{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 119,
  "global_step": 1425,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.434104859828949,
      "learning_rate": 2e-05,
      "loss": 0.8629,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 0.9369699358940125,
      "eval_runtime": 61.2717,
      "eval_samples_per_second": 1.632,
      "eval_steps_per_second": 1.632,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.517804741859436,
      "learning_rate": 4e-05,
      "loss": 0.9794,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.3174158334732056,
      "learning_rate": 6e-05,
      "loss": 1.5473,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.6236504912376404,
      "learning_rate": 8e-05,
      "loss": 0.6592,
      "step": 4
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.49080607295036316,
      "learning_rate": 0.0001,
      "loss": 1.1104,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.43938764929771423,
      "learning_rate": 0.00012,
      "loss": 0.9446,
      "step": 6
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8905380368232727,
      "learning_rate": 0.00014,
      "loss": 0.6719,
      "step": 7
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.9044575095176697,
      "learning_rate": 0.00016,
      "loss": 0.6471,
      "step": 8
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.541214108467102,
      "learning_rate": 0.00018,
      "loss": 0.8339,
      "step": 9
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.075484275817871,
      "learning_rate": 0.0002,
      "loss": 0.9616,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.3413633406162262,
      "learning_rate": 0.0001999998618515421,
      "loss": 0.8251,
      "step": 11
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.7642049193382263,
      "learning_rate": 0.00019999944740655014,
      "loss": 1.3883,
      "step": 12
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.5759286284446716,
      "learning_rate": 0.00019999875666616918,
      "loss": 0.9162,
      "step": 13
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.16646409034729,
      "learning_rate": 0.00019999778963230775,
      "loss": 1.1735,
      "step": 14
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.5447037220001221,
      "learning_rate": 0.0001999965463076377,
      "loss": 1.2769,
      "step": 15
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.510498046875,
      "learning_rate": 0.00019999502669559432,
      "loss": 1.1439,
      "step": 16
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.514502227306366,
      "learning_rate": 0.00019999323080037624,
      "loss": 0.9929,
      "step": 17
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.2014903873205185,
      "learning_rate": 0.00019999115862694546,
      "loss": 0.6706,
      "step": 18
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.6941856741905212,
      "learning_rate": 0.00019998881018102737,
      "loss": 0.7576,
      "step": 19
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.29424500465393066,
      "learning_rate": 0.00019998618546911056,
      "loss": 1.5048,
      "step": 20
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.431168556213379,
      "learning_rate": 0.00019998328449844714,
      "loss": 0.761,
      "step": 21
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.672117233276367,
      "learning_rate": 0.00019998010727705236,
      "loss": 0.9434,
      "step": 22
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.40351876616477966,
      "learning_rate": 0.00019997665381370477,
      "loss": 1.2708,
      "step": 23
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.36313024163246155,
      "learning_rate": 0.00019997292411794618,
      "loss": 0.6931,
      "step": 24
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.7412884831428528,
      "learning_rate": 0.00019996891820008164,
      "loss": 0.827,
      "step": 25
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.7299063205718994,
      "learning_rate": 0.00019996463607117935,
      "loss": 0.7135,
      "step": 26
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.5188469290733337,
      "learning_rate": 0.00019996007774307075,
      "loss": 0.574,
      "step": 27
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.23084047436714172,
      "learning_rate": 0.00019995524322835034,
      "loss": 1.0736,
      "step": 28
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.7209138870239258,
      "learning_rate": 0.00019995013254037574,
      "loss": 0.9087,
      "step": 29
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.2266876697540283,
      "learning_rate": 0.00019994474569326757,
      "loss": 1.2464,
      "step": 30
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.6613232493400574,
      "learning_rate": 0.0001999390827019096,
      "loss": 0.9568,
      "step": 31
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.0048911571502686,
      "learning_rate": 0.00019993314358194843,
      "loss": 1.1935,
      "step": 32
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.9797032475471497,
      "learning_rate": 0.00019992692834979372,
      "loss": 1.1969,
      "step": 33
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.4784688353538513,
      "learning_rate": 0.00019992043702261793,
      "loss": 0.8674,
      "step": 34
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.863600015640259,
      "learning_rate": 0.00019991366961835642,
      "loss": 1.3276,
      "step": 35
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.4809297025203705,
      "learning_rate": 0.0001999066261557073,
      "loss": 1.0116,
      "step": 36
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.6229730844497681,
      "learning_rate": 0.00019989930665413147,
      "loss": 1.2794,
      "step": 37
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.5807106494903564,
      "learning_rate": 0.0001998917111338525,
      "loss": 1.0074,
      "step": 38
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.5811257362365723,
      "learning_rate": 0.00019988383961585645,
      "loss": 1.2491,
      "step": 39
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.46693727374076843,
      "learning_rate": 0.00019987569212189224,
      "loss": 0.8432,
      "step": 40
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.9792713522911072,
      "learning_rate": 0.00019986726867447107,
      "loss": 0.8716,
      "step": 41
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.3240562081336975,
      "learning_rate": 0.00019985856929686667,
      "loss": 0.9934,
      "step": 42
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.7358172535896301,
      "learning_rate": 0.0001998495940131152,
      "loss": 0.7247,
      "step": 43
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.40497535467147827,
      "learning_rate": 0.00019984034284801502,
      "loss": 0.8262,
      "step": 44
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.36835265159606934,
      "learning_rate": 0.00019983081582712685,
      "loss": 1.0898,
      "step": 45
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.7027626633644104,
      "learning_rate": 0.0001998210129767735,
      "loss": 1.2949,
      "step": 46
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.35624387860298157,
      "learning_rate": 0.00019981093432404006,
      "loss": 0.9734,
      "step": 47
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.4896808862686157,
      "learning_rate": 0.00019980057989677345,
      "loss": 1.2297,
      "step": 48
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.9656649827957153,
      "learning_rate": 0.00019978994972358265,
      "loss": 0.8358,
      "step": 49
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.644644021987915,
      "learning_rate": 0.0001997790438338385,
      "loss": 0.7373,
      "step": 50
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.0634011030197144,
      "learning_rate": 0.00019976786225767365,
      "loss": 1.3792,
      "step": 51
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.9041422605514526,
      "learning_rate": 0.00019975640502598244,
      "loss": 0.856,
      "step": 52
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5682844519615173,
      "learning_rate": 0.00019974467217042085,
      "loss": 0.6686,
      "step": 53
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.7197520136833191,
      "learning_rate": 0.00019973266372340639,
      "loss": 0.6806,
      "step": 54
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.2542258501052856,
      "learning_rate": 0.00019972037971811802,
      "loss": 1.353,
      "step": 55
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.6802650094032288,
      "learning_rate": 0.0001997078201884961,
      "loss": 1.0014,
      "step": 56
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.4886693060398102,
      "learning_rate": 0.0001996949851692422,
      "loss": 0.8613,
      "step": 57
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.0226856470108032,
      "learning_rate": 0.0001996818746958191,
      "loss": 1.0443,
      "step": 58
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.5514834523200989,
      "learning_rate": 0.00019966848880445062,
      "loss": 0.8816,
      "step": 59
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.4890052378177643,
      "learning_rate": 0.00019965482753212156,
      "loss": 0.8541,
      "step": 60
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.9011398553848267,
      "learning_rate": 0.0001996408909165776,
      "loss": 1.1158,
      "step": 61
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.7809276580810547,
      "learning_rate": 0.00019962667899632518,
      "loss": 0.6702,
      "step": 62
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.604097843170166,
      "learning_rate": 0.00019961219181063142,
      "loss": 1.1875,
      "step": 63
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.9003333449363708,
      "learning_rate": 0.00019959742939952392,
      "loss": 1.2126,
      "step": 64
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.59239661693573,
      "learning_rate": 0.0001995823918037908,
      "loss": 1.1083,
      "step": 65
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.6981655955314636,
      "learning_rate": 0.00019956707906498044,
      "loss": 0.9634,
      "step": 66
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.4635857045650482,
      "learning_rate": 0.00019955149122540152,
      "loss": 1.0345,
      "step": 67
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.35098958015441895,
      "learning_rate": 0.00019953562832812272,
      "loss": 0.8871,
      "step": 68
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.4510989189147949,
      "learning_rate": 0.00019951949041697274,
      "loss": 0.6967,
      "step": 69
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.39661434292793274,
      "learning_rate": 0.00019950307753654017,
      "loss": 1.0786,
      "step": 70
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.5836047530174255,
      "learning_rate": 0.00019948638973217323,
      "loss": 0.9265,
      "step": 71
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.4589115381240845,
      "learning_rate": 0.00019946942704997982,
      "loss": 0.6476,
      "step": 72
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.4495834410190582,
      "learning_rate": 0.00019945218953682734,
      "loss": 0.8693,
      "step": 73
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.35905730724334717,
      "learning_rate": 0.00019943467724034252,
      "loss": 1.0325,
      "step": 74
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.235016345977783,
      "learning_rate": 0.0001994168902089112,
      "loss": 1.3103,
      "step": 75
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.36725524067878723,
      "learning_rate": 0.00019939882849167852,
      "loss": 0.908,
      "step": 76
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.66635662317276,
      "learning_rate": 0.0001993804921385484,
      "loss": 0.682,
      "step": 77
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.121004819869995,
      "learning_rate": 0.0001993618812001836,
      "loss": 0.8462,
      "step": 78
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.44895172119140625,
      "learning_rate": 0.00019934299572800556,
      "loss": 0.9625,
      "step": 79
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.5769445300102234,
      "learning_rate": 0.00019932383577419432,
      "loss": 0.7278,
      "step": 80
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.3807710111141205,
      "learning_rate": 0.00019930440139168817,
      "loss": 0.657,
      "step": 81
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.212838813662529,
      "learning_rate": 0.00019928469263418374,
      "loss": 0.3094,
      "step": 82
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.8039274215698242,
      "learning_rate": 0.0001992647095561357,
      "loss": 0.8898,
      "step": 83
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.7184070348739624,
      "learning_rate": 0.00019924445221275675,
      "loss": 0.8613,
      "step": 84
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.4697589874267578,
      "learning_rate": 0.00019922392066001722,
      "loss": 0.9533,
      "step": 85
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.7024903297424316,
      "learning_rate": 0.00019920311495464518,
      "loss": 0.7188,
      "step": 86
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.5008754730224609,
      "learning_rate": 0.00019918203515412617,
      "loss": 0.8329,
      "step": 87
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.6406499743461609,
      "learning_rate": 0.00019916068131670302,
      "loss": 1.4259,
      "step": 88
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.39489614963531494,
      "learning_rate": 0.00019913905350137573,
      "loss": 0.5831,
      "step": 89
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.7018424272537231,
      "learning_rate": 0.0001991171517679013,
      "loss": 0.9808,
      "step": 90
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.5011338591575623,
      "learning_rate": 0.00019909497617679348,
      "loss": 0.6806,
      "step": 91
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.2412053793668747,
      "learning_rate": 0.0001990725267893228,
      "loss": 1.0299,
      "step": 92
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.4145759046077728,
      "learning_rate": 0.00019904980366751624,
      "loss": 1.4344,
      "step": 93
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.5789082050323486,
      "learning_rate": 0.00019902680687415705,
      "loss": 0.4662,
      "step": 94
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.28986847400665283,
      "learning_rate": 0.00019900353647278466,
      "loss": 1.296,
      "step": 95
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.33722007274627686,
      "learning_rate": 0.00019897999252769448,
      "loss": 0.8011,
      "step": 96
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.6796722412109375,
      "learning_rate": 0.00019895617510393772,
      "loss": 0.972,
      "step": 97
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5858548879623413,
      "learning_rate": 0.00019893208426732115,
      "loss": 1.0073,
      "step": 98
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5766484141349792,
      "learning_rate": 0.00019890772008440704,
      "loss": 0.7884,
      "step": 99
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.37647876143455505,
      "learning_rate": 0.00019888308262251285,
      "loss": 0.6407,
      "step": 100
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.5475112199783325,
      "learning_rate": 0.00019885817194971117,
      "loss": 1.1401,
      "step": 101
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1082801818847656,
      "learning_rate": 0.00019883298813482938,
      "loss": 1.392,
      "step": 102
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.3952051103115082,
      "learning_rate": 0.00019880753124744963,
      "loss": 1.0498,
      "step": 103
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.19289755821228027,
      "learning_rate": 0.00019878180135790845,
      "loss": 0.4145,
      "step": 104
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.5658400654792786,
      "learning_rate": 0.00019875579853729676,
      "loss": 1.0984,
      "step": 105
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.8976437449455261,
      "learning_rate": 0.00019872952285745959,
      "loss": 0.6919,
      "step": 106
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.5265024900436401,
      "learning_rate": 0.00019870297439099577,
      "loss": 1.2932,
      "step": 107
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.8367021083831787,
      "learning_rate": 0.00019867615321125795,
      "loss": 1.4497,
      "step": 108
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.5223955512046814,
      "learning_rate": 0.00019864905939235214,
      "loss": 1.0325,
      "step": 109
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.408779501914978,
      "learning_rate": 0.00019862169300913785,
      "loss": 0.9026,
      "step": 110
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.24817530810832977,
      "learning_rate": 0.00019859405413722746,
      "loss": 0.826,
      "step": 111
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.450430154800415,
      "learning_rate": 0.0001985661428529863,
      "loss": 0.9791,
      "step": 112
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.4882315993309021,
      "learning_rate": 0.0001985379592335325,
      "loss": 0.7889,
      "step": 113
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.42783451080322266,
      "learning_rate": 0.00019850950335673643,
      "loss": 1.1608,
      "step": 114
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.0337790250778198,
      "learning_rate": 0.00019848077530122083,
      "loss": 1.045,
      "step": 115
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.3064819872379303,
      "learning_rate": 0.00019845177514636042,
      "loss": 0.6474,
      "step": 116
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.29662173986434937,
      "learning_rate": 0.00019842250297228176,
      "loss": 0.9493,
      "step": 117
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.515562891960144,
      "learning_rate": 0.00019839295885986296,
      "loss": 1.0605,
      "step": 118
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.4514832496643066,
      "learning_rate": 0.0001983631428907335,
      "loss": 0.6917,
      "step": 119
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.8804921507835388,
      "eval_runtime": 61.5233,
      "eval_samples_per_second": 1.625,
      "eval_steps_per_second": 1.625,
      "step": 119
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.30757004022598267,
      "learning_rate": 0.00019833305514727395,
      "loss": 0.9722,
      "step": 120
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.5162855386734009,
      "learning_rate": 0.00019830269571261583,
      "loss": 1.2197,
      "step": 121
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.5095639824867249,
      "learning_rate": 0.00019827206467064133,
      "loss": 0.8676,
      "step": 122
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.4804045557975769,
      "learning_rate": 0.00019824116210598306,
      "loss": 0.8565,
      "step": 123
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.28008362650871277,
      "learning_rate": 0.0001982099881040239,
      "loss": 0.9001,
      "step": 124
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.6209085583686829,
      "learning_rate": 0.0001981785427508966,
      "loss": 0.7188,
      "step": 125
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.32877278327941895,
      "learning_rate": 0.0001981468261334837,
      "loss": 0.6749,
      "step": 126
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.4256601631641388,
      "learning_rate": 0.00019811483833941728,
      "loss": 0.8086,
      "step": 127
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.1572288274765015,
      "learning_rate": 0.0001980825794570786,
      "loss": 0.8554,
      "step": 128
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.4987819194793701,
      "learning_rate": 0.00019805004957559793,
      "loss": 0.6999,
      "step": 129
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.6852537393569946,
      "learning_rate": 0.00019801724878485438,
      "loss": 0.8759,
      "step": 130
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.7970736622810364,
      "learning_rate": 0.00019798417717547552,
      "loss": 0.7471,
      "step": 131
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5638220310211182,
      "learning_rate": 0.00019795083483883715,
      "loss": 1.0391,
      "step": 132
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5482009649276733,
      "learning_rate": 0.00019791722186706317,
      "loss": 0.8363,
      "step": 133
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.23791633546352386,
      "learning_rate": 0.0001978833383530251,
      "loss": 0.725,
      "step": 134
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5339345335960388,
      "learning_rate": 0.00019784918439034216,
      "loss": 0.9828,
      "step": 135
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.24769064784049988,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.9496,
      "step": 136
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.46634215116500854,
      "learning_rate": 0.00019778006549725375,
      "loss": 1.0973,
      "step": 137
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.8007522821426392,
      "learning_rate": 0.00019774510075782172,
      "loss": 0.6847,
      "step": 138
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.5393804907798767,
      "learning_rate": 0.00019770986595169096,
      "loss": 0.6461,
      "step": 139
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.2891620695590973,
      "learning_rate": 0.00019767436117621413,
      "loss": 0.2937,
      "step": 140
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.9463545680046082,
      "learning_rate": 0.0001976385865294899,
      "loss": 0.4934,
      "step": 141
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.25647807121276855,
      "learning_rate": 0.00019760254211036244,
      "loss": 0.7446,
      "step": 142
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.49435535073280334,
      "learning_rate": 0.00019756622801842143,
      "loss": 0.3544,
      "step": 143
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.7826042175292969,
      "learning_rate": 0.00019752964435400155,
      "loss": 0.6972,
      "step": 144
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.7160178422927856,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.9655,
      "step": 145
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.3925221264362335,
      "learning_rate": 0.00019745566871278794,
      "loss": 0.9041,
      "step": 146
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.5669321417808533,
      "learning_rate": 0.0001974182769403866,
      "loss": 0.9093,
      "step": 147
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.5025343298912048,
      "learning_rate": 0.00019738061600429064,
      "loss": 0.6226,
      "step": 148
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.1127972602844238,
      "learning_rate": 0.0001973426860085561,
      "loss": 0.7431,
      "step": 149
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.4064362049102783,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.8444,
      "step": 150
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9272475242614746,
      "learning_rate": 0.00019726601925811204,
      "loss": 0.836,
      "step": 151
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.6594715118408203,
      "learning_rate": 0.00019722728271523034,
      "loss": 0.9031,
      "step": 152
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9399688839912415,
      "learning_rate": 0.00019718827753636522,
      "loss": 0.7959,
      "step": 153
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.4452652633190155,
      "learning_rate": 0.00019714900382928675,
      "loss": 0.5638,
      "step": 154
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.47481146454811096,
      "learning_rate": 0.000197109461702507,
      "loss": 0.8291,
      "step": 155
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.1962246149778366,
      "learning_rate": 0.00019706965126527963,
      "loss": 0.7894,
      "step": 156
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.366571307182312,
      "learning_rate": 0.00019702957262759965,
      "loss": 1.1808,
      "step": 157
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.3261445760726929,
      "learning_rate": 0.00019698922590020312,
      "loss": 0.8769,
      "step": 158
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.5637160539627075,
      "learning_rate": 0.00019694861119456679,
      "loss": 0.882,
      "step": 159
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.4508800208568573,
      "learning_rate": 0.0001969077286229078,
      "loss": 1.2723,
      "step": 160
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.41292956471443176,
      "learning_rate": 0.0001968665782981835,
      "loss": 0.7919,
      "step": 161
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.6105634570121765,
      "learning_rate": 0.00019682516033409092,
      "loss": 1.0901,
      "step": 162
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.6460319757461548,
      "learning_rate": 0.00019678347484506669,
      "loss": 1.0425,
      "step": 163
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.8627430200576782,
      "learning_rate": 0.00019674152194628638,
      "loss": 0.8019,
      "step": 164
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.3218872547149658,
      "learning_rate": 0.00019669930175366472,
      "loss": 0.8345,
      "step": 165
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.6773053407669067,
      "learning_rate": 0.00019665681438385473,
      "loss": 1.3567,
      "step": 166
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.3802971839904785,
      "learning_rate": 0.0001966140599542477,
      "loss": 0.7315,
      "step": 167
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.9038891196250916,
      "learning_rate": 0.0001965710385829728,
      "loss": 0.6807,
      "step": 168
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.7831525802612305,
      "learning_rate": 0.00019652775038889674,
      "loss": 1.2796,
      "step": 169
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.3705346882343292,
      "learning_rate": 0.00019648419549162348,
      "loss": 0.8275,
      "step": 170
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.7794845104217529,
      "learning_rate": 0.0001964403740114939,
      "loss": 0.7539,
      "step": 171
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.2621815800666809,
      "learning_rate": 0.00019639628606958533,
      "loss": 0.976,
      "step": 172
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.6929745674133301,
      "learning_rate": 0.00019635193178771143,
      "loss": 0.6198,
      "step": 173
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.543230414390564,
      "learning_rate": 0.0001963073112884217,
      "loss": 0.9319,
      "step": 174
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.6732174158096313,
      "learning_rate": 0.0001962624246950012,
      "loss": 0.804,
      "step": 175
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.25452062487602234,
      "learning_rate": 0.00019621727213147027,
      "loss": 0.7632,
      "step": 176
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.6591973304748535,
      "learning_rate": 0.00019617185372258392,
      "loss": 0.9745,
      "step": 177
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.6275454163551331,
      "learning_rate": 0.0001961261695938319,
      "loss": 0.3411,
      "step": 178
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.6691128611564636,
      "learning_rate": 0.00019608021987143804,
      "loss": 0.9564,
      "step": 179
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.3190310299396515,
      "learning_rate": 0.00019603400468235998,
      "loss": 1.3002,
      "step": 180
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.4648153781890869,
      "learning_rate": 0.0001959875241542889,
      "loss": 0.9507,
      "step": 181
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.5921639800071716,
      "learning_rate": 0.00019594077841564907,
      "loss": 0.9397,
      "step": 182
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5769446492195129,
      "learning_rate": 0.00019589376759559745,
      "loss": 0.9958,
      "step": 183
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.8454503417015076,
      "learning_rate": 0.00019584649182402357,
      "loss": 1.189,
      "step": 184
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.2865101099014282,
      "learning_rate": 0.0001957989512315489,
      "loss": 0.6747,
      "step": 185
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.3642055094242096,
      "learning_rate": 0.0001957511459495266,
      "loss": 0.5196,
      "step": 186
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.4965610206127167,
      "learning_rate": 0.00019570307611004124,
      "loss": 0.9448,
      "step": 187
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5694214105606079,
      "learning_rate": 0.00019565474184590826,
      "loss": 0.868,
      "step": 188
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6402484774589539,
      "learning_rate": 0.00019560614329067378,
      "loss": 0.8872,
      "step": 189
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.37722048163414,
      "learning_rate": 0.0001955572805786141,
      "loss": 0.9253,
      "step": 190
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.9157966375350952,
      "learning_rate": 0.00019550815384473534,
      "loss": 1.6508,
      "step": 191
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.33376675844192505,
      "learning_rate": 0.0001954587632247732,
      "loss": 0.9109,
      "step": 192
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.2680880129337311,
      "learning_rate": 0.00019540910885519242,
      "loss": 1.0693,
      "step": 193
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.7726811766624451,
      "learning_rate": 0.00019535919087318652,
      "loss": 0.9574,
      "step": 194
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.8604207634925842,
      "learning_rate": 0.0001953090094166773,
      "loss": 0.9475,
      "step": 195
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.3954675197601318,
      "learning_rate": 0.0001952585646243146,
      "loss": 1.5094,
      "step": 196
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.39931145310401917,
      "learning_rate": 0.00019520785663547586,
      "loss": 0.9915,
      "step": 197
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.772156298160553,
      "learning_rate": 0.00019515688559026563,
      "loss": 1.4155,
      "step": 198
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.48633861541748047,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.9607,
      "step": 199
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.4661516845226288,
      "learning_rate": 0.0001950541548947829,
      "loss": 1.0283,
      "step": 200
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.8846752047538757,
      "learning_rate": 0.00019500239552835215,
      "loss": 0.756,
      "step": 201
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.9870714545249939,
      "learning_rate": 0.00019495037367323262,
      "loss": 0.7688,
      "step": 202
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.7435501217842102,
      "learning_rate": 0.00019489808947315915,
      "loss": 0.4752,
      "step": 203
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.6509325504302979,
      "learning_rate": 0.0001948455430725913,
      "loss": 0.9053,
      "step": 204
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.30190637707710266,
      "learning_rate": 0.0001947927346167132,
      "loss": 0.9323,
      "step": 205
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.420055627822876,
      "learning_rate": 0.00019473966425143292,
      "loss": 0.6446,
      "step": 206
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.49513018131256104,
      "learning_rate": 0.00019468633212338233,
      "loss": 0.9022,
      "step": 207
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.4812709391117096,
      "learning_rate": 0.00019463273837991643,
      "loss": 0.6835,
      "step": 208
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.2101246416568756,
      "learning_rate": 0.00019457888316911306,
      "loss": 0.5991,
      "step": 209
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.3539298176765442,
      "learning_rate": 0.00019452476663977248,
      "loss": 0.7323,
      "step": 210
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.29954612255096436,
      "learning_rate": 0.00019447038894141705,
      "loss": 0.6868,
      "step": 211
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.4053567349910736,
      "learning_rate": 0.00019441575022429065,
      "loss": 1.0805,
      "step": 212
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.7733739614486694,
      "learning_rate": 0.00019436085063935835,
      "loss": 1.3524,
      "step": 213
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.6096423864364624,
      "learning_rate": 0.00019430569033830605,
      "loss": 1.0183,
      "step": 214
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.1940584182739258,
      "learning_rate": 0.00019425026947353992,
      "loss": 1.0919,
      "step": 215
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.4030895233154297,
      "learning_rate": 0.00019419458819818614,
      "loss": 0.7642,
      "step": 216
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.4116997718811035,
      "learning_rate": 0.00019413864666609034,
      "loss": 0.6112,
      "step": 217
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.4545953869819641,
      "learning_rate": 0.00019408244503181724,
      "loss": 0.7328,
      "step": 218
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.9334838390350342,
      "learning_rate": 0.0001940259834506502,
      "loss": 1.0518,
      "step": 219
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.2695348858833313,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.987,
      "step": 220
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.3967281579971313,
      "learning_rate": 0.00019391228107235858,
      "loss": 1.0819,
      "step": 221
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.0220236778259277,
      "learning_rate": 0.00019385504058939024,
      "loss": 0.9621,
      "step": 222
    },
    {
      "epoch": 0.47,
      "grad_norm": 2.5694682598114014,
      "learning_rate": 0.00019379754078783937,
      "loss": 1.0647,
      "step": 223
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.6181725263595581,
      "learning_rate": 0.00019373978182657625,
      "loss": 1.0991,
      "step": 224
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.508532702922821,
      "learning_rate": 0.0001936817638651871,
      "loss": 1.0276,
      "step": 225
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.3763074278831482,
      "learning_rate": 0.00019362348706397373,
      "loss": 0.7447,
      "step": 226
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.9533042311668396,
      "learning_rate": 0.00019356495158395315,
      "loss": 1.1979,
      "step": 227
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.43593689799308777,
      "learning_rate": 0.00019350615758685708,
      "loss": 1.0028,
      "step": 228
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.7646205425262451,
      "learning_rate": 0.00019344710523513156,
      "loss": 1.463,
      "step": 229
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.29402196407318115,
      "learning_rate": 0.00019338779469193639,
      "loss": 1.2726,
      "step": 230
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.5773300528526306,
      "learning_rate": 0.00019332822612114475,
      "loss": 0.4847,
      "step": 231
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.0580178499221802,
      "learning_rate": 0.00019326839968734279,
      "loss": 1.0639,
      "step": 232
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.6212771534919739,
      "learning_rate": 0.00019320831555582908,
      "loss": 0.7302,
      "step": 233
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.1953450441360474,
      "learning_rate": 0.00019314797389261424,
      "loss": 0.9873,
      "step": 234
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.856995940208435,
      "learning_rate": 0.00019308737486442045,
      "loss": 0.9573,
      "step": 235
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.36539939045906067,
      "learning_rate": 0.00019302651863868092,
      "loss": 0.6884,
      "step": 236
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.3269266188144684,
      "learning_rate": 0.0001929654053835395,
      "loss": 0.9445,
      "step": 237
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.46403074264526367,
      "learning_rate": 0.00019290403526785025,
      "loss": 0.9783,
      "step": 238
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.8782849311828613,
      "eval_runtime": 61.3598,
      "eval_samples_per_second": 1.63,
      "eval_steps_per_second": 1.63,
      "step": 238
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.6627680659294128,
      "learning_rate": 0.00019284240846117697,
      "loss": 0.9527,
      "step": 239
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.866802990436554,
      "learning_rate": 0.00019278052513379255,
      "loss": 0.6096,
      "step": 240
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.5304962396621704,
      "learning_rate": 0.00019271838545667876,
      "loss": 0.8335,
      "step": 241
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.076063632965088,
      "learning_rate": 0.00019265598960152555,
      "loss": 1.3308,
      "step": 242
    },
    {
      "epoch": 0.51,
      "grad_norm": 2.491516351699829,
      "learning_rate": 0.00019259333774073083,
      "loss": 1.4458,
      "step": 243
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.3771064281463623,
      "learning_rate": 0.00019253043004739968,
      "loss": 1.4581,
      "step": 244
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.24413131177425385,
      "learning_rate": 0.00019246726669534415,
      "loss": 0.7537,
      "step": 245
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.02517831325531,
      "learning_rate": 0.00019240384785908265,
      "loss": 1.0646,
      "step": 246
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.4848421514034271,
      "learning_rate": 0.00019234017371383945,
      "loss": 0.6972,
      "step": 247
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.8870792388916016,
      "learning_rate": 0.00019227624443554425,
      "loss": 1.2114,
      "step": 248
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.5171313285827637,
      "learning_rate": 0.00019221206020083166,
      "loss": 0.7243,
      "step": 249
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.5975112915039062,
      "learning_rate": 0.00019214762118704076,
      "loss": 0.964,
      "step": 250
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.0921701192855835,
      "learning_rate": 0.0001920829275722146,
      "loss": 1.1413,
      "step": 251
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.6540035009384155,
      "learning_rate": 0.00019201797953509955,
      "loss": 0.9732,
      "step": 252
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.137863278388977,
      "learning_rate": 0.0001919527772551451,
      "loss": 1.3374,
      "step": 253
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.4139158725738525,
      "learning_rate": 0.00019188732091250307,
      "loss": 1.1147,
      "step": 254
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.5039550065994263,
      "learning_rate": 0.00019182161068802741,
      "loss": 0.7832,
      "step": 255
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.567670464515686,
      "learning_rate": 0.00019175564676327339,
      "loss": 0.6684,
      "step": 256
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.4372114837169647,
      "learning_rate": 0.0001916894293204973,
      "loss": 0.7285,
      "step": 257
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.4466225206851959,
      "learning_rate": 0.00019162295854265594,
      "loss": 0.5705,
      "step": 258
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.7975250482559204,
      "learning_rate": 0.00019155623461340594,
      "loss": 1.4155,
      "step": 259
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.6310514211654663,
      "learning_rate": 0.00019148925771710347,
      "loss": 0.7388,
      "step": 260
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5273220539093018,
      "learning_rate": 0.0001914220280388037,
      "loss": 0.9241,
      "step": 261
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.8354101181030273,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.8085,
      "step": 262
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.7362698316574097,
      "learning_rate": 0.00019128681107992415,
      "loss": 0.953,
      "step": 263
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5334580540657043,
      "learning_rate": 0.00019121882417294462,
      "loss": 0.4416,
      "step": 264
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.6351854205131531,
      "learning_rate": 0.00019115058523116733,
      "loss": 0.6414,
      "step": 265
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.28386977314949036,
      "learning_rate": 0.00019108209444313433,
      "loss": 1.0273,
      "step": 266
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5504246354103088,
      "learning_rate": 0.00019101335199808354,
      "loss": 1.1191,
      "step": 267
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.7449864149093628,
      "learning_rate": 0.00019094435808594823,
      "loss": 1.1073,
      "step": 268
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.6302490830421448,
      "learning_rate": 0.00019087511289735644,
      "loss": 1.2092,
      "step": 269
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.5618910789489746,
      "learning_rate": 0.0001908056166236305,
      "loss": 1.1966,
      "step": 270
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.46393775939941406,
      "learning_rate": 0.0001907358694567865,
      "loss": 0.7148,
      "step": 271
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.34640607237815857,
      "learning_rate": 0.00019066587158953366,
      "loss": 1.1297,
      "step": 272
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.3277580738067627,
      "learning_rate": 0.00019059562321527396,
      "loss": 1.0978,
      "step": 273
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.8730579018592834,
      "learning_rate": 0.0001905251245281015,
      "loss": 0.9732,
      "step": 274
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.32950034737586975,
      "learning_rate": 0.00019045437572280194,
      "loss": 1.0795,
      "step": 275
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.48170116543769836,
      "learning_rate": 0.00019038337699485208,
      "loss": 0.8124,
      "step": 276
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.858323335647583,
      "learning_rate": 0.00019031212854041918,
      "loss": 0.813,
      "step": 277
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.9366027116775513,
      "learning_rate": 0.00019024063055636057,
      "loss": 1.5074,
      "step": 278
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.4378308653831482,
      "learning_rate": 0.00019016888324022296,
      "loss": 0.8387,
      "step": 279
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.5781106948852539,
      "learning_rate": 0.0001900968867902419,
      "loss": 1.0496,
      "step": 280
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.834186851978302,
      "learning_rate": 0.00019002464140534147,
      "loss": 1.2684,
      "step": 281
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.752008855342865,
      "learning_rate": 0.00018995214728513343,
      "loss": 1.069,
      "step": 282
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3941871225833893,
      "learning_rate": 0.0001898794046299167,
      "loss": 0.942,
      "step": 283
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4069131314754486,
      "learning_rate": 0.0001898064136406771,
      "loss": 0.7116,
      "step": 284
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.6478765606880188,
      "learning_rate": 0.00018973317451908642,
      "loss": 0.9494,
      "step": 285
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.8658535480499268,
      "learning_rate": 0.0001896596874675021,
      "loss": 0.7592,
      "step": 286
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.8622011542320251,
      "learning_rate": 0.0001895859526889666,
      "loss": 0.9392,
      "step": 287
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.8127020001411438,
      "learning_rate": 0.00018951197038720688,
      "loss": 1.3309,
      "step": 288
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.5042945146560669,
      "learning_rate": 0.0001894377407666337,
      "loss": 0.7607,
      "step": 289
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.7252426743507385,
      "learning_rate": 0.00018936326403234125,
      "loss": 1.1221,
      "step": 290
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.7334456443786621,
      "learning_rate": 0.0001892885403901064,
      "loss": 0.4738,
      "step": 291
    },
    {
      "epoch": 0.61,
      "grad_norm": 2.6204662322998047,
      "learning_rate": 0.00018921357004638835,
      "loss": 1.2511,
      "step": 292
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.5708286762237549,
      "learning_rate": 0.00018913835320832778,
      "loss": 1.0887,
      "step": 293
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.0324314832687378,
      "learning_rate": 0.00018906289008374655,
      "loss": 1.1019,
      "step": 294
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.3663407862186432,
      "learning_rate": 0.0001889871808811469,
      "loss": 1.0333,
      "step": 295
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.7219849824905396,
      "learning_rate": 0.00018891122580971098,
      "loss": 0.858,
      "step": 296
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.7850363850593567,
      "learning_rate": 0.00018883502507930042,
      "loss": 0.9503,
      "step": 297
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.28012195229530334,
      "learning_rate": 0.00018875857890045543,
      "loss": 0.8068,
      "step": 298
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.7574068307876587,
      "learning_rate": 0.00018868188748439444,
      "loss": 0.7557,
      "step": 299
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.9131019711494446,
      "learning_rate": 0.00018860495104301345,
      "loss": 1.1462,
      "step": 300
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.24085545539855957,
      "learning_rate": 0.00018852776978888551,
      "loss": 0.8286,
      "step": 301
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.4502617418766022,
      "learning_rate": 0.00018845034393526005,
      "loss": 1.0052,
      "step": 302
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.7258254289627075,
      "learning_rate": 0.00018837267369606228,
      "loss": 0.9703,
      "step": 303
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.6078888773918152,
      "learning_rate": 0.00018829475928589271,
      "loss": 0.8479,
      "step": 304
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5912296772003174,
      "learning_rate": 0.00018821660092002641,
      "loss": 1.0336,
      "step": 305
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3440995216369629,
      "learning_rate": 0.0001881381988144126,
      "loss": 0.7629,
      "step": 306
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5613306164741516,
      "learning_rate": 0.0001880595531856738,
      "loss": 1.0355,
      "step": 307
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5265874862670898,
      "learning_rate": 0.0001879806642511055,
      "loss": 0.9046,
      "step": 308
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.37300053238868713,
      "learning_rate": 0.0001879015322286754,
      "loss": 0.578,
      "step": 309
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.7948945164680481,
      "learning_rate": 0.00018782215733702286,
      "loss": 0.5693,
      "step": 310
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5222792625427246,
      "learning_rate": 0.0001877425397954582,
      "loss": 0.812,
      "step": 311
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.6407319903373718,
      "learning_rate": 0.00018766267982396224,
      "loss": 0.7317,
      "step": 312
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.36041396856307983,
      "learning_rate": 0.00018758257764318567,
      "loss": 0.3617,
      "step": 313
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.6465966105461121,
      "learning_rate": 0.00018750223347444828,
      "loss": 0.6037,
      "step": 314
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.4281207025051117,
      "learning_rate": 0.00018742164753973855,
      "loss": 0.5269,
      "step": 315
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.3671799898147583,
      "learning_rate": 0.00018734082006171299,
      "loss": 0.66,
      "step": 316
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.4369129240512848,
      "learning_rate": 0.00018725975126369535,
      "loss": 1.1395,
      "step": 317
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.4631548523902893,
      "learning_rate": 0.00018717844136967624,
      "loss": 0.7871,
      "step": 318
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.4736942946910858,
      "learning_rate": 0.00018709689060431242,
      "loss": 1.2983,
      "step": 319
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.7346480488777161,
      "learning_rate": 0.00018701509919292613,
      "loss": 0.9507,
      "step": 320
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.5298660397529602,
      "learning_rate": 0.00018693306736150444,
      "loss": 0.6621,
      "step": 321
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.5501769781112671,
      "learning_rate": 0.0001868507953366989,
      "loss": 0.6954,
      "step": 322
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.565510630607605,
      "learning_rate": 0.0001867682833458245,
      "loss": 1.2279,
      "step": 323
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.2679019570350647,
      "learning_rate": 0.00018668553161685933,
      "loss": 0.6207,
      "step": 324
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.0185893774032593,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.1179,
      "step": 325
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.400493323802948,
      "learning_rate": 0.00018651930985988036,
      "loss": 0.5947,
      "step": 326
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.7746186256408691,
      "learning_rate": 0.00018643584029113215,
      "loss": 1.0365,
      "step": 327
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.5792235136032104,
      "learning_rate": 0.0001863521319028231,
      "loss": 0.7102,
      "step": 328
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.35895833373069763,
      "learning_rate": 0.00018626818492623688,
      "loss": 0.5571,
      "step": 329
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.41158926486968994,
      "learning_rate": 0.0001861839995933164,
      "loss": 0.9009,
      "step": 330
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5845640301704407,
      "learning_rate": 0.00018609957613666315,
      "loss": 0.3317,
      "step": 331
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.4458400309085846,
      "learning_rate": 0.00018601491478953657,
      "loss": 1.0094,
      "step": 332
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.6415822505950928,
      "learning_rate": 0.00018593001578585326,
      "loss": 0.9772,
      "step": 333
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.616220474243164,
      "learning_rate": 0.00018584487936018661,
      "loss": 0.6879,
      "step": 334
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.4885902404785156,
      "learning_rate": 0.00018575950574776595,
      "loss": 0.9627,
      "step": 335
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.2818461060523987,
      "learning_rate": 0.0001856738951844759,
      "loss": 0.9156,
      "step": 336
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.2286068201065063,
      "learning_rate": 0.00018558804790685588,
      "loss": 2.6577,
      "step": 337
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.7086435556411743,
      "learning_rate": 0.00018550196415209914,
      "loss": 0.8172,
      "step": 338
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.0317937135696411,
      "learning_rate": 0.00018541564415805258,
      "loss": 1.3381,
      "step": 339
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.693418562412262,
      "learning_rate": 0.00018532908816321558,
      "loss": 1.1259,
      "step": 340
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.25714910030365,
      "learning_rate": 0.00018524229640673974,
      "loss": 0.7892,
      "step": 341
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.6042699813842773,
      "learning_rate": 0.00018515526912842796,
      "loss": 0.8982,
      "step": 342
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.3453720211982727,
      "learning_rate": 0.00018506800656873398,
      "loss": 0.9424,
      "step": 343
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.7436335682868958,
      "learning_rate": 0.0001849805089687615,
      "loss": 0.7121,
      "step": 344
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.8308970928192139,
      "learning_rate": 0.00018489277657026375,
      "loss": 1.1099,
      "step": 345
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.6892271637916565,
      "learning_rate": 0.0001848048096156426,
      "loss": 0.6814,
      "step": 346
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.30851200222969055,
      "learning_rate": 0.00018471660834794805,
      "loss": 0.283,
      "step": 347
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.2706887722015381,
      "learning_rate": 0.00018462817301087748,
      "loss": 0.6258,
      "step": 348
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.9876924157142639,
      "learning_rate": 0.00018453950384877504,
      "loss": 0.6983,
      "step": 349
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.3037252128124237,
      "learning_rate": 0.0001844506011066308,
      "loss": 0.9854,
      "step": 350
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.0091379880905151,
      "learning_rate": 0.00018436146503008035,
      "loss": 0.9871,
      "step": 351
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5219744443893433,
      "learning_rate": 0.0001842720958654039,
      "loss": 0.3771,
      "step": 352
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.49409008026123047,
      "learning_rate": 0.00018418249385952575,
      "loss": 1.0838,
      "step": 353
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.29014095664024353,
      "learning_rate": 0.00018409265926001343,
      "loss": 0.9922,
      "step": 354
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3307441771030426,
      "learning_rate": 0.00018400259231507717,
      "loss": 1.0458,
      "step": 355
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3356322646141052,
      "learning_rate": 0.00018391229327356916,
      "loss": 0.9891,
      "step": 356
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3707556426525116,
      "learning_rate": 0.00018382176238498286,
      "loss": 0.9578,
      "step": 357
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.8826732635498047,
      "eval_runtime": 61.8974,
      "eval_samples_per_second": 1.616,
      "eval_steps_per_second": 1.616,
      "step": 357
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.7507327198982239,
      "learning_rate": 0.00018373099989945236,
      "loss": 0.8916,
      "step": 358
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.3686985373497009,
      "learning_rate": 0.00018364000606775155,
      "loss": 0.9855,
      "step": 359
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.34240958094596863,
      "learning_rate": 0.00018354878114129367,
      "loss": 1.0874,
      "step": 360
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.2911188304424286,
      "learning_rate": 0.00018345732537213027,
      "loss": 1.2217,
      "step": 361
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.5415646433830261,
      "learning_rate": 0.0001833656390129509,
      "loss": 0.6675,
      "step": 362
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.36682239174842834,
      "learning_rate": 0.00018327372231708212,
      "loss": 0.8702,
      "step": 363
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5462591648101807,
      "learning_rate": 0.0001831815755384869,
      "loss": 0.9005,
      "step": 364
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5059930682182312,
      "learning_rate": 0.00018308919893176396,
      "loss": 0.8994,
      "step": 365
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.6344266533851624,
      "learning_rate": 0.00018299659275214706,
      "loss": 1.1571,
      "step": 366
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.2552272081375122,
      "learning_rate": 0.00018290375725550417,
      "loss": 1.2492,
      "step": 367
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.5543289184570312,
      "learning_rate": 0.00018281069269833692,
      "loss": 1.0141,
      "step": 368
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.3686586618423462,
      "learning_rate": 0.0001827173993377798,
      "loss": 0.8264,
      "step": 369
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.5549390912055969,
      "learning_rate": 0.0001826238774315995,
      "loss": 1.0753,
      "step": 370
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.8563418388366699,
      "learning_rate": 0.00018253012723819416,
      "loss": 0.4458,
      "step": 371
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.4292491376399994,
      "learning_rate": 0.00018243614901659264,
      "loss": 1.1994,
      "step": 372
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.37186571955680847,
      "learning_rate": 0.00018234194302645394,
      "loss": 0.9811,
      "step": 373
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.6655788421630859,
      "learning_rate": 0.00018224750952806624,
      "loss": 0.5048,
      "step": 374
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.7731723785400391,
      "learning_rate": 0.00018215284878234642,
      "loss": 0.9481,
      "step": 375
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.36243554949760437,
      "learning_rate": 0.00018205796105083915,
      "loss": 1.0048,
      "step": 376
    },
    {
      "epoch": 0.79,
      "grad_norm": 1.08484947681427,
      "learning_rate": 0.00018196284659571639,
      "loss": 1.0245,
      "step": 377
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.128653883934021,
      "learning_rate": 0.00018186750567977637,
      "loss": 0.9997,
      "step": 378
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6685619950294495,
      "learning_rate": 0.00018177193856644316,
      "loss": 1.3555,
      "step": 379
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.30426543951034546,
      "learning_rate": 0.00018167614551976567,
      "loss": 1.1209,
      "step": 380
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6189528107643127,
      "learning_rate": 0.00018158012680441723,
      "loss": 1.0321,
      "step": 381
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6775807738304138,
      "learning_rate": 0.00018148388268569453,
      "loss": 0.7826,
      "step": 382
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.4594517946243286,
      "learning_rate": 0.00018138741342951705,
      "loss": 0.6422,
      "step": 383
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.537011444568634,
      "learning_rate": 0.00018129071930242648,
      "loss": 0.9219,
      "step": 384
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.43772855401039124,
      "learning_rate": 0.00018119380057158568,
      "loss": 1.1737,
      "step": 385
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.7221130132675171,
      "learning_rate": 0.00018109665750477806,
      "loss": 0.8636,
      "step": 386
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.3437989354133606,
      "learning_rate": 0.00018099929037040694,
      "loss": 0.9238,
      "step": 387
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.47244492173194885,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.7715,
      "step": 388
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.7109631299972534,
      "learning_rate": 0.0001808038849756822,
      "loss": 0.4109,
      "step": 389
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.27005669474601746,
      "learning_rate": 0.00018070584725522762,
      "loss": 0.7158,
      "step": 390
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.4006590247154236,
      "learning_rate": 0.00018060758654700622,
      "loss": 1.0167,
      "step": 391
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.5627204179763794,
      "learning_rate": 0.00018050910312250931,
      "loss": 0.8679,
      "step": 392
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.5019241571426392,
      "learning_rate": 0.00018041039725384352,
      "loss": 0.9163,
      "step": 393
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.00431227684021,
      "learning_rate": 0.00018031146921373018,
      "loss": 0.676,
      "step": 394
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.7062071561813354,
      "learning_rate": 0.0001802123192755044,
      "loss": 1.2407,
      "step": 395
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.6554285287857056,
      "learning_rate": 0.00018011294771311435,
      "loss": 1.1187,
      "step": 396
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.08072829246521,
      "learning_rate": 0.00018001335480112064,
      "loss": 0.4878,
      "step": 397
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.3923906981945038,
      "learning_rate": 0.00017991354081469538,
      "loss": 0.7836,
      "step": 398
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.20446747541427612,
      "learning_rate": 0.0001798135060296216,
      "loss": 0.4597,
      "step": 399
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.5178759098052979,
      "learning_rate": 0.00017971325072229226,
      "loss": 1.7021,
      "step": 400
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.5159180164337158,
      "learning_rate": 0.0001796127751697097,
      "loss": 0.6037,
      "step": 401
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.9448319673538208,
      "learning_rate": 0.0001795120796494848,
      "loss": 0.8965,
      "step": 402
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.0035223960876465,
      "learning_rate": 0.00017941116443983613,
      "loss": 0.9786,
      "step": 403
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.26040011644363403,
      "learning_rate": 0.00017931002981958933,
      "loss": 0.8624,
      "step": 404
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.518144965171814,
      "learning_rate": 0.00017920867606817625,
      "loss": 1.0095,
      "step": 405
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5256940722465515,
      "learning_rate": 0.00017910710346563416,
      "loss": 0.7392,
      "step": 406
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.8347258567810059,
      "learning_rate": 0.000179005312292605,
      "loss": 0.8081,
      "step": 407
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.8221095204353333,
      "learning_rate": 0.00017890330283033468,
      "loss": 1.1406,
      "step": 408
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.8048923015594482,
      "learning_rate": 0.00017880107536067218,
      "loss": 1.4362,
      "step": 409
    },
    {
      "epoch": 0.86,
      "grad_norm": 1.9037342071533203,
      "learning_rate": 0.0001786986301660689,
      "loss": 1.2935,
      "step": 410
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.5521582961082458,
      "learning_rate": 0.00017859596752957768,
      "loss": 1.0742,
      "step": 411
    },
    {
      "epoch": 0.87,
      "grad_norm": 1.052284598350525,
      "learning_rate": 0.00017849308773485226,
      "loss": 0.7661,
      "step": 412
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.43000859022140503,
      "learning_rate": 0.00017838999106614632,
      "loss": 0.812,
      "step": 413
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.7804751396179199,
      "learning_rate": 0.00017828667780831278,
      "loss": 0.7995,
      "step": 414
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.5827552080154419,
      "learning_rate": 0.000178183148246803,
      "loss": 0.6489,
      "step": 415
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.3453142642974854,
      "learning_rate": 0.00017807940266766593,
      "loss": 0.7154,
      "step": 416
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.24924832582473755,
      "learning_rate": 0.00017797544135754744,
      "loss": 0.8061,
      "step": 417
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.4459979236125946,
      "learning_rate": 0.0001778712646036894,
      "loss": 1.1167,
      "step": 418
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.6095878481864929,
      "learning_rate": 0.000177766872693929,
      "loss": 0.8344,
      "step": 419
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.43662723898887634,
      "learning_rate": 0.00017766226591669785,
      "loss": 1.0373,
      "step": 420
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.8759774565696716,
      "learning_rate": 0.00017755744456102122,
      "loss": 1.0988,
      "step": 421
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.1800742149353027,
      "learning_rate": 0.00017745240891651735,
      "loss": 0.7385,
      "step": 422
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.5820197463035583,
      "learning_rate": 0.0001773471592733964,
      "loss": 0.9363,
      "step": 423
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.6128491759300232,
      "learning_rate": 0.00017724169592245995,
      "loss": 0.7762,
      "step": 424
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.5693449378013611,
      "learning_rate": 0.0001771360191551,
      "loss": 0.7526,
      "step": 425
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.7725418210029602,
      "learning_rate": 0.00017703012926329815,
      "loss": 0.7019,
      "step": 426
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.5068923234939575,
      "learning_rate": 0.0001769240265396249,
      "loss": 0.8308,
      "step": 427
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.34859699010849,
      "learning_rate": 0.0001768177112772388,
      "loss": 0.9593,
      "step": 428
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.34673023223876953,
      "learning_rate": 0.00017671118376988573,
      "loss": 1.0334,
      "step": 429
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.5354735851287842,
      "learning_rate": 0.0001766044443118978,
      "loss": 1.2355,
      "step": 430
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.2567592859268188,
      "learning_rate": 0.0001764974931981929,
      "loss": 0.8935,
      "step": 431
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.4151657521724701,
      "learning_rate": 0.00017639033072427366,
      "loss": 1.1042,
      "step": 432
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.4307219386100769,
      "learning_rate": 0.00017628295718622665,
      "loss": 1.2273,
      "step": 433
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.6330164074897766,
      "learning_rate": 0.0001761753728807217,
      "loss": 1.2027,
      "step": 434
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.47434625029563904,
      "learning_rate": 0.00017606757810501088,
      "loss": 0.9242,
      "step": 435
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.0463887453079224,
      "learning_rate": 0.00017595957315692782,
      "loss": 1.151,
      "step": 436
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.7210713028907776,
      "learning_rate": 0.00017585135833488692,
      "loss": 0.8223,
      "step": 437
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.5121049284934998,
      "learning_rate": 0.00017574293393788235,
      "loss": 0.6994,
      "step": 438
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.8933761119842529,
      "learning_rate": 0.00017563430026548734,
      "loss": 0.846,
      "step": 439
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.5270050764083862,
      "learning_rate": 0.0001755254576178535,
      "loss": 0.7119,
      "step": 440
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.37028369307518005,
      "learning_rate": 0.0001754164062957096,
      "loss": 0.8623,
      "step": 441
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.6245588660240173,
      "learning_rate": 0.00017530714660036112,
      "loss": 1.0409,
      "step": 442
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.878105640411377,
      "learning_rate": 0.0001751976788336892,
      "loss": 0.6867,
      "step": 443
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.3765283226966858,
      "learning_rate": 0.00017508800329814995,
      "loss": 1.2251,
      "step": 444
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.4110933840274811,
      "learning_rate": 0.00017497812029677344,
      "loss": 0.8676,
      "step": 445
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.3986817598342896,
      "learning_rate": 0.000174868030133163,
      "loss": 1.6298,
      "step": 446
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.4310443103313446,
      "learning_rate": 0.0001747577331114945,
      "loss": 0.7328,
      "step": 447
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.5922423601150513,
      "learning_rate": 0.00017464722953651504,
      "loss": 0.6629,
      "step": 448
    },
    {
      "epoch": 0.95,
      "grad_norm": 2.27004075050354,
      "learning_rate": 0.00017453651971354264,
      "loss": 1.4748,
      "step": 449
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.31181880831718445,
      "learning_rate": 0.00017442560394846516,
      "loss": 1.0477,
      "step": 450
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.1180263757705688,
      "learning_rate": 0.00017431448254773944,
      "loss": 0.9225,
      "step": 451
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.7490403056144714,
      "learning_rate": 0.00017420315581839044,
      "loss": 0.7847,
      "step": 452
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.138551115989685,
      "learning_rate": 0.0001740916240680105,
      "loss": 1.2782,
      "step": 453
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.9375423789024353,
      "learning_rate": 0.0001739798876047584,
      "loss": 0.8316,
      "step": 454
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.0941681861877441,
      "learning_rate": 0.0001738679467373586,
      "loss": 0.9702,
      "step": 455
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.2845444083213806,
      "learning_rate": 0.00017375580177510016,
      "loss": 0.8563,
      "step": 456
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.7341310381889343,
      "learning_rate": 0.0001736434530278362,
      "loss": 0.7102,
      "step": 457
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.886854350566864,
      "learning_rate": 0.0001735309008059829,
      "loss": 1.4872,
      "step": 458
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.44623202085494995,
      "learning_rate": 0.00017341814542051845,
      "loss": 0.8142,
      "step": 459
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.8813387155532837,
      "learning_rate": 0.00017330518718298264,
      "loss": 1.0869,
      "step": 460
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.8468006253242493,
      "learning_rate": 0.0001731920264054755,
      "loss": 1.2859,
      "step": 461
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.6797575354576111,
      "learning_rate": 0.00017307866340065685,
      "loss": 1.0288,
      "step": 462
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.25991517305374146,
      "learning_rate": 0.00017296509848174508,
      "loss": 0.7996,
      "step": 463
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.557244598865509,
      "learning_rate": 0.00017285133196251663,
      "loss": 0.6877,
      "step": 464
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.49986258149147034,
      "learning_rate": 0.00017273736415730488,
      "loss": 0.8285,
      "step": 465
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.5839115977287292,
      "learning_rate": 0.0001726231953809993,
      "loss": 0.8617,
      "step": 466
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.1967806816101074,
      "learning_rate": 0.0001725088259490448,
      "loss": 0.719,
      "step": 467
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.7830839157104492,
      "learning_rate": 0.00017239425617744048,
      "loss": 0.623,
      "step": 468
    },
    {
      "epoch": 0.99,
      "grad_norm": 2.0930089950561523,
      "learning_rate": 0.00017227948638273916,
      "loss": 1.1768,
      "step": 469
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.562641441822052,
      "learning_rate": 0.0001721645168820462,
      "loss": 0.5235,
      "step": 470
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.5656068325042725,
      "learning_rate": 0.00017204934799301883,
      "loss": 0.9211,
      "step": 471
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.934866726398468,
      "learning_rate": 0.0001719339800338651,
      "loss": 0.7897,
      "step": 472
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.30100950598716736,
      "learning_rate": 0.00017181841332334318,
      "loss": 1.0436,
      "step": 473
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5494408011436462,
      "learning_rate": 0.00017170264818076026,
      "loss": 0.6412,
      "step": 474
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6607212424278259,
      "learning_rate": 0.00017158668492597186,
      "loss": 1.3501,
      "step": 475
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5112847089767456,
      "learning_rate": 0.0001714705238793809,
      "loss": 0.4772,
      "step": 476
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8900191783905029,
      "eval_runtime": 62.0282,
      "eval_samples_per_second": 1.612,
      "eval_steps_per_second": 1.612,
      "step": 476
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2824682593345642,
      "learning_rate": 0.0001713541653619368,
      "loss": 0.5561,
      "step": 477
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.28952574729919434,
      "learning_rate": 0.0001712376096951345,
      "loss": 1.1009,
      "step": 478
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.2117149382829666,
      "learning_rate": 0.00017112085720101373,
      "loss": 0.8326,
      "step": 479
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.4022321403026581,
      "learning_rate": 0.00017100390820215804,
      "loss": 0.5327,
      "step": 480
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.26270753145217896,
      "learning_rate": 0.00017088676302169393,
      "loss": 0.2126,
      "step": 481
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.44842302799224854,
      "learning_rate": 0.00017076942198328987,
      "loss": 0.5412,
      "step": 482
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.6974923610687256,
      "learning_rate": 0.00017065188541115554,
      "loss": 0.3271,
      "step": 483
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.5276718735694885,
      "learning_rate": 0.0001705341536300409,
      "loss": 0.4566,
      "step": 484
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.30386191606521606,
      "learning_rate": 0.00017041622696523518,
      "loss": 0.8557,
      "step": 485
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.2913454473018646,
      "learning_rate": 0.0001702981057425662,
      "loss": 0.6007,
      "step": 486
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.5108489394187927,
      "learning_rate": 0.00017017979028839916,
      "loss": 0.8481,
      "step": 487
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.6002893447875977,
      "learning_rate": 0.00017006128092963605,
      "loss": 0.3967,
      "step": 488
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.34100326895713806,
      "learning_rate": 0.00016994257799371457,
      "loss": 0.2971,
      "step": 489
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.34491753578186035,
      "learning_rate": 0.00016982368180860728,
      "loss": 0.594,
      "step": 490
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.3472824692726135,
      "learning_rate": 0.00016970459270282067,
      "loss": 0.426,
      "step": 491
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.2740953266620636,
      "learning_rate": 0.00016958531100539427,
      "loss": 0.3144,
      "step": 492
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.26527807116508484,
      "learning_rate": 0.00016946583704589973,
      "loss": 0.6867,
      "step": 493
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.2539099156856537,
      "learning_rate": 0.00016934617115443992,
      "loss": 0.5074,
      "step": 494
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.34288522601127625,
      "learning_rate": 0.00016922631366164797,
      "loss": 0.5723,
      "step": 495
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.4750526249408722,
      "learning_rate": 0.00016910626489868649,
      "loss": 0.0978,
      "step": 496
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.3608519732952118,
      "learning_rate": 0.00016898602519724645,
      "loss": 0.4997,
      "step": 497
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.47260135412216187,
      "learning_rate": 0.00016886559488954648,
      "loss": 0.4042,
      "step": 498
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.7438716292381287,
      "learning_rate": 0.00016874497430833182,
      "loss": 0.2184,
      "step": 499
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.4565902650356293,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.6163,
      "step": 500
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.5079072713851929,
      "learning_rate": 0.0001685031636589669,
      "loss": 0.3755,
      "step": 501
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.5474829077720642,
      "learning_rate": 0.00016838197425893202,
      "loss": 0.5009,
      "step": 502
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.4594095051288605,
      "learning_rate": 0.00016826059592161134,
      "loss": 0.7541,
      "step": 503
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.40495601296424866,
      "learning_rate": 0.00016813902898236939,
      "loss": 0.7832,
      "step": 504
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.5781679153442383,
      "learning_rate": 0.00016801727377709194,
      "loss": 0.6996,
      "step": 505
    },
    {
      "epoch": 1.07,
      "grad_norm": 1.2371175289154053,
      "learning_rate": 0.00016789533064218485,
      "loss": 0.7179,
      "step": 506
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.6955786347389221,
      "learning_rate": 0.00016777319991457325,
      "loss": 0.478,
      "step": 507
    },
    {
      "epoch": 1.07,
      "grad_norm": 1.1571210622787476,
      "learning_rate": 0.00016765088193170053,
      "loss": 0.5954,
      "step": 508
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.7339815497398376,
      "learning_rate": 0.00016752837703152754,
      "loss": 0.5888,
      "step": 509
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.29333943128585815,
      "learning_rate": 0.00016740568555253155,
      "loss": 0.4534,
      "step": 510
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.4680086374282837,
      "learning_rate": 0.0001672828078337053,
      "loss": 0.4307,
      "step": 511
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.6249940395355225,
      "learning_rate": 0.00016715974421455617,
      "loss": 0.2269,
      "step": 512
    },
    {
      "epoch": 1.08,
      "grad_norm": 1.774949312210083,
      "learning_rate": 0.00016703649503510513,
      "loss": 0.6022,
      "step": 513
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.3996463418006897,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.9525,
      "step": 514
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.4572999179363251,
      "learning_rate": 0.00016678944135794374,
      "loss": 0.5463,
      "step": 515
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.6360291838645935,
      "learning_rate": 0.00016666563754283515,
      "loss": 0.4418,
      "step": 516
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.5520346164703369,
      "learning_rate": 0.00016654164953262612,
      "loss": 0.6817,
      "step": 517
    },
    {
      "epoch": 1.09,
      "grad_norm": 2.0099127292633057,
      "learning_rate": 0.0001664174776698917,
      "loss": 0.6017,
      "step": 518
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.4746718406677246,
      "learning_rate": 0.00016629312229771495,
      "loss": 1.0119,
      "step": 519
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.32624900341033936,
      "learning_rate": 0.00016616858375968595,
      "loss": 0.6034,
      "step": 520
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.459741473197937,
      "learning_rate": 0.00016604386239990078,
      "loss": 0.8181,
      "step": 521
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.8022719621658325,
      "learning_rate": 0.00016591895856296073,
      "loss": 0.4458,
      "step": 522
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.3159444034099579,
      "learning_rate": 0.00016579387259397127,
      "loss": 0.7185,
      "step": 523
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.4759514629840851,
      "learning_rate": 0.00016566860483854104,
      "loss": 0.5851,
      "step": 524
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.26993754506111145,
      "learning_rate": 0.000165543155642781,
      "loss": 0.4677,
      "step": 525
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.5374035239219666,
      "learning_rate": 0.00016541752535330345,
      "loss": 0.4579,
      "step": 526
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.6800963282585144,
      "learning_rate": 0.00016529171431722096,
      "loss": 0.7814,
      "step": 527
    },
    {
      "epoch": 1.11,
      "grad_norm": 1.4050697088241577,
      "learning_rate": 0.00016516572288214552,
      "loss": 0.3604,
      "step": 528
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.4229757785797119,
      "learning_rate": 0.00016503955139618762,
      "loss": 0.4654,
      "step": 529
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.5959732532501221,
      "learning_rate": 0.0001649132002079552,
      "loss": 0.8165,
      "step": 530
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.5716747045516968,
      "learning_rate": 0.00016478666966655264,
      "loss": 0.5398,
      "step": 531
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.381700873374939,
      "learning_rate": 0.00016465996012157995,
      "loss": 0.5922,
      "step": 532
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.7402687668800354,
      "learning_rate": 0.00016453307192313175,
      "loss": 0.5325,
      "step": 533
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.6408881545066833,
      "learning_rate": 0.00016440600542179615,
      "loss": 0.6203,
      "step": 534
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.7938200235366821,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.4506,
      "step": 535
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.5587771534919739,
      "learning_rate": 0.0001641513389152777,
      "loss": 0.4175,
      "step": 536
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.35594528913497925,
      "learning_rate": 0.0001640237396137306,
      "loss": 0.9313,
      "step": 537
    },
    {
      "epoch": 1.13,
      "grad_norm": 1.8496744632720947,
      "learning_rate": 0.0001638959634165656,
      "loss": 0.816,
      "step": 538
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.8227376341819763,
      "learning_rate": 0.00016376801067682434,
      "loss": 0.1371,
      "step": 539
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.9681535363197327,
      "learning_rate": 0.00016363988174803638,
      "loss": 0.6228,
      "step": 540
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.5398049354553223,
      "learning_rate": 0.0001635115769842179,
      "loss": 0.4775,
      "step": 541
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.34808897972106934,
      "learning_rate": 0.00016338309673987101,
      "loss": 0.8051,
      "step": 542
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.7682779431343079,
      "learning_rate": 0.0001632544413699828,
      "loss": 0.1041,
      "step": 543
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.4708777964115143,
      "learning_rate": 0.0001631256112300239,
      "loss": 0.5147,
      "step": 544
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.3061200976371765,
      "learning_rate": 0.00016299660667594814,
      "loss": 0.3265,
      "step": 545
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.540558934211731,
      "learning_rate": 0.00016286742806419108,
      "loss": 0.605,
      "step": 546
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.25295355916023254,
      "learning_rate": 0.00016273807575166926,
      "loss": 0.394,
      "step": 547
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.2657540440559387,
      "learning_rate": 0.0001626085500957791,
      "loss": 0.5722,
      "step": 548
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.551193118095398,
      "learning_rate": 0.000162478851454396,
      "loss": 0.2836,
      "step": 549
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.4108597934246063,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.4717,
      "step": 550
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.4006686806678772,
      "learning_rate": 0.00016221893664904142,
      "loss": 0.5644,
      "step": 551
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.2879432439804077,
      "learning_rate": 0.0001620887212032065,
      "loss": 0.8188,
      "step": 552
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.45707154273986816,
      "learning_rate": 0.00016195833420814984,
      "loss": 0.8171,
      "step": 553
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.9172948002815247,
      "learning_rate": 0.00016182777602412665,
      "loss": 0.4868,
      "step": 554
    },
    {
      "epoch": 1.17,
      "grad_norm": 1.1610100269317627,
      "learning_rate": 0.00016169704701186527,
      "loss": 0.8614,
      "step": 555
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.5628842115402222,
      "learning_rate": 0.0001615661475325658,
      "loss": 0.3256,
      "step": 556
    },
    {
      "epoch": 1.17,
      "grad_norm": 1.1540424823760986,
      "learning_rate": 0.0001614350779478996,
      "loss": 0.4672,
      "step": 557
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.3111453354358673,
      "learning_rate": 0.0001613038386200078,
      "loss": 0.3977,
      "step": 558
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.48439329862594604,
      "learning_rate": 0.00016117242991150064,
      "loss": 0.6522,
      "step": 559
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.49099549651145935,
      "learning_rate": 0.00016104085218545633,
      "loss": 0.6117,
      "step": 560
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.4174061119556427,
      "learning_rate": 0.00016090910580542005,
      "loss": 0.4991,
      "step": 561
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.7796496152877808,
      "learning_rate": 0.00016077719113540302,
      "loss": 0.613,
      "step": 562
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.414725124835968,
      "learning_rate": 0.00016064510853988138,
      "loss": 0.4263,
      "step": 563
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.30187514424324036,
      "learning_rate": 0.00016051285838379525,
      "loss": 0.3254,
      "step": 564
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.4453214406967163,
      "learning_rate": 0.00016038044103254775,
      "loss": 0.2087,
      "step": 565
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.46796607971191406,
      "learning_rate": 0.00016024785685200395,
      "loss": 0.5363,
      "step": 566
    },
    {
      "epoch": 1.19,
      "grad_norm": 1.049502968788147,
      "learning_rate": 0.00016011510620848987,
      "loss": 0.3565,
      "step": 567
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.5326039791107178,
      "learning_rate": 0.00015998218946879138,
      "loss": 0.7829,
      "step": 568
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.260036826133728,
      "learning_rate": 0.00015984910700015336,
      "loss": 0.5265,
      "step": 569
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.54875648021698,
      "learning_rate": 0.00015971585917027862,
      "loss": 0.2853,
      "step": 570
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.24017104506492615,
      "learning_rate": 0.00015958244634732674,
      "loss": 0.5476,
      "step": 571
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.0179369449615479,
      "learning_rate": 0.00015944886889991325,
      "loss": 0.4053,
      "step": 572
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.7541561722755432,
      "learning_rate": 0.00015931512719710855,
      "loss": 0.4962,
      "step": 573
    },
    {
      "epoch": 1.21,
      "grad_norm": 1.7088395357131958,
      "learning_rate": 0.00015918122160843678,
      "loss": 1.24,
      "step": 574
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.2890975773334503,
      "learning_rate": 0.00015904715250387498,
      "loss": 0.8903,
      "step": 575
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.3250918388366699,
      "learning_rate": 0.000158912920253852,
      "loss": 0.5375,
      "step": 576
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.7649716734886169,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.4943,
      "step": 577
    },
    {
      "epoch": 1.22,
      "grad_norm": 1.180847406387329,
      "learning_rate": 0.0001586439678013903,
      "loss": 0.5133,
      "step": 578
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.22564201056957245,
      "learning_rate": 0.00015850924834205895,
      "loss": 0.4563,
      "step": 579
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.396543025970459,
      "learning_rate": 0.000158374367223479,
      "loss": 0.3559,
      "step": 580
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.421466588973999,
      "learning_rate": 0.0001582393248183228,
      "loss": 0.4872,
      "step": 581
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.6064138412475586,
      "learning_rate": 0.00015810412149970833,
      "loss": 0.4341,
      "step": 582
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.4124835431575775,
      "learning_rate": 0.00015796875764119826,
      "loss": 0.415,
      "step": 583
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.7403770089149475,
      "learning_rate": 0.00015783323361679864,
      "loss": 0.391,
      "step": 584
    },
    {
      "epoch": 1.23,
      "grad_norm": 1.0920146703720093,
      "learning_rate": 0.0001576975498009583,
      "loss": 0.6798,
      "step": 585
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.5007575154304504,
      "learning_rate": 0.00015756170656856737,
      "loss": 0.6142,
      "step": 586
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.3402646780014038,
      "learning_rate": 0.00015742570429495652,
      "loss": 0.7871,
      "step": 587
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.49383026361465454,
      "learning_rate": 0.0001572895433558958,
      "loss": 0.3604,
      "step": 588
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.6136035919189453,
      "learning_rate": 0.00015715322412759375,
      "loss": 0.854,
      "step": 589
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.41479477286338806,
      "learning_rate": 0.0001570167469866962,
      "loss": 0.1273,
      "step": 590
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.4173536002635956,
      "learning_rate": 0.00015688011231028518,
      "loss": 0.601,
      "step": 591
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.4010690748691559,
      "learning_rate": 0.0001567433204758782,
      "loss": 0.5361,
      "step": 592
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.45052483677864075,
      "learning_rate": 0.00015660637186142682,
      "loss": 0.4356,
      "step": 593
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.6652331352233887,
      "learning_rate": 0.00015646926684531585,
      "loss": 0.2981,
      "step": 594
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.568655788898468,
      "learning_rate": 0.0001563320058063622,
      "loss": 0.4653,
      "step": 595
    },
    {
      "epoch": 1.25,
      "eval_loss": 0.9619532227516174,
      "eval_runtime": 61.5436,
      "eval_samples_per_second": 1.625,
      "eval_steps_per_second": 1.625,
      "step": 595
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.2903865575790405,
      "learning_rate": 0.00015619458912381396,
      "loss": 0.1973,
      "step": 596
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.7614594101905823,
      "learning_rate": 0.0001560570171773491,
      "loss": 0.6037,
      "step": 597
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.3540831208229065,
      "learning_rate": 0.0001559192903470747,
      "loss": 0.5743,
      "step": 598
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.4056189954280853,
      "learning_rate": 0.00015578140901352573,
      "loss": 0.6213,
      "step": 599
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.5303568840026855,
      "learning_rate": 0.00015564337355766412,
      "loss": 0.7036,
      "step": 600
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.5078765153884888,
      "learning_rate": 0.0001555051843608775,
      "loss": 0.411,
      "step": 601
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.9911600351333618,
      "learning_rate": 0.0001553668418049784,
      "loss": 0.1678,
      "step": 602
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.2692767083644867,
      "learning_rate": 0.000155228346272203,
      "loss": 0.4074,
      "step": 603
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.386247843503952,
      "learning_rate": 0.00015508969814521025,
      "loss": 0.5516,
      "step": 604
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.39059126377105713,
      "learning_rate": 0.0001549508978070806,
      "loss": 0.355,
      "step": 605
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.6897940039634705,
      "learning_rate": 0.00015481194564131512,
      "loss": 0.5107,
      "step": 606
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.523536741733551,
      "learning_rate": 0.00015467284203183435,
      "loss": 0.4266,
      "step": 607
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.37748581171035767,
      "learning_rate": 0.00015453358736297729,
      "loss": 0.7265,
      "step": 608
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.8041501641273499,
      "learning_rate": 0.00015439418201950025,
      "loss": 0.2922,
      "step": 609
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.36440232396125793,
      "learning_rate": 0.00015425462638657595,
      "loss": 0.6034,
      "step": 610
    },
    {
      "epoch": 1.29,
      "grad_norm": 1.179821491241455,
      "learning_rate": 0.00015411492084979226,
      "loss": 0.3024,
      "step": 611
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.23662069439888,
      "learning_rate": 0.0001539750657951513,
      "loss": 0.4297,
      "step": 612
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.3672749102115631,
      "learning_rate": 0.00015383506160906825,
      "loss": 0.5914,
      "step": 613
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.42869898676872253,
      "learning_rate": 0.00015369490867837035,
      "loss": 0.8226,
      "step": 614
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.34783145785331726,
      "learning_rate": 0.00015355460739029586,
      "loss": 0.9571,
      "step": 615
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.5273573994636536,
      "learning_rate": 0.00015341415813249288,
      "loss": 0.4833,
      "step": 616
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.7641803026199341,
      "learning_rate": 0.0001532735612930184,
      "loss": 0.2554,
      "step": 617
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.423232764005661,
      "learning_rate": 0.00015313281726033715,
      "loss": 0.6854,
      "step": 618
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.42158639430999756,
      "learning_rate": 0.0001529919264233205,
      "loss": 0.6112,
      "step": 619
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.359598845243454,
      "learning_rate": 0.00015285088917124556,
      "loss": 0.6985,
      "step": 620
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.301753431558609,
      "learning_rate": 0.0001527097058937939,
      "loss": 0.6063,
      "step": 621
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.4818098545074463,
      "learning_rate": 0.00015256837698105047,
      "loss": 0.2259,
      "step": 622
    },
    {
      "epoch": 1.31,
      "grad_norm": 1.6764453649520874,
      "learning_rate": 0.0001524269028235028,
      "loss": 0.8115,
      "step": 623
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.8210150003433228,
      "learning_rate": 0.00015228528381203962,
      "loss": 0.3319,
      "step": 624
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.5808678865432739,
      "learning_rate": 0.0001521435203379498,
      "loss": 0.3861,
      "step": 625
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.2755192816257477,
      "learning_rate": 0.00015200161279292155,
      "loss": 0.2439,
      "step": 626
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.4608403146266937,
      "learning_rate": 0.000151859561569041,
      "loss": 0.8368,
      "step": 627
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.6705602407455444,
      "learning_rate": 0.00015171736705879126,
      "loss": 0.5849,
      "step": 628
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.45606300234794617,
      "learning_rate": 0.00015157502965505143,
      "loss": 0.6276,
      "step": 629
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.5950043797492981,
      "learning_rate": 0.00015143254975109538,
      "loss": 0.6346,
      "step": 630
    },
    {
      "epoch": 1.33,
      "grad_norm": 2.2966413497924805,
      "learning_rate": 0.00015128992774059063,
      "loss": 0.5741,
      "step": 631
    },
    {
      "epoch": 1.33,
      "grad_norm": 1.1310389041900635,
      "learning_rate": 0.0001511471640175974,
      "loss": 0.7679,
      "step": 632
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.5066660046577454,
      "learning_rate": 0.00015100425897656753,
      "loss": 0.5976,
      "step": 633
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.534641683101654,
      "learning_rate": 0.00015086121301234316,
      "loss": 0.642,
      "step": 634
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.39099201560020447,
      "learning_rate": 0.0001507180265201559,
      "loss": 0.5081,
      "step": 635
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.5232080221176147,
      "learning_rate": 0.00015057469989562567,
      "loss": 0.2411,
      "step": 636
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.5573452115058899,
      "learning_rate": 0.00015043123353475943,
      "loss": 1.0094,
      "step": 637
    },
    {
      "epoch": 1.34,
      "grad_norm": 2.027163505554199,
      "learning_rate": 0.00015028762783395034,
      "loss": 0.2975,
      "step": 638
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.46357014775276184,
      "learning_rate": 0.00015014388318997655,
      "loss": 0.8153,
      "step": 639
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.5300567746162415,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.7068,
      "step": 640
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.3386455476284027,
      "learning_rate": 0.00014985597866156559,
      "loss": 0.9168,
      "step": 641
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.2023034393787384,
      "learning_rate": 0.0001497118195725998,
      "loss": 0.382,
      "step": 642
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.2776263654232025,
      "learning_rate": 0.00014956752313140977,
      "loss": 0.693,
      "step": 643
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.6025331020355225,
      "learning_rate": 0.0001494230897366821,
      "loss": 0.7256,
      "step": 644
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.4146818518638611,
      "learning_rate": 0.00014927851978748178,
      "loss": 0.5046,
      "step": 645
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.3705938756465912,
      "learning_rate": 0.00014913381368325115,
      "loss": 0.7319,
      "step": 646
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.2651060223579407,
      "learning_rate": 0.0001489889718238087,
      "loss": 0.526,
      "step": 647
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.41096463799476624,
      "learning_rate": 0.00014884399460934805,
      "loss": 0.3067,
      "step": 648
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.22056828439235687,
      "learning_rate": 0.00014869888244043673,
      "loss": 0.5476,
      "step": 649
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.6910893321037292,
      "learning_rate": 0.00014855363571801523,
      "loss": 0.5243,
      "step": 650
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.4330577552318573,
      "learning_rate": 0.00014840825484339573,
      "loss": 0.4357,
      "step": 651
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.43148112297058105,
      "learning_rate": 0.0001482627402182611,
      "loss": 0.3913,
      "step": 652
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.4191662073135376,
      "learning_rate": 0.0001481170922446638,
      "loss": 0.2875,
      "step": 653
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.8446200489997864,
      "learning_rate": 0.00014797131132502465,
      "loss": 0.6589,
      "step": 654
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.7334960103034973,
      "learning_rate": 0.00014782539786213183,
      "loss": 0.6975,
      "step": 655
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.42938506603240967,
      "learning_rate": 0.00014767935225913975,
      "loss": 0.3074,
      "step": 656
    },
    {
      "epoch": 1.38,
      "grad_norm": 2.6491518020629883,
      "learning_rate": 0.00014753317491956796,
      "loss": 0.6397,
      "step": 657
    },
    {
      "epoch": 1.39,
      "grad_norm": 1.0263487100601196,
      "learning_rate": 0.00014738686624729986,
      "loss": 0.5503,
      "step": 658
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.4753721058368683,
      "learning_rate": 0.00014724042664658184,
      "loss": 1.0253,
      "step": 659
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.7451716065406799,
      "learning_rate": 0.00014709385652202203,
      "loss": 0.3982,
      "step": 660
    },
    {
      "epoch": 1.39,
      "grad_norm": 1.6008319854736328,
      "learning_rate": 0.00014694715627858908,
      "loss": 0.212,
      "step": 661
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.4117997884750366,
      "learning_rate": 0.0001468003263216113,
      "loss": 0.3975,
      "step": 662
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.33254194259643555,
      "learning_rate": 0.00014665336705677534,
      "loss": 0.5263,
      "step": 663
    },
    {
      "epoch": 1.4,
      "grad_norm": 1.039075255393982,
      "learning_rate": 0.00014650627889012507,
      "loss": 0.6964,
      "step": 664
    },
    {
      "epoch": 1.4,
      "grad_norm": 7.058536052703857,
      "learning_rate": 0.00014635906222806058,
      "loss": 0.7029,
      "step": 665
    },
    {
      "epoch": 1.4,
      "grad_norm": 1.0019419193267822,
      "learning_rate": 0.00014621171747733697,
      "loss": 0.6372,
      "step": 666
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.31377118825912476,
      "learning_rate": 0.00014606424504506324,
      "loss": 0.6574,
      "step": 667
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.46048787236213684,
      "learning_rate": 0.00014591664533870118,
      "loss": 0.3682,
      "step": 668
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.6753351092338562,
      "learning_rate": 0.0001457689187660642,
      "loss": 0.4969,
      "step": 669
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.4977830946445465,
      "learning_rate": 0.0001456210657353163,
      "loss": 0.4409,
      "step": 670
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.34079307317733765,
      "learning_rate": 0.00014547308665497082,
      "loss": 0.3568,
      "step": 671
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.651228129863739,
      "learning_rate": 0.0001453249819338894,
      "loss": 0.8023,
      "step": 672
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.34143513441085815,
      "learning_rate": 0.00014517675198128085,
      "loss": 0.6065,
      "step": 673
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.4881991446018219,
      "learning_rate": 0.00014502839720669989,
      "loss": 0.5526,
      "step": 674
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.28715357184410095,
      "learning_rate": 0.00014487991802004623,
      "loss": 0.5798,
      "step": 675
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.9956842660903931,
      "learning_rate": 0.00014473131483156327,
      "loss": 0.2817,
      "step": 676
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.4922630190849304,
      "learning_rate": 0.00014458258805183705,
      "loss": 0.3929,
      "step": 677
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.4495314061641693,
      "learning_rate": 0.00014443373809179508,
      "loss": 0.2987,
      "step": 678
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.7611126899719238,
      "learning_rate": 0.00014428476536270515,
      "loss": 0.9684,
      "step": 679
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.40701159834861755,
      "learning_rate": 0.0001441356702761744,
      "loss": 0.6025,
      "step": 680
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.7356356382369995,
      "learning_rate": 0.00014398645324414792,
      "loss": 0.8664,
      "step": 681
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.0680326223373413,
      "learning_rate": 0.00014383711467890774,
      "loss": 0.5663,
      "step": 682
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.4097828269004822,
      "learning_rate": 0.00014368765499307178,
      "loss": 0.5657,
      "step": 683
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.771783709526062,
      "learning_rate": 0.00014353807459959242,
      "loss": 0.3531,
      "step": 684
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.7945293188095093,
      "learning_rate": 0.00014338837391175582,
      "loss": 0.3199,
      "step": 685
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.1944937705993652,
      "learning_rate": 0.00014323855334318026,
      "loss": 0.495,
      "step": 686
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.3822149634361267,
      "learning_rate": 0.0001430886133078154,
      "loss": 0.5544,
      "step": 687
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.3462957441806793,
      "learning_rate": 0.00014293855421994094,
      "loss": 0.0456,
      "step": 688
    },
    {
      "epoch": 1.45,
      "grad_norm": 1.3546236753463745,
      "learning_rate": 0.00014278837649416544,
      "loss": 0.5839,
      "step": 689
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.6205141544342041,
      "learning_rate": 0.0001426380805454254,
      "loss": 0.8681,
      "step": 690
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.4317213296890259,
      "learning_rate": 0.00014248766678898387,
      "loss": 0.3221,
      "step": 691
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.31438273191452026,
      "learning_rate": 0.00014233713564042937,
      "loss": 0.4549,
      "step": 692
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.6450943946838379,
      "learning_rate": 0.00014218648751567492,
      "loss": 0.3213,
      "step": 693
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.5037809610366821,
      "learning_rate": 0.00014203572283095657,
      "loss": 0.8642,
      "step": 694
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.26184359192848206,
      "learning_rate": 0.0001418848420028325,
      "loss": 0.4245,
      "step": 695
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.6354640126228333,
      "learning_rate": 0.0001417338454481818,
      "loss": 0.647,
      "step": 696
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.5512405633926392,
      "learning_rate": 0.0001415827335842033,
      "loss": 0.701,
      "step": 697
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.30941978096961975,
      "learning_rate": 0.00014143150682841438,
      "loss": 0.3872,
      "step": 698
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.5071930885314941,
      "learning_rate": 0.00014128016559864998,
      "loss": 0.3423,
      "step": 699
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.5384394526481628,
      "learning_rate": 0.00014112871031306119,
      "loss": 0.8117,
      "step": 700
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.7472350597381592,
      "learning_rate": 0.00014097714139011427,
      "loss": 0.2549,
      "step": 701
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.712765097618103,
      "learning_rate": 0.00014082545924858954,
      "loss": 0.5212,
      "step": 702
    },
    {
      "epoch": 1.48,
      "grad_norm": 1.0152575969696045,
      "learning_rate": 0.00014067366430758004,
      "loss": 0.8595,
      "step": 703
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.4496733546257019,
      "learning_rate": 0.00014052175698649053,
      "loss": 0.8319,
      "step": 704
    },
    {
      "epoch": 1.48,
      "grad_norm": 1.291023850440979,
      "learning_rate": 0.00014036973770503624,
      "loss": 0.7661,
      "step": 705
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.8034072518348694,
      "learning_rate": 0.00014021760688324176,
      "loss": 0.4416,
      "step": 706
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.48388585448265076,
      "learning_rate": 0.00014006536494143987,
      "loss": 0.6063,
      "step": 707
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.2967996895313263,
      "learning_rate": 0.0001399130123002703,
      "loss": 0.8233,
      "step": 708
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.4136080741882324,
      "learning_rate": 0.00013976054938067884,
      "loss": 0.2559,
      "step": 709
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.4075431525707245,
      "learning_rate": 0.0001396079766039157,
      "loss": 0.2941,
      "step": 710
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.5675719380378723,
      "learning_rate": 0.00013945529439153478,
      "loss": 0.5892,
      "step": 711
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.8851110339164734,
      "learning_rate": 0.00013930250316539238,
      "loss": 0.3651,
      "step": 712
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.8696531057357788,
      "learning_rate": 0.00013914960334764588,
      "loss": 0.2327,
      "step": 713
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.392892062664032,
      "learning_rate": 0.0001389965953607528,
      "loss": 0.5907,
      "step": 714
    },
    {
      "epoch": 1.5,
      "eval_loss": 0.953182578086853,
      "eval_runtime": 61.7108,
      "eval_samples_per_second": 1.62,
      "eval_steps_per_second": 1.62,
      "step": 714
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.42428654432296753,
      "learning_rate": 0.00013884347962746948,
      "loss": 0.3576,
      "step": 715
    },
    {
      "epoch": 1.51,
      "grad_norm": 2.1607768535614014,
      "learning_rate": 0.00013869025657084995,
      "loss": 0.6363,
      "step": 716
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.4016755521297455,
      "learning_rate": 0.00013853692661424484,
      "loss": 0.3195,
      "step": 717
    },
    {
      "epoch": 1.51,
      "grad_norm": 1.9975876808166504,
      "learning_rate": 0.00013838349018130007,
      "loss": 0.5935,
      "step": 718
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.41282904148101807,
      "learning_rate": 0.0001382299476959557,
      "loss": 0.8013,
      "step": 719
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.6295652985572815,
      "learning_rate": 0.00013807629958244498,
      "loss": 0.344,
      "step": 720
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.4839375615119934,
      "learning_rate": 0.00013792254626529286,
      "loss": 0.5274,
      "step": 721
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.37345823645591736,
      "learning_rate": 0.00013776868816931502,
      "loss": 0.6027,
      "step": 722
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.7521209716796875,
      "learning_rate": 0.00013761472571961663,
      "loss": 0.4461,
      "step": 723
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.3980889320373535,
      "learning_rate": 0.00013746065934159123,
      "loss": 0.502,
      "step": 724
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.5544388890266418,
      "learning_rate": 0.0001373064894609194,
      "loss": 0.2908,
      "step": 725
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.3128870129585266,
      "learning_rate": 0.0001371522165035678,
      "loss": 0.6016,
      "step": 726
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.45354199409484863,
      "learning_rate": 0.0001369978408957879,
      "loss": 0.9534,
      "step": 727
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.4182490110397339,
      "learning_rate": 0.00013684336306411468,
      "loss": 0.5976,
      "step": 728
    },
    {
      "epoch": 1.53,
      "grad_norm": 1.1179499626159668,
      "learning_rate": 0.00013668878343536562,
      "loss": 0.4097,
      "step": 729
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.30916330218315125,
      "learning_rate": 0.00013653410243663952,
      "loss": 0.762,
      "step": 730
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.6563719511032104,
      "learning_rate": 0.00013637932049531516,
      "loss": 0.5264,
      "step": 731
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.6355602741241455,
      "learning_rate": 0.00013622443803905027,
      "loss": 0.4213,
      "step": 732
    },
    {
      "epoch": 1.54,
      "grad_norm": 1.685316562652588,
      "learning_rate": 0.0001360694554957804,
      "loss": 0.5827,
      "step": 733
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.5541813373565674,
      "learning_rate": 0.00013591437329371736,
      "loss": 0.9299,
      "step": 734
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.40998753905296326,
      "learning_rate": 0.0001357591918613486,
      "loss": 0.7085,
      "step": 735
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.43177279829978943,
      "learning_rate": 0.00013560391162743569,
      "loss": 0.5073,
      "step": 736
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.5776886940002441,
      "learning_rate": 0.00013544853302101302,
      "loss": 0.5856,
      "step": 737
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.3610301911830902,
      "learning_rate": 0.00013529305647138687,
      "loss": 0.6362,
      "step": 738
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.4736679196357727,
      "learning_rate": 0.0001351374824081343,
      "loss": 0.4307,
      "step": 739
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.33841657638549805,
      "learning_rate": 0.0001349818112611015,
      "loss": 0.5294,
      "step": 740
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.5574224591255188,
      "learning_rate": 0.00013482604346040308,
      "loss": 0.5722,
      "step": 741
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.3317987620830536,
      "learning_rate": 0.00013467017943642073,
      "loss": 0.7735,
      "step": 742
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.6277002692222595,
      "learning_rate": 0.00013451421961980188,
      "loss": 0.5771,
      "step": 743
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.8945910334587097,
      "learning_rate": 0.0001343581644414587,
      "loss": 0.6094,
      "step": 744
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.2320517748594284,
      "learning_rate": 0.00013420201433256689,
      "loss": 0.502,
      "step": 745
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.44287192821502686,
      "learning_rate": 0.00013404576972456431,
      "loss": 0.6849,
      "step": 746
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.7059826850891113,
      "learning_rate": 0.00013388943104915003,
      "loss": 0.6448,
      "step": 747
    },
    {
      "epoch": 1.57,
      "grad_norm": 1.8904210329055786,
      "learning_rate": 0.00013373299873828303,
      "loss": 0.58,
      "step": 748
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.4500790238380432,
      "learning_rate": 0.00013357647322418087,
      "loss": 0.4979,
      "step": 749
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.49751782417297363,
      "learning_rate": 0.00013341985493931877,
      "loss": 0.473,
      "step": 750
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.39845967292785645,
      "learning_rate": 0.00013326314431642822,
      "loss": 0.2201,
      "step": 751
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.30875203013420105,
      "learning_rate": 0.0001331063417884958,
      "loss": 0.2684,
      "step": 752
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.7159584164619446,
      "learning_rate": 0.00013294944778876214,
      "loss": 0.2587,
      "step": 753
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.6593707203865051,
      "learning_rate": 0.00013279246275072046,
      "loss": 0.5709,
      "step": 754
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.44912752509117126,
      "learning_rate": 0.0001326353871081156,
      "loss": 0.5268,
      "step": 755
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.7455440163612366,
      "learning_rate": 0.00013247822129494266,
      "loss": 0.6083,
      "step": 756
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.41440096497535706,
      "learning_rate": 0.00013232096574544602,
      "loss": 0.658,
      "step": 757
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.4352113604545593,
      "learning_rate": 0.00013216362089411783,
      "loss": 0.466,
      "step": 758
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.46454110741615295,
      "learning_rate": 0.00013200618717569714,
      "loss": 0.635,
      "step": 759
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.34865137934684753,
      "learning_rate": 0.00013184866502516845,
      "loss": 0.757,
      "step": 760
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.6294916272163391,
      "learning_rate": 0.00013169105487776056,
      "loss": 0.6611,
      "step": 761
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.5948600172996521,
      "learning_rate": 0.00013153335716894544,
      "loss": 0.6016,
      "step": 762
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.3446013033390045,
      "learning_rate": 0.00013137557233443707,
      "loss": 0.6529,
      "step": 763
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.9169672727584839,
      "learning_rate": 0.00013121770081018998,
      "loss": 0.3821,
      "step": 764
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.6247507333755493,
      "learning_rate": 0.00013105974303239838,
      "loss": 0.4863,
      "step": 765
    },
    {
      "epoch": 1.61,
      "grad_norm": 1.3251171112060547,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.5048,
      "step": 766
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.24779891967773438,
      "learning_rate": 0.00013074357046214863,
      "loss": 0.7598,
      "step": 767
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.555656373500824,
      "learning_rate": 0.00013058535654326554,
      "loss": 0.4528,
      "step": 768
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.6941070556640625,
      "learning_rate": 0.00013042705811798565,
      "loss": 0.3112,
      "step": 769
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.29382842779159546,
      "learning_rate": 0.0001302686756236826,
      "loss": 0.2031,
      "step": 770
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.7080028057098389,
      "learning_rate": 0.00013011020949796237,
      "loss": 0.4234,
      "step": 771
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.6657422780990601,
      "learning_rate": 0.00012995166017866193,
      "loss": 0.4992,
      "step": 772
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.6290334463119507,
      "learning_rate": 0.0001297930281038482,
      "loss": 0.5391,
      "step": 773
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.37018316984176636,
      "learning_rate": 0.00012963431371181672,
      "loss": 0.7651,
      "step": 774
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.480070561170578,
      "learning_rate": 0.00012947551744109043,
      "loss": 0.6715,
      "step": 775
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.5766746401786804,
      "learning_rate": 0.00012931663973041855,
      "loss": 0.3435,
      "step": 776
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.46330827474594116,
      "learning_rate": 0.00012915768101877525,
      "loss": 0.4134,
      "step": 777
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.36259955167770386,
      "learning_rate": 0.00012899864174535864,
      "loss": 0.4665,
      "step": 778
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.9827147722244263,
      "learning_rate": 0.0001288395223495892,
      "loss": 0.8229,
      "step": 779
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.7168895602226257,
      "learning_rate": 0.00012868032327110904,
      "loss": 0.7883,
      "step": 780
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.503113865852356,
      "learning_rate": 0.00012852104494978024,
      "loss": 0.8635,
      "step": 781
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.48859935998916626,
      "learning_rate": 0.00012836168782568385,
      "loss": 0.4803,
      "step": 782
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.7904655337333679,
      "learning_rate": 0.00012820225233911876,
      "loss": 0.6279,
      "step": 783
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.2756960988044739,
      "learning_rate": 0.00012804273893060028,
      "loss": 0.2352,
      "step": 784
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.42820924520492554,
      "learning_rate": 0.00012788314804085903,
      "loss": 0.4173,
      "step": 785
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.3982052505016327,
      "learning_rate": 0.00012772348011083973,
      "loss": 0.4763,
      "step": 786
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.3944327235221863,
      "learning_rate": 0.0001275637355816999,
      "loss": 0.6724,
      "step": 787
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.5017027854919434,
      "learning_rate": 0.00012740391489480884,
      "loss": 0.9624,
      "step": 788
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.47813552618026733,
      "learning_rate": 0.0001272440184917461,
      "loss": 0.5583,
      "step": 789
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.4271741807460785,
      "learning_rate": 0.00012708404681430053,
      "loss": 0.6461,
      "step": 790
    },
    {
      "epoch": 1.67,
      "grad_norm": 1.1472680568695068,
      "learning_rate": 0.00012692400030446893,
      "loss": 0.5068,
      "step": 791
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.30405759811401367,
      "learning_rate": 0.0001267638794044549,
      "loss": 0.4573,
      "step": 792
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.4505164921283722,
      "learning_rate": 0.00012660368455666752,
      "loss": 0.6588,
      "step": 793
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.504728376865387,
      "learning_rate": 0.00012644341620372023,
      "loss": 0.3744,
      "step": 794
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.8362789154052734,
      "learning_rate": 0.00012628307478842953,
      "loss": 0.2572,
      "step": 795
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.6768229007720947,
      "learning_rate": 0.00012612266075381386,
      "loss": 0.4818,
      "step": 796
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.1750926375389099,
      "learning_rate": 0.00012596217454309216,
      "loss": 0.2631,
      "step": 797
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.5636873245239258,
      "learning_rate": 0.00012580161659968294,
      "loss": 0.414,
      "step": 798
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.5396051406860352,
      "learning_rate": 0.00012564098736720283,
      "loss": 0.6055,
      "step": 799
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.5941131114959717,
      "learning_rate": 0.0001254802872894655,
      "loss": 0.4737,
      "step": 800
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.2654617130756378,
      "learning_rate": 0.0001253195168104802,
      "loss": 0.256,
      "step": 801
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.6253994703292847,
      "learning_rate": 0.00012515867637445086,
      "loss": 0.5111,
      "step": 802
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.35557523369789124,
      "learning_rate": 0.00012499776642577466,
      "loss": 0.4252,
      "step": 803
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.634124219417572,
      "learning_rate": 0.00012483678740904082,
      "loss": 0.4969,
      "step": 804
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.42550286650657654,
      "learning_rate": 0.00012467573976902935,
      "loss": 0.2964,
      "step": 805
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.8458385467529297,
      "learning_rate": 0.00012451462395071,
      "loss": 0.8494,
      "step": 806
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.3704116940498352,
      "learning_rate": 0.00012435344039924076,
      "loss": 0.566,
      "step": 807
    },
    {
      "epoch": 1.7,
      "grad_norm": 2.0013949871063232,
      "learning_rate": 0.00012419218955996676,
      "loss": 0.8766,
      "step": 808
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.48777440190315247,
      "learning_rate": 0.0001240308718784192,
      "loss": 0.6281,
      "step": 809
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.6042513847351074,
      "learning_rate": 0.0001238694878003138,
      "loss": 0.6793,
      "step": 810
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.6612951755523682,
      "learning_rate": 0.00012370803777154977,
      "loss": 0.7568,
      "step": 811
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.4469200074672699,
      "learning_rate": 0.00012354652223820858,
      "loss": 0.6635,
      "step": 812
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.49686670303344727,
      "learning_rate": 0.00012338494164655268,
      "loss": 0.4435,
      "step": 813
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.3647472560405731,
      "learning_rate": 0.00012322329644302426,
      "loss": 0.3977,
      "step": 814
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.5049201846122742,
      "learning_rate": 0.00012306158707424403,
      "loss": 0.3614,
      "step": 815
    },
    {
      "epoch": 1.72,
      "grad_norm": 1.0189746618270874,
      "learning_rate": 0.00012289981398700995,
      "loss": 0.2356,
      "step": 816
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.660258948802948,
      "learning_rate": 0.00012273797762829615,
      "loss": 0.6134,
      "step": 817
    },
    {
      "epoch": 1.72,
      "grad_norm": 1.4135748147964478,
      "learning_rate": 0.00012257607844525146,
      "loss": 0.5336,
      "step": 818
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.6823858618736267,
      "learning_rate": 0.00012241411688519827,
      "loss": 0.5941,
      "step": 819
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.760971188545227,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.5189,
      "step": 820
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.3797072470188141,
      "learning_rate": 0.00012209000842421688,
      "loss": 0.62,
      "step": 821
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.39116472005844116,
      "learning_rate": 0.00012192786241879033,
      "loss": 0.4138,
      "step": 822
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.4047084152698517,
      "learning_rate": 0.00012176565582735625,
      "loss": 0.836,
      "step": 823
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.2494349628686905,
      "learning_rate": 0.0001216033890980864,
      "loss": 0.5686,
      "step": 824
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.3844553232192993,
      "learning_rate": 0.00012144106267931876,
      "loss": 0.9203,
      "step": 825
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.6064060926437378,
      "learning_rate": 0.00012127867701955622,
      "loss": 0.4321,
      "step": 826
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.4317924380302429,
      "learning_rate": 0.00012111623256746538,
      "loss": 0.5162,
      "step": 827
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.6777471303939819,
      "learning_rate": 0.0001209537297718752,
      "loss": 0.3923,
      "step": 828
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.3700021207332611,
      "learning_rate": 0.00012079116908177593,
      "loss": 0.6012,
      "step": 829
    },
    {
      "epoch": 1.75,
      "grad_norm": 2.029829502105713,
      "learning_rate": 0.00012062855094631778,
      "loss": 0.9376,
      "step": 830
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.513691246509552,
      "learning_rate": 0.00012046587581480953,
      "loss": 0.6733,
      "step": 831
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.2661391794681549,
      "learning_rate": 0.00012030314413671762,
      "loss": 0.6343,
      "step": 832
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.7096115946769714,
      "learning_rate": 0.00012014035636166468,
      "loss": 0.7364,
      "step": 833
    },
    {
      "epoch": 1.75,
      "eval_loss": 0.9359864592552185,
      "eval_runtime": 61.6239,
      "eval_samples_per_second": 1.623,
      "eval_steps_per_second": 1.623,
      "step": 833
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.976125955581665,
      "learning_rate": 0.00011997751293942827,
      "loss": 0.8367,
      "step": 834
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.4215434193611145,
      "learning_rate": 0.00011981461431993977,
      "loss": 0.749,
      "step": 835
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.7470360994338989,
      "learning_rate": 0.00011965166095328301,
      "loss": 0.6391,
      "step": 836
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.37723225355148315,
      "learning_rate": 0.00011948865328969317,
      "loss": 0.3735,
      "step": 837
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.47738218307495117,
      "learning_rate": 0.00011932559177955533,
      "loss": 0.2499,
      "step": 838
    },
    {
      "epoch": 1.77,
      "grad_norm": 1.9608547687530518,
      "learning_rate": 0.00011916247687340347,
      "loss": 1.1033,
      "step": 839
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.8636322617530823,
      "learning_rate": 0.00011899930902191902,
      "loss": 0.4688,
      "step": 840
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.8400352001190186,
      "learning_rate": 0.0001188360886759297,
      "loss": 0.7346,
      "step": 841
    },
    {
      "epoch": 1.77,
      "grad_norm": 2.1385717391967773,
      "learning_rate": 0.00011867281628640835,
      "loss": 0.6854,
      "step": 842
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.5982779860496521,
      "learning_rate": 0.00011850949230447145,
      "loss": 0.203,
      "step": 843
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.5503920316696167,
      "learning_rate": 0.00011834611718137824,
      "loss": 0.4089,
      "step": 844
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.3790716230869293,
      "learning_rate": 0.00011818269136852909,
      "loss": 0.8513,
      "step": 845
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.9155630469322205,
      "learning_rate": 0.00011801921531746444,
      "loss": 0.6007,
      "step": 846
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.3659191429615021,
      "learning_rate": 0.00011785568947986367,
      "loss": 0.3286,
      "step": 847
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.5917383432388306,
      "learning_rate": 0.00011769211430754357,
      "loss": 0.4512,
      "step": 848
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.5010570287704468,
      "learning_rate": 0.00011752849025245727,
      "loss": 0.783,
      "step": 849
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.6034415364265442,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.7131,
      "step": 850
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.33147016167640686,
      "learning_rate": 0.0001172010973024729,
      "loss": 0.7657,
      "step": 851
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.781022310256958,
      "learning_rate": 0.00011703732931215141,
      "loss": 0.3487,
      "step": 852
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.5436139106750488,
      "learning_rate": 0.00011687351424821449,
      "loss": 0.667,
      "step": 853
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.3158597946166992,
      "learning_rate": 0.00011670965256327818,
      "loss": 0.7158,
      "step": 854
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.3362921178340912,
      "learning_rate": 0.00011654574471008713,
      "loss": 0.6947,
      "step": 855
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.4755779802799225,
      "learning_rate": 0.00011638179114151377,
      "loss": 0.4976,
      "step": 856
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.33236339688301086,
      "learning_rate": 0.00011621779231055676,
      "loss": 0.7231,
      "step": 857
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.30901312828063965,
      "learning_rate": 0.00011605374867033977,
      "loss": 0.5085,
      "step": 858
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.426242470741272,
      "learning_rate": 0.00011588966067411034,
      "loss": 0.5185,
      "step": 859
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.4367331862449646,
      "learning_rate": 0.00011572552877523854,
      "loss": 0.7451,
      "step": 860
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.4386216700077057,
      "learning_rate": 0.00011556135342721574,
      "loss": 0.6259,
      "step": 861
    },
    {
      "epoch": 1.81,
      "grad_norm": 1.1260708570480347,
      "learning_rate": 0.00011539713508365335,
      "loss": 0.789,
      "step": 862
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.4716445803642273,
      "learning_rate": 0.00011523287419828163,
      "loss": 0.7175,
      "step": 863
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.2573232054710388,
      "learning_rate": 0.00011506857122494831,
      "loss": 0.3327,
      "step": 864
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.4652167558670044,
      "learning_rate": 0.00011490422661761744,
      "loss": 0.305,
      "step": 865
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.3845941424369812,
      "learning_rate": 0.00011473984083036813,
      "loss": 0.4717,
      "step": 866
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.5258691906929016,
      "learning_rate": 0.0001145754143173932,
      "loss": 0.2964,
      "step": 867
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.6041063070297241,
      "learning_rate": 0.00011441094753299801,
      "loss": 1.1448,
      "step": 868
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.9182747602462769,
      "learning_rate": 0.00011424644093159931,
      "loss": 0.7663,
      "step": 869
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.3786636292934418,
      "learning_rate": 0.00011408189496772368,
      "loss": 0.6454,
      "step": 870
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.39566946029663086,
      "learning_rate": 0.00011391731009600654,
      "loss": 0.8292,
      "step": 871
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.5287953615188599,
      "learning_rate": 0.00011375268677119089,
      "loss": 0.4593,
      "step": 872
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.4483492970466614,
      "learning_rate": 0.00011358802544812584,
      "loss": 0.1606,
      "step": 873
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.38028889894485474,
      "learning_rate": 0.00011342332658176555,
      "loss": 0.3923,
      "step": 874
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.660707950592041,
      "learning_rate": 0.00011325859062716795,
      "loss": 0.3406,
      "step": 875
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.6110001802444458,
      "learning_rate": 0.00011309381803949333,
      "loss": 0.3173,
      "step": 876
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.7987465858459473,
      "learning_rate": 0.00011292900927400333,
      "loss": 0.4357,
      "step": 877
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.6956415176391602,
      "learning_rate": 0.00011276416478605949,
      "loss": 0.3612,
      "step": 878
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.6051459908485413,
      "learning_rate": 0.00011259928503112198,
      "loss": 0.2962,
      "step": 879
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.41652801632881165,
      "learning_rate": 0.00011243437046474853,
      "loss": 0.5236,
      "step": 880
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.8061907887458801,
      "learning_rate": 0.000112269421542593,
      "loss": 0.8685,
      "step": 881
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.6048658490180969,
      "learning_rate": 0.00011210443872040414,
      "loss": 0.4611,
      "step": 882
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.4245402216911316,
      "learning_rate": 0.00011193942245402443,
      "loss": 0.903,
      "step": 883
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.6208779215812683,
      "learning_rate": 0.00011177437319938875,
      "loss": 0.6526,
      "step": 884
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.8669800162315369,
      "learning_rate": 0.00011160929141252303,
      "loss": 0.7721,
      "step": 885
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.3639528751373291,
      "learning_rate": 0.0001114441775495432,
      "loss": 0.2891,
      "step": 886
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.5209739804267883,
      "learning_rate": 0.00011127903206665378,
      "loss": 0.8096,
      "step": 887
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.41638287901878357,
      "learning_rate": 0.00011111385542014663,
      "loss": 0.2956,
      "step": 888
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.5916814804077148,
      "learning_rate": 0.00011094864806639971,
      "loss": 0.5097,
      "step": 889
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.44301638007164,
      "learning_rate": 0.00011078341046187589,
      "loss": 0.7395,
      "step": 890
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.3692547380924225,
      "learning_rate": 0.00011061814306312152,
      "loss": 0.4997,
      "step": 891
    },
    {
      "epoch": 1.88,
      "grad_norm": 1.0468300580978394,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.7649,
      "step": 892
    },
    {
      "epoch": 1.88,
      "grad_norm": 1.3064887523651123,
      "learning_rate": 0.0001102875207095172,
      "loss": 0.5308,
      "step": 893
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.904100239276886,
      "learning_rate": 0.00011012216666816659,
      "loss": 0.5012,
      "step": 894
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.6699868440628052,
      "learning_rate": 0.00010995678465958168,
      "loss": 0.362,
      "step": 895
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.24509219825267792,
      "learning_rate": 0.00010979137514070782,
      "loss": 0.3418,
      "step": 896
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.4075641632080078,
      "learning_rate": 0.00010962593856856649,
      "loss": 0.5487,
      "step": 897
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.5983563661575317,
      "learning_rate": 0.00010946047540025372,
      "loss": 0.515,
      "step": 898
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.3288837671279907,
      "learning_rate": 0.00010929498609293924,
      "loss": 0.6094,
      "step": 899
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.4095224440097809,
      "learning_rate": 0.00010912947110386484,
      "loss": 0.4269,
      "step": 900
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.9093605875968933,
      "learning_rate": 0.00010896393089034336,
      "loss": 0.4983,
      "step": 901
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.29987531900405884,
      "learning_rate": 0.00010879836590975731,
      "loss": 0.363,
      "step": 902
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.4612436592578888,
      "learning_rate": 0.00010863277661955758,
      "loss": 0.6466,
      "step": 903
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.8924248814582825,
      "learning_rate": 0.00010846716347726233,
      "loss": 0.3571,
      "step": 904
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.2619093954563141,
      "learning_rate": 0.00010830152694045552,
      "loss": 0.568,
      "step": 905
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.9936345815658569,
      "learning_rate": 0.00010813586746678583,
      "loss": 0.5164,
      "step": 906
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.6397780776023865,
      "learning_rate": 0.00010797018551396527,
      "loss": 0.4196,
      "step": 907
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.5577610731124878,
      "learning_rate": 0.00010780448153976793,
      "loss": 0.7255,
      "step": 908
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.5776187777519226,
      "learning_rate": 0.00010763875600202879,
      "loss": 0.371,
      "step": 909
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.3465639650821686,
      "learning_rate": 0.00010747300935864243,
      "loss": 0.272,
      "step": 910
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.4619837999343872,
      "learning_rate": 0.00010730724206756168,
      "loss": 0.2819,
      "step": 911
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.34520411491394043,
      "learning_rate": 0.00010714145458679649,
      "loss": 0.6186,
      "step": 912
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.6020563840866089,
      "learning_rate": 0.00010697564737441252,
      "loss": 0.2653,
      "step": 913
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.6317043304443359,
      "learning_rate": 0.00010680982088853002,
      "loss": 0.3674,
      "step": 914
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.3305717706680298,
      "learning_rate": 0.00010664397558732244,
      "loss": 0.6258,
      "step": 915
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.6932215690612793,
      "learning_rate": 0.00010647811192901518,
      "loss": 0.2891,
      "step": 916
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.7648591995239258,
      "learning_rate": 0.00010631223037188449,
      "loss": 0.4415,
      "step": 917
    },
    {
      "epoch": 1.93,
      "grad_norm": 1.066448450088501,
      "learning_rate": 0.00010614633137425598,
      "loss": 0.6719,
      "step": 918
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.4558663070201874,
      "learning_rate": 0.00010598041539450343,
      "loss": 0.3681,
      "step": 919
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.6853288412094116,
      "learning_rate": 0.00010581448289104758,
      "loss": 0.5901,
      "step": 920
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.6174774169921875,
      "learning_rate": 0.00010564853432235486,
      "loss": 0.5672,
      "step": 921
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.3689481019973755,
      "learning_rate": 0.00010548257014693601,
      "loss": 0.5118,
      "step": 922
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.6491348743438721,
      "learning_rate": 0.00010531659082334495,
      "loss": 0.756,
      "step": 923
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.7349205613136292,
      "learning_rate": 0.0001051505968101774,
      "loss": 0.5861,
      "step": 924
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.5765767693519592,
      "learning_rate": 0.00010498458856606972,
      "loss": 0.6011,
      "step": 925
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.28173473477363586,
      "learning_rate": 0.00010481856654969758,
      "loss": 1.0505,
      "step": 926
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.6159635782241821,
      "learning_rate": 0.0001046525312197747,
      "loss": 0.4108,
      "step": 927
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.569395899772644,
      "learning_rate": 0.00010448648303505151,
      "loss": 0.4487,
      "step": 928
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.7190093994140625,
      "learning_rate": 0.00010432042245431406,
      "loss": 0.1999,
      "step": 929
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.5158098340034485,
      "learning_rate": 0.00010415434993638269,
      "loss": 0.7024,
      "step": 930
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.4488438665866852,
      "learning_rate": 0.0001039882659401105,
      "loss": 0.4289,
      "step": 931
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.4636310935020447,
      "learning_rate": 0.00010382217092438255,
      "loss": 0.2705,
      "step": 932
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.72694993019104,
      "learning_rate": 0.00010365606534811423,
      "loss": 0.2194,
      "step": 933
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.4917081296443939,
      "learning_rate": 0.00010348994967025012,
      "loss": 1.0842,
      "step": 934
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.6921563744544983,
      "learning_rate": 0.00010332382434976266,
      "loss": 0.5801,
      "step": 935
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.4937489628791809,
      "learning_rate": 0.0001031576898456511,
      "loss": 0.7167,
      "step": 936
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.23887041211128235,
      "learning_rate": 0.00010299154661693987,
      "loss": 0.6585,
      "step": 937
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.6684651970863342,
      "learning_rate": 0.00010282539512267757,
      "loss": 0.6252,
      "step": 938
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.2771519124507904,
      "learning_rate": 0.00010265923582193573,
      "loss": 0.6683,
      "step": 939
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.4243355393409729,
      "learning_rate": 0.0001024930691738073,
      "loss": 0.1698,
      "step": 940
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.5778141617774963,
      "learning_rate": 0.00010232689563740563,
      "loss": 0.6546,
      "step": 941
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.5111245512962341,
      "learning_rate": 0.00010216071567186312,
      "loss": 0.2172,
      "step": 942
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.43212172389030457,
      "learning_rate": 0.00010199452973632981,
      "loss": 0.6029,
      "step": 943
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.5338983535766602,
      "learning_rate": 0.00010182833828997238,
      "loss": 0.5504,
      "step": 944
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.9532368779182434,
      "learning_rate": 0.00010166214179197264,
      "loss": 0.4724,
      "step": 945
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.3191937804222107,
      "learning_rate": 0.00010149594070152638,
      "loss": 0.7334,
      "step": 946
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.7247849702835083,
      "learning_rate": 0.0001013297354778421,
      "loss": 0.5641,
      "step": 947
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3969646692276001,
      "learning_rate": 0.00010116352658013973,
      "loss": 0.3362,
      "step": 948
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1442451477050781,
      "learning_rate": 0.00010099731446764926,
      "loss": 0.4536,
      "step": 949
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.36780816316604614,
      "learning_rate": 0.00010083109959960973,
      "loss": 0.3626,
      "step": 950
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2609235644340515,
      "learning_rate": 0.00010066488243526761,
      "loss": 0.6026,
      "step": 951
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.31235870718955994,
      "learning_rate": 0.00010049866343387581,
      "loss": 0.2611,
      "step": 952
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9570428729057312,
      "eval_runtime": 61.8021,
      "eval_samples_per_second": 1.618,
      "eval_steps_per_second": 1.618,
      "step": 952
    },
    {
      "epoch": 2.01,
      "grad_norm": 0.29149293899536133,
      "learning_rate": 0.00010033244305469234,
      "loss": 0.1439,
      "step": 953
    },
    {
      "epoch": 2.01,
      "grad_norm": 0.48990726470947266,
      "learning_rate": 0.00010016622175697898,
      "loss": 0.3245,
      "step": 954
    },
    {
      "epoch": 2.01,
      "grad_norm": 0.8410664200782776,
      "learning_rate": 0.0001,
      "loss": 0.4141,
      "step": 955
    },
    {
      "epoch": 2.01,
      "grad_norm": 0.23176737129688263,
      "learning_rate": 9.983377824302106e-05,
      "loss": 0.4396,
      "step": 956
    },
    {
      "epoch": 2.01,
      "grad_norm": 0.37275928258895874,
      "learning_rate": 9.966755694530767e-05,
      "loss": 0.384,
      "step": 957
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.34968245029449463,
      "learning_rate": 9.950133656612421e-05,
      "loss": 0.3296,
      "step": 958
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.6505431532859802,
      "learning_rate": 9.933511756473244e-05,
      "loss": 0.1885,
      "step": 959
    },
    {
      "epoch": 2.02,
      "grad_norm": 1.4213581085205078,
      "learning_rate": 9.916890040039031e-05,
      "loss": 0.4766,
      "step": 960
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.5529109835624695,
      "learning_rate": 9.900268553235076e-05,
      "loss": 0.2335,
      "step": 961
    },
    {
      "epoch": 2.03,
      "grad_norm": 0.3431006371974945,
      "learning_rate": 9.883647341986032e-05,
      "loss": 0.4784,
      "step": 962
    },
    {
      "epoch": 2.03,
      "grad_norm": 0.4143410623073578,
      "learning_rate": 9.867026452215792e-05,
      "loss": 0.6342,
      "step": 963
    },
    {
      "epoch": 2.03,
      "grad_norm": 0.3886817395687103,
      "learning_rate": 9.850405929847366e-05,
      "loss": 0.1899,
      "step": 964
    },
    {
      "epoch": 2.03,
      "grad_norm": 0.3255102336406708,
      "learning_rate": 9.833785820802739e-05,
      "loss": 0.1885,
      "step": 965
    },
    {
      "epoch": 2.03,
      "grad_norm": 0.23849962651729584,
      "learning_rate": 9.817166171002765e-05,
      "loss": 0.2219,
      "step": 966
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.6556320190429688,
      "learning_rate": 9.800547026367022e-05,
      "loss": 0.2923,
      "step": 967
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.7272720336914062,
      "learning_rate": 9.783928432813688e-05,
      "loss": 0.5208,
      "step": 968
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.3971239924430847,
      "learning_rate": 9.767310436259438e-05,
      "loss": 0.2383,
      "step": 969
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.2979855537414551,
      "learning_rate": 9.750693082619273e-05,
      "loss": 0.1653,
      "step": 970
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.6237159967422485,
      "learning_rate": 9.734076417806428e-05,
      "loss": 0.0886,
      "step": 971
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.9377636909484863,
      "learning_rate": 9.717460487732245e-05,
      "loss": 0.2564,
      "step": 972
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.19992011785507202,
      "learning_rate": 9.700845338306018e-05,
      "loss": 0.0384,
      "step": 973
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.3822425603866577,
      "learning_rate": 9.68423101543489e-05,
      "loss": 0.1232,
      "step": 974
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.2883025109767914,
      "learning_rate": 9.667617565023735e-05,
      "loss": 0.2164,
      "step": 975
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.6428910493850708,
      "learning_rate": 9.651005032974994e-05,
      "loss": 0.1398,
      "step": 976
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.28312209248542786,
      "learning_rate": 9.634393465188578e-05,
      "loss": 0.11,
      "step": 977
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.8573331236839294,
      "learning_rate": 9.617782907561748e-05,
      "loss": 0.2709,
      "step": 978
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.24638248980045319,
      "learning_rate": 9.601173405988953e-05,
      "loss": 0.1721,
      "step": 979
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.2952326834201813,
      "learning_rate": 9.584565006361734e-05,
      "loss": 0.5673,
      "step": 980
    },
    {
      "epoch": 2.07,
      "grad_norm": 0.417782723903656,
      "learning_rate": 9.567957754568596e-05,
      "loss": 0.4372,
      "step": 981
    },
    {
      "epoch": 2.07,
      "grad_norm": 0.4788338840007782,
      "learning_rate": 9.551351696494854e-05,
      "loss": 0.1572,
      "step": 982
    },
    {
      "epoch": 2.07,
      "grad_norm": 0.42218559980392456,
      "learning_rate": 9.534746878022534e-05,
      "loss": 0.3792,
      "step": 983
    },
    {
      "epoch": 2.07,
      "grad_norm": 0.8672342896461487,
      "learning_rate": 9.518143345030246e-05,
      "loss": 0.589,
      "step": 984
    },
    {
      "epoch": 2.07,
      "grad_norm": 0.3684612214565277,
      "learning_rate": 9.501541143393028e-05,
      "loss": 0.1279,
      "step": 985
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.533931314945221,
      "learning_rate": 9.48494031898226e-05,
      "loss": 0.1256,
      "step": 986
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.2679530084133148,
      "learning_rate": 9.468340917665508e-05,
      "loss": 0.1006,
      "step": 987
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.2058538943529129,
      "learning_rate": 9.451742985306398e-05,
      "loss": 0.0577,
      "step": 988
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.3021174669265747,
      "learning_rate": 9.435146567764515e-05,
      "loss": 0.2261,
      "step": 989
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.6816737055778503,
      "learning_rate": 9.418551710895243e-05,
      "loss": 0.3723,
      "step": 990
    },
    {
      "epoch": 2.09,
      "grad_norm": 0.4222981929779053,
      "learning_rate": 9.401958460549658e-05,
      "loss": 0.0325,
      "step": 991
    },
    {
      "epoch": 2.09,
      "grad_norm": 0.16284583508968353,
      "learning_rate": 9.385366862574404e-05,
      "loss": 0.1287,
      "step": 992
    },
    {
      "epoch": 2.09,
      "grad_norm": 1.3745120763778687,
      "learning_rate": 9.368776962811552e-05,
      "loss": 0.3241,
      "step": 993
    },
    {
      "epoch": 2.09,
      "grad_norm": 0.36204075813293457,
      "learning_rate": 9.352188807098481e-05,
      "loss": 0.2495,
      "step": 994
    },
    {
      "epoch": 2.09,
      "grad_norm": 0.19530382752418518,
      "learning_rate": 9.335602441267759e-05,
      "loss": 0.2201,
      "step": 995
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.2768145203590393,
      "learning_rate": 9.319017911147e-05,
      "loss": 0.2036,
      "step": 996
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.28405070304870605,
      "learning_rate": 9.302435262558747e-05,
      "loss": 0.4085,
      "step": 997
    },
    {
      "epoch": 2.1,
      "grad_norm": 4.290142059326172,
      "learning_rate": 9.285854541320352e-05,
      "loss": 0.0938,
      "step": 998
    },
    {
      "epoch": 2.1,
      "grad_norm": 1.0401676893234253,
      "learning_rate": 9.269275793243833e-05,
      "loss": 0.5443,
      "step": 999
    },
    {
      "epoch": 2.11,
      "grad_norm": 1.6484922170639038,
      "learning_rate": 9.252699064135758e-05,
      "loss": 0.5032,
      "step": 1000
    },
    {
      "epoch": 2.11,
      "grad_norm": 0.3814872205257416,
      "learning_rate": 9.236124399797122e-05,
      "loss": 0.3484,
      "step": 1001
    },
    {
      "epoch": 2.11,
      "grad_norm": 0.5454087257385254,
      "learning_rate": 9.219551846023211e-05,
      "loss": 0.0768,
      "step": 1002
    },
    {
      "epoch": 2.11,
      "grad_norm": 0.7552561163902283,
      "learning_rate": 9.202981448603477e-05,
      "loss": 0.3679,
      "step": 1003
    },
    {
      "epoch": 2.11,
      "grad_norm": 1.8529096841812134,
      "learning_rate": 9.186413253321418e-05,
      "loss": 0.3955,
      "step": 1004
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.18287956714630127,
      "learning_rate": 9.169847305954447e-05,
      "loss": 0.0373,
      "step": 1005
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.302222341299057,
      "learning_rate": 9.153283652273768e-05,
      "loss": 0.3458,
      "step": 1006
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.3268778324127197,
      "learning_rate": 9.136722338044243e-05,
      "loss": 0.0853,
      "step": 1007
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.2930258512496948,
      "learning_rate": 9.120163409024271e-05,
      "loss": 0.1806,
      "step": 1008
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.4745717942714691,
      "learning_rate": 9.103606910965666e-05,
      "loss": 0.204,
      "step": 1009
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.45598700642585754,
      "learning_rate": 9.087052889613518e-05,
      "loss": 0.1858,
      "step": 1010
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.23771706223487854,
      "learning_rate": 9.070501390706079e-05,
      "loss": 0.0799,
      "step": 1011
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.6027151942253113,
      "learning_rate": 9.05395245997463e-05,
      "loss": 0.398,
      "step": 1012
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.8044284582138062,
      "learning_rate": 9.037406143143356e-05,
      "loss": 0.1046,
      "step": 1013
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.23316510021686554,
      "learning_rate": 9.020862485929219e-05,
      "loss": 0.2189,
      "step": 1014
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.4902825355529785,
      "learning_rate": 9.004321534041835e-05,
      "loss": 0.2999,
      "step": 1015
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.3512743413448334,
      "learning_rate": 8.987783333183344e-05,
      "loss": 0.0409,
      "step": 1016
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.29709306359291077,
      "learning_rate": 8.971247929048283e-05,
      "loss": 0.19,
      "step": 1017
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.6619227528572083,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.1516,
      "step": 1018
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.5215200781822205,
      "learning_rate": 8.938185693687853e-05,
      "loss": 0.3649,
      "step": 1019
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.28022971749305725,
      "learning_rate": 8.921658953812415e-05,
      "loss": 0.2562,
      "step": 1020
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.41529372334480286,
      "learning_rate": 8.905135193360033e-05,
      "loss": 0.228,
      "step": 1021
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.3765081465244293,
      "learning_rate": 8.888614457985341e-05,
      "loss": 0.079,
      "step": 1022
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.6531975865364075,
      "learning_rate": 8.872096793334624e-05,
      "loss": 0.3251,
      "step": 1023
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.3692251145839691,
      "learning_rate": 8.855582245045683e-05,
      "loss": 0.1668,
      "step": 1024
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.4639212489128113,
      "learning_rate": 8.839070858747697e-05,
      "loss": 0.2352,
      "step": 1025
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.5719773769378662,
      "learning_rate": 8.822562680061125e-05,
      "loss": 0.7878,
      "step": 1026
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.2982478439807892,
      "learning_rate": 8.806057754597558e-05,
      "loss": 0.2832,
      "step": 1027
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.2849707305431366,
      "learning_rate": 8.789556127959585e-05,
      "loss": 0.3516,
      "step": 1028
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.16983425617218018,
      "learning_rate": 8.773057845740702e-05,
      "loss": 0.0755,
      "step": 1029
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.7474312782287598,
      "learning_rate": 8.756562953525152e-05,
      "loss": 0.1744,
      "step": 1030
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.44700291752815247,
      "learning_rate": 8.740071496887803e-05,
      "loss": 0.1424,
      "step": 1031
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.5309647917747498,
      "learning_rate": 8.723583521394054e-05,
      "loss": 0.047,
      "step": 1032
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.3638722002506256,
      "learning_rate": 8.70709907259967e-05,
      "loss": 0.4982,
      "step": 1033
    },
    {
      "epoch": 2.18,
      "grad_norm": 1.1174355745315552,
      "learning_rate": 8.690618196050666e-05,
      "loss": 0.197,
      "step": 1034
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.3625263571739197,
      "learning_rate": 8.674140937283208e-05,
      "loss": 0.0991,
      "step": 1035
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.883642315864563,
      "learning_rate": 8.657667341823448e-05,
      "loss": 0.451,
      "step": 1036
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.32223352789878845,
      "learning_rate": 8.641197455187417e-05,
      "loss": 0.4483,
      "step": 1037
    },
    {
      "epoch": 2.19,
      "grad_norm": 0.39049550890922546,
      "learning_rate": 8.624731322880912e-05,
      "loss": 0.2865,
      "step": 1038
    },
    {
      "epoch": 2.19,
      "grad_norm": 0.886722981929779,
      "learning_rate": 8.608268990399349e-05,
      "loss": 0.4363,
      "step": 1039
    },
    {
      "epoch": 2.19,
      "grad_norm": 0.8225802183151245,
      "learning_rate": 8.591810503227635e-05,
      "loss": 0.0689,
      "step": 1040
    },
    {
      "epoch": 2.19,
      "grad_norm": 0.5393767356872559,
      "learning_rate": 8.575355906840072e-05,
      "loss": 0.2782,
      "step": 1041
    },
    {
      "epoch": 2.19,
      "grad_norm": 0.3159850835800171,
      "learning_rate": 8.558905246700201e-05,
      "loss": 0.4313,
      "step": 1042
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.17237627506256104,
      "learning_rate": 8.542458568260682e-05,
      "loss": 0.0598,
      "step": 1043
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.3424827456474304,
      "learning_rate": 8.526015916963191e-05,
      "loss": 0.0955,
      "step": 1044
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.22092819213867188,
      "learning_rate": 8.509577338238255e-05,
      "loss": 0.1096,
      "step": 1045
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.3480028212070465,
      "learning_rate": 8.49314287750517e-05,
      "loss": 0.499,
      "step": 1046
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.24549205601215363,
      "learning_rate": 8.476712580171838e-05,
      "loss": 0.2929,
      "step": 1047
    },
    {
      "epoch": 2.21,
      "grad_norm": 0.4028603136539459,
      "learning_rate": 8.460286491634663e-05,
      "loss": 0.3242,
      "step": 1048
    },
    {
      "epoch": 2.21,
      "grad_norm": 0.6208504438400269,
      "learning_rate": 8.443864657278428e-05,
      "loss": 0.4581,
      "step": 1049
    },
    {
      "epoch": 2.21,
      "grad_norm": 0.3889882266521454,
      "learning_rate": 8.427447122476148e-05,
      "loss": 0.4558,
      "step": 1050
    },
    {
      "epoch": 2.21,
      "grad_norm": 0.3713911771774292,
      "learning_rate": 8.411033932588967e-05,
      "loss": 0.5298,
      "step": 1051
    },
    {
      "epoch": 2.21,
      "grad_norm": 0.4244590401649475,
      "learning_rate": 8.394625132966025e-05,
      "loss": 0.2284,
      "step": 1052
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.3483653664588928,
      "learning_rate": 8.378220768944327e-05,
      "loss": 0.3504,
      "step": 1053
    },
    {
      "epoch": 2.22,
      "grad_norm": 1.9254424571990967,
      "learning_rate": 8.361820885848624e-05,
      "loss": 0.2707,
      "step": 1054
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.606145977973938,
      "learning_rate": 8.345425528991288e-05,
      "loss": 0.3264,
      "step": 1055
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.5714905261993408,
      "learning_rate": 8.329034743672187e-05,
      "loss": 0.1881,
      "step": 1056
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.8185067176818848,
      "learning_rate": 8.31264857517855e-05,
      "loss": 0.362,
      "step": 1057
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.6066401600837708,
      "learning_rate": 8.296267068784862e-05,
      "loss": 0.3876,
      "step": 1058
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.4317091107368469,
      "learning_rate": 8.279890269752715e-05,
      "loss": 0.4905,
      "step": 1059
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.5521796941757202,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.1143,
      "step": 1060
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.5201196670532227,
      "learning_rate": 8.247150974754275e-05,
      "loss": 0.2074,
      "step": 1061
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.6514804363250732,
      "learning_rate": 8.230788569245648e-05,
      "loss": 0.1698,
      "step": 1062
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.3170391917228699,
      "learning_rate": 8.214431052013634e-05,
      "loss": 0.1715,
      "step": 1063
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.2641740143299103,
      "learning_rate": 8.198078468253557e-05,
      "loss": 0.2376,
      "step": 1064
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.49258503317832947,
      "learning_rate": 8.181730863147093e-05,
      "loss": 0.8573,
      "step": 1065
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.30264657735824585,
      "learning_rate": 8.165388281862178e-05,
      "loss": 0.1837,
      "step": 1066
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.26163825392723083,
      "learning_rate": 8.149050769552856e-05,
      "loss": 0.1082,
      "step": 1067
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.263866126537323,
      "learning_rate": 8.132718371359166e-05,
      "loss": 0.0358,
      "step": 1068
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.3995482623577118,
      "learning_rate": 8.116391132407033e-05,
      "loss": 0.5514,
      "step": 1069
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.39222079515457153,
      "learning_rate": 8.100069097808103e-05,
      "loss": 0.4839,
      "step": 1070
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.2744399309158325,
      "learning_rate": 8.083752312659654e-05,
      "loss": 0.1999,
      "step": 1071
    },
    {
      "epoch": 2.25,
      "eval_loss": 1.0414544343948364,
      "eval_runtime": 61.5922,
      "eval_samples_per_second": 1.624,
      "eval_steps_per_second": 1.624,
      "step": 1071
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.2859790623188019,
      "learning_rate": 8.067440822044469e-05,
      "loss": 0.1046,
      "step": 1072
    },
    {
      "epoch": 2.26,
      "grad_norm": 1.1303648948669434,
      "learning_rate": 8.051134671030687e-05,
      "loss": 0.4458,
      "step": 1073
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.7454203963279724,
      "learning_rate": 8.034833904671698e-05,
      "loss": 0.3143,
      "step": 1074
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.2475353479385376,
      "learning_rate": 8.018538568006027e-05,
      "loss": 0.1534,
      "step": 1075
    },
    {
      "epoch": 2.27,
      "grad_norm": 0.41427668929100037,
      "learning_rate": 8.002248706057177e-05,
      "loss": 0.172,
      "step": 1076
    },
    {
      "epoch": 2.27,
      "grad_norm": 0.23500694334506989,
      "learning_rate": 7.985964363833532e-05,
      "loss": 0.0494,
      "step": 1077
    },
    {
      "epoch": 2.27,
      "grad_norm": 0.30438652634620667,
      "learning_rate": 7.96968558632824e-05,
      "loss": 0.1334,
      "step": 1078
    },
    {
      "epoch": 2.27,
      "grad_norm": 0.4113299548625946,
      "learning_rate": 7.953412418519052e-05,
      "loss": 0.3013,
      "step": 1079
    },
    {
      "epoch": 2.27,
      "grad_norm": 0.28593701124191284,
      "learning_rate": 7.937144905368226e-05,
      "loss": 0.1119,
      "step": 1080
    },
    {
      "epoch": 2.28,
      "grad_norm": 0.3217616081237793,
      "learning_rate": 7.920883091822408e-05,
      "loss": 0.3012,
      "step": 1081
    },
    {
      "epoch": 2.28,
      "grad_norm": 0.39298737049102783,
      "learning_rate": 7.904627022812483e-05,
      "loss": 0.5322,
      "step": 1082
    },
    {
      "epoch": 2.28,
      "grad_norm": 0.3343609869480133,
      "learning_rate": 7.888376743253463e-05,
      "loss": 0.2569,
      "step": 1083
    },
    {
      "epoch": 2.28,
      "grad_norm": 0.7963635325431824,
      "learning_rate": 7.872132298044382e-05,
      "loss": 0.282,
      "step": 1084
    },
    {
      "epoch": 2.28,
      "grad_norm": 0.4038046896457672,
      "learning_rate": 7.855893732068125e-05,
      "loss": 0.203,
      "step": 1085
    },
    {
      "epoch": 2.29,
      "grad_norm": 0.3325504958629608,
      "learning_rate": 7.839661090191362e-05,
      "loss": 0.353,
      "step": 1086
    },
    {
      "epoch": 2.29,
      "grad_norm": 0.46112361550331116,
      "learning_rate": 7.823434417264378e-05,
      "loss": 0.3071,
      "step": 1087
    },
    {
      "epoch": 2.29,
      "grad_norm": 0.36491167545318604,
      "learning_rate": 7.807213758120966e-05,
      "loss": 0.352,
      "step": 1088
    },
    {
      "epoch": 2.29,
      "grad_norm": 0.3772267997264862,
      "learning_rate": 7.790999157578314e-05,
      "loss": 0.3064,
      "step": 1089
    },
    {
      "epoch": 2.29,
      "grad_norm": 0.4712262749671936,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.2215,
      "step": 1090
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.634762167930603,
      "learning_rate": 7.758588311480174e-05,
      "loss": 0.1912,
      "step": 1091
    },
    {
      "epoch": 2.3,
      "grad_norm": 1.0294770002365112,
      "learning_rate": 7.742392155474858e-05,
      "loss": 0.1456,
      "step": 1092
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.3933314383029938,
      "learning_rate": 7.726202237170387e-05,
      "loss": 0.2846,
      "step": 1093
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.30901187658309937,
      "learning_rate": 7.710018601299004e-05,
      "loss": 0.2486,
      "step": 1094
    },
    {
      "epoch": 2.31,
      "grad_norm": 0.30429914593696594,
      "learning_rate": 7.693841292575598e-05,
      "loss": 0.387,
      "step": 1095
    },
    {
      "epoch": 2.31,
      "grad_norm": 0.2635176181793213,
      "learning_rate": 7.677670355697577e-05,
      "loss": 0.1412,
      "step": 1096
    },
    {
      "epoch": 2.31,
      "grad_norm": 0.3051837086677551,
      "learning_rate": 7.661505835344732e-05,
      "loss": 0.1199,
      "step": 1097
    },
    {
      "epoch": 2.31,
      "grad_norm": 0.4841059744358063,
      "learning_rate": 7.645347776179144e-05,
      "loss": 0.1758,
      "step": 1098
    },
    {
      "epoch": 2.31,
      "grad_norm": 0.7497323155403137,
      "learning_rate": 7.629196222845026e-05,
      "loss": 0.2512,
      "step": 1099
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.3562595546245575,
      "learning_rate": 7.613051219968623e-05,
      "loss": 0.2186,
      "step": 1100
    },
    {
      "epoch": 2.32,
      "grad_norm": 1.2094510793685913,
      "learning_rate": 7.596912812158083e-05,
      "loss": 0.2998,
      "step": 1101
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.6023332476615906,
      "learning_rate": 7.580781044003324e-05,
      "loss": 0.1246,
      "step": 1102
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.4656884968280792,
      "learning_rate": 7.564655960075927e-05,
      "loss": 0.2749,
      "step": 1103
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.6948531866073608,
      "learning_rate": 7.548537604929001e-05,
      "loss": 0.5442,
      "step": 1104
    },
    {
      "epoch": 2.33,
      "grad_norm": 1.315352201461792,
      "learning_rate": 7.532426023097063e-05,
      "loss": 0.4247,
      "step": 1105
    },
    {
      "epoch": 2.33,
      "grad_norm": 0.45906028151512146,
      "learning_rate": 7.516321259095921e-05,
      "loss": 0.1876,
      "step": 1106
    },
    {
      "epoch": 2.33,
      "grad_norm": 0.5653383135795593,
      "learning_rate": 7.500223357422536e-05,
      "loss": 0.1735,
      "step": 1107
    },
    {
      "epoch": 2.33,
      "grad_norm": 0.3202337920665741,
      "learning_rate": 7.484132362554915e-05,
      "loss": 0.3102,
      "step": 1108
    },
    {
      "epoch": 2.33,
      "grad_norm": 0.612182080745697,
      "learning_rate": 7.468048318951983e-05,
      "loss": 0.4846,
      "step": 1109
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.3194877803325653,
      "learning_rate": 7.451971271053455e-05,
      "loss": 0.059,
      "step": 1110
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.5662250518798828,
      "learning_rate": 7.435901263279716e-05,
      "loss": 0.0554,
      "step": 1111
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.37810468673706055,
      "learning_rate": 7.419838340031708e-05,
      "loss": 0.2623,
      "step": 1112
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.4857700765132904,
      "learning_rate": 7.403782545690787e-05,
      "loss": 0.3497,
      "step": 1113
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.22125770151615143,
      "learning_rate": 7.387733924618617e-05,
      "loss": 0.035,
      "step": 1114
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.3674735426902771,
      "learning_rate": 7.371692521157048e-05,
      "loss": 0.625,
      "step": 1115
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.45555412769317627,
      "learning_rate": 7.35565837962798e-05,
      "loss": 0.4273,
      "step": 1116
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.7296884059906006,
      "learning_rate": 7.339631544333249e-05,
      "loss": 0.3723,
      "step": 1117
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.41084760427474976,
      "learning_rate": 7.323612059554513e-05,
      "loss": 0.1341,
      "step": 1118
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.4270436465740204,
      "learning_rate": 7.307599969553111e-05,
      "loss": 0.4426,
      "step": 1119
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.23851610720157623,
      "learning_rate": 7.291595318569951e-05,
      "loss": 0.3558,
      "step": 1120
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.3444399833679199,
      "learning_rate": 7.275598150825393e-05,
      "loss": 0.3752,
      "step": 1121
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.43362972140312195,
      "learning_rate": 7.25960851051912e-05,
      "loss": 0.1467,
      "step": 1122
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.6192312240600586,
      "learning_rate": 7.243626441830009e-05,
      "loss": 0.376,
      "step": 1123
    },
    {
      "epoch": 2.37,
      "grad_norm": 0.5423337817192078,
      "learning_rate": 7.227651988916031e-05,
      "loss": 0.4163,
      "step": 1124
    },
    {
      "epoch": 2.37,
      "grad_norm": 1.0165411233901978,
      "learning_rate": 7.211685195914097e-05,
      "loss": 0.3563,
      "step": 1125
    },
    {
      "epoch": 2.37,
      "grad_norm": 0.544395923614502,
      "learning_rate": 7.195726106939974e-05,
      "loss": 0.3344,
      "step": 1126
    },
    {
      "epoch": 2.37,
      "grad_norm": 0.32629308104515076,
      "learning_rate": 7.179774766088126e-05,
      "loss": 0.3126,
      "step": 1127
    },
    {
      "epoch": 2.37,
      "grad_norm": 0.3347086012363434,
      "learning_rate": 7.163831217431615e-05,
      "loss": 0.3867,
      "step": 1128
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.35171234607696533,
      "learning_rate": 7.14789550502198e-05,
      "loss": 0.3186,
      "step": 1129
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.41637492179870605,
      "learning_rate": 7.131967672889101e-05,
      "loss": 0.308,
      "step": 1130
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.3099021315574646,
      "learning_rate": 7.116047765041079e-05,
      "loss": 0.2962,
      "step": 1131
    },
    {
      "epoch": 2.38,
      "grad_norm": 1.0291274785995483,
      "learning_rate": 7.100135825464139e-05,
      "loss": 0.0858,
      "step": 1132
    },
    {
      "epoch": 2.39,
      "grad_norm": 0.3761727213859558,
      "learning_rate": 7.084231898122477e-05,
      "loss": 0.3224,
      "step": 1133
    },
    {
      "epoch": 2.39,
      "grad_norm": 0.21233822405338287,
      "learning_rate": 7.068336026958146e-05,
      "loss": 0.0349,
      "step": 1134
    },
    {
      "epoch": 2.39,
      "grad_norm": 1.1428797245025635,
      "learning_rate": 7.052448255890957e-05,
      "loss": 0.2133,
      "step": 1135
    },
    {
      "epoch": 2.39,
      "grad_norm": 0.44500914216041565,
      "learning_rate": 7.036568628818331e-05,
      "loss": 0.2843,
      "step": 1136
    },
    {
      "epoch": 2.39,
      "grad_norm": 0.4282483458518982,
      "learning_rate": 7.02069718961518e-05,
      "loss": 0.1139,
      "step": 1137
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.3170280456542969,
      "learning_rate": 7.004833982133808e-05,
      "loss": 0.1759,
      "step": 1138
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.54608553647995,
      "learning_rate": 6.988979050203768e-05,
      "loss": 0.32,
      "step": 1139
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.40999898314476013,
      "learning_rate": 6.973132437631742e-05,
      "loss": 0.1294,
      "step": 1140
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.5694934129714966,
      "learning_rate": 6.957294188201438e-05,
      "loss": 0.4025,
      "step": 1141
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.19408564269542694,
      "learning_rate": 6.941464345673449e-05,
      "loss": 0.0711,
      "step": 1142
    },
    {
      "epoch": 2.41,
      "grad_norm": 1.0297935009002686,
      "learning_rate": 6.925642953785136e-05,
      "loss": 0.4554,
      "step": 1143
    },
    {
      "epoch": 2.41,
      "grad_norm": 0.6384499669075012,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.7755,
      "step": 1144
    },
    {
      "epoch": 2.41,
      "grad_norm": 0.35377582907676697,
      "learning_rate": 6.894025696760163e-05,
      "loss": 0.3368,
      "step": 1145
    },
    {
      "epoch": 2.41,
      "grad_norm": 0.6168931126594543,
      "learning_rate": 6.878229918981003e-05,
      "loss": 0.3632,
      "step": 1146
    },
    {
      "epoch": 2.41,
      "grad_norm": 0.4333438575267792,
      "learning_rate": 6.862442766556297e-05,
      "loss": 0.4481,
      "step": 1147
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.3434096872806549,
      "learning_rate": 6.846664283105455e-05,
      "loss": 0.4594,
      "step": 1148
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.8049106001853943,
      "learning_rate": 6.830894512223946e-05,
      "loss": 0.1239,
      "step": 1149
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.21577104926109314,
      "learning_rate": 6.815133497483157e-05,
      "loss": 0.0594,
      "step": 1150
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.3035653829574585,
      "learning_rate": 6.799381282430284e-05,
      "loss": 0.2847,
      "step": 1151
    },
    {
      "epoch": 2.43,
      "grad_norm": 0.346308171749115,
      "learning_rate": 6.783637910588216e-05,
      "loss": 0.4226,
      "step": 1152
    },
    {
      "epoch": 2.43,
      "grad_norm": 0.40908312797546387,
      "learning_rate": 6.767903425455401e-05,
      "loss": 0.5447,
      "step": 1153
    },
    {
      "epoch": 2.43,
      "grad_norm": 0.44740766286849976,
      "learning_rate": 6.752177870505736e-05,
      "loss": 0.1076,
      "step": 1154
    },
    {
      "epoch": 2.43,
      "grad_norm": 0.3309715986251831,
      "learning_rate": 6.736461289188445e-05,
      "loss": 0.1884,
      "step": 1155
    },
    {
      "epoch": 2.43,
      "grad_norm": 0.29329484701156616,
      "learning_rate": 6.720753724927958e-05,
      "loss": 0.3133,
      "step": 1156
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.6964632272720337,
      "learning_rate": 6.705055221123788e-05,
      "loss": 0.5469,
      "step": 1157
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.3863834738731384,
      "learning_rate": 6.68936582115042e-05,
      "loss": 0.4276,
      "step": 1158
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.32202091813087463,
      "learning_rate": 6.673685568357182e-05,
      "loss": 0.2867,
      "step": 1159
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.45666739344596863,
      "learning_rate": 6.658014506068126e-05,
      "loss": 0.3404,
      "step": 1160
    },
    {
      "epoch": 2.44,
      "grad_norm": 1.0935767889022827,
      "learning_rate": 6.642352677581917e-05,
      "loss": 0.2642,
      "step": 1161
    },
    {
      "epoch": 2.45,
      "grad_norm": 0.49452221393585205,
      "learning_rate": 6.626700126171702e-05,
      "loss": 0.1137,
      "step": 1162
    },
    {
      "epoch": 2.45,
      "grad_norm": 0.6080031394958496,
      "learning_rate": 6.611056895084998e-05,
      "loss": 0.2378,
      "step": 1163
    },
    {
      "epoch": 2.45,
      "grad_norm": 0.3335520327091217,
      "learning_rate": 6.595423027543571e-05,
      "loss": 0.191,
      "step": 1164
    },
    {
      "epoch": 2.45,
      "grad_norm": 0.8033477067947388,
      "learning_rate": 6.579798566743314e-05,
      "loss": 0.2892,
      "step": 1165
    },
    {
      "epoch": 2.45,
      "grad_norm": 2.931178331375122,
      "learning_rate": 6.56418355585413e-05,
      "loss": 0.4743,
      "step": 1166
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.48405173420906067,
      "learning_rate": 6.548578038019815e-05,
      "loss": 0.2486,
      "step": 1167
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.6350341439247131,
      "learning_rate": 6.532982056357928e-05,
      "loss": 0.3742,
      "step": 1168
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.36276134848594666,
      "learning_rate": 6.517395653959694e-05,
      "loss": 0.2189,
      "step": 1169
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.6255000233650208,
      "learning_rate": 6.501818873889855e-05,
      "loss": 0.2459,
      "step": 1170
    },
    {
      "epoch": 2.47,
      "grad_norm": 0.36843547224998474,
      "learning_rate": 6.486251759186572e-05,
      "loss": 0.3125,
      "step": 1171
    },
    {
      "epoch": 2.47,
      "grad_norm": 0.40621039271354675,
      "learning_rate": 6.470694352861312e-05,
      "loss": 0.2004,
      "step": 1172
    },
    {
      "epoch": 2.47,
      "grad_norm": 0.3194919526576996,
      "learning_rate": 6.455146697898703e-05,
      "loss": 0.3094,
      "step": 1173
    },
    {
      "epoch": 2.47,
      "grad_norm": 0.21008367836475372,
      "learning_rate": 6.439608837256432e-05,
      "loss": 0.0541,
      "step": 1174
    },
    {
      "epoch": 2.47,
      "grad_norm": 0.3361469507217407,
      "learning_rate": 6.424080813865138e-05,
      "loss": 0.5029,
      "step": 1175
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.24147911369800568,
      "learning_rate": 6.408562670628266e-05,
      "loss": 0.1654,
      "step": 1176
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.8166019916534424,
      "learning_rate": 6.393054450421963e-05,
      "loss": 0.3575,
      "step": 1177
    },
    {
      "epoch": 2.48,
      "grad_norm": 1.122574806213379,
      "learning_rate": 6.377556196094973e-05,
      "loss": 0.7164,
      "step": 1178
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.7233923673629761,
      "learning_rate": 6.362067950468489e-05,
      "loss": 0.3521,
      "step": 1179
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.41336318850517273,
      "learning_rate": 6.34658975633605e-05,
      "loss": 0.3212,
      "step": 1180
    },
    {
      "epoch": 2.49,
      "grad_norm": 0.8844769597053528,
      "learning_rate": 6.331121656463441e-05,
      "loss": 0.0649,
      "step": 1181
    },
    {
      "epoch": 2.49,
      "grad_norm": 0.44808632135391235,
      "learning_rate": 6.315663693588534e-05,
      "loss": 0.3333,
      "step": 1182
    },
    {
      "epoch": 2.49,
      "grad_norm": 0.3650015592575073,
      "learning_rate": 6.300215910421212e-05,
      "loss": 0.1375,
      "step": 1183
    },
    {
      "epoch": 2.49,
      "grad_norm": 0.4140397310256958,
      "learning_rate": 6.28477834964322e-05,
      "loss": 0.1505,
      "step": 1184
    },
    {
      "epoch": 2.49,
      "grad_norm": 0.2868010401725769,
      "learning_rate": 6.269351053908061e-05,
      "loss": 0.0466,
      "step": 1185
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.3398640751838684,
      "learning_rate": 6.25393406584088e-05,
      "loss": 0.088,
      "step": 1186
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.488488107919693,
      "learning_rate": 6.238527428038339e-05,
      "loss": 0.3337,
      "step": 1187
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.7760544419288635,
      "learning_rate": 6.223131183068499e-05,
      "loss": 0.5087,
      "step": 1188
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.48542800545692444,
      "learning_rate": 6.207745373470716e-05,
      "loss": 0.122,
      "step": 1189
    },
    {
      "epoch": 2.51,
      "grad_norm": 0.21850326657295227,
      "learning_rate": 6.192370041755505e-05,
      "loss": 0.1532,
      "step": 1190
    },
    {
      "epoch": 2.51,
      "eval_loss": 1.0776242017745972,
      "eval_runtime": 61.9441,
      "eval_samples_per_second": 1.614,
      "eval_steps_per_second": 1.614,
      "step": 1190
    },
    {
      "epoch": 2.51,
      "grad_norm": 0.4770156443119049,
      "learning_rate": 6.177005230404431e-05,
      "loss": 0.3974,
      "step": 1191
    },
    {
      "epoch": 2.51,
      "grad_norm": 1.0366460084915161,
      "learning_rate": 6.161650981869998e-05,
      "loss": 0.2319,
      "step": 1192
    },
    {
      "epoch": 2.51,
      "grad_norm": 0.3871290683746338,
      "learning_rate": 6.146307338575519e-05,
      "loss": 0.4389,
      "step": 1193
    },
    {
      "epoch": 2.51,
      "grad_norm": 0.44873878359794617,
      "learning_rate": 6.130974342915005e-05,
      "loss": 0.2469,
      "step": 1194
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.32535475492477417,
      "learning_rate": 6.115652037253053e-05,
      "loss": 0.239,
      "step": 1195
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.3552875220775604,
      "learning_rate": 6.100340463924723e-05,
      "loss": 0.2276,
      "step": 1196
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.45674723386764526,
      "learning_rate": 6.0850396652354125e-05,
      "loss": 0.3405,
      "step": 1197
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.29195958375930786,
      "learning_rate": 6.069749683460765e-05,
      "loss": 0.4767,
      "step": 1198
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.3897278308868408,
      "learning_rate": 6.0544705608465234e-05,
      "loss": 0.2277,
      "step": 1199
    },
    {
      "epoch": 2.53,
      "grad_norm": 0.250284880399704,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.2529,
      "step": 1200
    },
    {
      "epoch": 2.53,
      "grad_norm": 0.2508828043937683,
      "learning_rate": 6.023945061932119e-05,
      "loss": 0.0292,
      "step": 1201
    },
    {
      "epoch": 2.53,
      "grad_norm": 0.29530829191207886,
      "learning_rate": 6.008698769972967e-05,
      "loss": 0.1958,
      "step": 1202
    },
    {
      "epoch": 2.53,
      "grad_norm": 0.18633241951465607,
      "learning_rate": 5.9934635058560154e-05,
      "loss": 0.0424,
      "step": 1203
    },
    {
      "epoch": 2.53,
      "grad_norm": 0.7199178338050842,
      "learning_rate": 5.978239311675826e-05,
      "loss": 0.3123,
      "step": 1204
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.5743251442909241,
      "learning_rate": 5.963026229496378e-05,
      "loss": 0.18,
      "step": 1205
    },
    {
      "epoch": 2.54,
      "grad_norm": 2.2675962448120117,
      "learning_rate": 5.9478243013509505e-05,
      "loss": 0.324,
      "step": 1206
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.24627915024757385,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 0.1563,
      "step": 1207
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.5204538702964783,
      "learning_rate": 5.9174540751410487e-05,
      "loss": 0.1695,
      "step": 1208
    },
    {
      "epoch": 2.55,
      "grad_norm": 1.0078840255737305,
      "learning_rate": 5.902285860988576e-05,
      "loss": 0.2403,
      "step": 1209
    },
    {
      "epoch": 2.55,
      "grad_norm": 0.8918837904930115,
      "learning_rate": 5.887128968693887e-05,
      "loss": 0.2705,
      "step": 1210
    },
    {
      "epoch": 2.55,
      "grad_norm": 0.5288832783699036,
      "learning_rate": 5.871983440135005e-05,
      "loss": 0.3406,
      "step": 1211
    },
    {
      "epoch": 2.55,
      "grad_norm": 0.7802530527114868,
      "learning_rate": 5.856849317158563e-05,
      "loss": 0.4431,
      "step": 1212
    },
    {
      "epoch": 2.55,
      "grad_norm": 0.829023540019989,
      "learning_rate": 5.8417266415796745e-05,
      "loss": 0.1579,
      "step": 1213
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.2933697998523712,
      "learning_rate": 5.8266154551818216e-05,
      "loss": 0.292,
      "step": 1214
    },
    {
      "epoch": 2.56,
      "grad_norm": 1.175118327140808,
      "learning_rate": 5.8115157997167536e-05,
      "loss": 0.3135,
      "step": 1215
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.26484665274620056,
      "learning_rate": 5.796427716904347e-05,
      "loss": 0.0947,
      "step": 1216
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.290715754032135,
      "learning_rate": 5.7813512484325095e-05,
      "loss": 0.3051,
      "step": 1217
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.7810901403427124,
      "learning_rate": 5.7662864359570624e-05,
      "loss": 0.6841,
      "step": 1218
    },
    {
      "epoch": 2.57,
      "grad_norm": 0.5301364660263062,
      "learning_rate": 5.751233321101617e-05,
      "loss": 0.2107,
      "step": 1219
    },
    {
      "epoch": 2.57,
      "grad_norm": 0.3347890079021454,
      "learning_rate": 5.736191945457463e-05,
      "loss": 0.2544,
      "step": 1220
    },
    {
      "epoch": 2.57,
      "grad_norm": 0.34437447786331177,
      "learning_rate": 5.72116235058346e-05,
      "loss": 0.3537,
      "step": 1221
    },
    {
      "epoch": 2.57,
      "grad_norm": 1.3457096815109253,
      "learning_rate": 5.7061445780059074e-05,
      "loss": 0.462,
      "step": 1222
    },
    {
      "epoch": 2.57,
      "grad_norm": 0.32543686032295227,
      "learning_rate": 5.69113866921846e-05,
      "loss": 0.0387,
      "step": 1223
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.38246065378189087,
      "learning_rate": 5.676144665681974e-05,
      "loss": 0.3505,
      "step": 1224
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.35182633996009827,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.2105,
      "step": 1225
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.4109022617340088,
      "learning_rate": 5.6461925400407576e-05,
      "loss": 0.3537,
      "step": 1226
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.3107440173625946,
      "learning_rate": 5.631234500692828e-05,
      "loss": 0.1429,
      "step": 1227
    },
    {
      "epoch": 2.59,
      "grad_norm": 0.4284103512763977,
      "learning_rate": 5.616288532109225e-05,
      "loss": 0.2854,
      "step": 1228
    },
    {
      "epoch": 2.59,
      "grad_norm": 0.32733407616615295,
      "learning_rate": 5.601354675585209e-05,
      "loss": 0.2061,
      "step": 1229
    },
    {
      "epoch": 2.59,
      "grad_norm": 1.2653546333312988,
      "learning_rate": 5.58643297238256e-05,
      "loss": 0.2411,
      "step": 1230
    },
    {
      "epoch": 2.59,
      "grad_norm": 0.3521691560745239,
      "learning_rate": 5.571523463729487e-05,
      "loss": 0.2751,
      "step": 1231
    },
    {
      "epoch": 2.59,
      "grad_norm": 0.5209056735038757,
      "learning_rate": 5.5566261908204966e-05,
      "loss": 0.3047,
      "step": 1232
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.9035019278526306,
      "learning_rate": 5.541741194816299e-05,
      "loss": 0.3731,
      "step": 1233
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.34125107526779175,
      "learning_rate": 5.526868516843673e-05,
      "loss": 0.2955,
      "step": 1234
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.36946702003479004,
      "learning_rate": 5.5120081979953785e-05,
      "loss": 0.1661,
      "step": 1235
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.3534347414970398,
      "learning_rate": 5.497160279330014e-05,
      "loss": 0.4519,
      "step": 1236
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.2882026135921478,
      "learning_rate": 5.482324801871919e-05,
      "loss": 0.5972,
      "step": 1237
    },
    {
      "epoch": 2.61,
      "grad_norm": 0.7276318669319153,
      "learning_rate": 5.467501806611062e-05,
      "loss": 0.2326,
      "step": 1238
    },
    {
      "epoch": 2.61,
      "grad_norm": 0.23008614778518677,
      "learning_rate": 5.452691334502922e-05,
      "loss": 0.2549,
      "step": 1239
    },
    {
      "epoch": 2.61,
      "grad_norm": 0.23662728071212769,
      "learning_rate": 5.43789342646837e-05,
      "loss": 0.0845,
      "step": 1240
    },
    {
      "epoch": 2.61,
      "grad_norm": 1.2522404193878174,
      "learning_rate": 5.423108123393581e-05,
      "loss": 0.4237,
      "step": 1241
    },
    {
      "epoch": 2.61,
      "grad_norm": 0.2206917107105255,
      "learning_rate": 5.4083354661298814e-05,
      "loss": 0.1515,
      "step": 1242
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.3296979069709778,
      "learning_rate": 5.393575495493679e-05,
      "loss": 0.2217,
      "step": 1243
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.6194382905960083,
      "learning_rate": 5.378828252266308e-05,
      "loss": 0.3087,
      "step": 1244
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.1941995471715927,
      "learning_rate": 5.3640937771939436e-05,
      "loss": 0.0136,
      "step": 1245
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.3312687277793884,
      "learning_rate": 5.349372110987496e-05,
      "loss": 0.2721,
      "step": 1246
    },
    {
      "epoch": 2.63,
      "grad_norm": 0.40799418091773987,
      "learning_rate": 5.3346632943224695e-05,
      "loss": 0.492,
      "step": 1247
    },
    {
      "epoch": 2.63,
      "grad_norm": 1.0968602895736694,
      "learning_rate": 5.3199673678388685e-05,
      "loss": 0.3102,
      "step": 1248
    },
    {
      "epoch": 2.63,
      "grad_norm": 0.5079402327537537,
      "learning_rate": 5.305284372141095e-05,
      "loss": 0.361,
      "step": 1249
    },
    {
      "epoch": 2.63,
      "grad_norm": 1.0647687911987305,
      "learning_rate": 5.290614347797802e-05,
      "loss": 0.3519,
      "step": 1250
    },
    {
      "epoch": 2.63,
      "grad_norm": 0.9241762161254883,
      "learning_rate": 5.275957335341814e-05,
      "loss": 0.5112,
      "step": 1251
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.20941267907619476,
      "learning_rate": 5.261313375270014e-05,
      "loss": 0.0871,
      "step": 1252
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.3228456676006317,
      "learning_rate": 5.246682508043206e-05,
      "loss": 0.2729,
      "step": 1253
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.3993156850337982,
      "learning_rate": 5.232064774086022e-05,
      "loss": 0.2958,
      "step": 1254
    },
    {
      "epoch": 2.64,
      "grad_norm": 2.0890214443206787,
      "learning_rate": 5.217460213786821e-05,
      "loss": 0.2181,
      "step": 1255
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.35725289583206177,
      "learning_rate": 5.2028688674975415e-05,
      "loss": 0.4336,
      "step": 1256
    },
    {
      "epoch": 2.65,
      "grad_norm": 0.22372879087924957,
      "learning_rate": 5.188290775533624e-05,
      "loss": 0.2441,
      "step": 1257
    },
    {
      "epoch": 2.65,
      "grad_norm": 0.38314974308013916,
      "learning_rate": 5.1737259781738936e-05,
      "loss": 0.3979,
      "step": 1258
    },
    {
      "epoch": 2.65,
      "grad_norm": 0.3898037075996399,
      "learning_rate": 5.159174515660432e-05,
      "loss": 0.2707,
      "step": 1259
    },
    {
      "epoch": 2.65,
      "grad_norm": 0.5374806523323059,
      "learning_rate": 5.1446364281984774e-05,
      "loss": 0.2368,
      "step": 1260
    },
    {
      "epoch": 2.65,
      "grad_norm": 0.45632028579711914,
      "learning_rate": 5.130111755956327e-05,
      "loss": 0.4022,
      "step": 1261
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.635205090045929,
      "learning_rate": 5.115600539065197e-05,
      "loss": 0.286,
      "step": 1262
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.30840864777565,
      "learning_rate": 5.101102817619131e-05,
      "loss": 0.1724,
      "step": 1263
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.3157990276813507,
      "learning_rate": 5.086618631674888e-05,
      "loss": 0.1023,
      "step": 1264
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.6306793093681335,
      "learning_rate": 5.072148021251821e-05,
      "loss": 0.3076,
      "step": 1265
    },
    {
      "epoch": 2.67,
      "grad_norm": 0.6977675557136536,
      "learning_rate": 5.057691026331792e-05,
      "loss": 0.3178,
      "step": 1266
    },
    {
      "epoch": 2.67,
      "grad_norm": 0.6471707224845886,
      "learning_rate": 5.043247686859024e-05,
      "loss": 0.3459,
      "step": 1267
    },
    {
      "epoch": 2.67,
      "grad_norm": 0.28806617856025696,
      "learning_rate": 5.02881804274002e-05,
      "loss": 0.2028,
      "step": 1268
    },
    {
      "epoch": 2.67,
      "grad_norm": 0.3172370195388794,
      "learning_rate": 5.014402133843443e-05,
      "loss": 0.2296,
      "step": 1269
    },
    {
      "epoch": 2.67,
      "grad_norm": 0.48926007747650146,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.1085,
      "step": 1270
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.41491979360580444,
      "learning_rate": 4.9856116810023465e-05,
      "loss": 0.1794,
      "step": 1271
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.5332885980606079,
      "learning_rate": 4.971237216604967e-05,
      "loss": 0.3493,
      "step": 1272
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.19919279217720032,
      "learning_rate": 4.956876646524059e-05,
      "loss": 0.0328,
      "step": 1273
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.29925766587257385,
      "learning_rate": 4.942530010437435e-05,
      "loss": 0.2714,
      "step": 1274
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.576008677482605,
      "learning_rate": 4.92819734798441e-05,
      "loss": 0.2385,
      "step": 1275
    },
    {
      "epoch": 2.69,
      "grad_norm": 0.5098739862442017,
      "learning_rate": 4.913878698765686e-05,
      "loss": 0.1016,
      "step": 1276
    },
    {
      "epoch": 2.69,
      "grad_norm": 0.4307500123977661,
      "learning_rate": 4.899574102343247e-05,
      "loss": 0.2031,
      "step": 1277
    },
    {
      "epoch": 2.69,
      "grad_norm": 1.0047227144241333,
      "learning_rate": 4.885283598240259e-05,
      "loss": 0.3458,
      "step": 1278
    },
    {
      "epoch": 2.69,
      "grad_norm": 1.3505383729934692,
      "learning_rate": 4.87100722594094e-05,
      "loss": 0.4995,
      "step": 1279
    },
    {
      "epoch": 2.69,
      "grad_norm": 0.4602445960044861,
      "learning_rate": 4.856745024890466e-05,
      "loss": 0.223,
      "step": 1280
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.5431117415428162,
      "learning_rate": 4.842497034494859e-05,
      "loss": 0.1288,
      "step": 1281
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.25237104296684265,
      "learning_rate": 4.8282632941208725e-05,
      "loss": 0.2603,
      "step": 1282
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.6471454501152039,
      "learning_rate": 4.814043843095902e-05,
      "loss": 0.2201,
      "step": 1283
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.3411142826080322,
      "learning_rate": 4.799838720707846e-05,
      "loss": 0.4188,
      "step": 1284
    },
    {
      "epoch": 2.71,
      "grad_norm": 0.41913872957229614,
      "learning_rate": 4.78564796620502e-05,
      "loss": 0.3233,
      "step": 1285
    },
    {
      "epoch": 2.71,
      "grad_norm": 0.4495401084423065,
      "learning_rate": 4.771471618796043e-05,
      "loss": 0.1504,
      "step": 1286
    },
    {
      "epoch": 2.71,
      "grad_norm": 0.3317515254020691,
      "learning_rate": 4.757309717649723e-05,
      "loss": 0.2903,
      "step": 1287
    },
    {
      "epoch": 2.71,
      "grad_norm": 0.5954946279525757,
      "learning_rate": 4.743162301894952e-05,
      "loss": 0.3404,
      "step": 1288
    },
    {
      "epoch": 2.71,
      "grad_norm": 0.4872910678386688,
      "learning_rate": 4.729029410620615e-05,
      "loss": 0.4495,
      "step": 1289
    },
    {
      "epoch": 2.72,
      "grad_norm": 0.23028811812400818,
      "learning_rate": 4.7149110828754464e-05,
      "loss": 0.278,
      "step": 1290
    },
    {
      "epoch": 2.72,
      "grad_norm": 0.3303956389427185,
      "learning_rate": 4.700807357667952e-05,
      "loss": 0.1051,
      "step": 1291
    },
    {
      "epoch": 2.72,
      "grad_norm": 0.35193932056427,
      "learning_rate": 4.686718273966291e-05,
      "loss": 0.2968,
      "step": 1292
    },
    {
      "epoch": 2.72,
      "grad_norm": 0.2598091959953308,
      "learning_rate": 4.6726438706981644e-05,
      "loss": 0.0954,
      "step": 1293
    },
    {
      "epoch": 2.72,
      "grad_norm": 0.39768552780151367,
      "learning_rate": 4.658584186750713e-05,
      "loss": 0.0541,
      "step": 1294
    },
    {
      "epoch": 2.73,
      "grad_norm": 0.4370318055152893,
      "learning_rate": 4.644539260970416e-05,
      "loss": 0.4754,
      "step": 1295
    },
    {
      "epoch": 2.73,
      "grad_norm": 0.5983580350875854,
      "learning_rate": 4.6305091321629666e-05,
      "loss": 0.0712,
      "step": 1296
    },
    {
      "epoch": 2.73,
      "grad_norm": 0.4080672264099121,
      "learning_rate": 4.616493839093179e-05,
      "loss": 0.1945,
      "step": 1297
    },
    {
      "epoch": 2.73,
      "grad_norm": 0.3521052300930023,
      "learning_rate": 4.6024934204848745e-05,
      "loss": 0.191,
      "step": 1298
    },
    {
      "epoch": 2.73,
      "grad_norm": 0.8113175630569458,
      "learning_rate": 4.5885079150207776e-05,
      "loss": 0.5054,
      "step": 1299
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.899402916431427,
      "learning_rate": 4.574537361342407e-05,
      "loss": 0.2557,
      "step": 1300
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.8417747020721436,
      "learning_rate": 4.560581798049976e-05,
      "loss": 0.203,
      "step": 1301
    },
    {
      "epoch": 2.74,
      "grad_norm": 1.2963255643844604,
      "learning_rate": 4.5466412637022704e-05,
      "loss": 0.5346,
      "step": 1302
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.3572009801864624,
      "learning_rate": 4.532715796816564e-05,
      "loss": 0.2946,
      "step": 1303
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.6167850494384766,
      "learning_rate": 4.518805435868492e-05,
      "loss": 0.1102,
      "step": 1304
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.2798488736152649,
      "learning_rate": 4.50491021929194e-05,
      "loss": 0.1322,
      "step": 1305
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.2718496322631836,
      "learning_rate": 4.491030185478976e-05,
      "loss": 0.0642,
      "step": 1306
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.8502088785171509,
      "learning_rate": 4.4771653727797e-05,
      "loss": 0.298,
      "step": 1307
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.5349703431129456,
      "learning_rate": 4.4633158195021594e-05,
      "loss": 0.3594,
      "step": 1308
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.25136202573776245,
      "learning_rate": 4.449481563912251e-05,
      "loss": 0.0455,
      "step": 1309
    },
    {
      "epoch": 2.76,
      "eval_loss": 1.0920302867889404,
      "eval_runtime": 61.5845,
      "eval_samples_per_second": 1.624,
      "eval_steps_per_second": 1.624,
      "step": 1309
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.7967007160186768,
      "learning_rate": 4.435662644233594e-05,
      "loss": 0.1578,
      "step": 1310
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.3636241555213928,
      "learning_rate": 4.421859098647427e-05,
      "loss": 0.2332,
      "step": 1311
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.3658440411090851,
      "learning_rate": 4.4080709652925336e-05,
      "loss": 0.4128,
      "step": 1312
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.4984844923019409,
      "learning_rate": 4.394298282265095e-05,
      "loss": 0.1836,
      "step": 1313
    },
    {
      "epoch": 2.77,
      "grad_norm": 0.3186807930469513,
      "learning_rate": 4.380541087618606e-05,
      "loss": 0.0893,
      "step": 1314
    },
    {
      "epoch": 2.77,
      "grad_norm": 0.6703417897224426,
      "learning_rate": 4.3667994193637796e-05,
      "loss": 0.0759,
      "step": 1315
    },
    {
      "epoch": 2.77,
      "grad_norm": 0.4573896825313568,
      "learning_rate": 4.3530733154684164e-05,
      "loss": 0.1458,
      "step": 1316
    },
    {
      "epoch": 2.77,
      "grad_norm": 0.4950135052204132,
      "learning_rate": 4.339362813857321e-05,
      "loss": 0.3033,
      "step": 1317
    },
    {
      "epoch": 2.77,
      "grad_norm": 0.24762655794620514,
      "learning_rate": 4.3256679524121834e-05,
      "loss": 0.0559,
      "step": 1318
    },
    {
      "epoch": 2.78,
      "grad_norm": 0.3558330237865448,
      "learning_rate": 4.3119887689714844e-05,
      "loss": 0.1862,
      "step": 1319
    },
    {
      "epoch": 2.78,
      "grad_norm": 0.48134902119636536,
      "learning_rate": 4.298325301330383e-05,
      "loss": 0.5581,
      "step": 1320
    },
    {
      "epoch": 2.78,
      "grad_norm": 0.22999516129493713,
      "learning_rate": 4.2846775872406256e-05,
      "loss": 0.1114,
      "step": 1321
    },
    {
      "epoch": 2.78,
      "grad_norm": 0.4079764485359192,
      "learning_rate": 4.27104566441042e-05,
      "loss": 0.3144,
      "step": 1322
    },
    {
      "epoch": 2.79,
      "grad_norm": 0.3731940686702728,
      "learning_rate": 4.257429570504352e-05,
      "loss": 0.2183,
      "step": 1323
    },
    {
      "epoch": 2.79,
      "grad_norm": 0.6186441779136658,
      "learning_rate": 4.2438293431432665e-05,
      "loss": 0.0373,
      "step": 1324
    },
    {
      "epoch": 2.79,
      "grad_norm": 0.18545430898666382,
      "learning_rate": 4.23024501990417e-05,
      "loss": 0.0479,
      "step": 1325
    },
    {
      "epoch": 2.79,
      "grad_norm": 0.39455363154411316,
      "learning_rate": 4.216676638320135e-05,
      "loss": 0.4562,
      "step": 1326
    },
    {
      "epoch": 2.79,
      "grad_norm": 1.193217158317566,
      "learning_rate": 4.203124235880178e-05,
      "loss": 0.1534,
      "step": 1327
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.34430086612701416,
      "learning_rate": 4.189587850029169e-05,
      "loss": 0.3745,
      "step": 1328
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.4106227159500122,
      "learning_rate": 4.176067518167723e-05,
      "loss": 0.7812,
      "step": 1329
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.5523481369018555,
      "learning_rate": 4.1625632776521037e-05,
      "loss": 0.3704,
      "step": 1330
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.31600770354270935,
      "learning_rate": 4.149075165794105e-05,
      "loss": 0.209,
      "step": 1331
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4721559286117554,
      "learning_rate": 4.1356032198609706e-05,
      "loss": 0.3099,
      "step": 1332
    },
    {
      "epoch": 2.81,
      "grad_norm": 1.2828038930892944,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.5042,
      "step": 1333
    },
    {
      "epoch": 2.81,
      "grad_norm": 0.5226539373397827,
      "learning_rate": 4.108707974614804e-05,
      "loss": 0.5119,
      "step": 1334
    },
    {
      "epoch": 2.81,
      "grad_norm": 0.48910781741142273,
      "learning_rate": 4.095284749612503e-05,
      "loss": 0.3925,
      "step": 1335
    },
    {
      "epoch": 2.81,
      "grad_norm": 0.3297548294067383,
      "learning_rate": 4.081877839156325e-05,
      "loss": 0.2415,
      "step": 1336
    },
    {
      "epoch": 2.81,
      "grad_norm": 0.34490349888801575,
      "learning_rate": 4.068487280289146e-05,
      "loss": 0.3771,
      "step": 1337
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.33798182010650635,
      "learning_rate": 4.0551131100086745e-05,
      "loss": 0.1344,
      "step": 1338
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.5897701382637024,
      "learning_rate": 4.041755365267324e-05,
      "loss": 0.3901,
      "step": 1339
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.29294416308403015,
      "learning_rate": 4.028414082972141e-05,
      "loss": 0.169,
      "step": 1340
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.5478091835975647,
      "learning_rate": 4.0150892999846656e-05,
      "loss": 0.2538,
      "step": 1341
    },
    {
      "epoch": 2.83,
      "grad_norm": 0.8328322172164917,
      "learning_rate": 4.001781053120863e-05,
      "loss": 0.3077,
      "step": 1342
    },
    {
      "epoch": 2.83,
      "grad_norm": 1.1498992443084717,
      "learning_rate": 3.988489379151016e-05,
      "loss": 0.6369,
      "step": 1343
    },
    {
      "epoch": 2.83,
      "grad_norm": 0.2736966907978058,
      "learning_rate": 3.975214314799607e-05,
      "loss": 0.1637,
      "step": 1344
    },
    {
      "epoch": 2.83,
      "grad_norm": 0.6017499566078186,
      "learning_rate": 3.961955896745224e-05,
      "loss": 0.5734,
      "step": 1345
    },
    {
      "epoch": 2.83,
      "grad_norm": 0.4597730338573456,
      "learning_rate": 3.94871416162048e-05,
      "loss": 0.6337,
      "step": 1346
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.5489735007286072,
      "learning_rate": 3.935489146011869e-05,
      "loss": 0.2923,
      "step": 1347
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.6476238965988159,
      "learning_rate": 3.9222808864597004e-05,
      "loss": 0.4118,
      "step": 1348
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.48180490732192993,
      "learning_rate": 3.909089419457996e-05,
      "loss": 0.1466,
      "step": 1349
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.25918513536453247,
      "learning_rate": 3.89591478145437e-05,
      "loss": 0.3142,
      "step": 1350
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.6687664985656738,
      "learning_rate": 3.8827570088499356e-05,
      "loss": 0.1736,
      "step": 1351
    },
    {
      "epoch": 2.85,
      "grad_norm": 0.3094065189361572,
      "learning_rate": 3.8696161379992225e-05,
      "loss": 0.1969,
      "step": 1352
    },
    {
      "epoch": 2.85,
      "grad_norm": 0.21293707191944122,
      "learning_rate": 3.856492205210043e-05,
      "loss": 0.0834,
      "step": 1353
    },
    {
      "epoch": 2.85,
      "grad_norm": 0.5569763779640198,
      "learning_rate": 3.843385246743417e-05,
      "loss": 0.4948,
      "step": 1354
    },
    {
      "epoch": 2.85,
      "grad_norm": 0.24184778332710266,
      "learning_rate": 3.8302952988134756e-05,
      "loss": 0.1577,
      "step": 1355
    },
    {
      "epoch": 2.85,
      "grad_norm": 0.29768210649490356,
      "learning_rate": 3.817222397587336e-05,
      "loss": 0.1199,
      "step": 1356
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.8061155080795288,
      "learning_rate": 3.804166579185018e-05,
      "loss": 0.5931,
      "step": 1357
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.4685113728046417,
      "learning_rate": 3.7911278796793516e-05,
      "loss": 0.1634,
      "step": 1358
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.3703949451446533,
      "learning_rate": 3.778106335095859e-05,
      "loss": 0.1887,
      "step": 1359
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.5604259967803955,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 0.187,
      "step": 1360
    },
    {
      "epoch": 2.87,
      "grad_norm": 0.3002054989337921,
      "learning_rate": 3.7521148545604e-05,
      "loss": 0.3549,
      "step": 1361
    },
    {
      "epoch": 2.87,
      "grad_norm": 0.3863959014415741,
      "learning_rate": 3.739144990422089e-05,
      "loss": 0.0768,
      "step": 1362
    },
    {
      "epoch": 2.87,
      "grad_norm": 0.6352940201759338,
      "learning_rate": 3.726192424833075e-05,
      "loss": 0.1575,
      "step": 1363
    },
    {
      "epoch": 2.87,
      "grad_norm": 0.2791038453578949,
      "learning_rate": 3.7132571935808924e-05,
      "loss": 0.3065,
      "step": 1364
    },
    {
      "epoch": 2.87,
      "grad_norm": 0.8539896607398987,
      "learning_rate": 3.7003393324051874e-05,
      "loss": 0.4698,
      "step": 1365
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.5503263473510742,
      "learning_rate": 3.687438876997612e-05,
      "loss": 0.4123,
      "step": 1366
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.2520607113838196,
      "learning_rate": 3.674555863001725e-05,
      "loss": 0.1486,
      "step": 1367
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.5313445329666138,
      "learning_rate": 3.661690326012897e-05,
      "loss": 0.2031,
      "step": 1368
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.5100160241127014,
      "learning_rate": 3.6488423015782125e-05,
      "loss": 0.1415,
      "step": 1369
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.3034670054912567,
      "learning_rate": 3.6360118251963645e-05,
      "loss": 0.5914,
      "step": 1370
    },
    {
      "epoch": 2.89,
      "grad_norm": 0.9517300724983215,
      "learning_rate": 3.623198932317566e-05,
      "loss": 0.3926,
      "step": 1371
    },
    {
      "epoch": 2.89,
      "grad_norm": 0.23673593997955322,
      "learning_rate": 3.610403658343443e-05,
      "loss": 0.2653,
      "step": 1372
    },
    {
      "epoch": 2.89,
      "grad_norm": 0.3499943017959595,
      "learning_rate": 3.597626038626942e-05,
      "loss": 0.5564,
      "step": 1373
    },
    {
      "epoch": 2.89,
      "grad_norm": 0.5328202843666077,
      "learning_rate": 3.58486610847223e-05,
      "loss": 0.2586,
      "step": 1374
    },
    {
      "epoch": 2.89,
      "grad_norm": 0.32311174273490906,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.1838,
      "step": 1375
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.17368283867835999,
      "learning_rate": 3.5593994578203896e-05,
      "loss": 0.2052,
      "step": 1376
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.23117925226688385,
      "learning_rate": 3.546692807686829e-05,
      "loss": 0.0167,
      "step": 1377
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.33799508213996887,
      "learning_rate": 3.534003987842005e-05,
      "loss": 0.1975,
      "step": 1378
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.24989762902259827,
      "learning_rate": 3.5213330333447346e-05,
      "loss": 0.019,
      "step": 1379
    },
    {
      "epoch": 2.91,
      "grad_norm": 0.5386832356452942,
      "learning_rate": 3.508679979204481e-05,
      "loss": 0.2893,
      "step": 1380
    },
    {
      "epoch": 2.91,
      "grad_norm": 0.9841434955596924,
      "learning_rate": 3.496044860381238e-05,
      "loss": 0.5701,
      "step": 1381
    },
    {
      "epoch": 2.91,
      "grad_norm": 0.13189686834812164,
      "learning_rate": 3.483427711785449e-05,
      "loss": 0.0177,
      "step": 1382
    },
    {
      "epoch": 2.91,
      "grad_norm": 0.43873071670532227,
      "learning_rate": 3.4708285682779076e-05,
      "loss": 0.2277,
      "step": 1383
    },
    {
      "epoch": 2.91,
      "grad_norm": 0.5309714078903198,
      "learning_rate": 3.458247464669657e-05,
      "loss": 0.4126,
      "step": 1384
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.2741256356239319,
      "learning_rate": 3.445684435721897e-05,
      "loss": 0.3022,
      "step": 1385
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.3837210237979889,
      "learning_rate": 3.4331395161458955e-05,
      "loss": 0.2618,
      "step": 1386
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.3155161440372467,
      "learning_rate": 3.4206127406028745e-05,
      "loss": 0.2366,
      "step": 1387
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.1386852264404297,
      "learning_rate": 3.408104143703929e-05,
      "loss": 0.0333,
      "step": 1388
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.2975553572177887,
      "learning_rate": 3.395613760009925e-05,
      "loss": 0.0488,
      "step": 1389
    },
    {
      "epoch": 2.93,
      "grad_norm": 0.46444180607795715,
      "learning_rate": 3.383141624031408e-05,
      "loss": 0.1012,
      "step": 1390
    },
    {
      "epoch": 2.93,
      "grad_norm": 0.475568950176239,
      "learning_rate": 3.3706877702285036e-05,
      "loss": 0.3058,
      "step": 1391
    },
    {
      "epoch": 2.93,
      "grad_norm": 0.3736167252063751,
      "learning_rate": 3.35825223301083e-05,
      "loss": 0.0624,
      "step": 1392
    },
    {
      "epoch": 2.93,
      "grad_norm": 0.35307514667510986,
      "learning_rate": 3.345835046737391e-05,
      "loss": 0.4223,
      "step": 1393
    },
    {
      "epoch": 2.93,
      "grad_norm": 0.977942943572998,
      "learning_rate": 3.333436245716488e-05,
      "loss": 0.2905,
      "step": 1394
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.43840837478637695,
      "learning_rate": 3.3210558642056275e-05,
      "loss": 0.1153,
      "step": 1395
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.7894395589828491,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.3199,
      "step": 1396
    },
    {
      "epoch": 2.94,
      "grad_norm": 1.0266164541244507,
      "learning_rate": 3.29635049648949e-05,
      "loss": 0.2558,
      "step": 1397
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.45427221059799194,
      "learning_rate": 3.2840255785443855e-05,
      "loss": 0.1216,
      "step": 1398
    },
    {
      "epoch": 2.95,
      "grad_norm": 0.422296404838562,
      "learning_rate": 3.271719216629468e-05,
      "loss": 0.2097,
      "step": 1399
    },
    {
      "epoch": 2.95,
      "grad_norm": 0.5444633364677429,
      "learning_rate": 3.259431444746846e-05,
      "loss": 0.3705,
      "step": 1400
    },
    {
      "epoch": 2.95,
      "grad_norm": 0.26783403754234314,
      "learning_rate": 3.247162296847249e-05,
      "loss": 0.1156,
      "step": 1401
    },
    {
      "epoch": 2.95,
      "grad_norm": 1.415783166885376,
      "learning_rate": 3.234911806829948e-05,
      "loss": 0.1728,
      "step": 1402
    },
    {
      "epoch": 2.95,
      "grad_norm": 0.4155539274215698,
      "learning_rate": 3.222680008542678e-05,
      "loss": 0.5061,
      "step": 1403
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.5668177008628845,
      "learning_rate": 3.210466935781516e-05,
      "loss": 0.3171,
      "step": 1404
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.41083770990371704,
      "learning_rate": 3.198272622290804e-05,
      "loss": 0.3899,
      "step": 1405
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.4589744210243225,
      "learning_rate": 3.1860971017630604e-05,
      "loss": 0.2183,
      "step": 1406
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.33844196796417236,
      "learning_rate": 3.173940407838871e-05,
      "loss": 0.2511,
      "step": 1407
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.4281659424304962,
      "learning_rate": 3.161802574106799e-05,
      "loss": 0.4536,
      "step": 1408
    },
    {
      "epoch": 2.97,
      "grad_norm": 0.5119270086288452,
      "learning_rate": 3.149683634103312e-05,
      "loss": 0.6213,
      "step": 1409
    },
    {
      "epoch": 2.97,
      "grad_norm": 0.3323350250720978,
      "learning_rate": 3.137583621312665e-05,
      "loss": 0.4426,
      "step": 1410
    },
    {
      "epoch": 2.97,
      "grad_norm": 0.3763193190097809,
      "learning_rate": 3.1255025691668185e-05,
      "loss": 0.3041,
      "step": 1411
    },
    {
      "epoch": 2.97,
      "grad_norm": 0.41001826524734497,
      "learning_rate": 3.1134405110453515e-05,
      "loss": 0.4205,
      "step": 1412
    },
    {
      "epoch": 2.97,
      "grad_norm": 0.4732879400253296,
      "learning_rate": 3.101397480275359e-05,
      "loss": 0.2774,
      "step": 1413
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.36144134402275085,
      "learning_rate": 3.089373510131354e-05,
      "loss": 0.2278,
      "step": 1414
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.39741820096969604,
      "learning_rate": 3.077368633835205e-05,
      "loss": 0.2114,
      "step": 1415
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.5269529223442078,
      "learning_rate": 3.065382884556012e-05,
      "loss": 0.5934,
      "step": 1416
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.3559035360813141,
      "learning_rate": 3.053416295410026e-05,
      "loss": 0.3411,
      "step": 1417
    },
    {
      "epoch": 2.99,
      "grad_norm": 0.5966904163360596,
      "learning_rate": 3.0414688994605723e-05,
      "loss": 0.1953,
      "step": 1418
    },
    {
      "epoch": 2.99,
      "grad_norm": 0.28111594915390015,
      "learning_rate": 3.0295407297179325e-05,
      "loss": 0.3585,
      "step": 1419
    },
    {
      "epoch": 2.99,
      "grad_norm": 0.4853847622871399,
      "learning_rate": 3.0176318191392726e-05,
      "loss": 0.5636,
      "step": 1420
    },
    {
      "epoch": 2.99,
      "grad_norm": 0.6061645150184631,
      "learning_rate": 3.005742200628545e-05,
      "loss": 0.1,
      "step": 1421
    },
    {
      "epoch": 2.99,
      "grad_norm": 0.28980934619903564,
      "learning_rate": 2.9938719070363952e-05,
      "loss": 0.383,
      "step": 1422
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.34016743302345276,
      "learning_rate": 2.9820209711600854e-05,
      "loss": 0.2209,
      "step": 1423
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.26997146010398865,
      "learning_rate": 2.9701894257433826e-05,
      "loss": 0.2524,
      "step": 1424
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.29038554430007935,
      "learning_rate": 2.9583773034764826e-05,
      "loss": 0.3877,
      "step": 1425
    }
  ],
  "logging_steps": 1,
  "max_steps": 1900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 475,
  "total_flos": 1.0468132032282624e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}