{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9815303430079156,
  "eval_steps": 500,
  "global_step": 93,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0316622691292876,
      "grad_norm": 2.5990071296691895,
      "learning_rate": 7.000000000000001e-07,
      "loss": 1.176,
      "step": 1
    },
    {
      "epoch": 0.0633245382585752,
      "grad_norm": 2.6270251274108887,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 1.1885,
      "step": 2
    },
    {
      "epoch": 0.09498680738786279,
      "grad_norm": 2.6077260971069336,
      "learning_rate": 2.1e-06,
      "loss": 1.1853,
      "step": 3
    },
    {
      "epoch": 0.1266490765171504,
      "grad_norm": 2.4010000228881836,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.1441,
      "step": 4
    },
    {
      "epoch": 0.158311345646438,
      "grad_norm": 1.6012561321258545,
      "learning_rate": 3.5e-06,
      "loss": 1.1434,
      "step": 5
    },
    {
      "epoch": 0.18997361477572558,
      "grad_norm": 1.4890481233596802,
      "learning_rate": 4.2e-06,
      "loss": 1.1287,
      "step": 6
    },
    {
      "epoch": 0.22163588390501318,
      "grad_norm": 2.0511271953582764,
      "learning_rate": 4.9e-06,
      "loss": 1.1233,
      "step": 7
    },
    {
      "epoch": 0.2532981530343008,
      "grad_norm": 1.9991264343261719,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.1195,
      "step": 8
    },
    {
      "epoch": 0.2849604221635884,
      "grad_norm": 2.4904370307922363,
      "learning_rate": 6.3e-06,
      "loss": 1.0933,
      "step": 9
    },
    {
      "epoch": 0.316622691292876,
      "grad_norm": 2.41306471824646,
      "learning_rate": 7e-06,
      "loss": 1.1054,
      "step": 10
    },
    {
      "epoch": 0.3482849604221636,
      "grad_norm": 1.916558861732483,
      "learning_rate": 6.99749314185716e-06,
      "loss": 1.0968,
      "step": 11
    },
    {
      "epoch": 0.37994722955145116,
      "grad_norm": 1.6149336099624634,
      "learning_rate": 6.989976158478782e-06,
      "loss": 1.0736,
      "step": 12
    },
    {
      "epoch": 0.41160949868073876,
      "grad_norm": 1.5957881212234497,
      "learning_rate": 6.977459817871147e-06,
      "loss": 1.0864,
      "step": 13
    },
    {
      "epoch": 0.44327176781002636,
      "grad_norm": 1.3141591548919678,
      "learning_rate": 6.959962049571609e-06,
      "loss": 1.0507,
      "step": 14
    },
    {
      "epoch": 0.47493403693931396,
      "grad_norm": 1.0635184049606323,
      "learning_rate": 6.937507918964709e-06,
      "loss": 1.0483,
      "step": 15
    },
    {
      "epoch": 0.5065963060686016,
      "grad_norm": 0.8129880428314209,
      "learning_rate": 6.9101295913762465e-06,
      "loss": 1.0232,
      "step": 16
    },
    {
      "epoch": 0.5382585751978892,
      "grad_norm": 1.096314549446106,
      "learning_rate": 6.877866285996766e-06,
      "loss": 1.0304,
      "step": 17
    },
    {
      "epoch": 0.5699208443271768,
      "grad_norm": 0.8672236204147339,
      "learning_rate": 6.840764219700443e-06,
      "loss": 1.0308,
      "step": 18
    },
    {
      "epoch": 0.6015831134564644,
      "grad_norm": 0.9555258750915527,
      "learning_rate": 6.798876540839855e-06,
      "loss": 1.0285,
      "step": 19
    },
    {
      "epoch": 0.633245382585752,
      "grad_norm": 1.5928786993026733,
      "learning_rate": 6.752263253111479e-06,
      "loss": 1.0189,
      "step": 20
    },
    {
      "epoch": 0.6649076517150396,
      "grad_norm": 1.2837454080581665,
      "learning_rate": 6.700991129600976e-06,
      "loss": 1.021,
      "step": 21
    },
    {
      "epoch": 0.6965699208443272,
      "grad_norm": 0.7489935755729675,
      "learning_rate": 6.645133617131388e-06,
      "loss": 1.0013,
      "step": 22
    },
    {
      "epoch": 0.7282321899736148,
      "grad_norm": 0.729206383228302,
      "learning_rate": 6.584770731051271e-06,
      "loss": 0.986,
      "step": 23
    },
    {
      "epoch": 0.7598944591029023,
      "grad_norm": 0.8594318628311157,
      "learning_rate": 6.51998894061348e-06,
      "loss": 0.9853,
      "step": 24
    },
    {
      "epoch": 0.7915567282321899,
      "grad_norm": 0.6937134861946106,
      "learning_rate": 6.4508810451087956e-06,
      "loss": 0.9969,
      "step": 25
    },
    {
      "epoch": 0.8232189973614775,
      "grad_norm": 0.6618143916130066,
      "learning_rate": 6.377546040931835e-06,
      "loss": 0.9784,
      "step": 26
    },
    {
      "epoch": 0.8548812664907651,
      "grad_norm": 0.7150548100471497,
      "learning_rate": 6.300088979769671e-06,
      "loss": 0.9775,
      "step": 27
    },
    {
      "epoch": 0.8865435356200527,
      "grad_norm": 0.8135938048362732,
      "learning_rate": 6.218620818116299e-06,
      "loss": 0.9555,
      "step": 28
    },
    {
      "epoch": 0.9182058047493403,
      "grad_norm": 0.7386907339096069,
      "learning_rate": 6.133258258328535e-06,
      "loss": 0.9536,
      "step": 29
    },
    {
      "epoch": 0.9498680738786279,
      "grad_norm": 0.6299906969070435,
      "learning_rate": 6.044123581451003e-06,
      "loss": 0.9513,
      "step": 30
    },
    {
      "epoch": 0.9815303430079155,
      "grad_norm": 0.6849163174629211,
      "learning_rate": 5.951344472049728e-06,
      "loss": 0.9491,
      "step": 31
    },
    {
      "epoch": 1.0316622691292876,
      "grad_norm": 0.5353211760520935,
      "learning_rate": 5.855053835305216e-06,
      "loss": 1.2099,
      "step": 32
    },
    {
      "epoch": 1.0633245382585752,
      "grad_norm": 0.5629773736000061,
      "learning_rate": 5.755389606627069e-06,
      "loss": 0.8727,
      "step": 33
    },
    {
      "epoch": 1.0949868073878628,
      "grad_norm": 0.5262039303779602,
      "learning_rate": 5.652494554062838e-06,
      "loss": 0.8777,
      "step": 34
    },
    {
      "epoch": 1.1266490765171504,
      "grad_norm": 0.9279022216796875,
      "learning_rate": 5.546516073784165e-06,
      "loss": 0.8661,
      "step": 35
    },
    {
      "epoch": 1.158311345646438,
      "grad_norm": 1.0550135374069214,
      "learning_rate": 5.4376059789431955e-06,
      "loss": 0.8665,
      "step": 36
    },
    {
      "epoch": 1.1899736147757256,
      "grad_norm": 0.4825997054576874,
      "learning_rate": 5.325920282201696e-06,
      "loss": 0.8584,
      "step": 37
    },
    {
      "epoch": 1.2216358839050132,
      "grad_norm": 0.5052205920219421,
      "learning_rate": 5.2116189722444164e-06,
      "loss": 0.8677,
      "step": 38
    },
    {
      "epoch": 1.2532981530343008,
      "grad_norm": 0.4654822051525116,
      "learning_rate": 5.094865784596845e-06,
      "loss": 0.8515,
      "step": 39
    },
    {
      "epoch": 1.2849604221635884,
      "grad_norm": 0.45359933376312256,
      "learning_rate": 4.975827967075644e-06,
      "loss": 0.851,
      "step": 40
    },
    {
      "epoch": 1.316622691292876,
      "grad_norm": 0.968210756778717,
      "learning_rate": 4.854676040207761e-06,
      "loss": 0.8733,
      "step": 41
    },
    {
      "epoch": 1.3482849604221636,
      "grad_norm": 0.5169340372085571,
      "learning_rate": 4.731583552961416e-06,
      "loss": 0.8698,
      "step": 42
    },
    {
      "epoch": 1.3799472295514512,
      "grad_norm": 0.8193064332008362,
      "learning_rate": 4.606726834138884e-06,
      "loss": 0.8464,
      "step": 43
    },
    {
      "epoch": 1.4116094986807388,
      "grad_norm": 0.589012622833252,
      "learning_rate": 4.480284739787175e-06,
      "loss": 0.8465,
      "step": 44
    },
    {
      "epoch": 1.4432717678100264,
      "grad_norm": 0.5069411993026733,
      "learning_rate": 4.352438396988471e-06,
      "loss": 0.8415,
      "step": 45
    },
    {
      "epoch": 1.474934036939314,
      "grad_norm": 0.4803805947303772,
      "learning_rate": 4.223370944397335e-06,
      "loss": 0.8089,
      "step": 46
    },
    {
      "epoch": 1.5065963060686016,
      "grad_norm": 0.44742244482040405,
      "learning_rate": 4.093267269896339e-06,
      "loss": 0.8141,
      "step": 47
    },
    {
      "epoch": 1.5382585751978892,
      "grad_norm": 0.5128947496414185,
      "learning_rate": 3.9623137457459586e-06,
      "loss": 0.8334,
      "step": 48
    },
    {
      "epoch": 1.5699208443271768,
      "grad_norm": 0.43568509817123413,
      "learning_rate": 3.83069796160811e-06,
      "loss": 0.7996,
      "step": 49
    },
    {
      "epoch": 1.6015831134564644,
      "grad_norm": 0.5734230279922485,
      "learning_rate": 3.6986084558257596e-06,
      "loss": 0.8206,
      "step": 50
    },
    {
      "epoch": 1.633245382585752,
      "grad_norm": 0.4465356469154358,
      "learning_rate": 3.5662344453435665e-06,
      "loss": 0.8036,
      "step": 51
    },
    {
      "epoch": 1.6649076517150396,
      "grad_norm": 0.9534016251564026,
      "learning_rate": 3.4337655546564343e-06,
      "loss": 0.849,
      "step": 52
    },
    {
      "epoch": 1.6965699208443272,
      "grad_norm": 0.5999336838722229,
      "learning_rate": 3.301391544174241e-06,
      "loss": 0.7874,
      "step": 53
    },
    {
      "epoch": 1.7282321899736148,
      "grad_norm": 0.4919511079788208,
      "learning_rate": 3.1693020383918907e-06,
      "loss": 0.8012,
      "step": 54
    },
    {
      "epoch": 1.7598944591029024,
      "grad_norm": 0.4128033518791199,
      "learning_rate": 3.0376862542540426e-06,
      "loss": 0.8056,
      "step": 55
    },
    {
      "epoch": 1.79155672823219,
      "grad_norm": 0.4979248642921448,
      "learning_rate": 2.9067327301036616e-06,
      "loss": 0.7769,
      "step": 56
    },
    {
      "epoch": 1.8232189973614776,
      "grad_norm": 0.46139153838157654,
      "learning_rate": 2.7766290556026646e-06,
      "loss": 0.7984,
      "step": 57
    },
    {
      "epoch": 1.8548812664907652,
      "grad_norm": 0.46961304545402527,
      "learning_rate": 2.6475616030115286e-06,
      "loss": 0.7917,
      "step": 58
    },
    {
      "epoch": 1.8865435356200528,
      "grad_norm": 0.4321727752685547,
      "learning_rate": 2.5197152602128256e-06,
      "loss": 0.7852,
      "step": 59
    },
    {
      "epoch": 1.9182058047493404,
      "grad_norm": 0.4466552138328552,
      "learning_rate": 2.393273165861116e-06,
      "loss": 0.8023,
      "step": 60
    },
    {
      "epoch": 1.949868073878628,
      "grad_norm": 0.4448838233947754,
      "learning_rate": 2.2684164470385843e-06,
      "loss": 0.7616,
      "step": 61
    },
    {
      "epoch": 1.9815303430079156,
      "grad_norm": 0.434826523065567,
      "learning_rate": 2.14532395979224e-06,
      "loss": 0.8165,
      "step": 62
    },
    {
      "epoch": 2.0316622691292876,
      "grad_norm": 0.6250742673873901,
      "learning_rate": 2.0241720329243563e-06,
      "loss": 1.0035,
      "step": 63
    },
    {
      "epoch": 2.063324538258575,
      "grad_norm": 0.41192013025283813,
      "learning_rate": 1.905134215403155e-06,
      "loss": 0.7532,
      "step": 64
    },
    {
      "epoch": 2.094986807387863,
      "grad_norm": 0.4167821407318115,
      "learning_rate": 1.7883810277555837e-06,
      "loss": 0.7628,
      "step": 65
    },
    {
      "epoch": 2.1266490765171504,
      "grad_norm": 0.4210691452026367,
      "learning_rate": 1.6740797177983044e-06,
      "loss": 0.7511,
      "step": 66
    },
    {
      "epoch": 2.158311345646438,
      "grad_norm": 0.44451218843460083,
      "learning_rate": 1.5623940210568042e-06,
      "loss": 0.7302,
      "step": 67
    },
    {
      "epoch": 2.1899736147757256,
      "grad_norm": 0.40137404203414917,
      "learning_rate": 1.453483926215835e-06,
      "loss": 0.7315,
      "step": 68
    },
    {
      "epoch": 2.221635883905013,
      "grad_norm": 0.6961039900779724,
      "learning_rate": 1.3475054459371625e-06,
      "loss": 0.7478,
      "step": 69
    },
    {
      "epoch": 2.253298153034301,
      "grad_norm": 0.37633243203163147,
      "learning_rate": 1.2446103933729302e-06,
      "loss": 0.7288,
      "step": 70
    },
    {
      "epoch": 2.2849604221635884,
      "grad_norm": 0.43067774176597595,
      "learning_rate": 1.1449461646947839e-06,
      "loss": 0.7628,
      "step": 71
    },
    {
      "epoch": 2.316622691292876,
      "grad_norm": 0.3962654769420624,
      "learning_rate": 1.048655527950273e-06,
      "loss": 0.7178,
      "step": 72
    },
    {
      "epoch": 2.3482849604221636,
      "grad_norm": 0.9008962512016296,
      "learning_rate": 9.558764185489968e-07,
      "loss": 0.7287,
      "step": 73
    },
    {
      "epoch": 2.379947229551451,
      "grad_norm": 0.4029214084148407,
      "learning_rate": 8.667417416714656e-07,
      "loss": 0.7135,
      "step": 74
    },
    {
      "epoch": 2.411609498680739,
      "grad_norm": 0.37933027744293213,
      "learning_rate": 7.813791818837012e-07,
      "loss": 0.7242,
      "step": 75
    },
    {
      "epoch": 2.4432717678100264,
      "grad_norm": 0.4242548644542694,
      "learning_rate": 6.999110202303293e-07,
      "loss": 0.7201,
      "step": 76
    },
    {
      "epoch": 2.474934036939314,
      "grad_norm": 0.5838273167610168,
      "learning_rate": 6.22453959068165e-07,
      "loss": 0.6838,
      "step": 77
    },
    {
      "epoch": 2.5065963060686016,
      "grad_norm": 0.3837423026561737,
      "learning_rate": 5.491189548912051e-07,
      "loss": 0.717,
      "step": 78
    },
    {
      "epoch": 2.538258575197889,
      "grad_norm": 1.0475167036056519,
      "learning_rate": 4.800110593865199e-07,
      "loss": 0.7152,
      "step": 79
    },
    {
      "epoch": 2.569920844327177,
      "grad_norm": 0.4407210946083069,
      "learning_rate": 4.15229268948729e-07,
      "loss": 0.7368,
      "step": 80
    },
    {
      "epoch": 2.6015831134564644,
      "grad_norm": 0.39730748534202576,
      "learning_rate": 3.5486638286861297e-07,
      "loss": 0.715,
      "step": 81
    },
    {
      "epoch": 2.633245382585752,
      "grad_norm": 0.5303342938423157,
      "learning_rate": 2.990088703990245e-07,
      "loss": 0.74,
      "step": 82
    },
    {
      "epoch": 2.6649076517150396,
      "grad_norm": 0.6698248386383057,
      "learning_rate": 2.4773674688852197e-07,
      "loss": 0.7142,
      "step": 83
    },
    {
      "epoch": 2.6965699208443272,
      "grad_norm": 0.43907734751701355,
      "learning_rate": 2.0112345916014578e-07,
      "loss": 0.7372,
      "step": 84
    },
    {
      "epoch": 2.728232189973615,
      "grad_norm": 0.37293171882629395,
      "learning_rate": 1.592357802995572e-07,
      "loss": 0.7241,
      "step": 85
    },
    {
      "epoch": 2.7598944591029024,
      "grad_norm": 0.394404798746109,
      "learning_rate": 1.2213371400323352e-07,
      "loss": 0.7095,
      "step": 86
    },
    {
      "epoch": 2.79155672823219,
      "grad_norm": 0.7737839818000793,
      "learning_rate": 8.987040862375339e-08,
      "loss": 0.6919,
      "step": 87
    },
    {
      "epoch": 2.8232189973614776,
      "grad_norm": 0.3485806882381439,
      "learning_rate": 6.249208103529092e-08,
      "loss": 0.7263,
      "step": 88
    },
    {
      "epoch": 2.8548812664907652,
      "grad_norm": 0.39798641204833984,
      "learning_rate": 4.0037950428390144e-08,
      "loss": 0.7415,
      "step": 89
    },
    {
      "epoch": 2.886543535620053,
      "grad_norm": 0.38925713300704956,
      "learning_rate": 2.254018212885278e-08,
      "loss": 0.7267,
      "step": 90
    },
    {
      "epoch": 2.9182058047493404,
      "grad_norm": 0.361558198928833,
      "learning_rate": 1.0023841521217825e-08,
      "loss": 0.7175,
      "step": 91
    },
    {
      "epoch": 2.949868073878628,
      "grad_norm": 0.5748413801193237,
      "learning_rate": 2.506858142839852e-09,
      "loss": 0.7126,
      "step": 92
    },
    {
      "epoch": 2.9815303430079156,
      "grad_norm": 0.3813362717628479,
      "learning_rate": 0.0,
      "loss": 0.7082,
      "step": 93
    },
    {
      "epoch": 2.9815303430079156,
      "step": 93,
      "total_flos": 2930651586101248.0,
      "train_loss": 0.8763364265041966,
      "train_runtime": 71308.8652,
      "train_samples_per_second": 0.382,
      "train_steps_per_second": 0.001
    }
  ],
  "logging_steps": 1,
  "max_steps": 93,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2930651586101248.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}