{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9988925802879292,
  "eval_steps": 113,
  "global_step": 451,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 3.428594393312656,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.1469,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 2.179504632949829,
      "eval_runtime": 172.7557,
      "eval_samples_per_second": 13.447,
      "eval_steps_per_second": 0.423,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 3.7159828982580754,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.1946,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.643082734610657,
      "learning_rate": 1.2e-05,
      "loss": 2.232,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.75889245136616,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.1482,
      "step": 4
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.121791718587376,
      "learning_rate": 2e-05,
      "loss": 1.9094,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.357880867767518,
      "learning_rate": 2.4e-05,
      "loss": 1.5871,
      "step": 6
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.946129682154882,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.326,
      "step": 7
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.108395610487625,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.0602,
      "step": 8
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.130447473758986,
      "learning_rate": 3.6e-05,
      "loss": 0.962,
      "step": 9
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.250625735269271,
      "learning_rate": 4e-05,
      "loss": 0.7239,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.086877732413652,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6204,
      "step": 11
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.1321791358110234,
      "learning_rate": 4.8e-05,
      "loss": 0.5483,
      "step": 12
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.8099243715089002,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.5086,
      "step": 13
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.8079844588753853,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.5112,
      "step": 14
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.9169759048137539,
      "learning_rate": 6e-05,
      "loss": 0.4889,
      "step": 15
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.6917931287891316,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.4691,
      "step": 16
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.6294590670553853,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.4549,
      "step": 17
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.6001819771732335,
      "learning_rate": 7.2e-05,
      "loss": 0.4412,
      "step": 18
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.6389927422614288,
      "learning_rate": 7.6e-05,
      "loss": 0.4077,
      "step": 19
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.5185334799357709,
      "learning_rate": 8e-05,
      "loss": 0.4219,
      "step": 20
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.5274718517549238,
      "learning_rate": 8.4e-05,
      "loss": 0.4124,
      "step": 21
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.5333597700699511,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.4333,
      "step": 22
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.4817408646893783,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.4022,
      "step": 23
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.5041871581629092,
      "learning_rate": 9.6e-05,
      "loss": 0.3971,
      "step": 24
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.5892498993207921,
      "learning_rate": 0.0001,
      "loss": 0.3769,
      "step": 25
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.4448471314677223,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.3905,
      "step": 26
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.41460492934076704,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.3814,
      "step": 27
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.39759977947743247,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.3675,
      "step": 28
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.42656614420804834,
      "learning_rate": 0.000116,
      "loss": 0.3949,
      "step": 29
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.3248894659390531,
      "learning_rate": 0.00012,
      "loss": 0.3734,
      "step": 30
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.35364315198613105,
      "learning_rate": 0.000124,
      "loss": 0.3452,
      "step": 31
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.3377660731261332,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.365,
      "step": 32
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.3029616210555195,
      "learning_rate": 0.000132,
      "loss": 0.3502,
      "step": 33
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.43234275224940705,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.3728,
      "step": 34
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.3831666942704003,
      "learning_rate": 0.00014,
      "loss": 0.3922,
      "step": 35
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.3421076533380305,
      "learning_rate": 0.000144,
      "loss": 0.3544,
      "step": 36
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.30146273904800347,
      "learning_rate": 0.000148,
      "loss": 0.3237,
      "step": 37
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.3234891150012619,
      "learning_rate": 0.000152,
      "loss": 0.3771,
      "step": 38
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.32536194802044366,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.3719,
      "step": 39
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.32489341033312524,
      "learning_rate": 0.00016,
      "loss": 0.3716,
      "step": 40
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.3135978131489568,
      "learning_rate": 0.000164,
      "loss": 0.3818,
      "step": 41
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.28403149178513853,
      "learning_rate": 0.000168,
      "loss": 0.3576,
      "step": 42
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.30747408490186307,
      "learning_rate": 0.000172,
      "loss": 0.3801,
      "step": 43
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.3491185114838396,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.3612,
      "step": 44
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.4062709802932099,
      "learning_rate": 0.00018,
      "loss": 0.3752,
      "step": 45
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.4174448098463489,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.3705,
      "step": 46
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.30034892483536746,
      "learning_rate": 0.000188,
      "loss": 0.3504,
      "step": 47
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.24699047743823555,
      "learning_rate": 0.000192,
      "loss": 0.3622,
      "step": 48
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.2944161708858025,
      "learning_rate": 0.000196,
      "loss": 0.3462,
      "step": 49
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.24968532785704994,
      "learning_rate": 0.0002,
      "loss": 0.3074,
      "step": 50
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.4989866478305154,
      "learning_rate": 0.00019999932018605637,
      "loss": 0.3426,
      "step": 51
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.2729667152979656,
      "learning_rate": 0.00019999728075346845,
      "loss": 0.3452,
      "step": 52
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.26553719135078474,
      "learning_rate": 0.00019999388172996495,
      "loss": 0.3771,
      "step": 53
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.2563892875653707,
      "learning_rate": 0.0001999891231617599,
      "loss": 0.3709,
      "step": 54
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.40493567306146466,
      "learning_rate": 0.0001999830051135521,
      "loss": 0.3659,
      "step": 55
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.282074263507646,
      "learning_rate": 0.00019997552766852432,
      "loss": 0.3579,
      "step": 56
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.24830919197340875,
      "learning_rate": 0.00019996669092834193,
      "loss": 0.3164,
      "step": 57
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.31153665113975915,
      "learning_rate": 0.0001999564950131517,
      "loss": 0.3554,
      "step": 58
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.2883397422934534,
      "learning_rate": 0.00019994494006158017,
      "loss": 0.3318,
      "step": 59
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.29607763624002476,
      "learning_rate": 0.00019993202623073172,
      "loss": 0.3515,
      "step": 60
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.26631042457457627,
      "learning_rate": 0.0001999177536961863,
      "loss": 0.3404,
      "step": 61
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.30709845993919116,
      "learning_rate": 0.00019990212265199738,
      "loss": 0.3454,
      "step": 62
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.2689959836388791,
      "learning_rate": 0.0001998851333106889,
      "loss": 0.3448,
      "step": 63
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.28079893446027976,
      "learning_rate": 0.00019986678590325273,
      "loss": 0.3537,
      "step": 64
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.2777161046281277,
      "learning_rate": 0.00019984708067914532,
      "loss": 0.3512,
      "step": 65
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.2612936496089595,
      "learning_rate": 0.0001998260179062844,
      "loss": 0.3355,
      "step": 66
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.270747618988818,
      "learning_rate": 0.0001998035978710453,
      "loss": 0.3557,
      "step": 67
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.2524425572972277,
      "learning_rate": 0.00019977982087825713,
      "loss": 0.324,
      "step": 68
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.2655824178335376,
      "learning_rate": 0.00019975468725119843,
      "loss": 0.3274,
      "step": 69
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.29931436509996834,
      "learning_rate": 0.000199728197331593,
      "loss": 0.3733,
      "step": 70
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.2945779980864737,
      "learning_rate": 0.00019970035147960524,
      "loss": 0.3161,
      "step": 71
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.42061603746317366,
      "learning_rate": 0.00019967115007383507,
      "loss": 0.3486,
      "step": 72
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.24899746628510128,
      "learning_rate": 0.000199640593511313,
      "loss": 0.3428,
      "step": 73
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.2748778960772334,
      "learning_rate": 0.00019960868220749448,
      "loss": 0.3215,
      "step": 74
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.2826057447583215,
      "learning_rate": 0.00019957541659625458,
      "loss": 0.3663,
      "step": 75
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.26758814883425874,
      "learning_rate": 0.00019954079712988183,
      "loss": 0.3473,
      "step": 76
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.26191530390935236,
      "learning_rate": 0.00019950482427907211,
      "loss": 0.3464,
      "step": 77
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.27009995213133564,
      "learning_rate": 0.00019946749853292232,
      "loss": 0.3427,
      "step": 78
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.2828252836889427,
      "learning_rate": 0.00019942882039892377,
      "loss": 0.3369,
      "step": 79
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.28359570095347486,
      "learning_rate": 0.00019938879040295508,
      "loss": 0.3474,
      "step": 80
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.23726568176198512,
      "learning_rate": 0.0001993474090892753,
      "loss": 0.3348,
      "step": 81
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.28359002617947426,
      "learning_rate": 0.00019930467702051628,
      "loss": 0.3434,
      "step": 82
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.24507300294017476,
      "learning_rate": 0.0001992605947776752,
      "loss": 0.3211,
      "step": 83
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.2459171433488338,
      "learning_rate": 0.00019921516296010644,
      "loss": 0.3539,
      "step": 84
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.23982609581354497,
      "learning_rate": 0.0001991683821855137,
      "loss": 0.3367,
      "step": 85
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.24948097532302946,
      "learning_rate": 0.00019912025308994148,
      "loss": 0.3313,
      "step": 86
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.25673241215001325,
      "learning_rate": 0.00019907077632776632,
      "loss": 0.3384,
      "step": 87
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.2248520328170477,
      "learning_rate": 0.00019901995257168807,
      "loss": 0.3075,
      "step": 88
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.2785744560779341,
      "learning_rate": 0.00019896778251272078,
      "loss": 0.3505,
      "step": 89
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.2612264615045669,
      "learning_rate": 0.00019891426686018305,
      "loss": 0.3319,
      "step": 90
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.2588107693763323,
      "learning_rate": 0.00019885940634168864,
      "loss": 0.3036,
      "step": 91
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.2539991795599821,
      "learning_rate": 0.0001988032017031364,
      "loss": 0.3275,
      "step": 92
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.2228639788098274,
      "learning_rate": 0.00019874565370870038,
      "loss": 0.3128,
      "step": 93
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.2295330254763288,
      "learning_rate": 0.00019868676314081904,
      "loss": 0.3226,
      "step": 94
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.26774082666954935,
      "learning_rate": 0.00019862653080018506,
      "loss": 0.3438,
      "step": 95
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.2096704558396889,
      "learning_rate": 0.0001985649575057341,
      "loss": 0.3158,
      "step": 96
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.222343383957648,
      "learning_rate": 0.00019850204409463385,
      "loss": 0.3127,
      "step": 97
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.24355910663526567,
      "learning_rate": 0.00019843779142227256,
      "loss": 0.3278,
      "step": 98
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.2589007730313338,
      "learning_rate": 0.00019837220036224756,
      "loss": 0.3433,
      "step": 99
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.2048208439355147,
      "learning_rate": 0.00019830527180635308,
      "loss": 0.3038,
      "step": 100
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.22100911829011585,
      "learning_rate": 0.00019823700666456853,
      "loss": 0.3295,
      "step": 101
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.2865876628348663,
      "learning_rate": 0.0001981674058650458,
      "loss": 0.3374,
      "step": 102
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.23267706317431597,
      "learning_rate": 0.00019809647035409672,
      "loss": 0.3146,
      "step": 103
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.22896912398059824,
      "learning_rate": 0.0001980242010961803,
      "loss": 0.3302,
      "step": 104
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.21199810980682918,
      "learning_rate": 0.00019795059907388952,
      "loss": 0.3089,
      "step": 105
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.2314314536279127,
      "learning_rate": 0.00019787566528793807,
      "loss": 0.3219,
      "step": 106
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.22578014749699987,
      "learning_rate": 0.00019779940075714648,
      "loss": 0.3089,
      "step": 107
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.26739038717214403,
      "learning_rate": 0.0001977218065184287,
      "loss": 0.3314,
      "step": 108
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.27640406493967007,
      "learning_rate": 0.00019764288362677753,
      "loss": 0.315,
      "step": 109
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.275170691575301,
      "learning_rate": 0.0001975626331552507,
      "loss": 0.3192,
      "step": 110
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.28590415176453904,
      "learning_rate": 0.00019748105619495594,
      "loss": 0.3235,
      "step": 111
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.26618886451702856,
      "learning_rate": 0.0001973981538550364,
      "loss": 0.3235,
      "step": 112
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.22783361042781863,
      "learning_rate": 0.00019731392726265537,
      "loss": 0.3319,
      "step": 113
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.3324408233165741,
      "eval_runtime": 173.7614,
      "eval_samples_per_second": 13.369,
      "eval_steps_per_second": 0.42,
      "step": 113
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.25003343596979083,
      "learning_rate": 0.00019722837756298113,
      "loss": 0.3269,
      "step": 114
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.2051643008869916,
      "learning_rate": 0.0001971415059191712,
      "loss": 0.3331,
      "step": 115
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.26679577582874325,
      "learning_rate": 0.00019705331351235674,
      "loss": 0.319,
      "step": 116
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.22959410656566043,
      "learning_rate": 0.0001969638015416263,
      "loss": 0.326,
      "step": 117
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.24732040292675736,
      "learning_rate": 0.0001968729712240095,
      "loss": 0.3456,
      "step": 118
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.21472772586501115,
      "learning_rate": 0.00019678082379446078,
      "loss": 0.3154,
      "step": 119
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.22004349633491344,
      "learning_rate": 0.00019668736050584224,
      "loss": 0.3296,
      "step": 120
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.20481829759367912,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.3168,
      "step": 121
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.22596082871640896,
      "learning_rate": 0.00019649649145228102,
      "loss": 0.3198,
      "step": 122
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.22416198789548378,
      "learning_rate": 0.00019639908828244718,
      "loss": 0.3122,
      "step": 123
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.25019709447245486,
      "learning_rate": 0.000196300374443726,
      "loss": 0.3256,
      "step": 124
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.23470807250735432,
      "learning_rate": 0.0001962003512782584,
      "loss": 0.3245,
      "step": 125
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.24693935678122386,
      "learning_rate": 0.00019609902014598718,
      "loss": 0.3292,
      "step": 126
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.2260534058582815,
      "learning_rate": 0.00019599638242463868,
      "loss": 0.325,
      "step": 127
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.23667285933893983,
      "learning_rate": 0.00019589243950970402,
      "loss": 0.3337,
      "step": 128
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.21298574370036155,
      "learning_rate": 0.00019578719281442003,
      "loss": 0.3092,
      "step": 129
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.23372716379048458,
      "learning_rate": 0.00019568064376975012,
      "loss": 0.317,
      "step": 130
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.22334413345013637,
      "learning_rate": 0.0001955727938243648,
      "loss": 0.2834,
      "step": 131
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.2248381817587477,
      "learning_rate": 0.00019546364444462207,
      "loss": 0.302,
      "step": 132
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.2360215129073668,
      "learning_rate": 0.00019535319711454728,
      "loss": 0.3293,
      "step": 133
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.22623309491159815,
      "learning_rate": 0.00019524145333581317,
      "loss": 0.3273,
      "step": 134
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.2070555672669519,
      "learning_rate": 0.00019512841462771924,
      "loss": 0.2972,
      "step": 135
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.22460201914808312,
      "learning_rate": 0.00019501408252717138,
      "loss": 0.3019,
      "step": 136
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.2225333175600629,
      "learning_rate": 0.00019489845858866066,
      "loss": 0.2983,
      "step": 137
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.21017634852282913,
      "learning_rate": 0.0001947815443842424,
      "loss": 0.3002,
      "step": 138
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.24382065213677345,
      "learning_rate": 0.00019466334150351476,
      "loss": 0.3061,
      "step": 139
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.22222229848717998,
      "learning_rate": 0.00019454385155359702,
      "loss": 0.3189,
      "step": 140
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.21144991906498956,
      "learning_rate": 0.00019442307615910793,
      "loss": 0.3093,
      "step": 141
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.20966684015092005,
      "learning_rate": 0.00019430101696214336,
      "loss": 0.2975,
      "step": 142
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.2285163015371888,
      "learning_rate": 0.0001941776756222542,
      "loss": 0.3291,
      "step": 143
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.22173438888731478,
      "learning_rate": 0.00019405305381642375,
      "loss": 0.3052,
      "step": 144
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.23472615797287633,
      "learning_rate": 0.00019392715323904481,
      "loss": 0.3158,
      "step": 145
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.19206597044565454,
      "learning_rate": 0.00019379997560189675,
      "loss": 0.3047,
      "step": 146
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.21928888599234125,
      "learning_rate": 0.00019367152263412217,
      "loss": 0.3196,
      "step": 147
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.21469742386937682,
      "learning_rate": 0.00019354179608220348,
      "loss": 0.2981,
      "step": 148
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.39037984784670976,
      "learning_rate": 0.000193410797709939,
      "loss": 0.2962,
      "step": 149
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.3224683875107671,
      "learning_rate": 0.00019327852929841916,
      "loss": 0.3268,
      "step": 150
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.22377973835731155,
      "learning_rate": 0.0001931449926460022,
      "loss": 0.3093,
      "step": 151
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.21525051451055552,
      "learning_rate": 0.00019301018956828964,
      "loss": 0.3173,
      "step": 152
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.19693490433987484,
      "learning_rate": 0.00019287412189810172,
      "loss": 0.3069,
      "step": 153
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.1985719221741534,
      "learning_rate": 0.00019273679148545245,
      "loss": 0.3239,
      "step": 154
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.19043619193681682,
      "learning_rate": 0.00019259820019752443,
      "loss": 0.3041,
      "step": 155
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.2029259146228578,
      "learning_rate": 0.0001924583499186434,
      "loss": 0.3049,
      "step": 156
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.1913024173068621,
      "learning_rate": 0.00019231724255025284,
      "loss": 0.3263,
      "step": 157
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.20418535912509125,
      "learning_rate": 0.00019217488001088784,
      "loss": 0.3093,
      "step": 158
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.21506493193668452,
      "learning_rate": 0.00019203126423614916,
      "loss": 0.3386,
      "step": 159
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.2078781708947467,
      "learning_rate": 0.00019188639717867696,
      "loss": 0.3098,
      "step": 160
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.21203565844547,
      "learning_rate": 0.00019174028080812415,
      "loss": 0.3245,
      "step": 161
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.22944231505967116,
      "learning_rate": 0.0001915929171111296,
      "loss": 0.3174,
      "step": 162
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.19389795184150505,
      "learning_rate": 0.00019144430809129128,
      "loss": 0.2985,
      "step": 163
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.2294568217196969,
      "learning_rate": 0.00019129445576913888,
      "loss": 0.2916,
      "step": 164
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.21471312626755512,
      "learning_rate": 0.00019114336218210634,
      "loss": 0.3203,
      "step": 165
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.200256096520887,
      "learning_rate": 0.00019099102938450416,
      "loss": 0.314,
      "step": 166
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.20286230376549838,
      "learning_rate": 0.00019083745944749162,
      "loss": 0.2953,
      "step": 167
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.22752630009694177,
      "learning_rate": 0.00019068265445904836,
      "loss": 0.3098,
      "step": 168
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.1969764402722988,
      "learning_rate": 0.00019052661652394618,
      "loss": 0.2798,
      "step": 169
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.21419927863312113,
      "learning_rate": 0.0001903693477637204,
      "loss": 0.315,
      "step": 170
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.1978129640154948,
      "learning_rate": 0.00019021085031664087,
      "loss": 0.2769,
      "step": 171
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.1832605646042805,
      "learning_rate": 0.00019005112633768313,
      "loss": 0.2787,
      "step": 172
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.25130865190581947,
      "learning_rate": 0.00018989017799849896,
      "loss": 0.3042,
      "step": 173
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.22333188194958617,
      "learning_rate": 0.0001897280074873868,
      "loss": 0.3366,
      "step": 174
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.23303955610127655,
      "learning_rate": 0.00018956461700926215,
      "loss": 0.3069,
      "step": 175
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.21946538873928723,
      "learning_rate": 0.00018940000878562758,
      "loss": 0.3026,
      "step": 176
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.22034016868322132,
      "learning_rate": 0.00018923418505454237,
      "loss": 0.3031,
      "step": 177
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.1918273691770089,
      "learning_rate": 0.00018906714807059218,
      "loss": 0.287,
      "step": 178
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.1984010069624954,
      "learning_rate": 0.00018889890010485847,
      "loss": 0.3039,
      "step": 179
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.19139523377149348,
      "learning_rate": 0.00018872944344488747,
      "loss": 0.3152,
      "step": 180
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.18841860181390324,
      "learning_rate": 0.0001885587803946592,
      "loss": 0.3171,
      "step": 181
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.19736334769102976,
      "learning_rate": 0.0001883869132745561,
      "loss": 0.2851,
      "step": 182
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.19610383893082234,
      "learning_rate": 0.00018821384442133145,
      "loss": 0.307,
      "step": 183
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.19693236953217128,
      "learning_rate": 0.00018803957618807764,
      "loss": 0.3219,
      "step": 184
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.1978461815572098,
      "learning_rate": 0.0001878641109441942,
      "loss": 0.2936,
      "step": 185
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.22453262012783057,
      "learning_rate": 0.00018768745107535542,
      "loss": 0.3225,
      "step": 186
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.1951859636493649,
      "learning_rate": 0.00018750959898347825,
      "loss": 0.2892,
      "step": 187
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.19051492201816908,
      "learning_rate": 0.00018733055708668926,
      "loss": 0.2922,
      "step": 188
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.19631810708829814,
      "learning_rate": 0.00018715032781929208,
      "loss": 0.2928,
      "step": 189
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.20533375929006709,
      "learning_rate": 0.00018696891363173405,
      "loss": 0.3212,
      "step": 190
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.21698315667726276,
      "learning_rate": 0.00018678631699057302,
      "loss": 0.3419,
      "step": 191
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.23742145444149265,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.3081,
      "step": 192
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.22429285552735956,
      "learning_rate": 0.00018641758629402467,
      "loss": 0.3132,
      "step": 193
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.20957107721564286,
      "learning_rate": 0.00018623145725200278,
      "loss": 0.3176,
      "step": 194
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.23119517784848204,
      "learning_rate": 0.0001860441557830405,
      "loss": 0.3174,
      "step": 195
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.22081382473360098,
      "learning_rate": 0.00018585568443374087,
      "loss": 0.3029,
      "step": 196
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.20857278454177905,
      "learning_rate": 0.00018566604576661288,
      "loss": 0.2803,
      "step": 197
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.20277792365487685,
      "learning_rate": 0.00018547524236003674,
      "loss": 0.3032,
      "step": 198
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.22068595819466755,
      "learning_rate": 0.0001852832768082288,
      "loss": 0.3196,
      "step": 199
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.22826508701764245,
      "learning_rate": 0.00018509015172120621,
      "loss": 0.307,
      "step": 200
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.23318100222090005,
      "learning_rate": 0.00018489586972475155,
      "loss": 0.3243,
      "step": 201
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.20790305208366794,
      "learning_rate": 0.00018470043346037698,
      "loss": 0.3026,
      "step": 202
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.23045901908374763,
      "learning_rate": 0.00018450384558528845,
      "loss": 0.3215,
      "step": 203
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.1895969081217627,
      "learning_rate": 0.0001843061087723496,
      "loss": 0.2827,
      "step": 204
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.21471234551245583,
      "learning_rate": 0.00018410722571004522,
      "loss": 0.2758,
      "step": 205
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.19174460263968052,
      "learning_rate": 0.00018390719910244487,
      "loss": 0.2935,
      "step": 206
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.2042082548764658,
      "learning_rate": 0.00018370603166916616,
      "loss": 0.3219,
      "step": 207
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.20862412820843024,
      "learning_rate": 0.00018350372614533753,
      "loss": 0.3079,
      "step": 208
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.19365588486473745,
      "learning_rate": 0.00018330028528156138,
      "loss": 0.2878,
      "step": 209
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.20923759592087007,
      "learning_rate": 0.0001830957118438764,
      "loss": 0.3052,
      "step": 210
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.19346679246935292,
      "learning_rate": 0.00018289000861372007,
      "loss": 0.2873,
      "step": 211
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.20707125547144337,
      "learning_rate": 0.00018268317838789088,
      "loss": 0.2888,
      "step": 212
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.210272509030541,
      "learning_rate": 0.00018247522397851028,
      "loss": 0.3063,
      "step": 213
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.22635533463893145,
      "learning_rate": 0.0001822661482129844,
      "loss": 0.2844,
      "step": 214
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.20691107915045812,
      "learning_rate": 0.00018205595393396568,
      "loss": 0.2986,
      "step": 215
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.21549907787627992,
      "learning_rate": 0.00018184464399931412,
      "loss": 0.3098,
      "step": 216
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.20061134281496176,
      "learning_rate": 0.00018163222128205853,
      "loss": 0.2871,
      "step": 217
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.20502352214692726,
      "learning_rate": 0.00018141868867035745,
      "loss": 0.294,
      "step": 218
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.2291358128642933,
      "learning_rate": 0.00018120404906745973,
      "loss": 0.2757,
      "step": 219
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.1972835362678214,
      "learning_rate": 0.00018098830539166536,
      "loss": 0.3084,
      "step": 220
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.21611715417590088,
      "learning_rate": 0.00018077146057628545,
      "loss": 0.2816,
      "step": 221
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.21599858891116713,
      "learning_rate": 0.00018055351756960262,
      "loss": 0.3085,
      "step": 222
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.19318954639097616,
      "learning_rate": 0.00018033447933483076,
      "loss": 0.2557,
      "step": 223
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.18823294633329682,
      "learning_rate": 0.00018011434885007482,
      "loss": 0.2902,
      "step": 224
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.21452443929587184,
      "learning_rate": 0.00017989312910829023,
      "loss": 0.311,
      "step": 225
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.20666447125090429,
      "learning_rate": 0.00017967082311724227,
      "loss": 0.2883,
      "step": 226
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.297645628452301,
      "eval_runtime": 173.6984,
      "eval_samples_per_second": 13.374,
      "eval_steps_per_second": 0.42,
      "step": 226
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.21336924271339083,
      "learning_rate": 0.00017944743389946524,
      "loss": 0.3026,
      "step": 227
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.20792583408257218,
      "learning_rate": 0.0001792229644922212,
      "loss": 0.2843,
      "step": 228
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.2129371399765845,
      "learning_rate": 0.0001789974179474588,
      "loss": 0.3091,
      "step": 229
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.19527091537284477,
      "learning_rate": 0.00017877079733177184,
      "loss": 0.297,
      "step": 230
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.20516345655708346,
      "learning_rate": 0.00017854310572635733,
      "loss": 0.2935,
      "step": 231
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.1969309791573733,
      "learning_rate": 0.00017831434622697385,
      "loss": 0.2898,
      "step": 232
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.2696175229862278,
      "learning_rate": 0.0001780845219438994,
      "loss": 0.2924,
      "step": 233
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.234973041162424,
      "learning_rate": 0.00017785363600188894,
      "loss": 0.3179,
      "step": 234
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.23939104068785497,
      "learning_rate": 0.00017762169154013216,
      "loss": 0.2796,
      "step": 235
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.20378572036784126,
      "learning_rate": 0.00017738869171221068,
      "loss": 0.2784,
      "step": 236
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.19159802735904477,
      "learning_rate": 0.0001771546396860551,
      "loss": 0.2834,
      "step": 237
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.23302725481391803,
      "learning_rate": 0.00017691953864390207,
      "loss": 0.2997,
      "step": 238
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.23471887316578038,
      "learning_rate": 0.0001766833917822509,
      "loss": 0.3,
      "step": 239
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.1796225243725005,
      "learning_rate": 0.00017644620231182015,
      "loss": 0.2901,
      "step": 240
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.20037902218428075,
      "learning_rate": 0.00017620797345750403,
      "loss": 0.294,
      "step": 241
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.20415485179217374,
      "learning_rate": 0.0001759687084583285,
      "loss": 0.3162,
      "step": 242
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.18182779738483645,
      "learning_rate": 0.00017572841056740722,
      "loss": 0.275,
      "step": 243
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.17275776985467062,
      "learning_rate": 0.00017548708305189722,
      "loss": 0.2592,
      "step": 244
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.18388792575433974,
      "learning_rate": 0.00017524472919295487,
      "loss": 0.2998,
      "step": 245
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.1821375376929017,
      "learning_rate": 0.00017500135228569068,
      "loss": 0.2586,
      "step": 246
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.18937126829543396,
      "learning_rate": 0.00017475695563912505,
      "loss": 0.2858,
      "step": 247
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.1833938565560613,
      "learning_rate": 0.00017451154257614287,
      "loss": 0.271,
      "step": 248
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.20382927797400074,
      "learning_rate": 0.0001742651164334486,
      "loss": 0.2931,
      "step": 249
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.23510651870506527,
      "learning_rate": 0.00017401768056152085,
      "loss": 0.3078,
      "step": 250
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.2191619740250893,
      "learning_rate": 0.00017376923832456665,
      "loss": 0.3111,
      "step": 251
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.20648235757385622,
      "learning_rate": 0.00017351979310047602,
      "loss": 0.2816,
      "step": 252
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.19445561313531604,
      "learning_rate": 0.00017326934828077573,
      "loss": 0.2894,
      "step": 253
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.19169798824869538,
      "learning_rate": 0.00017301790727058345,
      "loss": 0.2802,
      "step": 254
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.2006703950203184,
      "learning_rate": 0.0001727654734885612,
      "loss": 0.2749,
      "step": 255
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.21061482297381626,
      "learning_rate": 0.0001725120503668691,
      "loss": 0.3042,
      "step": 256
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.20740853426573325,
      "learning_rate": 0.00017225764135111868,
      "loss": 0.3025,
      "step": 257
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.1945016623980029,
      "learning_rate": 0.00017200224990032576,
      "loss": 0.2964,
      "step": 258
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.21095668740779128,
      "learning_rate": 0.00017174587948686374,
      "loss": 0.3047,
      "step": 259
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.18724414137242903,
      "learning_rate": 0.00017148853359641626,
      "loss": 0.2678,
      "step": 260
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.18247589724576602,
      "learning_rate": 0.00017123021572792982,
      "loss": 0.2796,
      "step": 261
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.20187877784359254,
      "learning_rate": 0.00017097092939356623,
      "loss": 0.2819,
      "step": 262
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.21960455156021205,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.2849,
      "step": 263
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.21920804195394356,
      "learning_rate": 0.00017044946544164433,
      "loss": 0.286,
      "step": 264
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.2153094965416609,
      "learning_rate": 0.00017018729491405536,
      "loss": 0.2728,
      "step": 265
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.18899974451413623,
      "learning_rate": 0.00016992417010043142,
      "loss": 0.2643,
      "step": 266
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.20452371771386804,
      "learning_rate": 0.00016966009457829086,
      "loss": 0.2805,
      "step": 267
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.19546419928152936,
      "learning_rate": 0.0001693950719380782,
      "loss": 0.2749,
      "step": 268
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.19627215184487343,
      "learning_rate": 0.00016912910578311503,
      "loss": 0.273,
      "step": 269
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.18828419766156645,
      "learning_rate": 0.00016886219972955146,
      "loss": 0.273,
      "step": 270
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.19027059707604657,
      "learning_rate": 0.00016859435740631658,
      "loss": 0.3046,
      "step": 271
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.18426233664144975,
      "learning_rate": 0.00016832558245506935,
      "loss": 0.2643,
      "step": 272
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.18658729778193736,
      "learning_rate": 0.00016805587853014895,
      "loss": 0.285,
      "step": 273
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.1796032355554721,
      "learning_rate": 0.00016778524929852512,
      "loss": 0.261,
      "step": 274
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.19790847765561645,
      "learning_rate": 0.0001675136984397484,
      "loss": 0.3036,
      "step": 275
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.2013507251688789,
      "learning_rate": 0.0001672412296459,
      "loss": 0.2929,
      "step": 276
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.20727255991158675,
      "learning_rate": 0.00016696784662154163,
      "loss": 0.28,
      "step": 277
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.22175173491924988,
      "learning_rate": 0.0001666935530836651,
      "loss": 0.2953,
      "step": 278
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.2110368794764076,
      "learning_rate": 0.00016641835276164183,
      "loss": 0.3012,
      "step": 279
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.1839097327175649,
      "learning_rate": 0.00016614224939717217,
      "loss": 0.2985,
      "step": 280
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.18075701410157072,
      "learning_rate": 0.00016586524674423446,
      "loss": 0.2614,
      "step": 281
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.19006328055997038,
      "learning_rate": 0.00016558734856903404,
      "loss": 0.2741,
      "step": 282
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.1936501426398552,
      "learning_rate": 0.00016530855864995195,
      "loss": 0.2486,
      "step": 283
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.2146360520459362,
      "learning_rate": 0.0001650288807774937,
      "loss": 0.2949,
      "step": 284
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.1934454081094374,
      "learning_rate": 0.00016474831875423767,
      "loss": 0.25,
      "step": 285
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.20138529225313043,
      "learning_rate": 0.0001644668763947833,
      "loss": 0.2826,
      "step": 286
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.20336180418412392,
      "learning_rate": 0.00016418455752569943,
      "loss": 0.281,
      "step": 287
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.2366660122305481,
      "learning_rate": 0.00016390136598547217,
      "loss": 0.2665,
      "step": 288
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.18478597928089585,
      "learning_rate": 0.00016361730562445263,
      "loss": 0.3022,
      "step": 289
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.18679948920602824,
      "learning_rate": 0.0001633323803048047,
      "loss": 0.2844,
      "step": 290
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.19949957744833288,
      "learning_rate": 0.00016304659390045252,
      "loss": 0.2912,
      "step": 291
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.20044341182168152,
      "learning_rate": 0.0001627599502970277,
      "loss": 0.2729,
      "step": 292
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.18558206726419454,
      "learning_rate": 0.00016247245339181662,
      "loss": 0.2693,
      "step": 293
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.2083655759577377,
      "learning_rate": 0.00016218410709370736,
      "loss": 0.3022,
      "step": 294
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.21456219690969847,
      "learning_rate": 0.00016189491532313664,
      "loss": 0.2933,
      "step": 295
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.2316084982608295,
      "learning_rate": 0.00016160488201203644,
      "loss": 0.2631,
      "step": 296
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.20943766303868608,
      "learning_rate": 0.00016131401110378043,
      "loss": 0.2847,
      "step": 297
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.2346281512353159,
      "learning_rate": 0.00016102230655313076,
      "loss": 0.2898,
      "step": 298
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.18690479698056445,
      "learning_rate": 0.0001607297723261837,
      "loss": 0.2761,
      "step": 299
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.22244239877246086,
      "learning_rate": 0.00016043641240031623,
      "loss": 0.2794,
      "step": 300
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.19513520777123738,
      "learning_rate": 0.00016014223076413173,
      "loss": 0.2757,
      "step": 301
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.1954004471181246,
      "learning_rate": 0.00015984723141740576,
      "loss": 0.2713,
      "step": 302
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.21399036326669596,
      "learning_rate": 0.00015955141837103168,
      "loss": 0.2767,
      "step": 303
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.2045546981741005,
      "learning_rate": 0.0001592547956469662,
      "loss": 0.2807,
      "step": 304
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.21321779886240727,
      "learning_rate": 0.00015895736727817455,
      "loss": 0.2899,
      "step": 305
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.20121770170139855,
      "learning_rate": 0.00015865913730857582,
      "loss": 0.2706,
      "step": 306
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.21901656836549904,
      "learning_rate": 0.00015836010979298782,
      "loss": 0.3043,
      "step": 307
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.19476889300368513,
      "learning_rate": 0.0001580602887970721,
      "loss": 0.294,
      "step": 308
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.1864916489760236,
      "learning_rate": 0.00015775967839727842,
      "loss": 0.2789,
      "step": 309
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.2005263777787887,
      "learning_rate": 0.0001574582826807897,
      "loss": 0.2786,
      "step": 310
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.20330910409013883,
      "learning_rate": 0.0001571561057454661,
      "loss": 0.2856,
      "step": 311
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.2075041911121307,
      "learning_rate": 0.00015685315169978954,
      "loss": 0.301,
      "step": 312
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.198545224318664,
      "learning_rate": 0.0001565494246628077,
      "loss": 0.2667,
      "step": 313
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.18262873322406858,
      "learning_rate": 0.0001562449287640781,
      "loss": 0.2761,
      "step": 314
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.20682904427400386,
      "learning_rate": 0.0001559396681436118,
      "loss": 0.2798,
      "step": 315
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.17100330949740156,
      "learning_rate": 0.00015563364695181741,
      "loss": 0.2638,
      "step": 316
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.19147233406100644,
      "learning_rate": 0.00015532686934944438,
      "loss": 0.2772,
      "step": 317
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.20859821686266017,
      "learning_rate": 0.00015501933950752656,
      "loss": 0.2899,
      "step": 318
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.22660943071408993,
      "learning_rate": 0.00015471106160732542,
      "loss": 0.2809,
      "step": 319
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.1970595992988207,
      "learning_rate": 0.00015440203984027324,
      "loss": 0.2664,
      "step": 320
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.21441465355834557,
      "learning_rate": 0.00015409227840791617,
      "loss": 0.2872,
      "step": 321
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.1928160770028818,
      "learning_rate": 0.000153781781521857,
      "loss": 0.2932,
      "step": 322
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.18232874606722474,
      "learning_rate": 0.00015347055340369804,
      "loss": 0.2865,
      "step": 323
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.18944518082470313,
      "learning_rate": 0.00015315859828498354,
      "loss": 0.2895,
      "step": 324
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.18688411692002266,
      "learning_rate": 0.00015284592040714227,
      "loss": 0.3068,
      "step": 325
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.15360887670295487,
      "learning_rate": 0.00015253252402142988,
      "loss": 0.2541,
      "step": 326
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.17886321037354558,
      "learning_rate": 0.00015221841338887104,
      "loss": 0.2735,
      "step": 327
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.18210509607368616,
      "learning_rate": 0.0001519035927802015,
      "loss": 0.2674,
      "step": 328
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.2113800439853146,
      "learning_rate": 0.00015158806647581002,
      "loss": 0.2611,
      "step": 329
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.21664373470568593,
      "learning_rate": 0.00015127183876568022,
      "loss": 0.2734,
      "step": 330
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.21152226314764647,
      "learning_rate": 0.0001509549139493323,
      "loss": 0.2605,
      "step": 331
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.20787608314066813,
      "learning_rate": 0.0001506372963357644,
      "loss": 0.2829,
      "step": 332
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.20890612340451087,
      "learning_rate": 0.00015031899024339415,
      "loss": 0.2761,
      "step": 333
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.18123961862890825,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.2625,
      "step": 334
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.20005061805451332,
      "learning_rate": 0.00014968032994266224,
      "loss": 0.2739,
      "step": 335
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.22011995491515385,
      "learning_rate": 0.00014935998441770407,
      "loss": 0.2769,
      "step": 336
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.1759458248293069,
      "learning_rate": 0.00014903896778063267,
      "loss": 0.2751,
      "step": 337
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.17963701036394614,
      "learning_rate": 0.00014871728439607966,
      "loss": 0.2861,
      "step": 338
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.22395035633400334,
      "learning_rate": 0.00014839493863774212,
      "loss": 0.2748,
      "step": 339
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.27847620844841003,
      "eval_runtime": 174.097,
      "eval_samples_per_second": 13.343,
      "eval_steps_per_second": 0.419,
      "step": 339
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.19931473943900235,
      "learning_rate": 0.00014807193488832282,
      "loss": 0.261,
      "step": 340
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.1895068181039295,
      "learning_rate": 0.00014774827753947088,
      "loss": 0.2666,
      "step": 341
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.19682173311096884,
      "learning_rate": 0.00014742397099172183,
      "loss": 0.2564,
      "step": 342
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.2183356533233642,
      "learning_rate": 0.00014709901965443794,
      "loss": 0.2904,
      "step": 343
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.2113562507034691,
      "learning_rate": 0.00014677342794574817,
      "loss": 0.2915,
      "step": 344
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.2034784414842117,
      "learning_rate": 0.00014644720029248829,
      "loss": 0.2717,
      "step": 345
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.1967572374697097,
      "learning_rate": 0.00014612034113014035,
      "loss": 0.2887,
      "step": 346
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.1899953535101574,
      "learning_rate": 0.00014579285490277274,
      "loss": 0.2922,
      "step": 347
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.19441384522232566,
      "learning_rate": 0.0001454647460629795,
      "loss": 0.2785,
      "step": 348
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.20710674744690838,
      "learning_rate": 0.00014513601907181992,
      "loss": 0.2929,
      "step": 349
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.18640646337351455,
      "learning_rate": 0.00014480667839875786,
      "loss": 0.261,
      "step": 350
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.1754057901024035,
      "learning_rate": 0.00014447672852160095,
      "loss": 0.267,
      "step": 351
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.1845116395890587,
      "learning_rate": 0.0001441461739264397,
      "loss": 0.2608,
      "step": 352
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.1832842348380918,
      "learning_rate": 0.00014381501910758662,
      "loss": 0.264,
      "step": 353
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.21078762275275081,
      "learning_rate": 0.00014348326856751496,
      "loss": 0.2903,
      "step": 354
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.2040423439668467,
      "learning_rate": 0.00014315092681679755,
      "loss": 0.2866,
      "step": 355
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.20916646529152538,
      "learning_rate": 0.00014281799837404552,
      "loss": 0.2669,
      "step": 356
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.20829199241699958,
      "learning_rate": 0.00014248448776584688,
      "loss": 0.2773,
      "step": 357
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.22863270132432637,
      "learning_rate": 0.0001421503995267048,
      "loss": 0.2691,
      "step": 358
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.19107899619014693,
      "learning_rate": 0.00014181573819897617,
      "loss": 0.2854,
      "step": 359
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.18310920202899897,
      "learning_rate": 0.00014148050833280977,
      "loss": 0.2523,
      "step": 360
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.19142180009852441,
      "learning_rate": 0.00014114471448608426,
      "loss": 0.2668,
      "step": 361
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.17916118207750328,
      "learning_rate": 0.0001408083612243465,
      "loss": 0.2826,
      "step": 362
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.1795532305403206,
      "learning_rate": 0.0001404714531207492,
      "loss": 0.2876,
      "step": 363
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.19812580507096825,
      "learning_rate": 0.0001401339947559889,
      "loss": 0.2813,
      "step": 364
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.16985158453017796,
      "learning_rate": 0.00013979599071824362,
      "loss": 0.2824,
      "step": 365
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.20447909651191687,
      "learning_rate": 0.00013945744560311057,
      "loss": 0.2567,
      "step": 366
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.20178806044954373,
      "learning_rate": 0.0001391183640135435,
      "loss": 0.2755,
      "step": 367
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.2265042443851448,
      "learning_rate": 0.00013877875055979023,
      "loss": 0.2905,
      "step": 368
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.22127748544952333,
      "learning_rate": 0.00013843860985933003,
      "loss": 0.2624,
      "step": 369
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.20805077265871227,
      "learning_rate": 0.00013809794653681074,
      "loss": 0.2396,
      "step": 370
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.21236429860308073,
      "learning_rate": 0.00013775676522398588,
      "loss": 0.2916,
      "step": 371
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.19893678645018886,
      "learning_rate": 0.00013741507055965168,
      "loss": 0.2551,
      "step": 372
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.18256634499151977,
      "learning_rate": 0.00013707286718958413,
      "loss": 0.2633,
      "step": 373
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.18221655160895703,
      "learning_rate": 0.00013673015976647568,
      "loss": 0.2672,
      "step": 374
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.19429764298431815,
      "learning_rate": 0.00013638695294987204,
      "loss": 0.2417,
      "step": 375
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.18793583918739298,
      "learning_rate": 0.0001360432514061087,
      "loss": 0.2613,
      "step": 376
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.2011435035031983,
      "learning_rate": 0.00013569905980824788,
      "loss": 0.2685,
      "step": 377
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.2052637622415086,
      "learning_rate": 0.00013535438283601435,
      "loss": 0.2959,
      "step": 378
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.1945089020971851,
      "learning_rate": 0.00013500922517573245,
      "loss": 0.2482,
      "step": 379
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.20812822716018067,
      "learning_rate": 0.00013466359152026195,
      "loss": 0.2741,
      "step": 380
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.22384533508071883,
      "learning_rate": 0.0001343174865689344,
      "loss": 0.2914,
      "step": 381
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.19177959970339475,
      "learning_rate": 0.0001339709150274893,
      "loss": 0.2694,
      "step": 382
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.18196106404878304,
      "learning_rate": 0.0001336238816080099,
      "loss": 0.2649,
      "step": 383
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.2526481416447456,
      "learning_rate": 0.00013327639102885937,
      "loss": 0.2813,
      "step": 384
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.26250954621985834,
      "learning_rate": 0.0001329284480146166,
      "loss": 0.2793,
      "step": 385
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.19318862080071506,
      "learning_rate": 0.00013258005729601177,
      "loss": 0.2441,
      "step": 386
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.21447364833995924,
      "learning_rate": 0.00013223122360986225,
      "loss": 0.2887,
      "step": 387
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.18021814111984105,
      "learning_rate": 0.00013188195169900813,
      "loss": 0.2722,
      "step": 388
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.1986609859985159,
      "learning_rate": 0.0001315322463122477,
      "loss": 0.2638,
      "step": 389
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.24674716367898283,
      "learning_rate": 0.00013118211220427298,
      "loss": 0.2753,
      "step": 390
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.22439353357611744,
      "learning_rate": 0.0001308315541356049,
      "loss": 0.2853,
      "step": 391
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.17776179888083857,
      "learning_rate": 0.00013048057687252865,
      "loss": 0.2441,
      "step": 392
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.21002490821212472,
      "learning_rate": 0.00013012918518702914,
      "loss": 0.2882,
      "step": 393
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.18514107951857695,
      "learning_rate": 0.00012977738385672557,
      "loss": 0.2643,
      "step": 394
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.18577497415553973,
      "learning_rate": 0.000129425177664807,
      "loss": 0.2588,
      "step": 395
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.21465706083350347,
      "learning_rate": 0.00012907257139996704,
      "loss": 0.287,
      "step": 396
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.1742663966229961,
      "learning_rate": 0.0001287195698563388,
      "loss": 0.2668,
      "step": 397
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.20553702826350395,
      "learning_rate": 0.0001283661778334297,
      "loss": 0.2739,
      "step": 398
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.16765771945192084,
      "learning_rate": 0.0001280124001360562,
      "loss": 0.2594,
      "step": 399
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.1943563901020515,
      "learning_rate": 0.0001276582415742786,
      "loss": 0.2708,
      "step": 400
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.1896178424172107,
      "learning_rate": 0.0001273037069633354,
      "loss": 0.2639,
      "step": 401
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.0712870595212587,
      "learning_rate": 0.00012694880112357808,
      "loss": 0.2765,
      "step": 402
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.2092081458414992,
      "learning_rate": 0.00012659352888040547,
      "loss": 0.2589,
      "step": 403
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.21211010351459872,
      "learning_rate": 0.0001262378950641979,
      "loss": 0.285,
      "step": 404
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.23377789093835202,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.3038,
      "step": 405
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.24727367430206143,
      "learning_rate": 0.00012552556205871478,
      "loss": 0.2577,
      "step": 406
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.1800512798597796,
      "learning_rate": 0.00012516887255451735,
      "loss": 0.2392,
      "step": 407
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.2114523591213948,
      "learning_rate": 0.00012481184084730976,
      "loss": 0.27,
      "step": 408
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.22674225384993477,
      "learning_rate": 0.0001244544717913947,
      "loss": 0.2372,
      "step": 409
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.17864125878915538,
      "learning_rate": 0.00012409677024566144,
      "loss": 0.2601,
      "step": 410
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.1904684467485375,
      "learning_rate": 0.00012373874107352004,
      "loss": 0.2647,
      "step": 411
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.17298512767214175,
      "learning_rate": 0.0001233803891428349,
      "loss": 0.2438,
      "step": 412
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.17544690229663243,
      "learning_rate": 0.00012302171932585885,
      "loss": 0.2585,
      "step": 413
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.20074139062085292,
      "learning_rate": 0.0001226627364991667,
      "loss": 0.2575,
      "step": 414
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.18591883669880138,
      "learning_rate": 0.0001223034455435891,
      "loss": 0.2593,
      "step": 415
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.20298533039339473,
      "learning_rate": 0.00012194385134414608,
      "loss": 0.2779,
      "step": 416
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.19947012767946487,
      "learning_rate": 0.00012158395878998063,
      "loss": 0.2776,
      "step": 417
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.18367461189103365,
      "learning_rate": 0.00012122377277429231,
      "loss": 0.2934,
      "step": 418
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.18639410238342366,
      "learning_rate": 0.00012086329819427065,
      "loss": 0.2848,
      "step": 419
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.18355116451736245,
      "learning_rate": 0.00012050253995102854,
      "loss": 0.2864,
      "step": 420
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.16618761241876043,
      "learning_rate": 0.00012014150294953563,
      "loss": 0.2722,
      "step": 421
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.1679981782550472,
      "learning_rate": 0.00011978019209855174,
      "loss": 0.2417,
      "step": 422
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.17373986628880816,
      "learning_rate": 0.00011941861231055994,
      "loss": 0.2464,
      "step": 423
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.16872090115264807,
      "learning_rate": 0.0001190567685016998,
      "loss": 0.2541,
      "step": 424
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.17551340253440462,
      "learning_rate": 0.00011869466559170073,
      "loss": 0.2521,
      "step": 425
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.18233468138593362,
      "learning_rate": 0.00011833230850381487,
      "loss": 0.2712,
      "step": 426
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.18504780357931186,
      "learning_rate": 0.00011796970216475018,
      "loss": 0.2754,
      "step": 427
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.18478336853897961,
      "learning_rate": 0.00011760685150460362,
      "loss": 0.2592,
      "step": 428
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.19917097640828008,
      "learning_rate": 0.00011724376145679394,
      "loss": 0.2855,
      "step": 429
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.19144241808727208,
      "learning_rate": 0.00011688043695799468,
      "loss": 0.2502,
      "step": 430
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.18405239160044018,
      "learning_rate": 0.00011651688294806706,
      "loss": 0.2477,
      "step": 431
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.1796721265270086,
      "learning_rate": 0.00011615310436999279,
      "loss": 0.249,
      "step": 432
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.198923200273133,
      "learning_rate": 0.00011578910616980683,
      "loss": 0.2559,
      "step": 433
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.2056661440897021,
      "learning_rate": 0.00011542489329653024,
      "loss": 0.2645,
      "step": 434
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.21059350822537876,
      "learning_rate": 0.00011506047070210282,
      "loss": 0.2747,
      "step": 435
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.19445339084850757,
      "learning_rate": 0.00011469584334131578,
      "loss": 0.2732,
      "step": 436
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.1978300160069901,
      "learning_rate": 0.0001143310161717444,
      "loss": 0.2653,
      "step": 437
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.1992099703929807,
      "learning_rate": 0.00011396599415368061,
      "loss": 0.2775,
      "step": 438
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.20064532246856512,
      "learning_rate": 0.00011360078225006562,
      "loss": 0.2642,
      "step": 439
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.19513907362313387,
      "learning_rate": 0.00011323538542642227,
      "loss": 0.2554,
      "step": 440
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.191943659814926,
      "learning_rate": 0.00011286980865078763,
      "loss": 0.2778,
      "step": 441
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.1921885618320068,
      "learning_rate": 0.0001125040568936456,
      "loss": 0.2734,
      "step": 442
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.19140570504247198,
      "learning_rate": 0.00011213813512785898,
      "loss": 0.2809,
      "step": 443
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.1772706721475436,
      "learning_rate": 0.00011177204832860213,
      "loss": 0.2558,
      "step": 444
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.17875694766580855,
      "learning_rate": 0.00011140580147329338,
      "loss": 0.2569,
      "step": 445
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.1891065652583873,
      "learning_rate": 0.000111039399541527,
      "loss": 0.271,
      "step": 446
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.17377167224369017,
      "learning_rate": 0.00011067284751500583,
      "loss": 0.2711,
      "step": 447
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.16281001225472738,
      "learning_rate": 0.00011030615037747353,
      "loss": 0.2464,
      "step": 448
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.17949964198592142,
      "learning_rate": 0.0001099393131146466,
      "loss": 0.2514,
      "step": 449
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.18463419257880492,
      "learning_rate": 0.00010957234071414674,
      "loss": 0.2799,
      "step": 450
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.18137088353673406,
      "learning_rate": 0.00010920523816543309,
      "loss": 0.2615,
      "step": 451
    }
  ],
  "logging_steps": 1,
  "max_steps": 902,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 451,
  "total_flos": 1.317682551726696e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}