{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2503209242618742,
  "eval_steps": 500,
  "global_step": 195,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012836970474967907,
      "grad_norm": 0.9255548715591431,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.8985,
      "step": 1
    },
    {
      "epoch": 0.0025673940949935813,
      "grad_norm": 0.7692601680755615,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 2.9774,
      "step": 2
    },
    {
      "epoch": 0.0038510911424903724,
      "grad_norm": 0.7884671092033386,
      "learning_rate": 1.5e-06,
      "loss": 2.9898,
      "step": 3
    },
    {
      "epoch": 0.005134788189987163,
      "grad_norm": 0.8319393396377563,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.9573,
      "step": 4
    },
    {
      "epoch": 0.006418485237483954,
      "grad_norm": 0.822285532951355,
      "learning_rate": 2.5e-06,
      "loss": 2.9316,
      "step": 5
    },
    {
      "epoch": 0.007702182284980745,
      "grad_norm": 0.7564650774002075,
      "learning_rate": 3e-06,
      "loss": 2.9537,
      "step": 6
    },
    {
      "epoch": 0.008985879332477536,
      "grad_norm": 0.9220781922340393,
      "learning_rate": 3.5000000000000004e-06,
      "loss": 2.9826,
      "step": 7
    },
    {
      "epoch": 0.010269576379974325,
      "grad_norm": 0.7977064847946167,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.8548,
      "step": 8
    },
    {
      "epoch": 0.011553273427471117,
      "grad_norm": 0.6889916658401489,
      "learning_rate": 4.5e-06,
      "loss": 2.9936,
      "step": 9
    },
    {
      "epoch": 0.012836970474967908,
      "grad_norm": 0.9777728915214539,
      "learning_rate": 5e-06,
      "loss": 2.9578,
      "step": 10
    },
    {
      "epoch": 0.014120667522464698,
      "grad_norm": 0.8187949061393738,
      "learning_rate": 5.500000000000001e-06,
      "loss": 2.9442,
      "step": 11
    },
    {
      "epoch": 0.01540436456996149,
      "grad_norm": 0.7016908526420593,
      "learning_rate": 6e-06,
      "loss": 2.9299,
      "step": 12
    },
    {
      "epoch": 0.01668806161745828,
      "grad_norm": 0.6974747180938721,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 2.9699,
      "step": 13
    },
    {
      "epoch": 0.01797175866495507,
      "grad_norm": 0.8423139452934265,
      "learning_rate": 7.000000000000001e-06,
      "loss": 2.8706,
      "step": 14
    },
    {
      "epoch": 0.019255455712451863,
      "grad_norm": 0.8017705082893372,
      "learning_rate": 7.5e-06,
      "loss": 2.8443,
      "step": 15
    },
    {
      "epoch": 0.02053915275994865,
      "grad_norm": 0.9362208247184753,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.872,
      "step": 16
    },
    {
      "epoch": 0.021822849807445442,
      "grad_norm": 1.013128638267517,
      "learning_rate": 8.500000000000002e-06,
      "loss": 2.797,
      "step": 17
    },
    {
      "epoch": 0.023106546854942234,
      "grad_norm": 1.255325436592102,
      "learning_rate": 9e-06,
      "loss": 2.8109,
      "step": 18
    },
    {
      "epoch": 0.024390243902439025,
      "grad_norm": 1.1081339120864868,
      "learning_rate": 9.5e-06,
      "loss": 2.6742,
      "step": 19
    },
    {
      "epoch": 0.025673940949935817,
      "grad_norm": 0.8878622651100159,
      "learning_rate": 1e-05,
      "loss": 2.7251,
      "step": 20
    },
    {
      "epoch": 0.026957637997432605,
      "grad_norm": 0.894791305065155,
      "learning_rate": 1.05e-05,
      "loss": 2.7127,
      "step": 21
    },
    {
      "epoch": 0.028241335044929396,
      "grad_norm": 0.6742448806762695,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 2.6842,
      "step": 22
    },
    {
      "epoch": 0.029525032092426188,
      "grad_norm": 0.6250098943710327,
      "learning_rate": 1.1500000000000002e-05,
      "loss": 2.6476,
      "step": 23
    },
    {
      "epoch": 0.03080872913992298,
      "grad_norm": 0.6331678032875061,
      "learning_rate": 1.2e-05,
      "loss": 2.6339,
      "step": 24
    },
    {
      "epoch": 0.03209242618741977,
      "grad_norm": 0.4726584255695343,
      "learning_rate": 1.25e-05,
      "loss": 2.5994,
      "step": 25
    },
    {
      "epoch": 0.03337612323491656,
      "grad_norm": 0.46077489852905273,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 2.5545,
      "step": 26
    },
    {
      "epoch": 0.03465982028241335,
      "grad_norm": 0.5746111273765564,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 2.5542,
      "step": 27
    },
    {
      "epoch": 0.03594351732991014,
      "grad_norm": 0.47136253118515015,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.6138,
      "step": 28
    },
    {
      "epoch": 0.037227214377406934,
      "grad_norm": 0.5951219797134399,
      "learning_rate": 1.45e-05,
      "loss": 2.5941,
      "step": 29
    },
    {
      "epoch": 0.038510911424903725,
      "grad_norm": 0.48593708872795105,
      "learning_rate": 1.5e-05,
      "loss": 2.5751,
      "step": 30
    },
    {
      "epoch": 0.03979460847240052,
      "grad_norm": 0.482264906167984,
      "learning_rate": 1.55e-05,
      "loss": 2.5689,
      "step": 31
    },
    {
      "epoch": 0.0410783055198973,
      "grad_norm": 0.4937015175819397,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.5559,
      "step": 32
    },
    {
      "epoch": 0.04236200256739409,
      "grad_norm": 0.5136978030204773,
      "learning_rate": 1.65e-05,
      "loss": 2.5274,
      "step": 33
    },
    {
      "epoch": 0.043645699614890884,
      "grad_norm": 0.40434661507606506,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 2.4391,
      "step": 34
    },
    {
      "epoch": 0.044929396662387676,
      "grad_norm": 0.49542951583862305,
      "learning_rate": 1.75e-05,
      "loss": 2.5738,
      "step": 35
    },
    {
      "epoch": 0.04621309370988447,
      "grad_norm": 0.4381186366081238,
      "learning_rate": 1.8e-05,
      "loss": 2.5095,
      "step": 36
    },
    {
      "epoch": 0.04749679075738126,
      "grad_norm": 0.486103892326355,
      "learning_rate": 1.85e-05,
      "loss": 2.6173,
      "step": 37
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 0.4313197135925293,
      "learning_rate": 1.9e-05,
      "loss": 2.4951,
      "step": 38
    },
    {
      "epoch": 0.05006418485237484,
      "grad_norm": 0.4211004078388214,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 2.5469,
      "step": 39
    },
    {
      "epoch": 0.051347881899871634,
      "grad_norm": 0.44780072569847107,
      "learning_rate": 2e-05,
      "loss": 2.4437,
      "step": 40
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.44611668586730957,
      "learning_rate": 2.05e-05,
      "loss": 2.4795,
      "step": 41
    },
    {
      "epoch": 0.05391527599486521,
      "grad_norm": 0.4598286747932434,
      "learning_rate": 2.1e-05,
      "loss": 2.4786,
      "step": 42
    },
    {
      "epoch": 0.055198973042362,
      "grad_norm": 0.4416978061199188,
      "learning_rate": 2.15e-05,
      "loss": 2.453,
      "step": 43
    },
    {
      "epoch": 0.05648267008985879,
      "grad_norm": 0.4136359989643097,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.4975,
      "step": 44
    },
    {
      "epoch": 0.057766367137355584,
      "grad_norm": 0.44032955169677734,
      "learning_rate": 2.25e-05,
      "loss": 2.411,
      "step": 45
    },
    {
      "epoch": 0.059050064184852376,
      "grad_norm": 0.49505728483200073,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 2.5049,
      "step": 46
    },
    {
      "epoch": 0.06033376123234917,
      "grad_norm": 0.43698814511299133,
      "learning_rate": 2.35e-05,
      "loss": 2.5828,
      "step": 47
    },
    {
      "epoch": 0.06161745827984596,
      "grad_norm": 0.44550350308418274,
      "learning_rate": 2.4e-05,
      "loss": 2.4326,
      "step": 48
    },
    {
      "epoch": 0.06290115532734275,
      "grad_norm": 0.38959425687789917,
      "learning_rate": 2.45e-05,
      "loss": 2.4684,
      "step": 49
    },
    {
      "epoch": 0.06418485237483953,
      "grad_norm": 0.4324244260787964,
      "learning_rate": 2.5e-05,
      "loss": 2.4496,
      "step": 50
    },
    {
      "epoch": 0.06546854942233633,
      "grad_norm": 0.4213118553161621,
      "learning_rate": 2.5500000000000003e-05,
      "loss": 2.4742,
      "step": 51
    },
    {
      "epoch": 0.06675224646983312,
      "grad_norm": 0.5279268622398376,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.4222,
      "step": 52
    },
    {
      "epoch": 0.06803594351732992,
      "grad_norm": 0.40476322174072266,
      "learning_rate": 2.6500000000000004e-05,
      "loss": 2.4224,
      "step": 53
    },
    {
      "epoch": 0.0693196405648267,
      "grad_norm": 0.6938806176185608,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 2.4194,
      "step": 54
    },
    {
      "epoch": 0.07060333761232349,
      "grad_norm": 0.43899399042129517,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 2.4288,
      "step": 55
    },
    {
      "epoch": 0.07188703465982028,
      "grad_norm": 0.3968575596809387,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.3968,
      "step": 56
    },
    {
      "epoch": 0.07317073170731707,
      "grad_norm": 0.6113290786743164,
      "learning_rate": 2.8499999999999998e-05,
      "loss": 2.3924,
      "step": 57
    },
    {
      "epoch": 0.07445442875481387,
      "grad_norm": 0.35704493522644043,
      "learning_rate": 2.9e-05,
      "loss": 2.4004,
      "step": 58
    },
    {
      "epoch": 0.07573812580231065,
      "grad_norm": 0.3809000551700592,
      "learning_rate": 2.95e-05,
      "loss": 2.4303,
      "step": 59
    },
    {
      "epoch": 0.07702182284980745,
      "grad_norm": 0.4394189715385437,
      "learning_rate": 3e-05,
      "loss": 2.4716,
      "step": 60
    },
    {
      "epoch": 0.07830551989730423,
      "grad_norm": 0.4325893521308899,
      "learning_rate": 3.05e-05,
      "loss": 2.4715,
      "step": 61
    },
    {
      "epoch": 0.07958921694480103,
      "grad_norm": 0.3560517728328705,
      "learning_rate": 3.1e-05,
      "loss": 2.4745,
      "step": 62
    },
    {
      "epoch": 0.08087291399229782,
      "grad_norm": 0.37922918796539307,
      "learning_rate": 3.15e-05,
      "loss": 2.4789,
      "step": 63
    },
    {
      "epoch": 0.0821566110397946,
      "grad_norm": 0.3665093779563904,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.4829,
      "step": 64
    },
    {
      "epoch": 0.0834403080872914,
      "grad_norm": 0.38106483221054077,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 2.4203,
      "step": 65
    },
    {
      "epoch": 0.08472400513478819,
      "grad_norm": 0.5111002326011658,
      "learning_rate": 3.3e-05,
      "loss": 2.3302,
      "step": 66
    },
    {
      "epoch": 0.08600770218228498,
      "grad_norm": 0.37738922238349915,
      "learning_rate": 3.35e-05,
      "loss": 2.4991,
      "step": 67
    },
    {
      "epoch": 0.08729139922978177,
      "grad_norm": 0.34703031182289124,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 2.4224,
      "step": 68
    },
    {
      "epoch": 0.08857509627727857,
      "grad_norm": 0.48427700996398926,
      "learning_rate": 3.45e-05,
      "loss": 2.3946,
      "step": 69
    },
    {
      "epoch": 0.08985879332477535,
      "grad_norm": 0.360221266746521,
      "learning_rate": 3.5e-05,
      "loss": 2.4853,
      "step": 70
    },
    {
      "epoch": 0.09114249037227215,
      "grad_norm": 0.4006412625312805,
      "learning_rate": 3.55e-05,
      "loss": 2.4654,
      "step": 71
    },
    {
      "epoch": 0.09242618741976893,
      "grad_norm": 0.3662618398666382,
      "learning_rate": 3.6e-05,
      "loss": 2.434,
      "step": 72
    },
    {
      "epoch": 0.09370988446726572,
      "grad_norm": 0.3694933354854584,
      "learning_rate": 3.65e-05,
      "loss": 2.4194,
      "step": 73
    },
    {
      "epoch": 0.09499358151476252,
      "grad_norm": 0.34268808364868164,
      "learning_rate": 3.7e-05,
      "loss": 2.4922,
      "step": 74
    },
    {
      "epoch": 0.0962772785622593,
      "grad_norm": 0.3664718270301819,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 2.4083,
      "step": 75
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.3909706473350525,
      "learning_rate": 3.8e-05,
      "loss": 2.4546,
      "step": 76
    },
    {
      "epoch": 0.09884467265725289,
      "grad_norm": 0.36276674270629883,
      "learning_rate": 3.85e-05,
      "loss": 2.5313,
      "step": 77
    },
    {
      "epoch": 0.10012836970474968,
      "grad_norm": 0.34822535514831543,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 2.4833,
      "step": 78
    },
    {
      "epoch": 0.10141206675224647,
      "grad_norm": 0.37480583786964417,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 2.449,
      "step": 79
    },
    {
      "epoch": 0.10269576379974327,
      "grad_norm": 0.3415388762950897,
      "learning_rate": 4e-05,
      "loss": 2.3953,
      "step": 80
    },
    {
      "epoch": 0.10397946084724005,
      "grad_norm": 0.3487205505371094,
      "learning_rate": 4.05e-05,
      "loss": 2.4469,
      "step": 81
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.5083756446838379,
      "learning_rate": 4.1e-05,
      "loss": 2.3423,
      "step": 82
    },
    {
      "epoch": 0.10654685494223363,
      "grad_norm": 0.3747817575931549,
      "learning_rate": 4.15e-05,
      "loss": 2.3919,
      "step": 83
    },
    {
      "epoch": 0.10783055198973042,
      "grad_norm": 0.39472389221191406,
      "learning_rate": 4.2e-05,
      "loss": 2.5431,
      "step": 84
    },
    {
      "epoch": 0.10911424903722722,
      "grad_norm": 0.36542952060699463,
      "learning_rate": 4.25e-05,
      "loss": 2.3858,
      "step": 85
    },
    {
      "epoch": 0.110397946084724,
      "grad_norm": 0.34629878401756287,
      "learning_rate": 4.3e-05,
      "loss": 2.3528,
      "step": 86
    },
    {
      "epoch": 0.1116816431322208,
      "grad_norm": 0.36755290627479553,
      "learning_rate": 4.35e-05,
      "loss": 2.5329,
      "step": 87
    },
    {
      "epoch": 0.11296534017971759,
      "grad_norm": 0.3599033057689667,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.4971,
      "step": 88
    },
    {
      "epoch": 0.11424903722721438,
      "grad_norm": 0.3730204701423645,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 2.4082,
      "step": 89
    },
    {
      "epoch": 0.11553273427471117,
      "grad_norm": 0.3773551881313324,
      "learning_rate": 4.5e-05,
      "loss": 2.3393,
      "step": 90
    },
    {
      "epoch": 0.11681643132220795,
      "grad_norm": 0.36052408814430237,
      "learning_rate": 4.55e-05,
      "loss": 2.3799,
      "step": 91
    },
    {
      "epoch": 0.11810012836970475,
      "grad_norm": 0.32685768604278564,
      "learning_rate": 4.600000000000001e-05,
      "loss": 2.4284,
      "step": 92
    },
    {
      "epoch": 0.11938382541720154,
      "grad_norm": 0.36063292622566223,
      "learning_rate": 4.6500000000000005e-05,
      "loss": 2.3903,
      "step": 93
    },
    {
      "epoch": 0.12066752246469833,
      "grad_norm": 0.3656150698661804,
      "learning_rate": 4.7e-05,
      "loss": 2.4378,
      "step": 94
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 0.3563483655452728,
      "learning_rate": 4.75e-05,
      "loss": 2.4082,
      "step": 95
    },
    {
      "epoch": 0.12323491655969192,
      "grad_norm": 0.35744163393974304,
      "learning_rate": 4.8e-05,
      "loss": 2.3979,
      "step": 96
    },
    {
      "epoch": 0.1245186136071887,
      "grad_norm": 0.3400294780731201,
      "learning_rate": 4.85e-05,
      "loss": 2.4419,
      "step": 97
    },
    {
      "epoch": 0.1258023106546855,
      "grad_norm": 0.3691268265247345,
      "learning_rate": 4.9e-05,
      "loss": 2.4671,
      "step": 98
    },
    {
      "epoch": 0.12708600770218229,
      "grad_norm": 0.3483717739582062,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 2.3947,
      "step": 99
    },
    {
      "epoch": 0.12836970474967907,
      "grad_norm": 0.3494178354740143,
      "learning_rate": 5e-05,
      "loss": 2.4063,
      "step": 100
    },
    {
      "epoch": 0.12965340179717585,
      "grad_norm": 0.3814634680747986,
      "learning_rate": 4.9999986437272225e-05,
      "loss": 2.4832,
      "step": 101
    },
    {
      "epoch": 0.13093709884467267,
      "grad_norm": 0.378907710313797,
      "learning_rate": 4.999994574910364e-05,
      "loss": 2.3272,
      "step": 102
    },
    {
      "epoch": 0.13222079589216945,
      "grad_norm": 0.3730032444000244,
      "learning_rate": 4.999987793553836e-05,
      "loss": 2.3965,
      "step": 103
    },
    {
      "epoch": 0.13350449293966624,
      "grad_norm": 0.3670955002307892,
      "learning_rate": 4.9999782996649994e-05,
      "loss": 2.4565,
      "step": 104
    },
    {
      "epoch": 0.13478818998716302,
      "grad_norm": 0.36450427770614624,
      "learning_rate": 4.999966093254153e-05,
      "loss": 2.5079,
      "step": 105
    },
    {
      "epoch": 0.13607188703465983,
      "grad_norm": 0.38658779859542847,
      "learning_rate": 4.9999511743345426e-05,
      "loss": 2.4775,
      "step": 106
    },
    {
      "epoch": 0.13735558408215662,
      "grad_norm": 0.33551573753356934,
      "learning_rate": 4.999933542922354e-05,
      "loss": 2.461,
      "step": 107
    },
    {
      "epoch": 0.1386392811296534,
      "grad_norm": 0.3854399025440216,
      "learning_rate": 4.999913199036719e-05,
      "loss": 2.4075,
      "step": 108
    },
    {
      "epoch": 0.1399229781771502,
      "grad_norm": 0.3932352364063263,
      "learning_rate": 4.9998901426997104e-05,
      "loss": 2.4311,
      "step": 109
    },
    {
      "epoch": 0.14120667522464697,
      "grad_norm": 0.3379668593406677,
      "learning_rate": 4.999864373936345e-05,
      "loss": 2.5016,
      "step": 110
    },
    {
      "epoch": 0.14249037227214378,
      "grad_norm": 0.32840296626091003,
      "learning_rate": 4.9998358927745826e-05,
      "loss": 2.3176,
      "step": 111
    },
    {
      "epoch": 0.14377406931964057,
      "grad_norm": 0.3191027343273163,
      "learning_rate": 4.999804699245325e-05,
      "loss": 2.4007,
      "step": 112
    },
    {
      "epoch": 0.14505776636713735,
      "grad_norm": 0.3358600437641144,
      "learning_rate": 4.999770793382418e-05,
      "loss": 2.3724,
      "step": 113
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 0.335860937833786,
      "learning_rate": 4.99973417522265e-05,
      "loss": 2.3479,
      "step": 114
    },
    {
      "epoch": 0.14762516046213095,
      "grad_norm": 0.34540730714797974,
      "learning_rate": 4.999694844805753e-05,
      "loss": 2.3675,
      "step": 115
    },
    {
      "epoch": 0.14890885750962773,
      "grad_norm": 0.3298475742340088,
      "learning_rate": 4.999652802174402e-05,
      "loss": 2.3948,
      "step": 116
    },
    {
      "epoch": 0.15019255455712452,
      "grad_norm": 0.3612127900123596,
      "learning_rate": 4.999608047374211e-05,
      "loss": 2.3855,
      "step": 117
    },
    {
      "epoch": 0.1514762516046213,
      "grad_norm": 0.4185655415058136,
      "learning_rate": 4.9995605804537426e-05,
      "loss": 2.4015,
      "step": 118
    },
    {
      "epoch": 0.1527599486521181,
      "grad_norm": 0.3759553134441376,
      "learning_rate": 4.9995104014644986e-05,
      "loss": 2.4483,
      "step": 119
    },
    {
      "epoch": 0.1540436456996149,
      "grad_norm": 0.35989564657211304,
      "learning_rate": 4.999457510460923e-05,
      "loss": 2.4974,
      "step": 120
    },
    {
      "epoch": 0.15532734274711169,
      "grad_norm": 0.3161202073097229,
      "learning_rate": 4.999401907500405e-05,
      "loss": 2.3712,
      "step": 121
    },
    {
      "epoch": 0.15661103979460847,
      "grad_norm": 0.3105814456939697,
      "learning_rate": 4.999343592643274e-05,
      "loss": 2.4311,
      "step": 122
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 0.3236968517303467,
      "learning_rate": 4.9992825659528024e-05,
      "loss": 2.5536,
      "step": 123
    },
    {
      "epoch": 0.15917843388960207,
      "grad_norm": 0.3107609748840332,
      "learning_rate": 4.9992188274952064e-05,
      "loss": 2.3922,
      "step": 124
    },
    {
      "epoch": 0.16046213093709885,
      "grad_norm": 0.39889928698539734,
      "learning_rate": 4.999152377339642e-05,
      "loss": 2.3488,
      "step": 125
    },
    {
      "epoch": 0.16174582798459564,
      "grad_norm": 0.379323273897171,
      "learning_rate": 4.99908321555821e-05,
      "loss": 2.5278,
      "step": 126
    },
    {
      "epoch": 0.16302952503209242,
      "grad_norm": 0.35020819306373596,
      "learning_rate": 4.999011342225952e-05,
      "loss": 2.3139,
      "step": 127
    },
    {
      "epoch": 0.1643132220795892,
      "grad_norm": 0.34851884841918945,
      "learning_rate": 4.998936757420851e-05,
      "loss": 2.3495,
      "step": 128
    },
    {
      "epoch": 0.16559691912708602,
      "grad_norm": 0.3453572392463684,
      "learning_rate": 4.9988594612238336e-05,
      "loss": 2.4128,
      "step": 129
    },
    {
      "epoch": 0.1668806161745828,
      "grad_norm": 0.34227538108825684,
      "learning_rate": 4.998779453718768e-05,
      "loss": 2.3419,
      "step": 130
    },
    {
      "epoch": 0.1681643132220796,
      "grad_norm": 0.3947238028049469,
      "learning_rate": 4.998696734992462e-05,
      "loss": 2.3941,
      "step": 131
    },
    {
      "epoch": 0.16944801026957637,
      "grad_norm": 0.306533545255661,
      "learning_rate": 4.998611305134669e-05,
      "loss": 2.4645,
      "step": 132
    },
    {
      "epoch": 0.17073170731707318,
      "grad_norm": 0.35172709822654724,
      "learning_rate": 4.998523164238082e-05,
      "loss": 2.4407,
      "step": 133
    },
    {
      "epoch": 0.17201540436456997,
      "grad_norm": 0.34511688351631165,
      "learning_rate": 4.9984323123983334e-05,
      "loss": 2.3815,
      "step": 134
    },
    {
      "epoch": 0.17329910141206675,
      "grad_norm": 0.33132505416870117,
      "learning_rate": 4.9983387497140006e-05,
      "loss": 2.3548,
      "step": 135
    },
    {
      "epoch": 0.17458279845956354,
      "grad_norm": 0.32891082763671875,
      "learning_rate": 4.998242476286601e-05,
      "loss": 2.5308,
      "step": 136
    },
    {
      "epoch": 0.17586649550706032,
      "grad_norm": 0.331152081489563,
      "learning_rate": 4.998143492220592e-05,
      "loss": 2.3858,
      "step": 137
    },
    {
      "epoch": 0.17715019255455713,
      "grad_norm": 0.31813687086105347,
      "learning_rate": 4.9980417976233735e-05,
      "loss": 2.3136,
      "step": 138
    },
    {
      "epoch": 0.17843388960205392,
      "grad_norm": 0.3268696069717407,
      "learning_rate": 4.9979373926052865e-05,
      "loss": 2.3133,
      "step": 139
    },
    {
      "epoch": 0.1797175866495507,
      "grad_norm": 0.3389696180820465,
      "learning_rate": 4.997830277279612e-05,
      "loss": 2.3983,
      "step": 140
    },
    {
      "epoch": 0.1810012836970475,
      "grad_norm": 0.3515508770942688,
      "learning_rate": 4.997720451762572e-05,
      "loss": 2.4848,
      "step": 141
    },
    {
      "epoch": 0.1822849807445443,
      "grad_norm": 0.3302924335002899,
      "learning_rate": 4.997607916173329e-05,
      "loss": 2.3037,
      "step": 142
    },
    {
      "epoch": 0.18356867779204109,
      "grad_norm": 0.3332863450050354,
      "learning_rate": 4.997492670633987e-05,
      "loss": 2.3563,
      "step": 143
    },
    {
      "epoch": 0.18485237483953787,
      "grad_norm": 0.3398495614528656,
      "learning_rate": 4.997374715269589e-05,
      "loss": 2.4056,
      "step": 144
    },
    {
      "epoch": 0.18613607188703465,
      "grad_norm": 0.3376169502735138,
      "learning_rate": 4.9972540502081184e-05,
      "loss": 2.3751,
      "step": 145
    },
    {
      "epoch": 0.18741976893453144,
      "grad_norm": 0.33639830350875854,
      "learning_rate": 4.9971306755804995e-05,
      "loss": 2.432,
      "step": 146
    },
    {
      "epoch": 0.18870346598202825,
      "grad_norm": 0.410265177488327,
      "learning_rate": 4.9970045915205954e-05,
      "loss": 2.3647,
      "step": 147
    },
    {
      "epoch": 0.18998716302952504,
      "grad_norm": 0.31853362917900085,
      "learning_rate": 4.99687579816521e-05,
      "loss": 2.4224,
      "step": 148
    },
    {
      "epoch": 0.19127086007702182,
      "grad_norm": 0.3495614230632782,
      "learning_rate": 4.9967442956540863e-05,
      "loss": 2.3961,
      "step": 149
    },
    {
      "epoch": 0.1925545571245186,
      "grad_norm": 0.33301132917404175,
      "learning_rate": 4.996610084129908e-05,
      "loss": 2.359,
      "step": 150
    },
    {
      "epoch": 0.19383825417201542,
      "grad_norm": 0.3186255395412445,
      "learning_rate": 4.996473163738295e-05,
      "loss": 2.4488,
      "step": 151
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.3374113142490387,
      "learning_rate": 4.996333534627809e-05,
      "loss": 2.4019,
      "step": 152
    },
    {
      "epoch": 0.196405648267009,
      "grad_norm": 0.33905014395713806,
      "learning_rate": 4.996191196949952e-05,
      "loss": 2.3272,
      "step": 153
    },
    {
      "epoch": 0.19768934531450577,
      "grad_norm": 0.3546963036060333,
      "learning_rate": 4.996046150859161e-05,
      "loss": 2.4338,
      "step": 154
    },
    {
      "epoch": 0.19897304236200256,
      "grad_norm": 0.35965755581855774,
      "learning_rate": 4.9958983965128145e-05,
      "loss": 2.3634,
      "step": 155
    },
    {
      "epoch": 0.20025673940949937,
      "grad_norm": 0.3362196385860443,
      "learning_rate": 4.995747934071229e-05,
      "loss": 2.4457,
      "step": 156
    },
    {
      "epoch": 0.20154043645699615,
      "grad_norm": 0.37214434146881104,
      "learning_rate": 4.995594763697657e-05,
      "loss": 2.3714,
      "step": 157
    },
    {
      "epoch": 0.20282413350449294,
      "grad_norm": 0.3538600206375122,
      "learning_rate": 4.995438885558294e-05,
      "loss": 2.4338,
      "step": 158
    },
    {
      "epoch": 0.20410783055198972,
      "grad_norm": 0.3853035569190979,
      "learning_rate": 4.995280299822268e-05,
      "loss": 2.4036,
      "step": 159
    },
    {
      "epoch": 0.20539152759948653,
      "grad_norm": 0.35037294030189514,
      "learning_rate": 4.9951190066616495e-05,
      "loss": 2.3846,
      "step": 160
    },
    {
      "epoch": 0.20667522464698332,
      "grad_norm": 0.3986567556858063,
      "learning_rate": 4.994955006251443e-05,
      "loss": 2.4405,
      "step": 161
    },
    {
      "epoch": 0.2079589216944801,
      "grad_norm": 0.385637491941452,
      "learning_rate": 4.994788298769593e-05,
      "loss": 2.3237,
      "step": 162
    },
    {
      "epoch": 0.2092426187419769,
      "grad_norm": 0.34437429904937744,
      "learning_rate": 4.994618884396979e-05,
      "loss": 2.3477,
      "step": 163
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.34156107902526855,
      "learning_rate": 4.99444676331742e-05,
      "loss": 2.3576,
      "step": 164
    },
    {
      "epoch": 0.21181001283697048,
      "grad_norm": 0.33888015151023865,
      "learning_rate": 4.99427193571767e-05,
      "loss": 2.311,
      "step": 165
    },
    {
      "epoch": 0.21309370988446727,
      "grad_norm": 0.34711146354675293,
      "learning_rate": 4.99409440178742e-05,
      "loss": 2.293,
      "step": 166
    },
    {
      "epoch": 0.21437740693196405,
      "grad_norm": 0.30586686730384827,
      "learning_rate": 4.993914161719297e-05,
      "loss": 2.479,
      "step": 167
    },
    {
      "epoch": 0.21566110397946084,
      "grad_norm": 0.4145469069480896,
      "learning_rate": 4.993731215708866e-05,
      "loss": 2.2754,
      "step": 168
    },
    {
      "epoch": 0.21694480102695765,
      "grad_norm": 0.6243994235992432,
      "learning_rate": 4.993545563954626e-05,
      "loss": 2.3751,
      "step": 169
    },
    {
      "epoch": 0.21822849807445444,
      "grad_norm": 0.3301653265953064,
      "learning_rate": 4.993357206658011e-05,
      "loss": 2.6124,
      "step": 170
    },
    {
      "epoch": 0.21951219512195122,
      "grad_norm": 0.337147980928421,
      "learning_rate": 4.993166144023396e-05,
      "loss": 2.3946,
      "step": 171
    },
    {
      "epoch": 0.220795892169448,
      "grad_norm": 0.3796294033527374,
      "learning_rate": 4.9929723762580835e-05,
      "loss": 2.3314,
      "step": 172
    },
    {
      "epoch": 0.2220795892169448,
      "grad_norm": 0.4021480679512024,
      "learning_rate": 4.9927759035723175e-05,
      "loss": 2.3035,
      "step": 173
    },
    {
      "epoch": 0.2233632862644416,
      "grad_norm": 0.3196207582950592,
      "learning_rate": 4.992576726179274e-05,
      "loss": 2.4047,
      "step": 174
    },
    {
      "epoch": 0.2246469833119384,
      "grad_norm": 0.31279096007347107,
      "learning_rate": 4.992374844295064e-05,
      "loss": 2.4409,
      "step": 175
    },
    {
      "epoch": 0.22593068035943517,
      "grad_norm": 0.3068607747554779,
      "learning_rate": 4.992170258138732e-05,
      "loss": 2.4109,
      "step": 176
    },
    {
      "epoch": 0.22721437740693196,
      "grad_norm": 0.35363098978996277,
      "learning_rate": 4.991962967932258e-05,
      "loss": 2.4083,
      "step": 177
    },
    {
      "epoch": 0.22849807445442877,
      "grad_norm": 0.33908936381340027,
      "learning_rate": 4.9917529739005574e-05,
      "loss": 2.4129,
      "step": 178
    },
    {
      "epoch": 0.22978177150192555,
      "grad_norm": 0.32510805130004883,
      "learning_rate": 4.991540276271476e-05,
      "loss": 2.3163,
      "step": 179
    },
    {
      "epoch": 0.23106546854942234,
      "grad_norm": 0.32639047503471375,
      "learning_rate": 4.991324875275794e-05,
      "loss": 2.3567,
      "step": 180
    },
    {
      "epoch": 0.23234916559691912,
      "grad_norm": 0.3410406708717346,
      "learning_rate": 4.991106771147227e-05,
      "loss": 2.4137,
      "step": 181
    },
    {
      "epoch": 0.2336328626444159,
      "grad_norm": 0.3334997892379761,
      "learning_rate": 4.990885964122421e-05,
      "loss": 2.3994,
      "step": 182
    },
    {
      "epoch": 0.23491655969191272,
      "grad_norm": 0.3203848600387573,
      "learning_rate": 4.990662454440956e-05,
      "loss": 2.4259,
      "step": 183
    },
    {
      "epoch": 0.2362002567394095,
      "grad_norm": 0.34999069571495056,
      "learning_rate": 4.9904362423453446e-05,
      "loss": 2.413,
      "step": 184
    },
    {
      "epoch": 0.2374839537869063,
      "grad_norm": 0.3413456678390503,
      "learning_rate": 4.990207328081029e-05,
      "loss": 2.3749,
      "step": 185
    },
    {
      "epoch": 0.23876765083440307,
      "grad_norm": 0.3702191114425659,
      "learning_rate": 4.989975711896388e-05,
      "loss": 2.4309,
      "step": 186
    },
    {
      "epoch": 0.24005134788189988,
      "grad_norm": 0.3365226089954376,
      "learning_rate": 4.989741394042727e-05,
      "loss": 2.3708,
      "step": 187
    },
    {
      "epoch": 0.24133504492939667,
      "grad_norm": 0.36596447229385376,
      "learning_rate": 4.989504374774288e-05,
      "loss": 2.4387,
      "step": 188
    },
    {
      "epoch": 0.24261874197689345,
      "grad_norm": 0.3280293941497803,
      "learning_rate": 4.9892646543482377e-05,
      "loss": 2.498,
      "step": 189
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.35989147424697876,
      "learning_rate": 4.989022233024681e-05,
      "loss": 2.4993,
      "step": 190
    },
    {
      "epoch": 0.24518613607188702,
      "grad_norm": 0.3124522268772125,
      "learning_rate": 4.988777111066646e-05,
      "loss": 2.3186,
      "step": 191
    },
    {
      "epoch": 0.24646983311938384,
      "grad_norm": 0.32323285937309265,
      "learning_rate": 4.988529288740096e-05,
      "loss": 2.3859,
      "step": 192
    },
    {
      "epoch": 0.24775353016688062,
      "grad_norm": 0.33156561851501465,
      "learning_rate": 4.988278766313922e-05,
      "loss": 2.3271,
      "step": 193
    },
    {
      "epoch": 0.2490372272143774,
      "grad_norm": 0.32494014501571655,
      "learning_rate": 4.9880255440599476e-05,
      "loss": 2.4023,
      "step": 194
    },
    {
      "epoch": 0.2503209242618742,
      "grad_norm": 0.3906209468841553,
      "learning_rate": 4.987769622252921e-05,
      "loss": 2.4245,
      "step": 195
    }
  ],
  "logging_steps": 1,
  "max_steps": 3116,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 195,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.366728800609239e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}