{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9989949748743718,
  "eval_steps": 125,
  "global_step": 497,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.5221,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 2.548204183578491,
      "eval_runtime": 51.7546,
      "eval_samples_per_second": 24.288,
      "eval_steps_per_second": 1.024,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.5234,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 2.55,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.5209,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 2.5177,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-05,
      "loss": 2.4932,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.495,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.4618,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-05,
      "loss": 2.4603,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 2.4364,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.4445,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-05,
      "loss": 2.4126,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.4573,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.4604,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 2.4551,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.400000000000001e-05,
      "loss": 2.4235,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.442,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.2e-05,
      "loss": 2.4189,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.6e-05,
      "loss": 2.4027,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 2.4114,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.4e-05,
      "loss": 2.4136,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.800000000000001e-05,
      "loss": 2.4136,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.200000000000001e-05,
      "loss": 2.4229,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.6e-05,
      "loss": 2.4245,
      "step": 24
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 2.3903,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010400000000000001,
      "loss": 2.4154,
      "step": 26
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010800000000000001,
      "loss": 2.46,
      "step": 27
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011200000000000001,
      "loss": 2.4382,
      "step": 28
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000116,
      "loss": 2.3889,
      "step": 29
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012,
      "loss": 2.4225,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000124,
      "loss": 2.4394,
      "step": 31
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012800000000000002,
      "loss": 2.4058,
      "step": 32
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000132,
      "loss": 2.448,
      "step": 33
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013600000000000003,
      "loss": 2.4017,
      "step": 34
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014,
      "loss": 2.4179,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000144,
      "loss": 2.4142,
      "step": 36
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000148,
      "loss": 2.419,
      "step": 37
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000152,
      "loss": 2.3895,
      "step": 38
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015600000000000002,
      "loss": 2.3415,
      "step": 39
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00016,
      "loss": 2.4038,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000164,
      "loss": 2.415,
      "step": 41
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000168,
      "loss": 2.3996,
      "step": 42
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000172,
      "loss": 2.4102,
      "step": 43
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00017600000000000002,
      "loss": 2.4241,
      "step": 44
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018,
      "loss": 2.4232,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018400000000000003,
      "loss": 2.4156,
      "step": 46
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000188,
      "loss": 2.4106,
      "step": 47
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000192,
      "loss": 2.4124,
      "step": 48
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000196,
      "loss": 2.4515,
      "step": 49
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.3911,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999753025044538,
      "loss": 2.437,
      "step": 51
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999012112377473,
      "loss": 2.4317,
      "step": 52
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001999777729859618,
      "loss": 2.4115,
      "step": 53
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019996048644694282,
      "loss": 2.482,
      "step": 54
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019993826236058612,
      "loss": 2.4374,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019991110182465032,
      "loss": 2.4609,
      "step": 56
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001998790061807298,
      "loss": 2.4661,
      "step": 57
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001998419770141887,
      "loss": 2.4656,
      "step": 58
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019980001615408228,
      "loss": 2.4659,
      "step": 59
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019975312567306687,
      "loss": 2.4142,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019970130788729738,
      "loss": 2.4815,
      "step": 61
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019964456535631286,
      "loss": 2.4746,
      "step": 62
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019958290088291011,
      "loss": 2.4358,
      "step": 63
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019951631751300531,
      "loss": 2.4215,
      "step": 64
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019944481853548335,
      "loss": 2.4716,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019936840748203561,
      "loss": 2.3693,
      "step": 66
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019928708812698545,
      "loss": 2.4516,
      "step": 67
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001992008644871016,
      "loss": 2.4226,
      "step": 68
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019910974082140004,
      "loss": 2.4769,
      "step": 69
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001990137216309334,
      "loss": 2.4157,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019891281165856873,
      "loss": 2.5004,
      "step": 71
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019880701588875327,
      "loss": 2.4319,
      "step": 72
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019869633954726807,
      "loss": 2.4563,
      "step": 73
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019858078810097002,
      "loss": 2.4156,
      "step": 74
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019846036725752186,
      "loss": 2.409,
      "step": 75
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019833508296511002,
      "loss": 2.4533,
      "step": 76
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019820494141215104,
      "loss": 2.4374,
      "step": 77
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019806994902698573,
      "loss": 2.3888,
      "step": 78
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019793011247756174,
      "loss": 2.4201,
      "step": 79
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019778543867110426,
      "loss": 2.4034,
      "step": 80
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019763593475377462,
      "loss": 2.442,
      "step": 81
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019748160811031747,
      "loss": 2.3813,
      "step": 82
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019732246636369605,
      "loss": 2.3356,
      "step": 83
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019715851737471546,
      "loss": 2.3447,
      "step": 84
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019698976924163456,
      "loss": 2.3692,
      "step": 85
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019681623029976588,
      "loss": 2.3599,
      "step": 86
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019663790912106393,
      "loss": 2.4325,
      "step": 87
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019645481451370172,
      "loss": 2.4405,
      "step": 88
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019626695552163578,
      "loss": 2.397,
      "step": 89
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001960743414241593,
      "loss": 2.3989,
      "step": 90
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019587698173544396,
      "loss": 2.3333,
      "step": 91
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019567488620406983,
      "loss": 2.3499,
      "step": 92
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001954680648125438,
      "loss": 2.3654,
      "step": 93
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019525652777680676,
      "loss": 2.3604,
      "step": 94
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019504028554572864,
      "loss": 2.368,
      "step": 95
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019481934880059257,
      "loss": 2.3225,
      "step": 96
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019459372845456705,
      "loss": 2.3822,
      "step": 97
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019436343565216711,
      "loss": 2.3697,
      "step": 98
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019412848176870363,
      "loss": 2.349,
      "step": 99
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019388887840972164,
      "loss": 2.3015,
      "step": 100
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019364463741042694,
      "loss": 2.4336,
      "step": 101
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019339577083510144,
      "loss": 2.2816,
      "step": 102
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019314229097650742,
      "loss": 2.3033,
      "step": 103
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019288421035528028,
      "loss": 2.372,
      "step": 104
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019262154171931,
      "loss": 2.2949,
      "step": 105
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001923542980431115,
      "loss": 2.3972,
      "step": 106
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001920824925271838,
      "loss": 2.3624,
      "step": 107
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019180613859735791,
      "loss": 2.4214,
      "step": 108
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001915252499041338,
      "loss": 2.2428,
      "step": 109
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019123984032200586,
      "loss": 2.3559,
      "step": 110
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019094992394877794,
      "loss": 2.3033,
      "step": 111
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001906555151048667,
      "loss": 2.3734,
      "step": 112
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019035662833259432,
      "loss": 2.2408,
      "step": 113
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001900532783954703,
      "loss": 2.3528,
      "step": 114
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001897454802774621,
      "loss": 2.2373,
      "step": 115
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018943324918225494,
      "loss": 2.3138,
      "step": 116
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018911660053250103,
      "loss": 2.2331,
      "step": 117
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018879554996905766,
      "loss": 2.2188,
      "step": 118
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018847011335021449,
      "loss": 2.2649,
      "step": 119
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001881403067509104,
      "loss": 2.2905,
      "step": 120
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018780614646193942,
      "loss": 2.2859,
      "step": 121
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001874676489891461,
      "loss": 2.1971,
      "step": 122
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018712483105261005,
      "loss": 2.2541,
      "step": 123
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018677770958582023,
      "loss": 2.2179,
      "step": 124
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018642630173483832,
      "loss": 2.2198,
      "step": 125
    },
    {
      "epoch": 0.25,
      "eval_loss": 2.3039979934692383,
      "eval_runtime": 51.9209,
      "eval_samples_per_second": 24.21,
      "eval_steps_per_second": 1.021,
      "step": 125
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018607062485745212,
      "loss": 2.332,
      "step": 126
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001857106965223177,
      "loss": 2.2744,
      "step": 127
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018534653450809197,
      "loss": 2.2837,
      "step": 128
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001849781568025545,
      "loss": 2.249,
      "step": 129
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018460558160171865,
      "loss": 2.3065,
      "step": 130
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001842288273089332,
      "loss": 2.2788,
      "step": 131
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001838479125339731,
      "loss": 2.2946,
      "step": 132
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018346285609212025,
      "loss": 2.2101,
      "step": 133
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001830736770032341,
      "loss": 2.2492,
      "step": 134
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001826803944908124,
      "loss": 2.1931,
      "step": 135
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018228302798104127,
      "loss": 2.196,
      "step": 136
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018188159710183594,
      "loss": 2.2698,
      "step": 137
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001814761216818711,
      "loss": 2.3152,
      "step": 138
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018106662174960153,
      "loss": 2.2096,
      "step": 139
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018065311753227273,
      "loss": 2.2467,
      "step": 140
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001802356294549218,
      "loss": 2.2236,
      "step": 141
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017981417813936864,
      "loss": 2.2537,
      "step": 142
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001793887844031972,
      "loss": 2.2716,
      "step": 143
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017895946925872733,
      "loss": 2.2136,
      "step": 144
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017852625391197674,
      "loss": 2.2374,
      "step": 145
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017808915976161362,
      "loss": 2.2258,
      "step": 146
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017764820839789964,
      "loss": 2.1188,
      "step": 147
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017720342160162348,
      "loss": 2.1268,
      "step": 148
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000176754821343025,
      "loss": 2.2547,
      "step": 149
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017630242978070997,
      "loss": 2.314,
      "step": 150
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017584626926055554,
      "loss": 2.3001,
      "step": 151
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001753863623146066,
      "loss": 2.1514,
      "step": 152
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017492273165996261,
      "loss": 2.2405,
      "step": 153
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001744554001976556,
      "loss": 2.2064,
      "step": 154
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017398439101151905,
      "loss": 2.1977,
      "step": 155
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001735097273670475,
      "loss": 2.2881,
      "step": 156
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017303143271024744,
      "loss": 2.1925,
      "step": 157
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017254953066647913,
      "loss": 2.1888,
      "step": 158
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001720640450392898,
      "loss": 2.2044,
      "step": 159
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017157499980923767,
      "loss": 2.145,
      "step": 160
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001710824191327075,
      "loss": 2.1138,
      "step": 161
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001705863273407174,
      "loss": 2.2124,
      "step": 162
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017008674893771706,
      "loss": 2.0964,
      "step": 163
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016958370860037717,
      "loss": 2.208,
      "step": 164
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016907723117637083,
      "loss": 2.1633,
      "step": 165
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016856734168314583,
      "loss": 2.1419,
      "step": 166
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001680540653066891,
      "loss": 2.1253,
      "step": 167
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016753742740028277,
      "loss": 2.1568,
      "step": 168
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016701745348325156,
      "loss": 2.1131,
      "step": 169
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001664941692397025,
      "loss": 2.1684,
      "step": 170
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016596760051725609,
      "loss": 2.1378,
      "step": 171
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016543777332576976,
      "loss": 2.0971,
      "step": 172
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016490471383605288,
      "loss": 2.1363,
      "step": 173
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016436844837857417,
      "loss": 2.0525,
      "step": 174
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016382900344216115,
      "loss": 2.1323,
      "step": 175
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001632864056726917,
      "loss": 2.1257,
      "step": 176
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016274068187177771,
      "loss": 2.0854,
      "step": 177
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016219185899544154,
      "loss": 2.2714,
      "step": 178
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016163996415278424,
      "loss": 2.0961,
      "step": 179
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016108502460464666,
      "loss": 2.1213,
      "step": 180
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016052706776226286,
      "loss": 2.121,
      "step": 181
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015996612118590603,
      "loss": 2.1398,
      "step": 182
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015940221258352742,
      "loss": 2.0577,
      "step": 183
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015883536980938734,
      "loss": 2.0841,
      "step": 184
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015826562086267956,
      "loss": 2.0541,
      "step": 185
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015769299388614826,
      "loss": 2.0365,
      "step": 186
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015711751716469786,
      "loss": 2.1263,
      "step": 187
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015653921912399589,
      "loss": 2.0934,
      "step": 188
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001559581283290689,
      "loss": 2.0882,
      "step": 189
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015537427348289153,
      "loss": 1.9549,
      "step": 190
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001547876834249687,
      "loss": 2.1164,
      "step": 191
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001541983871299111,
      "loss": 2.0739,
      "step": 192
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000153606413706004,
      "loss": 2.0541,
      "step": 193
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015301179239376938,
      "loss": 1.9866,
      "step": 194
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001524145525645216,
      "loss": 2.0699,
      "step": 195
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015181472371891686,
      "loss": 2.0908,
      "step": 196
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001512123354854955,
      "loss": 1.968,
      "step": 197
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00015060741761921902,
      "loss": 2.0859,
      "step": 198
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.9517,
      "step": 199
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014939011263122634,
      "loss": 2.0148,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014877778563827923,
      "loss": 2.0794,
      "step": 201
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000148163049267045,
      "loss": 1.9808,
      "step": 202
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014754593388242117,
      "loss": 2.0028,
      "step": 203
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001469264699668168,
      "loss": 2.14,
      "step": 204
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014630468811864633,
      "loss": 2.0264,
      "step": 205
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014568061905081875,
      "loss": 1.9986,
      "step": 206
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014505429358922,
      "loss": 2.0302,
      "step": 207
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014442574267119074,
      "loss": 1.894,
      "step": 208
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014379499734399798,
      "loss": 2.0404,
      "step": 209
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014316208876330146,
      "loss": 1.8718,
      "step": 210
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014252704819161496,
      "loss": 1.9787,
      "step": 211
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014188990699676184,
      "loss": 2.0504,
      "step": 212
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014125069665032574,
      "loss": 1.9288,
      "step": 213
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014060944872609606,
      "loss": 2.0359,
      "step": 214
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00013996619489850822,
      "loss": 2.0282,
      "step": 215
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001393209669410794,
      "loss": 1.9534,
      "step": 216
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001386737967248388,
      "loss": 1.9479,
      "step": 217
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013802471621675338,
      "loss": 1.9512,
      "step": 218
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013737375747814915,
      "loss": 1.9571,
      "step": 219
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001367209526631272,
      "loss": 1.9223,
      "step": 220
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013606633401697557,
      "loss": 1.9252,
      "step": 221
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001354099338745764,
      "loss": 1.9298,
      "step": 222
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001347517846588089,
      "loss": 1.9366,
      "step": 223
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001340919188789477,
      "loss": 1.8472,
      "step": 224
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013343036912905718,
      "loss": 1.9318,
      "step": 225
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013276716808638126,
      "loss": 2.0005,
      "step": 226
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013210234850972964,
      "loss": 1.9785,
      "step": 227
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013143594323785927,
      "loss": 1.8198,
      "step": 228
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013076798518785274,
      "loss": 1.8197,
      "step": 229
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001300985073534919,
      "loss": 1.8909,
      "step": 230
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001294275428036284,
      "loss": 1.937,
      "step": 231
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012875512468055024,
      "loss": 1.8939,
      "step": 232
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012808128619834461,
      "loss": 1.8948,
      "step": 233
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012740606064125736,
      "loss": 1.9238,
      "step": 234
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012672948136204887,
      "loss": 1.891,
      "step": 235
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012605158178034654,
      "loss": 1.8728,
      "step": 236
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012537239538099425,
      "loss": 1.9132,
      "step": 237
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001246919557123981,
      "loss": 1.8633,
      "step": 238
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012401029638486953,
      "loss": 1.8216,
      "step": 239
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012332745106896482,
      "loss": 1.8434,
      "step": 240
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012264345349382238,
      "loss": 1.8116,
      "step": 241
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001219583374454963,
      "loss": 1.8152,
      "step": 242
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012127213676528768,
      "loss": 1.8103,
      "step": 243
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012058488534807303,
      "loss": 1.8576,
      "step": 244
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00011989661714062999,
      "loss": 1.8415,
      "step": 245
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00011920736613996046,
      "loss": 1.8708,
      "step": 246
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011851716639161159,
      "loss": 1.8049,
      "step": 247
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001178260519879937,
      "loss": 1.8555,
      "step": 248
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011713405706669667,
      "loss": 1.8647,
      "step": 249
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011644121580880345,
      "loss": 1.8488,
      "step": 250
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.8219653367996216,
      "eval_runtime": 51.9603,
      "eval_samples_per_second": 24.192,
      "eval_steps_per_second": 1.02,
      "step": 250
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001157475624372018,
      "loss": 1.8457,
      "step": 251
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011505313121489383,
      "loss": 1.7723,
      "step": 252
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011435795644330359,
      "loss": 1.7381,
      "step": 253
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001136620724605827,
      "loss": 1.9117,
      "step": 254
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011296551363991432,
      "loss": 1.8667,
      "step": 255
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011226831438781518,
      "loss": 1.7878,
      "step": 256
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011157050914243614,
      "loss": 1.7116,
      "step": 257
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011087213237186108,
      "loss": 1.8073,
      "step": 258
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011017321857240432,
      "loss": 1.7985,
      "step": 259
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010947380226690684,
      "loss": 1.8121,
      "step": 260
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010877391800303074,
      "loss": 1.6811,
      "step": 261
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010807360035155305,
      "loss": 1.7594,
      "step": 262
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010737288390465792,
      "loss": 1.7029,
      "step": 263
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010667180327422797,
      "loss": 1.7555,
      "step": 264
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010597039309013472,
      "loss": 1.8195,
      "step": 265
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010526868799852796,
      "loss": 1.7216,
      "step": 266
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010456672266012446,
      "loss": 1.7184,
      "step": 267
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010386453174849584,
      "loss": 1.7327,
      "step": 268
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001031621499483559,
      "loss": 1.7251,
      "step": 269
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010245961195384743,
      "loss": 1.7582,
      "step": 270
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010175695246682841,
      "loss": 1.7147,
      "step": 271
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00010105420619515798,
      "loss": 1.7322,
      "step": 272
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00010035140785098187,
      "loss": 1.7607,
      "step": 273
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.964859214901814e-05,
      "loss": 1.7381,
      "step": 274
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.894579380484204e-05,
      "loss": 1.7026,
      "step": 275
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.82430475331716e-05,
      "loss": 1.6587,
      "step": 276
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.754038804615257e-05,
      "loss": 1.7142,
      "step": 277
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.683785005164411e-05,
      "loss": 1.738,
      "step": 278
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.613546825150421e-05,
      "loss": 1.672,
      "step": 279
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.543327733987557e-05,
      "loss": 1.7901,
      "step": 280
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.473131200147205e-05,
      "loss": 1.7879,
      "step": 281
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.402960690986532e-05,
      "loss": 1.6247,
      "step": 282
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.332819672577206e-05,
      "loss": 1.7031,
      "step": 283
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.26271160953421e-05,
      "loss": 1.72,
      "step": 284
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.192639964844695e-05,
      "loss": 1.7805,
      "step": 285
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.122608199696928e-05,
      "loss": 1.7854,
      "step": 286
    },
    {
      "epoch": 0.58,
      "learning_rate": 9.052619773309317e-05,
      "loss": 1.6424,
      "step": 287
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.982678142759566e-05,
      "loss": 1.6995,
      "step": 288
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.912786762813893e-05,
      "loss": 1.6633,
      "step": 289
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.84294908575639e-05,
      "loss": 1.6116,
      "step": 290
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.773168561218483e-05,
      "loss": 1.7391,
      "step": 291
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.70344863600857e-05,
      "loss": 1.5991,
      "step": 292
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.633792753941733e-05,
      "loss": 1.5397,
      "step": 293
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.564204355669643e-05,
      "loss": 1.6073,
      "step": 294
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.494686878510623e-05,
      "loss": 1.7106,
      "step": 295
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.425243756279824e-05,
      "loss": 1.6159,
      "step": 296
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.355878419119657e-05,
      "loss": 1.7041,
      "step": 297
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.286594293330332e-05,
      "loss": 1.6621,
      "step": 298
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.217394801200631e-05,
      "loss": 1.6209,
      "step": 299
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.148283360838844e-05,
      "loss": 1.6256,
      "step": 300
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.079263386003952e-05,
      "loss": 1.6747,
      "step": 301
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.010338285937006e-05,
      "loss": 1.7257,
      "step": 302
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.941511465192697e-05,
      "loss": 1.605,
      "step": 303
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.872786323471232e-05,
      "loss": 1.5881,
      "step": 304
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.804166255450373e-05,
      "loss": 1.6928,
      "step": 305
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.735654650617763e-05,
      "loss": 1.6106,
      "step": 306
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.667254893103519e-05,
      "loss": 1.6714,
      "step": 307
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.598970361513051e-05,
      "loss": 1.5388,
      "step": 308
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.53080442876019e-05,
      "loss": 1.546,
      "step": 309
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.462760461900576e-05,
      "loss": 1.5758,
      "step": 310
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.394841821965345e-05,
      "loss": 1.4756,
      "step": 311
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.327051863795118e-05,
      "loss": 1.5601,
      "step": 312
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.259393935874265e-05,
      "loss": 1.5874,
      "step": 313
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.191871380165538e-05,
      "loss": 1.6352,
      "step": 314
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.12448753194498e-05,
      "loss": 1.6191,
      "step": 315
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.057245719637164e-05,
      "loss": 1.5642,
      "step": 316
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.990149264650814e-05,
      "loss": 1.6193,
      "step": 317
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.923201481214732e-05,
      "loss": 1.5273,
      "step": 318
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.856405676214073e-05,
      "loss": 1.552,
      "step": 319
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.789765149027039e-05,
      "loss": 1.4993,
      "step": 320
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.723283191361873e-05,
      "loss": 1.5243,
      "step": 321
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.656963087094284e-05,
      "loss": 1.6382,
      "step": 322
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.590808112105232e-05,
      "loss": 1.6384,
      "step": 323
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.524821534119114e-05,
      "loss": 1.5141,
      "step": 324
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.459006612542365e-05,
      "loss": 1.526,
      "step": 325
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.393366598302446e-05,
      "loss": 1.5187,
      "step": 326
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.32790473368728e-05,
      "loss": 1.5672,
      "step": 327
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.262624252185087e-05,
      "loss": 1.5509,
      "step": 328
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.197528378324665e-05,
      "loss": 1.6236,
      "step": 329
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.132620327516126e-05,
      "loss": 1.5135,
      "step": 330
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.06790330589206e-05,
      "loss": 1.5453,
      "step": 331
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.0033805101491794e-05,
      "loss": 1.4761,
      "step": 332
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.939055127390396e-05,
      "loss": 1.5515,
      "step": 333
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.8749303349674254e-05,
      "loss": 1.5779,
      "step": 334
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.811009300323818e-05,
      "loss": 1.4634,
      "step": 335
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.747295180838503e-05,
      "loss": 1.4856,
      "step": 336
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.6837911236698536e-05,
      "loss": 1.4736,
      "step": 337
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.620500265600206e-05,
      "loss": 1.4468,
      "step": 338
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.5574257328809276e-05,
      "loss": 1.448,
      "step": 339
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.494570641077999e-05,
      "loss": 1.5192,
      "step": 340
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.431938094918132e-05,
      "loss": 1.4709,
      "step": 341
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.369531188135368e-05,
      "loss": 1.4481,
      "step": 342
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.307353003318325e-05,
      "loss": 1.5018,
      "step": 343
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.2454066117578815e-05,
      "loss": 1.5606,
      "step": 344
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.183695073295507e-05,
      "loss": 1.5407,
      "step": 345
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.122221436172079e-05,
      "loss": 1.4878,
      "step": 346
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.060988736877366e-05,
      "loss": 1.4904,
      "step": 347
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.3881,
      "step": 348
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.939258238078098e-05,
      "loss": 1.4511,
      "step": 349
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.8787664514504504e-05,
      "loss": 1.4791,
      "step": 350
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.818527628108317e-05,
      "loss": 1.323,
      "step": 351
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.758544743547839e-05,
      "loss": 1.4073,
      "step": 352
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.698820760623064e-05,
      "loss": 1.3715,
      "step": 353
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.639358629399602e-05,
      "loss": 1.4781,
      "step": 354
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.580161287008892e-05,
      "loss": 1.5291,
      "step": 355
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.521231657503132e-05,
      "loss": 1.4415,
      "step": 356
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.462572651710847e-05,
      "loss": 1.3697,
      "step": 357
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.4041871670931135e-05,
      "loss": 1.5058,
      "step": 358
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.346078087600412e-05,
      "loss": 1.3509,
      "step": 359
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.288248283530214e-05,
      "loss": 1.5078,
      "step": 360
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.230700611385174e-05,
      "loss": 1.4253,
      "step": 361
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.173437913732048e-05,
      "loss": 1.3528,
      "step": 362
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.116463019061269e-05,
      "loss": 1.4971,
      "step": 363
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.059778741647261e-05,
      "loss": 1.4212,
      "step": 364
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.003387881409397e-05,
      "loss": 1.4902,
      "step": 365
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.947293223773715e-05,
      "loss": 1.4026,
      "step": 366
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.8914975395353334e-05,
      "loss": 1.4036,
      "step": 367
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.836003584721577e-05,
      "loss": 1.3422,
      "step": 368
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.780814100455848e-05,
      "loss": 1.4615,
      "step": 369
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.7259318128222276e-05,
      "loss": 1.4738,
      "step": 370
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.671359432730834e-05,
      "loss": 1.2812,
      "step": 371
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.617099655783884e-05,
      "loss": 1.3518,
      "step": 372
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.563155162142584e-05,
      "loss": 1.3794,
      "step": 373
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.509528616394716e-05,
      "loss": 1.344,
      "step": 374
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.456222667423028e-05,
      "loss": 1.383,
      "step": 375
    },
    {
      "epoch": 0.75,
      "eval_loss": 1.3915969133377075,
      "eval_runtime": 52.0043,
      "eval_samples_per_second": 24.171,
      "eval_steps_per_second": 1.019,
      "step": 375
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.403239948274392e-05,
      "loss": 1.3758,
      "step": 376
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.350583076029754e-05,
      "loss": 1.3697,
      "step": 377
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.298254651674848e-05,
      "loss": 1.3343,
      "step": 378
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.246257259971727e-05,
      "loss": 1.4031,
      "step": 379
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.1945934693310896e-05,
      "loss": 1.4939,
      "step": 380
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.143265831685419e-05,
      "loss": 1.2987,
      "step": 381
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.092276882362918e-05,
      "loss": 1.3531,
      "step": 382
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.041629139962283e-05,
      "loss": 1.4016,
      "step": 383
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.9913251062282986e-05,
      "loss": 1.4369,
      "step": 384
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.9413672659282622e-05,
      "loss": 1.3164,
      "step": 385
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.8917580867292526e-05,
      "loss": 1.4983,
      "step": 386
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.8425000190762353e-05,
      "loss": 1.2823,
      "step": 387
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.793595496071021e-05,
      "loss": 1.3993,
      "step": 388
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.7450469333520855e-05,
      "loss": 1.3771,
      "step": 389
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.6968567289752578e-05,
      "loss": 1.3688,
      "step": 390
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.6490272632952505e-05,
      "loss": 1.3941,
      "step": 391
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.6015608988480955e-05,
      "loss": 1.4538,
      "step": 392
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.5544599802344394e-05,
      "loss": 1.3141,
      "step": 393
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.5077268340037454e-05,
      "loss": 1.4652,
      "step": 394
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.4613637685393432e-05,
      "loss": 1.2551,
      "step": 395
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.415373073944449e-05,
      "loss": 1.416,
      "step": 396
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.3697570219290077e-05,
      "loss": 1.351,
      "step": 397
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.324517865697501e-05,
      "loss": 1.3533,
      "step": 398
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.2796578398376523e-05,
      "loss": 1.2773,
      "step": 399
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.235179160210037e-05,
      "loss": 1.3286,
      "step": 400
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.1910840238386398e-05,
      "loss": 1.3392,
      "step": 401
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.147374608802326e-05,
      "loss": 1.2921,
      "step": 402
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.104053074127268e-05,
      "loss": 1.3551,
      "step": 403
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.06112155968028e-05,
      "loss": 1.2801,
      "step": 404
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.0185821860631394e-05,
      "loss": 1.3758,
      "step": 405
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9764370545078215e-05,
      "loss": 1.3692,
      "step": 406
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9346882467727325e-05,
      "loss": 1.2987,
      "step": 407
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.893337825039849e-05,
      "loss": 1.2623,
      "step": 408
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.852387831812893e-05,
      "loss": 1.4118,
      "step": 409
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.811840289816409e-05,
      "loss": 1.3289,
      "step": 410
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7716972018958766e-05,
      "loss": 1.37,
      "step": 411
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7319605509187608e-05,
      "loss": 1.3297,
      "step": 412
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6926322996765897e-05,
      "loss": 1.3106,
      "step": 413
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.653714390787979e-05,
      "loss": 1.2543,
      "step": 414
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.61520874660269e-05,
      "loss": 1.1748,
      "step": 415
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5771172691066794e-05,
      "loss": 1.3091,
      "step": 416
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5394418398281352e-05,
      "loss": 1.3359,
      "step": 417
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5021843197445528e-05,
      "loss": 1.361,
      "step": 418
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4653465491908003e-05,
      "loss": 1.3599,
      "step": 419
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4289303477682347e-05,
      "loss": 1.3696,
      "step": 420
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3929375142547917e-05,
      "loss": 1.1577,
      "step": 421
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3573698265161683e-05,
      "loss": 1.3131,
      "step": 422
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3222290414179794e-05,
      "loss": 1.2763,
      "step": 423
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2875168947389981e-05,
      "loss": 1.2822,
      "step": 424
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2532351010853916e-05,
      "loss": 1.3403,
      "step": 425
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.2193853538060595e-05,
      "loss": 1.2745,
      "step": 426
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1859693249089642e-05,
      "loss": 1.3022,
      "step": 427
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.152988664978556e-05,
      "loss": 1.3088,
      "step": 428
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1204450030942348e-05,
      "loss": 1.3025,
      "step": 429
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0883399467498956e-05,
      "loss": 1.3092,
      "step": 430
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0566750817745074e-05,
      "loss": 1.3048,
      "step": 431
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0254519722537947e-05,
      "loss": 1.2341,
      "step": 432
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.946721604529718e-06,
      "loss": 1.3788,
      "step": 433
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.643371667405698e-06,
      "loss": 1.4034,
      "step": 434
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.344484895133342e-06,
      "loss": 1.3039,
      "step": 435
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.050076051222067e-06,
      "loss": 1.3125,
      "step": 436
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.760159677994172e-06,
      "loss": 1.3098,
      "step": 437
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.474750095866236e-06,
      "loss": 1.2353,
      "step": 438
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.193861402642088e-06,
      "loss": 1.3627,
      "step": 439
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.91750747281621e-06,
      "loss": 1.4489,
      "step": 440
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.645701956888507e-06,
      "loss": 1.3553,
      "step": 441
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.378458280689993e-06,
      "loss": 1.3337,
      "step": 442
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.115789644719728e-06,
      "loss": 1.2856,
      "step": 443
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.857709023492587e-06,
      "loss": 1.3764,
      "step": 444
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.60422916489859e-06,
      "loss": 1.2939,
      "step": 445
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.355362589573077e-06,
      "loss": 1.3477,
      "step": 446
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.111121590278346e-06,
      "loss": 1.3298,
      "step": 447
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.8715182312963575e-06,
      "loss": 1.3331,
      "step": 448
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.636564347832907e-06,
      "loss": 1.2503,
      "step": 449
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.4062715454329726e-06,
      "loss": 1.2786,
      "step": 450
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.180651199407449e-06,
      "loss": 1.286,
      "step": 451
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.959714454271369e-06,
      "loss": 1.2775,
      "step": 452
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.7434722231932685e-06,
      "loss": 1.2779,
      "step": 453
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.531935187456216e-06,
      "loss": 1.315,
      "step": 454
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.325113795930203e-06,
      "loss": 1.3792,
      "step": 455
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.1230182645560555e-06,
      "loss": 1.4314,
      "step": 456
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.925658575840696e-06,
      "loss": 1.2617,
      "step": 457
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.7330444783642338e-06,
      "loss": 1.3592,
      "step": 458
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.5451854862982746e-06,
      "loss": 1.3299,
      "step": 459
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.3620908789360863e-06,
      "loss": 1.3729,
      "step": 460
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.1837697002341293e-06,
      "loss": 1.2571,
      "step": 461
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.010230758365462e-06,
      "loss": 1.2179,
      "step": 462
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.841482625284564e-06,
      "loss": 1.2873,
      "step": 463
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.677533636303964e-06,
      "loss": 1.3169,
      "step": 464
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.518391889682525e-06,
      "loss": 1.2881,
      "step": 465
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.3640652462253886e-06,
      "loss": 1.2479,
      "step": 466
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.2145613288957478e-06,
      "loss": 1.2183,
      "step": 467
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.069887522438252e-06,
      "loss": 1.3322,
      "step": 468
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9300509730142855e-06,
      "loss": 1.2666,
      "step": 469
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7950585878489856e-06,
      "loss": 1.2443,
      "step": 470
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.6649170348899789e-06,
      "loss": 1.2989,
      "step": 471
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5396327424781366e-06,
      "loss": 1.2325,
      "step": 472
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4192118990299707e-06,
      "loss": 1.3192,
      "step": 473
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3036604527319474e-06,
      "loss": 1.2725,
      "step": 474
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1929841112467533e-06,
      "loss": 1.3761,
      "step": 475
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0871883414312777e-06,
      "loss": 1.3084,
      "step": 476
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.862783690666178e-07,
      "loss": 1.2498,
      "step": 477
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.902591785999725e-07,
      "loss": 1.3384,
      "step": 478
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.991355128984079e-07,
      "loss": 1.2835,
      "step": 479
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.129118730145656e-07,
      "loss": 1.412,
      "step": 480
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.315925179643744e-07,
      "loss": 1.2562,
      "step": 481
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.55181464516652e-07,
      "loss": 1.3095,
      "step": 482
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.836824869946965e-07,
      "loss": 1.252,
      "step": 483
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.170991170898808e-07,
      "loss": 1.3766,
      "step": 484
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.554346436871581e-07,
      "loss": 1.2876,
      "step": 485
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.986921127026476e-07,
      "loss": 1.3465,
      "step": 486
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.468743269331442e-07,
      "loss": 1.3842,
      "step": 487
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.9998384591773944e-07,
      "loss": 1.3558,
      "step": 488
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.5802298581132358e-07,
      "loss": 1.2995,
      "step": 489
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.209938192701876e-07,
      "loss": 1.27,
      "step": 490
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.889817534969425e-08,
      "loss": 1.2425,
      "step": 491
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.173763941389465e-08,
      "loss": 1.2134,
      "step": 492
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.9513553057202165e-08,
      "loss": 1.2438,
      "step": 493
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.222701403818972e-08,
      "loss": 1.329,
      "step": 494
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.878876225277722e-09,
      "loss": 1.4423,
      "step": 495
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.469749554634415e-09,
      "loss": 1.2607,
      "step": 496
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.3635,
      "step": 497
    }
  ],
  "logging_steps": 1,
  "max_steps": 497,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 3.751894162656461e+17,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}