{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.962406015037594,
  "eval_steps": 17,
  "global_step": 132,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2e-05,
      "loss": 1.8373,
      "step": 1
    },
    {
      "epoch": 0.02,
      "eval_loss": 1.8333783149719238,
      "eval_runtime": 16.5756,
      "eval_samples_per_second": 2.715,
      "eval_steps_per_second": 1.388,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 4e-05,
      "loss": 1.8119,
      "step": 2
    },
    {
      "epoch": 0.05,
      "learning_rate": 6e-05,
      "loss": 1.8301,
      "step": 3
    },
    {
      "epoch": 0.06,
      "learning_rate": 8e-05,
      "loss": 1.7976,
      "step": 4
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.853,
      "step": 5
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012,
      "loss": 1.7586,
      "step": 6
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014,
      "loss": 1.8416,
      "step": 7
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00016,
      "loss": 1.7755,
      "step": 8
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018,
      "loss": 1.804,
      "step": 9
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.7858,
      "step": 10
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001999923511388017,
      "loss": 1.7311,
      "step": 11
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999694057253083,
      "loss": 1.7012,
      "step": 12
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019993116726964554,
      "loss": 1.742,
      "step": 13
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019987764162142613,
      "loss": 1.7209,
      "step": 14
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001998088369688552,
      "loss": 1.7578,
      "step": 15
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019972476383747748,
      "loss": 1.6906,
      "step": 16
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001996254350885672,
      "loss": 1.738,
      "step": 17
    },
    {
      "epoch": 0.26,
      "eval_loss": 1.754616141319275,
      "eval_runtime": 16.6372,
      "eval_samples_per_second": 2.705,
      "eval_steps_per_second": 1.382,
      "step": 17
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001995108659171607,
      "loss": 1.7976,
      "step": 18
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019938107384973166,
      "loss": 1.7781,
      "step": 19
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019923607874151032,
      "loss": 1.7737,
      "step": 20
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019907590277344582,
      "loss": 1.6662,
      "step": 21
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019890057044881306,
      "loss": 1.7869,
      "step": 22
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001987101085894644,
      "loss": 1.6646,
      "step": 23
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019850454633172631,
      "loss": 1.7482,
      "step": 24
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001982839151219424,
      "loss": 1.7112,
      "step": 25
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019804824871166255,
      "loss": 1.7083,
      "step": 26
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019779758315248004,
      "loss": 1.728,
      "step": 27
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019753195679051628,
      "loss": 1.7292,
      "step": 28
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001972514102605547,
      "loss": 1.6902,
      "step": 29
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019695598647982468,
      "loss": 1.7432,
      "step": 30
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019664573064143604,
      "loss": 1.7258,
      "step": 31
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019632069020746572,
      "loss": 1.7363,
      "step": 32
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019598091490169694,
      "loss": 1.7142,
      "step": 33
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019562645670201276,
      "loss": 1.704,
      "step": 34
    },
    {
      "epoch": 0.51,
      "eval_loss": 1.7388739585876465,
      "eval_runtime": 16.5955,
      "eval_samples_per_second": 2.712,
      "eval_steps_per_second": 1.386,
      "step": 34
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001952573698324446,
      "loss": 1.7393,
      "step": 35
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019487371075487713,
      "loss": 1.7568,
      "step": 36
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000194475538160411,
      "loss": 1.7445,
      "step": 37
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001940629129603844,
      "loss": 1.6595,
      "step": 38
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019363589827705492,
      "loss": 1.7288,
      "step": 39
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019319455943394347,
      "loss": 1.6342,
      "step": 40
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019273896394584103,
      "loss": 1.7066,
      "step": 41
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019226918150848068,
      "loss": 1.6558,
      "step": 42
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019178528398787551,
      "loss": 1.6756,
      "step": 43
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019128734540932495,
      "loss": 1.7146,
      "step": 44
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019077544194609042,
      "loss": 1.7043,
      "step": 45
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019024965190774263,
      "loss": 1.6396,
      "step": 46
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00018971005572818213,
      "loss": 1.648,
      "step": 47
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00018915673595333444,
      "loss": 1.5988,
      "step": 48
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00018858977722852275,
      "loss": 1.7394,
      "step": 49
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00018800926628551886,
      "loss": 1.6362,
      "step": 50
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00018741529192927526,
      "loss": 1.6762,
      "step": 51
    },
    {
      "epoch": 0.77,
      "eval_loss": 1.7409569025039673,
      "eval_runtime": 16.7147,
      "eval_samples_per_second": 2.692,
      "eval_steps_per_second": 1.376,
      "step": 51
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00018680794502434018,
      "loss": 1.6534,
      "step": 52
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00018618731848095706,
      "loss": 1.6551,
      "step": 53
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018555350724085162,
      "loss": 1.6297,
      "step": 54
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001849066082627079,
      "loss": 1.7152,
      "step": 55
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00018424672050733576,
      "loss": 1.7062,
      "step": 56
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018357394492253215,
      "loss": 1.5742,
      "step": 57
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018288838442763838,
      "loss": 1.6424,
      "step": 58
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018219014389779585,
      "loss": 1.6544,
      "step": 59
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018147933014790244,
      "loss": 1.6179,
      "step": 60
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001807560519162724,
      "loss": 1.6823,
      "step": 61
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018002041984800174,
      "loss": 1.5845,
      "step": 62
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00017927254647804209,
      "loss": 1.6177,
      "step": 63
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001785125462139855,
      "loss": 1.6196,
      "step": 64
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00017774053531856258,
      "loss": 1.6526,
      "step": 65
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000176956631891857,
      "loss": 1.5792,
      "step": 66
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00017616095585323878,
      "loss": 1.6652,
      "step": 67
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00017535362892301954,
      "loss": 1.5981,
      "step": 68
    },
    {
      "epoch": 1.02,
      "eval_loss": 1.7487449645996094,
      "eval_runtime": 16.6837,
      "eval_samples_per_second": 2.697,
      "eval_steps_per_second": 1.379,
      "step": 68
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001745347746038319,
      "loss": 1.6053,
      "step": 69
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001737045181617364,
      "loss": 1.6171,
      "step": 70
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00017286298660705875,
      "loss": 1.631,
      "step": 71
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00017201030867496005,
      "loss": 1.5558,
      "step": 72
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00017114661480574332,
      "loss": 1.5339,
      "step": 73
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.000170272037124899,
      "loss": 1.6548,
      "step": 74
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00016938670942289293,
      "loss": 1.5526,
      "step": 75
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00016849076713469914,
      "loss": 1.5565,
      "step": 76
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00016758434731908178,
      "loss": 1.5604,
      "step": 77
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00016666758863762793,
      "loss": 1.5654,
      "step": 78
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00016574063133353582,
      "loss": 1.5967,
      "step": 79
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00016480361721016054,
      "loss": 1.5608,
      "step": 80
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00016385668960932143,
      "loss": 1.5801,
      "step": 81
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00016289999338937427,
      "loss": 1.5472,
      "step": 82
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00016193367490305088,
      "loss": 1.5126,
      "step": 83
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00016095788197507081,
      "loss": 1.5896,
      "step": 84
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00015997276387952732,
      "loss": 1.5593,
      "step": 85
    },
    {
      "epoch": 1.26,
      "eval_loss": 1.79562509059906,
      "eval_runtime": 16.6149,
      "eval_samples_per_second": 2.708,
      "eval_steps_per_second": 1.384,
      "step": 85
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00015897847131705195,
      "loss": 1.5616,
      "step": 86
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00015797515639176074,
      "loss": 1.596,
      "step": 87
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001569629725879857,
      "loss": 1.595,
      "step": 88
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00015594207474679532,
      "loss": 1.5442,
      "step": 89
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00015491261904230727,
      "loss": 1.5812,
      "step": 90
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00015387476295779736,
      "loss": 1.5214,
      "step": 91
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00015282866526160837,
      "loss": 1.5403,
      "step": 92
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001517744859828618,
      "loss": 1.4751,
      "step": 93
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00015071238638697732,
      "loss": 1.5861,
      "step": 94
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00014964252895100264,
      "loss": 1.5334,
      "step": 95
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00014856507733875836,
      "loss": 1.4884,
      "step": 96
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00014748019637580114,
      "loss": 1.5297,
      "step": 97
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00014638805202420895,
      "loss": 1.4725,
      "step": 98
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001452888113571929,
      "loss": 1.4849,
      "step": 99
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001441826425335387,
      "loss": 1.5654,
      "step": 100
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00014306971477188223,
      "loss": 1.6349,
      "step": 101
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001419501983248229,
      "loss": 1.4415,
      "step": 102
    },
    {
      "epoch": 1.51,
      "eval_loss": 1.7860450744628906,
      "eval_runtime": 16.6303,
      "eval_samples_per_second": 2.706,
      "eval_steps_per_second": 1.383,
      "step": 102
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00014082426445287903,
      "loss": 1.5735,
      "step": 103
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00013969208539828872,
      "loss": 1.5328,
      "step": 104
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00013855383435866077,
      "loss": 1.5466,
      "step": 105
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00013740968546047935,
      "loss": 1.5861,
      "step": 106
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001362598137324667,
      "loss": 1.5449,
      "step": 107
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00013510439507880776,
      "loss": 1.6084,
      "step": 108
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00013394360625224068,
      "loss": 1.5249,
      "step": 109
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00013277762482701767,
      "loss": 1.5594,
      "step": 110
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00013160662917174044,
      "loss": 1.5877,
      "step": 111
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001304307984220736,
      "loss": 1.4964,
      "step": 112
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001292503124533411,
      "loss": 1.4538,
      "step": 113
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001280653518530093,
      "loss": 1.4454,
      "step": 114
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00012687609789306144,
      "loss": 1.4512,
      "step": 115
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001256827325022668,
      "loss": 1.38,
      "step": 116
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00012448543823835015,
      "loss": 1.5207,
      "step": 117
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00012328439826006415,
      "loss": 1.4787,
      "step": 118
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001220797962991706,
      "loss": 1.6098,
      "step": 119
    },
    {
      "epoch": 1.77,
      "eval_loss": 1.8019659519195557,
      "eval_runtime": 16.646,
      "eval_samples_per_second": 2.703,
      "eval_steps_per_second": 1.382,
      "step": 119
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00012087181663233354,
      "loss": 1.4798,
      "step": 120
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00011966064405292887,
      "loss": 1.5248,
      "step": 121
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001184464638427756,
      "loss": 1.4309,
      "step": 122
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00011722946174379168,
      "loss": 1.4477,
      "step": 123
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00011600982392957978,
      "loss": 1.4843,
      "step": 124
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00011478773697694691,
      "loss": 1.4298,
      "step": 125
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00011356338783736255,
      "loss": 1.4775,
      "step": 126
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001123369638083593,
      "loss": 1.5159,
      "step": 127
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00011110865250488047,
      "loss": 1.3696,
      "step": 128
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00010987864183057943,
      "loss": 1.4259,
      "step": 129
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00010864711994907458,
      "loss": 1.5685,
      "step": 130
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00010741427525516463,
      "loss": 1.4997,
      "step": 131
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00010618029634600843,
      "loss": 1.4718,
      "step": 132
    }
  ],
  "logging_steps": 1,
  "max_steps": 264,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 66,
  "total_flos": 1.735504576024412e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}