{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.99972833469166,
  "global_step": 230,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.00035999999999999997,
      "loss": 0.2157,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0005999707572027913,
      "loss": 0.2186,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0005995322292545942,
      "loss": 0.2325,
      "step": 9
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0005985682199945492,
      "loss": 0.2308,
      "step": 12
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000597080420622471,
      "loss": 0.236,
      "step": 15
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005950714412440158,
      "loss": 0.2367,
      "step": 18
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005925448062916689,
      "loss": 0.2416,
      "step": 21
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005895049483416934,
      "loss": 0.2413,
      "step": 24
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000585957200337884,
      "loss": 0.2479,
      "step": 27
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005819077862357724,
      "loss": 0.2352,
      "step": 30
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005773638100836939,
      "loss": 0.2438,
      "step": 33
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005723332435598725,
      "loss": 0.2371,
      "step": 36
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005668249119873892,
      "loss": 0.2392,
      "step": 39
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005608484788515657,
      "loss": 0.2229,
      "step": 42
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005544144288469277,
      "loss": 0.2289,
      "step": 45
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005475340494834885,
      "loss": 0.2342,
      "step": 48
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00054021941128462,
      "loss": 0.2318,
      "step": 51
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005324833466112538,
      "loss": 0.2189,
      "step": 54
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005243394271495595,
      "loss": 0.2193,
      "step": 57
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005158019401015953,
      "loss": 0.2233,
      "step": 60
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005068858631207009,
      "loss": 0.2111,
      "step": 63
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0004976068380356041,
      "loss": 0.2166,
      "step": 66
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00048798114340933813,
      "loss": 0.2088,
      "step": 69
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004780256659811104,
      "loss": 0.2029,
      "step": 72
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00046775787104122397,
      "loss": 0.2072,
      "step": 75
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00045719577179102375,
      "loss": 0.2002,
      "step": 78
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004463578977416198,
      "loss": 0.202,
      "step": 81
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004352632622068292,
      "loss": 0.1967,
      "step": 84
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004239313289473625,
      "loss": 0.1939,
      "step": 87
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004123819780247736,
      "loss": 0.1905,
      "step": 90
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004006354709250765,
      "loss": 0.1853,
      "step": 93
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000388712415013214,
      "loss": 0.1809,
      "step": 96
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003766337273807371,
      "loss": 0.177,
      "step": 99
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00036442059815011896,
      "loss": 0.1808,
      "step": 102
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003520944533000791,
      "loss": 0.1707,
      "step": 105
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00033967691707713674,
      "loss": 0.172,
      "step": 108
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003271897740593341,
      "loss": 0.1632,
      "step": 111
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000314654930938684,
      "loss": 0.1734,
      "step": 114
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 122.123,
      "eval_loss": 1.8751367330551147,
      "eval_rouge1": 57.9286,
      "eval_rouge2": 29.2743,
      "eval_rougeL": 44.7181,
      "eval_rougeLsum": 54.2295,
      "eval_runtime": 1692.8237,
      "eval_samples_per_second": 0.591,
      "eval_steps_per_second": 0.148,
      "step": 115
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00030209437808938845,
      "loss": 0.1607,
      "step": 117
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002895301509892498,
      "loss": 0.1423,
      "step": 120
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002769842915619544,
      "loss": 0.1361,
      "step": 123
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002644788095080497,
      "loss": 0.1438,
      "step": 126
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00025203564369244956,
      "loss": 0.1367,
      "step": 129
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00023967662365621063,
      "loss": 0.1333,
      "step": 132
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002274234313200997,
      "loss": 0.1325,
      "step": 135
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.000215297562947137,
      "loss": 0.1367,
      "step": 138
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00020332029143084668,
      "loss": 0.1309,
      "step": 141
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00019151262897537235,
      "loss": 0.1356,
      "step": 144
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017989529023293153,
      "loss": 0.128,
      "step": 147
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00016848865596327673,
      "loss": 0.1215,
      "step": 150
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001573127372789174,
      "loss": 0.1244,
      "step": 153
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00014638714053882856,
      "loss": 0.1265,
      "step": 156
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00013573103295223495,
      "loss": 0.117,
      "step": 159
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001253631089528132,
      "loss": 0.1216,
      "step": 162
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001153015574023025,
      "loss": 0.1157,
      "step": 165
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010556402968106073,
      "loss": 0.1197,
      "step": 168
    },
    {
      "epoch": 1.49,
      "learning_rate": 9.616760872154511e-05,
      "loss": 0.1227,
      "step": 171
    },
    {
      "epoch": 1.51,
      "learning_rate": 8.712877903904379e-05,
      "loss": 0.1156,
      "step": 174
    },
    {
      "epoch": 1.54,
      "learning_rate": 7.846339781223482e-05,
      "loss": 0.1198,
      "step": 177
    },
    {
      "epoch": 1.57,
      "learning_rate": 7.018666706430662e-05,
      "loss": 0.1192,
      "step": 180
    },
    {
      "epoch": 1.59,
      "learning_rate": 6.231310699344282e-05,
      "loss": 0.116,
      "step": 183
    },
    {
      "epoch": 1.62,
      "learning_rate": 5.485653049946145e-05,
      "loss": 0.119,
      "step": 186
    },
    {
      "epoch": 1.64,
      "learning_rate": 4.7830018951294724e-05,
      "loss": 0.1135,
      "step": 189
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.124589923782276e-05,
      "loss": 0.1169,
      "step": 192
    },
    {
      "epoch": 1.7,
      "learning_rate": 3.51157221423219e-05,
      "loss": 0.115,
      "step": 195
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.945024207846589e-05,
      "loss": 0.1156,
      "step": 198
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.425939822342968e-05,
      "loss": 0.1157,
      "step": 201
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.9552297081195668e-05,
      "loss": 0.1136,
      "step": 204
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.5337196506651038e-05,
      "loss": 0.111,
      "step": 207
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.162149121850433e-05,
      "loss": 0.113,
      "step": 210
    },
    {
      "epoch": 1.85,
      "learning_rate": 8.411699826436147e-06,
      "loss": 0.1098,
      "step": 213
    },
    {
      "epoch": 1.88,
      "learning_rate": 5.7134533952425395e-06,
      "loss": 0.1111,
      "step": 216
    },
    {
      "epoch": 1.9,
      "learning_rate": 3.5314855660341646e-06,
      "loss": 0.1098,
      "step": 219
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.869624251821089e-06,
      "loss": 0.1111,
      "step": 222
    },
    {
      "epoch": 1.96,
      "learning_rate": 7.307849220527406e-07,
      "loss": 0.1121,
      "step": 225
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.1696548789369431e-07,
      "loss": 0.1098,
      "step": 228
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 122.364,
      "eval_loss": 2.1311135292053223,
      "eval_rouge1": 58.1114,
      "eval_rouge2": 29.339,
      "eval_rougeL": 44.7611,
      "eval_rougeLsum": 54.2823,
      "eval_runtime": 1701.9255,
      "eval_samples_per_second": 0.588,
      "eval_steps_per_second": 0.147,
      "step": 230
    },
    {
      "epoch": 2.0,
      "step": 230,
      "total_flos": 2.7141869303916134e+17,
      "train_loss": 0.16691997828690902,
      "train_runtime": 19759.1358,
      "train_samples_per_second": 2.98,
      "train_steps_per_second": 0.012
    }
  ],
  "max_steps": 230,
  "num_train_epochs": 2,
  "total_flos": 2.7141869303916134e+17,
  "trial_name": null,
  "trial_params": null
}