{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9964071856287425,
  "eval_steps": 500,
  "global_step": 104,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 3.02,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 2.8946,
      "step": 2
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 2.9989,
      "step": 3
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 3.0185,
      "step": 4
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.9948,
      "step": 5
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.1701,
      "step": 6
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019995065603657316,
      "loss": 2.1174,
      "step": 7
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019980267284282717,
      "loss": 2.067,
      "step": 8
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019955619646030802,
      "loss": 1.9723,
      "step": 9
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.9417,
      "step": 10
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019876883405951377,
      "loss": 1.9781,
      "step": 11
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001982287250728689,
      "loss": 1.8071,
      "step": 12
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019759167619387476,
      "loss": 1.8272,
      "step": 13
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001968583161128631,
      "loss": 1.6803,
      "step": 14
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001960293685676943,
      "loss": 1.726,
      "step": 15
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.7271,
      "step": 16
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019408807689542257,
      "loss": 1.7266,
      "step": 17
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019297764858882514,
      "loss": 1.7272,
      "step": 18
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019177546256839812,
      "loss": 1.6868,
      "step": 19
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019048270524660196,
      "loss": 1.5478,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001891006524188368,
      "loss": 1.5898,
      "step": 21
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.6766,
      "step": 22
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001860742027003944,
      "loss": 1.5721,
      "step": 23
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018443279255020152,
      "loss": 1.5771,
      "step": 24
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018270805742745617,
      "loss": 1.5692,
      "step": 25
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.5286,
      "step": 26
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017901550123756906,
      "loss": 1.4898,
      "step": 27
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017705132427757895,
      "loss": 1.5101,
      "step": 28
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017501110696304596,
      "loss": 1.5265,
      "step": 29
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017289686274214118,
      "loss": 1.4373,
      "step": 30
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.3691,
      "step": 31
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016845471059286887,
      "loss": 1.5147,
      "step": 32
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016613118653236518,
      "loss": 1.4216,
      "step": 33
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000163742398974869,
      "loss": 1.3968,
      "step": 34
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016129070536529766,
      "loss": 1.4057,
      "step": 35
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.4042,
      "step": 36
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015620833778521307,
      "loss": 1.3287,
      "step": 37
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00015358267949789966,
      "loss": 1.2654,
      "step": 38
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015090414157503714,
      "loss": 1.3084,
      "step": 39
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014817536741017152,
      "loss": 1.2634,
      "step": 40
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014539904997395468,
      "loss": 1.2646,
      "step": 41
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014257792915650728,
      "loss": 1.29,
      "step": 42
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013971478906347806,
      "loss": 1.3563,
      "step": 43
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013681245526846783,
      "loss": 1.272,
      "step": 44
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00013387379202452917,
      "loss": 1.299,
      "step": 45
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.3304,
      "step": 46
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012789911060392294,
      "loss": 1.2768,
      "step": 47
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001248689887164855,
      "loss": 1.301,
      "step": 48
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012181432413965428,
      "loss": 1.1637,
      "step": 49
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011873813145857249,
      "loss": 1.2437,
      "step": 50
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001156434465040231,
      "loss": 1.2699,
      "step": 51
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011253332335643043,
      "loss": 1.2035,
      "step": 52
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010941083133185146,
      "loss": 1.2354,
      "step": 53
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010627905195293135,
      "loss": 1.3551,
      "step": 54
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010314107590781284,
      "loss": 1.1651,
      "step": 55
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 1.1803,
      "step": 56
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.685892409218717e-05,
      "loss": 1.1379,
      "step": 57
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.1446,
      "step": 58
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.058916866814858e-05,
      "loss": 1.2089,
      "step": 59
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.746667664356956e-05,
      "loss": 1.1623,
      "step": 60
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.0943,
      "step": 61
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.126186854142752e-05,
      "loss": 1.2074,
      "step": 62
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.818567586034577e-05,
      "loss": 1.1739,
      "step": 63
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.513101128351454e-05,
      "loss": 1.2538,
      "step": 64
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.210088939607708e-05,
      "loss": 1.288,
      "step": 65
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.1144,
      "step": 66
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.612620797547087e-05,
      "loss": 1.2695,
      "step": 67
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.318754473153221e-05,
      "loss": 1.205,
      "step": 68
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.0285210936521955e-05,
      "loss": 1.1551,
      "step": 69
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.1511,
      "step": 70
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 1.1414,
      "step": 71
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.182463258982846e-05,
      "loss": 1.1637,
      "step": 72
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.909585842496287e-05,
      "loss": 1.1339,
      "step": 73
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.6417320502100316e-05,
      "loss": 1.1118,
      "step": 74
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.379166221478697e-05,
      "loss": 1.1822,
      "step": 75
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.2311,
      "step": 76
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.8709294634702376e-05,
      "loss": 1.1172,
      "step": 77
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.6257601025131026e-05,
      "loss": 1.0924,
      "step": 78
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.386881346763483e-05,
      "loss": 1.1534,
      "step": 79
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.154528940713113e-05,
      "loss": 1.2601,
      "step": 80
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 1.0743,
      "step": 81
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.1419,
      "step": 82
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.4988893036954043e-05,
      "loss": 1.0558,
      "step": 83
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.2948675722421086e-05,
      "loss": 1.1382,
      "step": 84
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.098449876243096e-05,
      "loss": 1.1775,
      "step": 85
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.1861,
      "step": 86
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7291942572543807e-05,
      "loss": 1.1331,
      "step": 87
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5567207449798515e-05,
      "loss": 1.142,
      "step": 88
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3925797299605647e-05,
      "loss": 1.1482,
      "step": 89
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.2369331995613665e-05,
      "loss": 1.0885,
      "step": 90
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.2005,
      "step": 91
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.517294753398064e-06,
      "loss": 1.0784,
      "step": 92
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.224537431601886e-06,
      "loss": 1.133,
      "step": 93
    },
    {
      "epoch": 0.9,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.1096,
      "step": 94
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.911923104577455e-06,
      "loss": 1.108,
      "step": 95
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.9645,
      "step": 96
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.970631432305694e-06,
      "loss": 1.1942,
      "step": 97
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.1416838871368924e-06,
      "loss": 1.181,
      "step": 98
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.4083238061252567e-06,
      "loss": 1.0978,
      "step": 99
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.771274927131139e-06,
      "loss": 0.9967,
      "step": 100
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.231165940486234e-06,
      "loss": 1.2266,
      "step": 101
    },
    {
      "epoch": 0.98,
      "learning_rate": 7.885298685522235e-07,
      "loss": 1.216,
      "step": 102
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.438035396920004e-07,
      "loss": 1.2119,
      "step": 103
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.973271571728441e-07,
      "loss": 1.1436,
      "step": 104
    },
    {
      "epoch": 1.0,
      "step": 104,
      "total_flos": 1.0478460476588032e+16,
      "train_loss": 1.4066595842058842,
      "train_runtime": 3219.9547,
      "train_samples_per_second": 0.259,
      "train_steps_per_second": 0.032
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 104,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 104,
  "total_flos": 1.0478460476588032e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}