{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9914893617021276,
  "eval_steps": 50,
  "global_step": 117,
  "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": 1.6896,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 4e-05,
      "loss": 1.632,
      "step": 2
    },
    {
      "epoch": 0.05,
      "learning_rate": 6e-05,
      "loss": 1.7197,
      "step": 3
    },
    {
      "epoch": 0.07,
      "learning_rate": 8e-05,
      "loss": 1.6988,
      "step": 4
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 1.4945,
      "step": 5
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00012,
      "loss": 1.4763,
      "step": 6
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00014,
      "loss": 1.4645,
      "step": 7
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00016,
      "loss": 1.1569,
      "step": 8
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00018,
      "loss": 1.4501,
      "step": 9
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.1972,
      "step": 10
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019998209226697376,
      "loss": 1.1479,
      "step": 11
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019992837548163316,
      "loss": 1.1791,
      "step": 12
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019983886888289514,
      "loss": 1.1471,
      "step": 13
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019971360452796522,
      "loss": 0.9662,
      "step": 14
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001995526272808559,
      "loss": 1.2166,
      "step": 15
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001993559947963185,
      "loss": 1.1023,
      "step": 16
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019912377749919374,
      "loss": 0.9719,
      "step": 17
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019885605855918885,
      "loss": 0.9122,
      "step": 18
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019855293386108992,
      "loss": 0.8808,
      "step": 19
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019821451197042026,
      "loss": 1.0081,
      "step": 20
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019784091409455728,
      "loss": 1.0147,
      "step": 21
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019743227403932134,
      "loss": 0.8792,
      "step": 22
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019698873816105273,
      "loss": 0.8762,
      "step": 23
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019651046531419332,
      "loss": 0.7916,
      "step": 24
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001959976267943923,
      "loss": 0.8967,
      "step": 25
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001954504062771555,
      "loss": 1.0575,
      "step": 26
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019486899975206166,
      "loss": 0.9374,
      "step": 27
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019425361545256727,
      "loss": 0.8697,
      "step": 28
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019360447378142728,
      "loss": 0.788,
      "step": 29
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019292180723175654,
      "loss": 0.8215,
      "step": 30
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019220586030376134,
      "loss": 0.8943,
      "step": 31
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019145688941717075,
      "loss": 0.7825,
      "step": 32
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019067516281939825,
      "loss": 0.9878,
      "step": 33
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018986096048946824,
      "loss": 0.8517,
      "step": 34
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018901457403773967,
      "loss": 0.8132,
      "step": 35
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018813630660146488,
      "loss": 0.9143,
      "step": 36
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001872264727362194,
      "loss": 0.8659,
      "step": 37
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018628539830324229,
      "loss": 0.7977,
      "step": 38
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018531342035272766,
      "loss": 0.8188,
      "step": 39
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00018431088700310844,
      "loss": 0.871,
      "step": 40
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00018327815731637612,
      "loss": 0.6939,
      "step": 41
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00018221560116948103,
      "loss": 0.8147,
      "step": 42
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00018112359912185924,
      "loss": 0.8898,
      "step": 43
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00018000254227913348,
      "loss": 0.8074,
      "step": 44
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001788528321530366,
      "loss": 0.8351,
      "step": 45
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017767488051760857,
      "loss": 0.8811,
      "step": 46
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017646910926171747,
      "loss": 0.792,
      "step": 47
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00017523595023795813,
      "loss": 0.8558,
      "step": 48
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001739758451079821,
      "loss": 0.8308,
      "step": 49
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00017268924518431438,
      "loss": 0.8504,
      "step": 50
    },
    {
      "epoch": 0.85,
      "eval_loss": 0.8740054368972778,
      "eval_runtime": 0.8959,
      "eval_samples_per_second": 22.324,
      "eval_steps_per_second": 5.581,
      "step": 50
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001713766112687139,
      "loss": 0.83,
      "step": 51
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001700384134871351,
      "loss": 0.7499,
      "step": 52
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016867513112135013,
      "loss": 0.8685,
      "step": 53
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001672872524372919,
      "loss": 0.807,
      "step": 54
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00016587527451017938,
      "loss": 0.8627,
      "step": 55
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001644397030464877,
      "loss": 0.7606,
      "step": 56
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00016298105220282713,
      "loss": 0.8284,
      "step": 57
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00016149984440179537,
      "loss": 0.8585,
      "step": 58
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015999661014486956,
      "loss": 0.8819,
      "step": 59
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001584718878224047,
      "loss": 0.6723,
      "step": 60
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00015692622352080662,
      "loss": 0.7435,
      "step": 61
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00015536017082694846,
      "loss": 0.7002,
      "step": 62
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00015377429062990122,
      "loss": 0.7433,
      "step": 63
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00015216915092004847,
      "loss": 0.7356,
      "step": 64
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001505453265856581,
      "loss": 0.7616,
      "step": 65
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014890339920698334,
      "loss": 0.7192,
      "step": 66
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001472439568479671,
      "loss": 0.7354,
      "step": 67
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00014556759384562416,
      "loss": 0.7623,
      "step": 68
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00014387491059717652,
      "loss": 0.724,
      "step": 69
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001421665133450184,
      "loss": 0.8136,
      "step": 70
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001404430139595877,
      "loss": 0.8083,
      "step": 71
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00013870502972022173,
      "loss": 0.7054,
      "step": 72
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001369531830940757,
      "loss": 0.7301,
      "step": 73
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001351881015131833,
      "loss": 0.6925,
      "step": 74
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.000133410417149739,
      "loss": 0.7191,
      "step": 75
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001316207666896824,
      "loss": 0.6814,
      "step": 76
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012981979110466654,
      "loss": 0.6916,
      "step": 77
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00012800813542249072,
      "loss": 0.5781,
      "step": 78
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001261864484960807,
      "loss": 0.8074,
      "step": 79
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001243553827710992,
      "loss": 0.6563,
      "step": 80
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00012251559405226941,
      "loss": 0.6436,
      "step": 81
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00012066774126849529,
      "loss": 0.7692,
      "step": 82
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011881248623686338,
      "loss": 0.6265,
      "step": 83
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00011695049342560968,
      "loss": 0.5772,
      "step": 84
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00011508242971613741,
      "loss": 0.6841,
      "step": 85
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00011320896416417026,
      "loss": 0.7439,
      "step": 86
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.000111330767760127,
      "loss": 0.7303,
      "step": 87
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010944851318880314,
      "loss": 0.7767,
      "step": 88
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010756287458844569,
      "loss": 0.6361,
      "step": 89
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00010567452730930743,
      "loss": 0.6535,
      "step": 90
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00010378414767176705,
      "loss": 0.7178,
      "step": 91
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0001018924127241019,
      "loss": 0.6977,
      "step": 92
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001,
      "loss": 0.704,
      "step": 93
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.810758727589813e-05,
      "loss": 0.8041,
      "step": 94
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.621585232823298e-05,
      "loss": 0.7026,
      "step": 95
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.432547269069261e-05,
      "loss": 0.6892,
      "step": 96
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.243712541155436e-05,
      "loss": 0.7073,
      "step": 97
    },
    {
      "epoch": 1.67,
      "learning_rate": 9.055148681119688e-05,
      "loss": 0.7765,
      "step": 98
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.866923223987302e-05,
      "loss": 0.6896,
      "step": 99
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.679103583582979e-05,
      "loss": 0.6527,
      "step": 100
    },
    {
      "epoch": 1.7,
      "eval_loss": 0.8596932291984558,
      "eval_runtime": 0.897,
      "eval_samples_per_second": 22.297,
      "eval_steps_per_second": 5.574,
      "step": 100
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.491757028386263e-05,
      "loss": 0.6335,
      "step": 101
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.304950657439033e-05,
      "loss": 0.6348,
      "step": 102
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.118751376313664e-05,
      "loss": 0.6983,
      "step": 103
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.93322587315047e-05,
      "loss": 0.7995,
      "step": 104
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.74844059477306e-05,
      "loss": 0.654,
      "step": 105
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.564461722890081e-05,
      "loss": 0.6507,
      "step": 106
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.381355150391933e-05,
      "loss": 0.6623,
      "step": 107
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.19918645775093e-05,
      "loss": 0.7539,
      "step": 108
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.018020889533348e-05,
      "loss": 0.755,
      "step": 109
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.83792333103176e-05,
      "loss": 0.6394,
      "step": 110
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.658958285026102e-05,
      "loss": 0.7545,
      "step": 111
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.48118984868167e-05,
      "loss": 0.7215,
      "step": 112
    },
    {
      "epoch": 1.92,
      "learning_rate": 6.304681690592431e-05,
      "loss": 0.581,
      "step": 113
    },
    {
      "epoch": 1.94,
      "learning_rate": 6.129497027977829e-05,
      "loss": 0.673,
      "step": 114
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.955698604041231e-05,
      "loss": 0.6878,
      "step": 115
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.7833486654981606e-05,
      "loss": 0.738,
      "step": 116
    },
    {
      "epoch": 1.99,
      "learning_rate": 5.6125089402823485e-05,
      "loss": 0.812,
      "step": 117
    }
  ],
  "logging_steps": 1,
  "max_steps": 174,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 5053549897973760.0,
  "trial_name": null,
  "trial_params": null
}