{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00485074853113271,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.4253742655663552e-05,
      "grad_norm": 2.9237160682678223,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.4192,
      "step": 1
    },
    {
      "epoch": 4.8507485311327104e-05,
      "grad_norm": 8.286487579345703,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.7523,
      "step": 2
    },
    {
      "epoch": 7.276122796699065e-05,
      "grad_norm": 1.957672119140625,
      "learning_rate": 6e-06,
      "loss": 1.9875,
      "step": 3
    },
    {
      "epoch": 9.701497062265421e-05,
      "grad_norm": 0.5736268758773804,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.427,
      "step": 4
    },
    {
      "epoch": 0.00012126871327831776,
      "grad_norm": 0.7024741172790527,
      "learning_rate": 1e-05,
      "loss": 1.4541,
      "step": 5
    },
    {
      "epoch": 0.0001455224559339813,
      "grad_norm": 6.171888828277588,
      "learning_rate": 1.2e-05,
      "loss": 1.9617,
      "step": 6
    },
    {
      "epoch": 0.00016977619858964487,
      "grad_norm": 1.4335829019546509,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.6549,
      "step": 7
    },
    {
      "epoch": 0.00019402994124530841,
      "grad_norm": 0.8052822947502136,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.681,
      "step": 8
    },
    {
      "epoch": 0.00021828368390097196,
      "grad_norm": 1.0054032802581787,
      "learning_rate": 1.8e-05,
      "loss": 1.7113,
      "step": 9
    },
    {
      "epoch": 0.00024253742655663553,
      "grad_norm": 2.378899097442627,
      "learning_rate": 2e-05,
      "loss": 2.0225,
      "step": 10
    },
    {
      "epoch": 0.00026679116921229907,
      "grad_norm": 12.526110649108887,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.3219,
      "step": 11
    },
    {
      "epoch": 0.0002910449118679626,
      "grad_norm": 1.658133864402771,
      "learning_rate": 2.4e-05,
      "loss": 1.5336,
      "step": 12
    },
    {
      "epoch": 0.00031529865452362615,
      "grad_norm": 18.127710342407227,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.1609,
      "step": 13
    },
    {
      "epoch": 0.00033955239717928975,
      "grad_norm": 0.7923838496208191,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.7354,
      "step": 14
    },
    {
      "epoch": 0.0003638061398349533,
      "grad_norm": 1.6248362064361572,
      "learning_rate": 3e-05,
      "loss": 1.5774,
      "step": 15
    },
    {
      "epoch": 0.00038805988249061683,
      "grad_norm": 1.6371029615402222,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.2978,
      "step": 16
    },
    {
      "epoch": 0.00041231362514628037,
      "grad_norm": 1.409232497215271,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.1136,
      "step": 17
    },
    {
      "epoch": 0.0004365673678019439,
      "grad_norm": 5.593843936920166,
      "learning_rate": 3.6e-05,
      "loss": 2.3497,
      "step": 18
    },
    {
      "epoch": 0.0004608211104576075,
      "grad_norm": 1.9881709814071655,
      "learning_rate": 3.8e-05,
      "loss": 2.0849,
      "step": 19
    },
    {
      "epoch": 0.00048507485311327105,
      "grad_norm": 1.7124191522598267,
      "learning_rate": 4e-05,
      "loss": 1.565,
      "step": 20
    },
    {
      "epoch": 0.0005093285957689346,
      "grad_norm": 0.6472250819206238,
      "learning_rate": 4.2e-05,
      "loss": 1.0869,
      "step": 21
    },
    {
      "epoch": 0.0005335823384245981,
      "grad_norm": 4.816655158996582,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.2343,
      "step": 22
    },
    {
      "epoch": 0.0005578360810802617,
      "grad_norm": 1.3076063394546509,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.8767,
      "step": 23
    },
    {
      "epoch": 0.0005820898237359252,
      "grad_norm": 1.0358009338378906,
      "learning_rate": 4.8e-05,
      "loss": 1.7001,
      "step": 24
    },
    {
      "epoch": 0.0006063435663915888,
      "grad_norm": 0.8611243367195129,
      "learning_rate": 5e-05,
      "loss": 1.0703,
      "step": 25
    },
    {
      "epoch": 0.0006305973090472523,
      "grad_norm": 1.8082849979400635,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.409,
      "step": 26
    },
    {
      "epoch": 0.000654851051702916,
      "grad_norm": 2.4376935958862305,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.6188,
      "step": 27
    },
    {
      "epoch": 0.0006791047943585795,
      "grad_norm": 1.7561759948730469,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.8782,
      "step": 28
    },
    {
      "epoch": 0.000703358537014243,
      "grad_norm": 1.4189746379852295,
      "learning_rate": 5.8e-05,
      "loss": 2.1414,
      "step": 29
    },
    {
      "epoch": 0.0007276122796699066,
      "grad_norm": 1.186546802520752,
      "learning_rate": 6e-05,
      "loss": 1.5557,
      "step": 30
    },
    {
      "epoch": 0.0007518660223255701,
      "grad_norm": 1.365446925163269,
      "learning_rate": 6.2e-05,
      "loss": 1.9806,
      "step": 31
    },
    {
      "epoch": 0.0007761197649812337,
      "grad_norm": 5.6013641357421875,
      "learning_rate": 6.400000000000001e-05,
      "loss": 2.836,
      "step": 32
    },
    {
      "epoch": 0.0008003735076368972,
      "grad_norm": 1.5393822193145752,
      "learning_rate": 6.6e-05,
      "loss": 1.6833,
      "step": 33
    },
    {
      "epoch": 0.0008246272502925607,
      "grad_norm": 1.7934705018997192,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.6762,
      "step": 34
    },
    {
      "epoch": 0.0008488809929482243,
      "grad_norm": 1.1468597650527954,
      "learning_rate": 7e-05,
      "loss": 1.2819,
      "step": 35
    },
    {
      "epoch": 0.0008731347356038878,
      "grad_norm": 4.899059772491455,
      "learning_rate": 7.2e-05,
      "loss": 1.7406,
      "step": 36
    },
    {
      "epoch": 0.0008973884782595515,
      "grad_norm": 1.6008192300796509,
      "learning_rate": 7.4e-05,
      "loss": 1.5028,
      "step": 37
    },
    {
      "epoch": 0.000921642220915215,
      "grad_norm": 3.4235761165618896,
      "learning_rate": 7.6e-05,
      "loss": 1.6816,
      "step": 38
    },
    {
      "epoch": 0.0009458959635708786,
      "grad_norm": 1.1148329973220825,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.4805,
      "step": 39
    },
    {
      "epoch": 0.0009701497062265421,
      "grad_norm": 4.683089733123779,
      "learning_rate": 8e-05,
      "loss": 1.9679,
      "step": 40
    },
    {
      "epoch": 0.0009944034488822055,
      "grad_norm": 0.75764000415802,
      "learning_rate": 8.2e-05,
      "loss": 1.3406,
      "step": 41
    },
    {
      "epoch": 0.0010186571915378692,
      "grad_norm": 1.3041810989379883,
      "learning_rate": 8.4e-05,
      "loss": 1.4009,
      "step": 42
    },
    {
      "epoch": 0.0010429109341935328,
      "grad_norm": 1.4765511751174927,
      "learning_rate": 8.6e-05,
      "loss": 1.3446,
      "step": 43
    },
    {
      "epoch": 0.0010671646768491963,
      "grad_norm": 3.716846227645874,
      "learning_rate": 8.800000000000001e-05,
      "loss": 2.1417,
      "step": 44
    },
    {
      "epoch": 0.00109141841950486,
      "grad_norm": 1.0331724882125854,
      "learning_rate": 9e-05,
      "loss": 1.396,
      "step": 45
    },
    {
      "epoch": 0.0011156721621605234,
      "grad_norm": 2.426039934158325,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.466,
      "step": 46
    },
    {
      "epoch": 0.001139925904816187,
      "grad_norm": 1.3340977430343628,
      "learning_rate": 9.4e-05,
      "loss": 1.7891,
      "step": 47
    },
    {
      "epoch": 0.0011641796474718504,
      "grad_norm": 3.5191874504089355,
      "learning_rate": 9.6e-05,
      "loss": 1.6633,
      "step": 48
    },
    {
      "epoch": 0.001188433390127514,
      "grad_norm": 1.6775161027908325,
      "learning_rate": 9.8e-05,
      "loss": 1.4875,
      "step": 49
    },
    {
      "epoch": 0.0012126871327831775,
      "grad_norm": 8.406580924987793,
      "learning_rate": 0.0001,
      "loss": 2.1048,
      "step": 50
    },
    {
      "epoch": 0.0012369408754388412,
      "grad_norm": 6.012252330780029,
      "learning_rate": 0.00010200000000000001,
      "loss": 2.0742,
      "step": 51
    },
    {
      "epoch": 0.0012611946180945046,
      "grad_norm": 12.059433937072754,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.843,
      "step": 52
    },
    {
      "epoch": 0.0012854483607501683,
      "grad_norm": 1.3695584535598755,
      "learning_rate": 0.00010600000000000002,
      "loss": 1.8865,
      "step": 53
    },
    {
      "epoch": 0.001309702103405832,
      "grad_norm": 2.331925630569458,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.8662,
      "step": 54
    },
    {
      "epoch": 0.0013339558460614953,
      "grad_norm": 2.2023472785949707,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.3941,
      "step": 55
    },
    {
      "epoch": 0.001358209588717159,
      "grad_norm": 1.971096396446228,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.9362,
      "step": 56
    },
    {
      "epoch": 0.0013824633313728224,
      "grad_norm": 1.254345417022705,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.5581,
      "step": 57
    },
    {
      "epoch": 0.001406717074028486,
      "grad_norm": Infinity,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.5454,
      "step": 58
    },
    {
      "epoch": 0.0014309708166841495,
      "grad_norm": 1.5801585912704468,
      "learning_rate": 0.000116,
      "loss": 1.553,
      "step": 59
    },
    {
      "epoch": 0.0014552245593398132,
      "grad_norm": 0.9962314963340759,
      "learning_rate": 0.000118,
      "loss": 1.4924,
      "step": 60
    },
    {
      "epoch": 0.0014794783019954766,
      "grad_norm": 5.291327476501465,
      "learning_rate": 0.00012,
      "loss": 1.8365,
      "step": 61
    },
    {
      "epoch": 0.0015037320446511402,
      "grad_norm": 1.6945866346359253,
      "learning_rate": 0.000122,
      "loss": 1.4683,
      "step": 62
    },
    {
      "epoch": 0.0015279857873068039,
      "grad_norm": 1.0400323867797852,
      "learning_rate": 0.000124,
      "loss": 0.8587,
      "step": 63
    },
    {
      "epoch": 0.0015522395299624673,
      "grad_norm": 3.5120689868927,
      "learning_rate": 0.000126,
      "loss": 1.2127,
      "step": 64
    },
    {
      "epoch": 0.001576493272618131,
      "grad_norm": 1.0469675064086914,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.654,
      "step": 65
    },
    {
      "epoch": 0.0016007470152737944,
      "grad_norm": 1.5673848390579224,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.801,
      "step": 66
    },
    {
      "epoch": 0.001625000757929458,
      "grad_norm": 2.0134799480438232,
      "learning_rate": 0.000132,
      "loss": 2.0432,
      "step": 67
    },
    {
      "epoch": 0.0016492545005851215,
      "grad_norm": 7.747060775756836,
      "learning_rate": 0.000134,
      "loss": 1.4823,
      "step": 68
    },
    {
      "epoch": 0.0016735082432407851,
      "grad_norm": 3.2787840366363525,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.4865,
      "step": 69
    },
    {
      "epoch": 0.0016977619858964486,
      "grad_norm": 4.277163028717041,
      "learning_rate": 0.000138,
      "loss": 1.4665,
      "step": 70
    },
    {
      "epoch": 0.0017220157285521122,
      "grad_norm": 11.562691688537598,
      "learning_rate": 0.00014,
      "loss": 2.0221,
      "step": 71
    },
    {
      "epoch": 0.0017462694712077757,
      "grad_norm": 2.5653882026672363,
      "learning_rate": 0.000142,
      "loss": 1.4631,
      "step": 72
    },
    {
      "epoch": 0.0017705232138634393,
      "grad_norm": 2.392688751220703,
      "learning_rate": 0.000144,
      "loss": 1.3514,
      "step": 73
    },
    {
      "epoch": 0.001794776956519103,
      "grad_norm": 3.874115467071533,
      "learning_rate": 0.000146,
      "loss": 1.5983,
      "step": 74
    },
    {
      "epoch": 0.0018190306991747664,
      "grad_norm": 3.085160732269287,
      "learning_rate": 0.000148,
      "loss": 1.321,
      "step": 75
    },
    {
      "epoch": 0.00184328444183043,
      "grad_norm": 1.7499727010726929,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.385,
      "step": 76
    },
    {
      "epoch": 0.0018675381844860935,
      "grad_norm": 14.051904678344727,
      "learning_rate": 0.000152,
      "loss": 1.5748,
      "step": 77
    },
    {
      "epoch": 0.0018917919271417571,
      "grad_norm": 4.689906597137451,
      "learning_rate": 0.000154,
      "loss": 1.2126,
      "step": 78
    },
    {
      "epoch": 0.0019160456697974206,
      "grad_norm": 1.0368577241897583,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.0542,
      "step": 79
    },
    {
      "epoch": 0.0019402994124530842,
      "grad_norm": 3.577094078063965,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.9481,
      "step": 80
    },
    {
      "epoch": 0.001964553155108748,
      "grad_norm": NaN,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.2913,
      "step": 81
    },
    {
      "epoch": 0.001988806897764411,
      "grad_norm": 4.969227313995361,
      "learning_rate": 0.00016,
      "loss": 1.5551,
      "step": 82
    },
    {
      "epoch": 0.0020130606404200747,
      "grad_norm": 71.41371154785156,
      "learning_rate": 0.000162,
      "loss": 1.5847,
      "step": 83
    },
    {
      "epoch": 0.0020373143830757384,
      "grad_norm": 0.9679685831069946,
      "learning_rate": 0.000164,
      "loss": 1.1516,
      "step": 84
    },
    {
      "epoch": 0.002061568125731402,
      "grad_norm": 7.050138473510742,
      "learning_rate": 0.000166,
      "loss": 1.6904,
      "step": 85
    },
    {
      "epoch": 0.0020858218683870657,
      "grad_norm": 1.4181028604507446,
      "learning_rate": 0.000168,
      "loss": 1.5385,
      "step": 86
    },
    {
      "epoch": 0.002110075611042729,
      "grad_norm": 1.122887134552002,
      "learning_rate": 0.00017,
      "loss": 1.282,
      "step": 87
    },
    {
      "epoch": 0.0021343293536983925,
      "grad_norm": 3.0532054901123047,
      "learning_rate": 0.000172,
      "loss": 1.7126,
      "step": 88
    },
    {
      "epoch": 0.002158583096354056,
      "grad_norm": 1.1368091106414795,
      "learning_rate": 0.000174,
      "loss": 1.3792,
      "step": 89
    },
    {
      "epoch": 0.00218283683900972,
      "grad_norm": 1.5556614398956299,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.1266,
      "step": 90
    },
    {
      "epoch": 0.002207090581665383,
      "grad_norm": 2.5969090461730957,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.1916,
      "step": 91
    },
    {
      "epoch": 0.0022313443243210467,
      "grad_norm": 7.9968719482421875,
      "learning_rate": 0.00018,
      "loss": 2.3005,
      "step": 92
    },
    {
      "epoch": 0.0022555980669767104,
      "grad_norm": 1.0678150653839111,
      "learning_rate": 0.000182,
      "loss": 1.1991,
      "step": 93
    },
    {
      "epoch": 0.002279851809632374,
      "grad_norm": 6.678997993469238,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.9749,
      "step": 94
    },
    {
      "epoch": 0.0023041055522880377,
      "grad_norm": 2.6500961780548096,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.7569,
      "step": 95
    },
    {
      "epoch": 0.002328359294943701,
      "grad_norm": 1.547878384590149,
      "learning_rate": 0.000188,
      "loss": 1.7286,
      "step": 96
    },
    {
      "epoch": 0.0023526130375993645,
      "grad_norm": 1.910861849784851,
      "learning_rate": 0.00019,
      "loss": 2.0815,
      "step": 97
    },
    {
      "epoch": 0.002376866780255028,
      "grad_norm": 3.678144693374634,
      "learning_rate": 0.000192,
      "loss": 1.7011,
      "step": 98
    },
    {
      "epoch": 0.002401120522910692,
      "grad_norm": 1.6496407985687256,
      "learning_rate": 0.000194,
      "loss": 1.8013,
      "step": 99
    },
    {
      "epoch": 0.002425374265566355,
      "grad_norm": 1.3245445489883423,
      "learning_rate": 0.000196,
      "loss": 1.5302,
      "step": 100
    },
    {
      "epoch": 0.0024496280082220187,
      "grad_norm": 1.609408974647522,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.6082,
      "step": 101
    },
    {
      "epoch": 0.0024738817508776823,
      "grad_norm": 2.7757482528686523,
      "learning_rate": 0.0002,
      "loss": 1.6157,
      "step": 102
    },
    {
      "epoch": 0.002498135493533346,
      "grad_norm": 2.0618674755096436,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.7212,
      "step": 103
    },
    {
      "epoch": 0.002522389236189009,
      "grad_norm": 1.7433160543441772,
      "learning_rate": 0.000196,
      "loss": 1.9133,
      "step": 104
    },
    {
      "epoch": 0.002546642978844673,
      "grad_norm": 1.4754176139831543,
      "learning_rate": 0.000194,
      "loss": 1.3311,
      "step": 105
    },
    {
      "epoch": 0.0025708967215003365,
      "grad_norm": 1.4527512788772583,
      "learning_rate": 0.000192,
      "loss": 1.6432,
      "step": 106
    },
    {
      "epoch": 0.002595150464156,
      "grad_norm": 5.3099045753479,
      "learning_rate": 0.00019,
      "loss": 1.3233,
      "step": 107
    },
    {
      "epoch": 0.002619404206811664,
      "grad_norm": 1.016135573387146,
      "learning_rate": 0.000188,
      "loss": 1.3291,
      "step": 108
    },
    {
      "epoch": 0.002643657949467327,
      "grad_norm": 1.0468915700912476,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.4454,
      "step": 109
    },
    {
      "epoch": 0.0026679116921229907,
      "grad_norm": 3.245159387588501,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.6501,
      "step": 110
    },
    {
      "epoch": 0.0026921654347786543,
      "grad_norm": 1.1628005504608154,
      "learning_rate": 0.000182,
      "loss": 1.399,
      "step": 111
    },
    {
      "epoch": 0.002716419177434318,
      "grad_norm": 3.3215761184692383,
      "learning_rate": 0.00018,
      "loss": 1.4829,
      "step": 112
    },
    {
      "epoch": 0.002740672920089981,
      "grad_norm": 1.424054503440857,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.7692,
      "step": 113
    },
    {
      "epoch": 0.002764926662745645,
      "grad_norm": 1.2700444459915161,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.6959,
      "step": 114
    },
    {
      "epoch": 0.0027891804054013085,
      "grad_norm": 1.262736201286316,
      "learning_rate": 0.000174,
      "loss": 1.5445,
      "step": 115
    },
    {
      "epoch": 0.002813434148056972,
      "grad_norm": 4.976276397705078,
      "learning_rate": 0.000172,
      "loss": 1.4571,
      "step": 116
    },
    {
      "epoch": 0.002837687890712636,
      "grad_norm": 1.2716983556747437,
      "learning_rate": 0.00017,
      "loss": 1.217,
      "step": 117
    },
    {
      "epoch": 0.002861941633368299,
      "grad_norm": 1.5143672227859497,
      "learning_rate": 0.000168,
      "loss": 1.3059,
      "step": 118
    },
    {
      "epoch": 0.0028861953760239627,
      "grad_norm": 0.9907928705215454,
      "learning_rate": 0.000166,
      "loss": 1.8035,
      "step": 119
    },
    {
      "epoch": 0.0029104491186796263,
      "grad_norm": 1.7163773775100708,
      "learning_rate": 0.000164,
      "loss": 2.1635,
      "step": 120
    },
    {
      "epoch": 0.00293470286133529,
      "grad_norm": 7.744179725646973,
      "learning_rate": 0.000162,
      "loss": 2.2964,
      "step": 121
    },
    {
      "epoch": 0.002958956603990953,
      "grad_norm": 1.101208209991455,
      "learning_rate": 0.00016,
      "loss": 1.46,
      "step": 122
    },
    {
      "epoch": 0.002983210346646617,
      "grad_norm": 0.7589418888092041,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.1036,
      "step": 123
    },
    {
      "epoch": 0.0030074640893022805,
      "grad_norm": 4.626345634460449,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.5257,
      "step": 124
    },
    {
      "epoch": 0.003031717831957944,
      "grad_norm": 1.5994218587875366,
      "learning_rate": 0.000154,
      "loss": 1.2856,
      "step": 125
    },
    {
      "epoch": 0.0030559715746136078,
      "grad_norm": 1.3893097639083862,
      "learning_rate": 0.000152,
      "loss": 1.3359,
      "step": 126
    },
    {
      "epoch": 0.003080225317269271,
      "grad_norm": 1.0536174774169922,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.1718,
      "step": 127
    },
    {
      "epoch": 0.0031044790599249346,
      "grad_norm": 1.2898694276809692,
      "learning_rate": 0.000148,
      "loss": 1.2908,
      "step": 128
    },
    {
      "epoch": 0.0031287328025805983,
      "grad_norm": 1.6943238973617554,
      "learning_rate": 0.000146,
      "loss": 1.7723,
      "step": 129
    },
    {
      "epoch": 0.003152986545236262,
      "grad_norm": 1.2562038898468018,
      "learning_rate": 0.000144,
      "loss": 1.4476,
      "step": 130
    },
    {
      "epoch": 0.003177240287891925,
      "grad_norm": 1.0170366764068604,
      "learning_rate": 0.000142,
      "loss": 1.2967,
      "step": 131
    },
    {
      "epoch": 0.003201494030547589,
      "grad_norm": 5.646616458892822,
      "learning_rate": 0.00014,
      "loss": 1.4366,
      "step": 132
    },
    {
      "epoch": 0.0032257477732032525,
      "grad_norm": 1.29356849193573,
      "learning_rate": 0.000138,
      "loss": 1.4713,
      "step": 133
    },
    {
      "epoch": 0.003250001515858916,
      "grad_norm": 1.3575730323791504,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.2233,
      "step": 134
    },
    {
      "epoch": 0.0032742552585145793,
      "grad_norm": 1.158686876296997,
      "learning_rate": 0.000134,
      "loss": 1.3622,
      "step": 135
    },
    {
      "epoch": 0.003298509001170243,
      "grad_norm": 1.4680081605911255,
      "learning_rate": 0.000132,
      "loss": 1.7191,
      "step": 136
    },
    {
      "epoch": 0.0033227627438259066,
      "grad_norm": 1.2448982000350952,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.9376,
      "step": 137
    },
    {
      "epoch": 0.0033470164864815703,
      "grad_norm": 1.2404478788375854,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.5334,
      "step": 138
    },
    {
      "epoch": 0.003371270229137234,
      "grad_norm": 0.9862974882125854,
      "learning_rate": 0.000126,
      "loss": 1.2073,
      "step": 139
    },
    {
      "epoch": 0.003395523971792897,
      "grad_norm": 7.36776876449585,
      "learning_rate": 0.000124,
      "loss": 1.5745,
      "step": 140
    },
    {
      "epoch": 0.003419777714448561,
      "grad_norm": 1.1356145143508911,
      "learning_rate": 0.000122,
      "loss": 1.563,
      "step": 141
    },
    {
      "epoch": 0.0034440314571042244,
      "grad_norm": 2.073420286178589,
      "learning_rate": 0.00012,
      "loss": 1.7438,
      "step": 142
    },
    {
      "epoch": 0.003468285199759888,
      "grad_norm": 3.029547691345215,
      "learning_rate": 0.000118,
      "loss": 1.6755,
      "step": 143
    },
    {
      "epoch": 0.0034925389424155513,
      "grad_norm": 14.66256046295166,
      "learning_rate": 0.000116,
      "loss": 1.8375,
      "step": 144
    },
    {
      "epoch": 0.003516792685071215,
      "grad_norm": 0.8765383958816528,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.6782,
      "step": 145
    },
    {
      "epoch": 0.0035410464277268786,
      "grad_norm": 3.167731761932373,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.4619,
      "step": 146
    },
    {
      "epoch": 0.0035653001703825423,
      "grad_norm": 1.1016606092453003,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.5817,
      "step": 147
    },
    {
      "epoch": 0.003589553913038206,
      "grad_norm": 2.5535902976989746,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.3491,
      "step": 148
    },
    {
      "epoch": 0.003613807655693869,
      "grad_norm": 1.1920926570892334,
      "learning_rate": 0.00010600000000000002,
      "loss": 1.5675,
      "step": 149
    },
    {
      "epoch": 0.0036380613983495328,
      "grad_norm": 1.1023300886154175,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.2821,
      "step": 150
    },
    {
      "epoch": 0.0036623151410051964,
      "grad_norm": 2.1146063804626465,
      "learning_rate": 0.00010200000000000001,
      "loss": 1.5396,
      "step": 151
    },
    {
      "epoch": 0.00368656888366086,
      "grad_norm": 1.1838195323944092,
      "learning_rate": 0.0001,
      "loss": 1.2992,
      "step": 152
    },
    {
      "epoch": 0.0037108226263165233,
      "grad_norm": 1.414258360862732,
      "learning_rate": 9.8e-05,
      "loss": 1.6888,
      "step": 153
    },
    {
      "epoch": 0.003735076368972187,
      "grad_norm": 0.8630995154380798,
      "learning_rate": 9.6e-05,
      "loss": 1.141,
      "step": 154
    },
    {
      "epoch": 0.0037593301116278506,
      "grad_norm": 2.4763197898864746,
      "learning_rate": 9.4e-05,
      "loss": 1.5743,
      "step": 155
    },
    {
      "epoch": 0.0037835838542835142,
      "grad_norm": 0.9457703828811646,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.3879,
      "step": 156
    },
    {
      "epoch": 0.003807837596939178,
      "grad_norm": 1.308862328529358,
      "learning_rate": 9e-05,
      "loss": 1.1564,
      "step": 157
    },
    {
      "epoch": 0.003832091339594841,
      "grad_norm": 1.208833932876587,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.2059,
      "step": 158
    },
    {
      "epoch": 0.0038563450822505048,
      "grad_norm": 1.9145225286483765,
      "learning_rate": 8.6e-05,
      "loss": 1.4744,
      "step": 159
    },
    {
      "epoch": 0.0038805988249061684,
      "grad_norm": 1.0121599435806274,
      "learning_rate": 8.4e-05,
      "loss": 1.8676,
      "step": 160
    },
    {
      "epoch": 0.003904852567561832,
      "grad_norm": 1.9128226041793823,
      "learning_rate": 8.2e-05,
      "loss": 1.6948,
      "step": 161
    },
    {
      "epoch": 0.003929106310217496,
      "grad_norm": 1.7783511877059937,
      "learning_rate": 8e-05,
      "loss": 1.4198,
      "step": 162
    },
    {
      "epoch": 0.003953360052873159,
      "grad_norm": 0.9799928665161133,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.185,
      "step": 163
    },
    {
      "epoch": 0.003977613795528822,
      "grad_norm": 1.5025819540023804,
      "learning_rate": 7.6e-05,
      "loss": 1.0638,
      "step": 164
    },
    {
      "epoch": 0.004001867538184486,
      "grad_norm": 1.2552540302276611,
      "learning_rate": 7.4e-05,
      "loss": 1.3463,
      "step": 165
    },
    {
      "epoch": 0.0040261212808401494,
      "grad_norm": 1.0616928339004517,
      "learning_rate": 7.2e-05,
      "loss": 1.9275,
      "step": 166
    },
    {
      "epoch": 0.004050375023495813,
      "grad_norm": 2.8277781009674072,
      "learning_rate": 7e-05,
      "loss": 1.9653,
      "step": 167
    },
    {
      "epoch": 0.004074628766151477,
      "grad_norm": 1.7752915620803833,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.2783,
      "step": 168
    },
    {
      "epoch": 0.00409888250880714,
      "grad_norm": 2.4863102436065674,
      "learning_rate": 6.6e-05,
      "loss": 1.2803,
      "step": 169
    },
    {
      "epoch": 0.004123136251462804,
      "grad_norm": 0.9784297943115234,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.0347,
      "step": 170
    },
    {
      "epoch": 0.004147389994118468,
      "grad_norm": 2.0077602863311768,
      "learning_rate": 6.2e-05,
      "loss": 1.5035,
      "step": 171
    },
    {
      "epoch": 0.004171643736774131,
      "grad_norm": 1.5943875312805176,
      "learning_rate": 6e-05,
      "loss": 1.7834,
      "step": 172
    },
    {
      "epoch": 0.004195897479429794,
      "grad_norm": 1.0898661613464355,
      "learning_rate": 5.8e-05,
      "loss": 1.5043,
      "step": 173
    },
    {
      "epoch": 0.004220151222085458,
      "grad_norm": 1.8181873559951782,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.5026,
      "step": 174
    },
    {
      "epoch": 0.004244404964741121,
      "grad_norm": 0.9227128028869629,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.3945,
      "step": 175
    },
    {
      "epoch": 0.004268658707396785,
      "grad_norm": 1.3131438493728638,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.2629,
      "step": 176
    },
    {
      "epoch": 0.004292912450052449,
      "grad_norm": 1.388433814048767,
      "learning_rate": 5e-05,
      "loss": 1.607,
      "step": 177
    },
    {
      "epoch": 0.004317166192708112,
      "grad_norm": 1.5145083665847778,
      "learning_rate": 4.8e-05,
      "loss": 1.8671,
      "step": 178
    },
    {
      "epoch": 0.004341419935363776,
      "grad_norm": 2.0021004676818848,
      "learning_rate": 4.600000000000001e-05,
      "loss": 2.0679,
      "step": 179
    },
    {
      "epoch": 0.00436567367801944,
      "grad_norm": 1.8512483835220337,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.3095,
      "step": 180
    },
    {
      "epoch": 0.004389927420675103,
      "grad_norm": 1.0164090394973755,
      "learning_rate": 4.2e-05,
      "loss": 1.3749,
      "step": 181
    },
    {
      "epoch": 0.004414181163330766,
      "grad_norm": 30.730253219604492,
      "learning_rate": 4e-05,
      "loss": 2.3106,
      "step": 182
    },
    {
      "epoch": 0.00443843490598643,
      "grad_norm": 1.2311471700668335,
      "learning_rate": 3.8e-05,
      "loss": 1.1078,
      "step": 183
    },
    {
      "epoch": 0.004462688648642093,
      "grad_norm": 0.9555554389953613,
      "learning_rate": 3.6e-05,
      "loss": 1.4175,
      "step": 184
    },
    {
      "epoch": 0.004486942391297757,
      "grad_norm": 1.4511969089508057,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.4099,
      "step": 185
    },
    {
      "epoch": 0.004511196133953421,
      "grad_norm": 5.319721221923828,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.2749,
      "step": 186
    },
    {
      "epoch": 0.004535449876609084,
      "grad_norm": 1.8668482303619385,
      "learning_rate": 3e-05,
      "loss": 1.4658,
      "step": 187
    },
    {
      "epoch": 0.004559703619264748,
      "grad_norm": 1.737425684928894,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.8142,
      "step": 188
    },
    {
      "epoch": 0.004583957361920412,
      "grad_norm": 12.860699653625488,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.6338,
      "step": 189
    },
    {
      "epoch": 0.004608211104576075,
      "grad_norm": 0.6315305233001709,
      "learning_rate": 2.4e-05,
      "loss": 1.0426,
      "step": 190
    },
    {
      "epoch": 0.004632464847231738,
      "grad_norm": 1.0747138261795044,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.4042,
      "step": 191
    },
    {
      "epoch": 0.004656718589887402,
      "grad_norm": 1.1410670280456543,
      "learning_rate": 2e-05,
      "loss": 1.2148,
      "step": 192
    },
    {
      "epoch": 0.004680972332543065,
      "grad_norm": 1.4486732482910156,
      "learning_rate": 1.8e-05,
      "loss": 1.3208,
      "step": 193
    },
    {
      "epoch": 0.004705226075198729,
      "grad_norm": 2.5336716175079346,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.7136,
      "step": 194
    },
    {
      "epoch": 0.004729479817854393,
      "grad_norm": 3.4056637287139893,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.5443,
      "step": 195
    },
    {
      "epoch": 0.004753733560510056,
      "grad_norm": 1.1721996068954468,
      "learning_rate": 1.2e-05,
      "loss": 1.4518,
      "step": 196
    },
    {
      "epoch": 0.00477798730316572,
      "grad_norm": 1.9326874017715454,
      "learning_rate": 1e-05,
      "loss": 1.6381,
      "step": 197
    },
    {
      "epoch": 0.004802241045821384,
      "grad_norm": 1.0234136581420898,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.4116,
      "step": 198
    },
    {
      "epoch": 0.004826494788477047,
      "grad_norm": 2.1815526485443115,
      "learning_rate": 6e-06,
      "loss": 1.7442,
      "step": 199
    },
    {
      "epoch": 0.00485074853113271,
      "grad_norm": 1.9557406902313232,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.9568,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6034692870365184.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}