{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 78,
  "global_step": 310,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.12883105396714237,
      "learning_rate": 1e-05,
      "loss": 0.4154,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 0.4359087646007538,
      "eval_runtime": 45.0668,
      "eval_samples_per_second": 35.503,
      "eval_steps_per_second": 0.555,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.13019894725030426,
      "learning_rate": 2e-05,
      "loss": 0.4102,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.12448027718685753,
      "learning_rate": 3e-05,
      "loss": 0.4339,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.13617024064519495,
      "learning_rate": 4e-05,
      "loss": 0.4463,
      "step": 4
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.1192695514188061,
      "learning_rate": 5e-05,
      "loss": 0.4257,
      "step": 5
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.12484938518090542,
      "learning_rate": 6e-05,
      "loss": 0.4476,
      "step": 6
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.11589635616988343,
      "learning_rate": 7e-05,
      "loss": 0.4726,
      "step": 7
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.11326282450028814,
      "learning_rate": 8e-05,
      "loss": 0.44,
      "step": 8
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.10349552391227962,
      "learning_rate": 9e-05,
      "loss": 0.4623,
      "step": 9
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.10545214328006507,
      "learning_rate": 0.0001,
      "loss": 0.4116,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.08723759174445953,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.4216,
      "step": 11
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.08139085000714291,
      "learning_rate": 0.00012,
      "loss": 0.39,
      "step": 12
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.09205927275648706,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.434,
      "step": 13
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.10404439147125429,
      "learning_rate": 0.00014,
      "loss": 0.4511,
      "step": 14
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.08585041684076992,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.4048,
      "step": 15
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.09399258996254131,
      "learning_rate": 0.00016,
      "loss": 0.4322,
      "step": 16
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.10425830227796497,
      "learning_rate": 0.00017,
      "loss": 0.4174,
      "step": 17
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.08675512504623259,
      "learning_rate": 0.00018,
      "loss": 0.4247,
      "step": 18
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.08901871349393159,
      "learning_rate": 0.00019,
      "loss": 0.4369,
      "step": 19
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.08060121651209443,
      "learning_rate": 0.0002,
      "loss": 0.4746,
      "step": 20
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.0734185701687092,
      "learning_rate": 0.00019999940408195878,
      "loss": 0.4178,
      "step": 21
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.07838461773593017,
      "learning_rate": 0.00019999761633493753,
      "loss": 0.4321,
      "step": 22
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.07833972271815033,
      "learning_rate": 0.00019999463678024317,
      "loss": 0.4436,
      "step": 23
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.07548486089915235,
      "learning_rate": 0.0001999904654533872,
      "loss": 0.4709,
      "step": 24
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.08788637574838197,
      "learning_rate": 0.00019998510240408496,
      "loss": 0.3872,
      "step": 25
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0812532852957508,
      "learning_rate": 0.0001999785476962552,
      "loss": 0.4058,
      "step": 26
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.08537862859222577,
      "learning_rate": 0.00019997080140801932,
      "loss": 0.4225,
      "step": 27
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.08106258078139493,
      "learning_rate": 0.00019996186363170035,
      "loss": 0.4357,
      "step": 28
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.08010684638053245,
      "learning_rate": 0.00019995173447382193,
      "loss": 0.4038,
      "step": 29
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.08709110487516528,
      "learning_rate": 0.00019994041405510705,
      "loss": 0.4724,
      "step": 30
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.07096829165155712,
      "learning_rate": 0.00019992790251047656,
      "loss": 0.4139,
      "step": 31
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.06850018644329266,
      "learning_rate": 0.00019991419998904747,
      "loss": 0.4596,
      "step": 32
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.07099101390794227,
      "learning_rate": 0.00019989930665413147,
      "loss": 0.4004,
      "step": 33
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.07941015413576936,
      "learning_rate": 0.00019988322268323268,
      "loss": 0.4299,
      "step": 34
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.07638794258403328,
      "learning_rate": 0.0001998659482680456,
      "loss": 0.4252,
      "step": 35
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.07585182258910264,
      "learning_rate": 0.00019984748361445308,
      "loss": 0.4149,
      "step": 36
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.07502482333755954,
      "learning_rate": 0.0001998278289425234,
      "loss": 0.438,
      "step": 37
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.06605988872292592,
      "learning_rate": 0.00019980698448650804,
      "loss": 0.4252,
      "step": 38
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.07295876342245719,
      "learning_rate": 0.00019978495049483884,
      "loss": 0.4132,
      "step": 39
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.06948118376282203,
      "learning_rate": 0.0001997617272301248,
      "loss": 0.4054,
      "step": 40
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.07729338055807149,
      "learning_rate": 0.00019973731496914914,
      "loss": 0.3968,
      "step": 41
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.07332342728556553,
      "learning_rate": 0.000199711714002866,
      "loss": 0.4734,
      "step": 42
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.07828161218125397,
      "learning_rate": 0.00019968492463639704,
      "loss": 0.4479,
      "step": 43
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.07194198164352739,
      "learning_rate": 0.00019965694718902745,
      "loss": 0.438,
      "step": 44
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.07115652880951175,
      "learning_rate": 0.00019962778199420265,
      "loss": 0.4227,
      "step": 45
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.0775651962190502,
      "learning_rate": 0.00019959742939952392,
      "loss": 0.4058,
      "step": 46
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.06438123421666499,
      "learning_rate": 0.00019956588976674443,
      "loss": 0.3703,
      "step": 47
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.07812636493444186,
      "learning_rate": 0.00019953316347176488,
      "loss": 0.4644,
      "step": 48
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.07727134848765603,
      "learning_rate": 0.00019949925090462909,
      "loss": 0.4314,
      "step": 49
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.07027735759113077,
      "learning_rate": 0.0001994641524695193,
      "loss": 0.4238,
      "step": 50
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.07736957822008628,
      "learning_rate": 0.00019942786858475126,
      "loss": 0.4785,
      "step": 51
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.0681570396521893,
      "learning_rate": 0.0001993903996827694,
      "loss": 0.4374,
      "step": 52
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.07143343715720442,
      "learning_rate": 0.00019935174621014173,
      "loss": 0.4194,
      "step": 53
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.06299350036763142,
      "learning_rate": 0.00019931190862755417,
      "loss": 0.4492,
      "step": 54
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.07366865611199422,
      "learning_rate": 0.0001992708874098054,
      "loss": 0.4214,
      "step": 55
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.06347135008905311,
      "learning_rate": 0.00019922868304580118,
      "loss": 0.43,
      "step": 56
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.08268927152964092,
      "learning_rate": 0.00019918529603854825,
      "loss": 0.4425,
      "step": 57
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.07034294144963513,
      "learning_rate": 0.0001991407269051487,
      "loss": 0.4105,
      "step": 58
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.06630993618399812,
      "learning_rate": 0.00019909497617679348,
      "loss": 0.3882,
      "step": 59
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.07226317955725141,
      "learning_rate": 0.00019904804439875633,
      "loss": 0.4266,
      "step": 60
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.06938919184806121,
      "learning_rate": 0.0001989999321303871,
      "loss": 0.4572,
      "step": 61
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.06492831162679569,
      "learning_rate": 0.0001989506399451051,
      "loss": 0.4318,
      "step": 62
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.06645996011351867,
      "learning_rate": 0.0001989001684303925,
      "loss": 0.417,
      "step": 63
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.08653889274769928,
      "learning_rate": 0.00019884851818778693,
      "loss": 0.4353,
      "step": 64
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.07059932526364451,
      "learning_rate": 0.00019879568983287467,
      "loss": 0.4175,
      "step": 65
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.07931101113959307,
      "learning_rate": 0.00019874168399528305,
      "loss": 0.4187,
      "step": 66
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.07125698961933573,
      "learning_rate": 0.0001986865013186732,
      "loss": 0.4159,
      "step": 67
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.08050044278206689,
      "learning_rate": 0.00019863014246073214,
      "loss": 0.4353,
      "step": 68
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.07318879088432853,
      "learning_rate": 0.0001985726080931651,
      "loss": 0.4202,
      "step": 69
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.07082720625138651,
      "learning_rate": 0.0001985138989016874,
      "loss": 0.4464,
      "step": 70
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.06698591714547134,
      "learning_rate": 0.00019845401558601634,
      "loss": 0.4251,
      "step": 71
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.07603667866936462,
      "learning_rate": 0.00019839295885986296,
      "loss": 0.4298,
      "step": 72
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.06997110349403513,
      "learning_rate": 0.00019833072945092334,
      "loss": 0.4205,
      "step": 73
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.06648812435842759,
      "learning_rate": 0.00019826732810086998,
      "loss": 0.388,
      "step": 74
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.08031943933680023,
      "learning_rate": 0.00019820275556534304,
      "loss": 0.4296,
      "step": 75
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.07292849758364575,
      "learning_rate": 0.00019813701261394136,
      "loss": 0.4693,
      "step": 76
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.06207113723375016,
      "learning_rate": 0.00019807010003021312,
      "loss": 0.4117,
      "step": 77
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.07162805849513847,
      "learning_rate": 0.00019800201861164664,
      "loss": 0.4055,
      "step": 78
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.4264196753501892,
      "eval_runtime": 45.9946,
      "eval_samples_per_second": 34.787,
      "eval_steps_per_second": 0.544,
      "step": 78
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.07162623816355349,
      "learning_rate": 0.00019793276916966083,
      "loss": 0.4203,
      "step": 79
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.06472836232949207,
      "learning_rate": 0.00019786235252959553,
      "loss": 0.4625,
      "step": 80
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.06372740407034722,
      "learning_rate": 0.00019779076953070168,
      "loss": 0.4073,
      "step": 81
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.06667839761368001,
      "learning_rate": 0.00019771802102613127,
      "loss": 0.4778,
      "step": 82
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.059574939985801316,
      "learning_rate": 0.00019764410788292722,
      "loss": 0.407,
      "step": 83
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.07648625055922231,
      "learning_rate": 0.00019756903098201308,
      "loss": 0.4295,
      "step": 84
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.06038606924130534,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.41,
      "step": 85
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.07670919708474994,
      "learning_rate": 0.00019741538950008818,
      "loss": 0.4139,
      "step": 86
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.07017791304733184,
      "learning_rate": 0.00019733682675023207,
      "loss": 0.4117,
      "step": 87
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0604723656482711,
      "learning_rate": 0.0001972571039049533,
      "loss": 0.4323,
      "step": 88
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.08127405172847653,
      "learning_rate": 0.0001971762219144174,
      "loss": 0.4396,
      "step": 89
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.07061782085169709,
      "learning_rate": 0.0001970941817426052,
      "loss": 0.3927,
      "step": 90
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.06402819168379283,
      "learning_rate": 0.00019701098436730106,
      "loss": 0.4581,
      "step": 91
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.07968710882894958,
      "learning_rate": 0.00019692663078008132,
      "loss": 0.4587,
      "step": 92
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.061691070941232884,
      "learning_rate": 0.00019684112198630244,
      "loss": 0.3996,
      "step": 93
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.07482749601200543,
      "learning_rate": 0.00019675445900508909,
      "loss": 0.4824,
      "step": 94
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.062418664967878255,
      "learning_rate": 0.00019666664286932198,
      "loss": 0.4019,
      "step": 95
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.07330319089356814,
      "learning_rate": 0.00019657767462562544,
      "loss": 0.4083,
      "step": 96
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.07046344898906809,
      "learning_rate": 0.00019648755533435518,
      "loss": 0.4487,
      "step": 97
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.06780433458947788,
      "learning_rate": 0.00019639628606958533,
      "loss": 0.428,
      "step": 98
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.07589568906196692,
      "learning_rate": 0.00019630386791909602,
      "loss": 0.4351,
      "step": 99
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.06426439686349943,
      "learning_rate": 0.00019621030198436006,
      "loss": 0.4144,
      "step": 100
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.06946467483247702,
      "learning_rate": 0.00019611558938053002,
      "loss": 0.42,
      "step": 101
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.06687266974088095,
      "learning_rate": 0.00019601973123642492,
      "loss": 0.4102,
      "step": 102
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.06476195717860939,
      "learning_rate": 0.0001959227286945167,
      "loss": 0.4307,
      "step": 103
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.06784624564247167,
      "learning_rate": 0.00019582458291091663,
      "loss": 0.437,
      "step": 104
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.07092126591759794,
      "learning_rate": 0.0001957252950553616,
      "loss": 0.4086,
      "step": 105
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.07528584467610183,
      "learning_rate": 0.00019562486631120006,
      "loss": 0.4131,
      "step": 106
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.07372322110054848,
      "learning_rate": 0.00019552329787537805,
      "loss": 0.4021,
      "step": 107
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.06862887663783342,
      "learning_rate": 0.00019542059095842485,
      "loss": 0.3967,
      "step": 108
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.06913146575239316,
      "learning_rate": 0.00019531674678443853,
      "loss": 0.3912,
      "step": 109
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.06645883203424491,
      "learning_rate": 0.00019521176659107142,
      "loss": 0.4251,
      "step": 110
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.06416682030197016,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.441,
      "step": 111
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.06876092886215074,
      "learning_rate": 0.00019499840316448673,
      "loss": 0.4391,
      "step": 112
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.06688267191994776,
      "learning_rate": 0.00019489002247421148,
      "loss": 0.4257,
      "step": 113
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.06324346733094179,
      "learning_rate": 0.00019478051085040975,
      "loss": 0.4528,
      "step": 114
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.06725879673299155,
      "learning_rate": 0.0001946698695982806,
      "loss": 0.4147,
      "step": 115
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.07241340618039839,
      "learning_rate": 0.00019455810003648637,
      "loss": 0.4527,
      "step": 116
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.06613334861150516,
      "learning_rate": 0.00019444520349713704,
      "loss": 0.4283,
      "step": 117
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.06840872345753035,
      "learning_rate": 0.0001943311813257743,
      "loss": 0.4131,
      "step": 118
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.0704617274405355,
      "learning_rate": 0.00019421603488135557,
      "loss": 0.4379,
      "step": 119
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.06787816360755813,
      "learning_rate": 0.00019409976553623766,
      "loss": 0.4177,
      "step": 120
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.06972714992884815,
      "learning_rate": 0.0001939823746761606,
      "loss": 0.3795,
      "step": 121
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.06779189257040956,
      "learning_rate": 0.00019386386370023103,
      "loss": 0.4323,
      "step": 122
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.07014006424788279,
      "learning_rate": 0.00019374423402090553,
      "loss": 0.3989,
      "step": 123
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.07661659071907612,
      "learning_rate": 0.00019362348706397373,
      "loss": 0.4422,
      "step": 124
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.07584620511227261,
      "learning_rate": 0.0001935016242685415,
      "loss": 0.4512,
      "step": 125
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.07525185527526344,
      "learning_rate": 0.00019337864708701357,
      "loss": 0.4298,
      "step": 126
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.0710375411666665,
      "learning_rate": 0.00019325455698507638,
      "loss": 0.3878,
      "step": 127
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.0673112696784915,
      "learning_rate": 0.00019312935544168048,
      "loss": 0.3705,
      "step": 128
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.0668828668657636,
      "learning_rate": 0.00019300304394902313,
      "loss": 0.4017,
      "step": 129
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.07246208549885681,
      "learning_rate": 0.00019287562401253022,
      "loss": 0.3806,
      "step": 130
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.06437628312475605,
      "learning_rate": 0.0001927470971508386,
      "loss": 0.4033,
      "step": 131
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.062491146220490415,
      "learning_rate": 0.00019261746489577765,
      "loss": 0.4136,
      "step": 132
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.06460575253319188,
      "learning_rate": 0.0001924867287923515,
      "loss": 0.4285,
      "step": 133
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.06783309737426804,
      "learning_rate": 0.0001923548903987201,
      "loss": 0.4211,
      "step": 134
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.07213052803073557,
      "learning_rate": 0.00019222195128618106,
      "loss": 0.4416,
      "step": 135
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.0677809803143048,
      "learning_rate": 0.00019208791303915063,
      "loss": 0.4384,
      "step": 136
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.07088268081293747,
      "learning_rate": 0.0001919527772551451,
      "loss": 0.4099,
      "step": 137
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.06916606268106777,
      "learning_rate": 0.0001918165455447614,
      "loss": 0.4299,
      "step": 138
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.07309072410021103,
      "learning_rate": 0.00019167921953165825,
      "loss": 0.4122,
      "step": 139
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.07900186130531832,
      "learning_rate": 0.00019154080085253666,
      "loss": 0.4599,
      "step": 140
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.06570679783619483,
      "learning_rate": 0.00019140129115712034,
      "loss": 0.3662,
      "step": 141
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.08015148942504076,
      "learning_rate": 0.0001912606921081362,
      "loss": 0.4002,
      "step": 142
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.06917459897842565,
      "learning_rate": 0.00019111900538129443,
      "loss": 0.4339,
      "step": 143
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.07295609866871429,
      "learning_rate": 0.0001909762326652686,
      "loss": 0.4252,
      "step": 144
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.0808022860773497,
      "learning_rate": 0.0001908323756616754,
      "loss": 0.4424,
      "step": 145
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.06342264967015554,
      "learning_rate": 0.00019068743608505455,
      "loss": 0.4039,
      "step": 146
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.06858427993056751,
      "learning_rate": 0.0001905414156628482,
      "loss": 0.4157,
      "step": 147
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.06968670755842428,
      "learning_rate": 0.00019039431613538047,
      "loss": 0.413,
      "step": 148
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.07867845357193032,
      "learning_rate": 0.00019024613925583652,
      "loss": 0.4086,
      "step": 149
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.0737734252643262,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.42,
      "step": 150
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.06795299857235934,
      "learning_rate": 0.0001899465605174414,
      "loss": 0.4186,
      "step": 151
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.07145917531667596,
      "learning_rate": 0.00018979516222907775,
      "loss": 0.4451,
      "step": 152
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.07680401394397088,
      "learning_rate": 0.00018964269372957038,
      "loss": 0.4206,
      "step": 153
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.06594889233352544,
      "learning_rate": 0.00018948915683609388,
      "loss": 0.4234,
      "step": 154
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.07340962027871342,
      "learning_rate": 0.00018933455337855632,
      "loss": 0.4543,
      "step": 155
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.07514208916494701,
      "learning_rate": 0.00018917888519957754,
      "loss": 0.4281,
      "step": 156
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.42719101905822754,
      "eval_runtime": 31.4768,
      "eval_samples_per_second": 50.831,
      "eval_steps_per_second": 0.794,
      "step": 156
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.06549409287056523,
      "learning_rate": 0.000189022154154467,
      "loss": 0.4324,
      "step": 157
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.0682462164394273,
      "learning_rate": 0.00018886436211120193,
      "loss": 0.433,
      "step": 158
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.08588011407859532,
      "learning_rate": 0.00018870551095040477,
      "loss": 0.4304,
      "step": 159
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.06987370558027692,
      "learning_rate": 0.000188545602565321,
      "loss": 0.4482,
      "step": 160
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.06240247030946795,
      "learning_rate": 0.00018838463886179644,
      "loss": 0.3907,
      "step": 161
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.06891290467646147,
      "learning_rate": 0.00018822262175825462,
      "loss": 0.4267,
      "step": 162
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.06542585845674868,
      "learning_rate": 0.0001880595531856738,
      "loss": 0.4284,
      "step": 163
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.0629730206122836,
      "learning_rate": 0.00018789543508756408,
      "loss": 0.4003,
      "step": 164
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.06871544541236552,
      "learning_rate": 0.0001877302694199442,
      "loss": 0.4216,
      "step": 165
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.07149666774302382,
      "learning_rate": 0.00018756405815131813,
      "loss": 0.3836,
      "step": 166
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.06997442761322878,
      "learning_rate": 0.0001873968032626518,
      "loss": 0.4188,
      "step": 167
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.084225812122246,
      "learning_rate": 0.00018722850674734927,
      "loss": 0.4298,
      "step": 168
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.06761216783540702,
      "learning_rate": 0.00018705917061122916,
      "loss": 0.361,
      "step": 169
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.07234030808073647,
      "learning_rate": 0.00018688879687250067,
      "loss": 0.4097,
      "step": 170
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.06626071479471723,
      "learning_rate": 0.00018671738756173944,
      "loss": 0.4082,
      "step": 171
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.06855387266060617,
      "learning_rate": 0.0001865449447218635,
      "loss": 0.4192,
      "step": 172
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.06828142558387336,
      "learning_rate": 0.00018637147040810885,
      "loss": 0.4425,
      "step": 173
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.06573023022659233,
      "learning_rate": 0.00018619696668800492,
      "loss": 0.436,
      "step": 174
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.07607545925103458,
      "learning_rate": 0.0001860214356413501,
      "loss": 0.4538,
      "step": 175
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.06694123802468883,
      "learning_rate": 0.00018584487936018661,
      "loss": 0.4172,
      "step": 176
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.06815569028292222,
      "learning_rate": 0.00018566729994877603,
      "loss": 0.4514,
      "step": 177
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.10184702083851915,
      "learning_rate": 0.0001854886995235738,
      "loss": 0.4442,
      "step": 178
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.07024340413477916,
      "learning_rate": 0.00018530908021320425,
      "loss": 0.4424,
      "step": 179
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.07366377295970097,
      "learning_rate": 0.00018512844415843514,
      "loss": 0.4149,
      "step": 180
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.07181140519657206,
      "learning_rate": 0.0001849467935121521,
      "loss": 0.4355,
      "step": 181
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.06898359648739377,
      "learning_rate": 0.00018476413043933313,
      "loss": 0.4275,
      "step": 182
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.06680808433374633,
      "learning_rate": 0.00018458045711702264,
      "loss": 0.4172,
      "step": 183
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.06630828587681081,
      "learning_rate": 0.00018439577573430555,
      "loss": 0.3927,
      "step": 184
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.06251103706062068,
      "learning_rate": 0.00018421008849228118,
      "loss": 0.4255,
      "step": 185
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.06270748210458083,
      "learning_rate": 0.00018402339760403713,
      "loss": 0.3854,
      "step": 186
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.06864674994414362,
      "learning_rate": 0.00018383570529462273,
      "loss": 0.4186,
      "step": 187
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.06636160864684977,
      "learning_rate": 0.00018364701380102266,
      "loss": 0.3948,
      "step": 188
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.06783696558409527,
      "learning_rate": 0.00018345732537213027,
      "loss": 0.4157,
      "step": 189
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.06273783195633519,
      "learning_rate": 0.00018326664226872065,
      "loss": 0.42,
      "step": 190
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0635460399988344,
      "learning_rate": 0.00018307496676342385,
      "loss": 0.3863,
      "step": 191
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.06892459709466887,
      "learning_rate": 0.00018288230114069765,
      "loss": 0.3972,
      "step": 192
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.06554573002953047,
      "learning_rate": 0.00018268864769680054,
      "loss": 0.4235,
      "step": 193
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.07841135830884972,
      "learning_rate": 0.0001824940087397641,
      "loss": 0.4345,
      "step": 194
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.07099852734871953,
      "learning_rate": 0.00018229838658936564,
      "loss": 0.4582,
      "step": 195
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.07334719442008945,
      "learning_rate": 0.00018210178357710058,
      "loss": 0.4247,
      "step": 196
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.06401877277457285,
      "learning_rate": 0.0001819042020461545,
      "loss": 0.4233,
      "step": 197
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.05794553222990041,
      "learning_rate": 0.0001817056443513754,
      "loss": 0.3993,
      "step": 198
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.06734254228013473,
      "learning_rate": 0.00018150611285924556,
      "loss": 0.4501,
      "step": 199
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.061167398242663894,
      "learning_rate": 0.00018130560994785325,
      "loss": 0.4791,
      "step": 200
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.06368439834981215,
      "learning_rate": 0.00018110413800686456,
      "loss": 0.4031,
      "step": 201
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.06396454527108245,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.4333,
      "step": 202
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.07036915456962346,
      "learning_rate": 0.00018069829665247976,
      "loss": 0.4089,
      "step": 203
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.07566355163015755,
      "learning_rate": 0.00018049393207604733,
      "loss": 0.4125,
      "step": 204
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.07110213568246515,
      "learning_rate": 0.00018028860814388827,
      "loss": 0.4423,
      "step": 205
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.06609288074156261,
      "learning_rate": 0.00018008232730312723,
      "loss": 0.3893,
      "step": 206
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.06540430345204035,
      "learning_rate": 0.00017987509201229378,
      "loss": 0.3645,
      "step": 207
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.06607405584993503,
      "learning_rate": 0.00017966690474129285,
      "loss": 0.4117,
      "step": 208
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0662155287622059,
      "learning_rate": 0.00017945776797137543,
      "loss": 0.4269,
      "step": 209
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.0617368116387909,
      "learning_rate": 0.00017924768419510904,
      "loss": 0.3799,
      "step": 210
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.0627987397717418,
      "learning_rate": 0.00017903665591634794,
      "loss": 0.371,
      "step": 211
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.06749499008783807,
      "learning_rate": 0.00017882468565020326,
      "loss": 0.3992,
      "step": 212
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.06631945098396477,
      "learning_rate": 0.00017861177592301317,
      "loss": 0.4095,
      "step": 213
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.06685762710051685,
      "learning_rate": 0.00017839792927231254,
      "loss": 0.4349,
      "step": 214
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.07502266024951904,
      "learning_rate": 0.000178183148246803,
      "loss": 0.4197,
      "step": 215
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.08306628299652864,
      "learning_rate": 0.00017796743540632223,
      "loss": 0.4286,
      "step": 216
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.06166158787464328,
      "learning_rate": 0.0001777507933218138,
      "loss": 0.3879,
      "step": 217
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.06410797862871172,
      "learning_rate": 0.00017753322457529614,
      "loss": 0.4082,
      "step": 218
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.07279590060361223,
      "learning_rate": 0.00017731473175983212,
      "loss": 0.4491,
      "step": 219
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.06330655145519701,
      "learning_rate": 0.00017709531747949796,
      "loss": 0.3696,
      "step": 220
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.06265173315476923,
      "learning_rate": 0.00017687498434935223,
      "loss": 0.4107,
      "step": 221
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.06448654912056977,
      "learning_rate": 0.00017665373499540463,
      "loss": 0.4038,
      "step": 222
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.08291630469395751,
      "learning_rate": 0.00017643157205458483,
      "loss": 0.422,
      "step": 223
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.06632609649023061,
      "learning_rate": 0.00017620849817471092,
      "loss": 0.4271,
      "step": 224
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.07513194076660681,
      "learning_rate": 0.0001759845160144579,
      "loss": 0.4529,
      "step": 225
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.0687911159938889,
      "learning_rate": 0.00017575962824332596,
      "loss": 0.3814,
      "step": 226
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.06806851223680013,
      "learning_rate": 0.00017553383754160865,
      "loss": 0.4038,
      "step": 227
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.060354615878050986,
      "learning_rate": 0.00017530714660036112,
      "loss": 0.4139,
      "step": 228
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.06771319705049085,
      "learning_rate": 0.00017507955812136775,
      "loss": 0.4178,
      "step": 229
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.06554465726049169,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.4008,
      "step": 230
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.06628707050461834,
      "learning_rate": 0.00017462169941073475,
      "loss": 0.3704,
      "step": 231
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.0704660527100064,
      "learning_rate": 0.0001743914346360205,
      "loss": 0.4096,
      "step": 232
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.06714268412305492,
      "learning_rate": 0.00017416028323734598,
      "loss": 0.4047,
      "step": 233
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.06708061829484278,
      "learning_rate": 0.00017392824796965702,
      "loss": 0.3995,
      "step": 234
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.42397916316986084,
      "eval_runtime": 31.4123,
      "eval_samples_per_second": 50.936,
      "eval_steps_per_second": 0.796,
      "step": 234
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.0692311421790837,
      "learning_rate": 0.00017369533159843369,
      "loss": 0.4493,
      "step": 235
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.07010639301506344,
      "learning_rate": 0.00017346153689965727,
      "loss": 0.4134,
      "step": 236
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.0657681493331333,
      "learning_rate": 0.00017322686665977737,
      "loss": 0.3958,
      "step": 237
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.06417143561447558,
      "learning_rate": 0.00017299132367567857,
      "loss": 0.4104,
      "step": 238
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.08433041973271442,
      "learning_rate": 0.00017275491075464716,
      "loss": 0.4417,
      "step": 239
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.06309959644633113,
      "learning_rate": 0.00017251763071433765,
      "loss": 0.4027,
      "step": 240
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.06840734501694612,
      "learning_rate": 0.00017227948638273916,
      "loss": 0.3961,
      "step": 241
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.06502571584749511,
      "learning_rate": 0.00017204048059814175,
      "loss": 0.3961,
      "step": 242
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.06645154810491374,
      "learning_rate": 0.00017180061620910263,
      "loss": 0.4034,
      "step": 243
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.07169067898808924,
      "learning_rate": 0.00017155989607441213,
      "loss": 0.4578,
      "step": 244
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.06951259218049313,
      "learning_rate": 0.00017131832306305965,
      "loss": 0.4222,
      "step": 245
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.06936292391783441,
      "learning_rate": 0.0001710759000541995,
      "loss": 0.4412,
      "step": 246
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.0641932957849969,
      "learning_rate": 0.00017083262993711662,
      "loss": 0.4122,
      "step": 247
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.06519962544514646,
      "learning_rate": 0.00017058851561119198,
      "loss": 0.3949,
      "step": 248
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.06139777990217894,
      "learning_rate": 0.00017034355998586827,
      "loss": 0.4533,
      "step": 249
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.06382389409436602,
      "learning_rate": 0.00017009776598061495,
      "loss": 0.4225,
      "step": 250
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.0745112215377997,
      "learning_rate": 0.00016985113652489374,
      "loss": 0.4172,
      "step": 251
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.06202295907342136,
      "learning_rate": 0.00016960367455812336,
      "loss": 0.4156,
      "step": 252
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.0601321734977661,
      "learning_rate": 0.00016935538302964494,
      "loss": 0.4094,
      "step": 253
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.07237506968634055,
      "learning_rate": 0.00016910626489868649,
      "loss": 0.4254,
      "step": 254
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.06626388773117148,
      "learning_rate": 0.0001688563231343277,
      "loss": 0.4277,
      "step": 255
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.06262183979430723,
      "learning_rate": 0.0001686055607154648,
      "loss": 0.4143,
      "step": 256
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.07788401630185697,
      "learning_rate": 0.00016835398063077474,
      "loss": 0.4328,
      "step": 257
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.06846682414537354,
      "learning_rate": 0.00016810158587867973,
      "loss": 0.418,
      "step": 258
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.0689288634381005,
      "learning_rate": 0.00016784837946731148,
      "loss": 0.4209,
      "step": 259
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.06820042044945746,
      "learning_rate": 0.00016759436441447545,
      "loss": 0.3902,
      "step": 260
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.07119552472188734,
      "learning_rate": 0.0001673395437476146,
      "loss": 0.4306,
      "step": 261
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.06555865871255981,
      "learning_rate": 0.00016708392050377363,
      "loss": 0.3975,
      "step": 262
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.0712809166108178,
      "learning_rate": 0.0001668274977295626,
      "loss": 0.3934,
      "step": 263
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.07147432449436239,
      "learning_rate": 0.00016657027848112062,
      "loss": 0.3742,
      "step": 264
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.06455739935278262,
      "learning_rate": 0.00016631226582407952,
      "loss": 0.4168,
      "step": 265
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.06793873318686483,
      "learning_rate": 0.00016605346283352727,
      "loss": 0.4116,
      "step": 266
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.058261601463606476,
      "learning_rate": 0.00016579387259397127,
      "loss": 0.3845,
      "step": 267
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.062017087628894275,
      "learning_rate": 0.00016553349819930165,
      "loss": 0.3933,
      "step": 268
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.059279362535743535,
      "learning_rate": 0.00016527234275275445,
      "loss": 0.3607,
      "step": 269
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.0615298158124674,
      "learning_rate": 0.00016501040936687443,
      "loss": 0.3978,
      "step": 270
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.05968002667313829,
      "learning_rate": 0.00016474770116347824,
      "loss": 0.4241,
      "step": 271
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.06836235857310884,
      "learning_rate": 0.00016448422127361706,
      "loss": 0.4213,
      "step": 272
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.06328807134715098,
      "learning_rate": 0.00016421997283753927,
      "loss": 0.3835,
      "step": 273
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.07185050583270135,
      "learning_rate": 0.00016395495900465304,
      "loss": 0.4397,
      "step": 274
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.06731895516948408,
      "learning_rate": 0.00016368918293348892,
      "loss": 0.4266,
      "step": 275
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.06154277474915469,
      "learning_rate": 0.000163422647791662,
      "loss": 0.405,
      "step": 276
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.060450974009086104,
      "learning_rate": 0.00016315535675583424,
      "loss": 0.4149,
      "step": 277
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.0607120928467259,
      "learning_rate": 0.00016288731301167668,
      "loss": 0.42,
      "step": 278
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.06605542298126882,
      "learning_rate": 0.00016261851975383137,
      "loss": 0.4092,
      "step": 279
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.06717022241182037,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.4373,
      "step": 280
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.06027581892234991,
      "learning_rate": 0.00016207869752027246,
      "loss": 0.3889,
      "step": 281
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.06756360223208042,
      "learning_rate": 0.00016180767497835503,
      "loss": 0.411,
      "step": 282
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.062275969305366226,
      "learning_rate": 0.00016153591579026546,
      "loss": 0.4146,
      "step": 283
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.06405007529726114,
      "learning_rate": 0.00016126342319492784,
      "loss": 0.3982,
      "step": 284
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.06859548867939594,
      "learning_rate": 0.00016099020044000727,
      "loss": 0.3841,
      "step": 285
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.06040247687681776,
      "learning_rate": 0.00016071625078187114,
      "loss": 0.4261,
      "step": 286
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.0705993351573918,
      "learning_rate": 0.00016044157748555026,
      "loss": 0.4264,
      "step": 287
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.0728951497630979,
      "learning_rate": 0.00016016618382470012,
      "loss": 0.4225,
      "step": 288
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.058326948226576664,
      "learning_rate": 0.00015989007308156173,
      "loss": 0.3817,
      "step": 289
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.06467973723572644,
      "learning_rate": 0.00015961324854692254,
      "loss": 0.4132,
      "step": 290
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.0650952066772671,
      "learning_rate": 0.0001593357135200773,
      "loss": 0.4185,
      "step": 291
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.06768263235822244,
      "learning_rate": 0.0001590574713087885,
      "loss": 0.4362,
      "step": 292
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.05967945902895899,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.3907,
      "step": 293
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.05879444877054761,
      "learning_rate": 0.00015849887860603374,
      "loss": 0.398,
      "step": 294
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.06052224942840143,
      "learning_rate": 0.00015821853477207708,
      "loss": 0.3788,
      "step": 295
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.058292067258336945,
      "learning_rate": 0.00015793749706861636,
      "loss": 0.3658,
      "step": 296
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.06616138091865216,
      "learning_rate": 0.00015765576884516031,
      "loss": 0.4136,
      "step": 297
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.06466816301584516,
      "learning_rate": 0.00015737335345944757,
      "loss": 0.3972,
      "step": 298
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.06889146736527235,
      "learning_rate": 0.00015709025427740661,
      "loss": 0.4038,
      "step": 299
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.07028354273665399,
      "learning_rate": 0.00015680647467311557,
      "loss": 0.4375,
      "step": 300
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.06913117274097347,
      "learning_rate": 0.00015652201802876227,
      "loss": 0.4067,
      "step": 301
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.06933114545676364,
      "learning_rate": 0.00015623688773460357,
      "loss": 0.3561,
      "step": 302
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.0732735312469693,
      "learning_rate": 0.0001559510871889252,
      "loss": 0.4192,
      "step": 303
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.06095351289998777,
      "learning_rate": 0.00015566461979800122,
      "loss": 0.4002,
      "step": 304
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.06279122778820988,
      "learning_rate": 0.0001553774889760533,
      "loss": 0.4052,
      "step": 305
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.06346871620982147,
      "learning_rate": 0.00015508969814521025,
      "loss": 0.4115,
      "step": 306
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.06265655296923098,
      "learning_rate": 0.00015480125073546704,
      "loss": 0.4103,
      "step": 307
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.06650336261140556,
      "learning_rate": 0.00015451215018464387,
      "loss": 0.4208,
      "step": 308
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.062225515787237784,
      "learning_rate": 0.00015422239993834552,
      "loss": 0.3965,
      "step": 309
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0705406540443855,
      "learning_rate": 0.00015393200344991995,
      "loss": 0.4105,
      "step": 310
    }
  ],
  "logging_steps": 1,
  "max_steps": 930,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 310,
  "total_flos": 1.6990690477500006e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}