": 0.0,
      "num_input_tokens_seen": 8958512,
      "step": 31995
    },
    {
      "epoch": 355.55555555555554,
      "grad_norm": 9.18641696046052e-09,
      "learning_rate": 0.028654375899896892,
      "loss": 0.0,
      "num_input_tokens_seen": 8959920,
      "step": 32000
    },
    {
      "epoch": 355.55555555555554,
      "eval_loss": 1.701120376586914,
      "eval_runtime": 1.1859,
      "eval_samples_per_second": 33.731,
      "eval_steps_per_second": 16.865,
      "num_input_tokens_seen": 8959920,
      "step": 32000
    },
    {
      "epoch": 355.6111111111111,
      "grad_norm": 1.9968807052350712e-08,
      "learning_rate": 0.02861975810526437,
      "loss": 0.0,
      "num_input_tokens_seen": 8961296,
      "step": 32005
    },
    {
      "epoch": 355.6666666666667,
      "grad_norm": 3.604601772622118e-08,
      "learning_rate": 0.02858515902899056,
      "loss": 0.0,
      "num_input_tokens_seen": 8962688,
      "step": 32010
    },
    {
      "epoch": 355.72222222222223,
      "grad_norm": 5.463058894150663e-09,
      "learning_rate": 0.028550578676410976,
      "loss": 0.0,
      "num_input_tokens_seen": 8964112,
      "step": 32015
    },
    {
      "epoch": 355.77777777777777,
      "grad_norm": 2.679692734375294e-08,
      "learning_rate": 0.02851601705285837,
      "loss": 0.0,
      "num_input_tokens_seen": 8965552,
      "step": 32020
    },
    {
      "epoch": 355.8333333333333,
      "grad_norm": 1.2625165801694038e-08,
      "learning_rate": 0.028481474163662666,
      "loss": 0.0,
      "num_input_tokens_seen": 8966928,
      "step": 32025
    },
    {
      "epoch": 355.8888888888889,
      "grad_norm": 2.3732805942699997e-08,
      "learning_rate": 0.028446950014150683,
      "loss": 0.0,
      "num_input_tokens_seen": 8968304,
      "step": 32030
    },
    {
      "epoch": 355.94444444444446,
      "grad_norm": 9.66578550531949e-09,
      "learning_rate": 0.028412444609646596,
      "loss": 0.0,
      "num_input_tokens_seen": 8969728,
      "step": 32035
    },
    {
      "epoch": 356.0,
      "grad_norm": 8.592256683925825e-09,
      "learning_rate": 0.028377957955471465,
      "loss": 0.0,
      "num_input_tokens_seen": 8971152,
      "step": 32040
    },
    {
      "epoch": 356.05555555555554,
      "grad_norm": 1.771903868075242e-08,
      "learning_rate": 0.0283434900569436,
      "loss": 0.0,
      "num_input_tokens_seen": 8972576,
      "step": 32045
    },
    {
      "epoch": 356.1111111111111,
      "grad_norm": 3.789834224221522e-08,
      "learning_rate": 0.028309040919378456,
      "loss": 0.0,
      "num_input_tokens_seen": 8974016,
      "step": 32050
    },
    {
      "epoch": 356.1666666666667,
      "grad_norm": 7.481805397446806e-09,
      "learning_rate": 0.02827461054808848,
      "loss": 0.0,
      "num_input_tokens_seen": 8975408,
      "step": 32055
    },
    {
      "epoch": 356.22222222222223,
      "grad_norm": 1.078411671073809e-08,
      "learning_rate": 0.028240198948383186,
      "loss": 0.0,
      "num_input_tokens_seen": 8976800,
      "step": 32060
    },
    {
      "epoch": 356.27777777777777,
      "grad_norm": 1.6206529451778806e-08,
      "learning_rate": 0.028205806125569402,
      "loss": 0.0,
      "num_input_tokens_seen": 8978192,
      "step": 32065
    },
    {
      "epoch": 356.3333333333333,
      "grad_norm": 2.6363387917172076e-08,
      "learning_rate": 0.028171432084950834,
      "loss": 0.0,
      "num_input_tokens_seen": 8979568,
      "step": 32070
    },
    {
      "epoch": 356.3888888888889,
      "grad_norm": 7.178777128302727e-09,
      "learning_rate": 0.028137076831828478,
      "loss": 0.0,
      "num_input_tokens_seen": 8980976,
      "step": 32075
    },
    {
      "epoch": 356.44444444444446,
      "grad_norm": 3.423272332270244e-08,
      "learning_rate": 0.028102740371500238,
      "loss": 0.0,
      "num_input_tokens_seen": 8982400,
      "step": 32080
    },
    {
      "epoch": 356.5,
      "grad_norm": 1.6792537138599073e-08,
      "learning_rate": 0.0280684227092613,
      "loss": 0.0,
      "num_input_tokens_seen": 8983792,
      "step": 32085
    },
    {
      "epoch": 356.55555555555554,
      "grad_norm": 1.6265925495417832e-08,
      "learning_rate": 0.02803412385040392,
      "loss": 0.0,
      "num_input_tokens_seen": 8985216,
      "step": 32090
    },
    {
      "epoch": 356.6111111111111,
      "grad_norm": 9.842792358938368e-09,
      "learning_rate": 0.027999843800217306,
      "loss": 0.0,
      "num_input_tokens_seen": 8986624,
      "step": 32095
    },
    {
      "epoch": 356.6666666666667,
      "grad_norm": 2.3645968738605916e-08,
      "learning_rate": 0.027965582563987932,
      "loss": 0.0,
      "num_input_tokens_seen": 8988000,
      "step": 32100
    },
    {
      "epoch": 356.72222222222223,
      "grad_norm": 3.072749521493279e-08,
      "learning_rate": 0.027931340146999346,
      "loss": 0.0,
      "num_input_tokens_seen": 8989344,
      "step": 32105
    },
    {
      "epoch": 356.77777777777777,
      "grad_norm": 2.193280224105365e-08,
      "learning_rate": 0.02789711655453208,
      "loss": 0.0,
      "num_input_tokens_seen": 8990800,
      "step": 32110
    },
    {
      "epoch": 356.8333333333333,
      "grad_norm": 5.0398742956758724e-08,
      "learning_rate": 0.02786291179186392,
      "loss": 0.0,
      "num_input_tokens_seen": 8992176,
      "step": 32115
    },
    {
      "epoch": 356.8888888888889,
      "grad_norm": 7.553959235906405e-09,
      "learning_rate": 0.02782872586426961,
      "loss": 0.0,
      "num_input_tokens_seen": 8993552,
      "step": 32120
    },
    {
      "epoch": 356.94444444444446,
      "grad_norm": 7.63965868344485e-09,
      "learning_rate": 0.027794558777021083,
      "loss": 0.0,
      "num_input_tokens_seen": 8994976,
      "step": 32125
    },
    {
      "epoch": 357.0,
      "grad_norm": 4.587672908229479e-09,
      "learning_rate": 0.02776041053538734,
      "loss": 0.0,
      "num_input_tokens_seen": 8996384,
      "step": 32130
    },
    {
      "epoch": 357.05555555555554,
      "grad_norm": 3.953222105224086e-08,
      "learning_rate": 0.027726281144634407,
      "loss": 0.0,
      "num_input_tokens_seen": 8997824,
      "step": 32135
    },
    {
      "epoch": 357.1111111111111,
      "grad_norm": 1.1593972892853799e-08,
      "learning_rate": 0.02769217061002552,
      "loss": 0.0,
      "num_input_tokens_seen": 8999216,
      "step": 32140
    },
    {
      "epoch": 357.1666666666667,
      "grad_norm": 2.8410465091610604e-08,
      "learning_rate": 0.027658078936820967,
      "loss": 0.0,
      "num_input_tokens_seen": 9000624,
      "step": 32145
    },
    {
      "epoch": 357.22222222222223,
      "grad_norm": 1.6852240491971315e-08,
      "learning_rate": 0.02762400613027805,
      "loss": 0.0,
      "num_input_tokens_seen": 9002080,
      "step": 32150
    },
    {
      "epoch": 357.27777777777777,
      "grad_norm": 2.7198447938303616e-08,
      "learning_rate": 0.027589952195651295,
      "loss": 0.0,
      "num_input_tokens_seen": 9003488,
      "step": 32155
    },
    {
      "epoch": 357.3333333333333,
      "grad_norm": 1.0382060544600336e-08,
      "learning_rate": 0.027555917138192186,
      "loss": 0.0,
      "num_input_tokens_seen": 9004896,
      "step": 32160
    },
    {
      "epoch": 357.3888888888889,
      "grad_norm": 2.041373647898581e-08,
      "learning_rate": 0.027521900963149375,
      "loss": 0.0,
      "num_input_tokens_seen": 9006256,
      "step": 32165
    },
    {
      "epoch": 357.44444444444446,
      "grad_norm": 2.273151622489422e-08,
      "learning_rate": 0.027487903675768633,
      "loss": 0.0,
      "num_input_tokens_seen": 9007680,
      "step": 32170
    },
    {
      "epoch": 357.5,
      "grad_norm": 9.375906273589862e-09,
      "learning_rate": 0.027453925281292677,
      "loss": 0.0,
      "num_input_tokens_seen": 9009120,
      "step": 32175
    },
    {
      "epoch": 357.55555555555554,
      "grad_norm": 2.2653571463138178e-08,
      "learning_rate": 0.027419965784961475,
      "loss": 0.0,
      "num_input_tokens_seen": 9010528,
      "step": 32180
    },
    {
      "epoch": 357.6111111111111,
      "grad_norm": 9.276180712447513e-09,
      "learning_rate": 0.027386025192012015,
      "loss": 0.0,
      "num_input_tokens_seen": 9011920,
      "step": 32185
    },
    {
      "epoch": 357.6666666666667,
      "grad_norm": 9.455981775374767e-09,
      "learning_rate": 0.027352103507678277,
      "loss": 0.0,
      "num_input_tokens_seen": 9013328,
      "step": 32190
    },
    {
      "epoch": 357.72222222222223,
      "grad_norm": 3.2442880382177464e-08,
      "learning_rate": 0.027318200737191527,
      "loss": 0.0,
      "num_input_tokens_seen": 9014704,
      "step": 32195
    },
    {
      "epoch": 357.77777777777777,
      "grad_norm": 1.0316201226601152e-08,
      "learning_rate": 0.027284316885779935,
      "loss": 0.0,
      "num_input_tokens_seen": 9016096,
      "step": 32200
    },
    {
      "epoch": 357.77777777777777,
      "eval_loss": 1.6816489696502686,
      "eval_runtime": 1.185,
      "eval_samples_per_second": 33.756,
      "eval_steps_per_second": 16.878,
      "num_input_tokens_seen": 9016096,
      "step": 32200
    },
    {
      "epoch": 357.8333333333333,
      "grad_norm": 3.572577966792778e-08,
      "learning_rate": 0.027250451958668785,
      "loss": 0.0,
      "num_input_tokens_seen": 9017456,
      "step": 32205
    },
    {
      "epoch": 357.8888888888889,
      "grad_norm": 8.179330990287781e-09,
      "learning_rate": 0.027216605961080536,
      "loss": 0.0,
      "num_input_tokens_seen": 9018848,
      "step": 32210
    },
    {
      "epoch": 357.94444444444446,
      "grad_norm": 2.1005464034828947e-08,
      "learning_rate": 0.02718277889823461,
      "loss": 0.0,
      "num_input_tokens_seen": 9020288,
      "step": 32215
    },
    {
      "epoch": 358.0,
      "grad_norm": 2.272219035148737e-08,
      "learning_rate": 0.027148970775347604,
      "loss": 0.0,
      "num_input_tokens_seen": 9021664,
      "step": 32220
    },
    {
      "epoch": 358.05555555555554,
      "grad_norm": 1.547257433287541e-08,
      "learning_rate": 0.027115181597633174,
      "loss": 0.0,
      "num_input_tokens_seen": 9023088,
      "step": 32225
    },
    {
      "epoch": 358.1111111111111,
      "grad_norm": 7.96211097053856e-09,
      "learning_rate": 0.027081411370301976,
      "loss": 0.0,
      "num_input_tokens_seen": 9024528,
      "step": 32230
    },
    {
      "epoch": 358.1666666666667,
      "grad_norm": 8.895749026294197e-09,
      "learning_rate": 0.027047660098561875,
      "loss": 0.0,
      "num_input_tokens_seen": 9025952,
      "step": 32235
    },
    {
      "epoch": 358.22222222222223,
      "grad_norm": 1.4193595632150391e-08,
      "learning_rate": 0.02701392778761766,
      "loss": 0.0,
      "num_input_tokens_seen": 9027360,
      "step": 32240
    },
    {
      "epoch": 358.27777777777777,
      "grad_norm": 1.0692964735881105e-08,
      "learning_rate": 0.02698021444267133,
      "loss": 0.0,
      "num_input_tokens_seen": 9028768,
      "step": 32245
    },
    {
      "epoch": 358.3333333333333,
      "grad_norm": 8.542593299409873e-09,
      "learning_rate": 0.026946520068921915,
      "loss": 0.0,
      "num_input_tokens_seen": 9030192,
      "step": 32250
    },
    {
      "epoch": 358.3888888888889,
      "grad_norm": 3.402974257937785e-08,
      "learning_rate": 0.02691284467156547,
      "loss": 0.0,
      "num_input_tokens_seen": 9031584,
      "step": 32255
    },
    {
      "epoch": 358.44444444444446,
      "grad_norm": 3.387383173958369e-08,
      "learning_rate": 0.026879188255795182,
      "loss": 0.0,
      "num_input_tokens_seen": 9032976,
      "step": 32260
    },
    {
      "epoch": 358.5,
      "grad_norm": 3.908809276254033e-08,
      "learning_rate": 0.026845550826801328,
      "loss": 0.0,
      "num_input_tokens_seen": 9034400,
      "step": 32265
    },
    {
      "epoch": 358.55555555555554,
      "grad_norm": 1.652378500693885e-08,
      "learning_rate": 0.02681193238977121,
      "loss": 0.0,
      "num_input_tokens_seen": 9035776,
      "step": 32270
    },
    {
      "epoch": 358.6111111111111,
      "grad_norm": 1.0559674912258288e-08,
      "learning_rate": 0.026778332949889145,
      "loss": 0.0,
      "num_input_tokens_seen": 9037168,
      "step": 32275
    },
    {
      "epoch": 358.6666666666667,
      "grad_norm": 2.0444440806954844e-08,
      "learning_rate": 0.026744752512336673,
      "loss": 0.0,
      "num_input_tokens_seen": 9038576,
      "step": 32280
    },
    {
      "epoch": 358.72222222222223,
      "grad_norm": 1.0171484987608892e-08,
      "learning_rate": 0.02671119108229225,
      "loss": 0.0,
      "num_input_tokens_seen": 9039968,
      "step": 32285
    },
    {
      "epoch": 358.77777777777777,
      "grad_norm": 1.8856338712680554e-08,
      "learning_rate": 0.026677648664931556,
      "loss": 0.0,
      "num_input_tokens_seen": 9041328,
      "step": 32290
    },
    {
      "epoch": 358.8333333333333,
      "grad_norm": 8.63288107666449e-09,
      "learning_rate": 0.026644125265427154,
      "loss": 0.0,
      "num_input_tokens_seen": 9042736,
      "step": 32295
    },
    {
      "epoch": 358.8888888888889,
      "grad_norm": 1.0784482640247006e-08,
      "learning_rate": 0.026610620888948822,
      "loss": 0.0,
      "num_input_tokens_seen": 9044176,
      "step": 32300
    },
    {
      "epoch": 358.94444444444446,
      "grad_norm": 2.2434724300524067e-08,
      "learning_rate": 0.026577135540663408,
      "loss": 0.0,
      "num_input_tokens_seen": 9045552,
      "step": 32305
    },
    {
      "epoch": 359.0,
      "grad_norm": 1.497155643903625e-08,
      "learning_rate": 0.026543669225734673,
      "loss": 0.0,
      "num_input_tokens_seen": 9046960,
      "step": 32310
    },
    {
      "epoch": 359.05555555555554,
      "grad_norm": 9.097062658725008e-09,
      "learning_rate": 0.02651022194932363,
      "loss": 0.0,
      "num_input_tokens_seen": 9048384,
      "step": 32315
    },
    {
      "epoch": 359.1111111111111,
      "grad_norm": 3.9822218411700305e-08,
      "learning_rate": 0.026476793716588194,
      "loss": 0.0,
      "num_input_tokens_seen": 9049824,
      "step": 32320
    },
    {
      "epoch": 359.1666666666667,
      "grad_norm": 9.751852658723692e-09,
      "learning_rate": 0.026443384532683467,
      "loss": 0.0,
      "num_input_tokens_seen": 9051232,
      "step": 32325
    },
    {
      "epoch": 359.22222222222223,
      "grad_norm": 1.0641866943217337e-08,
      "learning_rate": 0.026409994402761584,
      "loss": 0.0,
      "num_input_tokens_seen": 9052608,
      "step": 32330
    },
    {
      "epoch": 359.27777777777777,
      "grad_norm": 9.395536793022075e-09,
      "learning_rate": 0.026376623331971653,
      "loss": 0.0,
      "num_input_tokens_seen": 9054064,
      "step": 32335
    },
    {
      "epoch": 359.3333333333333,
      "grad_norm": 1.2149693695562291e-08,
      "learning_rate": 0.026343271325459997,
      "loss": 0.0,
      "num_input_tokens_seen": 9055456,
      "step": 32340
    },
    {
      "epoch": 359.3888888888889,
      "grad_norm": 2.2932356458227332e-08,
      "learning_rate": 0.02630993838836987,
      "loss": 0.0,
      "num_input_tokens_seen": 9056864,
      "step": 32345
    },
    {
      "epoch": 359.44444444444446,
      "grad_norm": 1.994176734854136e-08,
      "learning_rate": 0.026276624525841584,
      "loss": 0.0,
      "num_input_tokens_seen": 9058272,
      "step": 32350
    },
    {
      "epoch": 359.5,
      "grad_norm": 6.987851186579519e-09,
      "learning_rate": 0.026243329743012637,
      "loss": 0.0,
      "num_input_tokens_seen": 9059680,
      "step": 32355
    },
    {
      "epoch": 359.55555555555554,
      "grad_norm": 2.8063031010105988e-08,
      "learning_rate": 0.026210054045017438,
      "loss": 0.0,
      "num_input_tokens_seen": 9061040,
      "step": 32360
    },
    {
      "epoch": 359.6111111111111,
      "grad_norm": 6.952213471578261e-09,
      "learning_rate": 0.02617679743698755,
      "loss": 0.0,
      "num_input_tokens_seen": 9062432,
      "step": 32365
    },
    {
      "epoch": 359.6666666666667,
      "grad_norm": 2.754470784793739e-08,
      "learning_rate": 0.02614355992405158,
      "loss": 0.0,
      "num_input_tokens_seen": 9063808,
      "step": 32370
    },
    {
      "epoch": 359.72222222222223,
      "grad_norm": 3.386934466220737e-08,
      "learning_rate": 0.026110341511335115,
      "loss": 0.0,
      "num_input_tokens_seen": 9065200,
      "step": 32375
    },
    {
      "epoch": 359.77777777777777,
      "grad_norm": 4.2843318226459814e-08,
      "learning_rate": 0.02607714220396093,
      "loss": 0.0,
      "num_input_tokens_seen": 9066576,
      "step": 32380
    },
    {
      "epoch": 359.8333333333333,
      "grad_norm": 6.968511545579759e-09,
      "learning_rate": 0.02604396200704869,
      "loss": 0.0,
      "num_input_tokens_seen": 9067968,
      "step": 32385
    },
    {
      "epoch": 359.8888888888889,
      "grad_norm": 1.208705402433452e-08,
      "learning_rate": 0.02601080092571523,
      "loss": 0.0,
      "num_input_tokens_seen": 9069344,
      "step": 32390
    },
    {
      "epoch": 359.94444444444446,
      "grad_norm": 7.323994566377223e-08,
      "learning_rate": 0.025977658965074455,
      "loss": 0.0,
      "num_input_tokens_seen": 9070784,
      "step": 32395
    },
    {
      "epoch": 360.0,
      "grad_norm": 1.878023070389645e-08,
      "learning_rate": 0.02594453613023719,
      "loss": 0.0,
      "num_input_tokens_seen": 9072192,
      "step": 32400
    },
    {
      "epoch": 360.0,
      "eval_loss": 1.704831838607788,
      "eval_runtime": 1.1906,
      "eval_samples_per_second": 33.596,
      "eval_steps_per_second": 16.798,
      "num_input_tokens_seen": 9072192,
      "step": 32400
    },
    {
      "epoch": 360.05555555555554,
      "grad_norm": 2.1985387732570416e-08,
      "learning_rate": 0.025911432426311443,
      "loss": 0.0,
      "num_input_tokens_seen": 9073584,
      "step": 32405
    },
    {
      "epoch": 360.1111111111111,
      "grad_norm": 9.081412954969892e-09,
      "learning_rate": 0.025878347858402234,
      "loss": 0.0,
      "num_input_tokens_seen": 9075008,
      "step": 32410
    },
    {
      "epoch": 360.1666666666667,
      "grad_norm": 1.7924742579111808e-08,
      "learning_rate": 0.025845282431611598,
      "loss": 0.0,
      "num_input_tokens_seen": 9076400,
      "step": 32415
    },
    {
      "epoch": 360.22222222222223,
      "grad_norm": 1.1666549504241175e-08,
      "learning_rate": 0.025812236151038608,
      "loss": 0.0,
      "num_input_tokens_seen": 9077792,
      "step": 32420
    },
    {
      "epoch": 360.27777777777777,
      "grad_norm": 8.495221415216747e-09,
      "learning_rate": 0.025779209021779468,
      "loss": 0.0,
      "num_input_tokens_seen": 9079200,
      "step": 32425
    },
    {
      "epoch": 360.3333333333333,
      "grad_norm": 4.280820586899381e-09,
      "learning_rate": 0.025746201048927324,
      "loss": 0.0,
      "num_input_tokens_seen": 9080592,
      "step": 32430
    },
    {
      "epoch": 360.3888888888889,
      "grad_norm": 9.33897936761241e-09,
      "learning_rate": 0.025713212237572485,
      "loss": 0.0,
      "num_input_tokens_seen": 9082000,
      "step": 32435
    },
    {
      "epoch": 360.44444444444446,
      "grad_norm": 1.711050323649488e-08,
      "learning_rate": 0.025680242592802164,
      "loss": 0.0,
      "num_input_tokens_seen": 9083360,
      "step": 32440
    },
    {
      "epoch": 360.5,
      "grad_norm": 8.236327175836777e-09,
      "learning_rate": 0.02564729211970073,
      "loss": 0.0,
      "num_input_tokens_seen": 9084736,
      "step": 32445
    },
    {
      "epoch": 360.55555555555554,
      "grad_norm": 8.370170334615068e-09,
      "learning_rate": 0.025614360823349617,
      "loss": 0.0,
      "num_input_tokens_seen": 9086176,
      "step": 32450
    },
    {
      "epoch": 360.6111111111111,
      "grad_norm": 1.0927181826048127e-08,
      "learning_rate": 0.025581448708827146,
      "loss": 0.0,
      "num_input_tokens_seen": 9087584,
      "step": 32455
    },
    {
      "epoch": 360.6666666666667,
      "grad_norm": 1.1908138475291707e-08,
      "learning_rate": 0.025548555781208876,
      "loss": 0.0,
      "num_input_tokens_seen": 9088960,
      "step": 32460
    },
    {
      "epoch": 360.72222222222223,
      "grad_norm": 6.2695879599061755e-09,
      "learning_rate": 0.02551568204556721,
      "loss": 0.0,
      "num_input_tokens_seen": 9090352,
      "step": 32465
    },
    {
      "epoch": 360.77777777777777,
      "grad_norm": 6.928353002422227e-09,
      "learning_rate": 0.02548282750697173,
      "loss": 0.0,
      "num_input_tokens_seen": 9091712,
      "step": 32470
    },
    {
      "epoch": 360.8333333333333,
      "grad_norm": 7.67771624055058e-09,
      "learning_rate": 0.02544999217048909,
      "loss": 0.0,
      "num_input_tokens_seen": 9093120,
      "step": 32475
    },
    {
      "epoch": 360.8888888888889,
      "grad_norm": 7.987534189624057e-09,
      "learning_rate": 0.025417176041182793,
      "loss": 0.0,
      "num_input_tokens_seen": 9094544,
      "step": 32480
    },
    {
      "epoch": 360.94444444444446,
      "grad_norm": 2.0399085087774438e-08,
      "learning_rate": 0.025384379124113596,
      "loss": 0.0,
      "num_input_tokens_seen": 9095968,
      "step": 32485
    },
    {
      "epoch": 361.0,
      "grad_norm": 6.736404323248735e-09,
      "learning_rate": 0.025351601424339124,
      "loss": 0.0,
      "num_input_tokens_seen": 9097424,
      "step": 32490
    },
    {
      "epoch": 361.05555555555554,
      "grad_norm": 9.580264581643405e-09,
      "learning_rate": 0.025318842946914184,
      "loss": 0.0,
      "num_input_tokens_seen": 9098800,
      "step": 32495
    },
    {
      "epoch": 361.1111111111111,
      "grad_norm": 8.235117476829146e-09,
      "learning_rate": 0.025286103696890494,
      "loss": 0.0,
      "num_input_tokens_seen": 9100192,
      "step": 32500
    },
    {
      "epoch": 361.1666666666667,
      "grad_norm": 9.53028500561004e-09,
      "learning_rate": 0.025253383679316836,
      "loss": 0.0,
      "num_input_tokens_seen": 9101568,
      "step": 32505
    },
    {
      "epoch": 361.22222222222223,
      "grad_norm": 7.073247321187637e-09,
      "learning_rate": 0.025220682899239077,
      "loss": 0.0,
      "num_input_tokens_seen": 9103024,
      "step": 32510
    },
    {
      "epoch": 361.27777777777777,
      "grad_norm": 1.0881269218998568e-08,
      "learning_rate": 0.02518800136170013,
      "loss": 0.0,
      "num_input_tokens_seen": 9104432,
      "step": 32515
    },
    {
      "epoch": 361.3333333333333,
      "grad_norm": 7.62629959183414e-09,
      "learning_rate": 0.02515533907173981,
      "loss": 0.0,
      "num_input_tokens_seen": 9105824,
      "step": 32520
    },
    {
      "epoch": 361.3888888888889,
      "grad_norm": 1.1750479700367578e-08,
      "learning_rate": 0.025122696034395115,
      "loss": 0.0,
      "num_input_tokens_seen": 9107232,
      "step": 32525
    },
    {
      "epoch": 361.44444444444446,
      "grad_norm": 1.2862150455816845e-08,
      "learning_rate": 0.025090072254700023,
      "loss": 0.0,
      "num_input_tokens_seen": 9108576,
      "step": 32530
    },
    {
      "epoch": 361.5,
      "grad_norm": 1.1618025652637698e-08,
      "learning_rate": 0.025057467737685468,
      "loss": 0.0,
      "num_input_tokens_seen": 9109968,
      "step": 32535
    },
    {
      "epoch": 361.55555555555554,
      "grad_norm": 5.8316516060585855e-09,
      "learning_rate": 0.025024882488379557,
      "loss": 0.0,
      "num_input_tokens_seen": 9111360,
      "step": 32540
    },
    {
      "epoch": 361.6111111111111,
      "grad_norm": 1.8343543572996168e-08,
      "learning_rate": 0.02499231651180727,
      "loss": 0.0,
      "num_input_tokens_seen": 9112784,
      "step": 32545
    },
    {
      "epoch": 361.6666666666667,
      "grad_norm": 1.1054298809654028e-08,
      "learning_rate": 0.024959769812990713,
      "loss": 0.0,
      "num_input_tokens_seen": 9114208,
      "step": 32550
    },
    {
      "epoch": 361.72222222222223,
      "grad_norm": 1.7904897120502028e-08,
      "learning_rate": 0.024927242396949045,
      "loss": 0.0,
      "num_input_tokens_seen": 9115648,
      "step": 32555
    },
    {
      "epoch": 361.77777777777777,
      "grad_norm": 2.2221456674742512e-08,
      "learning_rate": 0.02489473426869836,
      "loss": 0.0,
      "num_input_tokens_seen": 9117008,
      "step": 32560
    },
    {
      "epoch": 361.8333333333333,
      "grad_norm": 9.562402425444816e-09,
      "learning_rate": 0.024862245433251776,
      "loss": 0.0,
      "num_input_tokens_seen": 9118400,
      "step": 32565
    },
    {
      "epoch": 361.8888888888889,
      "grad_norm": 8.532550666018324e-09,
      "learning_rate": 0.024829775895619577,
      "loss": 0.0,
      "num_input_tokens_seen": 9119808,
      "step": 32570
    },
    {
      "epoch": 361.94444444444446,
      "grad_norm": 2.0793786248418655e-08,
      "learning_rate": 0.024797325660808882,
      "loss": 0.0,
      "num_input_tokens_seen": 9121200,
      "step": 32575
    },
    {
      "epoch": 362.0,
      "grad_norm": 1.0776151526670219e-08,
      "learning_rate": 0.02476489473382401,
      "loss": 0.0,
      "num_input_tokens_seen": 9122624,
      "step": 32580
    },
    {
      "epoch": 362.05555555555554,
      "grad_norm": 1.4203203946294707e-08,
      "learning_rate": 0.024732483119666127,
      "loss": 0.0,
      "num_input_tokens_seen": 9124032,
      "step": 32585
    },
    {
      "epoch": 362.1111111111111,
      "grad_norm": 1.0251644866343668e-08,
      "learning_rate": 0.024700090823333548,
      "loss": 0.0,
      "num_input_tokens_seen": 9125424,
      "step": 32590
    },
    {
      "epoch": 362.1666666666667,
      "grad_norm": 1.9880861401588845e-08,
      "learning_rate": 0.02466771784982163,
      "loss": 0.0,
      "num_input_tokens_seen": 9126832,
      "step": 32595
    },
    {
      "epoch": 362.22222222222223,
      "grad_norm": 1.6657301316058692e-08,
      "learning_rate": 0.024635364204122594,
      "loss": 0.0,
      "num_input_tokens_seen": 9128272,
      "step": 32600
    },
    {
      "epoch": 362.22222222222223,
      "eval_loss": 1.7152143716812134,
      "eval_runtime": 1.1861,
      "eval_samples_per_second": 33.723,
      "eval_steps_per_second": 16.861,
      "num_input_tokens_seen": 9128272,
      "step": 32600
    },
    {
      "epoch": 362.27777777777777,
      "grad_norm": 1.162583984637422e-08,
      "learning_rate": 0.024603029891225852,
      "loss": 0.0,
      "num_input_tokens_seen": 9129664,
      "step": 32605
    },
    {
      "epoch": 362.3333333333333,
      "grad_norm": 5.883828091413079e-09,
      "learning_rate": 0.024570714916117748,
      "loss": 0.0,
      "num_input_tokens_seen": 9131008,
      "step": 32610
    },
    {
      "epoch": 362.3888888888889,
      "grad_norm": 1.0549286777461475e-08,
      "learning_rate": 0.024538419283781625,
      "loss": 0.0,
      "num_input_tokens_seen": 9132368,
      "step": 32615
    },
    {
      "epoch": 362.44444444444446,
      "grad_norm": 1.4039815532385092e-08,
      "learning_rate": 0.024506142999197938,
      "loss": 0.0,
      "num_input_tokens_seen": 9133728,
      "step": 32620
    },
    {
      "epoch": 362.5,
      "grad_norm": 2.3325915421423815e-08,
      "learning_rate": 0.024473886067344002,
      "loss": 0.0,
      "num_input_tokens_seen": 9135152,
      "step": 32625
    },
    {
      "epoch": 362.55555555555554,
      "grad_norm": 1.1038976843735782e-08,
      "learning_rate": 0.02444164849319434,
      "loss": 0.0,
      "num_input_tokens_seen": 9136544,
      "step": 32630
    },
    {
      "epoch": 362.6111111111111,
      "grad_norm": 4.496214245364172e-08,
      "learning_rate": 0.024409430281720306,
      "loss": 0.0,
      "num_input_tokens_seen": 9137952,
      "step": 32635
    },
    {
      "epoch": 362.6666666666667,
      "grad_norm": 9.817012980306572e-09,
      "learning_rate": 0.024377231437890428,
      "loss": 0.0,
      "num_input_tokens_seen": 9139344,
      "step": 32640
    },
    {
      "epoch": 362.72222222222223,
      "grad_norm": 1.6625245180534876e-08,
      "learning_rate": 0.024345051966670115,
      "loss": 0.0,
      "num_input_tokens_seen": 9140704,
      "step": 32645
    },
    {
      "epoch": 362.77777777777777,
      "grad_norm": 9.557844293794915e-09,
      "learning_rate": 0.024312891873021884,
      "loss": 0.0,
      "num_input_tokens_seen": 9142128,
      "step": 32650
    },
    {
      "epoch": 362.8333333333333,
      "grad_norm": 2.1045842402145354e-08,
      "learning_rate": 0.024280751161905183,
      "loss": 0.0,
      "num_input_tokens_seen": 9143520,
      "step": 32655
    },
    {
      "epoch": 362.8888888888889,
      "grad_norm": 2.4009411347947207e-08,
      "learning_rate": 0.02424862983827658,
      "loss": 0.0,
      "num_input_tokens_seen": 9144928,
      "step": 32660
    },
    {
      "epoch": 362.94444444444446,
      "grad_norm": 2.32769750141415e-08,
      "learning_rate": 0.024216527907089495,
      "loss": 0.0,
      "num_input_tokens_seen": 9146336,
      "step": 32665
    },
    {
      "epoch": 363.0,
      "grad_norm": 1.0748441248153995e-08,
      "learning_rate": 0.024184445373294505,
      "loss": 0.0,
      "num_input_tokens_seen": 9147776,
      "step": 32670
    },
    {
      "epoch": 363.05555555555554,
      "grad_norm": 9.668238654114703e-09,
      "learning_rate": 0.02415238224183918,
      "loss": 0.0,
      "num_input_tokens_seen": 9149200,
      "step": 32675
    },
    {
      "epoch": 363.1111111111111,
      "grad_norm": 7.940059276734246e-09,
      "learning_rate": 0.024120338517667973,
      "loss": 0.0,
      "num_input_tokens_seen": 9150576,
      "step": 32680
    },
    {
      "epoch": 363.1666666666667,
      "grad_norm": 2.2566771562537724e-08,
      "learning_rate": 0.02408831420572247,
      "loss": 0.0,
      "num_input_tokens_seen": 9152000,
      "step": 32685
    },
    {
      "epoch": 363.22222222222223,
      "grad_norm": 1.0800743410754876e-08,
      "learning_rate": 0.024056309310941264,
      "loss": 0.0,
      "num_input_tokens_seen": 9153424,
      "step": 32690
    },
    {
      "epoch": 363.27777777777777,
      "grad_norm": 8.69925198543342e-09,
      "learning_rate": 0.02402432383825982,
      "loss": 0.0,
      "num_input_tokens_seen": 9154800,
      "step": 32695
    },
    {
      "epoch": 363.3333333333333,
      "grad_norm": 3.6759242760808775e-08,
      "learning_rate": 0.023992357792610792,
      "loss": 0.0,
      "num_input_tokens_seen": 9156192,
      "step": 32700
    },
    {
      "epoch": 363.3888888888889,
      "grad_norm": 1.9733658263021425e-08,
      "learning_rate": 0.0239604111789237,
      "loss": 0.0,
      "num_input_tokens_seen": 9157600,
      "step": 32705
    },
    {
      "epoch": 363.44444444444446,
      "grad_norm": 2.771337648255212e-08,
      "learning_rate": 0.023928484002125095,
      "loss": 0.0,
      "num_input_tokens_seen": 9159024,
      "step": 32710
    },
    {
      "epoch": 363.5,
      "grad_norm": 1.0225326363411114e-08,
      "learning_rate": 0.023896576267138595,
      "loss": 0.0,
      "num_input_tokens_seen": 9160416,
      "step": 32715
    },
    {
      "epoch": 363.55555555555554,
      "grad_norm": 1.0097393143837508e-08,
      "learning_rate": 0.02386468797888471,
      "loss": 0.0,
      "num_input_tokens_seen": 9161776,
      "step": 32720
    },
    {
      "epoch": 363.6111111111111,
      "grad_norm": 1.1365511198846434e-08,
      "learning_rate": 0.023832819142281057,
      "loss": 0.0,
      "num_input_tokens_seen": 9163168,
      "step": 32725
    },
    {
      "epoch": 363.6666666666667,
      "grad_norm": 1.0345841516823384e-08,
      "learning_rate": 0.02380096976224225,
      "loss": 0.0,
      "num_input_tokens_seen": 9164592,
      "step": 32730
    },
    {
      "epoch": 363.72222222222223,
      "grad_norm": 7.461915529916041e-09,
      "learning_rate": 0.023769139843679777,
      "loss": 0.0,
      "num_input_tokens_seen": 9165952,
      "step": 32735
    },
    {
      "epoch": 363.77777777777777,
      "grad_norm": 9.870078976348395e-09,
      "learning_rate": 0.023737329391502287,
      "loss": 0.0,
      "num_input_tokens_seen": 9167360,
      "step": 32740
    },
    {
      "epoch": 363.8333333333333,
      "grad_norm": 3.600211684329224e-08,
      "learning_rate": 0.023705538410615293,
      "loss": 0.0,
      "num_input_tokens_seen": 9168768,
      "step": 32745
    },
    {
      "epoch": 363.8888888888889,
      "grad_norm": 1.1024748225452186e-08,
      "learning_rate": 0.023673766905921396,
      "loss": 0.0,
      "num_input_tokens_seen": 9170160,
      "step": 32750
    },
    {
      "epoch": 363.94444444444446,
      "grad_norm": 2.6607292369362767e-08,
      "learning_rate": 0.0236420148823202,
      "loss": 0.0,
      "num_input_tokens_seen": 9171600,
      "step": 32755
    },
    {
      "epoch": 364.0,
      "grad_norm": 2.3576632202093606e-08,
      "learning_rate": 0.02361028234470816,
      "loss": 0.0,
      "num_input_tokens_seen": 9172992,
      "step": 32760
    },
    {
      "epoch": 364.05555555555554,
      "grad_norm": 8.8771425765799e-09,
      "learning_rate": 0.023578569297978913,
      "loss": 0.0,
      "num_input_tokens_seen": 9174400,
      "step": 32765
    },
    {
      "epoch": 364.1111111111111,
      "grad_norm": 1.579956432351537e-08,
      "learning_rate": 0.023546875747023025,
      "loss": 0.0,
      "num_input_tokens_seen": 9175872,
      "step": 32770
    },
    {
      "epoch": 364.1666666666667,
      "grad_norm": 9.188275029714532e-09,
      "learning_rate": 0.02351520169672801,
      "loss": 0.0,
      "num_input_tokens_seen": 9177232,
      "step": 32775
    },
    {
      "epoch": 364.22222222222223,
      "grad_norm": 1.0035302366873111e-08,
      "learning_rate": 0.023483547151978357,
      "loss": 0.0,
      "num_input_tokens_seen": 9178608,
      "step": 32780
    },
    {
      "epoch": 364.27777777777777,
      "grad_norm": 1.191764020802566e-08,
      "learning_rate": 0.023451912117655675,
      "loss": 0.0,
      "num_input_tokens_seen": 9180032,
      "step": 32785
    },
    {
      "epoch": 364.3333333333333,
      "grad_norm": 7.086424780311518e-09,
      "learning_rate": 0.023420296598638417,
      "loss": 0.0,
      "num_input_tokens_seen": 9181408,
      "step": 32790
    },
    {
      "epoch": 364.3888888888889,
      "grad_norm": 6.402275598560436e-09,
      "learning_rate": 0.023388700599802165,
      "loss": 0.0,
      "num_input_tokens_seen": 9182816,
      "step": 32795
    },
    {
      "epoch": 364.44444444444446,
      "grad_norm": 2.0935658540111035e-08,
      "learning_rate": 0.023357124126019334,
      "loss": 0.0,
      "num_input_tokens_seen": 9184240,
      "step": 32800
    },
    {
      "epoch": 364.44444444444446,
      "eval_loss": 1.7084811925888062,
      "eval_runtime": 1.1919,
      "eval_samples_per_second": 33.559,
      "eval_steps_per_second": 16.78,
      "num_input_tokens_seen": 9184240,
      "step": 32800
    },
    {
      "epoch": 364.5,
      "grad_norm": 1.7835953158851225e-08,
      "learning_rate": 0.02332556718215945,
      "loss": 0.0,
      "num_input_tokens_seen": 9185664,
      "step": 32805
    },
    {
      "epoch": 364.55555555555554,
      "grad_norm": 1.730529675114667e-08,
      "learning_rate": 0.023294029773089035,
      "loss": 0.0,
      "num_input_tokens_seen": 9187056,
      "step": 32810
    },
    {
      "epoch": 364.6111111111111,
      "grad_norm": 1.6439635430742783e-08,
      "learning_rate": 0.023262511903671484,
      "loss": 0.0,
      "num_input_tokens_seen": 9188448,
      "step": 32815
    },
    {
      "epoch": 364.6666666666667,
      "grad_norm": 1.1334733152068566e-08,
      "learning_rate": 0.023231013578767324,
      "loss": 0.0,
      "num_input_tokens_seen": 9189808,
      "step": 32820
    },
    {
      "epoch": 364.72222222222223,
      "grad_norm": 1.3977853541291552e-08,
      "learning_rate": 0.0231995348032339,
      "loss": 0.0,
      "num_input_tokens_seen": 9191216,
      "step": 32825
    },
    {
      "epoch": 364.77777777777777,
      "grad_norm": 1.611109112786835e-08,
      "learning_rate": 0.023168075581925685,
      "loss": 0.0,
      "num_input_tokens_seen": 9192608,
      "step": 32830
    },
    {
      "epoch": 364.8333333333333,
      "grad_norm": 9.844912440826192e-09,
      "learning_rate": 0.023136635919694126,
      "loss": 0.0,
      "num_input_tokens_seen": 9194016,
      "step": 32835
    },
    {
      "epoch": 364.8888888888889,
      "grad_norm": 5.392899904421711e-09,
      "learning_rate": 0.02310521582138753,
      "loss": 0.0,
      "num_input_tokens_seen": 9195456,
      "step": 32840
    },
    {
      "epoch": 364.94444444444446,
      "grad_norm": 5.5363451600953795e-09,
      "learning_rate": 0.023073815291851357,
      "loss": 0.0,
      "num_input_tokens_seen": 9196800,
      "step": 32845
    },
    {
      "epoch": 365.0,
      "grad_norm": 2.1598822286250652e-08,
      "learning_rate": 0.02304243433592788,
      "loss": 0.0,
      "num_input_tokens_seen": 9198192,
      "step": 32850
    },
    {
      "epoch": 365.05555555555554,
      "grad_norm": 5.946541925538895e-09,
      "learning_rate": 0.023011072958456513,
      "loss": 0.0,
      "num_input_tokens_seen": 9199584,
      "step": 32855
    },
    {
      "epoch": 365.1111111111111,
      "grad_norm": 1.129150550838176e-08,
      "learning_rate": 0.022979731164273536,
      "loss": 0.0,
      "num_input_tokens_seen": 9200960,
      "step": 32860
    },
    {
      "epoch": 365.1666666666667,
      "grad_norm": 1.8831125103702107e-08,
      "learning_rate": 0.022948408958212218,
      "loss": 0.0,
      "num_input_tokens_seen": 9202336,
      "step": 32865
    },
    {
      "epoch": 365.22222222222223,
      "grad_norm": 1.1337174754544321e-08,
      "learning_rate": 0.022917106345102876,
      "loss": 0.0,
      "num_input_tokens_seen": 9203760,
      "step": 32870
    },
    {
      "epoch": 365.27777777777777,
      "grad_norm": 1.9442579102246782e-08,
      "learning_rate": 0.022885823329772785,
      "loss": 0.0,
      "num_input_tokens_seen": 9205168,
      "step": 32875
    },
    {
      "epoch": 365.3333333333333,
      "grad_norm": 9.05091290803739e-09,
      "learning_rate": 0.02285455991704612,
      "loss": 0.0,
      "num_input_tokens_seen": 9206640,
      "step": 32880
    },
    {
      "epoch": 365.3888888888889,
      "grad_norm": 8.882861557424349e-09,
      "learning_rate": 0.022823316111744117,
      "loss": 0.0,
      "num_input_tokens_seen": 9208048,
      "step": 32885
    },
    {
      "epoch": 365.44444444444446,
      "grad_norm": 9.658805311119067e-09,
      "learning_rate": 0.022792091918685014,
      "loss": 0.0,
      "num_input_tokens_seen": 9209392,
      "step": 32890
    },
    {
      "epoch": 365.5,
      "grad_norm": 1.7598436485855018e-08,
      "learning_rate": 0.022760887342683906,
      "loss": 0.0,
      "num_input_tokens_seen": 9210752,
      "step": 32895
    },
    {
      "epoch": 365.55555555555554,
      "grad_norm": 1.457455134357133e-08,
      "learning_rate": 0.022729702388552975,
      "loss": 0.0,
      "num_input_tokens_seen": 9212144,
      "step": 32900
    },
    {
      "epoch": 365.6111111111111,
      "grad_norm": 1.645489966506375e-08,
      "learning_rate": 0.022698537061101292,
      "loss": 0.0,
      "num_input_tokens_seen": 9213568,
      "step": 32905
    },
    {
      "epoch": 365.6666666666667,
      "grad_norm": 2.6941043174133483e-08,
      "learning_rate": 0.022667391365134962,
      "loss": 0.0,
      "num_input_tokens_seen": 9214992,
      "step": 32910
    },
    {
      "epoch": 365.72222222222223,
      "grad_norm": 9.67526680994979e-09,
      "learning_rate": 0.022636265305457065,
      "loss": 0.0,
      "num_input_tokens_seen": 9216384,
      "step": 32915
    },
    {
      "epoch": 365.77777777777777,
      "grad_norm": 2.5755070964805782e-08,
      "learning_rate": 0.02260515888686764,
      "loss": 0.0,
      "num_input_tokens_seen": 9217792,
      "step": 32920
    },
    {
      "epoch": 365.8333333333333,
      "grad_norm": 2.9797273981557737e-08,
      "learning_rate": 0.022574072114163596,
      "loss": 0.0,
      "num_input_tokens_seen": 9219216,
      "step": 32925
    },
    {
      "epoch": 365.8888888888889,
      "grad_norm": 1.3315188951423806e-08,
      "learning_rate": 0.022543004992139005,
      "loss": 0.0,
      "num_input_tokens_seen": 9220592,
      "step": 32930
    },
    {
      "epoch": 365.94444444444446,
      "grad_norm": 1.7516015304863686e-08,
      "learning_rate": 0.022511957525584745,
      "loss": 0.0,
      "num_input_tokens_seen": 9221936,
      "step": 32935
    },
    {
      "epoch": 366.0,
      "grad_norm": 1.2767219281784037e-08,
      "learning_rate": 0.022480929719288778,
      "loss": 0.0,
      "num_input_tokens_seen": 9223312,
      "step": 32940
    },
    {
      "epoch": 366.05555555555554,
      "grad_norm": 2.2634973007029657e-08,
      "learning_rate": 0.02244992157803592,
      "loss": 0.0,
      "num_input_tokens_seen": 9224720,
      "step": 32945
    },
    {
      "epoch": 366.1111111111111,
      "grad_norm": 1.8937846846256434e-08,
      "learning_rate": 0.022418933106608047,
      "loss": 0.0,
      "num_input_tokens_seen": 9226128,
      "step": 32950
    },
    {
      "epoch": 366.1666666666667,
      "grad_norm": 7.604604945754545e-09,
      "learning_rate": 0.022387964309784018,
      "loss": 0.0,
      "num_input_tokens_seen": 9227520,
      "step": 32955
    },
    {
      "epoch": 366.22222222222223,
      "grad_norm": 1.2571504726111016e-08,
      "learning_rate": 0.022357015192339517,
      "loss": 0.0,
      "num_input_tokens_seen": 9228880,
      "step": 32960
    },
    {
      "epoch": 366.27777777777777,
      "grad_norm": 1.0749528378539708e-08,
      "learning_rate": 0.02232608575904734,
      "loss": 0.0,
      "num_input_tokens_seen": 9230240,
      "step": 32965
    },
    {
      "epoch": 366.3333333333333,
      "grad_norm": 1.609441291350322e-08,
      "learning_rate": 0.022295176014677225,
      "loss": 0.0,
      "num_input_tokens_seen": 9231648,
      "step": 32970
    },
    {
      "epoch": 366.3888888888889,
      "grad_norm": 1.676917804616096e-08,
      "learning_rate": 0.02226428596399577,
      "loss": 0.0,
      "num_input_tokens_seen": 9233008,
      "step": 32975
    },
    {
      "epoch": 366.44444444444446,
      "grad_norm": 1.7436555310723634e-08,
      "learning_rate": 0.02223341561176669,
      "loss": 0.0,
      "num_input_tokens_seen": 9234400,
      "step": 32980
    },
    {
      "epoch": 366.5,
      "grad_norm": 1.9395928418930453e-08,
      "learning_rate": 0.0222025649627505,
      "loss": 0.0,
      "num_input_tokens_seen": 9235776,
      "step": 32985
    },
    {
      "epoch": 366.55555555555554,
      "grad_norm": 1.3012845023752106e-08,
      "learning_rate": 0.022171734021704814,
      "loss": 0.0,
      "num_input_tokens_seen": 9237216,
      "step": 32990
    },
    {
      "epoch": 366.6111111111111,
      "grad_norm": 3.238379520098533e-08,
      "learning_rate": 0.022140922793384116,
      "loss": 0.0,
      "num_input_tokens_seen": 9238656,
      "step": 32995
    },
    {
      "epoch": 366.6666666666667,
      "grad_norm": 1.3070006410487167e-08,
      "learning_rate": 0.022110131282539934,
      "loss": 0.0,
      "num_input_tokens_seen": 9240064,
      "step": 33000
    },
    {
      "epoch": 366.6666666666667,
      "eval_loss": 1.7311573028564453,
      "eval_runtime": 1.1922,
      "eval_samples_per_second": 33.551,
      "eval_steps_per_second": 16.775,
      "num_input_tokens_seen": 9240064,
      "step": 33000
    },
    {
      "epoch": 366.72222222222223,
      "grad_norm": 7.043109651050372e-09,
      "learning_rate": 0.022079359493920675,
      "loss": 0.0,
      "num_input_tokens_seen": 9241456,
      "step": 33005
    },
    {
      "epoch": 366.77777777777777,
      "grad_norm": 7.764480614014246e-09,
      "learning_rate": 0.02204860743227169,
      "loss": 0.0,
      "num_input_tokens_seen": 9242864,
      "step": 33010
    },
    {
      "epoch": 366.8333333333333,
      "grad_norm": 7.594317175119158e-09,
      "learning_rate": 0.022017875102335365,
      "loss": 0.0,
      "num_input_tokens_seen": 9244272,
      "step": 33015
    },
    {
      "epoch": 366.8888888888889,
      "grad_norm": 1.035900432100334e-08,
      "learning_rate": 0.02198716250885108,
      "loss": 0.0,
      "num_input_tokens_seen": 9245664,
      "step": 33020
    },
    {
      "epoch": 366.94444444444446,
      "grad_norm": 7.326983464395198e-09,
      "learning_rate": 0.021956469656555,
      "loss": 0.0,
      "num_input_tokens_seen": 9247056,
      "step": 33025
    },
    {
      "epoch": 367.0,
      "grad_norm": 1.1775687092097087e-08,
      "learning_rate": 0.0219257965501804,
      "loss": 0.0,
      "num_input_tokens_seen": 9248496,
      "step": 33030
    },
    {
      "epoch": 367.05555555555554,
      "grad_norm": 1.2811385730060465e-08,
      "learning_rate": 0.021895143194457494,
      "loss": 0.0,
      "num_input_tokens_seen": 9249888,
      "step": 33035
    },
    {
      "epoch": 367.1111111111111,
      "grad_norm": 2.6423556676036242e-08,
      "learning_rate": 0.021864509594113322,
      "loss": 0.0,
      "num_input_tokens_seen": 9251248,
      "step": 33040
    },
    {
      "epoch": 367.1666666666667,
      "grad_norm": 2.3465457132942902e-08,
      "learning_rate": 0.02183389575387207,
      "loss": 0.0,
      "num_input_tokens_seen": 9252672,
      "step": 33045
    },
    {
      "epoch": 367.22222222222223,
      "grad_norm": 7.685225789089145e-09,
      "learning_rate": 0.021803301678454682,
      "loss": 0.0,
      "num_input_tokens_seen": 9254080,
      "step": 33050
    },
    {
      "epoch": 367.27777777777777,
      "grad_norm": 7.558161208010006e-09,
      "learning_rate": 0.021772727372579213,
      "loss": 0.0,
      "num_input_tokens_seen": 9255488,
      "step": 33055
    },
    {
      "epoch": 367.3333333333333,
      "grad_norm": 1.0304337827449217e-08,
      "learning_rate": 0.02174217284096061,
      "loss": 0.0,
      "num_input_tokens_seen": 9256912,
      "step": 33060
    },
    {
      "epoch": 367.3888888888889,
      "grad_norm": 9.856386817830298e-09,
      "learning_rate": 0.0217116380883107,
      "loss": 0.0,
      "num_input_tokens_seen": 9258288,
      "step": 33065
    },
    {
      "epoch": 367.44444444444446,
      "grad_norm": 1.3804259957339582e-08,
      "learning_rate": 0.021681123119338425,
      "loss": 0.0,
      "num_input_tokens_seen": 9259664,
      "step": 33070
    },
    {
      "epoch": 367.5,
      "grad_norm": 1.4810892068339854e-08,
      "learning_rate": 0.02165062793874951,
      "loss": 0.0,
      "num_input_tokens_seen": 9261056,
      "step": 33075
    },
    {
      "epoch": 367.55555555555554,
      "grad_norm": 9.794665523088497e-09,
      "learning_rate": 0.021620152551246666,
      "loss": 0.0,
      "num_input_tokens_seen": 9262448,
      "step": 33080
    },
    {
      "epoch": 367.6111111111111,
      "grad_norm": 1.221977274923347e-08,
      "learning_rate": 0.02158969696152967,
      "loss": 0.0,
      "num_input_tokens_seen": 9263840,
      "step": 33085
    },
    {
      "epoch": 367.6666666666667,
      "grad_norm": 5.553154824866624e-09,
      "learning_rate": 0.021559261174295057,
      "loss": 0.0,
      "num_input_tokens_seen": 9265232,
      "step": 33090
    },
    {
      "epoch": 367.72222222222223,
      "grad_norm": 9.465738415315172e-09,
      "learning_rate": 0.02152884519423646,
      "loss": 0.0,
      "num_input_tokens_seen": 9266640,
      "step": 33095
    },
    {
      "epoch": 367.77777777777777,
      "grad_norm": 1.1140219413618979e-08,
      "learning_rate": 0.021498449026044447,
      "loss": 0.0,
      "num_input_tokens_seen": 9268000,
      "step": 33100
    },
    {
      "epoch": 367.8333333333333,
      "grad_norm": 1.3981297897203149e-08,
      "learning_rate": 0.021468072674406414,
      "loss": 0.0,
      "num_input_tokens_seen": 9269424,
      "step": 33105
    },
    {
      "epoch": 367.8888888888889,
      "grad_norm": 1.674050231770252e-08,
      "learning_rate": 0.021437716144006795,
      "loss": 0.0,
      "num_input_tokens_seen": 9270880,
      "step": 33110
    },
    {
      "epoch": 367.94444444444446,
      "grad_norm": 1.2290989559460286e-08,
      "learning_rate": 0.021407379439527002,
      "loss": 0.0,
      "num_input_tokens_seen": 9272272,
      "step": 33115
    },
    {
      "epoch": 368.0,
      "grad_norm": 1.497211066237014e-08,
      "learning_rate": 0.021377062565645255,
      "loss": 0.0,
      "num_input_tokens_seen": 9273664,
      "step": 33120
    },
    {
      "epoch": 368.05555555555554,
      "grad_norm": 7.355752895676915e-09,
      "learning_rate": 0.02134676552703688,
      "loss": 0.0,
      "num_input_tokens_seen": 9275088,
      "step": 33125
    },
    {
      "epoch": 368.1111111111111,
      "grad_norm": 1.3387306374568197e-08,
      "learning_rate": 0.02131648832837398,
      "loss": 0.0,
      "num_input_tokens_seen": 9276464,
      "step": 33130
    },
    {
      "epoch": 368.1666666666667,
      "grad_norm": 1.6619125631223142e-08,
      "learning_rate": 0.02128623097432574,
      "loss": 0.0,
      "num_input_tokens_seen": 9277872,
      "step": 33135
    },
    {
      "epoch": 368.22222222222223,
      "grad_norm": 1.0112684023511065e-08,
      "learning_rate": 0.021255993469558192,
      "loss": 0.0,
      "num_input_tokens_seen": 9279248,
      "step": 33140
    },
    {
      "epoch": 368.27777777777777,
      "grad_norm": 9.00053276353674e-09,
      "learning_rate": 0.021225775818734364,
      "loss": 0.0,
      "num_input_tokens_seen": 9280640,
      "step": 33145
    },
    {
      "epoch": 368.3333333333333,
      "grad_norm": 1.4484307975237698e-08,
      "learning_rate": 0.021195578026514166,
      "loss": 0.0,
      "num_input_tokens_seen": 9282000,
      "step": 33150
    },
    {
      "epoch": 368.3888888888889,
      "grad_norm": 1.0642227543655736e-08,
      "learning_rate": 0.02116540009755452,
      "loss": 0.0,
      "num_input_tokens_seen": 9283424,
      "step": 33155
    },
    {
      "epoch": 368.44444444444446,
      "grad_norm": 2.2562023360706007e-08,
      "learning_rate": 0.021135242036509173,
      "loss": 0.0,
      "num_input_tokens_seen": 9284816,
      "step": 33160
    },
    {
      "epoch": 368.5,
      "grad_norm": 2.1618031809111926e-08,
      "learning_rate": 0.021105103848028967,
      "loss": 0.0,
      "num_input_tokens_seen": 9286240,
      "step": 33165
    },
    {
      "epoch": 368.55555555555554,
      "grad_norm": 1.2387703307581432e-08,
      "learning_rate": 0.021074985536761504,
      "loss": 0.0,
      "num_input_tokens_seen": 9287664,
      "step": 33170
    },
    {
      "epoch": 368.6111111111111,
      "grad_norm": 1.5897677840825963e-08,
      "learning_rate": 0.021044887107351435,
      "loss": 0.0,
      "num_input_tokens_seen": 9289040,
      "step": 33175
    },
    {
      "epoch": 368.6666666666667,
      "grad_norm": 1.1114956066649029e-08,
      "learning_rate": 0.021014808564440362,
      "loss": 0.0,
      "num_input_tokens_seen": 9290416,
      "step": 33180
    },
    {
      "epoch": 368.72222222222223,
      "grad_norm": 1.1503089147879564e-08,
      "learning_rate": 0.02098474991266671,
      "loss": 0.0,
      "num_input_tokens_seen": 9291824,
      "step": 33185
    },
    {
      "epoch": 368.77777777777777,
      "grad_norm": 7.1866090856076426e-09,
      "learning_rate": 0.02095471115666592,
      "loss": 0.0,
      "num_input_tokens_seen": 9293200,
      "step": 33190
    },
    {
      "epoch": 368.8333333333333,
      "grad_norm": 6.143648079159902e-08,
      "learning_rate": 0.020924692301070406,
      "loss": 0.0,
      "num_input_tokens_seen": 9294560,
      "step": 33195
    },
    {
      "epoch": 368.8888888888889,
      "grad_norm": 7.994525041965517e-09,
      "learning_rate": 0.020894693350509346,
      "loss": 0.0,
      "num_input_tokens_seen": 9295952,
      "step": 33200
    },
    {
      "epoch": 368.8888888888889,
      "eval_loss": 1.753893256187439,
      "eval_runtime": 1.183,
      "eval_samples_per_second": 33.813,
      "eval_steps_per_second": 16.907,
      "num_input_tokens_seen": 9295952,
      "step": 33200
    },
    {
      "epoch": 368.94444444444446,
      "grad_norm": 1.0325368116070877e-08,
      "learning_rate": 0.020864714309609057,
      "loss": 0.0,
      "num_input_tokens_seen": 9297408,
      "step": 33205
    },
    {
      "epoch": 369.0,
      "grad_norm": 1.3663168374478118e-08,
      "learning_rate": 0.020834755182992604,
      "loss": 0.0,
      "num_input_tokens_seen": 9298832,
      "step": 33210
    },
    {
      "epoch": 369.05555555555554,
      "grad_norm": 9.148023671912142e-09,
      "learning_rate": 0.02080481597528011,
      "loss": 0.0,
      "num_input_tokens_seen": 9300224,
      "step": 33215
    },
    {
      "epoch": 369.1111111111111,
      "grad_norm": 8.750781432809163e-09,
      "learning_rate": 0.020774896691088583,
      "loss": 0.0,
      "num_input_tokens_seen": 9301584,
      "step": 33220
    },
    {
      "epoch": 369.1666666666667,
      "grad_norm": 1.8745407004416847e-08,
      "learning_rate": 0.020744997335031882,
      "loss": 0.0,
      "num_input_tokens_seen": 9302976,
      "step": 33225
    },
    {
      "epoch": 369.22222222222223,
      "grad_norm": 9.590826799410479e-09,
      "learning_rate": 0.02071511791172092,
      "loss": 0.0,
      "num_input_tokens_seen": 9304384,
      "step": 33230
    },
    {
      "epoch": 369.27777777777777,
      "grad_norm": 7.114538291830286e-09,
      "learning_rate": 0.02068525842576351,
      "loss": 0.0,
      "num_input_tokens_seen": 9305792,
      "step": 33235
    },
    {
      "epoch": 369.3333333333333,
      "grad_norm": 9.279109036697264e-09,
      "learning_rate": 0.020655418881764264,
      "loss": 0.0,
      "num_input_tokens_seen": 9307184,
      "step": 33240
    },
    {
      "epoch": 369.3888888888889,
      "grad_norm": 2.6744126913058608e-08,
      "learning_rate": 0.020625599284324923,
      "loss": 0.0,
      "num_input_tokens_seen": 9308592,
      "step": 33245
    },
    {
      "epoch": 369.44444444444446,
      "grad_norm": 1.6006824310466072e-08,
      "learning_rate": 0.02059579963804396,
      "loss": 0.0,
      "num_input_tokens_seen": 9309984,
      "step": 33250
    },
    {
      "epoch": 369.5,
      "grad_norm": 9.116408072884497e-09,
      "learning_rate": 0.02056601994751688,
      "loss": 0.0,
      "num_input_tokens_seen": 9311360,
      "step": 33255
    },
    {
      "epoch": 369.55555555555554,
      "grad_norm": 7.585409633747986e-09,
      "learning_rate": 0.02053626021733614,
      "loss": 0.0,
      "num_input_tokens_seen": 9312736,
      "step": 33260
    },
    {
      "epoch": 369.6111111111111,
      "grad_norm": 2.1937324845566764e-08,
      "learning_rate": 0.02050652045209097,
      "loss": 0.0,
      "num_input_tokens_seen": 9314112,
      "step": 33265
    },
    {
      "epoch": 369.6666666666667,
      "grad_norm": 8.319234190423686e-09,
      "learning_rate": 0.020476800656367672,
      "loss": 0.0,
      "num_input_tokens_seen": 9315584,
      "step": 33270
    },
    {
      "epoch": 369.72222222222223,
      "grad_norm": 3.349614985381777e-08,
      "learning_rate": 0.020447100834749425,
      "loss": 0.0,
      "num_input_tokens_seen": 9317008,
      "step": 33275
    },
    {
      "epoch": 369.77777777777777,
      "grad_norm": 1.98146477004002e-08,
      "learning_rate": 0.02041742099181627,
      "loss": 0.0,
      "num_input_tokens_seen": 9318416,
      "step": 33280
    },
    {
      "epoch": 369.8333333333333,
      "grad_norm": 1.934547100290729e-08,
      "learning_rate": 0.02038776113214526,
      "loss": 0.0,
      "num_input_tokens_seen": 9319776,
      "step": 33285
    },
    {
      "epoch": 369.8888888888889,
      "grad_norm": 9.541314405225876e-09,
      "learning_rate": 0.0203581212603103,
      "loss": 0.0,
      "num_input_tokens_seen": 9321200,
      "step": 33290
    },
    {
      "epoch": 369.94444444444446,
      "grad_norm": 1.1288496359895817e-08,
      "learning_rate": 0.02032850138088219,
      "loss": 0.0,
      "num_input_tokens_seen": 9322624,
      "step": 33295
    },
    {
      "epoch": 370.0,
      "grad_norm": 2.3826707717944373e-08,
      "learning_rate": 0.020298901498428754,
      "loss": 0.0,
      "num_input_tokens_seen": 9324064,
      "step": 33300
    },
    {
      "epoch": 370.05555555555554,
      "grad_norm": 1.29287478500828e-08,
      "learning_rate": 0.020269321617514595,
      "loss": 0.0,
      "num_input_tokens_seen": 9325472,
      "step": 33305
    },
    {
      "epoch": 370.1111111111111,
      "grad_norm": 2.103981167067559e-08,
      "learning_rate": 0.020239761742701343,
      "loss": 0.0,
      "num_input_tokens_seen": 9326880,
      "step": 33310
    },
    {
      "epoch": 370.1666666666667,
      "grad_norm": 1.9754688551643085e-08,
      "learning_rate": 0.02021022187854754,
      "loss": 0.0,
      "num_input_tokens_seen": 9328304,
      "step": 33315
    },
    {
      "epoch": 370.22222222222223,
      "grad_norm": 2.0189464322584172e-08,
      "learning_rate": 0.020180702029608522,
      "loss": 0.0,
      "num_input_tokens_seen": 9329648,
      "step": 33320
    },
    {
      "epoch": 370.27777777777777,
      "grad_norm": 1.8352325881210163e-08,
      "learning_rate": 0.020151202200436695,
      "loss": 0.0,
      "num_input_tokens_seen": 9331040,
      "step": 33325
    },
    {
      "epoch": 370.3333333333333,
      "grad_norm": 3.022423911147598e-08,
      "learning_rate": 0.020121722395581226,
      "loss": 0.0,
      "num_input_tokens_seen": 9332448,
      "step": 33330
    },
    {
      "epoch": 370.3888888888889,
      "grad_norm": 1.3751701111175407e-08,
      "learning_rate": 0.020092262619588342,
      "loss": 0.0,
      "num_input_tokens_seen": 9333872,
      "step": 33335
    },
    {
      "epoch": 370.44444444444446,
      "grad_norm": 1.0159501684370298e-08,
      "learning_rate": 0.02006282287700109,
      "loss": 0.0,
      "num_input_tokens_seen": 9335264,
      "step": 33340
    },
    {
      "epoch": 370.5,
      "grad_norm": 1.0040206888106695e-08,
      "learning_rate": 0.020033403172359427,
      "loss": 0.0,
      "num_input_tokens_seen": 9336672,
      "step": 33345
    },
    {
      "epoch": 370.55555555555554,
      "grad_norm": 8.216107794112304e-09,
      "learning_rate": 0.020004003510200284,
      "loss": 0.0,
      "num_input_tokens_seen": 9338000,
      "step": 33350
    },
    {
      "epoch": 370.6111111111111,
      "grad_norm": 3.317630259402904e-08,
      "learning_rate": 0.019974623895057407,
      "loss": 0.0,
      "num_input_tokens_seen": 9339376,
      "step": 33355
    },
    {
      "epoch": 370.6666666666667,
      "grad_norm": 1.7231620574875706e-08,
      "learning_rate": 0.019945264331461553,
      "loss": 0.0,
      "num_input_tokens_seen": 9340784,
      "step": 33360
    },
    {
      "epoch": 370.72222222222223,
      "grad_norm": 7.224450371268176e-09,
      "learning_rate": 0.019915924823940317,
      "loss": 0.0,
      "num_input_tokens_seen": 9342192,
      "step": 33365
    },
    {
      "epoch": 370.77777777777777,
      "grad_norm": 1.0675350381461612e-08,
      "learning_rate": 0.01988660537701816,
      "loss": 0.0,
      "num_input_tokens_seen": 9343568,
      "step": 33370
    },
    {
      "epoch": 370.8333333333333,
      "grad_norm": 1.8992363237657628e-08,
      "learning_rate": 0.01985730599521659,
      "loss": 0.0,
      "num_input_tokens_seen": 9344928,
      "step": 33375
    },
    {
      "epoch": 370.8888888888889,
      "grad_norm": 2.48178917416908e-08,
      "learning_rate": 0.019828026683053918,
      "loss": 0.0,
      "num_input_tokens_seen": 9346336,
      "step": 33380
    },
    {
      "epoch": 370.94444444444446,
      "grad_norm": 2.4818595178999203e-08,
      "learning_rate": 0.01979876744504535,
      "loss": 0.0,
      "num_input_tokens_seen": 9347776,
      "step": 33385
    },
    {
      "epoch": 371.0,
      "grad_norm": 1.670102456330369e-08,
      "learning_rate": 0.019769528285703046,
      "loss": 0.0,
      "num_input_tokens_seen": 9349184,
      "step": 33390
    },
    {
      "epoch": 371.05555555555554,
      "grad_norm": 2.4040874180286664e-08,
      "learning_rate": 0.019740309209536098,
      "loss": 0.0,
      "num_input_tokens_seen": 9350592,
      "step": 33395
    },
    {
      "epoch": 371.1111111111111,
      "grad_norm": 8.083186564533662e-09,
      "learning_rate": 0.019711110221050387,
      "loss": 0.0,
      "num_input_tokens_seen": 9352016,
      "step": 33400
    },
    {
      "epoch": 371.1111111111111,
      "eval_loss": 1.7248910665512085,
      "eval_runtime": 1.1858,
      "eval_samples_per_second": 33.733,
      "eval_steps_per_second": 16.867,
      "num_input_tokens_seen": 9352016,
      "step": 33400
    },
    {
      "epoch": 371.1666666666667,
      "grad_norm": 1.1569483149287407e-08,
      "learning_rate": 0.019681931324748825,
      "loss": 0.0,
      "num_input_tokens_seen": 9353392,
      "step": 33405
    },
    {
      "epoch": 371.22222222222223,
      "grad_norm": 1.1958793066924045e-08,
      "learning_rate": 0.019652772525131094,
      "loss": 0.0,
      "num_input_tokens_seen": 9354816,
      "step": 33410
    },
    {
      "epoch": 371.27777777777777,
      "grad_norm": 1.1298164181994252e-08,
      "learning_rate": 0.019623633826693885,
      "loss": 0.0,
      "num_input_tokens_seen": 9356160,
      "step": 33415
    },
    {
      "epoch": 371.3333333333333,
      "grad_norm": 9.088414465452388e-09,
      "learning_rate": 0.019594515233930788,
      "loss": 0.0,
      "num_input_tokens_seen": 9357568,
      "step": 33420
    },
    {
      "epoch": 371.3888888888889,
      "grad_norm": 5.617820431069731e-09,
      "learning_rate": 0.019565416751332186,
      "loss": 0.0,
      "num_input_tokens_seen": 9358992,
      "step": 33425
    },
    {
      "epoch": 371.44444444444446,
      "grad_norm": 8.548330043822716e-09,
      "learning_rate": 0.019536338383385497,
      "loss": 0.0,
      "num_input_tokens_seen": 9360432,
      "step": 33430
    },
    {
      "epoch": 371.5,
      "grad_norm": 8.350075297869353e-09,
      "learning_rate": 0.019507280134574933,
      "loss": 0.0,
      "num_input_tokens_seen": 9361840,
      "step": 33435
    },
    {
      "epoch": 371.55555555555554,
      "grad_norm": 3.6183287477342674e-08,
      "learning_rate": 0.019478242009381624,
      "loss": 0.0,
      "num_input_tokens_seen": 9363232,
      "step": 33440
    },
    {
      "epoch": 371.6111111111111,
      "grad_norm": 8.58850857099469e-09,
      "learning_rate": 0.01944922401228367,
      "loss": 0.0,
      "num_input_tokens_seen": 9364640,
      "step": 33445
    },
    {
      "epoch": 371.6666666666667,
      "grad_norm": 7.946437285966113e-09,
      "learning_rate": 0.01942022614775593,
      "loss": 0.0,
      "num_input_tokens_seen": 9365984,
      "step": 33450
    },
    {
      "epoch": 371.72222222222223,
      "grad_norm": 2.445311508836312e-08,
      "learning_rate": 0.01939124842027029,
      "loss": 0.0,
      "num_input_tokens_seen": 9367376,
      "step": 33455
    },
    {
      "epoch": 371.77777777777777,
      "grad_norm": 1.1692661949780359e-08,
      "learning_rate": 0.01936229083429551,
      "loss": 0.0,
      "num_input_tokens_seen": 9368768,
      "step": 33460
    },
    {
      "epoch": 371.8333333333333,
      "grad_norm": 9.568769776535646e-09,
      "learning_rate": 0.019333353394297148,
      "loss": 0.0,
      "num_input_tokens_seen": 9370192,
      "step": 33465
    },
    {
      "epoch": 371.8888888888889,
      "grad_norm": 2.8954524111668434e-08,
      "learning_rate": 0.019304436104737754,
      "loss": 0.0,
      "num_input_tokens_seen": 9371568,
      "step": 33470
    },
    {
      "epoch": 371.94444444444446,
      "grad_norm": 9.703240877456665e-09,
      "learning_rate": 0.019275538970076778,
      "loss": 0.0,
      "num_input_tokens_seen": 9372992,
      "step": 33475
    },
    {
      "epoch": 372.0,
      "grad_norm": 1.0556043150700134e-08,
      "learning_rate": 0.019246661994770434,
      "loss": 0.0,
      "num_input_tokens_seen": 9374416,
      "step": 33480
    },
    {
      "epoch": 372.05555555555554,
      "grad_norm": 9.529607325475808e-09,
      "learning_rate": 0.019217805183271985,
      "loss": 0.0,
      "num_input_tokens_seen": 9375824,
      "step": 33485
    },
    {
      "epoch": 372.1111111111111,
      "grad_norm": 1.2670000160142081e-08,
      "learning_rate": 0.019188968540031465,
      "loss": 0.0,
      "num_input_tokens_seen": 9377168,
      "step": 33490
    },
    {
      "epoch": 372.1666666666667,
      "grad_norm": 7.469520113545514e-09,
      "learning_rate": 0.019160152069495867,
      "loss": 0.0,
      "num_input_tokens_seen": 9378560,
      "step": 33495
    },
    {
      "epoch": 372.22222222222223,
      "grad_norm": 1.0713887554913981e-08,
      "learning_rate": 0.019131355776109103,
      "loss": 0.0,
      "num_input_tokens_seen": 9379936,
      "step": 33500
    },
    {
      "epoch": 372.27777777777777,
      "grad_norm": 1.2122205461650992e-08,
      "learning_rate": 0.019102579664311857,
      "loss": 0.0,
      "num_input_tokens_seen": 9381312,
      "step": 33505
    },
    {
      "epoch": 372.3333333333333,
      "grad_norm": 6.366355442821714e-09,
      "learning_rate": 0.019073823738541763,
      "loss": 0.0,
      "num_input_tokens_seen": 9382688,
      "step": 33510
    },
    {
      "epoch": 372.3888888888889,
      "grad_norm": 9.633066788694578e-09,
      "learning_rate": 0.0190450880032334,
      "loss": 0.0,
      "num_input_tokens_seen": 9384048,
      "step": 33515
    },
    {
      "epoch": 372.44444444444446,
      "grad_norm": 8.837474751999252e-09,
      "learning_rate": 0.019016372462818114,
      "loss": 0.0,
      "num_input_tokens_seen": 9385472,
      "step": 33520
    },
    {
      "epoch": 372.5,
      "grad_norm": 2.1661662685801275e-08,
      "learning_rate": 0.018987677121724278,
      "loss": 0.0,
      "num_input_tokens_seen": 9386896,
      "step": 33525
    },
    {
      "epoch": 372.55555555555554,
      "grad_norm": 1.0430462715760314e-08,
      "learning_rate": 0.018959001984377,
      "loss": 0.0,
      "num_input_tokens_seen": 9388272,
      "step": 33530
    },
    {
      "epoch": 372.6111111111111,
      "grad_norm": 1.3983505908754523e-08,
      "learning_rate": 0.018930347055198377,
      "loss": 0.0,
      "num_input_tokens_seen": 9389696,
      "step": 33535
    },
    {
      "epoch": 372.6666666666667,
      "grad_norm": 1.0216165691190326e-08,
      "learning_rate": 0.01890171233860739,
      "loss": 0.0,
      "num_input_tokens_seen": 9391104,
      "step": 33540
    },
    {
      "epoch": 372.72222222222223,
      "grad_norm": 1.3346475036257743e-08,
      "learning_rate": 0.018873097839019807,
      "loss": 0.0,
      "num_input_tokens_seen": 9392512,
      "step": 33545
    },
    {
      "epoch": 372.77777777777777,
      "grad_norm": 1.3814852373172926e-08,
      "learning_rate": 0.0188445035608484,
      "loss": 0.0,
      "num_input_tokens_seen": 9393872,
      "step": 33550
    },
    {
      "epoch": 372.8333333333333,
      "grad_norm": 1.5575182032989687e-08,
      "learning_rate": 0.018815929508502777,
      "loss": 0.0,
      "num_input_tokens_seen": 9395280,
      "step": 33555
    },
    {
      "epoch": 372.8888888888889,
      "grad_norm": 9.95637350342804e-09,
      "learning_rate": 0.01878737568638934,
      "loss": 0.0,
      "num_input_tokens_seen": 9396704,
      "step": 33560
    },
    {
      "epoch": 372.94444444444446,
      "grad_norm": 4.951782539563965e-09,
      "learning_rate": 0.01875884209891152,
      "loss": 0.0,
      "num_input_tokens_seen": 9398144,
      "step": 33565
    },
    {
      "epoch": 373.0,
      "grad_norm": 3.0127015548941927e-08,
      "learning_rate": 0.018730328750469514,
      "loss": 0.0,
      "num_input_tokens_seen": 9399584,
      "step": 33570
    },
    {
      "epoch": 373.05555555555554,
      "grad_norm": 1.557197748525141e-08,
      "learning_rate": 0.018701835645460473,
      "loss": 0.0,
      "num_input_tokens_seen": 9400992,
      "step": 33575
    },
    {
      "epoch": 373.1111111111111,
      "grad_norm": 1.2307576291448186e-08,
      "learning_rate": 0.01867336278827838,
      "loss": 0.0,
      "num_input_tokens_seen": 9402368,
      "step": 33580
    },
    {
      "epoch": 373.1666666666667,
      "grad_norm": 1.0289938678909039e-08,
      "learning_rate": 0.018644910183314056,
      "loss": 0.0,
      "num_input_tokens_seen": 9403744,
      "step": 33585
    },
    {
      "epoch": 373.22222222222223,
      "grad_norm": 1.0144024287228603e-08,
      "learning_rate": 0.01861647783495531,
      "loss": 0.0,
      "num_input_tokens_seen": 9405136,
      "step": 33590
    },
    {
      "epoch": 373.27777777777777,
      "grad_norm": 8.280230723300974e-09,
      "learning_rate": 0.01858806574758676,
      "loss": 0.0,
      "num_input_tokens_seen": 9406512,
      "step": 33595
    },
    {
      "epoch": 373.3333333333333,
      "grad_norm": 9.151934321494082e-09,
      "learning_rate": 0.01855967392558988,
      "loss": 0.0,
      "num_input_tokens_seen": 9407968,
      "step": 33600
    },
    {
      "epoch": 373.3333333333333,
      "eval_loss": 1.7503668069839478,
      "eval_runtime": 1.1868,
      "eval_samples_per_second": 33.705,
      "eval_steps_per_second": 16.853,
      "num_input_tokens_seen": 9407968,
      "step": 33600
    },
    {
      "epoch": 373.3888888888889,
      "grad_norm": 1.3408806509573878e-08,
      "learning_rate": 0.018531302373343096,
      "loss": 0.0,
      "num_input_tokens_seen": 9409376,
      "step": 33605
    },
    {
      "epoch": 373.44444444444446,
      "grad_norm": 1.3082542160702815e-08,
      "learning_rate": 0.018502951095221588,
      "loss": 0.0,
      "num_input_tokens_seen": 9410752,
      "step": 33610
    },
    {
      "epoch": 373.5,
      "grad_norm": 1.4584695229302724e-08,
      "learning_rate": 0.01847462009559751,
      "loss": 0.0,
      "num_input_tokens_seen": 9412144,
      "step": 33615
    },
    {
      "epoch": 373.55555555555554,
      "grad_norm": 1.3571857415684008e-08,
      "learning_rate": 0.01844630937883992,
      "loss": 0.0,
      "num_input_tokens_seen": 9413552,
      "step": 33620
    },
    {
      "epoch": 373.6111111111111,
      "grad_norm": 2.0513869714022803e-08,
      "learning_rate": 0.018418018949314573,
      "loss": 0.0,
      "num_input_tokens_seen": 9414912,
      "step": 33625
    },
    {
      "epoch": 373.6666666666667,
      "grad_norm": 1.630390222828737e-08,
      "learning_rate": 0.018389748811384315,
      "loss": 0.0,
      "num_input_tokens_seen": 9416336,
      "step": 33630
    },
    {
      "epoch": 373.72222222222223,
      "grad_norm": 1.9559053043849417e-08,
      "learning_rate": 0.018361498969408658,
      "loss": 0.0,
      "num_input_tokens_seen": 9417728,
      "step": 33635
    },
    {
      "epoch": 373.77777777777777,
      "grad_norm": 2.968273093983953e-08,
      "learning_rate": 0.01833326942774415,
      "loss": 0.0,
      "num_input_tokens_seen": 9419120,
      "step": 33640
    },
    {
      "epoch": 373.8333333333333,
      "grad_norm": 1.229722723650184e-08,
      "learning_rate": 0.018305060190744155,
      "loss": 0.0,
      "num_input_tokens_seen": 9420560,
      "step": 33645
    },
    {
      "epoch": 373.8888888888889,
      "grad_norm": 1.0877744927029198e-08,
      "learning_rate": 0.018276871262758846,
      "loss": 0.0,
      "num_input_tokens_seen": 9421904,
      "step": 33650
    },
    {
      "epoch": 373.94444444444446,
      "grad_norm": 1.0981645814922558e-08,
      "learning_rate": 0.0182487026481353,
      "loss": 0.0,
      "num_input_tokens_seen": 9423312,
      "step": 33655
    },
    {
      "epoch": 374.0,
      "grad_norm": 8.346251689772544e-09,
      "learning_rate": 0.018220554351217538,
      "loss": 0.0,
      "num_input_tokens_seen": 9424752,
      "step": 33660
    },
    {
      "epoch": 374.05555555555554,
      "grad_norm": 1.8930313316900538e-08,
      "learning_rate": 0.01819242637634629,
      "loss": 0.0,
      "num_input_tokens_seen": 9426208,
      "step": 33665
    },
    {
      "epoch": 374.1111111111111,
      "grad_norm": 9.295602509951095e-09,
      "learning_rate": 0.01816431872785933,
      "loss": 0.0,
      "num_input_tokens_seen": 9427552,
      "step": 33670
    },
    {
      "epoch": 374.1666666666667,
      "grad_norm": 1.033293983709882e-08,
      "learning_rate": 0.018136231410091148,
      "loss": 0.0,
      "num_input_tokens_seen": 9428928,
      "step": 33675
    },
    {
      "epoch": 374.22222222222223,
      "grad_norm": 8.380065530388947e-09,
      "learning_rate": 0.018108164427373175,
      "loss": 0.0,
      "num_input_tokens_seen": 9430288,
      "step": 33680
    },
    {
      "epoch": 374.27777777777777,
      "grad_norm": 1.2444366426223041e-08,
      "learning_rate": 0.01808011778403375,
      "loss": 0.0,
      "num_input_tokens_seen": 9431712,
      "step": 33685
    },
    {
      "epoch": 374.3333333333333,
      "grad_norm": 1.961392825933217e-08,
      "learning_rate": 0.01805209148439793,
      "loss": 0.0,
      "num_input_tokens_seen": 9433104,
      "step": 33690
    },
    {
      "epoch": 374.3888888888889,
      "grad_norm": 3.054982755656965e-08,
      "learning_rate": 0.018024085532787757,
      "loss": 0.0,
      "num_input_tokens_seen": 9434496,
      "step": 33695
    },
    {
      "epoch": 374.44444444444446,
      "grad_norm": 1.2282667327667696e-08,
      "learning_rate": 0.017996099933522164,
      "loss": 0.0,
      "num_input_tokens_seen": 9435888,
      "step": 33700
    },
    {
      "epoch": 374.5,
      "grad_norm": 1.9274670748359313e-08,
      "learning_rate": 0.017968134690916775,
      "loss": 0.0,
      "num_input_tokens_seen": 9437296,
      "step": 33705
    },
    {
      "epoch": 374.55555555555554,
      "grad_norm": 9.640620746154127e-09,
      "learning_rate": 0.017940189809284263,
      "loss": 0.0,
      "num_input_tokens_seen": 9438688,
      "step": 33710
    },
    {
      "epoch": 374.6111111111111,
      "grad_norm": 2.2324371684590005e-08,
      "learning_rate": 0.017912265292934024,
      "loss": 0.0,
      "num_input_tokens_seen": 9440096,
      "step": 33715
    },
    {
      "epoch": 374.6666666666667,
      "grad_norm": 9.663699174211615e-09,
      "learning_rate": 0.017884361146172423,
      "loss": 0.0,
      "num_input_tokens_seen": 9441488,
      "step": 33720
    },
    {
      "epoch": 374.72222222222223,
      "grad_norm": 1.772496105445498e-08,
      "learning_rate": 0.01785647737330261,
      "loss": 0.0,
      "num_input_tokens_seen": 9442880,
      "step": 33725
    },
    {
      "epoch": 374.77777777777777,
      "grad_norm": 7.86653320261621e-09,
      "learning_rate": 0.017828613978624563,
      "loss": 0.0,
      "num_input_tokens_seen": 9444288,
      "step": 33730
    },
    {
      "epoch": 374.8333333333333,
      "grad_norm": 8.661078076954709e-09,
      "learning_rate": 0.01780077096643523,
      "loss": 0.0,
      "num_input_tokens_seen": 9445664,
      "step": 33735
    },
    {
      "epoch": 374.8888888888889,
      "grad_norm": 9.639835596431112e-09,
      "learning_rate": 0.017772948341028345,
      "loss": 0.0,
      "num_input_tokens_seen": 9447008,
      "step": 33740
    },
    {
      "epoch": 374.94444444444446,
      "grad_norm": 1.0079582501987261e-08,
      "learning_rate": 0.01774514610669447,
      "loss": 0.0,
      "num_input_tokens_seen": 9448464,
      "step": 33745
    },
    {
      "epoch": 375.0,
      "grad_norm": 1.3277136723388594e-08,
      "learning_rate": 0.017717364267721112,
      "loss": 0.0,
      "num_input_tokens_seen": 9449888,
      "step": 33750
    },
    {
      "epoch": 375.05555555555554,
      "grad_norm": 2.1313733000738466e-08,
      "learning_rate": 0.017689602828392513,
      "loss": 0.0,
      "num_input_tokens_seen": 9451264,
      "step": 33755
    },
    {
      "epoch": 375.1111111111111,
      "grad_norm": 1.7187467449275573e-08,
      "learning_rate": 0.017661861792989897,
      "loss": 0.0,
      "num_input_tokens_seen": 9452624,
      "step": 33760
    },
    {
      "epoch": 375.1666666666667,
      "grad_norm": 9.326367234052668e-09,
      "learning_rate": 0.017634141165791272,
      "loss": 0.0,
      "num_input_tokens_seen": 9454096,
      "step": 33765
    },
    {
      "epoch": 375.22222222222223,
      "grad_norm": 1.2570766649844245e-08,
      "learning_rate": 0.017606440951071455,
      "loss": 0.0,
      "num_input_tokens_seen": 9455504,
      "step": 33770
    },
    {
      "epoch": 375.27777777777777,
      "grad_norm": 1.3719369640341483e-08,
      "learning_rate": 0.017578761153102213,
      "loss": 0.0,
      "num_input_tokens_seen": 9456912,
      "step": 33775
    },
    {
      "epoch": 375.3333333333333,
      "grad_norm": 8.052789546297845e-09,
      "learning_rate": 0.017551101776152146,
      "loss": 0.0,
      "num_input_tokens_seen": 9458304,
      "step": 33780
    },
    {
      "epoch": 375.3888888888889,
      "grad_norm": 1.4476488452430658e-08,
      "learning_rate": 0.017523462824486608,
      "loss": 0.0,
      "num_input_tokens_seen": 9459744,
      "step": 33785
    },
    {
      "epoch": 375.44444444444446,
      "grad_norm": 1.1700461044483745e-08,
      "learning_rate": 0.01749584430236794,
      "loss": 0.0,
      "num_input_tokens_seen": 9461120,
      "step": 33790
    },
    {
      "epoch": 375.5,
      "grad_norm": 9.342882023588572e-09,
      "learning_rate": 0.01746824621405524,
      "loss": 0.0,
      "num_input_tokens_seen": 9462512,
      "step": 33795
    },
    {
      "epoch": 375.55555555555554,
      "grad_norm": 1.026179585750242e-08,
      "learning_rate": 0.017440668563804412,
      "loss": 0.0,
      "num_input_tokens_seen": 9463920,
      "step": 33800
    },
    {
      "epoch": 375.55555555555554,
      "eval_loss": 1.7512394189834595,
      "eval_runtime": 1.185,
      "eval_samples_per_second": 33.754,
      "eval_steps_per_second": 16.877,
      "num_input_tokens_seen": 9463920,
      "step": 33800
    },
    {
      "epoch": 375.6111111111111,
      "grad_norm": 8.826654074312046e-09,
      "learning_rate": 0.017413111355868392,
      "loss": 0.0,
      "num_input_tokens_seen": 9465312,
      "step": 33805
    },
    {
      "epoch": 375.6666666666667,
      "grad_norm": 1.1244893904915898e-08,
      "learning_rate": 0.017385574594496748,
      "loss": 0.0,
      "num_input_tokens_seen": 9466736,
      "step": 33810
    },
    {
      "epoch": 375.72222222222223,
      "grad_norm": 1.9764200942518073e-08,
      "learning_rate": 0.01735805828393605,
      "loss": 0.0,
      "num_input_tokens_seen": 9468112,
      "step": 33815
    },
    {
      "epoch": 375.77777777777777,
      "grad_norm": 1.1135769639736282e-08,
      "learning_rate": 0.017330562428429667,
      "loss": 0.0,
      "num_input_tokens_seen": 9469536,
      "step": 33820
    },
    {
      "epoch": 375.8333333333333,
      "grad_norm": 1.1048809867020282e-08,
      "learning_rate": 0.01730308703221776,
      "loss": 0.0,
      "num_input_tokens_seen": 9470928,
      "step": 33825
    },
    {
      "epoch": 375.8888888888889,
      "grad_norm": 1.1410915767839924e-08,
      "learning_rate": 0.01727563209953744,
      "loss": 0.0,
      "num_input_tokens_seen": 9472304,
      "step": 33830
    },
    {
      "epoch": 375.94444444444446,
      "grad_norm": 1.8787970290645717e-08,
      "learning_rate": 0.017248197634622535,
      "loss": 0.0,
      "num_input_tokens_seen": 9473712,
      "step": 33835
    },
    {
      "epoch": 376.0,
      "grad_norm": 2.006557942024756e-08,
      "learning_rate": 0.01722078364170383,
      "loss": 0.0,
      "num_input_tokens_seen": 9475136,
      "step": 33840
    },
    {
      "epoch": 376.05555555555554,
      "grad_norm": 1.2966853368823195e-08,
      "learning_rate": 0.017193390125008905,
      "loss": 0.0,
      "num_input_tokens_seen": 9476544,
      "step": 33845
    },
    {
      "epoch": 376.1111111111111,
      "grad_norm": 1.262714643956997e-08,
      "learning_rate": 0.017166017088762153,
      "loss": 0.0,
      "num_input_tokens_seen": 9477936,
      "step": 33850
    },
    {
      "epoch": 376.1666666666667,
      "grad_norm": 2.952294231306496e-08,
      "learning_rate": 0.017138664537184878,
      "loss": 0.0,
      "num_input_tokens_seen": 9479312,
      "step": 33855
    },
    {
      "epoch": 376.22222222222223,
      "grad_norm": 9.273056988945427e-09,
      "learning_rate": 0.017111332474495172,
      "loss": 0.0,
      "num_input_tokens_seen": 9480688,
      "step": 33860
    },
    {
      "epoch": 376.27777777777777,
      "grad_norm": 2.524205555687331e-08,
      "learning_rate": 0.017084020904907998,
      "loss": 0.0,
      "num_input_tokens_seen": 9482128,
      "step": 33865
    },
    {
      "epoch": 376.3333333333333,
      "grad_norm": 1.8722703387652473e-08,
      "learning_rate": 0.017056729832635103,
      "loss": 0.0,
      "num_input_tokens_seen": 9483568,
      "step": 33870
    },
    {
      "epoch": 376.3888888888889,
      "grad_norm": 1.4334627707057734e-08,
      "learning_rate": 0.017029459261885153,
      "loss": 0.0,
      "num_input_tokens_seen": 9484928,
      "step": 33875
    },
    {
      "epoch": 376.44444444444446,
      "grad_norm": 8.137947205000273e-09,
      "learning_rate": 0.01700220919686359,
      "loss": 0.0,
      "num_input_tokens_seen": 9486336,
      "step": 33880
    },
    {
      "epoch": 376.5,
      "grad_norm": 1.3356605599312843e-08,
      "learning_rate": 0.016974979641772723,
      "loss": 0.0,
      "num_input_tokens_seen": 9487744,
      "step": 33885
    },
    {
      "epoch": 376.55555555555554,
      "grad_norm": 1.4061285469324503e-08,
      "learning_rate": 0.01694777060081169,
      "loss": 0.0,
      "num_input_tokens_seen": 9489088,
      "step": 33890
    },
    {
      "epoch": 376.6111111111111,
      "grad_norm": 1.5691288268726566e-08,
      "learning_rate": 0.016920582078176444,
      "loss": 0.0,
      "num_input_tokens_seen": 9490480,
      "step": 33895
    },
    {
      "epoch": 376.6666666666667,
      "grad_norm": 1.1704736735396182e-08,
      "learning_rate": 0.016893414078059863,
      "loss": 0.0,
      "num_input_tokens_seen": 9491872,
      "step": 33900
    },
    {
      "epoch": 376.72222222222223,
      "grad_norm": 7.191400808181925e-09,
      "learning_rate": 0.016866266604651535,
      "loss": 0.0,
      "num_input_tokens_seen": 9493280,
      "step": 33905
    },
    {
      "epoch": 376.77777777777777,
      "grad_norm": 8.506464865831731e-09,
      "learning_rate": 0.016839139662137976,
      "loss": 0.0,
      "num_input_tokens_seen": 9494672,
      "step": 33910
    },
    {
      "epoch": 376.8333333333333,
      "grad_norm": 8.035835996622609e-09,
      "learning_rate": 0.01681203325470245,
      "loss": 0.0,
      "num_input_tokens_seen": 9496080,
      "step": 33915
    },
    {
      "epoch": 376.8888888888889,
      "grad_norm": 2.068219728812437e-08,
      "learning_rate": 0.016784947386525157,
      "loss": 0.0,
      "num_input_tokens_seen": 9497504,
      "step": 33920
    },
    {
      "epoch": 376.94444444444446,
      "grad_norm": 1.1469104777006578e-08,
      "learning_rate": 0.01675788206178308,
      "loss": 0.0,
      "num_input_tokens_seen": 9498928,
      "step": 33925
    },
    {
      "epoch": 377.0,
      "grad_norm": 1.1435196789477686e-08,
      "learning_rate": 0.016730837284649986,
      "loss": 0.0,
      "num_input_tokens_seen": 9500336,
      "step": 33930
    },
    {
      "epoch": 377.05555555555554,
      "grad_norm": 2.3363151413491323e-08,
      "learning_rate": 0.016703813059296583,
      "loss": 0.0,
      "num_input_tokens_seen": 9501760,
      "step": 33935
    },
    {
      "epoch": 377.1111111111111,
      "grad_norm": 9.241397869175216e-09,
      "learning_rate": 0.016676809389890294,
      "loss": 0.0,
      "num_input_tokens_seen": 9503136,
      "step": 33940
    },
    {
      "epoch": 377.1666666666667,
      "grad_norm": 1.0353905288695842e-08,
      "learning_rate": 0.016649826280595435,
      "loss": 0.0,
      "num_input_tokens_seen": 9504560,
      "step": 33945
    },
    {
      "epoch": 377.22222222222223,
      "grad_norm": 8.993228384213126e-09,
      "learning_rate": 0.016622863735573163,
      "loss": 0.0,
      "num_input_tokens_seen": 9505936,
      "step": 33950
    },
    {
      "epoch": 377.27777777777777,
      "grad_norm": 1.3547450272710648e-08,
      "learning_rate": 0.016595921758981395,
      "loss": 0.0,
      "num_input_tokens_seen": 9507328,
      "step": 33955
    },
    {
      "epoch": 377.3333333333333,
      "grad_norm": 2.7754150977443715e-08,
      "learning_rate": 0.01656900035497495,
      "loss": 0.0,
      "num_input_tokens_seen": 9508768,
      "step": 33960
    },
    {
      "epoch": 377.3888888888889,
      "grad_norm": 1.0898316915586292e-08,
      "learning_rate": 0.016542099527705485,
      "loss": 0.0,
      "num_input_tokens_seen": 9510112,
      "step": 33965
    },
    {
      "epoch": 377.44444444444446,
      "grad_norm": 1.3479060534393739e-08,
      "learning_rate": 0.01651521928132138,
      "loss": 0.0,
      "num_input_tokens_seen": 9511536,
      "step": 33970
    },
    {
      "epoch": 377.5,
      "grad_norm": 1.0962163621286436e-08,
      "learning_rate": 0.01648835961996794,
      "loss": 0.0,
      "num_input_tokens_seen": 9512976,
      "step": 33975
    },
    {
      "epoch": 377.55555555555554,
      "grad_norm": 1.2675315019805566e-08,
      "learning_rate": 0.016461520547787285,
      "loss": 0.0,
      "num_input_tokens_seen": 9514368,
      "step": 33980
    },
    {
      "epoch": 377.6111111111111,
      "grad_norm": 1.1366378060984061e-08,
      "learning_rate": 0.016434702068918266,
      "loss": 0.0,
      "num_input_tokens_seen": 9515776,
      "step": 33985
    },
    {
      "epoch": 377.6666666666667,
      "grad_norm": 1.039667907321018e-08,
      "learning_rate": 0.01640790418749673,
      "loss": 0.0,
      "num_input_tokens_seen": 9517152,
      "step": 33990
    },
    {
      "epoch": 377.72222222222223,
      "grad_norm": 8.584169819414456e-09,
      "learning_rate": 0.016381126907655134,
      "loss": 0.0,
      "num_input_tokens_seen": 9518544,
      "step": 33995
    },
    {
      "epoch": 377.77777777777777,
      "grad_norm": 8.037366328039752e-09,
      "learning_rate": 0.016354370233522948,
      "loss": 0.0,
      "num_input_tokens_seen": 9519984,
      "step": 34000
    },
    {
      "epoch": 377.77777777777777,
      "eval_loss": 1.7509796619415283,
      "eval_runtime": 1.1826,
      "eval_samples_per_second": 33.823,
      "eval_steps_per_second": 16.911,
      "num_input_tokens_seen": 9519984,
      "step": 34000
    },
    {
      "epoch": 377.8333333333333,
      "grad_norm": 6.571204469452141e-09,
      "learning_rate": 0.016327634169226394,
      "loss": 0.0,
      "num_input_tokens_seen": 9521376,
      "step": 34005
    },
    {
      "epoch": 377.8888888888889,
      "grad_norm": 1.1079960060556004e-08,
      "learning_rate": 0.016300918718888485,
      "loss": 0.0,
      "num_input_tokens_seen": 9522784,
      "step": 34010
    },
    {
      "epoch": 377.94444444444446,
      "grad_norm": 7.352524367121305e-09,
      "learning_rate": 0.016274223886629052,
      "loss": 0.0,
      "num_input_tokens_seen": 9524192,
      "step": 34015
    },
    {
      "epoch": 378.0,
      "grad_norm": 3.47335742389987e-08,
      "learning_rate": 0.01624754967656482,
      "loss": 0.0,
      "num_input_tokens_seen": 9525568,
      "step": 34020
    },
    {
      "epoch": 378.05555555555554,
      "grad_norm": 2.5421003968517653e-08,
      "learning_rate": 0.016220896092809235,
      "loss": 0.0,
      "num_input_tokens_seen": 9526944,
      "step": 34025
    },
    {
      "epoch": 378.1111111111111,
      "grad_norm": 1.0734854782867842e-08,
      "learning_rate": 0.01619426313947267,
      "loss": 0.0,
      "num_input_tokens_seen": 9528272,
      "step": 34030
    },
    {
      "epoch": 378.1666666666667,
      "grad_norm": 8.960152619863493e-09,
      "learning_rate": 0.016167650820662228,
      "loss": 0.0,
      "num_input_tokens_seen": 9529680,
      "step": 34035
    },
    {
      "epoch": 378.22222222222223,
      "grad_norm": 1.3918970864779112e-08,
      "learning_rate": 0.016141059140481855,
      "loss": 0.0,
      "num_input_tokens_seen": 9531104,
      "step": 34040
    },
    {
      "epoch": 378.27777777777777,
      "grad_norm": 6.524194962054253e-09,
      "learning_rate": 0.016114488103032374,
      "loss": 0.0,
      "num_input_tokens_seen": 9532512,
      "step": 34045
    },
    {
      "epoch": 378.3333333333333,
      "grad_norm": 9.043692905663647e-09,
      "learning_rate": 0.016087937712411293,
      "loss": 0.0,
      "num_input_tokens_seen": 9533920,
      "step": 34050
    },
    {
      "epoch": 378.3888888888889,
      "grad_norm": 8.914676996596427e-09,
      "learning_rate": 0.01606140797271308,
      "loss": 0.0,
      "num_input_tokens_seen": 9535344,
      "step": 34055
    },
    {
      "epoch": 378.44444444444446,
      "grad_norm": 8.906634541006042e-09,
      "learning_rate": 0.01603489888802897,
      "loss": 0.0,
      "num_input_tokens_seen": 9536704,
      "step": 34060
    },
    {
      "epoch": 378.5,
      "grad_norm": 1.9901742476235995e-08,
      "learning_rate": 0.016008410462446918,
      "loss": 0.0,
      "num_input_tokens_seen": 9538128,
      "step": 34065
    },
    {
      "epoch": 378.55555555555554,
      "grad_norm": 5.8272473069109765e-08,
      "learning_rate": 0.01598194270005185,
      "loss": 0.0,
      "num_input_tokens_seen": 9539552,
      "step": 34070
    },
    {
      "epoch": 378.6111111111111,
      "grad_norm": 8.347727842306085e-09,
      "learning_rate": 0.015955495604925356,
      "loss": 0.0,
      "num_input_tokens_seen": 9540960,
      "step": 34075
    },
    {
      "epoch": 378.6666666666667,
      "grad_norm": 1.0024250762796783e-08,
      "learning_rate": 0.01592906918114598,
      "loss": 0.0,
      "num_input_tokens_seen": 9542336,
      "step": 34080
    },
    {
      "epoch": 378.72222222222223,
      "grad_norm": 4.994605973251964e-08,
      "learning_rate": 0.015902663432788965,
      "loss": 0.0,
      "num_input_tokens_seen": 9543712,
      "step": 34085
    },
    {
      "epoch": 378.77777777777777,
      "grad_norm": 9.953524227057642e-09,
      "learning_rate": 0.01587627836392643,
      "loss": 0.0,
      "num_input_tokens_seen": 9545104,
      "step": 34090
    },
    {
      "epoch": 378.8333333333333,
      "grad_norm": 1.1179102088476611e-08,
      "learning_rate": 0.01584991397862726,
      "loss": 0.0,
      "num_input_tokens_seen": 9546512,
      "step": 34095
    },
    {
      "epoch": 378.8888888888889,
      "grad_norm": 8.867528933365065e-09,
      "learning_rate": 0.015823570280957214,
      "loss": 0.0,
      "num_input_tokens_seen": 9547920,
      "step": 34100
    },
    {
      "epoch": 378.94444444444446,
      "grad_norm": 1.1039348990493636e-08,
      "learning_rate": 0.015797247274978766,
      "loss": 0.0,
      "num_input_tokens_seen": 9549328,
      "step": 34105
    },
    {
      "epoch": 379.0,
      "grad_norm": 1.0084671764332143e-08,
      "learning_rate": 0.015770944964751326,
      "loss": 0.0,
      "num_input_tokens_seen": 9550704,
      "step": 34110
    },
    {
      "epoch": 379.05555555555554,
      "grad_norm": 2.5686432536531356e-08,
      "learning_rate": 0.015744663354330956,
      "loss": 0.0,
      "num_input_tokens_seen": 9552128,
      "step": 34115
    },
    {
      "epoch": 379.1111111111111,
      "grad_norm": 1.4755562993684634e-08,
      "learning_rate": 0.015718402447770664,
      "loss": 0.0,
      "num_input_tokens_seen": 9553568,
      "step": 34120
    },
    {
      "epoch": 379.1666666666667,
      "grad_norm": 1.116648817856003e-08,
      "learning_rate": 0.015692162249120224,
      "loss": 0.0,
      "num_input_tokens_seen": 9554976,
      "step": 34125
    },
    {
      "epoch": 379.22222222222223,
      "grad_norm": 4.033871192632432e-08,
      "learning_rate": 0.01566594276242615,
      "loss": 0.0,
      "num_input_tokens_seen": 9556416,
      "step": 34130
    },
    {
      "epoch": 379.27777777777777,
      "grad_norm": 1.1540856270642053e-08,
      "learning_rate": 0.015639743991731857,
      "loss": 0.0,
      "num_input_tokens_seen": 9557824,
      "step": 34135
    },
    {
      "epoch": 379.3333333333333,
      "grad_norm": 1.126769255677118e-08,
      "learning_rate": 0.01561356594107755,
      "loss": 0.0,
      "num_input_tokens_seen": 9559216,
      "step": 34140
    },
    {
      "epoch": 379.3888888888889,
      "grad_norm": 1.1004820166249374e-08,
      "learning_rate": 0.015587408614500147,
      "loss": 0.0,
      "num_input_tokens_seen": 9560624,
      "step": 34145
    },
    {
      "epoch": 379.44444444444446,
      "grad_norm": 9.57930179623645e-09,
      "learning_rate": 0.015561272016033505,
      "loss": 0.0,
      "num_input_tokens_seen": 9562032,
      "step": 34150
    },
    {
      "epoch": 379.5,
      "grad_norm": 8.525885775156894e-09,
      "learning_rate": 0.015535156149708167,
      "loss": 0.0,
      "num_input_tokens_seen": 9563376,
      "step": 34155
    },
    {
      "epoch": 379.55555555555554,
      "grad_norm": 1.0709451991885999e-08,
      "learning_rate": 0.015509061019551528,
      "loss": 0.0,
      "num_input_tokens_seen": 9564736,
      "step": 34160
    },
    {
      "epoch": 379.6111111111111,
      "grad_norm": 9.969923553398985e-09,
      "learning_rate": 0.015482986629587818,
      "loss": 0.0,
      "num_input_tokens_seen": 9566096,
      "step": 34165
    },
    {
      "epoch": 379.6666666666667,
      "grad_norm": 1.0404923145301836e-08,
      "learning_rate": 0.01545693298383799,
      "loss": 0.0,
      "num_input_tokens_seen": 9567504,
      "step": 34170
    },
    {
      "epoch": 379.72222222222223,
      "grad_norm": 8.645620219738248e-09,
      "learning_rate": 0.015430900086319858,
      "loss": 0.0,
      "num_input_tokens_seen": 9568896,
      "step": 34175
    },
    {
      "epoch": 379.77777777777777,
      "grad_norm": 2.1047076970148737e-08,
      "learning_rate": 0.015404887941048084,
      "loss": 0.0,
      "num_input_tokens_seen": 9570304,
      "step": 34180
    },
    {
      "epoch": 379.8333333333333,
      "grad_norm": 1.1371137809135234e-08,
      "learning_rate": 0.01537889655203397,
      "loss": 0.0,
      "num_input_tokens_seen": 9571680,
      "step": 34185
    },
    {
      "epoch": 379.8888888888889,
      "grad_norm": 1.2619943312586202e-08,
      "learning_rate": 0.015352925923285798,
      "loss": 0.0,
      "num_input_tokens_seen": 9573104,
      "step": 34190
    },
    {
      "epoch": 379.94444444444446,
      "grad_norm": 9.847461512890732e-09,
      "learning_rate": 0.015326976058808511,
      "loss": 0.0,
      "num_input_tokens_seen": 9574544,
      "step": 34195
    },
    {
      "epoch": 380.0,
      "grad_norm": 4.015722510075648e-08,
      "learning_rate": 0.015301046962603908,
      "loss": 0.0,
      "num_input_tokens_seen": 9575936,
      "step": 34200
    },
    {
      "epoch": 380.0,
      "eval_loss": 1.7469669580459595,
      "eval_runtime": 1.1842,
      "eval_samples_per_second": 33.779,
      "eval_steps_per_second": 16.89,
      "num_input_tokens_seen": 9575936,
      "step": 34200
    },
    {
      "epoch": 380.05555555555554,
      "grad_norm": 1.368170288174042e-08,
      "learning_rate": 0.015275138638670626,
      "loss": 0.0,
      "num_input_tokens_seen": 9577312,
      "step": 34205
    },
    {
      "epoch": 380.1111111111111,
      "grad_norm": 9.07576147568534e-09,
      "learning_rate": 0.015249251091004001,
      "loss": 0.0,
      "num_input_tokens_seen": 9578704,
      "step": 34210
    },
    {
      "epoch": 380.1666666666667,
      "grad_norm": 1.1857467896447815e-08,
      "learning_rate": 0.01522338432359624,
      "loss": 0.0,
      "num_input_tokens_seen": 9580112,
      "step": 34215
    },
    {
      "epoch": 380.22222222222223,
      "grad_norm": 1.0859176668986947e-08,
      "learning_rate": 0.01519753834043635,
      "loss": 0.0,
      "num_input_tokens_seen": 9581536,
      "step": 34220
    },
    {
      "epoch": 380.27777777777777,
      "grad_norm": 6.6306498069934605e-09,
      "learning_rate": 0.015171713145510095,
      "loss": 0.0,
      "num_input_tokens_seen": 9582944,
      "step": 34225
    },
    {
      "epoch": 380.3333333333333,
      "grad_norm": 8.24733525917054e-09,
      "learning_rate": 0.01514590874279999,
      "loss": 0.0,
      "num_input_tokens_seen": 9584352,
      "step": 34230
    },
    {
      "epoch": 380.3888888888889,
      "grad_norm": 1.1466733340625979e-08,
      "learning_rate": 0.015120125136285467,
      "loss": 0.0,
      "num_input_tokens_seen": 9585776,
      "step": 34235
    },
    {
      "epoch": 380.44444444444446,
      "grad_norm": 8.421075392561761e-09,
      "learning_rate": 0.015094362329942629,
      "loss": 0.0,
      "num_input_tokens_seen": 9587136,
      "step": 34240
    },
    {
      "epoch": 380.5,
      "grad_norm": 9.521480492935552e-09,
      "learning_rate": 0.01506862032774448,
      "loss": 0.0,
      "num_input_tokens_seen": 9588576,
      "step": 34245
    },
    {
      "epoch": 380.55555555555554,
      "grad_norm": 1.297699547819775e-08,
      "learning_rate": 0.015042899133660697,
      "loss": 0.0,
      "num_input_tokens_seen": 9589968,
      "step": 34250
    },
    {
      "epoch": 380.6111111111111,
      "grad_norm": 5.27478549727789e-09,
      "learning_rate": 0.01501719875165789,
      "loss": 0.0,
      "num_input_tokens_seen": 9591344,
      "step": 34255
    },
    {
      "epoch": 380.6666666666667,
      "grad_norm": 9.858242222549052e-09,
      "learning_rate": 0.014991519185699286,
      "loss": 0.0,
      "num_input_tokens_seen": 9592752,
      "step": 34260
    },
    {
      "epoch": 380.72222222222223,
      "grad_norm": 8.560309794347631e-09,
      "learning_rate": 0.014965860439745054,
      "loss": 0.0,
      "num_input_tokens_seen": 9594208,
      "step": 34265
    },
    {
      "epoch": 380.77777777777777,
      "grad_norm": 1.0562495766919255e-08,
      "learning_rate": 0.01494022251775211,
      "loss": 0.0,
      "num_input_tokens_seen": 9595568,
      "step": 34270
    },
    {
      "epoch": 380.8333333333333,
      "grad_norm": 7.787546607573859e-09,
      "learning_rate": 0.014914605423674109,
      "loss": 0.0,
      "num_input_tokens_seen": 9596944,
      "step": 34275
    },
    {
      "epoch": 380.8888888888889,
      "grad_norm": 1.3508264729011898e-08,
      "learning_rate": 0.014889009161461525,
      "loss": 0.0,
      "num_input_tokens_seen": 9598336,
      "step": 34280
    },
    {
      "epoch": 380.94444444444446,
      "grad_norm": 2.095190865247787e-08,
      "learning_rate": 0.014863433735061665,
      "loss": 0.0,
      "num_input_tokens_seen": 9599776,
      "step": 34285
    },
    {
      "epoch": 381.0,
      "grad_norm": 9.647141752111565e-09,
      "learning_rate": 0.014837879148418541,
      "loss": 0.0,
      "num_input_tokens_seen": 9601152,
      "step": 34290
    },
    {
      "epoch": 381.05555555555554,
      "grad_norm": 1.041456787476136e-08,
      "learning_rate": 0.01481234540547302,
      "loss": 0.0,
      "num_input_tokens_seen": 9602512,
      "step": 34295
    },
    {
      "epoch": 381.1111111111111,
      "grad_norm": 9.678296386539387e-09,
      "learning_rate": 0.014786832510162717,
      "loss": 0.0,
      "num_input_tokens_seen": 9603920,
      "step": 34300
    },
    {
      "epoch": 381.1666666666667,
      "grad_norm": 1.1330193672165478e-08,
      "learning_rate": 0.014761340466422017,
      "loss": 0.0,
      "num_input_tokens_seen": 9605344,
      "step": 34305
    },
    {
      "epoch": 381.22222222222223,
      "grad_norm": 7.47296891034921e-09,
      "learning_rate": 0.014735869278182144,
      "loss": 0.0,
      "num_input_tokens_seen": 9606752,
      "step": 34310
    },
    {
      "epoch": 381.27777777777777,
      "grad_norm": 2.239177199214737e-08,
      "learning_rate": 0.014710418949371057,
      "loss": 0.0,
      "num_input_tokens_seen": 9608176,
      "step": 34315
    },
    {
      "epoch": 381.3333333333333,
      "grad_norm": 2.9451401317714954e-08,
      "learning_rate": 0.014684989483913495,
      "loss": 0.0,
      "num_input_tokens_seen": 9609552,
      "step": 34320
    },
    {
      "epoch": 381.3888888888889,
      "grad_norm": 1.2899757706463788e-08,
      "learning_rate": 0.014659580885731077,
      "loss": 0.0,
      "num_input_tokens_seen": 9610944,
      "step": 34325
    },
    {
      "epoch": 381.44444444444446,
      "grad_norm": 1.4034945650109876e-08,
      "learning_rate": 0.014634193158742047,
      "loss": 0.0,
      "num_input_tokens_seen": 9612352,
      "step": 34330
    },
    {
      "epoch": 381.5,
      "grad_norm": 9.724828942125896e-09,
      "learning_rate": 0.014608826306861576,
      "loss": 0.0,
      "num_input_tokens_seen": 9613760,
      "step": 34335
    },
    {
      "epoch": 381.55555555555554,
      "grad_norm": 9.197001382688086e-09,
      "learning_rate": 0.014583480334001486,
      "loss": 0.0,
      "num_input_tokens_seen": 9615136,
      "step": 34340
    },
    {
      "epoch": 381.6111111111111,
      "grad_norm": 1.0782759574112788e-08,
      "learning_rate": 0.014558155244070496,
      "loss": 0.0,
      "num_input_tokens_seen": 9616544,
      "step": 34345
    },
    {
      "epoch": 381.6666666666667,
      "grad_norm": 1.2115059178086085e-08,
      "learning_rate": 0.014532851040974036,
      "loss": 0.0,
      "num_input_tokens_seen": 9617936,
      "step": 34350
    },
    {
      "epoch": 381.72222222222223,
      "grad_norm": 1.0515361914542609e-08,
      "learning_rate": 0.014507567728614335,
      "loss": 0.0,
      "num_input_tokens_seen": 9619344,
      "step": 34355
    },
    {
      "epoch": 381.77777777777777,
      "grad_norm": 1.359589951732687e-08,
      "learning_rate": 0.01448230531089037,
      "loss": 0.0,
      "num_input_tokens_seen": 9620720,
      "step": 34360
    },
    {
      "epoch": 381.8333333333333,
      "grad_norm": 7.940779589432623e-09,
      "learning_rate": 0.014457063791697993,
      "loss": 0.0,
      "num_input_tokens_seen": 9622144,
      "step": 34365
    },
    {
      "epoch": 381.8888888888889,
      "grad_norm": 1.4588236396662069e-08,
      "learning_rate": 0.01443184317492971,
      "loss": 0.0,
      "num_input_tokens_seen": 9623520,
      "step": 34370
    },
    {
      "epoch": 381.94444444444446,
      "grad_norm": 9.341147411134898e-09,
      "learning_rate": 0.014406643464474822,
      "loss": 0.0,
      "num_input_tokens_seen": 9624960,
      "step": 34375
    },
    {
      "epoch": 382.0,
      "grad_norm": 7.87882559194486e-09,
      "learning_rate": 0.014381464664219539,
      "loss": 0.0,
      "num_input_tokens_seen": 9626368,
      "step": 34380
    },
    {
      "epoch": 382.05555555555554,
      "grad_norm": 1.5950385900964648e-08,
      "learning_rate": 0.014356306778046656,
      "loss": 0.0,
      "num_input_tokens_seen": 9627792,
      "step": 34385
    },
    {
      "epoch": 382.1111111111111,
      "grad_norm": 1.3882328175895964e-08,
      "learning_rate": 0.014331169809835885,
      "loss": 0.0,
      "num_input_tokens_seen": 9629168,
      "step": 34390
    },
    {
      "epoch": 382.1666666666667,
      "grad_norm": 1.2627968004608192e-08,
      "learning_rate": 0.014306053763463644,
      "loss": 0.0,
      "num_input_tokens_seen": 9630544,
      "step": 34395
    },
    {
      "epoch": 382.22222222222223,
      "grad_norm": 7.879020991197194e-09,
      "learning_rate": 0.014280958642803147,
      "loss": 0.0,
      "num_input_tokens_seen": 9631952,
      "step": 34400
    },
    {
      "epoch": 382.22222222222223,
      "eval_loss": 1.76837956905365,
      "eval_runtime": 1.1999,
      "eval_samples_per_second": 33.336,
      "eval_steps_per_second": 16.668,
      "num_input_tokens_seen": 9631952,
      "step": 34400
    },
    {
      "epoch": 382.27777777777777,
      "grad_norm": 7.513587974017355e-09,
      "learning_rate": 0.014255884451724404,
      "loss": 0.0,
      "num_input_tokens_seen": 9633392,
      "step": 34405
    },
    {
      "epoch": 382.3333333333333,
      "grad_norm": 1.4235801870654541e-08,
      "learning_rate": 0.014230831194094101,
      "loss": 0.0,
      "num_input_tokens_seen": 9634816,
      "step": 34410
    },
    {
      "epoch": 382.3888888888889,
      "grad_norm": 2.430890688742693e-08,
      "learning_rate": 0.014205798873775865,
      "loss": 0.0,
      "num_input_tokens_seen": 9636176,
      "step": 34415
    },
    {
      "epoch": 382.44444444444446,
      "grad_norm": 6.915404693330629e-09,
      "learning_rate": 0.014180787494629893,
      "loss": 0.0,
      "num_input_tokens_seen": 9637568,
      "step": 34420
    },
    {
      "epoch": 382.5,
      "grad_norm": 1.4088315403171237e-08,
      "learning_rate": 0.014155797060513314,
      "loss": 0.0,
      "num_input_tokens_seen": 9638992,
      "step": 34425
    },
    {
      "epoch": 382.55555555555554,
      "grad_norm": 7.976756144500996e-09,
      "learning_rate": 0.014130827575279963,
      "loss": 0.0,
      "num_input_tokens_seen": 9640400,
      "step": 34430
    },
    {
      "epoch": 382.6111111111111,
      "grad_norm": 9.667251887890416e-09,
      "learning_rate": 0.014105879042780427,
      "loss": 0.0,
      "num_input_tokens_seen": 9641760,
      "step": 34435
    },
    {
      "epoch": 382.6666666666667,
      "grad_norm": 1.93627300859589e-08,
      "learning_rate": 0.014080951466862113,
      "loss": 0.0,
      "num_input_tokens_seen": 9643184,
      "step": 34440
    },
    {
      "epoch": 382.72222222222223,
      "grad_norm": 1.8371393295524285e-08,
      "learning_rate": 0.014056044851369126,
      "loss": 0.0,
      "num_input_tokens_seen": 9644592,
      "step": 34445
    },
    {
      "epoch": 382.77777777777777,
      "grad_norm": 2.183050362702943e-08,
      "learning_rate": 0.014031159200142428,
      "loss": 0.0,
      "num_input_tokens_seen": 9645984,
      "step": 34450
    },
    {
      "epoch": 382.8333333333333,
      "grad_norm": 1.0671755035218666e-08,
      "learning_rate": 0.014006294517019667,
      "loss": 0.0,
      "num_input_tokens_seen": 9647376,
      "step": 34455
    },
    {
      "epoch": 382.8888888888889,
      "grad_norm": 3.113681756872211e-08,
      "learning_rate": 0.013981450805835276,
      "loss": 0.0,
      "num_input_tokens_seen": 9648752,
      "step": 34460
    },
    {
      "epoch": 382.94444444444446,
      "grad_norm": 1.4972995288076163e-08,
      "learning_rate": 0.01395662807042049,
      "loss": 0.0,
      "num_input_tokens_seen": 9650160,
      "step": 34465
    },
    {
      "epoch": 383.0,
      "grad_norm": 1.2040251462508422e-08,
      "learning_rate": 0.013931826314603296,
      "loss": 0.0,
      "num_input_tokens_seen": 9651584,
      "step": 34470
    },
    {
      "epoch": 383.05555555555554,
      "grad_norm": 1.1819357936815322e-08,
      "learning_rate": 0.013907045542208401,
      "loss": 0.0,
      "num_input_tokens_seen": 9653008,
      "step": 34475
    },
    {
      "epoch": 383.1111111111111,
      "grad_norm": 1.5776059569816425e-08,
      "learning_rate": 0.013882285757057333,
      "loss": 0.0,
      "num_input_tokens_seen": 9654400,
      "step": 34480
    },
    {
      "epoch": 383.1666666666667,
      "grad_norm": 3.5776981377466655e-08,
      "learning_rate": 0.013857546962968403,
      "loss": 0.0,
      "num_input_tokens_seen": 9655840,
      "step": 34485
    },
    {
      "epoch": 383.22222222222223,
      "grad_norm": 1.082620570969084e-08,
      "learning_rate": 0.013832829163756577,
      "loss": 0.0,
      "num_input_tokens_seen": 9657216,
      "step": 34490
    },
    {
      "epoch": 383.27777777777777,
      "grad_norm": 1.1952947076565579e-08,
      "learning_rate": 0.013808132363233689,
      "loss": 0.0,
      "num_input_tokens_seen": 9658624,
      "step": 34495
    },
    {
      "epoch": 383.3333333333333,
      "grad_norm": 2.282294886413183e-08,
      "learning_rate": 0.013783456565208256,
      "loss": 0.0,
      "num_input_tokens_seen": 9660032,
      "step": 34500
    },
    {
      "epoch": 383.3888888888889,
      "grad_norm": 2.174064306359469e-08,
      "learning_rate": 0.01375880177348564,
      "loss": 0.0,
      "num_input_tokens_seen": 9661424,
      "step": 34505
    },
    {
      "epoch": 383.44444444444446,
      "grad_norm": 1.949521788446873e-08,
      "learning_rate": 0.013734167991867928,
      "loss": 0.0,
      "num_input_tokens_seen": 9662816,
      "step": 34510
    },
    {
      "epoch": 383.5,
      "grad_norm": 1.2327589615779289e-08,
      "learning_rate": 0.013709555224153935,
      "loss": 0.0,
      "num_input_tokens_seen": 9664192,
      "step": 34515
    },
    {
      "epoch": 383.55555555555554,
      "grad_norm": 1.0432935404480759e-08,
      "learning_rate": 0.013684963474139222,
      "loss": 0.0,
      "num_input_tokens_seen": 9665600,
      "step": 34520
    },
    {
      "epoch": 383.6111111111111,
      "grad_norm": 1.2784195924098185e-08,
      "learning_rate": 0.013660392745616224,
      "loss": 0.0,
      "num_input_tokens_seen": 9667008,
      "step": 34525
    },
    {
      "epoch": 383.6666666666667,
      "grad_norm": 1.2826538053900549e-08,
      "learning_rate": 0.013635843042373974,
      "loss": 0.0,
      "num_input_tokens_seen": 9668400,
      "step": 34530
    },
    {
      "epoch": 383.72222222222223,
      "grad_norm": 6.4458047788207296e-09,
      "learning_rate": 0.01361131436819843,
      "loss": 0.0,
      "num_input_tokens_seen": 9669840,
      "step": 34535
    },
    {
      "epoch": 383.77777777777777,
      "grad_norm": 1.396689963684139e-08,
      "learning_rate": 0.013586806726872147,
      "loss": 0.0,
      "num_input_tokens_seen": 9671216,
      "step": 34540
    },
    {
      "epoch": 383.8333333333333,
      "grad_norm": 9.959774338597072e-09,
      "learning_rate": 0.013562320122174537,
      "loss": 0.0,
      "num_input_tokens_seen": 9672624,
      "step": 34545
    },
    {
      "epoch": 383.8888888888889,
      "grad_norm": 3.941885395875033e-08,
      "learning_rate": 0.013537854557881762,
      "loss": 0.0,
      "num_input_tokens_seen": 9674032,
      "step": 34550
    },
    {
      "epoch": 383.94444444444446,
      "grad_norm": 7.859192407977389e-09,
      "learning_rate": 0.013513410037766687,
      "loss": 0.0,
      "num_input_tokens_seen": 9675456,
      "step": 34555
    },
    {
      "epoch": 384.0,
      "grad_norm": 1.2345512168110417e-08,
      "learning_rate": 0.013488986565598998,
      "loss": 0.0,
      "num_input_tokens_seen": 9676864,
      "step": 34560
    },
    {
      "epoch": 384.05555555555554,
      "grad_norm": 6.6143628352222095e-09,
      "learning_rate": 0.013464584145145097,
      "loss": 0.0,
      "num_input_tokens_seen": 9678256,
      "step": 34565
    },
    {
      "epoch": 384.1111111111111,
      "grad_norm": 1.1222577533942513e-08,
      "learning_rate": 0.013440202780168109,
      "loss": 0.0,
      "num_input_tokens_seen": 9679632,
      "step": 34570
    },
    {
      "epoch": 384.1666666666667,
      "grad_norm": 9.224342178981715e-09,
      "learning_rate": 0.01341584247442799,
      "loss": 0.0,
      "num_input_tokens_seen": 9680992,
      "step": 34575
    },
    {
      "epoch": 384.22222222222223,
      "grad_norm": 1.0063454958242346e-08,
      "learning_rate": 0.013391503231681355,
      "loss": 0.0,
      "num_input_tokens_seen": 9682416,
      "step": 34580
    },
    {
      "epoch": 384.27777777777777,
      "grad_norm": 1.0520739834873893e-08,
      "learning_rate": 0.013367185055681685,
      "loss": 0.0,
      "num_input_tokens_seen": 9683808,
      "step": 34585
    },
    {
      "epoch": 384.3333333333333,
      "grad_norm": 6.376394967588794e-09,
      "learning_rate": 0.013342887950179095,
      "loss": 0.0,
      "num_input_tokens_seen": 9685232,
      "step": 34590
    },
    {
      "epoch": 384.3888888888889,
      "grad_norm": 1.8142822355571298e-08,
      "learning_rate": 0.013318611918920554,
      "loss": 0.0,
      "num_input_tokens_seen": 9686592,
      "step": 34595
    },
    {
      "epoch": 384.44444444444446,
      "grad_norm": 1.1855125769955066e-08,
      "learning_rate": 0.01329435696564965,
      "loss": 0.0,
      "num_input_tokens_seen": 9687936,
      "step": 34600
    },
    {
      "epoch": 384.44444444444446,
      "eval_loss": 1.759963035583496,
      "eval_runtime": 1.1853,
      "eval_samples_per_second": 33.745,
      "eval_steps_per_second": 16.873,
      "num_input_tokens_seen": 9687936,
      "step": 34600
    },
    {
      "epoch": 384.5,
      "grad_norm": 2.284039624100842e-08,
      "learning_rate": 0.013270123094106894,
      "loss": 0.0,
      "num_input_tokens_seen": 9689328,
      "step": 34605
    },
    {
      "epoch": 384.55555555555554,
      "grad_norm": 1.2679558736294894e-08,
      "learning_rate": 0.013245910308029395,
      "loss": 0.0,
      "num_input_tokens_seen": 9690768,
      "step": 34610
    },
    {
      "epoch": 384.6111111111111,
      "grad_norm": 1.2354038680939539e-08,
      "learning_rate": 0.0132217186111511,
      "loss": 0.0,
      "num_input_tokens_seen": 9692144,
      "step": 34615
    },
    {
      "epoch": 384.6666666666667,
      "grad_norm": 1.0094479030442471e-08,
      "learning_rate": 0.013197548007202626,
      "loss": 0.0,
      "num_input_tokens_seen": 9693552,
      "step": 34620
    },
    {
      "epoch": 384.72222222222223,
      "grad_norm": 7.656296929781092e-09,
      "learning_rate": 0.01317339849991142,
      "loss": 0.0,
      "num_input_tokens_seen": 9694992,
      "step": 34625
    },
    {
      "epoch": 384.77777777777777,
      "grad_norm": 3.766946221617218e-08,
      "learning_rate": 0.013149270093001675,
      "loss": 0.0,
      "num_input_tokens_seen": 9696384,
      "step": 34630
    },
    {
      "epoch": 384.8333333333333,
      "grad_norm": 1.5664923580516188e-08,
      "learning_rate": 0.013125162790194227,
      "loss": 0.0,
      "num_input_tokens_seen": 9697808,
      "step": 34635
    },
    {
      "epoch": 384.8888888888889,
      "grad_norm": 8.949641028266342e-09,
      "learning_rate": 0.01310107659520674,
      "loss": 0.0,
      "num_input_tokens_seen": 9699264,
      "step": 34640
    },
    {
      "epoch": 384.94444444444446,
      "grad_norm": 2.619399275261003e-08,
      "learning_rate": 0.013077011511753655,
      "loss": 0.0,
      "num_input_tokens_seen": 9700672,
      "step": 34645
    },
    {
      "epoch": 385.0,
      "grad_norm": 2.542903487778858e-08,
      "learning_rate": 0.013052967543546056,
      "loss": 0.0,
      "num_input_tokens_seen": 9702048,
      "step": 34650
    },
    {
      "epoch": 385.05555555555554,
      "grad_norm": 9.993006422348572e-09,
      "learning_rate": 0.01302894469429186,
      "loss": 0.0,
      "num_input_tokens_seen": 9703440,
      "step": 34655
    },
    {
      "epoch": 385.1111111111111,
      "grad_norm": 8.027151388034781e-09,
      "learning_rate": 0.013004942967695653,
      "loss": 0.0,
      "num_input_tokens_seen": 9704784,
      "step": 34660
    },
    {
      "epoch": 385.1666666666667,
      "grad_norm": 1.0281055118355198e-08,
      "learning_rate": 0.012980962367458859,
      "loss": 0.0,
      "num_input_tokens_seen": 9706192,
      "step": 34665
    },
    {
      "epoch": 385.22222222222223,
      "grad_norm": 1.0851831433456027e-08,
      "learning_rate": 0.012957002897279567,
      "loss": 0.0,
      "num_input_tokens_seen": 9707616,
      "step": 34670
    },
    {
      "epoch": 385.27777777777777,
      "grad_norm": 1.1147427869673265e-08,
      "learning_rate": 0.012933064560852576,
      "loss": 0.0,
      "num_input_tokens_seen": 9708960,
      "step": 34675
    },
    {
      "epoch": 385.3333333333333,
      "grad_norm": 9.615712670552057e-09,
      "learning_rate": 0.012909147361869527,
      "loss": 0.0,
      "num_input_tokens_seen": 9710352,
      "step": 34680
    },
    {
      "epoch": 385.3888888888889,
      "grad_norm": 8.6566638302088e-09,
      "learning_rate": 0.012885251304018774,
      "loss": 0.0,
      "num_input_tokens_seen": 9711744,
      "step": 34685
    },
    {
      "epoch": 385.44444444444446,
      "grad_norm": 1.0532163585708076e-08,
      "learning_rate": 0.012861376390985335,
      "loss": 0.0,
      "num_input_tokens_seen": 9713120,
      "step": 34690
    },
    {
      "epoch": 385.5,
      "grad_norm": 6.286736464744536e-09,
      "learning_rate": 0.012837522626451063,
      "loss": 0.0,
      "num_input_tokens_seen": 9714512,
      "step": 34695
    },
    {
      "epoch": 385.55555555555554,
      "grad_norm": 1.006954430948781e-08,
      "learning_rate": 0.01281369001409447,
      "loss": 0.0,
      "num_input_tokens_seen": 9715968,
      "step": 34700
    },
    {
      "epoch": 385.6111111111111,
      "grad_norm": 1.7655469974897642e-08,
      "learning_rate": 0.012789878557590877,
      "loss": 0.0,
      "num_input_tokens_seen": 9717344,
      "step": 34705
    },
    {
      "epoch": 385.6666666666667,
      "grad_norm": 7.509835420194122e-09,
      "learning_rate": 0.012766088260612334,
      "loss": 0.0,
      "num_input_tokens_seen": 9718752,
      "step": 34710
    },
    {
      "epoch": 385.72222222222223,
      "grad_norm": 6.5250516101400535e-09,
      "learning_rate": 0.012742319126827523,
      "loss": 0.0,
      "num_input_tokens_seen": 9720160,
      "step": 34715
    },
    {
      "epoch": 385.77777777777777,
      "grad_norm": 1.8519937583505452e-08,
      "learning_rate": 0.012718571159902008,
      "loss": 0.0,
      "num_input_tokens_seen": 9721552,
      "step": 34720
    },
    {
      "epoch": 385.8333333333333,
      "grad_norm": 5.414424819605301e-08,
      "learning_rate": 0.01269484436349803,
      "loss": 0.0,
      "num_input_tokens_seen": 9722976,
      "step": 34725
    },
    {
      "epoch": 385.8888888888889,
      "grad_norm": 1.3265575304899357e-08,
      "learning_rate": 0.012671138741274528,
      "loss": 0.0,
      "num_input_tokens_seen": 9724352,
      "step": 34730
    },
    {
      "epoch": 385.94444444444446,
      "grad_norm": 2.345610283782662e-08,
      "learning_rate": 0.012647454296887194,
      "loss": 0.0,
      "num_input_tokens_seen": 9725776,
      "step": 34735
    },
    {
      "epoch": 386.0,
      "grad_norm": 2.9655316424737066e-08,
      "learning_rate": 0.012623791033988507,
      "loss": 0.0,
      "num_input_tokens_seen": 9727216,
      "step": 34740
    },
    {
      "epoch": 386.05555555555554,
      "grad_norm": 9.615162888110262e-09,
      "learning_rate": 0.012600148956227597,
      "loss": 0.0,
      "num_input_tokens_seen": 9728592,
      "step": 34745
    },
    {
      "epoch": 386.1111111111111,
      "grad_norm": 9.06207553441618e-09,
      "learning_rate": 0.012576528067250414,
      "loss": 0.0,
      "num_input_tokens_seen": 9730016,
      "step": 34750
    },
    {
      "epoch": 386.1666666666667,
      "grad_norm": 1.9317319299716473e-08,
      "learning_rate": 0.012552928370699561,
      "loss": 0.0,
      "num_input_tokens_seen": 9731424,
      "step": 34755
    },
    {
      "epoch": 386.22222222222223,
      "grad_norm": 1.031188201494615e-08,
      "learning_rate": 0.012529349870214411,
      "loss": 0.0,
      "num_input_tokens_seen": 9732800,
      "step": 34760
    },
    {
      "epoch": 386.27777777777777,
      "grad_norm": 1.3018861544367155e-08,
      "learning_rate": 0.012505792569431106,
      "loss": 0.0,
      "num_input_tokens_seen": 9734208,
      "step": 34765
    },
    {
      "epoch": 386.3333333333333,
      "grad_norm": 2.318808256518423e-08,
      "learning_rate": 0.012482256471982422,
      "loss": 0.0,
      "num_input_tokens_seen": 9735616,
      "step": 34770
    },
    {
      "epoch": 386.3888888888889,
      "grad_norm": 1.0023835095296363e-08,
      "learning_rate": 0.012458741581497956,
      "loss": 0.0,
      "num_input_tokens_seen": 9736992,
      "step": 34775
    },
    {
      "epoch": 386.44444444444446,
      "grad_norm": 7.988192329833055e-09,
      "learning_rate": 0.012435247901603974,
      "loss": 0.0,
      "num_input_tokens_seen": 9738400,
      "step": 34780
    },
    {
      "epoch": 386.5,
      "grad_norm": 7.98435806359521e-09,
      "learning_rate": 0.012411775435923528,
      "loss": 0.0,
      "num_input_tokens_seen": 9739744,
      "step": 34785
    },
    {
      "epoch": 386.55555555555554,
      "grad_norm": 8.672461859760006e-09,
      "learning_rate": 0.012388324188076354,
      "loss": 0.0,
      "num_input_tokens_seen": 9741168,
      "step": 34790
    },
    {
      "epoch": 386.6111111111111,
      "grad_norm": 7.732530171722374e-09,
      "learning_rate": 0.012364894161678913,
      "loss": 0.0,
      "num_input_tokens_seen": 9742544,
      "step": 34795
    },
    {
      "epoch": 386.6666666666667,
      "grad_norm": 9.773051701245095e-09,
      "learning_rate": 0.012341485360344445,
      "loss": 0.0,
      "num_input_tokens_seen": 9743968,
      "step": 34800
    },
    {
      "epoch": 386.6666666666667,
      "eval_loss": 1.7497408390045166,
      "eval_runtime": 1.1845,
      "eval_samples_per_second": 33.768,
      "eval_steps_per_second": 16.884,
      "num_input_tokens_seen": 9743968,
      "step": 34800
    },
    {
      "epoch": 386.72222222222223,
      "grad_norm": 1.341564370704873e-08,
      "learning_rate": 0.01231809778768283,
      "loss": 0.0,
      "num_input_tokens_seen": 9745376,
      "step": 34805
    },
    {
      "epoch": 386.77777777777777,
      "grad_norm": 2.2675317623566116e-08,
      "learning_rate": 0.012294731447300799,
      "loss": 0.0,
      "num_input_tokens_seen": 9746704,
      "step": 34810
    },
    {
      "epoch": 386.8333333333333,
      "grad_norm": 1.0174725950662378e-08,
      "learning_rate": 0.012271386342801671,
      "loss": 0.0,
      "num_input_tokens_seen": 9748096,
      "step": 34815
    },
    {
      "epoch": 386.8888888888889,
      "grad_norm": 1.2423425843621771e-08,
      "learning_rate": 0.012248062477785565,
      "loss": 0.0,
      "num_input_tokens_seen": 9749488,
      "step": 34820
    },
    {
      "epoch": 386.94444444444446,
      "grad_norm": 7.837345883388025e-09,
      "learning_rate": 0.012224759855849305,
      "loss": 0.0,
      "num_input_tokens_seen": 9750912,
      "step": 34825
    },
    {
      "epoch": 387.0,
      "grad_norm": 2.2161996682257268e-08,
      "learning_rate": 0.012201478480586513,
      "loss": 0.0,
      "num_input_tokens_seen": 9752320,
      "step": 34830
    },
    {
      "epoch": 387.05555555555554,
      "grad_norm": 1.3757037287120966e-08,
      "learning_rate": 0.012178218355587389,
      "loss": 0.0,
      "num_input_tokens_seen": 9753712,
      "step": 34835
    },
    {
      "epoch": 387.1111111111111,
      "grad_norm": 4.709322709572916e-08,
      "learning_rate": 0.01215497948443896,
      "loss": 0.0,
      "num_input_tokens_seen": 9755088,
      "step": 34840
    },
    {
      "epoch": 387.1666666666667,
      "grad_norm": 1.1183738379827446e-08,
      "learning_rate": 0.012131761870724993,
      "loss": 0.0,
      "num_input_tokens_seen": 9756464,
      "step": 34845
    },
    {
      "epoch": 387.22222222222223,
      "grad_norm": 9.528498878808023e-09,
      "learning_rate": 0.012108565518025893,
      "loss": 0.0,
      "num_input_tokens_seen": 9757824,
      "step": 34850
    },
    {
      "epoch": 387.27777777777777,
      "grad_norm": 1.193831433710102e-08,
      "learning_rate": 0.012085390429918862,
      "loss": 0.0,
      "num_input_tokens_seen": 9759232,
      "step": 34855
    },
    {
      "epoch": 387.3333333333333,
      "grad_norm": 8.148162145005244e-09,
      "learning_rate": 0.012062236609977744,
      "loss": 0.0,
      "num_input_tokens_seen": 9760656,
      "step": 34860
    },
    {
      "epoch": 387.3888888888889,
      "grad_norm": 1.2341044630659326e-08,
      "learning_rate": 0.01203910406177318,
      "loss": 0.0,
      "num_input_tokens_seen": 9762032,
      "step": 34865
    },
    {
      "epoch": 387.44444444444446,
      "grad_norm": 1.3314354951887708e-08,
      "learning_rate": 0.01201599278887252,
      "loss": 0.0,
      "num_input_tokens_seen": 9763424,
      "step": 34870
    },
    {
      "epoch": 387.5,
      "grad_norm": 1.1070595995477106e-08,
      "learning_rate": 0.011992902794839744,
      "loss": 0.0,
      "num_input_tokens_seen": 9764880,
      "step": 34875
    },
    {
      "epoch": 387.55555555555554,
      "grad_norm": 7.867093643199041e-09,
      "learning_rate": 0.011969834083235703,
      "loss": 0.0,
      "num_input_tokens_seen": 9766304,
      "step": 34880
    },
    {
      "epoch": 387.6111111111111,
      "grad_norm": 9.536725187331285e-09,
      "learning_rate": 0.011946786657617836,
      "loss": 0.0,
      "num_input_tokens_seen": 9767728,
      "step": 34885
    },
    {
      "epoch": 387.6666666666667,
      "grad_norm": 3.7780839790002574e-08,
      "learning_rate": 0.011923760521540332,
      "loss": 0.0,
      "num_input_tokens_seen": 9769120,
      "step": 34890
    },
    {
      "epoch": 387.72222222222223,
      "grad_norm": 1.0612661860420758e-08,
      "learning_rate": 0.011900755678554153,
      "loss": 0.0,
      "num_input_tokens_seen": 9770544,
      "step": 34895
    },
    {
      "epoch": 387.77777777777777,
      "grad_norm": 1.0470110112237307e-08,
      "learning_rate": 0.011877772132206893,
      "loss": 0.0,
      "num_input_tokens_seen": 9771984,
      "step": 34900
    },
    {
      "epoch": 387.8333333333333,
      "grad_norm": 8.18274070724101e-09,
      "learning_rate": 0.011854809886042915,
      "loss": 0.0,
      "num_input_tokens_seen": 9773424,
      "step": 34905
    },
    {
      "epoch": 387.8888888888889,
      "grad_norm": 5.360791810460341e-09,
      "learning_rate": 0.011831868943603325,
      "loss": 0.0,
      "num_input_tokens_seen": 9774816,
      "step": 34910
    },
    {
      "epoch": 387.94444444444446,
      "grad_norm": 1.1505354002849799e-08,
      "learning_rate": 0.011808949308425836,
      "loss": 0.0,
      "num_input_tokens_seen": 9776192,
      "step": 34915
    },
    {
      "epoch": 388.0,
      "grad_norm": 8.550530949946733e-09,
      "learning_rate": 0.01178605098404501,
      "loss": 0.0,
      "num_input_tokens_seen": 9777568,
      "step": 34920
    },
    {
      "epoch": 388.05555555555554,
      "grad_norm": 1.623643441917011e-08,
      "learning_rate": 0.011763173973992002,
      "loss": 0.0,
      "num_input_tokens_seen": 9778976,
      "step": 34925
    },
    {
      "epoch": 388.1111111111111,
      "grad_norm": 1.0599422672896708e-08,
      "learning_rate": 0.011740318281794776,
      "loss": 0.0,
      "num_input_tokens_seen": 9780416,
      "step": 34930
    },
    {
      "epoch": 388.1666666666667,
      "grad_norm": 1.2643121216626696e-08,
      "learning_rate": 0.01171748391097796,
      "loss": 0.0,
      "num_input_tokens_seen": 9781840,
      "step": 34935
    },
    {
      "epoch": 388.22222222222223,
      "grad_norm": 1.0816574302907611e-08,
      "learning_rate": 0.011694670865062873,
      "loss": 0.0,
      "num_input_tokens_seen": 9783232,
      "step": 34940
    },
    {
      "epoch": 388.27777777777777,
      "grad_norm": 1.1816327472047305e-08,
      "learning_rate": 0.011671879147567616,
      "loss": 0.0,
      "num_input_tokens_seen": 9784656,
      "step": 34945
    },
    {
      "epoch": 388.3333333333333,
      "grad_norm": 1.1895657792138081e-08,
      "learning_rate": 0.011649108762006893,
      "loss": 0.0,
      "num_input_tokens_seen": 9786080,
      "step": 34950
    },
    {
      "epoch": 388.3888888888889,
      "grad_norm": 5.2807681782951477e-08,
      "learning_rate": 0.011626359711892265,
      "loss": 0.0,
      "num_input_tokens_seen": 9787440,
      "step": 34955
    },
    {
      "epoch": 388.44444444444446,
      "grad_norm": 1.480880129633988e-08,
      "learning_rate": 0.01160363200073189,
      "loss": 0.0,
      "num_input_tokens_seen": 9788832,
      "step": 34960
    },
    {
      "epoch": 388.5,
      "grad_norm": 1.981518238380886e-08,
      "learning_rate": 0.011580925632030614,
      "loss": 0.0,
      "num_input_tokens_seen": 9790240,
      "step": 34965
    },
    {
      "epoch": 388.55555555555554,
      "grad_norm": 1.8333514262280914e-08,
      "learning_rate": 0.011558240609290104,
      "loss": 0.0,
      "num_input_tokens_seen": 9791600,
      "step": 34970
    },
    {
      "epoch": 388.6111111111111,
      "grad_norm": 5.967724980848743e-09,
      "learning_rate": 0.011535576936008679,
      "loss": 0.0,
      "num_input_tokens_seen": 9793008,
      "step": 34975
    },
    {
      "epoch": 388.6666666666667,
      "grad_norm": 3.064208797809442e-08,
      "learning_rate": 0.011512934615681309,
      "loss": 0.0,
      "num_input_tokens_seen": 9794416,
      "step": 34980
    },
    {
      "epoch": 388.72222222222223,
      "grad_norm": 8.238712823072092e-09,
      "learning_rate": 0.011490313651799765,
      "loss": 0.0,
      "num_input_tokens_seen": 9795792,
      "step": 34985
    },
    {
      "epoch": 388.77777777777777,
      "grad_norm": 1.3122829045641993e-08,
      "learning_rate": 0.011467714047852512,
      "loss": 0.0,
      "num_input_tokens_seen": 9797232,
      "step": 34990
    },
    {
      "epoch": 388.8333333333333,
      "grad_norm": 1.5284335574961005e-08,
      "learning_rate": 0.011445135807324624,
      "loss": 0.0,
      "num_input_tokens_seen": 9798624,
      "step": 34995
    },
    {
      "epoch": 388.8888888888889,
      "grad_norm": 9.772646691885711e-09,
      "learning_rate": 0.011422578933698002,
      "loss": 0.0,
      "num_input_tokens_seen": 9800016,
      "step": 35000
    },
    {
      "epoch": 388.8888888888889,
      "eval_loss": 1.7552423477172852,
      "eval_runtime": 1.1932,
      "eval_samples_per_second": 33.523,
      "eval_steps_per_second": 16.761,
      "num_input_tokens_seen": 9800016,
      "step": 35000
    },
    {
      "epoch": 388.94444444444446,
      "grad_norm": 1.1593354720673688e-08,
      "learning_rate": 0.011400043430451161,
      "loss": 0.0,
      "num_input_tokens_seen": 9801376,
      "step": 35005
    },
    {
      "epoch": 389.0,
      "grad_norm": 2.1962605956105108e-08,
      "learning_rate": 0.011377529301059392,
      "loss": 0.0,
      "num_input_tokens_seen": 9802816,
      "step": 35010
    },
    {
      "epoch": 389.05555555555554,
      "grad_norm": 3.333116538328795e-08,
      "learning_rate": 0.011355036548994646,
      "loss": 0.0,
      "num_input_tokens_seen": 9804256,
      "step": 35015
    },
    {
      "epoch": 389.1111111111111,
      "grad_norm": 2.201849191862948e-08,
      "learning_rate": 0.011332565177725584,
      "loss": 0.0,
      "num_input_tokens_seen": 9805648,
      "step": 35020
    },
    {
      "epoch": 389.1666666666667,
      "grad_norm": 1.3514280361448527e-08,
      "learning_rate": 0.011310115190717585,
      "loss": 0.0,
      "num_input_tokens_seen": 9807040,
      "step": 35025
    },
    {
      "epoch": 389.22222222222223,
      "grad_norm": 8.484198232849849e-09,
      "learning_rate": 0.01128768659143271,
      "loss": 0.0,
      "num_input_tokens_seen": 9808416,
      "step": 35030
    },
    {
      "epoch": 389.27777777777777,
      "grad_norm": 8.102469806203771e-09,
      "learning_rate": 0.011265279383329713,
      "loss": 0.0,
      "num_input_tokens_seen": 9809808,
      "step": 35035
    },
    {
      "epoch": 389.3333333333333,
      "grad_norm": 9.713676973888141e-09,
      "learning_rate": 0.01124289356986411,
      "loss": 0.0,
      "num_input_tokens_seen": 9811232,
      "step": 35040
    },
    {
      "epoch": 389.3888888888889,
      "grad_norm": 8.884700086753128e-09,
      "learning_rate": 0.011220529154488023,
      "loss": 0.0,
      "num_input_tokens_seen": 9812640,
      "step": 35045
    },
    {
      "epoch": 389.44444444444446,
      "grad_norm": 2.238755847372431e-08,
      "learning_rate": 0.011198186140650346,
      "loss": 0.0,
      "num_input_tokens_seen": 9814048,
      "step": 35050
    },
    {
      "epoch": 389.5,
      "grad_norm": 1.3999051695634535e-08,
      "learning_rate": 0.011175864531796685,
      "loss": 0.0,
      "num_input_tokens_seen": 9815424,
      "step": 35055
    },
    {
      "epoch": 389.55555555555554,
      "grad_norm": 1.3855608216317705e-08,
      "learning_rate": 0.011153564331369258,
      "loss": 0.0,
      "num_input_tokens_seen": 9816816,
      "step": 35060
    },
    {
      "epoch": 389.6111111111111,
      "grad_norm": 7.73724906366624e-09,
      "learning_rate": 0.011131285542807078,
      "loss": 0.0,
      "num_input_tokens_seen": 9818272,
      "step": 35065
    },
    {
      "epoch": 389.6666666666667,
      "grad_norm": 1.102967939203836e-08,
      "learning_rate": 0.011109028169545815,
      "loss": 0.0,
      "num_input_tokens_seen": 9819712,
      "step": 35070
    },
    {
      "epoch": 389.72222222222223,
      "grad_norm": 8.271894280653669e-09,
      "learning_rate": 0.011086792215017804,
      "loss": 0.0,
      "num_input_tokens_seen": 9821056,
      "step": 35075
    },
    {
      "epoch": 389.77777777777777,
      "grad_norm": 3.400718640023115e-08,
      "learning_rate": 0.011064577682652137,
      "loss": 0.0,
      "num_input_tokens_seen": 9822448,
      "step": 35080
    },
    {
      "epoch": 389.8333333333333,
      "grad_norm": 6.652655759609161e-09,
      "learning_rate": 0.011042384575874559,
      "loss": 0.0,
      "num_input_tokens_seen": 9823824,
      "step": 35085
    },
    {
      "epoch": 389.8888888888889,
      "grad_norm": 1.1901485130749734e-08,
      "learning_rate": 0.011020212898107512,
      "loss": 0.0,
      "num_input_tokens_seen": 9825248,
      "step": 35090
    },
    {
      "epoch": 389.94444444444446,
      "grad_norm": 8.65847127329289e-09,
      "learning_rate": 0.010998062652770197,
      "loss": 0.0,
      "num_input_tokens_seen": 9826624,
      "step": 35095
    },
    {
      "epoch": 390.0,
      "grad_norm": 6.3915441828044095e-09,
      "learning_rate": 0.010975933843278428,
      "loss": 0.0,
      "num_input_tokens_seen": 9828016,
      "step": 35100
    },
    {
      "epoch": 390.05555555555554,
      "grad_norm": 1.2724565401356358e-08,
      "learning_rate": 0.010953826473044714,
      "loss": 0.0,
      "num_input_tokens_seen": 9829408,
      "step": 35105
    },
    {
      "epoch": 390.1111111111111,
      "grad_norm": 1.0018498031172385e-08,
      "learning_rate": 0.010931740545478357,
      "loss": 0.0,
      "num_input_tokens_seen": 9830832,
      "step": 35110
    },
    {
      "epoch": 390.1666666666667,
      "grad_norm": 9.179683679860773e-09,
      "learning_rate": 0.010909676063985218,
      "loss": 0.0,
      "num_input_tokens_seen": 9832288,
      "step": 35115
    },
    {
      "epoch": 390.22222222222223,
      "grad_norm": 7.61353646794305e-09,
      "learning_rate": 0.010887633031967974,
      "loss": 0.0,
      "num_input_tokens_seen": 9833664,
      "step": 35120
    },
    {
      "epoch": 390.27777777777777,
      "grad_norm": 7.4430062113606255e-09,
      "learning_rate": 0.01086561145282589,
      "loss": 0.0,
      "num_input_tokens_seen": 9835072,
      "step": 35125
    },
    {
      "epoch": 390.3333333333333,
      "grad_norm": 1.2142405303450232e-08,
      "learning_rate": 0.010843611329954983,
      "loss": 0.0,
      "num_input_tokens_seen": 9836464,
      "step": 35130
    },
    {
      "epoch": 390.3888888888889,
      "grad_norm": 1.2473300614601612e-08,
      "learning_rate": 0.010821632666747988,
      "loss": 0.0,
      "num_input_tokens_seen": 9837840,
      "step": 35135
    },
    {
      "epoch": 390.44444444444446,
      "grad_norm": 8.450028232687146e-09,
      "learning_rate": 0.010799675466594244,
      "loss": 0.0,
      "num_input_tokens_seen": 9839264,
      "step": 35140
    },
    {
      "epoch": 390.5,
      "grad_norm": 9.808077905404389e-09,
      "learning_rate": 0.010777739732879826,
      "loss": 0.0,
      "num_input_tokens_seen": 9840640,
      "step": 35145
    },
    {
      "epoch": 390.55555555555554,
      "grad_norm": 8.000891504877927e-09,
      "learning_rate": 0.010755825468987562,
      "loss": 0.0,
      "num_input_tokens_seen": 9842016,
      "step": 35150
    },
    {
      "epoch": 390.6111111111111,
      "grad_norm": 1.1988431580789438e-08,
      "learning_rate": 0.010733932678296814,
      "loss": 0.0,
      "num_input_tokens_seen": 9843408,
      "step": 35155
    },
    {
      "epoch": 390.6666666666667,
      "grad_norm": 1.451780207162301e-08,
      "learning_rate": 0.010712061364183817,
      "loss": 0.0,
      "num_input_tokens_seen": 9844800,
      "step": 35160
    },
    {
      "epoch": 390.72222222222223,
      "grad_norm": 1.8481868480080266e-08,
      "learning_rate": 0.010690211530021337,
      "loss": 0.0,
      "num_input_tokens_seen": 9846160,
      "step": 35165
    },
    {
      "epoch": 390.77777777777777,
      "grad_norm": 1.3198398818303758e-08,
      "learning_rate": 0.01066838317917893,
      "loss": 0.0,
      "num_input_tokens_seen": 9847664,
      "step": 35170
    },
    {
      "epoch": 390.8333333333333,
      "grad_norm": 1.2647945801802507e-08,
      "learning_rate": 0.010646576315022787,
      "loss": 0.0,
      "num_input_tokens_seen": 9849072,
      "step": 35175
    },
    {
      "epoch": 390.8888888888889,
      "grad_norm": 1.3066094872726808e-08,
      "learning_rate": 0.010624790940915785,
      "loss": 0.0,
      "num_input_tokens_seen": 9850480,
      "step": 35180
    },
    {
      "epoch": 390.94444444444446,
      "grad_norm": 1.5704298306218334e-08,
      "learning_rate": 0.0106030270602175,
      "loss": 0.0,
      "num_input_tokens_seen": 9851840,
      "step": 35185
    },
    {
      "epoch": 391.0,
      "grad_norm": 1.3176937763148544e-08,
      "learning_rate": 0.010581284676284252,
      "loss": 0.0,
      "num_input_tokens_seen": 9853232,
      "step": 35190
    },
    {
      "epoch": 391.05555555555554,
      "grad_norm": 9.835281922221384e-09,
      "learning_rate": 0.010559563792468923,
      "loss": 0.0,
      "num_input_tokens_seen": 9854640,
      "step": 35195
    },
    {
      "epoch": 391.1111111111111,
      "grad_norm": 1.247795999859136e-08,
      "learning_rate": 0.010537864412121217,
      "loss": 0.0,
      "num_input_tokens_seen": 9856016,
      "step": 35200
    },
    {
      "epoch": 391.1111111111111,
      "eval_loss": 1.7796262502670288,
      "eval_runtime": 1.185,
      "eval_samples_per_second": 33.754,
      "eval_steps_per_second": 16.877,
      "num_input_tokens_seen": 9856016,
      "step": 35200
    },
    {
      "epoch": 391.1666666666667,
      "grad_norm": 7.3957147073144824e-09,
      "learning_rate": 0.010516186538587357,
      "loss": 0.0,
      "num_input_tokens_seen": 9857408,
      "step": 35205
    },
    {
      "epoch": 391.22222222222223,
      "grad_norm": 1.9751423607772267e-08,
      "learning_rate": 0.01049453017521042,
      "loss": 0.0,
      "num_input_tokens_seen": 9858784,
      "step": 35210
    },
    {
      "epoch": 391.27777777777777,
      "grad_norm": 2.557147738002641e-08,
      "learning_rate": 0.010472895325330083,
      "loss": 0.0,
      "num_input_tokens_seen": 9860192,
      "step": 35215
    },
    {
      "epoch": 391.3333333333333,
      "grad_norm": 5.236248323825521e-09,
      "learning_rate": 0.010451281992282662,
      "loss": 0.0,
      "num_input_tokens_seen": 9861552,
      "step": 35220
    },
    {
      "epoch": 391.3888888888889,
      "grad_norm": 1.36715172516233e-08,
      "learning_rate": 0.01042969017940124,
      "loss": 0.0,
      "num_input_tokens_seen": 9862960,
      "step": 35225
    },
    {
      "epoch": 391.44444444444446,
      "grad_norm": 1.3126207676350532e-08,
      "learning_rate": 0.01040811989001557,
      "loss": 0.0,
      "num_input_tokens_seen": 9864384,
      "step": 35230
    },
    {
      "epoch": 391.5,
      "grad_norm": 1.3504595663960117e-08,
      "learning_rate": 0.010386571127451992,
      "loss": 0.0,
      "num_input_tokens_seen": 9865824,
      "step": 35235
    },
    {
      "epoch": 391.55555555555554,
      "grad_norm": 9.52495504691342e-09,
      "learning_rate": 0.010365043895033682,
      "loss": 0.0,
      "num_input_tokens_seen": 9867232,
      "step": 35240
    },
    {
      "epoch": 391.6111111111111,
      "grad_norm": 9.00941454773374e-09,
      "learning_rate": 0.010343538196080365,
      "loss": 0.0,
      "num_input_tokens_seen": 9868624,
      "step": 35245
    },
    {
      "epoch": 391.6666666666667,
      "grad_norm": 1.2853092812292743e-08,
      "learning_rate": 0.010322054033908457,
      "loss": 0.0,
      "num_input_tokens_seen": 9870016,
      "step": 35250
    },
    {
      "epoch": 391.72222222222223,
      "grad_norm": 1.1110675046666074e-08,
      "learning_rate": 0.010300591411831156,
      "loss": 0.0,
      "num_input_tokens_seen": 9871424,
      "step": 35255
    },
    {
      "epoch": 391.77777777777777,
      "grad_norm": 7.58320428673187e-09,
      "learning_rate": 0.010279150333158198,
      "loss": 0.0,
      "num_input_tokens_seen": 9872864,
      "step": 35260
    },
    {
      "epoch": 391.8333333333333,
      "grad_norm": 1.1829334845003814e-08,
      "learning_rate": 0.010257730801196107,
      "loss": 0.0,
      "num_input_tokens_seen": 9874240,
      "step": 35265
    },
    {
      "epoch": 391.8888888888889,
      "grad_norm": 2.545291444278064e-08,
      "learning_rate": 0.010236332819248056,
      "loss": 0.0,
      "num_input_tokens_seen": 9875680,
      "step": 35270
    },
    {
      "epoch": 391.94444444444446,
      "grad_norm": 5.004042336054226e-08,
      "learning_rate": 0.010214956390613854,
      "loss": 0.0,
      "num_input_tokens_seen": 9877056,
      "step": 35275
    },
    {
      "epoch": 392.0,
      "grad_norm": 1.2076495359281125e-08,
      "learning_rate": 0.010193601518590034,
      "loss": 0.0,
      "num_input_tokens_seen": 9878496,
      "step": 35280
    },
    {
      "epoch": 392.05555555555554,
      "grad_norm": 1.984030362223166e-08,
      "learning_rate": 0.010172268206469758,
      "loss": 0.0,
      "num_input_tokens_seen": 9879904,
      "step": 35285
    },
    {
      "epoch": 392.1111111111111,
      "grad_norm": 7.4032375785293425e-09,
      "learning_rate": 0.010150956457542897,
      "loss": 0.0,
      "num_input_tokens_seen": 9881296,
      "step": 35290
    },
    {
      "epoch": 392.1666666666667,
      "grad_norm": 1.1206570782462677e-08,
      "learning_rate": 0.010129666275096054,
      "loss": 0.0,
      "num_input_tokens_seen": 9882624,
      "step": 35295
    },
    {
      "epoch": 392.22222222222223,
      "grad_norm": 2.5435472394974568e-08,
      "learning_rate": 0.010108397662412338,
      "loss": 0.0,
      "num_input_tokens_seen": 9884032,
      "step": 35300
    },
    {
      "epoch": 392.27777777777777,
      "grad_norm": 9.536436529344883e-09,
      "learning_rate": 0.010087150622771707,
      "loss": 0.0,
      "num_input_tokens_seen": 9885424,
      "step": 35305
    },
    {
      "epoch": 392.3333333333333,
      "grad_norm": 1.3049865188463627e-08,
      "learning_rate": 0.010065925159450739,
      "loss": 0.0,
      "num_input_tokens_seen": 9886832,
      "step": 35310
    },
    {
      "epoch": 392.3888888888889,
      "grad_norm": 2.6652489992784467e-08,
      "learning_rate": 0.010044721275722618,
      "loss": 0.0,
      "num_input_tokens_seen": 9888208,
      "step": 35315
    },
    {
      "epoch": 392.44444444444446,
      "grad_norm": 7.796794321279776e-09,
      "learning_rate": 0.01002353897485726,
      "loss": 0.0,
      "num_input_tokens_seen": 9889616,
      "step": 35320
    },
    {
      "epoch": 392.5,
      "grad_norm": 1.7535800367340926e-08,
      "learning_rate": 0.010002378260121236,
      "loss": 0.0,
      "num_input_tokens_seen": 9891072,
      "step": 35325
    },
    {
      "epoch": 392.55555555555554,
      "grad_norm": 1.1822099743596937e-08,
      "learning_rate": 0.009981239134777786,
      "loss": 0.0,
      "num_input_tokens_seen": 9892416,
      "step": 35330
    },
    {
      "epoch": 392.6111111111111,
      "grad_norm": 1.5235736228191854e-08,
      "learning_rate": 0.009960121602086884,
      "loss": 0.0,
      "num_input_tokens_seen": 9893840,
      "step": 35335
    },
    {
      "epoch": 392.6666666666667,
      "grad_norm": 1.6597136109908206e-08,
      "learning_rate": 0.009939025665305062,
      "loss": 0.0,
      "num_input_tokens_seen": 9895200,
      "step": 35340
    },
    {
      "epoch": 392.72222222222223,
      "grad_norm": 1.1498974217261093e-08,
      "learning_rate": 0.009917951327685597,
      "loss": 0.0,
      "num_input_tokens_seen": 9896640,
      "step": 35345
    },
    {
      "epoch": 392.77777777777777,
      "grad_norm": 7.277322300325295e-09,
      "learning_rate": 0.009896898592478425,
      "loss": 0.0,
      "num_input_tokens_seen": 9898000,
      "step": 35350
    },
    {
      "epoch": 392.8333333333333,
      "grad_norm": 1.2339368637981352e-08,
      "learning_rate": 0.009875867462930132,
      "loss": 0.0,
      "num_input_tokens_seen": 9899440,
      "step": 35355
    },
    {
      "epoch": 392.8888888888889,
      "grad_norm": 9.492612029760039e-09,
      "learning_rate": 0.009854857942284006,
      "loss": 0.0,
      "num_input_tokens_seen": 9900864,
      "step": 35360
    },
    {
      "epoch": 392.94444444444446,
      "grad_norm": 1.4315463481295865e-08,
      "learning_rate": 0.009833870033779923,
      "loss": 0.0,
      "num_input_tokens_seen": 9902272,
      "step": 35365
    },
    {
      "epoch": 393.0,
      "grad_norm": 1.1563554558335909e-08,
      "learning_rate": 0.009812903740654527,
      "loss": 0.0,
      "num_input_tokens_seen": 9903712,
      "step": 35370
    },
    {
      "epoch": 393.05555555555554,
      "grad_norm": 1.0167683583972575e-08,
      "learning_rate": 0.009791959066141097,
      "loss": 0.0,
      "num_input_tokens_seen": 9905072,
      "step": 35375
    },
    {
      "epoch": 393.1111111111111,
      "grad_norm": 2.1819401396783178e-08,
      "learning_rate": 0.009771036013469537,
      "loss": 0.0,
      "num_input_tokens_seen": 9906480,
      "step": 35380
    },
    {
      "epoch": 393.1666666666667,
      "grad_norm": 9.91088011659258e-09,
      "learning_rate": 0.00975013458586646,
      "loss": 0.0,
      "num_input_tokens_seen": 9907856,
      "step": 35385
    },
    {
      "epoch": 393.22222222222223,
      "grad_norm": 1.3287905886727458e-08,
      "learning_rate": 0.009729254786555107,
      "loss": 0.0,
      "num_input_tokens_seen": 9909280,
      "step": 35390
    },
    {
      "epoch": 393.27777777777777,
      "grad_norm": 1.1416895873139765e-08,
      "learning_rate": 0.009708396618755421,
      "loss": 0.0,
      "num_input_tokens_seen": 9910672,
      "step": 35395
    },
    {
      "epoch": 393.3333333333333,
      "grad_norm": 1.0208762724062126e-08,
      "learning_rate": 0.009687560085683994,
      "loss": 0.0,
      "num_input_tokens_seen": 9912112,
      "step": 35400
    },
    {
      "epoch": 393.3333333333333,
      "eval_loss": 1.7958481311798096,
      "eval_runtime": 1.1836,
      "eval_samples_per_second": 33.794,
      "eval_steps_per_second": 16.897,
      "num_input_tokens_seen": 9912112,
      "step": 35400
    },
    {
      "epoch": 393.3888888888889,
      "grad_norm": 9.328780414818993e-09,
      "learning_rate": 0.009666745190554054,
      "loss": 0.0,
      "num_input_tokens_seen": 9913472,
      "step": 35405
    },
    {
      "epoch": 393.44444444444446,
      "grad_norm": 9.812819889987168e-09,
      "learning_rate": 0.009645951936575553,
      "loss": 0.0,
      "num_input_tokens_seen": 9914864,
      "step": 35410
    },
    {
      "epoch": 393.5,
      "grad_norm": 1.1933182442191992e-08,
      "learning_rate": 0.00962518032695509,
      "loss": 0.0,
      "num_input_tokens_seen": 9916240,
      "step": 35415
    },
    {
      "epoch": 393.55555555555554,
      "grad_norm": 1.3794211994877514e-08,
      "learning_rate": 0.009604430364895855,
      "loss": 0.0,
      "num_input_tokens_seen": 9917664,
      "step": 35420
    },
    {
      "epoch": 393.6111111111111,
      "grad_norm": 1.7070293623078214e-08,
      "learning_rate": 0.00958370205359777,
      "loss": 0.0,
      "num_input_tokens_seen": 9919056,
      "step": 35425
    },
    {
      "epoch": 393.6666666666667,
      "grad_norm": 8.889469604866918e-09,
      "learning_rate": 0.009562995396257445,
      "loss": 0.0,
      "num_input_tokens_seen": 9920448,
      "step": 35430
    },
    {
      "epoch": 393.72222222222223,
      "grad_norm": 1.2310634289747213e-08,
      "learning_rate": 0.009542310396068026,
      "loss": 0.0,
      "num_input_tokens_seen": 9921872,
      "step": 35435
    },
    {
      "epoch": 393.77777777777777,
      "grad_norm": 1.4523675595512486e-08,
      "learning_rate": 0.009521647056219495,
      "loss": 0.0,
      "num_input_tokens_seen": 9923280,
      "step": 35440
    },
    {
      "epoch": 393.8333333333333,
      "grad_norm": 8.146986196777561e-09,
      "learning_rate": 0.00950100537989832,
      "loss": 0.0,
      "num_input_tokens_seen": 9924688,
      "step": 35445
    },
    {
      "epoch": 393.8888888888889,
      "grad_norm": 1.3264953580005567e-08,
      "learning_rate": 0.00948038537028772,
      "loss": 0.0,
      "num_input_tokens_seen": 9926064,
      "step": 35450
    },
    {
      "epoch": 393.94444444444446,
      "grad_norm": 2.0589780547197734e-08,
      "learning_rate": 0.009459787030567617,
      "loss": 0.0,
      "num_input_tokens_seen": 9927456,
      "step": 35455
    },
    {
      "epoch": 394.0,
      "grad_norm": 1.2618030176270167e-08,
      "learning_rate": 0.00943921036391449,
      "loss": 0.0,
      "num_input_tokens_seen": 9928832,
      "step": 35460
    },
    {
      "epoch": 394.05555555555554,
      "grad_norm": 1.755091894040106e-08,
      "learning_rate": 0.009418655373501483,
      "loss": 0.0,
      "num_input_tokens_seen": 9930256,
      "step": 35465
    },
    {
      "epoch": 394.1111111111111,
      "grad_norm": 1.1170500080481816e-08,
      "learning_rate": 0.00939812206249851,
      "loss": 0.0,
      "num_input_tokens_seen": 9931664,
      "step": 35470
    },
    {
      "epoch": 394.1666666666667,
      "grad_norm": 1.9762035563530844e-08,
      "learning_rate": 0.009377610434072004,
      "loss": 0.0,
      "num_input_tokens_seen": 9933056,
      "step": 35475
    },
    {
      "epoch": 394.22222222222223,
      "grad_norm": 2.0917443777079825e-08,
      "learning_rate": 0.009357120491385167,
      "loss": 0.0,
      "num_input_tokens_seen": 9934432,
      "step": 35480
    },
    {
      "epoch": 394.27777777777777,
      "grad_norm": 1.1958508849829741e-08,
      "learning_rate": 0.009336652237597743,
      "loss": 0.0,
      "num_input_tokens_seen": 9935808,
      "step": 35485
    },
    {
      "epoch": 394.3333333333333,
      "grad_norm": 1.1736252858440821e-08,
      "learning_rate": 0.009316205675866251,
      "loss": 0.0,
      "num_input_tokens_seen": 9937216,
      "step": 35490
    },
    {
      "epoch": 394.3888888888889,
      "grad_norm": 3.01228801902198e-08,
      "learning_rate": 0.00929578080934379,
      "loss": 0.0,
      "num_input_tokens_seen": 9938672,
      "step": 35495
    },
    {
      "epoch": 394.44444444444446,
      "grad_norm": 5.292240867760256e-09,
      "learning_rate": 0.00927537764118012,
      "loss": 0.0,
      "num_input_tokens_seen": 9940080,
      "step": 35500
    },
    {
      "epoch": 394.5,
      "grad_norm": 8.392901484910453e-09,
      "learning_rate": 0.009254996174521678,
      "loss": 0.0,
      "num_input_tokens_seen": 9941488,
      "step": 35505
    },
    {
      "epoch": 394.55555555555554,
      "grad_norm": 1.2895378986854666e-08,
      "learning_rate": 0.009234636412511531,
      "loss": 0.0,
      "num_input_tokens_seen": 9942832,
      "step": 35510
    },
    {
      "epoch": 394.6111111111111,
      "grad_norm": 1.1583479064825042e-08,
      "learning_rate": 0.009214298358289418,
      "loss": 0.0,
      "num_input_tokens_seen": 9944224,
      "step": 35515
    },
    {
      "epoch": 394.6666666666667,
      "grad_norm": 1.1205422367766005e-08,
      "learning_rate": 0.00919398201499173,
      "loss": 0.0,
      "num_input_tokens_seen": 9945648,
      "step": 35520
    },
    {
      "epoch": 394.72222222222223,
      "grad_norm": 1.8830128567515203e-08,
      "learning_rate": 0.009173687385751495,
      "loss": 0.0,
      "num_input_tokens_seen": 9947040,
      "step": 35525
    },
    {
      "epoch": 394.77777777777777,
      "grad_norm": 8.273733698160868e-09,
      "learning_rate": 0.009153414473698407,
      "loss": 0.0,
      "num_input_tokens_seen": 9948480,
      "step": 35530
    },
    {
      "epoch": 394.8333333333333,
      "grad_norm": 1.602507815334775e-08,
      "learning_rate": 0.009133163281958784,
      "loss": 0.0,
      "num_input_tokens_seen": 9949888,
      "step": 35535
    },
    {
      "epoch": 394.8888888888889,
      "grad_norm": 8.621928060392747e-09,
      "learning_rate": 0.009112933813655627,
      "loss": 0.0,
      "num_input_tokens_seen": 9951312,
      "step": 35540
    },
    {
      "epoch": 394.94444444444446,
      "grad_norm": 9.244223164728282e-09,
      "learning_rate": 0.009092726071908573,
      "loss": 0.0,
      "num_input_tokens_seen": 9952720,
      "step": 35545
    },
    {
      "epoch": 395.0,
      "grad_norm": 9.915140708471881e-09,
      "learning_rate": 0.0090725400598339,
      "loss": 0.0,
      "num_input_tokens_seen": 9954096,
      "step": 35550
    },
    {
      "epoch": 395.05555555555554,
      "grad_norm": 1.4259990521736654e-08,
      "learning_rate": 0.009052375780544563,
      "loss": 0.0,
      "num_input_tokens_seen": 9955504,
      "step": 35555
    },
    {
      "epoch": 395.1111111111111,
      "grad_norm": 1.1783419573418996e-08,
      "learning_rate": 0.009032233237150144,
      "loss": 0.0,
      "num_input_tokens_seen": 9956864,
      "step": 35560
    },
    {
      "epoch": 395.1666666666667,
      "grad_norm": 1.3954956301631682e-08,
      "learning_rate": 0.009012112432756875,
      "loss": 0.0,
      "num_input_tokens_seen": 9958240,
      "step": 35565
    },
    {
      "epoch": 395.22222222222223,
      "grad_norm": 2.5634653511019678e-08,
      "learning_rate": 0.008992013370467605,
      "loss": 0.0,
      "num_input_tokens_seen": 9959696,
      "step": 35570
    },
    {
      "epoch": 395.27777777777777,
      "grad_norm": 9.837348713404026e-09,
      "learning_rate": 0.008971936053381924,
      "loss": 0.0,
      "num_input_tokens_seen": 9961104,
      "step": 35575
    },
    {
      "epoch": 395.3333333333333,
      "grad_norm": 1.3343801619214446e-08,
      "learning_rate": 0.008951880484595953,
      "loss": 0.0,
      "num_input_tokens_seen": 9962496,
      "step": 35580
    },
    {
      "epoch": 395.3888888888889,
      "grad_norm": 8.386939143179006e-09,
      "learning_rate": 0.008931846667202552,
      "loss": 0.0,
      "num_input_tokens_seen": 9963888,
      "step": 35585
    },
    {
      "epoch": 395.44444444444446,
      "grad_norm": 1.2456479403510912e-08,
      "learning_rate": 0.008911834604291152,
      "loss": 0.0,
      "num_input_tokens_seen": 9965312,
      "step": 35590
    },
    {
      "epoch": 395.5,
      "grad_norm": 1.1155541379537226e-08,
      "learning_rate": 0.008891844298947882,
      "loss": 0.0,
      "num_input_tokens_seen": 9966704,
      "step": 35595
    },
    {
      "epoch": 395.55555555555554,
      "grad_norm": 9.191679417597243e-09,
      "learning_rate": 0.008871875754255508,
      "loss": 0.0,
      "num_input_tokens_seen": 9968112,
      "step": 35600
    },
    {
      "epoch": 395.55555555555554,
      "eval_loss": 1.789812445640564,
      "eval_runtime": 1.1819,
      "eval_samples_per_second": 33.844,
      "eval_steps_per_second": 16.922,
      "num_input_tokens_seen": 9968112,
      "step": 35600
    },
    {
      "epoch": 395.6111111111111,
      "grad_norm": 1.664336224393992e-08,
      "learning_rate": 0.008851928973293422,
      "loss": 0.0,
      "num_input_tokens_seen": 9969520,
      "step": 35605
    },
    {
      "epoch": 395.6666666666667,
      "grad_norm": 1.2235675583838201e-08,
      "learning_rate": 0.00883200395913764,
      "loss": 0.0,
      "num_input_tokens_seen": 9970912,
      "step": 35610
    },
    {
      "epoch": 395.72222222222223,
      "grad_norm": 1.1185314896522414e-08,
      "learning_rate": 0.00881210071486091,
      "loss": 0.0,
      "num_input_tokens_seen": 9972304,
      "step": 35615
    },
    {
      "epoch": 395.77777777777777,
      "grad_norm": 1.4486046140405051e-08,
      "learning_rate": 0.008792219243532505,
      "loss": 0.0,
      "num_input_tokens_seen": 9973712,
      "step": 35620
    },
    {
      "epoch": 395.8333333333333,
      "grad_norm": 1.1963850354845817e-08,
      "learning_rate": 0.008772359548218428,
      "loss": 0.0,
      "num_input_tokens_seen": 9975072,
      "step": 35625
    },
    {
      "epoch": 395.8888888888889,
      "grad_norm": 1.469485866323339e-08,
      "learning_rate": 0.008752521631981274,
      "loss": 0.0,
      "num_input_tokens_seen": 9976480,
      "step": 35630
    },
    {
      "epoch": 395.94444444444446,
      "grad_norm": 9.11506425893549e-09,
      "learning_rate": 0.008732705497880315,
      "loss": 0.0,
      "num_input_tokens_seen": 9977888,
      "step": 35635
    },
    {
      "epoch": 396.0,
      "grad_norm": 1.1892178797268116e-08,
      "learning_rate": 0.008712911148971459,
      "loss": 0.0,
      "num_input_tokens_seen": 9979264,
      "step": 35640
    },
    {
      "epoch": 396.05555555555554,
      "grad_norm": 9.019291979939226e-09,
      "learning_rate": 0.008693138588307208,
      "loss": 0.0,
      "num_input_tokens_seen": 9980640,
      "step": 35645
    },
    {
      "epoch": 396.1111111111111,
      "grad_norm": 1.0973089104027167e-08,
      "learning_rate": 0.008673387818936762,
      "loss": 0.0,
      "num_input_tokens_seen": 9982048,
      "step": 35650
    },
    {
      "epoch": 396.1666666666667,
      "grad_norm": 1.1644482711403725e-08,
      "learning_rate": 0.008653658843905948,
      "loss": 0.0,
      "num_input_tokens_seen": 9983424,
      "step": 35655
    },
    {
      "epoch": 396.22222222222223,
      "grad_norm": 7.798298895522748e-09,
      "learning_rate": 0.0086339516662572,
      "loss": 0.0,
      "num_input_tokens_seen": 9984816,
      "step": 35660
    },
    {
      "epoch": 396.27777777777777,
      "grad_norm": 1.2671379501227875e-08,
      "learning_rate": 0.008614266289029638,
      "loss": 0.0,
      "num_input_tokens_seen": 9986256,
      "step": 35665
    },
    {
      "epoch": 396.3333333333333,
      "grad_norm": 1.0463464761301111e-08,
      "learning_rate": 0.008594602715258965,
      "loss": 0.0,
      "num_input_tokens_seen": 9987664,
      "step": 35670
    },
    {
      "epoch": 396.3888888888889,
      "grad_norm": 1.058072918169728e-08,
      "learning_rate": 0.008574960947977573,
      "loss": 0.0,
      "num_input_tokens_seen": 9989120,
      "step": 35675
    },
    {
      "epoch": 396.44444444444446,
      "grad_norm": 3.9443612820377894e-08,
      "learning_rate": 0.008555340990214438,
      "loss": 0.0,
      "num_input_tokens_seen": 9990576,
      "step": 35680
    },
    {
      "epoch": 396.5,
      "grad_norm": 1.303196750512825e-08,
      "learning_rate": 0.008535742844995258,
      "loss": 0.0,
      "num_input_tokens_seen": 9991984,
      "step": 35685
    },
    {
      "epoch": 396.55555555555554,
      "grad_norm": 4.335595704674233e-08,
      "learning_rate": 0.008516166515342266,
      "loss": 0.0,
      "num_input_tokens_seen": 9993392,
      "step": 35690
    },
    {
      "epoch": 396.6111111111111,
      "grad_norm": 8.18537593261226e-09,
      "learning_rate": 0.008496612004274411,
      "loss": 0.0,
      "num_input_tokens_seen": 9994784,
      "step": 35695
    },
    {
      "epoch": 396.6666666666667,
      "grad_norm": 9.04051322692112e-09,
      "learning_rate": 0.008477079314807201,
      "loss": 0.0,
      "num_input_tokens_seen": 9996160,
      "step": 35700
    },
    {
      "epoch": 396.72222222222223,
      "grad_norm": 1.0896208380017924e-08,
      "learning_rate": 0.008457568449952874,
      "loss": 0.0,
      "num_input_tokens_seen": 9997584,
      "step": 35705
    },
    {
      "epoch": 396.77777777777777,
      "grad_norm": 1.0040410280964807e-08,
      "learning_rate": 0.008438079412720189,
      "loss": 0.0,
      "num_input_tokens_seen": 9998944,
      "step": 35710
    },
    {
      "epoch": 396.8333333333333,
      "grad_norm": 8.851317900848699e-09,
      "learning_rate": 0.00841861220611466,
      "loss": 0.0,
      "num_input_tokens_seen": 10000368,
      "step": 35715
    },
    {
      "epoch": 396.8888888888889,
      "grad_norm": 8.498407311208211e-09,
      "learning_rate": 0.008399166833138355,
      "loss": 0.0,
      "num_input_tokens_seen": 10001792,
      "step": 35720
    },
    {
      "epoch": 396.94444444444446,
      "grad_norm": 8.42243963461442e-09,
      "learning_rate": 0.008379743296789987,
      "loss": 0.0,
      "num_input_tokens_seen": 10003184,
      "step": 35725
    },
    {
      "epoch": 397.0,
      "grad_norm": 7.4331252264414616e-09,
      "learning_rate": 0.008360341600064896,
      "loss": 0.0,
      "num_input_tokens_seen": 10004528,
      "step": 35730
    },
    {
      "epoch": 397.05555555555554,
      "grad_norm": 2.5379117474244595e-08,
      "learning_rate": 0.008340961745955121,
      "loss": 0.0,
      "num_input_tokens_seen": 10005936,
      "step": 35735
    },
    {
      "epoch": 397.1111111111111,
      "grad_norm": 1.216095224521041e-08,
      "learning_rate": 0.008321603737449224,
      "loss": 0.0,
      "num_input_tokens_seen": 10007344,
      "step": 35740
    },
    {
      "epoch": 397.1666666666667,
      "grad_norm": 1.2260962911625484e-08,
      "learning_rate": 0.008302267577532479,
      "loss": 0.0,
      "num_input_tokens_seen": 10008752,
      "step": 35745
    },
    {
      "epoch": 397.22222222222223,
      "grad_norm": 1.9520477678725e-08,
      "learning_rate": 0.008282953269186771,
      "loss": 0.0,
      "num_input_tokens_seen": 10010176,
      "step": 35750
    },
    {
      "epoch": 397.27777777777777,
      "grad_norm": 1.26782966347605e-08,
      "learning_rate": 0.008263660815390567,
      "loss": 0.0,
      "num_input_tokens_seen": 10011536,
      "step": 35755
    },
    {
      "epoch": 397.3333333333333,
      "grad_norm": 1.2180927377869466e-08,
      "learning_rate": 0.008244390219119069,
      "loss": 0.0,
      "num_input_tokens_seen": 10012928,
      "step": 35760
    },
    {
      "epoch": 397.3888888888889,
      "grad_norm": 1.228090873439669e-08,
      "learning_rate": 0.008225141483343967,
      "loss": 0.0,
      "num_input_tokens_seen": 10014304,
      "step": 35765
    },
    {
      "epoch": 397.44444444444446,
      "grad_norm": 8.467337053730262e-09,
      "learning_rate": 0.00820591461103372,
      "loss": 0.0,
      "num_input_tokens_seen": 10015728,
      "step": 35770
    },
    {
      "epoch": 397.5,
      "grad_norm": 1.2105755509139726e-08,
      "learning_rate": 0.008186709605153358,
      "loss": 0.0,
      "num_input_tokens_seen": 10017152,
      "step": 35775
    },
    {
      "epoch": 397.55555555555554,
      "grad_norm": 1.2923784709073516e-08,
      "learning_rate": 0.008167526468664492,
      "loss": 0.0,
      "num_input_tokens_seen": 10018560,
      "step": 35780
    },
    {
      "epoch": 397.6111111111111,
      "grad_norm": 1.3891834349522014e-08,
      "learning_rate": 0.008148365204525443,
      "loss": 0.0,
      "num_input_tokens_seen": 10019920,
      "step": 35785
    },
    {
      "epoch": 397.6666666666667,
      "grad_norm": 1.9884526025748528e-08,
      "learning_rate": 0.00812922581569106,
      "loss": 0.0,
      "num_input_tokens_seen": 10021296,
      "step": 35790
    },
    {
      "epoch": 397.72222222222223,
      "grad_norm": 1.1406355859833184e-08,
      "learning_rate": 0.008110108305112934,
      "loss": 0.0,
      "num_input_tokens_seen": 10022704,
      "step": 35795
    },
    {
      "epoch": 397.77777777777777,
      "grad_norm": 5.400793057219744e-08,
      "learning_rate": 0.008091012675739223,
      "loss": 0.0,
      "num_input_tokens_seen": 10024160,
      "step": 35800
    },
    {
      "epoch": 397.77777777777777,
      "eval_loss": 1.7810821533203125,
      "eval_runtime": 1.184,
      "eval_samples_per_second": 33.783,
      "eval_steps_per_second": 16.892,
      "num_input_tokens_seen": 10024160,
      "step": 35800
    },
    {
      "epoch": 397.8333333333333,
      "grad_norm": 1.1054553716860482e-08,
      "learning_rate": 0.008071938930514671,
      "loss": 0.0,
      "num_input_tokens_seen": 10025536,
      "step": 35805
    },
    {
      "epoch": 397.8888888888889,
      "grad_norm": 2.375509566832079e-08,
      "learning_rate": 0.008052887072380726,
      "loss": 0.0,
      "num_input_tokens_seen": 10026912,
      "step": 35810
    },
    {
      "epoch": 397.94444444444446,
      "grad_norm": 2.888208605611453e-08,
      "learning_rate": 0.008033857104275437,
      "loss": 0.0,
      "num_input_tokens_seen": 10028336,
      "step": 35815
    },
    {
      "epoch": 398.0,
      "grad_norm": 8.89742857168585e-09,
      "learning_rate": 0.008014849029133424,
      "loss": 0.0,
      "num_input_tokens_seen": 10029728,
      "step": 35820
    },
    {
      "epoch": 398.05555555555554,
      "grad_norm": 1.063655830080279e-08,
      "learning_rate": 0.007995862849885975,
      "loss": 0.0,
      "num_input_tokens_seen": 10031120,
      "step": 35825
    },
    {
      "epoch": 398.1111111111111,
      "grad_norm": 1.1811541078543542e-08,
      "learning_rate": 0.007976898569461032,
      "loss": 0.0,
      "num_input_tokens_seen": 10032544,
      "step": 35830
    },
    {
      "epoch": 398.1666666666667,
      "grad_norm": 1.1940750610506257e-08,
      "learning_rate": 0.007957956190783088,
      "loss": 0.0,
      "num_input_tokens_seen": 10033984,
      "step": 35835
    },
    {
      "epoch": 398.22222222222223,
      "grad_norm": 7.127950674146177e-09,
      "learning_rate": 0.007939035716773324,
      "loss": 0.0,
      "num_input_tokens_seen": 10035376,
      "step": 35840
    },
    {
      "epoch": 398.27777777777777,
      "grad_norm": 2.076525262850737e-08,
      "learning_rate": 0.007920137150349487,
      "loss": 0.0,
      "num_input_tokens_seen": 10036800,
      "step": 35845
    },
    {
      "epoch": 398.3333333333333,
      "grad_norm": 2.3428214035448036e-08,
      "learning_rate": 0.007901260494425981,
      "loss": 0.0,
      "num_input_tokens_seen": 10038176,
      "step": 35850
    },
    {
      "epoch": 398.3888888888889,
      "grad_norm": 1.25044357091042e-08,
      "learning_rate": 0.007882405751913861,
      "loss": 0.0,
      "num_input_tokens_seen": 10039600,
      "step": 35855
    },
    {
      "epoch": 398.44444444444446,
      "grad_norm": 9.47161016284781e-09,
      "learning_rate": 0.007863572925720702,
      "loss": 0.0,
      "num_input_tokens_seen": 10040992,
      "step": 35860
    },
    {
      "epoch": 398.5,
      "grad_norm": 1.2583053710102376e-08,
      "learning_rate": 0.007844762018750827,
      "loss": 0.0,
      "num_input_tokens_seen": 10042416,
      "step": 35865
    },
    {
      "epoch": 398.55555555555554,
      "grad_norm": 1.3744176463603708e-08,
      "learning_rate": 0.007825973033905054,
      "loss": 0.0,
      "num_input_tokens_seen": 10043760,
      "step": 35870
    },
    {
      "epoch": 398.6111111111111,
      "grad_norm": 1.4543156012791769e-08,
      "learning_rate": 0.007807205974080927,
      "loss": 0.0,
      "num_input_tokens_seen": 10045216,
      "step": 35875
    },
    {
      "epoch": 398.6666666666667,
      "grad_norm": 1.1344032380122826e-08,
      "learning_rate": 0.007788460842172551,
      "loss": 0.0,
      "num_input_tokens_seen": 10046592,
      "step": 35880
    },
    {
      "epoch": 398.72222222222223,
      "grad_norm": 1.2102616686604506e-08,
      "learning_rate": 0.0077697376410706285,
      "loss": 0.0,
      "num_input_tokens_seen": 10047968,
      "step": 35885
    },
    {
      "epoch": 398.77777777777777,
      "grad_norm": 1.1526596566113767e-08,
      "learning_rate": 0.007751036373662567,
      "loss": 0.0,
      "num_input_tokens_seen": 10049392,
      "step": 35890
    },
    {
      "epoch": 398.8333333333333,
      "grad_norm": 8.628896708273714e-09,
      "learning_rate": 0.00773235704283231,
      "loss": 0.0,
      "num_input_tokens_seen": 10050832,
      "step": 35895
    },
    {
      "epoch": 398.8888888888889,
      "grad_norm": 9.544492307611563e-09,
      "learning_rate": 0.007713699651460437,
      "loss": 0.0,
      "num_input_tokens_seen": 10052176,
      "step": 35900
    },
    {
      "epoch": 398.94444444444446,
      "grad_norm": 9.76995551127402e-09,
      "learning_rate": 0.007695064202424162,
      "loss": 0.0,
      "num_input_tokens_seen": 10053600,
      "step": 35905
    },
    {
      "epoch": 399.0,
      "grad_norm": 1.1620071127538267e-08,
      "learning_rate": 0.007676450698597286,
      "loss": 0.0,
      "num_input_tokens_seen": 10055008,
      "step": 35910
    },
    {
      "epoch": 399.05555555555554,
      "grad_norm": 7.552987568715253e-09,
      "learning_rate": 0.007657859142850265,
      "loss": 0.0,
      "num_input_tokens_seen": 10056432,
      "step": 35915
    },
    {
      "epoch": 399.1111111111111,
      "grad_norm": 5.867044627905216e-09,
      "learning_rate": 0.0076392895380501535,
      "loss": 0.0,
      "num_input_tokens_seen": 10057840,
      "step": 35920
    },
    {
      "epoch": 399.1666666666667,
      "grad_norm": 8.061109113555176e-09,
      "learning_rate": 0.007620741887060611,
      "loss": 0.0,
      "num_input_tokens_seen": 10059248,
      "step": 35925
    },
    {
      "epoch": 399.22222222222223,
      "grad_norm": 1.3753644445557711e-08,
      "learning_rate": 0.007602216192741901,
      "loss": 0.0,
      "num_input_tokens_seen": 10060656,
      "step": 35930
    },
    {
      "epoch": 399.27777777777777,
      "grad_norm": 6.804227403733876e-09,
      "learning_rate": 0.007583712457950969,
      "loss": 0.0,
      "num_input_tokens_seen": 10062080,
      "step": 35935
    },
    {
      "epoch": 399.3333333333333,
      "grad_norm": 8.121824102147457e-09,
      "learning_rate": 0.007565230685541269,
      "loss": 0.0,
      "num_input_tokens_seen": 10063456,
      "step": 35940
    },
    {
      "epoch": 399.3888888888889,
      "grad_norm": 1.20792353897059e-08,
      "learning_rate": 0.007546770878362968,
      "loss": 0.0,
      "num_input_tokens_seen": 10064896,
      "step": 35945
    },
    {
      "epoch": 399.44444444444446,
      "grad_norm": 6.9663643742501336e-09,
      "learning_rate": 0.0075283330392627405,
      "loss": 0.0,
      "num_input_tokens_seen": 10066320,
      "step": 35950
    },
    {
      "epoch": 399.5,
      "grad_norm": 1.1607228955767823e-08,
      "learning_rate": 0.007509917171083979,
      "loss": 0.0,
      "num_input_tokens_seen": 10067696,
      "step": 35955
    },
    {
      "epoch": 399.55555555555554,
      "grad_norm": 1.6173537176200625e-08,
      "learning_rate": 0.007491523276666662,
      "loss": 0.0,
      "num_input_tokens_seen": 10069120,
      "step": 35960
    },
    {
      "epoch": 399.6111111111111,
      "grad_norm": 1.2574180807689572e-08,
      "learning_rate": 0.007473151358847318,
      "loss": 0.0,
      "num_input_tokens_seen": 10070464,
      "step": 35965
    },
    {
      "epoch": 399.6666666666667,
      "grad_norm": 9.177023585493771e-09,
      "learning_rate": 0.007454801420459117,
      "loss": 0.0,
      "num_input_tokens_seen": 10071840,
      "step": 35970
    },
    {
      "epoch": 399.72222222222223,
      "grad_norm": 2.277432109565325e-08,
      "learning_rate": 0.0074364734643319105,
      "loss": 0.0,
      "num_input_tokens_seen": 10073248,
      "step": 35975
    },
    {
      "epoch": 399.77777777777777,
      "grad_norm": 2.5246954749036377e-08,
      "learning_rate": 0.007418167493292022,
      "loss": 0.0,
      "num_input_tokens_seen": 10074656,
      "step": 35980
    },
    {
      "epoch": 399.8333333333333,
      "grad_norm": 1.210820155250758e-08,
      "learning_rate": 0.0073998835101625245,
      "loss": 0.0,
      "num_input_tokens_seen": 10076064,
      "step": 35985
    },
    {
      "epoch": 399.8888888888889,
      "grad_norm": 1.9378331828079354e-08,
      "learning_rate": 0.007381621517762998,
      "loss": 0.0,
      "num_input_tokens_seen": 10077456,
      "step": 35990
    },
    {
      "epoch": 399.94444444444446,
      "grad_norm": 5.453556717327501e-09,
      "learning_rate": 0.007363381518909689,
      "loss": 0.0,
      "num_input_tokens_seen": 10078848,
      "step": 35995
    },
    {
      "epoch": 400.0,
      "grad_norm": 2.8629134618540775e-08,
      "learning_rate": 0.007345163516415448,
      "loss": 0.0,
      "num_input_tokens_seen": 10080240,
      "step": 36000
    },
    {
      "epoch": 400.0,
      "eval_loss": 1.7935562133789062,
      "eval_runtime": 1.184,
      "eval_samples_per_second": 33.784,
      "eval_steps_per_second": 16.892,
      "num_input_tokens_seen": 10080240,
      "step": 36000
    },
    {
      "epoch": 400.05555555555554,
      "grad_norm": 7.636387522325094e-09,
      "learning_rate": 0.007326967513089693,
      "loss": 0.0,
      "num_input_tokens_seen": 10081712,
      "step": 36005
    },
    {
      "epoch": 400.1111111111111,
      "grad_norm": 1.0613478984566882e-08,
      "learning_rate": 0.0073087935117384815,
      "loss": 0.0,
      "num_input_tokens_seen": 10083104,
      "step": 36010
    },
    {
      "epoch": 400.1666666666667,
      "grad_norm": 1.3771876083978896e-08,
      "learning_rate": 0.007290641515164503,
      "loss": 0.0,
      "num_input_tokens_seen": 10084528,
      "step": 36015
    },
    {
      "epoch": 400.22222222222223,
      "grad_norm": 2.5206208675854214e-08,
      "learning_rate": 0.007272511526166986,
      "loss": 0.0,
      "num_input_tokens_seen": 10085984,
      "step": 36020
    },
    {
      "epoch": 400.27777777777777,
      "grad_norm": 1.1771572161478616e-08,
      "learning_rate": 0.0072544035475418265,
      "loss": 0.0,
      "num_input_tokens_seen": 10087392,
      "step": 36025
    },
    {
      "epoch": 400.3333333333333,
      "grad_norm": 1.7712958211291152e-08,
      "learning_rate": 0.007236317582081475,
      "loss": 0.0,
      "num_input_tokens_seen": 10088784,
      "step": 36030
    },
    {
      "epoch": 400.3888888888889,
      "grad_norm": 9.275839651934348e-09,
      "learning_rate": 0.007218253632575066,
      "loss": 0.0,
      "num_input_tokens_seen": 10090160,
      "step": 36035
    },
    {
      "epoch": 400.44444444444446,
      "grad_norm": 6.963573273566226e-09,
      "learning_rate": 0.007200211701808223,
      "loss": 0.0,
      "num_input_tokens_seen": 10091536,
      "step": 36040
    },
    {
      "epoch": 400.5,
      "grad_norm": 2.842546820147618e-08,
      "learning_rate": 0.007182191792563286,
      "loss": 0.0,
      "num_input_tokens_seen": 10092928,
      "step": 36045
    },
    {
      "epoch": 400.55555555555554,
      "grad_norm": 9.299403913587412e-09,
      "learning_rate": 0.0071641939076191145,
      "loss": 0.0,
      "num_input_tokens_seen": 10094304,
      "step": 36050
    },
    {
      "epoch": 400.6111111111111,
      "grad_norm": 8.827364617047806e-09,
      "learning_rate": 0.007146218049751257,
      "loss": 0.0,
      "num_input_tokens_seen": 10095680,
      "step": 36055
    },
    {
      "epoch": 400.6666666666667,
      "grad_norm": 3.303113871311325e-08,
      "learning_rate": 0.0071282642217317775,
      "loss": 0.0,
      "num_input_tokens_seen": 10097072,
      "step": 36060
    },
    {
      "epoch": 400.72222222222223,
      "grad_norm": 1.2429238971378709e-08,
      "learning_rate": 0.007110332426329396,
      "loss": 0.0,
      "num_input_tokens_seen": 10098432,
      "step": 36065
    },
    {
      "epoch": 400.77777777777777,
      "grad_norm": 3.817151039697819e-08,
      "learning_rate": 0.007092422666309417,
      "loss": 0.0,
      "num_input_tokens_seen": 10099856,
      "step": 36070
    },
    {
      "epoch": 400.8333333333333,
      "grad_norm": 1.0471003619727526e-08,
      "learning_rate": 0.0070745349444337295,
      "loss": 0.0,
      "num_input_tokens_seen": 10101264,
      "step": 36075
    },
    {
      "epoch": 400.8888888888889,
      "grad_norm": 9.140115331263132e-09,
      "learning_rate": 0.007056669263460913,
      "loss": 0.0,
      "num_input_tokens_seen": 10102608,
      "step": 36080
    },
    {
      "epoch": 400.94444444444446,
      "grad_norm": 1.4320503005649243e-08,
      "learning_rate": 0.007038825626145995,
      "loss": 0.0,
      "num_input_tokens_seen": 10104032,
      "step": 36085
    },
    {
      "epoch": 401.0,
      "grad_norm": 2.6213266224317522e-08,
      "learning_rate": 0.007021004035240724,
      "loss": 0.0,
      "num_input_tokens_seen": 10105376,
      "step": 36090
    },
    {
      "epoch": 401.05555555555554,
      "grad_norm": 9.357543184762562e-09,
      "learning_rate": 0.007003204493493453,
      "loss": 0.0,
      "num_input_tokens_seen": 10106800,
      "step": 36095
    },
    {
      "epoch": 401.1111111111111,
      "grad_norm": 1.151453421499582e-08,
      "learning_rate": 0.006985427003649036,
      "loss": 0.0,
      "num_input_tokens_seen": 10108240,
      "step": 36100
    },
    {
      "epoch": 401.1666666666667,
      "grad_norm": 7.189330020196394e-09,
      "learning_rate": 0.006967671568449013,
      "loss": 0.0,
      "num_input_tokens_seen": 10109648,
      "step": 36105
    },
    {
      "epoch": 401.22222222222223,
      "grad_norm": 1.3441272983527597e-08,
      "learning_rate": 0.006949938190631511,
      "loss": 0.0,
      "num_input_tokens_seen": 10111072,
      "step": 36110
    },
    {
      "epoch": 401.27777777777777,
      "grad_norm": 6.502498095528608e-09,
      "learning_rate": 0.0069322268729311905,
      "loss": 0.0,
      "num_input_tokens_seen": 10112448,
      "step": 36115
    },
    {
      "epoch": 401.3333333333333,
      "grad_norm": 1.131475535487425e-08,
      "learning_rate": 0.006914537618079403,
      "loss": 0.0,
      "num_input_tokens_seen": 10113824,
      "step": 36120
    },
    {
      "epoch": 401.3888888888889,
      "grad_norm": 1.1842920422111547e-08,
      "learning_rate": 0.006896870428804031,
      "loss": 0.0,
      "num_input_tokens_seen": 10115232,
      "step": 36125
    },
    {
      "epoch": 401.44444444444446,
      "grad_norm": 1.1698131352488872e-08,
      "learning_rate": 0.006879225307829595,
      "loss": 0.0,
      "num_input_tokens_seen": 10116656,
      "step": 36130
    },
    {
      "epoch": 401.5,
      "grad_norm": 2.2037344393766034e-08,
      "learning_rate": 0.00686160225787717,
      "loss": 0.0,
      "num_input_tokens_seen": 10118096,
      "step": 36135
    },
    {
      "epoch": 401.55555555555554,
      "grad_norm": 1.1235583130542182e-08,
      "learning_rate": 0.006844001281664463,
      "loss": 0.0,
      "num_input_tokens_seen": 10119488,
      "step": 36140
    },
    {
      "epoch": 401.6111111111111,
      "grad_norm": 1.0466832733868614e-08,
      "learning_rate": 0.006826422381905789,
      "loss": 0.0,
      "num_input_tokens_seen": 10120896,
      "step": 36145
    },
    {
      "epoch": 401.6666666666667,
      "grad_norm": 1.4141872561879154e-08,
      "learning_rate": 0.006808865561311994,
      "loss": 0.0,
      "num_input_tokens_seen": 10122304,
      "step": 36150
    },
    {
      "epoch": 401.72222222222223,
      "grad_norm": 9.878251994166476e-09,
      "learning_rate": 0.00679133082259058,
      "loss": 0.0,
      "num_input_tokens_seen": 10123712,
      "step": 36155
    },
    {
      "epoch": 401.77777777777777,
      "grad_norm": 8.199259937669012e-09,
      "learning_rate": 0.00677381816844565,
      "loss": 0.0,
      "num_input_tokens_seen": 10125104,
      "step": 36160
    },
    {
      "epoch": 401.8333333333333,
      "grad_norm": 1.3126941311725204e-08,
      "learning_rate": 0.0067563276015778434,
      "loss": 0.0,
      "num_input_tokens_seen": 10126496,
      "step": 36165
    },
    {
      "epoch": 401.8888888888889,
      "grad_norm": 8.26247070762065e-09,
      "learning_rate": 0.006738859124684437,
      "loss": 0.0,
      "num_input_tokens_seen": 10127840,
      "step": 36170
    },
    {
      "epoch": 401.94444444444446,
      "grad_norm": 7.269554203048756e-08,
      "learning_rate": 0.006721412740459259,
      "loss": 0.0,
      "num_input_tokens_seen": 10129216,
      "step": 36175
    },
    {
      "epoch": 402.0,
      "grad_norm": 1.2222042933274224e-08,
      "learning_rate": 0.006703988451592824,
      "loss": 0.0,
      "num_input_tokens_seen": 10130624,
      "step": 36180
    },
    {
      "epoch": 402.05555555555554,
      "grad_norm": 9.736882411459646e-09,
      "learning_rate": 0.006686586260772114,
      "loss": 0.0,
      "num_input_tokens_seen": 10132032,
      "step": 36185
    },
    {
      "epoch": 402.1111111111111,
      "grad_norm": 8.482054170144693e-09,
      "learning_rate": 0.006669206170680819,
      "loss": 0.0,
      "num_input_tokens_seen": 10133392,
      "step": 36190
    },
    {
      "epoch": 402.1666666666667,
      "grad_norm": 9.154867974814351e-09,
      "learning_rate": 0.0066518481839991095,
      "loss": 0.0,
      "num_input_tokens_seen": 10134800,
      "step": 36195
    },
    {
      "epoch": 402.22222222222223,
      "grad_norm": 1.1795621368548836e-08,
      "learning_rate": 0.006634512303403861,
      "loss": 0.0,
      "num_input_tokens_seen": 10136208,
      "step": 36200
    },
    {
      "epoch": 402.22222222222223,
      "eval_loss": 1.7834364175796509,
      "eval_runtime": 1.1821,
      "eval_samples_per_second": 33.839,
      "eval_steps_per_second": 16.92,
      "num_input_tokens_seen": 10136208,
      "step": 36200
    },
    {
      "epoch": 402.27777777777777,
      "grad_norm": 8.200692569459989e-09,
      "learning_rate": 0.0066171985315684355,
      "loss": 0.0,
      "num_input_tokens_seen": 10137648,
      "step": 36205
    },
    {
      "epoch": 402.3333333333333,
      "grad_norm": 1.1673947142298857e-08,
      "learning_rate": 0.0065999068711628806,
      "loss": 0.0,
      "num_input_tokens_seen": 10139056,
      "step": 36210
    },
    {
      "epoch": 402.3888888888889,
      "grad_norm": 1.2393473802774224e-08,
      "learning_rate": 0.0065826373248537295,
      "loss": 0.0,
      "num_input_tokens_seen": 10140432,
      "step": 36215
    },
    {
      "epoch": 402.44444444444446,
      "grad_norm": 1.1020305556996846e-08,
      "learning_rate": 0.006565389895304218,
      "loss": 0.0,
      "num_input_tokens_seen": 10141824,
      "step": 36220
    },
    {
      "epoch": 402.5,
      "grad_norm": 8.13831224633077e-09,
      "learning_rate": 0.006548164585174104,
      "loss": 0.0,
      "num_input_tokens_seen": 10143216,
      "step": 36225
    },
    {
      "epoch": 402.55555555555554,
      "grad_norm": 1.1788314324689964e-08,
      "learning_rate": 0.006530961397119728,
      "loss": 0.0,
      "num_input_tokens_seen": 10144624,
      "step": 36230
    },
    {
      "epoch": 402.6111111111111,
      "grad_norm": 8.924405214827402e-09,
      "learning_rate": 0.00651378033379405,
      "loss": 0.0,
      "num_input_tokens_seen": 10146032,
      "step": 36235
    },
    {
      "epoch": 402.6666666666667,
      "grad_norm": 1.449185393909147e-08,
      "learning_rate": 0.006496621397846619,
      "loss": 0.0,
      "num_input_tokens_seen": 10147408,
      "step": 36240
    },
    {
      "epoch": 402.72222222222223,
      "grad_norm": 7.933552481631523e-09,
      "learning_rate": 0.006479484591923518,
      "loss": 0.0,
      "num_input_tokens_seen": 10148816,
      "step": 36245
    },
    {
      "epoch": 402.77777777777777,
      "grad_norm": 1.2376315972062457e-08,
      "learning_rate": 0.006462369918667515,
      "loss": 0.0,
      "num_input_tokens_seen": 10150224,
      "step": 36250
    },
    {
      "epoch": 402.8333333333333,
      "grad_norm": 2.198392579089159e-08,
      "learning_rate": 0.006445277380717851,
      "loss": 0.0,
      "num_input_tokens_seen": 10151648,
      "step": 36255
    },
    {
      "epoch": 402.8888888888889,
      "grad_norm": 9.44323641505207e-09,
      "learning_rate": 0.006428206980710466,
      "loss": 0.0,
      "num_input_tokens_seen": 10152992,
      "step": 36260
    },
    {
      "epoch": 402.94444444444446,
      "grad_norm": 1.2768285984066097e-08,
      "learning_rate": 0.006411158721277788,
      "loss": 0.0,
      "num_input_tokens_seen": 10154384,
      "step": 36265
    },
    {
      "epoch": 403.0,
      "grad_norm": 1.160555118673301e-08,
      "learning_rate": 0.00639413260504888,
      "loss": 0.0,
      "num_input_tokens_seen": 10155744,
      "step": 36270
    },
    {
      "epoch": 403.05555555555554,
      "grad_norm": 9.021623448290939e-09,
      "learning_rate": 0.006377128634649376,
      "loss": 0.0,
      "num_input_tokens_seen": 10157088,
      "step": 36275
    },
    {
      "epoch": 403.1111111111111,
      "grad_norm": 9.31099108925082e-09,
      "learning_rate": 0.006360146812701528,
      "loss": 0.0,
      "num_input_tokens_seen": 10158512,
      "step": 36280
    },
    {
      "epoch": 403.1666666666667,
      "grad_norm": 2.682444488755209e-08,
      "learning_rate": 0.006343187141824125,
      "loss": 0.0,
      "num_input_tokens_seen": 10159920,
      "step": 36285
    },
    {
      "epoch": 403.22222222222223,
      "grad_norm": 8.221707759048513e-09,
      "learning_rate": 0.00632624962463259,
      "loss": 0.0,
      "num_input_tokens_seen": 10161296,
      "step": 36290
    },
    {
      "epoch": 403.27777777777777,
      "grad_norm": 9.05449670796088e-09,
      "learning_rate": 0.006309334263738853,
      "loss": 0.0,
      "num_input_tokens_seen": 10162704,
      "step": 36295
    },
    {
      "epoch": 403.3333333333333,
      "grad_norm": 2.3347800137685226e-08,
      "learning_rate": 0.006292441061751508,
      "loss": 0.0,
      "num_input_tokens_seen": 10164128,
      "step": 36300
    },
    {
      "epoch": 403.3888888888889,
      "grad_norm": 7.0085914849471465e-09,
      "learning_rate": 0.0062755700212757054,
      "loss": 0.0,
      "num_input_tokens_seen": 10165552,
      "step": 36305
    },
    {
      "epoch": 403.44444444444446,
      "grad_norm": 6.2732339323190445e-09,
      "learning_rate": 0.006258721144913148,
      "loss": 0.0,
      "num_input_tokens_seen": 10166976,
      "step": 36310
    },
    {
      "epoch": 403.5,
      "grad_norm": 1.0897845292845432e-08,
      "learning_rate": 0.0062418944352621575,
      "loss": 0.0,
      "num_input_tokens_seen": 10168384,
      "step": 36315
    },
    {
      "epoch": 403.55555555555554,
      "grad_norm": 2.0754860940996878e-08,
      "learning_rate": 0.0062250898949176405,
      "loss": 0.0,
      "num_input_tokens_seen": 10169760,
      "step": 36320
    },
    {
      "epoch": 403.6111111111111,
      "grad_norm": 9.186877925060344e-09,
      "learning_rate": 0.006208307526471041,
      "loss": 0.0,
      "num_input_tokens_seen": 10171200,
      "step": 36325
    },
    {
      "epoch": 403.6666666666667,
      "grad_norm": 9.290601177269764e-09,
      "learning_rate": 0.006191547332510405,
      "loss": 0.0,
      "num_input_tokens_seen": 10172624,
      "step": 36330
    },
    {
      "epoch": 403.72222222222223,
      "grad_norm": 1.5916922890824026e-08,
      "learning_rate": 0.006174809315620416,
      "loss": 0.0,
      "num_input_tokens_seen": 10174000,
      "step": 36335
    },
    {
      "epoch": 403.77777777777777,
      "grad_norm": 1.1130662613823006e-08,
      "learning_rate": 0.00615809347838221,
      "loss": 0.0,
      "num_input_tokens_seen": 10175408,
      "step": 36340
    },
    {
      "epoch": 403.8333333333333,
      "grad_norm": 1.4898944300512085e-08,
      "learning_rate": 0.006141399823373655,
      "loss": 0.0,
      "num_input_tokens_seen": 10176816,
      "step": 36345
    },
    {
      "epoch": 403.8888888888889,
      "grad_norm": 1.0609384482052064e-08,
      "learning_rate": 0.0061247283531690455,
      "loss": 0.0,
      "num_input_tokens_seen": 10178208,
      "step": 36350
    },
    {
      "epoch": 403.94444444444446,
      "grad_norm": 1.2114931280393648e-08,
      "learning_rate": 0.0061080790703393895,
      "loss": 0.0,
      "num_input_tokens_seen": 10179600,
      "step": 36355
    },
    {
      "epoch": 404.0,
      "grad_norm": 1.6276707981432992e-08,
      "learning_rate": 0.006091451977452217,
      "loss": 0.0,
      "num_input_tokens_seen": 10180976,
      "step": 36360
    },
    {
      "epoch": 404.05555555555554,
      "grad_norm": 2.7267789803886444e-08,
      "learning_rate": 0.00607484707707161,
      "loss": 0.0,
      "num_input_tokens_seen": 10182384,
      "step": 36365
    },
    {
      "epoch": 404.1111111111111,
      "grad_norm": 9.713991389048715e-09,
      "learning_rate": 0.006058264371758254,
      "loss": 0.0,
      "num_input_tokens_seen": 10183728,
      "step": 36370
    },
    {
      "epoch": 404.1666666666667,
      "grad_norm": 1.135749894132232e-08,
      "learning_rate": 0.00604170386406942,
      "loss": 0.0,
      "num_input_tokens_seen": 10185152,
      "step": 36375
    },
    {
      "epoch": 404.22222222222223,
      "grad_norm": 7.877332564021344e-09,
      "learning_rate": 0.006025165556558931,
      "loss": 0.0,
      "num_input_tokens_seen": 10186560,
      "step": 36380
    },
    {
      "epoch": 404.27777777777777,
      "grad_norm": 1.454958020730146e-08,
      "learning_rate": 0.006008649451777248,
      "loss": 0.0,
      "num_input_tokens_seen": 10187984,
      "step": 36385
    },
    {
      "epoch": 404.3333333333333,
      "grad_norm": 9.200814332643859e-09,
      "learning_rate": 0.005992155552271283,
      "loss": 0.0,
      "num_input_tokens_seen": 10189392,
      "step": 36390
    },
    {
      "epoch": 404.3888888888889,
      "grad_norm": 1.195771304196569e-08,
      "learning_rate": 0.005975683860584685,
      "loss": 0.0,
      "num_input_tokens_seen": 10190800,
      "step": 36395
    },
    {
      "epoch": 404.44444444444446,
      "grad_norm": 1.3409932719810058e-08,
      "learning_rate": 0.0059592343792575385,
      "loss": 0.0,
      "num_input_tokens_seen": 10192208,
      "step": 36400
    },
    {
      "epoch": 404.44444444444446,
      "eval_loss": 1.7830196619033813,
      "eval_runtime": 1.1905,
      "eval_samples_per_second": 33.6,
      "eval_steps_per_second": 16.8,
      "num_input_tokens_seen": 10192208,
      "step": 36400
    },
    {
      "epoch": 404.5,
      "grad_norm": 1.0335948097406344e-08,
      "learning_rate": 0.0059428071108265975,
      "loss": 0.0,
      "num_input_tokens_seen": 10193616,
      "step": 36405
    },
    {
      "epoch": 404.55555555555554,
      "grad_norm": 2.5573344331064618e-08,
      "learning_rate": 0.005926402057825136,
      "loss": 0.0,
      "num_input_tokens_seen": 10195008,
      "step": 36410
    },
    {
      "epoch": 404.6111111111111,
      "grad_norm": 1.4385045155052012e-08,
      "learning_rate": 0.005910019222782997,
      "loss": 0.0,
      "num_input_tokens_seen": 10196432,
      "step": 36415
    },
    {
      "epoch": 404.6666666666667,
      "grad_norm": 1.1693239265753164e-08,
      "learning_rate": 0.005893658608226643,
      "loss": 0.0,
      "num_input_tokens_seen": 10197856,
      "step": 36420
    },
    {
      "epoch": 404.72222222222223,
      "grad_norm": 1.3665551357178174e-08,
      "learning_rate": 0.0058773202166791045,
      "loss": 0.0,
      "num_input_tokens_seen": 10199248,
      "step": 36425
    },
    {
      "epoch": 404.77777777777777,
      "grad_norm": 9.590078065002672e-09,
      "learning_rate": 0.005861004050659918,
      "loss": 0.0,
      "num_input_tokens_seen": 10200704,
      "step": 36430
    },
    {
      "epoch": 404.8333333333333,
      "grad_norm": 1.2159331319594457e-08,
      "learning_rate": 0.005844710112685286,
      "loss": 0.0,
      "num_input_tokens_seen": 10202128,
      "step": 36435
    },
    {
      "epoch": 404.8888888888889,
      "grad_norm": 9.929402189357006e-09,
      "learning_rate": 0.005828438405267933,
      "loss": 0.0,
      "num_input_tokens_seen": 10203488,
      "step": 36440
    },
    {
      "epoch": 404.94444444444446,
      "grad_norm": 1.8878434815405853e-08,
      "learning_rate": 0.00581218893091715,
      "loss": 0.0,
      "num_input_tokens_seen": 10204880,
      "step": 36445
    },
    {
      "epoch": 405.0,
      "grad_norm": 9.085316499124474e-09,
      "learning_rate": 0.005795961692138801,
      "loss": 0.0,
      "num_input_tokens_seen": 10206272,
      "step": 36450
    },
    {
      "epoch": 405.05555555555554,
      "grad_norm": 9.405141554452712e-09,
      "learning_rate": 0.00577975669143535,
      "loss": 0.0,
      "num_input_tokens_seen": 10207648,
      "step": 36455
    },
    {
      "epoch": 405.1111111111111,
      "grad_norm": 1.3539401599871326e-08,
      "learning_rate": 0.005763573931305782,
      "loss": 0.0,
      "num_input_tokens_seen": 10209040,
      "step": 36460
    },
    {
      "epoch": 405.1666666666667,
      "grad_norm": 6.872018065706698e-09,
      "learning_rate": 0.005747413414245733,
      "loss": 0.0,
      "num_input_tokens_seen": 10210416,
      "step": 36465
    },
    {
      "epoch": 405.22222222222223,
      "grad_norm": 2.3340332333532388e-08,
      "learning_rate": 0.005731275142747294,
      "loss": 0.0,
      "num_input_tokens_seen": 10211792,
      "step": 36470
    },
    {
      "epoch": 405.27777777777777,
      "grad_norm": 1.3845241397802965e-08,
      "learning_rate": 0.005715159119299256,
      "loss": 0.0,
      "num_input_tokens_seen": 10213200,
      "step": 36475
    },
    {
      "epoch": 405.3333333333333,
      "grad_norm": 1.3662605269360029e-08,
      "learning_rate": 0.005699065346386867,
      "loss": 0.0,
      "num_input_tokens_seen": 10214608,
      "step": 36480
    },
    {
      "epoch": 405.3888888888889,
      "grad_norm": 8.649513993930213e-09,
      "learning_rate": 0.0056829938264919885,
      "loss": 0.0,
      "num_input_tokens_seen": 10215968,
      "step": 36485
    },
    {
      "epoch": 405.44444444444446,
      "grad_norm": 2.393639064734998e-08,
      "learning_rate": 0.005666944562093074,
      "loss": 0.0,
      "num_input_tokens_seen": 10217376,
      "step": 36490
    },
    {
      "epoch": 405.5,
      "grad_norm": 1.3508652862981307e-08,
      "learning_rate": 0.005650917555665108,
      "loss": 0.0,
      "num_input_tokens_seen": 10218784,
      "step": 36495
    },
    {
      "epoch": 405.55555555555554,
      "grad_norm": 1.3151722377813257e-08,
      "learning_rate": 0.005634912809679632,
      "loss": 0.0,
      "num_input_tokens_seen": 10220224,
      "step": 36500
    },
    {
      "epoch": 405.6111111111111,
      "grad_norm": 6.034289068423959e-09,
      "learning_rate": 0.005618930326604854,
      "loss": 0.0,
      "num_input_tokens_seen": 10221648,
      "step": 36505
    },
    {
      "epoch": 405.6666666666667,
      "grad_norm": 9.528585032114734e-09,
      "learning_rate": 0.005602970108905386,
      "loss": 0.0,
      "num_input_tokens_seen": 10223056,
      "step": 36510
    },
    {
      "epoch": 405.72222222222223,
      "grad_norm": 8.577679011523287e-09,
      "learning_rate": 0.005587032159042543,
      "loss": 0.0,
      "num_input_tokens_seen": 10224464,
      "step": 36515
    },
    {
      "epoch": 405.77777777777777,
      "grad_norm": 8.008907315115721e-09,
      "learning_rate": 0.005571116479474158,
      "loss": 0.0,
      "num_input_tokens_seen": 10225840,
      "step": 36520
    },
    {
      "epoch": 405.8333333333333,
      "grad_norm": 1.205930466596783e-08,
      "learning_rate": 0.005555223072654619,
      "loss": 0.0,
      "num_input_tokens_seen": 10227200,
      "step": 36525
    },
    {
      "epoch": 405.8888888888889,
      "grad_norm": 1.3552690525386879e-08,
      "learning_rate": 0.005539351941034881,
      "loss": 0.0,
      "num_input_tokens_seen": 10228624,
      "step": 36530
    },
    {
      "epoch": 405.94444444444446,
      "grad_norm": 9.218590335535737e-09,
      "learning_rate": 0.0055235030870624865,
      "loss": 0.0,
      "num_input_tokens_seen": 10230000,
      "step": 36535
    },
    {
      "epoch": 406.0,
      "grad_norm": 2.5818780002850872e-08,
      "learning_rate": 0.005507676513181514,
      "loss": 0.0,
      "num_input_tokens_seen": 10231360,
      "step": 36540
    },
    {
      "epoch": 406.05555555555554,
      "grad_norm": 7.384755473793803e-09,
      "learning_rate": 0.005491872221832628,
      "loss": 0.0,
      "num_input_tokens_seen": 10232736,
      "step": 36545
    },
    {
      "epoch": 406.1111111111111,
      "grad_norm": 3.758729860692256e-08,
      "learning_rate": 0.005476090215453061,
      "loss": 0.0,
      "num_input_tokens_seen": 10234144,
      "step": 36550
    },
    {
      "epoch": 406.1666666666667,
      "grad_norm": 1.1803973798407696e-08,
      "learning_rate": 0.0054603304964765675,
      "loss": 0.0,
      "num_input_tokens_seen": 10235520,
      "step": 36555
    },
    {
      "epoch": 406.22222222222223,
      "grad_norm": 2.868388548904477e-08,
      "learning_rate": 0.005444593067333519,
      "loss": 0.0,
      "num_input_tokens_seen": 10236960,
      "step": 36560
    },
    {
      "epoch": 406.27777777777777,
      "grad_norm": 1.2149445005604775e-08,
      "learning_rate": 0.00542887793045081,
      "loss": 0.0,
      "num_input_tokens_seen": 10238384,
      "step": 36565
    },
    {
      "epoch": 406.3333333333333,
      "grad_norm": 1.1352250695040311e-08,
      "learning_rate": 0.005413185088251932,
      "loss": 0.0,
      "num_input_tokens_seen": 10239776,
      "step": 36570
    },
    {
      "epoch": 406.3888888888889,
      "grad_norm": 8.731107392634385e-09,
      "learning_rate": 0.005397514543156884,
      "loss": 0.0,
      "num_input_tokens_seen": 10241184,
      "step": 36575
    },
    {
      "epoch": 406.44444444444446,
      "grad_norm": 1.696030693665307e-08,
      "learning_rate": 0.0053818662975822825,
      "loss": 0.0,
      "num_input_tokens_seen": 10242576,
      "step": 36580
    },
    {
      "epoch": 406.5,
      "grad_norm": 2.981354541020664e-08,
      "learning_rate": 0.005366240353941315,
      "loss": 0.0,
      "num_input_tokens_seen": 10244000,
      "step": 36585
    },
    {
      "epoch": 406.55555555555554,
      "grad_norm": 2.0559397739816632e-08,
      "learning_rate": 0.005350636714643636,
      "loss": 0.0,
      "num_input_tokens_seen": 10245392,
      "step": 36590
    },
    {
      "epoch": 406.6111111111111,
      "grad_norm": 1.2285532591249648e-08,
      "learning_rate": 0.005335055382095555,
      "loss": 0.0,
      "num_input_tokens_seen": 10246816,
      "step": 36595
    },
    {
      "epoch": 406.6666666666667,
      "grad_norm": 2.5999788988428918e-08,
      "learning_rate": 0.005319496358699915,
      "loss": 0.0,
      "num_input_tokens_seen": 10248192,
      "step": 36600
    },
    {
      "epoch": 406.6666666666667,
      "eval_loss": 1.8049618005752563,
      "eval_runtime": 1.1841,
      "eval_samples_per_second": 33.78,
      "eval_steps_per_second": 16.89,
      "num_input_tokens_seen": 10248192,
      "step": 36600
    },
    {
      "epoch": 406.72222222222223,
      "grad_norm": 2.171546142903935e-08,
      "learning_rate": 0.005303959646856099,
      "loss": 0.0,
      "num_input_tokens_seen": 10249600,
      "step": 36605
    },
    {
      "epoch": 406.77777777777777,
      "grad_norm": 1.2244941061112513e-08,
      "learning_rate": 0.005288445248960089,
      "loss": 0.0,
      "num_input_tokens_seen": 10250992,
      "step": 36610
    },
    {
      "epoch": 406.8333333333333,
      "grad_norm": 1.4003541437546119e-08,
      "learning_rate": 0.005272953167404354,
      "loss": 0.0,
      "num_input_tokens_seen": 10252384,
      "step": 36615
    },
    {
      "epoch": 406.8888888888889,
      "grad_norm": 2.2248912046052283e-08,
      "learning_rate": 0.005257483404578017,
      "loss": 0.0,
      "num_input_tokens_seen": 10253776,
      "step": 36620
    },
    {
      "epoch": 406.94444444444446,
      "grad_norm": 1.3747005311870453e-08,
      "learning_rate": 0.0052420359628666865,
      "loss": 0.0,
      "num_input_tokens_seen": 10255168,
      "step": 36625
    },
    {
      "epoch": 407.0,
      "grad_norm": 1.437468277742937e-08,
      "learning_rate": 0.00522661084465254,
      "loss": 0.0,
      "num_input_tokens_seen": 10256544,
      "step": 36630
    },
    {
      "epoch": 407.05555555555554,
      "grad_norm": 9.828722724591898e-09,
      "learning_rate": 0.005211208052314326,
      "loss": 0.0,
      "num_input_tokens_seen": 10257952,
      "step": 36635
    },
    {
      "epoch": 407.1111111111111,
      "grad_norm": 9.370603848424253e-09,
      "learning_rate": 0.005195827588227391,
      "loss": 0.0,
      "num_input_tokens_seen": 10259328,
      "step": 36640
    },
    {
      "epoch": 407.1666666666667,
      "grad_norm": 2.4073667503898832e-08,
      "learning_rate": 0.0051804694547635255,
      "loss": 0.0,
      "num_input_tokens_seen": 10260704,
      "step": 36645
    },
    {
      "epoch": 407.22222222222223,
      "grad_norm": 1.073169197951529e-08,
      "learning_rate": 0.005165133654291232,
      "loss": 0.0,
      "num_input_tokens_seen": 10262096,
      "step": 36650
    },
    {
      "epoch": 407.27777777777777,
      "grad_norm": 7.574620930483889e-09,
      "learning_rate": 0.005149820189175402,
      "loss": 0.0,
      "num_input_tokens_seen": 10263488,
      "step": 36655
    },
    {
      "epoch": 407.3333333333333,
      "grad_norm": 1.2979452179706641e-08,
      "learning_rate": 0.005134529061777598,
      "loss": 0.0,
      "num_input_tokens_seen": 10264864,
      "step": 36660
    },
    {
      "epoch": 407.3888888888889,
      "grad_norm": 1.5024754773662607e-08,
      "learning_rate": 0.005119260274455933,
      "loss": 0.0,
      "num_input_tokens_seen": 10266320,
      "step": 36665
    },
    {
      "epoch": 407.44444444444446,
      "grad_norm": 8.828421549367249e-09,
      "learning_rate": 0.005104013829565007,
      "loss": 0.0,
      "num_input_tokens_seen": 10267728,
      "step": 36670
    },
    {
      "epoch": 407.5,
      "grad_norm": 9.852806570620487e-09,
      "learning_rate": 0.005088789729456006,
      "loss": 0.0,
      "num_input_tokens_seen": 10269104,
      "step": 36675
    },
    {
      "epoch": 407.55555555555554,
      "grad_norm": 1.3180083691111122e-08,
      "learning_rate": 0.005073587976476735,
      "loss": 0.0,
      "num_input_tokens_seen": 10270528,
      "step": 36680
    },
    {
      "epoch": 407.6111111111111,
      "grad_norm": 3.000091908234026e-08,
      "learning_rate": 0.005058408572971418,
      "loss": 0.0,
      "num_input_tokens_seen": 10271920,
      "step": 36685
    },
    {
      "epoch": 407.6666666666667,
      "grad_norm": 1.2939103122278084e-08,
      "learning_rate": 0.005043251521280983,
      "loss": 0.0,
      "num_input_tokens_seen": 10273296,
      "step": 36690
    },
    {
      "epoch": 407.72222222222223,
      "grad_norm": 1.496850288162932e-08,
      "learning_rate": 0.005028116823742795,
      "loss": 0.0,
      "num_input_tokens_seen": 10274688,
      "step": 36695
    },
    {
      "epoch": 407.77777777777777,
      "grad_norm": 6.056150247957248e-09,
      "learning_rate": 0.005013004482690819,
      "loss": 0.0,
      "num_input_tokens_seen": 10276128,
      "step": 36700
    },
    {
      "epoch": 407.8333333333333,
      "grad_norm": 8.771572801435923e-09,
      "learning_rate": 0.0049979145004555746,
      "loss": 0.0,
      "num_input_tokens_seen": 10277520,
      "step": 36705
    },
    {
      "epoch": 407.8888888888889,
      "grad_norm": 1.7577868050011602e-08,
      "learning_rate": 0.004982846879364116,
      "loss": 0.0,
      "num_input_tokens_seen": 10278912,
      "step": 36710
    },
    {
      "epoch": 407.94444444444446,
      "grad_norm": 9.713490456420004e-09,
      "learning_rate": 0.0049678016217400535,
      "loss": 0.0,
      "num_input_tokens_seen": 10280288,
      "step": 36715
    },
    {
      "epoch": 408.0,
      "grad_norm": 2.4790564268073467e-08,
      "learning_rate": 0.004952778729903595,
      "loss": 0.0,
      "num_input_tokens_seen": 10281680,
      "step": 36720
    },
    {
      "epoch": 408.05555555555554,
      "grad_norm": 9.33397359403898e-09,
      "learning_rate": 0.004937778206171422,
      "loss": 0.0,
      "num_input_tokens_seen": 10283104,
      "step": 36725
    },
    {
      "epoch": 408.1111111111111,
      "grad_norm": 1.4689100602538474e-08,
      "learning_rate": 0.004922800052856835,
      "loss": 0.0,
      "num_input_tokens_seen": 10284544,
      "step": 36730
    },
    {
      "epoch": 408.1666666666667,
      "grad_norm": 8.29463697726851e-09,
      "learning_rate": 0.004907844272269602,
      "loss": 0.0,
      "num_input_tokens_seen": 10285952,
      "step": 36735
    },
    {
      "epoch": 408.22222222222223,
      "grad_norm": 1.474941502266347e-08,
      "learning_rate": 0.004892910866716144,
      "loss": 0.0,
      "num_input_tokens_seen": 10287328,
      "step": 36740
    },
    {
      "epoch": 408.27777777777777,
      "grad_norm": 6.682718378669961e-09,
      "learning_rate": 0.004877999838499369,
      "loss": 0.0,
      "num_input_tokens_seen": 10288688,
      "step": 36745
    },
    {
      "epoch": 408.3333333333333,
      "grad_norm": 1.1478434203127108e-08,
      "learning_rate": 0.0048631111899187065,
      "loss": 0.0,
      "num_input_tokens_seen": 10290064,
      "step": 36750
    },
    {
      "epoch": 408.3888888888889,
      "grad_norm": 2.3069132382147473e-08,
      "learning_rate": 0.0048482449232702335,
      "loss": 0.0,
      "num_input_tokens_seen": 10291472,
      "step": 36755
    },
    {
      "epoch": 408.44444444444446,
      "grad_norm": 8.478936663891545e-09,
      "learning_rate": 0.004833401040846469,
      "loss": 0.0,
      "num_input_tokens_seen": 10292896,
      "step": 36760
    },
    {
      "epoch": 408.5,
      "grad_norm": 1.1374660324747765e-08,
      "learning_rate": 0.004818579544936546,
      "loss": 0.0,
      "num_input_tokens_seen": 10294352,
      "step": 36765
    },
    {
      "epoch": 408.55555555555554,
      "grad_norm": 1.2500550816696432e-08,
      "learning_rate": 0.004803780437826121,
      "loss": 0.0,
      "num_input_tokens_seen": 10295760,
      "step": 36770
    },
    {
      "epoch": 408.6111111111111,
      "grad_norm": 8.87186679676688e-09,
      "learning_rate": 0.004789003721797402,
      "loss": 0.0,
      "num_input_tokens_seen": 10297168,
      "step": 36775
    },
    {
      "epoch": 408.6666666666667,
      "grad_norm": 2.3008501770505063e-08,
      "learning_rate": 0.004774249399129132,
      "loss": 0.0,
      "num_input_tokens_seen": 10298592,
      "step": 36780
    },
    {
      "epoch": 408.72222222222223,
      "grad_norm": 1.1640670649626372e-08,
      "learning_rate": 0.004759517472096642,
      "loss": 0.0,
      "num_input_tokens_seen": 10299952,
      "step": 36785
    },
    {
      "epoch": 408.77777777777777,
      "grad_norm": 4.0919694299645926e-08,
      "learning_rate": 0.004744807942971746,
      "loss": 0.0,
      "num_input_tokens_seen": 10301392,
      "step": 36790
    },
    {
      "epoch": 408.8333333333333,
      "grad_norm": 1.6061134644473896e-08,
      "learning_rate": 0.004730120814022881,
      "loss": 0.0,
      "num_input_tokens_seen": 10302768,
      "step": 36795
    },
    {
      "epoch": 408.8888888888889,
      "grad_norm": 1.2110320746216985e-08,
      "learning_rate": 0.004715456087514935,
      "loss": 0.0,
      "num_input_tokens_seen": 10304144,
      "step": 36800
    },
    {
      "epoch": 408.8888888888889,
      "eval_loss": 1.7913951873779297,
      "eval_runtime": 1.1836,
      "eval_samples_per_second": 33.796,
      "eval_steps_per_second": 16.898,
      "num_input_tokens_seen": 10304144,
      "step": 36800
    },
    {
      "epoch": 408.94444444444446,
      "grad_norm": 1.2194642629026475e-08,
      "learning_rate": 0.004700813765709432,
      "loss": 0.0,
      "num_input_tokens_seen": 10305552,
      "step": 36805
    },
    {
      "epoch": 409.0,
      "grad_norm": 1.58795057103589e-08,
      "learning_rate": 0.004686193850864401,
      "loss": 0.0,
      "num_input_tokens_seen": 10306960,
      "step": 36810
    },
    {
      "epoch": 409.05555555555554,
      "grad_norm": 5.917213830031187e-09,
      "learning_rate": 0.004671596345234385,
      "loss": 0.0,
      "num_input_tokens_seen": 10308320,
      "step": 36815
    },
    {
      "epoch": 409.1111111111111,
      "grad_norm": 1.825121387355466e-08,
      "learning_rate": 0.00465702125107052,
      "loss": 0.0,
      "num_input_tokens_seen": 10309728,
      "step": 36820
    },
    {
      "epoch": 409.1666666666667,
      "grad_norm": 9.700822367619821e-09,
      "learning_rate": 0.004642468570620506,
      "loss": 0.0,
      "num_input_tokens_seen": 10311136,
      "step": 36825
    },
    {
      "epoch": 409.22222222222223,
      "grad_norm": 1.0811387340936562e-08,
      "learning_rate": 0.004627938306128482,
      "loss": 0.0,
      "num_input_tokens_seen": 10312544,
      "step": 36830
    },
    {
      "epoch": 409.27777777777777,
      "grad_norm": 1.3845165014458871e-08,
      "learning_rate": 0.004613430459835255,
      "loss": 0.0,
      "num_input_tokens_seen": 10313936,
      "step": 36835
    },
    {
      "epoch": 409.3333333333333,
      "grad_norm": 7.168984517136323e-09,
      "learning_rate": 0.004598945033978085,
      "loss": 0.0,
      "num_input_tokens_seen": 10315376,
      "step": 36840
    },
    {
      "epoch": 409.3888888888889,
      "grad_norm": 2.2761767581869208e-08,
      "learning_rate": 0.004584482030790804,
      "loss": 0.0,
      "num_input_tokens_seen": 10316752,
      "step": 36845
    },
    {
      "epoch": 409.44444444444446,
      "grad_norm": 1.1356066309531343e-08,
      "learning_rate": 0.004570041452503826,
      "loss": 0.0,
      "num_input_tokens_seen": 10318112,
      "step": 36850
    },
    {
      "epoch": 409.5,
      "grad_norm": 1.219744394376221e-08,
      "learning_rate": 0.004555623301344003,
      "loss": 0.0,
      "num_input_tokens_seen": 10319520,
      "step": 36855
    },
    {
      "epoch": 409.55555555555554,
      "grad_norm": 1.1448267223101993e-08,
      "learning_rate": 0.004541227579534857,
      "loss": 0.0,
      "num_input_tokens_seen": 10320880,
      "step": 36860
    },
    {
      "epoch": 409.6111111111111,
      "grad_norm": 6.486166714836372e-09,
      "learning_rate": 0.004526854289296378,
      "loss": 0.0,
      "num_input_tokens_seen": 10322304,
      "step": 36865
    },
    {
      "epoch": 409.6666666666667,
      "grad_norm": 2.241324104090836e-08,
      "learning_rate": 0.004512503432845078,
      "loss": 0.0,
      "num_input_tokens_seen": 10323760,
      "step": 36870
    },
    {
      "epoch": 409.72222222222223,
      "grad_norm": 1.231893786979299e-08,
      "learning_rate": 0.004498175012394068,
      "loss": 0.0,
      "num_input_tokens_seen": 10325168,
      "step": 36875
    },
    {
      "epoch": 409.77777777777777,
      "grad_norm": 9.164915049097999e-09,
      "learning_rate": 0.004483869030152965,
      "loss": 0.0,
      "num_input_tokens_seen": 10326608,
      "step": 36880
    },
    {
      "epoch": 409.8333333333333,
      "grad_norm": 8.549200458674022e-09,
      "learning_rate": 0.004469585488327904,
      "loss": 0.0,
      "num_input_tokens_seen": 10327984,
      "step": 36885
    },
    {
      "epoch": 409.8888888888889,
      "grad_norm": 1.3607369453438878e-08,
      "learning_rate": 0.0044553243891216395,
      "loss": 0.0,
      "num_input_tokens_seen": 10329360,
      "step": 36890
    },
    {
      "epoch": 409.94444444444446,
      "grad_norm": 1.1365537844199025e-08,
      "learning_rate": 0.004441085734733363,
      "loss": 0.0,
      "num_input_tokens_seen": 10330752,
      "step": 36895
    },
    {
      "epoch": 410.0,
      "grad_norm": 9.286469371261319e-09,
      "learning_rate": 0.004426869527358884,
      "loss": 0.0,
      "num_input_tokens_seen": 10332176,
      "step": 36900
    },
    {
      "epoch": 410.05555555555554,
      "grad_norm": 8.33139246481096e-09,
      "learning_rate": 0.0044126757691905156,
      "loss": 0.0,
      "num_input_tokens_seen": 10333600,
      "step": 36905
    },
    {
      "epoch": 410.1111111111111,
      "grad_norm": 1.4666687420117341e-08,
      "learning_rate": 0.004398504462417107,
      "loss": 0.0,
      "num_input_tokens_seen": 10335024,
      "step": 36910
    },
    {
      "epoch": 410.1666666666667,
      "grad_norm": 1.1486323003850885e-08,
      "learning_rate": 0.0043843556092240605,
      "loss": 0.0,
      "num_input_tokens_seen": 10336448,
      "step": 36915
    },
    {
      "epoch": 410.22222222222223,
      "grad_norm": 1.3636645590509033e-08,
      "learning_rate": 0.004370229211793281,
      "loss": 0.0,
      "num_input_tokens_seen": 10337856,
      "step": 36920
    },
    {
      "epoch": 410.27777777777777,
      "grad_norm": 1.0040555942225637e-08,
      "learning_rate": 0.0043561252723032405,
      "loss": 0.0,
      "num_input_tokens_seen": 10339200,
      "step": 36925
    },
    {
      "epoch": 410.3333333333333,
      "grad_norm": 1.1344753580999622e-08,
      "learning_rate": 0.004342043792929001,
      "loss": 0.0,
      "num_input_tokens_seen": 10340608,
      "step": 36930
    },
    {
      "epoch": 410.3888888888889,
      "grad_norm": 1.2472402666219295e-08,
      "learning_rate": 0.004327984775842025,
      "loss": 0.0,
      "num_input_tokens_seen": 10342000,
      "step": 36935
    },
    {
      "epoch": 410.44444444444446,
      "grad_norm": 2.4411345833641462e-08,
      "learning_rate": 0.004313948223210428,
      "loss": 0.0,
      "num_input_tokens_seen": 10343424,
      "step": 36940
    },
    {
      "epoch": 410.5,
      "grad_norm": 2.1239724645738534e-08,
      "learning_rate": 0.004299934137198846,
      "loss": 0.0,
      "num_input_tokens_seen": 10344784,
      "step": 36945
    },
    {
      "epoch": 410.55555555555554,
      "grad_norm": 1.1994642612478401e-08,
      "learning_rate": 0.004285942519968383,
      "loss": 0.0,
      "num_input_tokens_seen": 10346128,
      "step": 36950
    },
    {
      "epoch": 410.6111111111111,
      "grad_norm": 8.752314428761565e-09,
      "learning_rate": 0.004271973373676746,
      "loss": 0.0,
      "num_input_tokens_seen": 10347488,
      "step": 36955
    },
    {
      "epoch": 410.6666666666667,
      "grad_norm": 2.4536886300552396e-08,
      "learning_rate": 0.004258026700478146,
      "loss": 0.0,
      "num_input_tokens_seen": 10348912,
      "step": 36960
    },
    {
      "epoch": 410.72222222222223,
      "grad_norm": 8.062585976631453e-08,
      "learning_rate": 0.004244102502523328,
      "loss": 0.0,
      "num_input_tokens_seen": 10350288,
      "step": 36965
    },
    {
      "epoch": 410.77777777777777,
      "grad_norm": 1.4096907641203416e-08,
      "learning_rate": 0.004230200781959592,
      "loss": 0.0,
      "num_input_tokens_seen": 10351712,
      "step": 36970
    },
    {
      "epoch": 410.8333333333333,
      "grad_norm": 1.1705711067122593e-08,
      "learning_rate": 0.004216321540930756,
      "loss": 0.0,
      "num_input_tokens_seen": 10353136,
      "step": 36975
    },
    {
      "epoch": 410.8888888888889,
      "grad_norm": 1.2524791870305307e-08,
      "learning_rate": 0.004202464781577175,
      "loss": 0.0,
      "num_input_tokens_seen": 10354576,
      "step": 36980
    },
    {
      "epoch": 410.94444444444446,
      "grad_norm": 1.071276312103464e-08,
      "learning_rate": 0.00418863050603574,
      "loss": 0.0,
      "num_input_tokens_seen": 10356000,
      "step": 36985
    },
    {
      "epoch": 411.0,
      "grad_norm": 7.507066079881497e-09,
      "learning_rate": 0.004174818716439843,
      "loss": 0.0,
      "num_input_tokens_seen": 10357408,
      "step": 36990
    },
    {
      "epoch": 411.05555555555554,
      "grad_norm": 8.275587326522782e-09,
      "learning_rate": 0.004161029414919464,
      "loss": 0.0,
      "num_input_tokens_seen": 10358784,
      "step": 36995
    },
    {
      "epoch": 411.1111111111111,
      "grad_norm": 2.101555729439042e-08,
      "learning_rate": 0.004147262603601071,
      "loss": 0.0,
      "num_input_tokens_seen": 10360192,
      "step": 37000
    },
    {
      "epoch": 411.1111111111111,
      "eval_loss": 1.8238990306854248,
      "eval_runtime": 1.1881,
      "eval_samples_per_second": 33.667,
      "eval_steps_per_second": 16.833,
      "num_input_tokens_seen": 10360192,
      "step": 37000
    },
    {
      "epoch": 411.1666666666667,
      "grad_norm": 4.1635271230688886e-08,
      "learning_rate": 0.004133518284607679,
      "loss": 0.0,
      "num_input_tokens_seen": 10361616,
      "step": 37005
    },
    {
      "epoch": 411.22222222222223,
      "grad_norm": 1.4846869511586647e-08,
      "learning_rate": 0.004119796460058861,
      "loss": 0.0,
      "num_input_tokens_seen": 10363040,
      "step": 37010
    },
    {
      "epoch": 411.27777777777777,
      "grad_norm": 1.0531656435830428e-08,
      "learning_rate": 0.00410609713207064,
      "loss": 0.0,
      "num_input_tokens_seen": 10364432,
      "step": 37015
    },
    {
      "epoch": 411.3333333333333,
      "grad_norm": 2.0749279627807482e-08,
      "learning_rate": 0.004092420302755678,
      "loss": 0.0,
      "num_input_tokens_seen": 10365808,
      "step": 37020
    },
    {
      "epoch": 411.3888888888889,
      "grad_norm": 1.5919912499384736e-08,
      "learning_rate": 0.004078765974223103,
      "loss": 0.0,
      "num_input_tokens_seen": 10367200,
      "step": 37025
    },
    {
      "epoch": 411.44444444444446,
      "grad_norm": 1.1361410479082679e-08,
      "learning_rate": 0.004065134148578564,
      "loss": 0.0,
      "num_input_tokens_seen": 10368592,
      "step": 37030
    },
    {
      "epoch": 411.5,
      "grad_norm": 1.2710915875402407e-08,
      "learning_rate": 0.004051524827924279,
      "loss": 0.0,
      "num_input_tokens_seen": 10370016,
      "step": 37035
    },
    {
      "epoch": 411.55555555555554,
      "grad_norm": 9.049270666139364e-09,
      "learning_rate": 0.004037938014358955,
      "loss": 0.0,
      "num_input_tokens_seen": 10371424,
      "step": 37040
    },
    {
      "epoch": 411.6111111111111,
      "grad_norm": 9.496605279935011e-09,
      "learning_rate": 0.004024373709977863,
      "loss": 0.0,
      "num_input_tokens_seen": 10372832,
      "step": 37045
    },
    {
      "epoch": 411.6666666666667,
      "grad_norm": 7.193502682412145e-09,
      "learning_rate": 0.004010831916872814,
      "loss": 0.0,
      "num_input_tokens_seen": 10374192,
      "step": 37050
    },
    {
      "epoch": 411.72222222222223,
      "grad_norm": 1.1080821593623114e-08,
      "learning_rate": 0.003997312637132089,
      "loss": 0.0,
      "num_input_tokens_seen": 10375600,
      "step": 37055
    },
    {
      "epoch": 411.77777777777777,
      "grad_norm": 2.168308910199812e-08,
      "learning_rate": 0.003983815872840535,
      "loss": 0.0,
      "num_input_tokens_seen": 10377008,
      "step": 37060
    },
    {
      "epoch": 411.8333333333333,
      "grad_norm": 1.1521766651867438e-08,
      "learning_rate": 0.003970341626079521,
      "loss": 0.0,
      "num_input_tokens_seen": 10378432,
      "step": 37065
    },
    {
      "epoch": 411.8888888888889,
      "grad_norm": 1.2666202309219443e-08,
      "learning_rate": 0.003956889898926952,
      "loss": 0.0,
      "num_input_tokens_seen": 10379840,
      "step": 37070
    },
    {
      "epoch": 411.94444444444446,
      "grad_norm": 1.159903462166767e-08,
      "learning_rate": 0.0039434606934572675,
      "loss": 0.0,
      "num_input_tokens_seen": 10381264,
      "step": 37075
    },
    {
      "epoch": 412.0,
      "grad_norm": 8.570420817477498e-09,
      "learning_rate": 0.003930054011741396,
      "loss": 0.0,
      "num_input_tokens_seen": 10382640,
      "step": 37080
    },
    {
      "epoch": 412.05555555555554,
      "grad_norm": 1.3236181928277801e-08,
      "learning_rate": 0.0039166698558468155,
      "loss": 0.0,
      "num_input_tokens_seen": 10384016,
      "step": 37085
    },
    {
      "epoch": 412.1111111111111,
      "grad_norm": 7.0491923409576884e-09,
      "learning_rate": 0.0039033082278375594,
      "loss": 0.0,
      "num_input_tokens_seen": 10385440,
      "step": 37090
    },
    {
      "epoch": 412.1666666666667,
      "grad_norm": 2.4795717479264567e-08,
      "learning_rate": 0.003889969129774112,
      "loss": 0.0,
      "num_input_tokens_seen": 10386848,
      "step": 37095
    },
    {
      "epoch": 412.22222222222223,
      "grad_norm": 9.945972045954932e-09,
      "learning_rate": 0.0038766525637135784,
      "loss": 0.0,
      "num_input_tokens_seen": 10388240,
      "step": 37100
    },
    {
      "epoch": 412.27777777777777,
      "grad_norm": 1.3100465601212363e-08,
      "learning_rate": 0.0038633585317095318,
      "loss": 0.0,
      "num_input_tokens_seen": 10389648,
      "step": 37105
    },
    {
      "epoch": 412.3333333333333,
      "grad_norm": 2.1655553794630578e-08,
      "learning_rate": 0.00385008703581205,
      "loss": 0.0,
      "num_input_tokens_seen": 10391072,
      "step": 37110
    },
    {
      "epoch": 412.3888888888889,
      "grad_norm": 8.268523643550907e-09,
      "learning_rate": 0.0038368380780677944,
      "loss": 0.0,
      "num_input_tokens_seen": 10392544,
      "step": 37115
    },
    {
      "epoch": 412.44444444444446,
      "grad_norm": 1.0290491125886092e-08,
      "learning_rate": 0.003823611660519882,
      "loss": 0.0,
      "num_input_tokens_seen": 10393936,
      "step": 37120
    },
    {
      "epoch": 412.5,
      "grad_norm": 1.1739047067749198e-08,
      "learning_rate": 0.0038104077852080475,
      "loss": 0.0,
      "num_input_tokens_seen": 10395312,
      "step": 37125
    },
    {
      "epoch": 412.55555555555554,
      "grad_norm": 1.1730877602644796e-08,
      "learning_rate": 0.003797226454168462,
      "loss": 0.0,
      "num_input_tokens_seen": 10396704,
      "step": 37130
    },
    {
      "epoch": 412.6111111111111,
      "grad_norm": 4.351054982976166e-08,
      "learning_rate": 0.003784067669433849,
      "loss": 0.0,
      "num_input_tokens_seen": 10398096,
      "step": 37135
    },
    {
      "epoch": 412.6666666666667,
      "grad_norm": 1.7281951869563272e-08,
      "learning_rate": 0.0037709314330334528,
      "loss": 0.0,
      "num_input_tokens_seen": 10399520,
      "step": 37140
    },
    {
      "epoch": 412.72222222222223,
      "grad_norm": 1.1921946985182785e-08,
      "learning_rate": 0.003757817746993086,
      "loss": 0.0,
      "num_input_tokens_seen": 10400944,
      "step": 37145
    },
    {
      "epoch": 412.77777777777777,
      "grad_norm": 1.2399455684430905e-08,
      "learning_rate": 0.0037447266133349977,
      "loss": 0.0,
      "num_input_tokens_seen": 10402336,
      "step": 37150
    },
    {
      "epoch": 412.8333333333333,
      "grad_norm": 7.069784313529226e-09,
      "learning_rate": 0.003731658034078039,
      "loss": 0.0,
      "num_input_tokens_seen": 10403712,
      "step": 37155
    },
    {
      "epoch": 412.8888888888889,
      "grad_norm": 1.6596482410591307e-08,
      "learning_rate": 0.0037186120112375153,
      "loss": 0.0,
      "num_input_tokens_seen": 10405104,
      "step": 37160
    },
    {
      "epoch": 412.94444444444446,
      "grad_norm": 1.071246735762088e-08,
      "learning_rate": 0.003705588546825317,
      "loss": 0.0,
      "num_input_tokens_seen": 10406528,
      "step": 37165
    },
    {
      "epoch": 413.0,
      "grad_norm": 1.1849403236396938e-08,
      "learning_rate": 0.0036925876428498205,
      "loss": 0.0,
      "num_input_tokens_seen": 10407920,
      "step": 37170
    },
    {
      "epoch": 413.05555555555554,
      "grad_norm": 1.0866666677600278e-08,
      "learning_rate": 0.0036796093013159057,
      "loss": 0.0,
      "num_input_tokens_seen": 10409312,
      "step": 37175
    },
    {
      "epoch": 413.1111111111111,
      "grad_norm": 1.0949928075376647e-08,
      "learning_rate": 0.0036666535242250217,
      "loss": 0.0,
      "num_input_tokens_seen": 10410640,
      "step": 37180
    },
    {
      "epoch": 413.1666666666667,
      "grad_norm": 1.8885872421492422e-08,
      "learning_rate": 0.003653720313575104,
      "loss": 0.0,
      "num_input_tokens_seen": 10412016,
      "step": 37185
    },
    {
      "epoch": 413.22222222222223,
      "grad_norm": 1.0539994654834572e-08,
      "learning_rate": 0.003640809671360623,
      "loss": 0.0,
      "num_input_tokens_seen": 10413472,
      "step": 37190
    },
    {
      "epoch": 413.27777777777777,
      "grad_norm": 1.2042287167446375e-08,
      "learning_rate": 0.003627921599572553,
      "loss": 0.0,
      "num_input_tokens_seen": 10414848,
      "step": 37195
    },
    {
      "epoch": 413.3333333333333,
      "grad_norm": 1.2579229213827148e-08,
      "learning_rate": 0.003615056100198405,
      "loss": 0.0,
      "num_input_tokens_seen": 10416288,
      "step": 37200
    },
    {
      "epoch": 413.3333333333333,
      "eval_loss": 1.77797532081604,
      "eval_runtime": 1.1844,
      "eval_samples_per_second": 33.773,
      "eval_steps_per_second": 16.886,
      "num_input_tokens_seen": 10416288,
      "step": 37200
    },
    {
      "epoch": 413.3888888888889,
      "grad_norm": 8.170712106903011e-09,
      "learning_rate": 0.003602213175222174,
      "loss": 0.0,
      "num_input_tokens_seen": 10417696,
      "step": 37205
    },
    {
      "epoch": 413.44444444444446,
      "grad_norm": 8.503826975925222e-09,
      "learning_rate": 0.0035893928266244432,
      "loss": 0.0,
      "num_input_tokens_seen": 10419136,
      "step": 37210
    },
    {
      "epoch": 413.5,
      "grad_norm": 1.1970637814329166e-08,
      "learning_rate": 0.003576595056382248,
      "loss": 0.0,
      "num_input_tokens_seen": 10420560,
      "step": 37215
    },
    {
      "epoch": 413.55555555555554,
      "grad_norm": 8.217034164204051e-09,
      "learning_rate": 0.0035638198664691423,
      "loss": 0.0,
      "num_input_tokens_seen": 10421984,
      "step": 37220
    },
    {
      "epoch": 413.6111111111111,
      "grad_norm": 7.121127687526041e-09,
      "learning_rate": 0.003551067258855267,
      "loss": 0.0,
      "num_input_tokens_seen": 10423408,
      "step": 37225
    },
    {
      "epoch": 413.6666666666667,
      "grad_norm": 1.0402174233092865e-08,
      "learning_rate": 0.0035383372355071996,
      "loss": 0.0,
      "num_input_tokens_seen": 10424800,
      "step": 37230
    },
    {
      "epoch": 413.72222222222223,
      "grad_norm": 1.223239198822057e-08,
      "learning_rate": 0.0035256297983881023,
      "loss": 0.0,
      "num_input_tokens_seen": 10426208,
      "step": 37235
    },
    {
      "epoch": 413.77777777777777,
      "grad_norm": 9.550735313723635e-09,
      "learning_rate": 0.0035129449494575747,
      "loss": 0.0,
      "num_input_tokens_seen": 10427616,
      "step": 37240
    },
    {
      "epoch": 413.8333333333333,
      "grad_norm": 9.549913748685412e-09,
      "learning_rate": 0.0035002826906718187,
      "loss": 0.0,
      "num_input_tokens_seen": 10429008,
      "step": 37245
    },
    {
      "epoch": 413.8888888888889,
      "grad_norm": 1.5032677325166333e-08,
      "learning_rate": 0.003487643023983522,
      "loss": 0.0,
      "num_input_tokens_seen": 10430416,
      "step": 37250
    },
    {
      "epoch": 413.94444444444446,
      "grad_norm": 1.8859969586060288e-08,
      "learning_rate": 0.003475025951341842,
      "loss": 0.0,
      "num_input_tokens_seen": 10431824,
      "step": 37255
    },
    {
      "epoch": 414.0,
      "grad_norm": 9.076198459467832e-09,
      "learning_rate": 0.00346243147469249,
      "loss": 0.0,
      "num_input_tokens_seen": 10433200,
      "step": 37260
    },
    {
      "epoch": 414.05555555555554,
      "grad_norm": 1.0421151053208177e-08,
      "learning_rate": 0.0034498595959777446,
      "loss": 0.0,
      "num_input_tokens_seen": 10434624,
      "step": 37265
    },
    {
      "epoch": 414.1111111111111,
      "grad_norm": 9.111759347035786e-09,
      "learning_rate": 0.003437310317136305,
      "loss": 0.0,
      "num_input_tokens_seen": 10436016,
      "step": 37270
    },
    {
      "epoch": 414.1666666666667,
      "grad_norm": 1.1603781047142547e-08,
      "learning_rate": 0.0034247836401034236,
      "loss": 0.0,
      "num_input_tokens_seen": 10437408,
      "step": 37275
    },
    {
      "epoch": 414.22222222222223,
      "grad_norm": 1.7123372941796333e-08,
      "learning_rate": 0.003412279566810905,
      "loss": 0.0,
      "num_input_tokens_seen": 10438784,
      "step": 37280
    },
    {
      "epoch": 414.27777777777777,
      "grad_norm": 1.3210296856414061e-08,
      "learning_rate": 0.00339979809918699,
      "loss": 0.0,
      "num_input_tokens_seen": 10440176,
      "step": 37285
    },
    {
      "epoch": 414.3333333333333,
      "grad_norm": 1.5276402365316244e-08,
      "learning_rate": 0.0033873392391565228,
      "loss": 0.0,
      "num_input_tokens_seen": 10441600,
      "step": 37290
    },
    {
      "epoch": 414.3888888888889,
      "grad_norm": 1.2589507214499918e-08,
      "learning_rate": 0.003374902988640782,
      "loss": 0.0,
      "num_input_tokens_seen": 10442976,
      "step": 37295
    },
    {
      "epoch": 414.44444444444446,
      "grad_norm": 8.82442119376492e-09,
      "learning_rate": 0.0033624893495576014,
      "loss": 0.0,
      "num_input_tokens_seen": 10444384,
      "step": 37300
    },
    {
      "epoch": 414.5,
      "grad_norm": 1.165456620100258e-08,
      "learning_rate": 0.0033500983238213323,
      "loss": 0.0,
      "num_input_tokens_seen": 10445728,
      "step": 37305
    },
    {
      "epoch": 414.55555555555554,
      "grad_norm": 1.2311637931361474e-08,
      "learning_rate": 0.0033377299133428126,
      "loss": 0.0,
      "num_input_tokens_seen": 10447168,
      "step": 37310
    },
    {
      "epoch": 414.6111111111111,
      "grad_norm": 8.53830606217798e-09,
      "learning_rate": 0.003325384120029434,
      "loss": 0.0,
      "num_input_tokens_seen": 10448560,
      "step": 37315
    },
    {
      "epoch": 414.6666666666667,
      "grad_norm": 1.4968373207580044e-08,
      "learning_rate": 0.0033130609457850233,
      "loss": 0.0,
      "num_input_tokens_seen": 10449968,
      "step": 37320
    },
    {
      "epoch": 414.72222222222223,
      "grad_norm": 1.6210231379432116e-08,
      "learning_rate": 0.0033007603925100104,
      "loss": 0.0,
      "num_input_tokens_seen": 10451376,
      "step": 37325
    },
    {
      "epoch": 414.77777777777777,
      "grad_norm": 1.2213870803634563e-08,
      "learning_rate": 0.003288482462101294,
      "loss": 0.0,
      "num_input_tokens_seen": 10452800,
      "step": 37330
    },
    {
      "epoch": 414.8333333333333,
      "grad_norm": 8.288043140680657e-09,
      "learning_rate": 0.0032762271564522605,
      "loss": 0.0,
      "num_input_tokens_seen": 10454192,
      "step": 37335
    },
    {
      "epoch": 414.8888888888889,
      "grad_norm": 1.3055643677262196e-08,
      "learning_rate": 0.003263994477452864,
      "loss": 0.0,
      "num_input_tokens_seen": 10455600,
      "step": 37340
    },
    {
      "epoch": 414.94444444444446,
      "grad_norm": 2.128745357765638e-08,
      "learning_rate": 0.0032517844269895125,
      "loss": 0.0,
      "num_input_tokens_seen": 10456992,
      "step": 37345
    },
    {
      "epoch": 415.0,
      "grad_norm": 6.085066228678215e-09,
      "learning_rate": 0.0032395970069451496,
      "loss": 0.0,
      "num_input_tokens_seen": 10458416,
      "step": 37350
    },
    {
      "epoch": 415.05555555555554,
      "grad_norm": 1.2238784208307152e-08,
      "learning_rate": 0.0032274322191992388,
      "loss": 0.0,
      "num_input_tokens_seen": 10459856,
      "step": 37355
    },
    {
      "epoch": 415.1111111111111,
      "grad_norm": 7.640718280299552e-09,
      "learning_rate": 0.0032152900656277294,
      "loss": 0.0,
      "num_input_tokens_seen": 10461248,
      "step": 37360
    },
    {
      "epoch": 415.1666666666667,
      "grad_norm": 1.2516090386327505e-08,
      "learning_rate": 0.0032031705481030902,
      "loss": 0.0,
      "num_input_tokens_seen": 10462608,
      "step": 37365
    },
    {
      "epoch": 415.22222222222223,
      "grad_norm": 7.784092481699645e-09,
      "learning_rate": 0.0031910736684943428,
      "loss": 0.0,
      "num_input_tokens_seen": 10464016,
      "step": 37370
    },
    {
      "epoch": 415.27777777777777,
      "grad_norm": 1.1941160060757738e-08,
      "learning_rate": 0.0031789994286669453,
      "loss": 0.0,
      "num_input_tokens_seen": 10465392,
      "step": 37375
    },
    {
      "epoch": 415.3333333333333,
      "grad_norm": 2.076110305893053e-08,
      "learning_rate": 0.003166947830482908,
      "loss": 0.0,
      "num_input_tokens_seen": 10466800,
      "step": 37380
    },
    {
      "epoch": 415.3888888888889,
      "grad_norm": 1.0843068665167266e-08,
      "learning_rate": 0.003154918875800727,
      "loss": 0.0,
      "num_input_tokens_seen": 10468192,
      "step": 37385
    },
    {
      "epoch": 415.44444444444446,
      "grad_norm": 8.563963760366278e-09,
      "learning_rate": 0.00314291256647542,
      "loss": 0.0,
      "num_input_tokens_seen": 10469520,
      "step": 37390
    },
    {
      "epoch": 415.5,
      "grad_norm": 1.1483415107704786e-08,
      "learning_rate": 0.0031309289043585375,
      "loss": 0.0,
      "num_input_tokens_seen": 10470912,
      "step": 37395
    },
    {
      "epoch": 415.55555555555554,
      "grad_norm": 1.2629564061228393e-08,
      "learning_rate": 0.003118967891298069,
      "loss": 0.0,
      "num_input_tokens_seen": 10472368,
      "step": 37400
    },
    {
      "epoch": 415.55555555555554,
      "eval_loss": 1.7845722436904907,
      "eval_runtime": 1.1852,
      "eval_samples_per_second": 33.749,
      "eval_steps_per_second": 16.875,
      "num_input_tokens_seen": 10472368,
      "step": 37400
    },
    {
      "epoch": 415.6111111111111,
      "grad_norm": 1.027032769940206e-08,
      "learning_rate": 0.003107029529138572,
      "loss": 0.0,
      "num_input_tokens_seen": 10473776,
      "step": 37405
    },
    {
      "epoch": 415.6666666666667,
      "grad_norm": 1.7295395338123853e-08,
      "learning_rate": 0.0030951138197211235,
      "loss": 0.0,
      "num_input_tokens_seen": 10475216,
      "step": 37410
    },
    {
      "epoch": 415.72222222222223,
      "grad_norm": 6.383789497022008e-09,
      "learning_rate": 0.0030832207648832377,
      "loss": 0.0,
      "num_input_tokens_seen": 10476608,
      "step": 37415
    },
    {
      "epoch": 415.77777777777777,
      "grad_norm": 1.2503790003393078e-08,
      "learning_rate": 0.0030713503664589635,
      "loss": 0.0,
      "num_input_tokens_seen": 10477984,
      "step": 37420
    },
    {
      "epoch": 415.8333333333333,
      "grad_norm": 9.177538728977197e-09,
      "learning_rate": 0.0030595026262788872,
      "loss": 0.0,
      "num_input_tokens_seen": 10479360,
      "step": 37425
    },
    {
      "epoch": 415.8888888888889,
      "grad_norm": 2.1949544404264998e-08,
      "learning_rate": 0.00304767754617008,
      "loss": 0.0,
      "num_input_tokens_seen": 10480752,
      "step": 37430
    },
    {
      "epoch": 415.94444444444446,
      "grad_norm": 1.9136756179705117e-08,
      "learning_rate": 0.003035875127956117,
      "loss": 0.0,
      "num_input_tokens_seen": 10482160,
      "step": 37435
    },
    {
      "epoch": 416.0,
      "grad_norm": 1.3284831013038456e-08,
      "learning_rate": 0.0030240953734570752,
      "loss": 0.0,
      "num_input_tokens_seen": 10483600,
      "step": 37440
    },
    {
      "epoch": 416.05555555555554,
      "grad_norm": 1.2068177568380634e-08,
      "learning_rate": 0.003012338284489535,
      "loss": 0.0,
      "num_input_tokens_seen": 10485024,
      "step": 37445
    },
    {
      "epoch": 416.1111111111111,
      "grad_norm": 1.080363354333258e-08,
      "learning_rate": 0.0030006038628665964,
      "loss": 0.0,
      "num_input_tokens_seen": 10486432,
      "step": 37450
    },
    {
      "epoch": 416.1666666666667,
      "grad_norm": 5.9914806449512525e-09,
      "learning_rate": 0.002988892110397845,
      "loss": 0.0,
      "num_input_tokens_seen": 10487792,
      "step": 37455
    },
    {
      "epoch": 416.22222222222223,
      "grad_norm": 2.5676452963807606e-08,
      "learning_rate": 0.0029772030288894025,
      "loss": 0.0,
      "num_input_tokens_seen": 10489136,
      "step": 37460
    },
    {
      "epoch": 416.27777777777777,
      "grad_norm": 9.732099570669561e-09,
      "learning_rate": 0.0029655366201438438,
      "loss": 0.0,
      "num_input_tokens_seen": 10490528,
      "step": 37465
    },
    {
      "epoch": 416.3333333333333,
      "grad_norm": 1.2750484224000047e-08,
      "learning_rate": 0.0029538928859602965,
      "loss": 0.0,
      "num_input_tokens_seen": 10491920,
      "step": 37470
    },
    {
      "epoch": 416.3888888888889,
      "grad_norm": 8.099224402258187e-09,
      "learning_rate": 0.002942271828134374,
      "loss": 0.0,
      "num_input_tokens_seen": 10493360,
      "step": 37475
    },
    {
      "epoch": 416.44444444444446,
      "grad_norm": 3.108599599954687e-08,
      "learning_rate": 0.00293067344845816,
      "loss": 0.0,
      "num_input_tokens_seen": 10494784,
      "step": 37480
    },
    {
      "epoch": 416.5,
      "grad_norm": 1.2659817194560219e-08,
      "learning_rate": 0.0029190977487202896,
      "loss": 0.0,
      "num_input_tokens_seen": 10496144,
      "step": 37485
    },
    {
      "epoch": 416.55555555555554,
      "grad_norm": 1.1008630451669887e-08,
      "learning_rate": 0.0029075447307058853,
      "loss": 0.0,
      "num_input_tokens_seen": 10497520,
      "step": 37490
    },
    {
      "epoch": 416.6111111111111,
      "grad_norm": 1.3406369347990221e-08,
      "learning_rate": 0.0028960143961965722,
      "loss": 0.0,
      "num_input_tokens_seen": 10498928,
      "step": 37495
    },
    {
      "epoch": 416.6666666666667,
      "grad_norm": 2.0565753544588006e-08,
      "learning_rate": 0.002884506746970461,
      "loss": 0.0,
      "num_input_tokens_seen": 10500336,
      "step": 37500
    },
    {
      "epoch": 416.72222222222223,
      "grad_norm": 4.141909570876123e-08,
      "learning_rate": 0.0028730217848021654,
      "loss": 0.0,
      "num_input_tokens_seen": 10501696,
      "step": 37505
    },
    {
      "epoch": 416.77777777777777,
      "grad_norm": 1.2385402925474409e-08,
      "learning_rate": 0.0028615595114628188,
      "loss": 0.0,
      "num_input_tokens_seen": 10503136,
      "step": 37510
    },
    {
      "epoch": 416.8333333333333,
      "grad_norm": 1.3372278395706871e-08,
      "learning_rate": 0.002850119928720074,
      "loss": 0.0,
      "num_input_tokens_seen": 10504544,
      "step": 37515
    },
    {
      "epoch": 416.8888888888889,
      "grad_norm": 1.4292071526256223e-08,
      "learning_rate": 0.0028387030383380195,
      "loss": 0.0,
      "num_input_tokens_seen": 10505984,
      "step": 37520
    },
    {
      "epoch": 416.94444444444446,
      "grad_norm": 7.272977597949648e-08,
      "learning_rate": 0.0028273088420772974,
      "loss": 0.0,
      "num_input_tokens_seen": 10507408,
      "step": 37525
    },
    {
      "epoch": 417.0,
      "grad_norm": 1.0651382886806005e-08,
      "learning_rate": 0.002815937341695068,
      "loss": 0.0,
      "num_input_tokens_seen": 10508816,
      "step": 37530
    },
    {
      "epoch": 417.05555555555554,
      "grad_norm": 1.174208819065825e-08,
      "learning_rate": 0.0028045885389448963,
      "loss": 0.0,
      "num_input_tokens_seen": 10510176,
      "step": 37535
    },
    {
      "epoch": 417.1111111111111,
      "grad_norm": 1.1854519144094411e-08,
      "learning_rate": 0.002793262435576965,
      "loss": 0.0,
      "num_input_tokens_seen": 10511552,
      "step": 37540
    },
    {
      "epoch": 417.1666666666667,
      "grad_norm": 1.0671739936185531e-08,
      "learning_rate": 0.0027819590333378772,
      "loss": 0.0,
      "num_input_tokens_seen": 10512928,
      "step": 37545
    },
    {
      "epoch": 417.22222222222223,
      "grad_norm": 9.169252024321395e-09,
      "learning_rate": 0.002770678333970755,
      "loss": 0.0,
      "num_input_tokens_seen": 10514304,
      "step": 37550
    },
    {
      "epoch": 417.27777777777777,
      "grad_norm": 1.2064638177378129e-08,
      "learning_rate": 0.0027594203392152573,
      "loss": 0.0,
      "num_input_tokens_seen": 10515696,
      "step": 37555
    },
    {
      "epoch": 417.3333333333333,
      "grad_norm": 1.2967680262931935e-08,
      "learning_rate": 0.002748185050807478,
      "loss": 0.0,
      "num_input_tokens_seen": 10517072,
      "step": 37560
    },
    {
      "epoch": 417.3888888888889,
      "grad_norm": 1.5125202423860173e-08,
      "learning_rate": 0.002736972470480031,
      "loss": 0.0,
      "num_input_tokens_seen": 10518432,
      "step": 37565
    },
    {
      "epoch": 417.44444444444446,
      "grad_norm": 1.5197674230194025e-08,
      "learning_rate": 0.002725782599962068,
      "loss": 0.0,
      "num_input_tokens_seen": 10519872,
      "step": 37570
    },
    {
      "epoch": 417.5,
      "grad_norm": 2.5418737337190578e-08,
      "learning_rate": 0.0027146154409791734,
      "loss": 0.0,
      "num_input_tokens_seen": 10521296,
      "step": 37575
    },
    {
      "epoch": 417.55555555555554,
      "grad_norm": 1.2050232811589012e-08,
      "learning_rate": 0.002703470995253504,
      "loss": 0.0,
      "num_input_tokens_seen": 10522736,
      "step": 37580
    },
    {
      "epoch": 417.6111111111111,
      "grad_norm": 9.931040878541353e-09,
      "learning_rate": 0.0026923492645036184,
      "loss": 0.0,
      "num_input_tokens_seen": 10524128,
      "step": 37585
    },
    {
      "epoch": 417.6666666666667,
      "grad_norm": 1.4394792913208221e-08,
      "learning_rate": 0.0026812502504446776,
      "loss": 0.0,
      "num_input_tokens_seen": 10525536,
      "step": 37590
    },
    {
      "epoch": 417.72222222222223,
      "grad_norm": 7.983770089481368e-09,
      "learning_rate": 0.0026701739547882798,
      "loss": 0.0,
      "num_input_tokens_seen": 10526960,
      "step": 37595
    },
    {
      "epoch": 417.77777777777777,
      "grad_norm": 9.736156769690751e-09,
      "learning_rate": 0.0026591203792425077,
      "loss": 0.0,
      "num_input_tokens_seen": 10528352,
      "step": 37600
    },
    {
      "epoch": 417.77777777777777,
      "eval_loss": 1.7937984466552734,
      "eval_runtime": 1.1891,
      "eval_samples_per_second": 33.639,
      "eval_steps_per_second": 16.819,
      "num_input_tokens_seen": 10528352,
      "step": 37600
    },
    {
      "epoch": 417.8333333333333,
      "grad_norm": 3.116237223821372e-08,
      "learning_rate": 0.0026480895255119818,
      "loss": 0.0,
      "num_input_tokens_seen": 10529792,
      "step": 37605
    },
    {
      "epoch": 417.8888888888889,
      "grad_norm": 1.2081794231733056e-08,
      "learning_rate": 0.002637081395297791,
      "loss": 0.0,
      "num_input_tokens_seen": 10531184,
      "step": 37610
    },
    {
      "epoch": 417.94444444444446,
      "grad_norm": 2.369426077564185e-08,
      "learning_rate": 0.0026260959902975113,
      "loss": 0.0,
      "num_input_tokens_seen": 10532624,
      "step": 37615
    },
    {
      "epoch": 418.0,
      "grad_norm": 9.417504998054937e-09,
      "learning_rate": 0.00261513331220527,
      "loss": 0.0,
      "num_input_tokens_seen": 10534016,
      "step": 37620
    },
    {
      "epoch": 418.05555555555554,
      "grad_norm": 2.3094425927183693e-08,
      "learning_rate": 0.0026041933627116154,
      "loss": 0.0,
      "num_input_tokens_seen": 10535456,
      "step": 37625
    },
    {
      "epoch": 418.1111111111111,
      "grad_norm": 6.966159205035183e-09,
      "learning_rate": 0.0025932761435036476,
      "loss": 0.0,
      "num_input_tokens_seen": 10536848,
      "step": 37630
    },
    {
      "epoch": 418.1666666666667,
      "grad_norm": 1.1180666170673703e-08,
      "learning_rate": 0.002582381656264904,
      "loss": 0.0,
      "num_input_tokens_seen": 10538320,
      "step": 37635
    },
    {
      "epoch": 418.22222222222223,
      "grad_norm": 9.775189546701313e-09,
      "learning_rate": 0.0025715099026754895,
      "loss": 0.0,
      "num_input_tokens_seen": 10539728,
      "step": 37640
    },
    {
      "epoch": 418.27777777777777,
      "grad_norm": 2.7733497276472008e-08,
      "learning_rate": 0.002560660884411947,
      "loss": 0.0,
      "num_input_tokens_seen": 10541104,
      "step": 37645
    },
    {
      "epoch": 418.3333333333333,
      "grad_norm": 7.0609504909668885e-09,
      "learning_rate": 0.0025498346031473385,
      "loss": 0.0,
      "num_input_tokens_seen": 10542480,
      "step": 37650
    },
    {
      "epoch": 418.3888888888889,
      "grad_norm": 1.5260349428558584e-08,
      "learning_rate": 0.0025390310605511945,
      "loss": 0.0,
      "num_input_tokens_seen": 10543824,
      "step": 37655
    },
    {
      "epoch": 418.44444444444446,
      "grad_norm": 1.3760067751888982e-08,
      "learning_rate": 0.0025282502582895995,
      "loss": 0.0,
      "num_input_tokens_seen": 10545200,
      "step": 37660
    },
    {
      "epoch": 418.5,
      "grad_norm": 1.2451187636486338e-08,
      "learning_rate": 0.002517492198025023,
      "loss": 0.0,
      "num_input_tokens_seen": 10546656,
      "step": 37665
    },
    {
      "epoch": 418.55555555555554,
      "grad_norm": 2.613027660913758e-08,
      "learning_rate": 0.0025067568814165554,
      "loss": 0.0,
      "num_input_tokens_seen": 10548048,
      "step": 37670
    },
    {
      "epoch": 418.6111111111111,
      "grad_norm": 7.791680189939143e-09,
      "learning_rate": 0.0024960443101196884,
      "loss": 0.0,
      "num_input_tokens_seen": 10549472,
      "step": 37675
    },
    {
      "epoch": 418.6666666666667,
      "grad_norm": 1.0930763849614777e-08,
      "learning_rate": 0.002485354485786434,
      "loss": 0.0,
      "num_input_tokens_seen": 10550848,
      "step": 37680
    },
    {
      "epoch": 418.72222222222223,
      "grad_norm": 9.78029124354407e-09,
      "learning_rate": 0.002474687410065307,
      "loss": 0.0,
      "num_input_tokens_seen": 10552224,
      "step": 37685
    },
    {
      "epoch": 418.77777777777777,
      "grad_norm": 2.6592870128183677e-08,
      "learning_rate": 0.002464043084601308,
      "loss": 0.0,
      "num_input_tokens_seen": 10553632,
      "step": 37690
    },
    {
      "epoch": 418.8333333333333,
      "grad_norm": 2.6136660835618386e-08,
      "learning_rate": 0.0024534215110358915,
      "loss": 0.0,
      "num_input_tokens_seen": 10555008,
      "step": 37695
    },
    {
      "epoch": 418.8888888888889,
      "grad_norm": 1.0502423819502837e-08,
      "learning_rate": 0.002442822691007096,
      "loss": 0.0,
      "num_input_tokens_seen": 10556368,
      "step": 37700
    },
    {
      "epoch": 418.94444444444446,
      "grad_norm": 1.1714234915416455e-08,
      "learning_rate": 0.002432246626149348,
      "loss": 0.0,
      "num_input_tokens_seen": 10557776,
      "step": 37705
    },
    {
      "epoch": 419.0,
      "grad_norm": 8.55524806553376e-09,
      "learning_rate": 0.002421693318093626,
      "loss": 0.0,
      "num_input_tokens_seen": 10559152,
      "step": 37710
    },
    {
      "epoch": 419.05555555555554,
      "grad_norm": 8.689548636198197e-09,
      "learning_rate": 0.0024111627684673784,
      "loss": 0.0,
      "num_input_tokens_seen": 10560560,
      "step": 37715
    },
    {
      "epoch": 419.1111111111111,
      "grad_norm": 1.765731028058326e-08,
      "learning_rate": 0.0024006549788945395,
      "loss": 0.0,
      "num_input_tokens_seen": 10562016,
      "step": 37720
    },
    {
      "epoch": 419.1666666666667,
      "grad_norm": 1.1309715830520872e-08,
      "learning_rate": 0.0023901699509955463,
      "loss": 0.0,
      "num_input_tokens_seen": 10563424,
      "step": 37725
    },
    {
      "epoch": 419.22222222222223,
      "grad_norm": 9.467707506871648e-09,
      "learning_rate": 0.0023797076863873554,
      "loss": 0.0,
      "num_input_tokens_seen": 10564800,
      "step": 37730
    },
    {
      "epoch": 419.27777777777777,
      "grad_norm": 1.3734646309160325e-08,
      "learning_rate": 0.0023692681866833262,
      "loss": 0.0,
      "num_input_tokens_seen": 10566192,
      "step": 37735
    },
    {
      "epoch": 419.3333333333333,
      "grad_norm": 1.3302549284333054e-08,
      "learning_rate": 0.0023588514534934046,
      "loss": 0.0,
      "num_input_tokens_seen": 10567600,
      "step": 37740
    },
    {
      "epoch": 419.3888888888889,
      "grad_norm": 9.049361260338173e-09,
      "learning_rate": 0.002348457488423955,
      "loss": 0.0,
      "num_input_tokens_seen": 10568976,
      "step": 37745
    },
    {
      "epoch": 419.44444444444446,
      "grad_norm": 8.550276930918699e-09,
      "learning_rate": 0.0023380862930778624,
      "loss": 0.0,
      "num_input_tokens_seen": 10570368,
      "step": 37750
    },
    {
      "epoch": 419.5,
      "grad_norm": 9.393748001684799e-09,
      "learning_rate": 0.0023277378690545135,
      "loss": 0.0,
      "num_input_tokens_seen": 10571808,
      "step": 37755
    },
    {
      "epoch": 419.55555555555554,
      "grad_norm": 1.1851731152034972e-08,
      "learning_rate": 0.0023174122179497325,
      "loss": 0.0,
      "num_input_tokens_seen": 10573248,
      "step": 37760
    },
    {
      "epoch": 419.6111111111111,
      "grad_norm": 9.348342544512889e-09,
      "learning_rate": 0.0023071093413558784,
      "loss": 0.0,
      "num_input_tokens_seen": 10574624,
      "step": 37765
    },
    {
      "epoch": 419.6666666666667,
      "grad_norm": 1.3316017621889387e-08,
      "learning_rate": 0.002296829240861814,
      "loss": 0.0,
      "num_input_tokens_seen": 10576016,
      "step": 37770
    },
    {
      "epoch": 419.72222222222223,
      "grad_norm": 6.820142228747272e-09,
      "learning_rate": 0.002286571918052821,
      "loss": 0.0,
      "num_input_tokens_seen": 10577408,
      "step": 37775
    },
    {
      "epoch": 419.77777777777777,
      "grad_norm": 8.880451041193282e-09,
      "learning_rate": 0.0022763373745107174,
      "loss": 0.0,
      "num_input_tokens_seen": 10578768,
      "step": 37780
    },
    {
      "epoch": 419.8333333333333,
      "grad_norm": 2.3219001832330832e-08,
      "learning_rate": 0.0022661256118138074,
      "loss": 0.0,
      "num_input_tokens_seen": 10580128,
      "step": 37785
    },
    {
      "epoch": 419.8888888888889,
      "grad_norm": 1.495289581043835e-08,
      "learning_rate": 0.0022559366315368645,
      "loss": 0.0,
      "num_input_tokens_seen": 10581552,
      "step": 37790
    },
    {
      "epoch": 419.94444444444446,
      "grad_norm": 1.2482393785262502e-08,
      "learning_rate": 0.002245770435251182,
      "loss": 0.0,
      "num_input_tokens_seen": 10582960,
      "step": 37795
    },
    {
      "epoch": 420.0,
      "grad_norm": 8.297967646342386e-09,
      "learning_rate": 0.002235627024524456,
      "loss": 0.0,
      "num_input_tokens_seen": 10584384,
      "step": 37800
    },
    {
      "epoch": 420.0,
      "eval_loss": 1.792441964149475,
      "eval_runtime": 1.204,
      "eval_samples_per_second": 33.223,
      "eval_steps_per_second": 16.612,
      "num_input_tokens_seen": 10584384,
      "step": 37800
    },
    {
      "epoch": 420.05555555555554,
      "grad_norm": 2.007111987722965e-08,
      "learning_rate": 0.0022255064009209847,
      "loss": 0.0,
      "num_input_tokens_seen": 10585808,
      "step": 37805
    },
    {
      "epoch": 420.1111111111111,
      "grad_norm": 2.049652714219974e-08,
      "learning_rate": 0.0022154085660014864,
      "loss": 0.0,
      "num_input_tokens_seen": 10587216,
      "step": 37810
    },
    {
      "epoch": 420.1666666666667,
      "grad_norm": 9.928232458378261e-09,
      "learning_rate": 0.0022053335213231494,
      "loss": 0.0,
      "num_input_tokens_seen": 10588656,
      "step": 37815
    },
    {
      "epoch": 420.22222222222223,
      "grad_norm": 1.1935536115004197e-08,
      "learning_rate": 0.002195281268439697,
      "loss": 0.0,
      "num_input_tokens_seen": 10590032,
      "step": 37820
    },
    {
      "epoch": 420.27777777777777,
      "grad_norm": 1.4011813043168786e-08,
      "learning_rate": 0.002185251808901306,
      "loss": 0.0,
      "num_input_tokens_seen": 10591424,
      "step": 37825
    },
    {
      "epoch": 420.3333333333333,
      "grad_norm": 8.789510452800187e-09,
      "learning_rate": 0.0021752451442546227,
      "loss": 0.0,
      "num_input_tokens_seen": 10592816,
      "step": 37830
    },
    {
      "epoch": 420.3888888888889,
      "grad_norm": 8.546490626315517e-09,
      "learning_rate": 0.0021652612760428456,
      "loss": 0.0,
      "num_input_tokens_seen": 10594272,
      "step": 37835
    },
    {
      "epoch": 420.44444444444446,
      "grad_norm": 7.3508199527339e-09,
      "learning_rate": 0.0021553002058055603,
      "loss": 0.0,
      "num_input_tokens_seen": 10595648,
      "step": 37840
    },
    {
      "epoch": 420.5,
      "grad_norm": 1.0104578507252882e-08,
      "learning_rate": 0.0021453619350789376,
      "loss": 0.0,
      "num_input_tokens_seen": 10597056,
      "step": 37845
    },
    {
      "epoch": 420.55555555555554,
      "grad_norm": 1.71160632334022e-08,
      "learning_rate": 0.0021354464653955516,
      "loss": 0.0,
      "num_input_tokens_seen": 10598480,
      "step": 37850
    },
    {
      "epoch": 420.6111111111111,
      "grad_norm": 3.0993650312893806e-08,
      "learning_rate": 0.002125553798284513,
      "loss": 0.0,
      "num_input_tokens_seen": 10599856,
      "step": 37855
    },
    {
      "epoch": 420.6666666666667,
      "grad_norm": 1.2206880839471523e-08,
      "learning_rate": 0.002115683935271384,
      "loss": 0.0,
      "num_input_tokens_seen": 10601248,
      "step": 37860
    },
    {
      "epoch": 420.72222222222223,
      "grad_norm": 1.4696770911371004e-08,
      "learning_rate": 0.0021058368778782144,
      "loss": 0.0,
      "num_input_tokens_seen": 10602672,
      "step": 37865
    },
    {
      "epoch": 420.77777777777777,
      "grad_norm": 2.7143686409658585e-08,
      "learning_rate": 0.002096012627623539,
      "loss": 0.0,
      "num_input_tokens_seen": 10604064,
      "step": 37870
    },
    {
      "epoch": 420.8333333333333,
      "grad_norm": 8.063528511570439e-09,
      "learning_rate": 0.00208621118602243,
      "loss": 0.0,
      "num_input_tokens_seen": 10605440,
      "step": 37875
    },
    {
      "epoch": 420.8888888888889,
      "grad_norm": 1.3105381668765403e-08,
      "learning_rate": 0.002076432554586327,
      "loss": 0.0,
      "num_input_tokens_seen": 10606848,
      "step": 37880
    },
    {
      "epoch": 420.94444444444446,
      "grad_norm": 1.634175283982131e-08,
      "learning_rate": 0.002066676734823258,
      "loss": 0.0,
      "num_input_tokens_seen": 10608224,
      "step": 37885
    },
    {
      "epoch": 421.0,
      "grad_norm": 1.3693509437473494e-08,
      "learning_rate": 0.0020569437282376866,
      "loss": 0.0,
      "num_input_tokens_seen": 10609616,
      "step": 37890
    },
    {
      "epoch": 421.05555555555554,
      "grad_norm": 1.3568997481172573e-08,
      "learning_rate": 0.002047233536330545,
      "loss": 0.0,
      "num_input_tokens_seen": 10611008,
      "step": 37895
    },
    {
      "epoch": 421.1111111111111,
      "grad_norm": 1.7263376506093664e-08,
      "learning_rate": 0.0020375461605993015,
      "loss": 0.0,
      "num_input_tokens_seen": 10612400,
      "step": 37900
    },
    {
      "epoch": 421.1666666666667,
      "grad_norm": 1.1882913319993804e-08,
      "learning_rate": 0.002027881602537845,
      "loss": 0.0,
      "num_input_tokens_seen": 10613792,
      "step": 37905
    },
    {
      "epoch": 421.22222222222223,
      "grad_norm": 1.2570089857888433e-08,
      "learning_rate": 0.002018239863636567,
      "loss": 0.0,
      "num_input_tokens_seen": 10615200,
      "step": 37910
    },
    {
      "epoch": 421.27777777777777,
      "grad_norm": 8.883840330042858e-09,
      "learning_rate": 0.002008620945382378,
      "loss": 0.0,
      "num_input_tokens_seen": 10616576,
      "step": 37915
    },
    {
      "epoch": 421.3333333333333,
      "grad_norm": 1.394169579782556e-08,
      "learning_rate": 0.001999024849258607,
      "loss": 0.0,
      "num_input_tokens_seen": 10618000,
      "step": 37920
    },
    {
      "epoch": 421.3888888888889,
      "grad_norm": 7.122252565494591e-09,
      "learning_rate": 0.001989451576745105,
      "loss": 0.0,
      "num_input_tokens_seen": 10619408,
      "step": 37925
    },
    {
      "epoch": 421.44444444444446,
      "grad_norm": 1.1947548728130641e-08,
      "learning_rate": 0.00197990112931819,
      "loss": 0.0,
      "num_input_tokens_seen": 10620800,
      "step": 37930
    },
    {
      "epoch": 421.5,
      "grad_norm": 1.475773725445606e-08,
      "learning_rate": 0.0019703735084506345,
      "loss": 0.0,
      "num_input_tokens_seen": 10622160,
      "step": 37935
    },
    {
      "epoch": 421.55555555555554,
      "grad_norm": 1.4124753811017854e-08,
      "learning_rate": 0.001960868715611763,
      "loss": 0.0,
      "num_input_tokens_seen": 10623520,
      "step": 37940
    },
    {
      "epoch": 421.6111111111111,
      "grad_norm": 7.78422482028418e-09,
      "learning_rate": 0.0019513867522673034,
      "loss": 0.0,
      "num_input_tokens_seen": 10624928,
      "step": 37945
    },
    {
      "epoch": 421.6666666666667,
      "grad_norm": 3.0574913267855663e-08,
      "learning_rate": 0.001941927619879502,
      "loss": 0.0,
      "num_input_tokens_seen": 10626384,
      "step": 37950
    },
    {
      "epoch": 421.72222222222223,
      "grad_norm": 1.0136166572749516e-08,
      "learning_rate": 0.0019324913199070758,
      "loss": 0.0,
      "num_input_tokens_seen": 10627776,
      "step": 37955
    },
    {
      "epoch": 421.77777777777777,
      "grad_norm": 9.787916255277196e-09,
      "learning_rate": 0.0019230778538052106,
      "loss": 0.0,
      "num_input_tokens_seen": 10629216,
      "step": 37960
    },
    {
      "epoch": 421.8333333333333,
      "grad_norm": 8.446717103538504e-09,
      "learning_rate": 0.0019136872230255952,
      "loss": 0.0,
      "num_input_tokens_seen": 10630608,
      "step": 37965
    },
    {
      "epoch": 421.8888888888889,
      "grad_norm": 8.950481245051378e-09,
      "learning_rate": 0.0019043194290164045,
      "loss": 0.0,
      "num_input_tokens_seen": 10632000,
      "step": 37970
    },
    {
      "epoch": 421.94444444444446,
      "grad_norm": 7.578710992106608e-09,
      "learning_rate": 0.0018949744732222162,
      "loss": 0.0,
      "num_input_tokens_seen": 10633440,
      "step": 37975
    },
    {
      "epoch": 422.0,
      "grad_norm": 1.3527960973647168e-08,
      "learning_rate": 0.0018856523570841776,
      "loss": 0.0,
      "num_input_tokens_seen": 10634864,
      "step": 37980
    },
    {
      "epoch": 422.05555555555554,
      "grad_norm": 5.1618716412349386e-08,
      "learning_rate": 0.0018763530820398555,
      "loss": 0.0,
      "num_input_tokens_seen": 10636256,
      "step": 37985
    },
    {
      "epoch": 422.1111111111111,
      "grad_norm": 7.096953691387853e-09,
      "learning_rate": 0.0018670766495233525,
      "loss": 0.0,
      "num_input_tokens_seen": 10637680,
      "step": 37990
    },
    {
      "epoch": 422.1666666666667,
      "grad_norm": 1.2408674088248972e-08,
      "learning_rate": 0.001857823060965158,
      "loss": 0.0,
      "num_input_tokens_seen": 10639104,
      "step": 37995
    },
    {
      "epoch": 422.22222222222223,
      "grad_norm": 7.318939676537184e-09,
      "learning_rate": 0.0018485923177923467,
      "loss": 0.0,
      "num_input_tokens_seen": 10640496,
      "step": 38000
    },
    {
      "epoch": 422.22222222222223,
      "eval_loss": 1.7995392084121704,
      "eval_runtime": 1.185,
      "eval_samples_per_second": 33.756,
      "eval_steps_per_second": 16.878,
      "num_input_tokens_seen": 10640496,
      "step": 38000
    },
    {
      "epoch": 422.27777777777777,
      "grad_norm": 9.565953362766777e-09,
      "learning_rate": 0.001839384421428364,
      "loss": 0.0,
      "num_input_tokens_seen": 10641936,
      "step": 38005
    },
    {
      "epoch": 422.3333333333333,
      "grad_norm": 2.0321605731510317e-08,
      "learning_rate": 0.0018301993732932065,
      "loss": 0.0,
      "num_input_tokens_seen": 10643344,
      "step": 38010
    },
    {
      "epoch": 422.3888888888889,
      "grad_norm": 6.892065140817749e-09,
      "learning_rate": 0.0018210371748033248,
      "loss": 0.0,
      "num_input_tokens_seen": 10644768,
      "step": 38015
    },
    {
      "epoch": 422.44444444444446,
      "grad_norm": 9.063897188354986e-09,
      "learning_rate": 0.0018118978273716556,
      "loss": 0.0,
      "num_input_tokens_seen": 10646144,
      "step": 38020
    },
    {
      "epoch": 422.5,
      "grad_norm": 1.0513782733312382e-08,
      "learning_rate": 0.001802781332407588,
      "loss": 0.0,
      "num_input_tokens_seen": 10647536,
      "step": 38025
    },
    {
      "epoch": 422.55555555555554,
      "grad_norm": 1.101685853654999e-08,
      "learning_rate": 0.0017936876913169806,
      "loss": 0.0,
      "num_input_tokens_seen": 10648896,
      "step": 38030
    },
    {
      "epoch": 422.6111111111111,
      "grad_norm": 2.3281280903120205e-08,
      "learning_rate": 0.0017846169055022287,
      "loss": 0.0,
      "num_input_tokens_seen": 10650320,
      "step": 38035
    },
    {
      "epoch": 422.6666666666667,
      "grad_norm": 5.803459401931832e-08,
      "learning_rate": 0.0017755689763621295,
      "loss": 0.0,
      "num_input_tokens_seen": 10651760,
      "step": 38040
    },
    {
      "epoch": 422.72222222222223,
      "grad_norm": 3.173827067826096e-08,
      "learning_rate": 0.0017665439052920173,
      "loss": 0.0,
      "num_input_tokens_seen": 10653168,
      "step": 38045
    },
    {
      "epoch": 422.77777777777777,
      "grad_norm": 1.2339533839167416e-08,
      "learning_rate": 0.0017575416936836286,
      "loss": 0.0,
      "num_input_tokens_seen": 10654592,
      "step": 38050
    },
    {
      "epoch": 422.8333333333333,
      "grad_norm": 9.486258001345504e-09,
      "learning_rate": 0.0017485623429252528,
      "loss": 0.0,
      "num_input_tokens_seen": 10655968,
      "step": 38055
    },
    {
      "epoch": 422.8888888888889,
      "grad_norm": 9.632414865734518e-09,
      "learning_rate": 0.0017396058544016156,
      "loss": 0.0,
      "num_input_tokens_seen": 10657344,
      "step": 38060
    },
    {
      "epoch": 422.94444444444446,
      "grad_norm": 2.2022089041229265e-08,
      "learning_rate": 0.0017306722294938958,
      "loss": 0.0,
      "num_input_tokens_seen": 10658688,
      "step": 38065
    },
    {
      "epoch": 423.0,
      "grad_norm": 1.30071189374803e-08,
      "learning_rate": 0.0017217614695798078,
      "loss": 0.0,
      "num_input_tokens_seen": 10660080,
      "step": 38070
    },
    {
      "epoch": 423.05555555555554,
      "grad_norm": 1.5123843510878032e-08,
      "learning_rate": 0.001712873576033469,
      "loss": 0.0,
      "num_input_tokens_seen": 10661472,
      "step": 38075
    },
    {
      "epoch": 423.1111111111111,
      "grad_norm": 1.290001616638392e-08,
      "learning_rate": 0.0017040085502255163,
      "loss": 0.0,
      "num_input_tokens_seen": 10662848,
      "step": 38080
    },
    {
      "epoch": 423.1666666666667,
      "grad_norm": 1.4057940589395912e-08,
      "learning_rate": 0.0016951663935230565,
      "loss": 0.0,
      "num_input_tokens_seen": 10664256,
      "step": 38085
    },
    {
      "epoch": 423.22222222222223,
      "grad_norm": 1.3145855071172718e-08,
      "learning_rate": 0.0016863471072896485,
      "loss": 0.0,
      "num_input_tokens_seen": 10665728,
      "step": 38090
    },
    {
      "epoch": 423.27777777777777,
      "grad_norm": 1.1076139116994455e-08,
      "learning_rate": 0.0016775506928853377,
      "loss": 0.0,
      "num_input_tokens_seen": 10667120,
      "step": 38095
    },
    {
      "epoch": 423.3333333333333,
      "grad_norm": 2.321888636913627e-08,
      "learning_rate": 0.001668777151666656,
      "loss": 0.0,
      "num_input_tokens_seen": 10668512,
      "step": 38100
    },
    {
      "epoch": 423.3888888888889,
      "grad_norm": 5.8401696811927195e-09,
      "learning_rate": 0.0016600264849865709,
      "loss": 0.0,
      "num_input_tokens_seen": 10669904,
      "step": 38105
    },
    {
      "epoch": 423.44444444444446,
      "grad_norm": 1.4823392291418713e-08,
      "learning_rate": 0.0016512986941945695,
      "loss": 0.0,
      "num_input_tokens_seen": 10671328,
      "step": 38110
    },
    {
      "epoch": 423.5,
      "grad_norm": 1.6313434159087592e-08,
      "learning_rate": 0.0016425937806365753,
      "loss": 0.0,
      "num_input_tokens_seen": 10672752,
      "step": 38115
    },
    {
      "epoch": 423.55555555555554,
      "grad_norm": 9.643704501627326e-09,
      "learning_rate": 0.0016339117456549979,
      "loss": 0.0,
      "num_input_tokens_seen": 10674144,
      "step": 38120
    },
    {
      "epoch": 423.6111111111111,
      "grad_norm": 1.1465846050384698e-08,
      "learning_rate": 0.0016252525905886995,
      "loss": 0.0,
      "num_input_tokens_seen": 10675520,
      "step": 38125
    },
    {
      "epoch": 423.6666666666667,
      "grad_norm": 1.2707044305670934e-08,
      "learning_rate": 0.0016166163167730617,
      "loss": 0.0,
      "num_input_tokens_seen": 10676912,
      "step": 38130
    },
    {
      "epoch": 423.72222222222223,
      "grad_norm": 5.915869127903761e-09,
      "learning_rate": 0.0016080029255398864,
      "loss": 0.0,
      "num_input_tokens_seen": 10678320,
      "step": 38135
    },
    {
      "epoch": 423.77777777777777,
      "grad_norm": 8.729260869699829e-09,
      "learning_rate": 0.0015994124182174606,
      "loss": 0.0,
      "num_input_tokens_seen": 10679744,
      "step": 38140
    },
    {
      "epoch": 423.8333333333333,
      "grad_norm": 8.372086135466361e-09,
      "learning_rate": 0.001590844796130575,
      "loss": 0.0,
      "num_input_tokens_seen": 10681168,
      "step": 38145
    },
    {
      "epoch": 423.8888888888889,
      "grad_norm": 1.0251985038678413e-08,
      "learning_rate": 0.001582300060600439,
      "loss": 0.0,
      "num_input_tokens_seen": 10682576,
      "step": 38150
    },
    {
      "epoch": 423.94444444444446,
      "grad_norm": 1.3356742378789477e-08,
      "learning_rate": 0.0015737782129447652,
      "loss": 0.0,
      "num_input_tokens_seen": 10683952,
      "step": 38155
    },
    {
      "epoch": 424.0,
      "grad_norm": 1.2576687247189966e-08,
      "learning_rate": 0.0015652792544777361,
      "loss": 0.0,
      "num_input_tokens_seen": 10685344,
      "step": 38160
    },
    {
      "epoch": 424.05555555555554,
      "grad_norm": 8.12750311496302e-09,
      "learning_rate": 0.0015568031865099863,
      "loss": 0.0,
      "num_input_tokens_seen": 10686720,
      "step": 38165
    },
    {
      "epoch": 424.1111111111111,
      "grad_norm": 1.2289247841579254e-08,
      "learning_rate": 0.0015483500103486369,
      "loss": 0.0,
      "num_input_tokens_seen": 10688112,
      "step": 38170
    },
    {
      "epoch": 424.1666666666667,
      "grad_norm": 7.528075940399503e-09,
      "learning_rate": 0.0015399197272972787,
      "loss": 0.0,
      "num_input_tokens_seen": 10689552,
      "step": 38175
    },
    {
      "epoch": 424.22222222222223,
      "grad_norm": 9.793041044758866e-09,
      "learning_rate": 0.0015315123386559714,
      "loss": 0.0,
      "num_input_tokens_seen": 10690928,
      "step": 38180
    },
    {
      "epoch": 424.27777777777777,
      "grad_norm": 1.3279109367658748e-08,
      "learning_rate": 0.0015231278457212283,
      "loss": 0.0,
      "num_input_tokens_seen": 10692336,
      "step": 38185
    },
    {
      "epoch": 424.3333333333333,
      "grad_norm": 2.8886111280712612e-08,
      "learning_rate": 0.001514766249786048,
      "loss": 0.0,
      "num_input_tokens_seen": 10693728,
      "step": 38190
    },
    {
      "epoch": 424.3888888888889,
      "grad_norm": 1.604723465220559e-08,
      "learning_rate": 0.0015064275521398994,
      "loss": 0.0,
      "num_input_tokens_seen": 10695104,
      "step": 38195
    },
    {
      "epoch": 424.44444444444446,
      "grad_norm": 9.573109416294301e-09,
      "learning_rate": 0.0014981117540686872,
      "loss": 0.0,
      "num_input_tokens_seen": 10696528,
      "step": 38200
    },
    {
      "epoch": 424.44444444444446,
      "eval_loss": 1.8109524250030518,
      "eval_runtime": 1.1862,
      "eval_samples_per_second": 33.721,
      "eval_steps_per_second": 16.86,
      "num_input_tokens_seen": 10696528,
      "step": 38200
    },
    {
      "epoch": 424.5,
      "grad_norm": 1.2733746501680798e-08,
      "learning_rate": 0.0014898188568548687,
      "loss": 0.0,
      "num_input_tokens_seen": 10697920,
      "step": 38205
    },
    {
      "epoch": 424.55555555555554,
      "grad_norm": 9.351735386076143e-09,
      "learning_rate": 0.0014815488617772542,
      "loss": 0.0,
      "num_input_tokens_seen": 10699392,
      "step": 38210
    },
    {
      "epoch": 424.6111111111111,
      "grad_norm": 2.663257347990111e-08,
      "learning_rate": 0.0014733017701112072,
      "loss": 0.0,
      "num_input_tokens_seen": 10700768,
      "step": 38215
    },
    {
      "epoch": 424.6666666666667,
      "grad_norm": 2.529282383534337e-08,
      "learning_rate": 0.0014650775831285435,
      "loss": 0.0,
      "num_input_tokens_seen": 10702176,
      "step": 38220
    },
    {
      "epoch": 424.72222222222223,
      "grad_norm": 7.512228172856794e-09,
      "learning_rate": 0.001456876302097515,
      "loss": 0.0,
      "num_input_tokens_seen": 10703536,
      "step": 38225
    },
    {
      "epoch": 424.77777777777777,
      "grad_norm": 1.22875096764119e-08,
      "learning_rate": 0.0014486979282828604,
      "loss": 0.0,
      "num_input_tokens_seen": 10704928,
      "step": 38230
    },
    {
      "epoch": 424.8333333333333,
      "grad_norm": 1.1727979476461314e-08,
      "learning_rate": 0.001440542462945804,
      "loss": 0.0,
      "num_input_tokens_seen": 10706416,
      "step": 38235
    },
    {
      "epoch": 424.8888888888889,
      "grad_norm": 1.2866231635655367e-08,
      "learning_rate": 0.0014324099073440232,
      "loss": 0.0,
      "num_input_tokens_seen": 10707808,
      "step": 38240
    },
    {
      "epoch": 424.94444444444446,
      "grad_norm": 8.055994982214543e-09,
      "learning_rate": 0.0014243002627316482,
      "loss": 0.0,
      "num_input_tokens_seen": 10709200,
      "step": 38245
    },
    {
      "epoch": 425.0,
      "grad_norm": 1.2333784660256697e-08,
      "learning_rate": 0.0014162135303592781,
      "loss": 0.0,
      "num_input_tokens_seen": 10710608,
      "step": 38250
    },
    {
      "epoch": 425.05555555555554,
      "grad_norm": 2.6918346662796466e-08,
      "learning_rate": 0.001408149711474016,
      "loss": 0.0,
      "num_input_tokens_seen": 10712016,
      "step": 38255
    },
    {
      "epoch": 425.1111111111111,
      "grad_norm": 9.007634638180662e-09,
      "learning_rate": 0.0014001088073193834,
      "loss": 0.0,
      "num_input_tokens_seen": 10713424,
      "step": 38260
    },
    {
      "epoch": 425.1666666666667,
      "grad_norm": 2.194571635527609e-08,
      "learning_rate": 0.0013920908191354052,
      "loss": 0.0,
      "num_input_tokens_seen": 10714832,
      "step": 38265
    },
    {
      "epoch": 425.22222222222223,
      "grad_norm": 2.378036789707494e-08,
      "learning_rate": 0.001384095748158526,
      "loss": 0.0,
      "num_input_tokens_seen": 10716224,
      "step": 38270
    },
    {
      "epoch": 425.27777777777777,
      "grad_norm": 1.3438290480394244e-08,
      "learning_rate": 0.0013761235956217255,
      "loss": 0.0,
      "num_input_tokens_seen": 10717632,
      "step": 38275
    },
    {
      "epoch": 425.3333333333333,
      "grad_norm": 1.3196188142217125e-08,
      "learning_rate": 0.0013681743627543873,
      "loss": 0.0,
      "num_input_tokens_seen": 10718992,
      "step": 38280
    },
    {
      "epoch": 425.3888888888889,
      "grad_norm": 1.6409645198223188e-08,
      "learning_rate": 0.001360248050782381,
      "loss": 0.0,
      "num_input_tokens_seen": 10720416,
      "step": 38285
    },
    {
      "epoch": 425.44444444444446,
      "grad_norm": 1.2333960519583798e-08,
      "learning_rate": 0.001352344660928062,
      "loss": 0.0,
      "num_input_tokens_seen": 10721808,
      "step": 38290
    },
    {
      "epoch": 425.5,
      "grad_norm": 9.460990213483456e-09,
      "learning_rate": 0.0013444641944102052,
      "loss": 0.0,
      "num_input_tokens_seen": 10723248,
      "step": 38295
    },
    {
      "epoch": 425.55555555555554,
      "grad_norm": 2.5422242089234715e-08,
      "learning_rate": 0.0013366066524441056,
      "loss": 0.0,
      "num_input_tokens_seen": 10724656,
      "step": 38300
    },
    {
      "epoch": 425.6111111111111,
      "grad_norm": 3.265410697395055e-08,
      "learning_rate": 0.0013287720362414768,
      "loss": 0.0,
      "num_input_tokens_seen": 10726096,
      "step": 38305
    },
    {
      "epoch": 425.6666666666667,
      "grad_norm": 1.0066182554169245e-08,
      "learning_rate": 0.0013209603470105025,
      "loss": 0.0,
      "num_input_tokens_seen": 10727536,
      "step": 38310
    },
    {
      "epoch": 425.72222222222223,
      "grad_norm": 8.128785644601066e-09,
      "learning_rate": 0.0013131715859558857,
      "loss": 0.0,
      "num_input_tokens_seen": 10728912,
      "step": 38315
    },
    {
      "epoch": 425.77777777777777,
      "grad_norm": 1.3402186915811853e-08,
      "learning_rate": 0.001305405754278699,
      "loss": 0.0,
      "num_input_tokens_seen": 10730256,
      "step": 38320
    },
    {
      "epoch": 425.8333333333333,
      "grad_norm": 2.4288359767865586e-08,
      "learning_rate": 0.0012976628531765843,
      "loss": 0.0,
      "num_input_tokens_seen": 10731648,
      "step": 38325
    },
    {
      "epoch": 425.8888888888889,
      "grad_norm": 1.1831688517816019e-08,
      "learning_rate": 0.0012899428838435533,
      "loss": 0.0,
      "num_input_tokens_seen": 10733024,
      "step": 38330
    },
    {
      "epoch": 425.94444444444446,
      "grad_norm": 1.4009587268049017e-08,
      "learning_rate": 0.001282245847470137,
      "loss": 0.0,
      "num_input_tokens_seen": 10734416,
      "step": 38335
    },
    {
      "epoch": 426.0,
      "grad_norm": 1.2806609106519318e-08,
      "learning_rate": 0.001274571745243319,
      "loss": 0.0,
      "num_input_tokens_seen": 10735840,
      "step": 38340
    },
    {
      "epoch": 426.05555555555554,
      "grad_norm": 6.689433895701313e-09,
      "learning_rate": 0.0012669205783465364,
      "loss": 0.0,
      "num_input_tokens_seen": 10737200,
      "step": 38345
    },
    {
      "epoch": 426.1111111111111,
      "grad_norm": 8.122453820647024e-09,
      "learning_rate": 0.001259292347959695,
      "loss": 0.0,
      "num_input_tokens_seen": 10738608,
      "step": 38350
    },
    {
      "epoch": 426.1666666666667,
      "grad_norm": 1.399805693580447e-08,
      "learning_rate": 0.0012516870552591707,
      "loss": 0.0,
      "num_input_tokens_seen": 10740032,
      "step": 38355
    },
    {
      "epoch": 426.22222222222223,
      "grad_norm": 1.2095146217916408e-08,
      "learning_rate": 0.001244104701417792,
      "loss": 0.0,
      "num_input_tokens_seen": 10741408,
      "step": 38360
    },
    {
      "epoch": 426.27777777777777,
      "grad_norm": 1.624179368775458e-08,
      "learning_rate": 0.0012365452876048565,
      "loss": 0.0,
      "num_input_tokens_seen": 10742864,
      "step": 38365
    },
    {
      "epoch": 426.3333333333333,
      "grad_norm": 1.0324712640397138e-08,
      "learning_rate": 0.001229008814986099,
      "loss": 0.0,
      "num_input_tokens_seen": 10744224,
      "step": 38370
    },
    {
      "epoch": 426.3888888888889,
      "grad_norm": 2.3415472227839018e-08,
      "learning_rate": 0.0012214952847237725,
      "loss": 0.0,
      "num_input_tokens_seen": 10745616,
      "step": 38375
    },
    {
      "epoch": 426.44444444444446,
      "grad_norm": 1.0071020462021352e-08,
      "learning_rate": 0.0012140046979765339,
      "loss": 0.0,
      "num_input_tokens_seen": 10747056,
      "step": 38380
    },
    {
      "epoch": 426.5,
      "grad_norm": 1.2071748045627828e-08,
      "learning_rate": 0.0012065370558995258,
      "loss": 0.0,
      "num_input_tokens_seen": 10748416,
      "step": 38385
    },
    {
      "epoch": 426.55555555555554,
      "grad_norm": 2.851278146920322e-08,
      "learning_rate": 0.0011990923596443602,
      "loss": 0.0,
      "num_input_tokens_seen": 10749824,
      "step": 38390
    },
    {
      "epoch": 426.6111111111111,
      "grad_norm": 1.2280307437606552e-08,
      "learning_rate": 0.001191670610359119,
      "loss": 0.0,
      "num_input_tokens_seen": 10751248,
      "step": 38395
    },
    {
      "epoch": 426.6666666666667,
      "grad_norm": 1.2521446990376717e-08,
      "learning_rate": 0.0011842718091882865,
      "loss": 0.0,
      "num_input_tokens_seen": 10752640,
      "step": 38400
    },
    {
      "epoch": 426.6666666666667,
      "eval_loss": 1.7963682413101196,
      "eval_runtime": 1.1831,
      "eval_samples_per_second": 33.809,
      "eval_steps_per_second": 16.905,
      "num_input_tokens_seen": 10752640,
      "step": 38400
    },
    {
      "epoch": 426.72222222222223,
      "grad_norm": 1.1753867212860314e-08,
      "learning_rate": 0.0011768959572729,
      "loss": 0.0,
      "num_input_tokens_seen": 10754096,
      "step": 38405
    },
    {
      "epoch": 426.77777777777777,
      "grad_norm": 1.599290833098621e-08,
      "learning_rate": 0.001169543055750366,
      "loss": 0.0,
      "num_input_tokens_seen": 10755456,
      "step": 38410
    },
    {
      "epoch": 426.8333333333333,
      "grad_norm": 1.2760482448470611e-08,
      "learning_rate": 0.0011622131057546115,
      "loss": 0.0,
      "num_input_tokens_seen": 10756880,
      "step": 38415
    },
    {
      "epoch": 426.8888888888889,
      "grad_norm": 1.4899589118044787e-08,
      "learning_rate": 0.0011549061084160316,
      "loss": 0.0,
      "num_input_tokens_seen": 10758288,
      "step": 38420
    },
    {
      "epoch": 426.94444444444446,
      "grad_norm": 1.0396405514256912e-08,
      "learning_rate": 0.0011476220648614088,
      "loss": 0.0,
      "num_input_tokens_seen": 10759696,
      "step": 38425
    },
    {
      "epoch": 427.0,
      "grad_norm": 6.938548846591175e-09,
      "learning_rate": 0.0011403609762140777,
      "loss": 0.0,
      "num_input_tokens_seen": 10761104,
      "step": 38430
    },
    {
      "epoch": 427.05555555555554,
      "grad_norm": 1.3514340757581067e-08,
      "learning_rate": 0.0011331228435937756,
      "loss": 0.0,
      "num_input_tokens_seen": 10762496,
      "step": 38435
    },
    {
      "epoch": 427.1111111111111,
      "grad_norm": 1.1443316516590585e-08,
      "learning_rate": 0.0011259076681166935,
      "loss": 0.0,
      "num_input_tokens_seen": 10763936,
      "step": 38440
    },
    {
      "epoch": 427.1666666666667,
      "grad_norm": 7.869343399136142e-09,
      "learning_rate": 0.0011187154508955244,
      "loss": 0.0,
      "num_input_tokens_seen": 10765360,
      "step": 38445
    },
    {
      "epoch": 427.22222222222223,
      "grad_norm": 1.1068230776345445e-08,
      "learning_rate": 0.001111546193039381,
      "loss": 0.0,
      "num_input_tokens_seen": 10766752,
      "step": 38450
    },
    {
      "epoch": 427.27777777777777,
      "grad_norm": 1.0924287252578324e-08,
      "learning_rate": 0.0011043998956538792,
      "loss": 0.0,
      "num_input_tokens_seen": 10768176,
      "step": 38455
    },
    {
      "epoch": 427.3333333333333,
      "grad_norm": 1.2098301915841603e-08,
      "learning_rate": 0.0010972765598410538,
      "loss": 0.0,
      "num_input_tokens_seen": 10769584,
      "step": 38460
    },
    {
      "epoch": 427.3888888888889,
      "grad_norm": 7.152511916075355e-09,
      "learning_rate": 0.0010901761866993931,
      "loss": 0.0,
      "num_input_tokens_seen": 10770976,
      "step": 38465
    },
    {
      "epoch": 427.44444444444446,
      "grad_norm": 1.0259404881196588e-08,
      "learning_rate": 0.0010830987773238876,
      "loss": 0.0,
      "num_input_tokens_seen": 10772336,
      "step": 38470
    },
    {
      "epoch": 427.5,
      "grad_norm": 7.650624134214468e-09,
      "learning_rate": 0.0010760443328059644,
      "loss": 0.0,
      "num_input_tokens_seen": 10773744,
      "step": 38475
    },
    {
      "epoch": 427.55555555555554,
      "grad_norm": 1.2641796054424503e-08,
      "learning_rate": 0.001069012854233503,
      "loss": 0.0,
      "num_input_tokens_seen": 10775136,
      "step": 38480
    },
    {
      "epoch": 427.6111111111111,
      "grad_norm": 1.6287806658965565e-08,
      "learning_rate": 0.0010620043426908365,
      "loss": 0.0,
      "num_input_tokens_seen": 10776512,
      "step": 38485
    },
    {
      "epoch": 427.6666666666667,
      "grad_norm": 1.2266509585856511e-08,
      "learning_rate": 0.0010550187992587833,
      "loss": 0.0,
      "num_input_tokens_seen": 10777888,
      "step": 38490
    },
    {
      "epoch": 427.72222222222223,
      "grad_norm": 3.1144146817041474e-08,
      "learning_rate": 0.0010480562250145653,
      "loss": 0.0,
      "num_input_tokens_seen": 10779264,
      "step": 38495
    },
    {
      "epoch": 427.77777777777777,
      "grad_norm": 1.716857767064539e-08,
      "learning_rate": 0.0010411166210319567,
      "loss": 0.0,
      "num_input_tokens_seen": 10780688,
      "step": 38500
    },
    {
      "epoch": 427.8333333333333,
      "grad_norm": 3.75063820001742e-08,
      "learning_rate": 0.0010341999883810848,
      "loss": 0.0,
      "num_input_tokens_seen": 10782112,
      "step": 38505
    },
    {
      "epoch": 427.8888888888889,
      "grad_norm": 5.1405287138095446e-08,
      "learning_rate": 0.0010273063281285965,
      "loss": 0.0,
      "num_input_tokens_seen": 10783472,
      "step": 38510
    },
    {
      "epoch": 427.94444444444446,
      "grad_norm": 1.0868779654060745e-08,
      "learning_rate": 0.0010204356413375747,
      "loss": 0.0,
      "num_input_tokens_seen": 10784896,
      "step": 38515
    },
    {
      "epoch": 428.0,
      "grad_norm": 9.829263625249496e-09,
      "learning_rate": 0.001013587929067572,
      "loss": 0.0,
      "num_input_tokens_seen": 10786256,
      "step": 38520
    },
    {
      "epoch": 428.05555555555554,
      "grad_norm": 4.7765379207476144e-08,
      "learning_rate": 0.00100676319237461,
      "loss": 0.0,
      "num_input_tokens_seen": 10787632,
      "step": 38525
    },
    {
      "epoch": 428.1111111111111,
      "grad_norm": 8.848121346716198e-09,
      "learning_rate": 0.0009999614323110972,
      "loss": 0.0,
      "num_input_tokens_seen": 10789072,
      "step": 38530
    },
    {
      "epoch": 428.1666666666667,
      "grad_norm": 1.209872291241254e-08,
      "learning_rate": 0.000993182649926011,
      "loss": 0.0,
      "num_input_tokens_seen": 10790432,
      "step": 38535
    },
    {
      "epoch": 428.22222222222223,
      "grad_norm": 1.4874694365119012e-08,
      "learning_rate": 0.000986426846264682,
      "loss": 0.0,
      "num_input_tokens_seen": 10791824,
      "step": 38540
    },
    {
      "epoch": 428.27777777777777,
      "grad_norm": 1.2826242290486789e-08,
      "learning_rate": 0.00097969402236896,
      "loss": 0.0,
      "num_input_tokens_seen": 10793248,
      "step": 38545
    },
    {
      "epoch": 428.3333333333333,
      "grad_norm": 1.6533336477664307e-08,
      "learning_rate": 0.0009729841792771143,
      "loss": 0.0,
      "num_input_tokens_seen": 10794624,
      "step": 38550
    },
    {
      "epoch": 428.3888888888889,
      "grad_norm": 1.2836390617110283e-08,
      "learning_rate": 0.0009662973180239176,
      "loss": 0.0,
      "num_input_tokens_seen": 10796048,
      "step": 38555
    },
    {
      "epoch": 428.44444444444446,
      "grad_norm": 1.2503884150305566e-08,
      "learning_rate": 0.0009596334396405448,
      "loss": 0.0,
      "num_input_tokens_seen": 10797424,
      "step": 38560
    },
    {
      "epoch": 428.5,
      "grad_norm": 7.753982345093391e-09,
      "learning_rate": 0.0009529925451546406,
      "loss": 0.0,
      "num_input_tokens_seen": 10798816,
      "step": 38565
    },
    {
      "epoch": 428.55555555555554,
      "grad_norm": 1.156823259407247e-08,
      "learning_rate": 0.0009463746355903357,
      "loss": 0.0,
      "num_input_tokens_seen": 10800224,
      "step": 38570
    },
    {
      "epoch": 428.6111111111111,
      "grad_norm": 1.4195943087713658e-08,
      "learning_rate": 0.0009397797119681971,
      "loss": 0.0,
      "num_input_tokens_seen": 10801616,
      "step": 38575
    },
    {
      "epoch": 428.6666666666667,
      "grad_norm": 1.2179451225335924e-08,
      "learning_rate": 0.0009332077753052281,
      "loss": 0.0,
      "num_input_tokens_seen": 10803024,
      "step": 38580
    },
    {
      "epoch": 428.72222222222223,
      "grad_norm": 8.564472686600766e-09,
      "learning_rate": 0.0009266588266149011,
      "loss": 0.0,
      "num_input_tokens_seen": 10804432,
      "step": 38585
    },
    {
      "epoch": 428.77777777777777,
      "grad_norm": 2.5866956576692246e-08,
      "learning_rate": 0.0009201328669071584,
      "loss": 0.0,
      "num_input_tokens_seen": 10805840,
      "step": 38590
    },
    {
      "epoch": 428.8333333333333,
      "grad_norm": 1.320561970885592e-08,
      "learning_rate": 0.0009136298971883949,
      "loss": 0.0,
      "num_input_tokens_seen": 10807264,
      "step": 38595
    },
    {
      "epoch": 428.8888888888889,
      "grad_norm": 1.6663165069985553e-08,
      "learning_rate": 0.0009071499184614251,
      "loss": 0.0,
      "num_input_tokens_seen": 10808672,
      "step": 38600
    },
    {
      "epoch": 428.8888888888889,
      "eval_loss": 1.8125019073486328,
      "eval_runtime": 1.1901,
      "eval_samples_per_second": 33.609,
      "eval_steps_per_second": 16.805,
      "num_input_tokens_seen": 10808672,
      "step": 38600
    },
    {
      "epoch": 428.94444444444446,
      "grad_norm": 9.393250621769766e-09,
      "learning_rate": 0.0009006929317255663,
      "loss": 0.0,
      "num_input_tokens_seen": 10810048,
      "step": 38605
    },
    {
      "epoch": 429.0,
      "grad_norm": 2.4383876251476977e-08,
      "learning_rate": 0.0008942589379765387,
      "loss": 0.0,
      "num_input_tokens_seen": 10811408,
      "step": 38610
    },
    {
      "epoch": 429.05555555555554,
      "grad_norm": 1.5520724261364194e-08,
      "learning_rate": 0.0008878479382065817,
      "loss": 0.0,
      "num_input_tokens_seen": 10812800,
      "step": 38615
    },
    {
      "epoch": 429.1111111111111,
      "grad_norm": 8.34359514811922e-09,
      "learning_rate": 0.0008814599334043215,
      "loss": 0.0,
      "num_input_tokens_seen": 10814160,
      "step": 38620
    },
    {
      "epoch": 429.1666666666667,
      "grad_norm": 1.2455255493648565e-08,
      "learning_rate": 0.0008750949245548866,
      "loss": 0.0,
      "num_input_tokens_seen": 10815568,
      "step": 38625
    },
    {
      "epoch": 429.22222222222223,
      "grad_norm": 1.316951525609511e-08,
      "learning_rate": 0.0008687529126398252,
      "loss": 0.0,
      "num_input_tokens_seen": 10816976,
      "step": 38630
    },
    {
      "epoch": 429.27777777777777,
      "grad_norm": 9.182403282181895e-09,
      "learning_rate": 0.0008624338986371715,
      "loss": 0.0,
      "num_input_tokens_seen": 10818352,
      "step": 38635
    },
    {
      "epoch": 429.3333333333333,
      "grad_norm": 9.651618171346854e-09,
      "learning_rate": 0.0008561378835213962,
      "loss": 0.0,
      "num_input_tokens_seen": 10819712,
      "step": 38640
    },
    {
      "epoch": 429.3888888888889,
      "grad_norm": 1.0377726233912199e-08,
      "learning_rate": 0.0008498648682634058,
      "loss": 0.0,
      "num_input_tokens_seen": 10821168,
      "step": 38645
    },
    {
      "epoch": 429.44444444444446,
      "grad_norm": 1.2380422020896731e-08,
      "learning_rate": 0.0008436148538306099,
      "loss": 0.0,
      "num_input_tokens_seen": 10822560,
      "step": 38650
    },
    {
      "epoch": 429.5,
      "grad_norm": 1.641594593593254e-08,
      "learning_rate": 0.0008373878411868041,
      "loss": 0.0,
      "num_input_tokens_seen": 10823952,
      "step": 38655
    },
    {
      "epoch": 429.55555555555554,
      "grad_norm": 8.623564085041835e-09,
      "learning_rate": 0.000831183831292287,
      "loss": 0.0,
      "num_input_tokens_seen": 10825376,
      "step": 38660
    },
    {
      "epoch": 429.6111111111111,
      "grad_norm": 7.933476098287429e-09,
      "learning_rate": 0.0008250028251037933,
      "loss": 0.0,
      "num_input_tokens_seen": 10826784,
      "step": 38665
    },
    {
      "epoch": 429.6666666666667,
      "grad_norm": 3.0178231469335515e-08,
      "learning_rate": 0.0008188448235745271,
      "loss": 0.0,
      "num_input_tokens_seen": 10828208,
      "step": 38670
    },
    {
      "epoch": 429.72222222222223,
      "grad_norm": 7.80484121776226e-09,
      "learning_rate": 0.0008127098276541122,
      "loss": 0.0,
      "num_input_tokens_seen": 10829616,
      "step": 38675
    },
    {
      "epoch": 429.77777777777777,
      "grad_norm": 9.527902911088404e-09,
      "learning_rate": 0.0008065978382886418,
      "loss": 0.0,
      "num_input_tokens_seen": 10830976,
      "step": 38680
    },
    {
      "epoch": 429.8333333333333,
      "grad_norm": 8.711074528378049e-09,
      "learning_rate": 0.0008005088564206785,
      "loss": 0.0,
      "num_input_tokens_seen": 10832384,
      "step": 38685
    },
    {
      "epoch": 429.8888888888889,
      "grad_norm": 9.063779948803585e-09,
      "learning_rate": 0.0007944428829891881,
      "loss": 0.0,
      "num_input_tokens_seen": 10833808,
      "step": 38690
    },
    {
      "epoch": 429.94444444444446,
      "grad_norm": 1.0217656054578583e-08,
      "learning_rate": 0.0007883999189296386,
      "loss": 0.0,
      "num_input_tokens_seen": 10835168,
      "step": 38695
    },
    {
      "epoch": 430.0,
      "grad_norm": 1.2748794020467358e-08,
      "learning_rate": 0.0007823799651739515,
      "loss": 0.0,
      "num_input_tokens_seen": 10836592,
      "step": 38700
    },
    {
      "epoch": 430.05555555555554,
      "grad_norm": 1.534142413106565e-08,
      "learning_rate": 0.0007763830226504509,
      "loss": 0.0,
      "num_input_tokens_seen": 10838032,
      "step": 38705
    },
    {
      "epoch": 430.1111111111111,
      "grad_norm": 2.544165234041884e-08,
      "learning_rate": 0.0007704090922839468,
      "loss": 0.0,
      "num_input_tokens_seen": 10839408,
      "step": 38710
    },
    {
      "epoch": 430.1666666666667,
      "grad_norm": 6.777565175752898e-09,
      "learning_rate": 0.0007644581749957025,
      "loss": 0.0,
      "num_input_tokens_seen": 10840768,
      "step": 38715
    },
    {
      "epoch": 430.22222222222223,
      "grad_norm": 1.1755870943375157e-08,
      "learning_rate": 0.000758530271703417,
      "loss": 0.0,
      "num_input_tokens_seen": 10842176,
      "step": 38720
    },
    {
      "epoch": 430.27777777777777,
      "grad_norm": 8.456367162068545e-09,
      "learning_rate": 0.0007526253833212426,
      "loss": 0.0,
      "num_input_tokens_seen": 10843552,
      "step": 38725
    },
    {
      "epoch": 430.3333333333333,
      "grad_norm": 1.1594370796785824e-08,
      "learning_rate": 0.0007467435107598008,
      "loss": 0.0,
      "num_input_tokens_seen": 10844976,
      "step": 38730
    },
    {
      "epoch": 430.3888888888889,
      "grad_norm": 1.1674191391364275e-08,
      "learning_rate": 0.0007408846549261328,
      "loss": 0.0,
      "num_input_tokens_seen": 10846400,
      "step": 38735
    },
    {
      "epoch": 430.44444444444446,
      "grad_norm": 1.6593521223740026e-08,
      "learning_rate": 0.0007350488167237656,
      "loss": 0.0,
      "num_input_tokens_seen": 10847744,
      "step": 38740
    },
    {
      "epoch": 430.5,
      "grad_norm": 1.4491098099256305e-08,
      "learning_rate": 0.0007292359970526629,
      "loss": 0.0,
      "num_input_tokens_seen": 10849136,
      "step": 38745
    },
    {
      "epoch": 430.55555555555554,
      "grad_norm": 7.63323768637747e-08,
      "learning_rate": 0.0007234461968092076,
      "loss": 0.0,
      "num_input_tokens_seen": 10850496,
      "step": 38750
    },
    {
      "epoch": 430.6111111111111,
      "grad_norm": 7.652285916037727e-09,
      "learning_rate": 0.0007176794168862854,
      "loss": 0.0,
      "num_input_tokens_seen": 10851920,
      "step": 38755
    },
    {
      "epoch": 430.6666666666667,
      "grad_norm": 9.709400394797285e-09,
      "learning_rate": 0.000711935658173185,
      "loss": 0.0,
      "num_input_tokens_seen": 10853328,
      "step": 38760
    },
    {
      "epoch": 430.72222222222223,
      "grad_norm": 2.4325942149516777e-08,
      "learning_rate": 0.0007062149215556812,
      "loss": 0.0,
      "num_input_tokens_seen": 10854688,
      "step": 38765
    },
    {
      "epoch": 430.77777777777777,
      "grad_norm": 1.3179918489925058e-08,
      "learning_rate": 0.0007005172079159849,
      "loss": 0.0,
      "num_input_tokens_seen": 10856112,
      "step": 38770
    },
    {
      "epoch": 430.8333333333333,
      "grad_norm": 1.3338712356869564e-08,
      "learning_rate": 0.0006948425181327267,
      "loss": 0.0,
      "num_input_tokens_seen": 10857552,
      "step": 38775
    },
    {
      "epoch": 430.8888888888889,
      "grad_norm": 7.310321237241624e-09,
      "learning_rate": 0.000689190853081073,
      "loss": 0.0,
      "num_input_tokens_seen": 10858976,
      "step": 38780
    },
    {
      "epoch": 430.94444444444446,
      "grad_norm": 8.270561124845699e-09,
      "learning_rate": 0.000683562213632527,
      "loss": 0.0,
      "num_input_tokens_seen": 10860352,
      "step": 38785
    },
    {
      "epoch": 431.0,
      "grad_norm": 1.0709237940886851e-08,
      "learning_rate": 0.0006779566006551108,
      "loss": 0.0,
      "num_input_tokens_seen": 10861760,
      "step": 38790
    },
    {
      "epoch": 431.05555555555554,
      "grad_norm": 1.27005099770372e-08,
      "learning_rate": 0.0006723740150132995,
      "loss": 0.0,
      "num_input_tokens_seen": 10863152,
      "step": 38795
    },
    {
      "epoch": 431.1111111111111,
      "grad_norm": 1.3949815524938458e-08,
      "learning_rate": 0.0006668144575679713,
      "loss": 0.0,
      "num_input_tokens_seen": 10864512,
      "step": 38800
    },
    {
      "epoch": 431.1111111111111,
      "eval_loss": 1.7951276302337646,
      "eval_runtime": 1.185,
      "eval_samples_per_second": 33.755,
      "eval_steps_per_second": 16.878,
      "num_input_tokens_seen": 10864512,
      "step": 38800
    },
    {
      "epoch": 431.1666666666667,
      "grad_norm": 2.4900545625428094e-08,
      "learning_rate": 0.0006612779291765069,
      "loss": 0.0,
      "num_input_tokens_seen": 10865968,
      "step": 38805
    },
    {
      "epoch": 431.22222222222223,
      "grad_norm": 1.3147188226980688e-08,
      "learning_rate": 0.0006557644306926736,
      "loss": 0.0,
      "num_input_tokens_seen": 10867392,
      "step": 38810
    },
    {
      "epoch": 431.27777777777777,
      "grad_norm": 4.071930703730686e-08,
      "learning_rate": 0.0006502739629667575,
      "loss": 0.0,
      "num_input_tokens_seen": 10868768,
      "step": 38815
    },
    {
      "epoch": 431.3333333333333,
      "grad_norm": 1.5903172112530228e-08,
      "learning_rate": 0.0006448065268454317,
      "loss": 0.0,
      "num_input_tokens_seen": 10870176,
      "step": 38820
    },
    {
      "epoch": 431.3888888888889,
      "grad_norm": 1.4369835099614647e-08,
      "learning_rate": 0.0006393621231718549,
      "loss": 0.0,
      "num_input_tokens_seen": 10871536,
      "step": 38825
    },
    {
      "epoch": 431.44444444444446,
      "grad_norm": 1.2092762347037933e-08,
      "learning_rate": 0.0006339407527856389,
      "loss": 0.0,
      "num_input_tokens_seen": 10872880,
      "step": 38830
    },
    {
      "epoch": 431.5,
      "grad_norm": 1.2377126878959643e-08,
      "learning_rate": 0.0006285424165227982,
      "loss": 0.0,
      "num_input_tokens_seen": 10874208,
      "step": 38835
    },
    {
      "epoch": 431.55555555555554,
      "grad_norm": 8.6803559895543e-09,
      "learning_rate": 0.0006231671152158169,
      "loss": 0.0,
      "num_input_tokens_seen": 10875632,
      "step": 38840
    },
    {
      "epoch": 431.6111111111111,
      "grad_norm": 9.288999791579045e-09,
      "learning_rate": 0.0006178148496936819,
      "loss": 0.0,
      "num_input_tokens_seen": 10877072,
      "step": 38845
    },
    {
      "epoch": 431.6666666666667,
      "grad_norm": 1.1982284497946694e-08,
      "learning_rate": 0.000612485620781733,
      "loss": 0.0,
      "num_input_tokens_seen": 10878432,
      "step": 38850
    },
    {
      "epoch": 431.72222222222223,
      "grad_norm": 1.6196352703445882e-08,
      "learning_rate": 0.0006071794293018296,
      "loss": 0.0,
      "num_input_tokens_seen": 10879776,
      "step": 38855
    },
    {
      "epoch": 431.77777777777777,
      "grad_norm": 1.1863219739893793e-08,
      "learning_rate": 0.0006018962760722501,
      "loss": 0.0,
      "num_input_tokens_seen": 10881200,
      "step": 38860
    },
    {
      "epoch": 431.8333333333333,
      "grad_norm": 1.4195718378573474e-08,
      "learning_rate": 0.0005966361619077098,
      "loss": 0.0,
      "num_input_tokens_seen": 10882624,
      "step": 38865
    },
    {
      "epoch": 431.8888888888889,
      "grad_norm": 1.9381145577312964e-08,
      "learning_rate": 0.000591399087619393,
      "loss": 0.0,
      "num_input_tokens_seen": 10884080,
      "step": 38870
    },
    {
      "epoch": 431.94444444444446,
      "grad_norm": 3.8297969240375096e-08,
      "learning_rate": 0.0005861850540149371,
      "loss": 0.0,
      "num_input_tokens_seen": 10885504,
      "step": 38875
    },
    {
      "epoch": 432.0,
      "grad_norm": 3.601254405793952e-08,
      "learning_rate": 0.0005809940618983822,
      "loss": 0.0,
      "num_input_tokens_seen": 10886912,
      "step": 38880
    },
    {
      "epoch": 432.05555555555554,
      "grad_norm": 2.3060028553345546e-08,
      "learning_rate": 0.0005758261120702712,
      "loss": 0.0,
      "num_input_tokens_seen": 10888304,
      "step": 38885
    },
    {
      "epoch": 432.1111111111111,
      "grad_norm": 8.985269417394193e-09,
      "learning_rate": 0.0005706812053275501,
      "loss": 0.0,
      "num_input_tokens_seen": 10889696,
      "step": 38890
    },
    {
      "epoch": 432.1666666666667,
      "grad_norm": 1.0348450985020463e-08,
      "learning_rate": 0.0005655593424636173,
      "loss": 0.0,
      "num_input_tokens_seen": 10891072,
      "step": 38895
    },
    {
      "epoch": 432.22222222222223,
      "grad_norm": 1.306857644323145e-08,
      "learning_rate": 0.0005604605242683746,
      "loss": 0.0,
      "num_input_tokens_seen": 10892480,
      "step": 38900
    },
    {
      "epoch": 432.27777777777777,
      "grad_norm": 1.5099278272145966e-08,
      "learning_rate": 0.0005553847515280596,
      "loss": 0.0,
      "num_input_tokens_seen": 10893888,
      "step": 38905
    },
    {
      "epoch": 432.3333333333333,
      "grad_norm": 9.538068113101872e-09,
      "learning_rate": 0.0005503320250254795,
      "loss": 0.0,
      "num_input_tokens_seen": 10895328,
      "step": 38910
    },
    {
      "epoch": 432.3888888888889,
      "grad_norm": 1.4789955038452263e-08,
      "learning_rate": 0.0005453023455397943,
      "loss": 0.0,
      "num_input_tokens_seen": 10896736,
      "step": 38915
    },
    {
      "epoch": 432.44444444444446,
      "grad_norm": 1.0907974967722112e-08,
      "learning_rate": 0.0005402957138466502,
      "loss": 0.0,
      "num_input_tokens_seen": 10898096,
      "step": 38920
    },
    {
      "epoch": 432.5,
      "grad_norm": 8.619866598280623e-09,
      "learning_rate": 0.0005353121307181463,
      "loss": 0.0,
      "num_input_tokens_seen": 10899472,
      "step": 38925
    },
    {
      "epoch": 432.55555555555554,
      "grad_norm": 1.311072317378148e-08,
      "learning_rate": 0.0005303515969227845,
      "loss": 0.0,
      "num_input_tokens_seen": 10900864,
      "step": 38930
    },
    {
      "epoch": 432.6111111111111,
      "grad_norm": 8.557076824899923e-09,
      "learning_rate": 0.0005254141132255862,
      "loss": 0.0,
      "num_input_tokens_seen": 10902224,
      "step": 38935
    },
    {
      "epoch": 432.6666666666667,
      "grad_norm": 8.075102364557551e-09,
      "learning_rate": 0.0005204996803879258,
      "loss": 0.0,
      "num_input_tokens_seen": 10903616,
      "step": 38940
    },
    {
      "epoch": 432.72222222222223,
      "grad_norm": 1.2133858362517458e-08,
      "learning_rate": 0.0005156082991676969,
      "loss": 0.0,
      "num_input_tokens_seen": 10905024,
      "step": 38945
    },
    {
      "epoch": 432.77777777777777,
      "grad_norm": 1.811133110152241e-08,
      "learning_rate": 0.0005107399703192127,
      "loss": 0.0,
      "num_input_tokens_seen": 10906464,
      "step": 38950
    },
    {
      "epoch": 432.8333333333333,
      "grad_norm": 1.3644226193321174e-08,
      "learning_rate": 0.0005058946945932063,
      "loss": 0.0,
      "num_input_tokens_seen": 10907856,
      "step": 38955
    },
    {
      "epoch": 432.8888888888889,
      "grad_norm": 7.931378220860097e-09,
      "learning_rate": 0.0005010724727369131,
      "loss": 0.0,
      "num_input_tokens_seen": 10909280,
      "step": 38960
    },
    {
      "epoch": 432.94444444444446,
      "grad_norm": 1.1374211794645817e-08,
      "learning_rate": 0.000496273305493955,
      "loss": 0.0,
      "num_input_tokens_seen": 10910688,
      "step": 38965
    },
    {
      "epoch": 433.0,
      "grad_norm": 1.4860962238572029e-08,
      "learning_rate": 0.0004914971936044399,
      "loss": 0.0,
      "num_input_tokens_seen": 10912096,
      "step": 38970
    },
    {
      "epoch": 433.05555555555554,
      "grad_norm": 9.519997234974653e-09,
      "learning_rate": 0.00048674413780491196,
      "loss": 0.0,
      "num_input_tokens_seen": 10913536,
      "step": 38975
    },
    {
      "epoch": 433.1111111111111,
      "grad_norm": 1.2052807640827723e-08,
      "learning_rate": 0.0004820141388283183,
      "loss": 0.0,
      "num_input_tokens_seen": 10914960,
      "step": 38980
    },
    {
      "epoch": 433.1666666666667,
      "grad_norm": 1.2413754468809657e-08,
      "learning_rate": 0.00047730719740410874,
      "loss": 0.0,
      "num_input_tokens_seen": 10916352,
      "step": 38985
    },
    {
      "epoch": 433.22222222222223,
      "grad_norm": 1.342171707108264e-08,
      "learning_rate": 0.00047262331425816927,
      "loss": 0.0,
      "num_input_tokens_seen": 10917776,
      "step": 38990
    },
    {
      "epoch": 433.27777777777777,
      "grad_norm": 1.0865973898432912e-08,
      "learning_rate": 0.00046796249011277213,
      "loss": 0.0,
      "num_input_tokens_seen": 10919200,
      "step": 38995
    },
    {
      "epoch": 433.3333333333333,
      "grad_norm": 1.7144129671464725e-08,
      "learning_rate": 0.00046332472568669236,
      "loss": 0.0,
      "num_input_tokens_seen": 10920608,
      "step": 39000
    },
    {
      "epoch": 433.3333333333333,
      "eval_loss": 1.8055505752563477,
      "eval_runtime": 1.1883,
      "eval_samples_per_second": 33.663,
      "eval_steps_per_second": 16.831,
      "num_input_tokens_seen": 10920608,
      "step": 39000
    },
    {
      "epoch": 433.3888888888889,
      "grad_norm": 9.231725606184682e-09,
      "learning_rate": 0.0004587100216951578,
      "loss": 0.0,
      "num_input_tokens_seen": 10921968,
      "step": 39005
    },
    {
      "epoch": 433.44444444444446,
      "grad_norm": 9.292858038634222e-09,
      "learning_rate": 0.00045411837884978265,
      "loss": 0.0,
      "num_input_tokens_seen": 10923360,
      "step": 39010
    },
    {
      "epoch": 433.5,
      "grad_norm": 1.2853496933473707e-08,
      "learning_rate": 0.00044954979785865045,
      "loss": 0.0,
      "num_input_tokens_seen": 10924768,
      "step": 39015
    },
    {
      "epoch": 433.55555555555554,
      "grad_norm": 1.651187986340119e-08,
      "learning_rate": 0.00044500427942631426,
      "loss": 0.0,
      "num_input_tokens_seen": 10926160,
      "step": 39020
    },
    {
      "epoch": 433.6111111111111,
      "grad_norm": 1.4635227252313143e-08,
      "learning_rate": 0.0004404818242537467,
      "loss": 0.0,
      "num_input_tokens_seen": 10927600,
      "step": 39025
    },
    {
      "epoch": 433.6666666666667,
      "grad_norm": 1.312556197063941e-08,
      "learning_rate": 0.00043598243303837324,
      "loss": 0.0,
      "num_input_tokens_seen": 10928992,
      "step": 39030
    },
    {
      "epoch": 433.72222222222223,
      "grad_norm": 1.1466608107468801e-08,
      "learning_rate": 0.00043150610647403885,
      "loss": 0.0,
      "num_input_tokens_seen": 10930400,
      "step": 39035
    },
    {
      "epoch": 433.77777777777777,
      "grad_norm": 1.5642918071989698e-08,
      "learning_rate": 0.00042705284525104134,
      "loss": 0.0,
      "num_input_tokens_seen": 10931824,
      "step": 39040
    },
    {
      "epoch": 433.8333333333333,
      "grad_norm": 8.677825569236575e-09,
      "learning_rate": 0.0004226226500561647,
      "loss": 0.0,
      "num_input_tokens_seen": 10933232,
      "step": 39045
    },
    {
      "epoch": 433.8888888888889,
      "grad_norm": 3.876618492881789e-08,
      "learning_rate": 0.0004182155215725791,
      "loss": 0.0,
      "num_input_tokens_seen": 10934608,
      "step": 39050
    },
    {
      "epoch": 433.94444444444446,
      "grad_norm": 2.8007793417827997e-08,
      "learning_rate": 0.00041383146047992424,
      "loss": 0.0,
      "num_input_tokens_seen": 10935984,
      "step": 39055
    },
    {
      "epoch": 434.0,
      "grad_norm": 1.4680448856552175e-08,
      "learning_rate": 0.00040947046745427597,
      "loss": 0.0,
      "num_input_tokens_seen": 10937392,
      "step": 39060
    },
    {
      "epoch": 434.05555555555554,
      "grad_norm": 1.3455442982035493e-08,
      "learning_rate": 0.00040513254316814625,
      "loss": 0.0,
      "num_input_tokens_seen": 10938800,
      "step": 39065
    },
    {
      "epoch": 434.1111111111111,
      "grad_norm": 1.669012483773713e-08,
      "learning_rate": 0.0004008176882905168,
      "loss": 0.0,
      "num_input_tokens_seen": 10940160,
      "step": 39070
    },
    {
      "epoch": 434.1666666666667,
      "grad_norm": 1.329711274422607e-08,
      "learning_rate": 0.00039652590348677184,
      "loss": 0.0,
      "num_input_tokens_seen": 10941552,
      "step": 39075
    },
    {
      "epoch": 434.22222222222223,
      "grad_norm": 2.5905048772756345e-08,
      "learning_rate": 0.00039225718941878206,
      "loss": 0.0,
      "num_input_tokens_seen": 10942960,
      "step": 39080
    },
    {
      "epoch": 434.27777777777777,
      "grad_norm": 9.095054487318066e-09,
      "learning_rate": 0.00038801154674480417,
      "loss": 0.0,
      "num_input_tokens_seen": 10944416,
      "step": 39085
    },
    {
      "epoch": 434.3333333333333,
      "grad_norm": 2.198955684207249e-08,
      "learning_rate": 0.00038378897611959784,
      "loss": 0.0,
      "num_input_tokens_seen": 10945808,
      "step": 39090
    },
    {
      "epoch": 434.3888888888889,
      "grad_norm": 1.4257052427524286e-08,
      "learning_rate": 0.00037958947819430875,
      "loss": 0.0,
      "num_input_tokens_seen": 10947216,
      "step": 39095
    },
    {
      "epoch": 434.44444444444446,
      "grad_norm": 1.183562581275055e-08,
      "learning_rate": 0.0003754130536165856,
      "loss": 0.0,
      "num_input_tokens_seen": 10948608,
      "step": 39100
    },
    {
      "epoch": 434.5,
      "grad_norm": 4.510614814989822e-08,
      "learning_rate": 0.0003712597030304632,
      "loss": 0.0,
      "num_input_tokens_seen": 10950016,
      "step": 39105
    },
    {
      "epoch": 434.55555555555554,
      "grad_norm": 1.2939185722871116e-08,
      "learning_rate": 0.00036712942707646247,
      "loss": 0.0,
      "num_input_tokens_seen": 10951360,
      "step": 39110
    },
    {
      "epoch": 434.6111111111111,
      "grad_norm": 2.440987501017844e-08,
      "learning_rate": 0.00036302222639149063,
      "loss": 0.0,
      "num_input_tokens_seen": 10952752,
      "step": 39115
    },
    {
      "epoch": 434.6666666666667,
      "grad_norm": 3.546569971035751e-08,
      "learning_rate": 0.000358938101608941,
      "loss": 0.0,
      "num_input_tokens_seen": 10954144,
      "step": 39120
    },
    {
      "epoch": 434.72222222222223,
      "grad_norm": 1.1205719907536604e-08,
      "learning_rate": 0.0003548770533586598,
      "loss": 0.0,
      "num_input_tokens_seen": 10955520,
      "step": 39125
    },
    {
      "epoch": 434.77777777777777,
      "grad_norm": 1.3307254853600625e-08,
      "learning_rate": 0.0003508390822668961,
      "loss": 0.0,
      "num_input_tokens_seen": 10956912,
      "step": 39130
    },
    {
      "epoch": 434.8333333333333,
      "grad_norm": 7.466733897842914e-09,
      "learning_rate": 0.00034682418895633503,
      "loss": 0.0,
      "num_input_tokens_seen": 10958352,
      "step": 39135
    },
    {
      "epoch": 434.8888888888889,
      "grad_norm": 9.323051664011928e-09,
      "learning_rate": 0.0003428323740461647,
      "loss": 0.0,
      "num_input_tokens_seen": 10959744,
      "step": 39140
    },
    {
      "epoch": 434.94444444444446,
      "grad_norm": 1.0935774952258726e-08,
      "learning_rate": 0.00033886363815194276,
      "loss": 0.0,
      "num_input_tokens_seen": 10961200,
      "step": 39145
    },
    {
      "epoch": 435.0,
      "grad_norm": 1.6034094940664545e-08,
      "learning_rate": 0.0003349179818857129,
      "loss": 0.0,
      "num_input_tokens_seen": 10962608,
      "step": 39150
    },
    {
      "epoch": 435.05555555555554,
      "grad_norm": 1.3025181822001741e-08,
      "learning_rate": 0.0003309954058559383,
      "loss": 0.0,
      "num_input_tokens_seen": 10964000,
      "step": 39155
    },
    {
      "epoch": 435.1111111111111,
      "grad_norm": 4.42462066985172e-08,
      "learning_rate": 0.0003270959106675186,
      "loss": 0.0,
      "num_input_tokens_seen": 10965456,
      "step": 39160
    },
    {
      "epoch": 435.1666666666667,
      "grad_norm": 1.4817845617187686e-08,
      "learning_rate": 0.0003232194969218227,
      "loss": 0.0,
      "num_input_tokens_seen": 10966864,
      "step": 39165
    },
    {
      "epoch": 435.22222222222223,
      "grad_norm": 7.34634841847992e-09,
      "learning_rate": 0.00031936616521663905,
      "loss": 0.0,
      "num_input_tokens_seen": 10968272,
      "step": 39170
    },
    {
      "epoch": 435.27777777777777,
      "grad_norm": 7.811487456876876e-09,
      "learning_rate": 0.00031553591614619236,
      "loss": 0.0,
      "num_input_tokens_seen": 10969648,
      "step": 39175
    },
    {
      "epoch": 435.3333333333333,
      "grad_norm": 1.298952589934288e-08,
      "learning_rate": 0.00031172875030117676,
      "loss": 0.0,
      "num_input_tokens_seen": 10970992,
      "step": 39180
    },
    {
      "epoch": 435.3888888888889,
      "grad_norm": 1.1632094398805748e-08,
      "learning_rate": 0.0003079446682686726,
      "loss": 0.0,
      "num_input_tokens_seen": 10972400,
      "step": 39185
    },
    {
      "epoch": 435.44444444444446,
      "grad_norm": 1.8670011314725343e-08,
      "learning_rate": 0.0003041836706322465,
      "loss": 0.0,
      "num_input_tokens_seen": 10973824,
      "step": 39190
    },
    {
      "epoch": 435.5,
      "grad_norm": 2.3539454829801798e-08,
      "learning_rate": 0.0003004457579719011,
      "loss": 0.0,
      "num_input_tokens_seen": 10975216,
      "step": 39195
    },
    {
      "epoch": 435.55555555555554,
      "grad_norm": 1.3091770334483499e-08,
      "learning_rate": 0.00029673093086405867,
      "loss": 0.0,
      "num_input_tokens_seen": 10976624,
      "step": 39200
    },
    {
      "epoch": 435.55555555555554,
      "eval_loss": 1.7908271551132202,
      "eval_runtime": 1.2006,
      "eval_samples_per_second": 33.316,
      "eval_steps_per_second": 16.658,
      "num_input_tokens_seen": 10976624,
      "step": 39200
    },
    {
      "epoch": 435.6111111111111,
      "grad_norm": 9.615876095381282e-09,
      "learning_rate": 0.00029303918988159426,
      "loss": 0.0,
      "num_input_tokens_seen": 10977936,
      "step": 39205
    },
    {
      "epoch": 435.6666666666667,
      "grad_norm": 7.402936486045064e-09,
      "learning_rate": 0.0002893705355938192,
      "loss": 0.0,
      "num_input_tokens_seen": 10979312,
      "step": 39210
    },
    {
      "epoch": 435.72222222222223,
      "grad_norm": 7.79387931970632e-09,
      "learning_rate": 0.0002857249685664975,
      "loss": 0.0,
      "num_input_tokens_seen": 10980704,
      "step": 39215
    },
    {
      "epoch": 435.77777777777777,
      "grad_norm": 1.2886681943768963e-08,
      "learning_rate": 0.0002821024893618129,
      "loss": 0.0,
      "num_input_tokens_seen": 10982064,
      "step": 39220
    },
    {
      "epoch": 435.8333333333333,
      "grad_norm": 2.102459006891877e-08,
      "learning_rate": 0.0002785030985383852,
      "loss": 0.0,
      "num_input_tokens_seen": 10983520,
      "step": 39225
    },
    {
      "epoch": 435.8888888888889,
      "grad_norm": 1.6376503708670498e-08,
      "learning_rate": 0.00027492679665130356,
      "loss": 0.0,
      "num_input_tokens_seen": 10984960,
      "step": 39230
    },
    {
      "epoch": 435.94444444444446,
      "grad_norm": 1.0482557044610985e-08,
      "learning_rate": 0.000271373584252077,
      "loss": 0.0,
      "num_input_tokens_seen": 10986368,
      "step": 39235
    },
    {
      "epoch": 436.0,
      "grad_norm": 1.6163534510837962e-08,
      "learning_rate": 0.00026784346188865046,
      "loss": 0.0,
      "num_input_tokens_seen": 10987808,
      "step": 39240
    },
    {
      "epoch": 436.05555555555554,
      "grad_norm": 9.163928282873712e-09,
      "learning_rate": 0.0002643364301054218,
      "loss": 0.0,
      "num_input_tokens_seen": 10989216,
      "step": 39245
    },
    {
      "epoch": 436.1111111111111,
      "grad_norm": 1.3466272541506896e-08,
      "learning_rate": 0.0002608524894431918,
      "loss": 0.0,
      "num_input_tokens_seen": 10990608,
      "step": 39250
    },
    {
      "epoch": 436.1666666666667,
      "grad_norm": 8.384561489549469e-09,
      "learning_rate": 0.000257391640439264,
      "loss": 0.0,
      "num_input_tokens_seen": 10992048,
      "step": 39255
    },
    {
      "epoch": 436.22222222222223,
      "grad_norm": 1.5639512795928567e-08,
      "learning_rate": 0.00025395388362732806,
      "loss": 0.0,
      "num_input_tokens_seen": 10993424,
      "step": 39260
    },
    {
      "epoch": 436.27777777777777,
      "grad_norm": 1.2273919658412069e-08,
      "learning_rate": 0.00025053921953751,
      "loss": 0.0,
      "num_input_tokens_seen": 10994800,
      "step": 39265
    },
    {
      "epoch": 436.3333333333333,
      "grad_norm": 1.0300647446115363e-08,
      "learning_rate": 0.00024714764869643855,
      "loss": 0.0,
      "num_input_tokens_seen": 10996240,
      "step": 39270
    },
    {
      "epoch": 436.3888888888889,
      "grad_norm": 3.160750239317167e-08,
      "learning_rate": 0.0002437791716270954,
      "loss": 0.0,
      "num_input_tokens_seen": 10997616,
      "step": 39275
    },
    {
      "epoch": 436.44444444444446,
      "grad_norm": 2.608538451909226e-08,
      "learning_rate": 0.00024043378884896493,
      "loss": 0.0,
      "num_input_tokens_seen": 10998960,
      "step": 39280
    },
    {
      "epoch": 436.5,
      "grad_norm": 1.0168301756152687e-08,
      "learning_rate": 0.00023711150087793453,
      "loss": 0.0,
      "num_input_tokens_seen": 11000336,
      "step": 39285
    },
    {
      "epoch": 436.55555555555554,
      "grad_norm": 1.0675054618047852e-08,
      "learning_rate": 0.000233812308226361,
      "loss": 0.0,
      "num_input_tokens_seen": 11001744,
      "step": 39290
    },
    {
      "epoch": 436.6111111111111,
      "grad_norm": 1.489122603004489e-08,
      "learning_rate": 0.00023053621140300406,
      "loss": 0.0,
      "num_input_tokens_seen": 11003136,
      "step": 39295
    },
    {
      "epoch": 436.6666666666667,
      "grad_norm": 8.762483183488712e-09,
      "learning_rate": 0.00022728321091307623,
      "loss": 0.0,
      "num_input_tokens_seen": 11004512,
      "step": 39300
    },
    {
      "epoch": 436.72222222222223,
      "grad_norm": 1.1886867490318309e-08,
      "learning_rate": 0.0002240533072582429,
      "loss": 0.0,
      "num_input_tokens_seen": 11005888,
      "step": 39305
    },
    {
      "epoch": 436.77777777777777,
      "grad_norm": 1.2536883531311105e-08,
      "learning_rate": 0.00022084650093658897,
      "loss": 0.0,
      "num_input_tokens_seen": 11007280,
      "step": 39310
    },
    {
      "epoch": 436.8333333333333,
      "grad_norm": 1.2364040458123782e-08,
      "learning_rate": 0.0002176627924426522,
      "loss": 0.0,
      "num_input_tokens_seen": 11008704,
      "step": 39315
    },
    {
      "epoch": 436.8888888888889,
      "grad_norm": 1.544651517804141e-08,
      "learning_rate": 0.0002145021822673898,
      "loss": 0.0,
      "num_input_tokens_seen": 11010112,
      "step": 39320
    },
    {
      "epoch": 436.94444444444446,
      "grad_norm": 8.880676638511886e-09,
      "learning_rate": 0.00021136467089822862,
      "loss": 0.0,
      "num_input_tokens_seen": 11011552,
      "step": 39325
    },
    {
      "epoch": 437.0,
      "grad_norm": 2.2551574829776655e-08,
      "learning_rate": 0.00020825025881898162,
      "loss": 0.0,
      "num_input_tokens_seen": 11012960,
      "step": 39330
    },
    {
      "epoch": 437.05555555555554,
      "grad_norm": 1.1847809844311996e-08,
      "learning_rate": 0.0002051589465099479,
      "loss": 0.0,
      "num_input_tokens_seen": 11014352,
      "step": 39335
    },
    {
      "epoch": 437.1111111111111,
      "grad_norm": 8.974788023863312e-09,
      "learning_rate": 0.0002020907344478462,
      "loss": 0.0,
      "num_input_tokens_seen": 11015728,
      "step": 39340
    },
    {
      "epoch": 437.1666666666667,
      "grad_norm": 2.3864291875952404e-08,
      "learning_rate": 0.0001990456231058313,
      "loss": 0.0,
      "num_input_tokens_seen": 11017184,
      "step": 39345
    },
    {
      "epoch": 437.22222222222223,
      "grad_norm": 1.2848162533884988e-08,
      "learning_rate": 0.00019602361295349423,
      "loss": 0.0,
      "num_input_tokens_seen": 11018544,
      "step": 39350
    },
    {
      "epoch": 437.27777777777777,
      "grad_norm": 1.0255070570508451e-08,
      "learning_rate": 0.0001930247044568789,
      "loss": 0.0,
      "num_input_tokens_seen": 11019936,
      "step": 39355
    },
    {
      "epoch": 437.3333333333333,
      "grad_norm": 1.215834632972701e-08,
      "learning_rate": 0.00019004889807843205,
      "loss": 0.0,
      "num_input_tokens_seen": 11021376,
      "step": 39360
    },
    {
      "epoch": 437.3888888888889,
      "grad_norm": 1.4902703071584256e-08,
      "learning_rate": 0.00018709619427708656,
      "loss": 0.0,
      "num_input_tokens_seen": 11022720,
      "step": 39365
    },
    {
      "epoch": 437.44444444444446,
      "grad_norm": 2.8586841338551494e-08,
      "learning_rate": 0.00018416659350817822,
      "loss": 0.0,
      "num_input_tokens_seen": 11024128,
      "step": 39370
    },
    {
      "epoch": 437.5,
      "grad_norm": 1.1443586522830174e-08,
      "learning_rate": 0.00018126009622346229,
      "loss": 0.0,
      "num_input_tokens_seen": 11025504,
      "step": 39375
    },
    {
      "epoch": 437.55555555555554,
      "grad_norm": 8.103714144169771e-09,
      "learning_rate": 0.00017837670287119687,
      "loss": 0.0,
      "num_input_tokens_seen": 11026928,
      "step": 39380
    },
    {
      "epoch": 437.6111111111111,
      "grad_norm": 1.6354178455912916e-08,
      "learning_rate": 0.00017551641389602633,
      "loss": 0.0,
      "num_input_tokens_seen": 11028368,
      "step": 39385
    },
    {
      "epoch": 437.6666666666667,
      "grad_norm": 1.6367419419793805e-08,
      "learning_rate": 0.00017267922973903115,
      "loss": 0.0,
      "num_input_tokens_seen": 11029776,
      "step": 39390
    },
    {
      "epoch": 437.72222222222223,
      "grad_norm": 1.559057594135993e-08,
      "learning_rate": 0.00016986515083774467,
      "loss": 0.0,
      "num_input_tokens_seen": 11031168,
      "step": 39395
    },
    {
      "epoch": 437.77777777777777,
      "grad_norm": 1.134016880399713e-08,
      "learning_rate": 0.00016707417762611975,
      "loss": 0.0,
      "num_input_tokens_seen": 11032608,
      "step": 39400
    },
    {
      "epoch": 437.77777777777777,
      "eval_loss": 1.8039343357086182,
      "eval_runtime": 1.1877,
      "eval_samples_per_second": 33.679,
      "eval_steps_per_second": 16.84,
      "num_input_tokens_seen": 11032608,
      "step": 39400
    },
    {
      "epoch": 437.8333333333333,
      "grad_norm": 1.1960680446065908e-08,
      "learning_rate": 0.00016430631053459543,
      "loss": 0.0,
      "num_input_tokens_seen": 11034032,
      "step": 39405
    },
    {
      "epoch": 437.8888888888889,
      "grad_norm": 1.1236109820345064e-08,
      "learning_rate": 0.0001615615499899803,
      "loss": 0.0,
      "num_input_tokens_seen": 11035424,
      "step": 39410
    },
    {
      "epoch": 437.94444444444446,
      "grad_norm": 6.927660223254861e-09,
      "learning_rate": 0.00015883989641556905,
      "loss": 0.0,
      "num_input_tokens_seen": 11036832,
      "step": 39415
    },
    {
      "epoch": 438.0,
      "grad_norm": 8.345763191641709e-09,
      "learning_rate": 0.00015614135023105934,
      "loss": 0.0,
      "num_input_tokens_seen": 11038224,
      "step": 39420
    },
    {
      "epoch": 438.05555555555554,
      "grad_norm": 1.1211716000048e-08,
      "learning_rate": 0.00015346591185261827,
      "loss": 0.0,
      "num_input_tokens_seen": 11039664,
      "step": 39425
    },
    {
      "epoch": 438.1111111111111,
      "grad_norm": 1.530836790664125e-08,
      "learning_rate": 0.00015081358169281576,
      "loss": 0.0,
      "num_input_tokens_seen": 11041104,
      "step": 39430
    },
    {
      "epoch": 438.1666666666667,
      "grad_norm": 1.0790094151502672e-08,
      "learning_rate": 0.00014818436016069135,
      "loss": 0.0,
      "num_input_tokens_seen": 11042512,
      "step": 39435
    },
    {
      "epoch": 438.22222222222223,
      "grad_norm": 1.0621461044024727e-08,
      "learning_rate": 0.00014557824766168735,
      "loss": 0.0,
      "num_input_tokens_seen": 11043920,
      "step": 39440
    },
    {
      "epoch": 438.27777777777777,
      "grad_norm": 9.219702334917201e-09,
      "learning_rate": 0.00014299524459769896,
      "loss": 0.0,
      "num_input_tokens_seen": 11045344,
      "step": 39445
    },
    {
      "epoch": 438.3333333333333,
      "grad_norm": 1.2696004247914061e-08,
      "learning_rate": 0.0001404353513670742,
      "loss": 0.0,
      "num_input_tokens_seen": 11046784,
      "step": 39450
    },
    {
      "epoch": 438.3888888888889,
      "grad_norm": 1.7861873757851754e-08,
      "learning_rate": 0.0001378985683645806,
      "loss": 0.0,
      "num_input_tokens_seen": 11048208,
      "step": 39455
    },
    {
      "epoch": 438.44444444444446,
      "grad_norm": 1.3254071618007401e-08,
      "learning_rate": 0.0001353848959813886,
      "loss": 0.0,
      "num_input_tokens_seen": 11049584,
      "step": 39460
    },
    {
      "epoch": 438.5,
      "grad_norm": 2.507276342100795e-08,
      "learning_rate": 0.00013289433460517142,
      "loss": 0.0,
      "num_input_tokens_seen": 11050992,
      "step": 39465
    },
    {
      "epoch": 438.55555555555554,
      "grad_norm": 2.5356493793537993e-08,
      "learning_rate": 0.00013042688462000518,
      "loss": 0.0,
      "num_input_tokens_seen": 11052368,
      "step": 39470
    },
    {
      "epoch": 438.6111111111111,
      "grad_norm": 2.2989013359620003e-08,
      "learning_rate": 0.0001279825464063855,
      "loss": 0.0,
      "num_input_tokens_seen": 11053760,
      "step": 39475
    },
    {
      "epoch": 438.6666666666667,
      "grad_norm": 1.089020962297127e-08,
      "learning_rate": 0.00012556132034126087,
      "loss": 0.0,
      "num_input_tokens_seen": 11055152,
      "step": 39480
    },
    {
      "epoch": 438.72222222222223,
      "grad_norm": 1.0673144146267077e-08,
      "learning_rate": 0.0001231632067980326,
      "loss": 0.0,
      "num_input_tokens_seen": 11056528,
      "step": 39485
    },
    {
      "epoch": 438.77777777777777,
      "grad_norm": 8.566953368926988e-09,
      "learning_rate": 0.00012078820614650486,
      "loss": 0.0,
      "num_input_tokens_seen": 11057920,
      "step": 39490
    },
    {
      "epoch": 438.8333333333333,
      "grad_norm": 1.400854277022745e-08,
      "learning_rate": 0.00011843631875291804,
      "loss": 0.0,
      "num_input_tokens_seen": 11059344,
      "step": 39495
    },
    {
      "epoch": 438.8888888888889,
      "grad_norm": 1.33514008737734e-08,
      "learning_rate": 0.00011610754497999863,
      "loss": 0.0,
      "num_input_tokens_seen": 11060736,
      "step": 39500
    },
    {
      "epoch": 438.94444444444446,
      "grad_norm": 2.2637340890696578e-08,
      "learning_rate": 0.0001138018851868594,
      "loss": 0.0,
      "num_input_tokens_seen": 11062128,
      "step": 39505
    },
    {
      "epoch": 439.0,
      "grad_norm": 9.536714529190249e-09,
      "learning_rate": 0.0001115193397290326,
      "loss": 0.0,
      "num_input_tokens_seen": 11063488,
      "step": 39510
    },
    {
      "epoch": 439.05555555555554,
      "grad_norm": 1.1449898806858982e-08,
      "learning_rate": 0.00010925990895856996,
      "loss": 0.0,
      "num_input_tokens_seen": 11064864,
      "step": 39515
    },
    {
      "epoch": 439.1111111111111,
      "grad_norm": 3.5437967227380796e-08,
      "learning_rate": 0.00010702359322385946,
      "loss": 0.0,
      "num_input_tokens_seen": 11066288,
      "step": 39520
    },
    {
      "epoch": 439.1666666666667,
      "grad_norm": 9.11506603529233e-09,
      "learning_rate": 0.00010481039286977523,
      "loss": 0.0,
      "num_input_tokens_seen": 11067664,
      "step": 39525
    },
    {
      "epoch": 439.22222222222223,
      "grad_norm": 9.811663481684718e-09,
      "learning_rate": 0.00010262030823764423,
      "loss": 0.0,
      "num_input_tokens_seen": 11069056,
      "step": 39530
    },
    {
      "epoch": 439.27777777777777,
      "grad_norm": 1.1652591780375587e-08,
      "learning_rate": 0.00010045333966517966,
      "loss": 0.0,
      "num_input_tokens_seen": 11070480,
      "step": 39535
    },
    {
      "epoch": 439.3333333333333,
      "grad_norm": 1.0014297835425623e-08,
      "learning_rate": 9.83094874865642e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11071824,
      "step": 39540
    },
    {
      "epoch": 439.3888888888889,
      "grad_norm": 8.186907152207823e-09,
      "learning_rate": 9.618875203241672e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11073200,
      "step": 39545
    },
    {
      "epoch": 439.44444444444446,
      "grad_norm": 7.73979991208762e-09,
      "learning_rate": 9.409113362977561e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11074576,
      "step": 39550
    },
    {
      "epoch": 439.5,
      "grad_norm": 1.3575666812926102e-08,
      "learning_rate": 9.20166326020988e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11076032,
      "step": 39555
    },
    {
      "epoch": 439.55555555555554,
      "grad_norm": 1.3158592437889638e-08,
      "learning_rate": 8.996524926933035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11077408,
      "step": 39560
    },
    {
      "epoch": 439.6111111111111,
      "grad_norm": 7.4120816151435065e-09,
      "learning_rate": 8.793698394781723e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11078800,
      "step": 39565
    },
    {
      "epoch": 439.6666666666667,
      "grad_norm": 1.1096941143762251e-08,
      "learning_rate": 8.593183695030926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11080224,
      "step": 39570
    },
    {
      "epoch": 439.72222222222223,
      "grad_norm": 1.5324737034916325e-08,
      "learning_rate": 8.39498085860757e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11081664,
      "step": 39575
    },
    {
      "epoch": 439.77777777777777,
      "grad_norm": 1.7759056447630428e-08,
      "learning_rate": 8.199089916072211e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11083104,
      "step": 39580
    },
    {
      "epoch": 439.8333333333333,
      "grad_norm": 1.4952405535950675e-08,
      "learning_rate": 8.005510897637346e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11084512,
      "step": 39585
    },
    {
      "epoch": 439.8888888888889,
      "grad_norm": 8.111086913231702e-09,
      "learning_rate": 7.8142438331541e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11085888,
      "step": 39590
    },
    {
      "epoch": 439.94444444444446,
      "grad_norm": 1.4272999671050002e-08,
      "learning_rate": 7.625288752117209e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11087296,
      "step": 39595
    },
    {
      "epoch": 440.0,
      "grad_norm": 2.0524622001971693e-08,
      "learning_rate": 7.4386456836667e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11088720,
      "step": 39600
    },
    {
      "epoch": 440.0,
      "eval_loss": 1.7929683923721313,
      "eval_runtime": 1.1874,
      "eval_samples_per_second": 33.688,
      "eval_steps_per_second": 16.844,
      "num_input_tokens_seen": 11088720,
      "step": 39600
    },
    {
      "epoch": 440.05555555555554,
      "grad_norm": 4.3356219947554564e-08,
      "learning_rate": 7.254314656586214e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11090144,
      "step": 39605
    },
    {
      "epoch": 440.1111111111111,
      "grad_norm": 9.68948121737867e-09,
      "learning_rate": 7.07229569929968e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11091552,
      "step": 39610
    },
    {
      "epoch": 440.1666666666667,
      "grad_norm": 1.3951960475822034e-08,
      "learning_rate": 6.892588839879643e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11092912,
      "step": 39615
    },
    {
      "epoch": 440.22222222222223,
      "grad_norm": 1.3870452342246153e-08,
      "learning_rate": 6.71519410603727e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11094320,
      "step": 39620
    },
    {
      "epoch": 440.27777777777777,
      "grad_norm": 1.3292896561267753e-08,
      "learning_rate": 6.540111525129011e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11095696,
      "step": 39625
    },
    {
      "epoch": 440.3333333333333,
      "grad_norm": 9.57983470328827e-09,
      "learning_rate": 6.367341124154934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11097088,
      "step": 39630
    },
    {
      "epoch": 440.3888888888889,
      "grad_norm": 1.4634608191954612e-08,
      "learning_rate": 6.19688292975873e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11098544,
      "step": 39635
    },
    {
      "epoch": 440.44444444444446,
      "grad_norm": 1.3601662907092305e-08,
      "learning_rate": 6.0287369682260336e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11099952,
      "step": 39640
    },
    {
      "epoch": 440.5,
      "grad_norm": 1.4319909702464884e-08,
      "learning_rate": 5.8629032654894384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11101376,
      "step": 39645
    },
    {
      "epoch": 440.55555555555554,
      "grad_norm": 1.3629539274973013e-08,
      "learning_rate": 5.699381847120155e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11102752,
      "step": 39650
    },
    {
      "epoch": 440.6111111111111,
      "grad_norm": 1.2614004951672086e-08,
      "learning_rate": 5.5381727383380094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11104128,
      "step": 39655
    },
    {
      "epoch": 440.6666666666667,
      "grad_norm": 1.508268177019545e-08,
      "learning_rate": 5.379275964001451e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11105504,
      "step": 39660
    },
    {
      "epoch": 440.72222222222223,
      "grad_norm": 9.676353052157083e-09,
      "learning_rate": 5.222691548614211e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11106928,
      "step": 39665
    },
    {
      "epoch": 440.77777777777777,
      "grad_norm": 1.0139044270829345e-08,
      "learning_rate": 5.068419516323641e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11108304,
      "step": 39670
    },
    {
      "epoch": 440.8333333333333,
      "grad_norm": 1.2680029470857335e-08,
      "learning_rate": 4.91645989092071e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11109696,
      "step": 39675
    },
    {
      "epoch": 440.8888888888889,
      "grad_norm": 1.149320993931724e-08,
      "learning_rate": 4.7668126958400056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11111104,
      "step": 39680
    },
    {
      "epoch": 440.94444444444446,
      "grad_norm": 9.610056750375406e-09,
      "learning_rate": 4.619477954159734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11112496,
      "step": 39685
    },
    {
      "epoch": 441.0,
      "grad_norm": 9.831538250182348e-09,
      "learning_rate": 4.4744556885983884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11113888,
      "step": 39690
    },
    {
      "epoch": 441.05555555555554,
      "grad_norm": 9.244957688281374e-09,
      "learning_rate": 4.331745921523078e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11115264,
      "step": 39695
    },
    {
      "epoch": 441.1111111111111,
      "grad_norm": 1.3814917210197564e-08,
      "learning_rate": 4.191348674937867e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11116672,
      "step": 39700
    },
    {
      "epoch": 441.1666666666667,
      "grad_norm": 1.1640089780939888e-08,
      "learning_rate": 4.0532639704971006e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11118096,
      "step": 39705
    },
    {
      "epoch": 441.22222222222223,
      "grad_norm": 1.4887185706413675e-08,
      "learning_rate": 3.917491829493747e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11119520,
      "step": 39710
    },
    {
      "epoch": 441.27777777777777,
      "grad_norm": 1.33859945350423e-08,
      "learning_rate": 3.78403227286439e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11120912,
      "step": 39715
    },
    {
      "epoch": 441.3333333333333,
      "grad_norm": 1.0162168884164657e-08,
      "learning_rate": 3.652885321192567e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11122320,
      "step": 39720
    },
    {
      "epoch": 441.3888888888889,
      "grad_norm": 1.8539383361826367e-08,
      "learning_rate": 3.524050994702099e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11123728,
      "step": 39725
    },
    {
      "epoch": 441.44444444444446,
      "grad_norm": 1.0025985375250457e-08,
      "learning_rate": 3.3975293132604276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11125168,
      "step": 39730
    },
    {
      "epoch": 441.5,
      "grad_norm": 1.22832490845326e-08,
      "learning_rate": 3.2733202963786125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11126576,
      "step": 39735
    },
    {
      "epoch": 441.55555555555554,
      "grad_norm": 1.6223770771262025e-08,
      "learning_rate": 3.15142396321133e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11127952,
      "step": 39740
    },
    {
      "epoch": 441.6111111111111,
      "grad_norm": 3.336561960054496e-08,
      "learning_rate": 3.0318403325552132e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11129360,
      "step": 39745
    },
    {
      "epoch": 441.6666666666667,
      "grad_norm": 1.9235784520788002e-08,
      "learning_rate": 2.914569422855506e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11130736,
      "step": 39750
    },
    {
      "epoch": 441.72222222222223,
      "grad_norm": 2.0275145118375804e-08,
      "learning_rate": 2.7996112521927462e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11132144,
      "step": 39755
    },
    {
      "epoch": 441.77777777777777,
      "grad_norm": 8.704485132682294e-09,
      "learning_rate": 2.68696583829775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11133552,
      "step": 39760
    },
    {
      "epoch": 441.8333333333333,
      "grad_norm": 1.5487524152035803e-08,
      "learning_rate": 2.576633198539957e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11134912,
      "step": 39765
    },
    {
      "epoch": 441.8888888888889,
      "grad_norm": 7.775584620617337e-09,
      "learning_rate": 2.46861334993409e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11136336,
      "step": 39770
    },
    {
      "epoch": 441.94444444444446,
      "grad_norm": 2.387093900324544e-08,
      "learning_rate": 2.3629063091384903e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11137744,
      "step": 39775
    },
    {
      "epoch": 442.0,
      "grad_norm": 1.085460965555285e-08,
      "learning_rate": 2.2595120924567834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11139120,
      "step": 39780
    },
    {
      "epoch": 442.05555555555554,
      "grad_norm": 1.2002222327112122e-08,
      "learning_rate": 2.158430715829551e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11140544,
      "step": 39785
    },
    {
      "epoch": 442.1111111111111,
      "grad_norm": 9.081518648201836e-09,
      "learning_rate": 2.059662194849321e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11141920,
      "step": 39790
    },
    {
      "epoch": 442.1666666666667,
      "grad_norm": 1.3396149078914732e-08,
      "learning_rate": 1.9632065447422463e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11143312,
      "step": 39795
    },
    {
      "epoch": 442.22222222222223,
      "grad_norm": 1.4614958132597167e-08,
      "learning_rate": 1.8690637803880916e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11144688,
      "step": 39800
    },
    {
      "epoch": 442.22222222222223,
      "eval_loss": 1.7873080968856812,
      "eval_runtime": 1.1912,
      "eval_samples_per_second": 33.581,
      "eval_steps_per_second": 16.79,
      "num_input_tokens_seen": 11144688,
      "step": 39800
    },
    {
      "epoch": 442.27777777777777,
      "grad_norm": 9.711456527838891e-09,
      "learning_rate": 1.7772339163019123e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11146048,
      "step": 39805
    },
    {
      "epoch": 442.3333333333333,
      "grad_norm": 7.849419780825428e-09,
      "learning_rate": 1.6877169666457138e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11147488,
      "step": 39810
    },
    {
      "epoch": 442.3888888888889,
      "grad_norm": 9.652922017266974e-09,
      "learning_rate": 1.6005129452234532e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11148912,
      "step": 39815
    },
    {
      "epoch": 442.44444444444446,
      "grad_norm": 2.3585144504068012e-08,
      "learning_rate": 1.5156218654843733e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11150288,
      "step": 39820
    },
    {
      "epoch": 442.5,
      "grad_norm": 8.523211469935177e-09,
      "learning_rate": 1.4330437405196683e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11151664,
      "step": 39825
    },
    {
      "epoch": 442.55555555555554,
      "grad_norm": 1.4468820808133387e-08,
      "learning_rate": 1.352778583062486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11152992,
      "step": 39830
    },
    {
      "epoch": 442.6111111111111,
      "grad_norm": 1.303351027104327e-08,
      "learning_rate": 1.2748264054929237e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11154416,
      "step": 39835
    },
    {
      "epoch": 442.6666666666667,
      "grad_norm": 2.0875498663031067e-08,
      "learning_rate": 1.1991872198297004e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11155824,
      "step": 39840
    },
    {
      "epoch": 442.72222222222223,
      "grad_norm": 1.101146818172083e-08,
      "learning_rate": 1.1258610377384847e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11157216,
      "step": 39845
    },
    {
      "epoch": 442.77777777777777,
      "grad_norm": 1.6989348594620424e-08,
      "learning_rate": 1.0548478705268982e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 11158624,
      "step": 39850
    },
    {
      "epoch": 442.8333333333333,
      "grad_norm": 9.763104102944453e-09,
      "learning_rate": 9.86147729147846e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11160000,
      "step": 39855
    },
    {
      "epoch": 442.8888888888889,
      "grad_norm": 9.822134217074563e-09,
      "learning_rate": 9.197606241928557e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11161456,
      "step": 39860
    },
    {
      "epoch": 442.94444444444446,
      "grad_norm": 1.3814624999497482e-08,
      "learning_rate": 8.556865659004042e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11162896,
      "step": 39865
    },
    {
      "epoch": 443.0,
      "grad_norm": 3.0108001425332986e-08,
      "learning_rate": 7.939255641525867e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11164336,
      "step": 39870
    },
    {
      "epoch": 443.05555555555554,
      "grad_norm": 1.4929238290051217e-08,
      "learning_rate": 7.344776284751164e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11165712,
      "step": 39875
    },
    {
      "epoch": 443.1111111111111,
      "grad_norm": 2.639696106143674e-08,
      "learning_rate": 6.773427680323296e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11167104,
      "step": 39880
    },
    {
      "epoch": 443.1666666666667,
      "grad_norm": 1.2633201151857065e-08,
      "learning_rate": 6.225209916355112e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11168560,
      "step": 39885
    },
    {
      "epoch": 443.22222222222223,
      "grad_norm": 1.3705848012079969e-08,
      "learning_rate": 5.7001230774123e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11169968,
      "step": 39890
    },
    {
      "epoch": 443.27777777777777,
      "grad_norm": 2.5921451651811367e-08,
      "learning_rate": 5.198167244446772e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11171376,
      "step": 39895
    },
    {
      "epoch": 443.3333333333333,
      "grad_norm": 2.8648244665419043e-08,
      "learning_rate": 4.71934249487993e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11172768,
      "step": 39900
    },
    {
      "epoch": 443.3888888888889,
      "grad_norm": 1.3418642197393638e-08,
      "learning_rate": 4.2636489025527075e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11174160,
      "step": 39905
    },
    {
      "epoch": 443.44444444444446,
      "grad_norm": 2.7277978986717244e-08,
      "learning_rate": 3.831086537742223e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11175584,
      "step": 39910
    },
    {
      "epoch": 443.5,
      "grad_norm": 1.1758192641764253e-08,
      "learning_rate": 3.4216554671451236e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11176928,
      "step": 39915
    },
    {
      "epoch": 443.55555555555554,
      "grad_norm": 1.2274373517584536e-08,
      "learning_rate": 3.035355753894242e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11178304,
      "step": 39920
    },
    {
      "epoch": 443.6111111111111,
      "grad_norm": 1.3935435916323513e-08,
      "learning_rate": 2.6721874575752477e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11179728,
      "step": 39925
    },
    {
      "epoch": 443.6666666666667,
      "grad_norm": 3.076690191505804e-08,
      "learning_rate": 2.3321506341933418e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11181104,
      "step": 39930
    },
    {
      "epoch": 443.72222222222223,
      "grad_norm": 1.313865372054579e-08,
      "learning_rate": 2.0152453361732546e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11182512,
      "step": 39935
    },
    {
      "epoch": 443.77777777777777,
      "grad_norm": 1.152978690299733e-08,
      "learning_rate": 1.7214716123925554e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11183952,
      "step": 39940
    },
    {
      "epoch": 443.8333333333333,
      "grad_norm": 1.2824979300773975e-08,
      "learning_rate": 1.4508295081649968e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11185344,
      "step": 39945
    },
    {
      "epoch": 443.8888888888889,
      "grad_norm": 8.118235861331868e-09,
      "learning_rate": 1.2033190652238623e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 11186752,
      "step": 39950
    },
    {
      "epoch": 443.94444444444446,
      "grad_norm": 1.3537112764083759e-08,
      "learning_rate": 9.78940321721966e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 11188176,
      "step": 39955
    },
    {
      "epoch": 444.0,
      "grad_norm": 7.64869323433004e-09,
      "learning_rate": 7.776933122816132e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 11189552,
      "step": 39960
    },
    {
      "epoch": 444.05555555555554,
      "grad_norm": 1.8343284224897616e-08,
      "learning_rate": 5.99578067927986e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 11190960,
      "step": 39965
    },
    {
      "epoch": 444.1111111111111,
      "grad_norm": 1.310325981052074e-08,
      "learning_rate": 4.445946161224512e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 11192368,
      "step": 39970
    },
    {
      "epoch": 444.1666666666667,
      "grad_norm": 9.238860343430133e-09,
      "learning_rate": 3.127429807792126e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 11193776,
      "step": 39975
    },
    {
      "epoch": 444.22222222222223,
      "grad_norm": 1.1962029589085432e-08,
      "learning_rate": 2.040231822320049e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 11195216,
      "step": 39980
    },
    {
      "epoch": 444.27777777777777,
      "grad_norm": 1.2285404693557211e-08,
      "learning_rate": 1.1843523723409354e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 11196624,
      "step": 39985
    },
    {
      "epoch": 444.3333333333333,
      "grad_norm": 9.588492666523507e-09,
      "learning_rate": 5.597915897492811e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11198032,
      "step": 39990
    },
    {
      "epoch": 444.3888888888889,
      "grad_norm": 8.378552074361778e-09,
      "learning_rate": 1.6654957113448885e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11199424,
      "step": 39995
    },
    {
      "epoch": 444.44444444444446,
      "grad_norm": 1.401437721426646e-08,
      "learning_rate": 4.626377114735902e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11200800,
      "step": 40000
    },
    {
      "epoch": 444.44444444444446,
      "eval_loss": 1.787787675857544,
      "eval_runtime": 1.1837,
      "eval_samples_per_second": 33.793,
      "eval_steps_per_second": 16.896,
      "num_input_tokens_seen": 11200800,
      "step": 40000
    },
    {
      "epoch": 444.44444444444446,
      "num_input_tokens_seen": 11200800,
      "step": 40000,
      "total_flos": 4.69019654019072e+16,
      "train_loss": 0.02244321696852476,
      "train_runtime": 8547.6032,
      "train_samples_per_second": 18.719,
      "train_steps_per_second": 4.68
    }
  ],
  "logging_steps": 5,
  "max_steps": 40000,
  "num_input_tokens_seen": 11200800,
  "num_train_epochs": 445,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.69019654019072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}