{
  "best_metric": 1.933449387550354,
  "best_model_checkpoint": "/opt/ml/input/Summarization/checkpoint-10000",
  "epoch": 10.0,
  "global_step": 35480,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 9.603605964719648e-06,
      "loss": 2.9628,
      "step": 100
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.651882655109716e-05,
      "loss": 2.3592,
      "step": 200
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9653319145399344e-05,
      "loss": 2.2458,
      "step": 300
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.5272614557174996e-05,
      "loss": 2.2573,
      "step": 400
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.1805441557799242e-05,
      "loss": 2.2079,
      "step": 500
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.1082060287457063e-07,
      "loss": 2.1759,
      "step": 600
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.722474358076239e-05,
      "loss": 2.1902,
      "step": 700
    },
    {
      "epoch": 0.23,
      "learning_rate": 3.921546108807772e-05,
      "loss": 2.1833,
      "step": 800
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.786089912498746e-05,
      "loss": 2.1655,
      "step": 900
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.5842522332451548e-05,
      "loss": 2.1736,
      "step": 1000
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.998560182965376e-06,
      "loss": 2.1269,
      "step": 1100
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.537378853569256e-07,
      "loss": 2.1282,
      "step": 1200
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.975624045467085e-05,
      "loss": 2.1398,
      "step": 1300
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.817047144722464e-05,
      "loss": 2.1608,
      "step": 1400
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.519891933012913e-05,
      "loss": 2.1441,
      "step": 1500
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.1019691489417214e-05,
      "loss": 2.1726,
      "step": 1600
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.588328036709013e-05,
      "loss": 2.08,
      "step": 1700
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.009754957197535e-05,
      "loss": 2.1441,
      "step": 1800
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.4009281306639542e-05,
      "loss": 2.121,
      "step": 1900
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.798339111133779e-05,
      "loss": 2.115,
      "step": 2000
    },
    {
      "epoch": 0.56,
      "eval_gen_len": 20.0,
      "eval_loss": 1.985213279724121,
      "eval_rouge1": 21.6401,
      "eval_rouge2": 5.6588,
      "eval_rougeL": 21.4503,
      "eval_rougeLsum": 21.4438,
      "eval_runtime": 165.0934,
      "eval_samples_per_second": 42.449,
      "eval_steps_per_second": 2.653,
      "step": 2000
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.2381055741151043e-05,
      "loss": 2.0857,
      "step": 2100
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.538065136536039e-06,
      "loss": 2.0659,
      "step": 2200
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.7446960159146312e-06,
      "loss": 2.0782,
      "step": 2300
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.2283134167178716e-06,
      "loss": 2.0432,
      "step": 2400
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.397430049077326e-07,
      "loss": 2.0695,
      "step": 2500
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.9888693982206995e-05,
      "loss": 2.1082,
      "step": 2600
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.9413728617356034e-05,
      "loss": 2.1176,
      "step": 2700
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.857231009627857e-05,
      "loss": 2.1424,
      "step": 2800
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.737709413672616e-05,
      "loss": 2.1241,
      "step": 2900
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.5846057899240565e-05,
      "loss": 2.115,
      "step": 3000
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.400222959392605e-05,
      "loss": 2.0883,
      "step": 3100
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.187334211473467e-05,
      "loss": 2.1088,
      "step": 3200
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.949141591092745e-05,
      "loss": 2.0855,
      "step": 3300
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.6892277369712686e-05,
      "loss": 2.0811,
      "step": 3400
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.411501995403511e-05,
      "loss": 2.0632,
      "step": 3500
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.1201416200504895e-05,
      "loss": 1.9746,
      "step": 3600
    },
    {
      "epoch": 1.04,
      "learning_rate": 2.8195289421565e-05,
      "loss": 1.8776,
      "step": 3700
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.5141854562081277e-05,
      "loss": 1.878,
      "step": 3800
    },
    {
      "epoch": 1.1,
      "learning_rate": 2.208703812448537e-05,
      "loss": 1.9068,
      "step": 3900
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.9076787391429783e-05,
      "loss": 1.8943,
      "step": 4000
    },
    {
      "epoch": 1.13,
      "eval_gen_len": 20.0,
      "eval_loss": 1.964289665222168,
      "eval_rouge1": 21.3418,
      "eval_rouge2": 5.6223,
      "eval_rougeL": 21.1288,
      "eval_rougeLsum": 21.1143,
      "eval_runtime": 162.0352,
      "eval_samples_per_second": 43.25,
      "eval_steps_per_second": 2.703,
      "step": 4000
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.6156379335888783e-05,
      "loss": 1.8808,
      "step": 4100
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.3369739613341079e-05,
      "loss": 1.8741,
      "step": 4200
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.0758781879025238e-05,
      "loss": 1.86,
      "step": 4300
    },
    {
      "epoch": 1.24,
      "learning_rate": 8.362777367551548e-06,
      "loss": 1.8857,
      "step": 4400
    },
    {
      "epoch": 1.27,
      "learning_rate": 6.2177642169797586e-06,
      "loss": 1.8757,
      "step": 4500
    },
    {
      "epoch": 1.3,
      "learning_rate": 4.356005421678249e-06,
      "loss": 1.8509,
      "step": 4600
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.8055035668582452e-06,
      "loss": 1.8304,
      "step": 4700
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.589579643627363e-06,
      "loss": 1.8435,
      "step": 4800
    },
    {
      "epoch": 1.38,
      "learning_rate": 7.265222795761219e-07,
      "loss": 1.888,
      "step": 4900
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.2931266079587017e-07,
      "loss": 1.8392,
      "step": 5000
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.99986426423885e-05,
      "loss": 1.8821,
      "step": 5100
    },
    {
      "epoch": 1.47,
      "learning_rate": 4.9935733363756125e-05,
      "loss": 1.9121,
      "step": 5200
    },
    {
      "epoch": 1.49,
      "learning_rate": 4.9779159803948603e-05,
      "loss": 1.8862,
      "step": 5300
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.952951127049067e-05,
      "loss": 1.9367,
      "step": 5400
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.9187727384091566e-05,
      "loss": 1.9389,
      "step": 5500
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.875509454212479e-05,
      "loss": 1.917,
      "step": 5600
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.823324107691887e-05,
      "loss": 1.9325,
      "step": 5700
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.762413112708219e-05,
      "loss": 1.939,
      "step": 5800
    },
    {
      "epoch": 1.66,
      "learning_rate": 4.6930057244928707e-05,
      "loss": 1.9489,
      "step": 5900
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.6153631767828776e-05,
      "loss": 1.9567,
      "step": 6000
    },
    {
      "epoch": 1.69,
      "eval_gen_len": 20.0,
      "eval_loss": 1.9752851724624634,
      "eval_rouge1": 21.8045,
      "eval_rouge2": 5.6422,
      "eval_rougeL": 21.628,
      "eval_rougeLsum": 21.6131,
      "eval_runtime": 162.1464,
      "eval_samples_per_second": 43.22,
      "eval_steps_per_second": 2.701,
      "step": 6000
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.529777698596109e-05,
      "loss": 1.9347,
      "step": 6100
    },
    {
      "epoch": 1.75,
      "learning_rate": 4.4365714143472324e-05,
      "loss": 1.9325,
      "step": 6200
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.3360951314441554e-05,
      "loss": 1.9184,
      "step": 6300
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.228727019928149e-05,
      "loss": 1.919,
      "step": 6400
    },
    {
      "epoch": 1.83,
      "learning_rate": 4.114871189127209e-05,
      "loss": 1.9375,
      "step": 6500
    },
    {
      "epoch": 1.86,
      "learning_rate": 3.994956166679789e-05,
      "loss": 1.9609,
      "step": 6600
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.869433285653533e-05,
      "loss": 1.9409,
      "step": 6700
    },
    {
      "epoch": 1.92,
      "learning_rate": 3.73877498582952e-05,
      "loss": 1.9153,
      "step": 6800
    },
    {
      "epoch": 1.94,
      "learning_rate": 3.603473035545605e-05,
      "loss": 1.918,
      "step": 6900
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.4640366807914365e-05,
      "loss": 1.9425,
      "step": 7000
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.320990728521537e-05,
      "loss": 1.918,
      "step": 7100
    },
    {
      "epoch": 2.03,
      "learning_rate": 3.174873571400432e-05,
      "loss": 1.7143,
      "step": 7200
    },
    {
      "epoch": 2.06,
      "learning_rate": 3.0262351614142278e-05,
      "loss": 1.7251,
      "step": 7300
    },
    {
      "epoch": 2.09,
      "learning_rate": 2.875634939975517e-05,
      "loss": 1.7188,
      "step": 7400
    },
    {
      "epoch": 2.11,
      "learning_rate": 2.7236397323122172e-05,
      "loss": 1.732,
      "step": 7500
    },
    {
      "epoch": 2.14,
      "learning_rate": 2.570821614065411e-05,
      "loss": 1.7565,
      "step": 7600
    },
    {
      "epoch": 2.17,
      "learning_rate": 2.4177557581258026e-05,
      "loss": 1.7159,
      "step": 7700
    },
    {
      "epoch": 2.2,
      "learning_rate": 2.2650182698128346e-05,
      "loss": 1.7191,
      "step": 7800
    },
    {
      "epoch": 2.23,
      "learning_rate": 2.1131840185443426e-05,
      "loss": 1.7215,
      "step": 7900
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.962824474157885e-05,
      "loss": 1.7129,
      "step": 8000
    },
    {
      "epoch": 2.25,
      "eval_gen_len": 20.0,
      "eval_loss": 1.9584242105484009,
      "eval_rouge1": 22.117,
      "eval_rouge2": 5.7798,
      "eval_rougeL": 21.9114,
      "eval_rougeLsum": 21.8886,
      "eval_runtime": 162.6289,
      "eval_samples_per_second": 43.092,
      "eval_steps_per_second": 2.693,
      "step": 8000
    },
    {
      "epoch": 2.28,
      "learning_rate": 1.8145055560273016e-05,
      "loss": 1.6991,
      "step": 8100
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.6687855030699798e-05,
      "loss": 1.7131,
      "step": 8200
    },
    {
      "epoch": 2.34,
      "learning_rate": 1.52621277266162e-05,
      "loss": 1.7091,
      "step": 8300
    },
    {
      "epoch": 2.37,
      "learning_rate": 1.3873239763665138e-05,
      "loss": 1.7208,
      "step": 8400
    },
    {
      "epoch": 2.4,
      "learning_rate": 1.2526418602527839e-05,
      "loss": 1.7373,
      "step": 8500
    },
    {
      "epoch": 2.42,
      "learning_rate": 1.1226733373942214e-05,
      "loss": 1.6905,
      "step": 8600
    },
    {
      "epoch": 2.45,
      "learning_rate": 9.979075799639335e-06,
      "loss": 1.7103,
      "step": 8700
    },
    {
      "epoch": 2.48,
      "learning_rate": 8.788141781007439e-06,
      "loss": 1.7381,
      "step": 8800
    },
    {
      "epoch": 2.51,
      "learning_rate": 7.658413724779386e-06,
      "loss": 1.7005,
      "step": 8900
    },
    {
      "epoch": 2.54,
      "learning_rate": 6.594143672265889e-06,
      "loss": 1.692,
      "step": 9000
    },
    {
      "epoch": 2.56,
      "learning_rate": 5.599337295632133e-06,
      "loss": 1.6929,
      "step": 9100
    },
    {
      "epoch": 2.59,
      "learning_rate": 4.677738821452162e-06,
      "loss": 1.7245,
      "step": 9200
    },
    {
      "epoch": 2.62,
      "learning_rate": 3.832816938285592e-06,
      "loss": 1.6818,
      "step": 9300
    },
    {
      "epoch": 2.65,
      "learning_rate": 3.0677517413170523e-06,
      "loss": 1.7,
      "step": 9400
    },
    {
      "epoch": 2.68,
      "learning_rate": 2.385422763195976e-06,
      "loss": 1.6961,
      "step": 9500
    },
    {
      "epoch": 2.71,
      "learning_rate": 1.7883981361259272e-06,
      "loss": 1.7067,
      "step": 9600
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.2789249259948616e-06,
      "loss": 1.6975,
      "step": 9700
    },
    {
      "epoch": 2.76,
      "learning_rate": 8.589206749264998e-07,
      "loss": 1.7217,
      "step": 9800
    },
    {
      "epoch": 2.79,
      "learning_rate": 5.29966184084788e-07,
      "loss": 1.7213,
      "step": 9900
    },
    {
      "epoch": 2.82,
      "learning_rate": 2.932995638952263e-07,
      "loss": 1.7072,
      "step": 10000
    },
    {
      "epoch": 2.82,
      "eval_gen_len": 20.0,
      "eval_loss": 1.933449387550354,
      "eval_rouge1": 22.3137,
      "eval_rouge2": 5.8376,
      "eval_rougeL": 22.1264,
      "eval_rougeLsum": 22.1274,
      "eval_runtime": 162.4524,
      "eval_samples_per_second": 43.139,
      "eval_steps_per_second": 2.696,
      "step": 10000
    },
    {
      "epoch": 2.85,
      "learning_rate": 1.5078315448915942e-07,
      "loss": 1.6934,
      "step": 10100
    },
    {
      "epoch": 2.87,
      "learning_rate": 1.0007514846990862e-07,
      "loss": 1.6952,
      "step": 10200
    },
    {
      "epoch": 2.9,
      "learning_rate": 4.998917939712543e-05,
      "loss": 1.757,
      "step": 10300
    },
    {
      "epoch": 2.93,
      "learning_rate": 4.995490569865264e-05,
      "loss": 1.7591,
      "step": 10400
    },
    {
      "epoch": 2.96,
      "learning_rate": 4.989719237466243e-05,
      "loss": 1.7812,
      "step": 10500
    },
    {
      "epoch": 2.99,
      "learning_rate": 4.9816093742915244e-05,
      "loss": 1.7639,
      "step": 10600
    },
    {
      "epoch": 3.02,
      "learning_rate": 4.9711686130604656e-05,
      "loss": 1.7264,
      "step": 10700
    },
    {
      "epoch": 3.04,
      "learning_rate": 4.9584067802520866e-05,
      "loss": 1.6739,
      "step": 10800
    },
    {
      "epoch": 3.07,
      "learning_rate": 4.943497980862275e-05,
      "loss": 1.6629,
      "step": 10900
    },
    {
      "epoch": 3.1,
      "learning_rate": 4.926155082525451e-05,
      "loss": 1.6756,
      "step": 11000
    },
    {
      "epoch": 3.13,
      "learning_rate": 4.906533477770676e-05,
      "loss": 1.6823,
      "step": 11100
    },
    {
      "epoch": 3.16,
      "learning_rate": 4.884651633765546e-05,
      "loss": 1.6432,
      "step": 11200
    },
    {
      "epoch": 3.18,
      "learning_rate": 4.860530144935725e-05,
      "loss": 1.6803,
      "step": 11300
    },
    {
      "epoch": 3.21,
      "learning_rate": 4.834191713582197e-05,
      "loss": 1.6985,
      "step": 11400
    },
    {
      "epoch": 3.24,
      "learning_rate": 4.8056611285146466e-05,
      "loss": 1.7087,
      "step": 11500
    },
    {
      "epoch": 3.27,
      "learning_rate": 4.7749652417211076e-05,
      "loss": 1.7142,
      "step": 11600
    },
    {
      "epoch": 3.3,
      "learning_rate": 4.742132943095807e-05,
      "loss": 1.7135,
      "step": 11700
    },
    {
      "epoch": 3.33,
      "learning_rate": 4.70719513324901e-05,
      "loss": 1.7136,
      "step": 11800
    },
    {
      "epoch": 3.35,
      "learning_rate": 4.670184694424442e-05,
      "loss": 1.7098,
      "step": 11900
    },
    {
      "epoch": 3.38,
      "learning_rate": 4.63113645955168e-05,
      "loss": 1.7184,
      "step": 12000
    },
    {
      "epoch": 3.38,
      "eval_gen_len": 20.0,
      "eval_loss": 2.0014004707336426,
      "eval_rouge1": 21.452,
      "eval_rouge2": 5.494,
      "eval_rougeL": 21.3143,
      "eval_rougeLsum": 21.3158,
      "eval_runtime": 162.8289,
      "eval_samples_per_second": 43.039,
      "eval_steps_per_second": 2.69,
      "step": 12000
    },
    {
      "epoch": 3.41,
      "learning_rate": 4.590087179462613e-05,
      "loss": 1.7121,
      "step": 12100
    },
    {
      "epoch": 3.44,
      "learning_rate": 4.547075488302845e-05,
      "loss": 1.7064,
      "step": 12200
    },
    {
      "epoch": 3.47,
      "learning_rate": 4.502141867170594e-05,
      "loss": 1.7182,
      "step": 12300
    },
    {
      "epoch": 3.49,
      "learning_rate": 4.455328606017294e-05,
      "loss": 1.7126,
      "step": 12400
    },
    {
      "epoch": 3.52,
      "learning_rate": 4.4066797638457747e-05,
      "loss": 1.7135,
      "step": 12500
    },
    {
      "epoch": 3.55,
      "learning_rate": 4.3562411272434736e-05,
      "loss": 1.7224,
      "step": 12600
    },
    {
      "epoch": 3.58,
      "learning_rate": 4.304060167289698e-05,
      "loss": 1.7393,
      "step": 12700
    },
    {
      "epoch": 3.61,
      "learning_rate": 4.250185994877508e-05,
      "loss": 1.7153,
      "step": 12800
    },
    {
      "epoch": 3.64,
      "learning_rate": 4.194669314492266e-05,
      "loss": 1.6978,
      "step": 12900
    },
    {
      "epoch": 3.66,
      "learning_rate": 4.137562376490343e-05,
      "loss": 1.7238,
      "step": 13000
    },
    {
      "epoch": 3.69,
      "learning_rate": 4.07891892792292e-05,
      "loss": 1.73,
      "step": 13100
    },
    {
      "epoch": 3.72,
      "learning_rate": 4.0187941619511394e-05,
      "loss": 1.7077,
      "step": 13200
    },
    {
      "epoch": 3.75,
      "learning_rate": 3.957244665900235e-05,
      "loss": 1.696,
      "step": 13300
    },
    {
      "epoch": 3.78,
      "learning_rate": 3.8943283680015245e-05,
      "loss": 1.7197,
      "step": 13400
    },
    {
      "epoch": 3.8,
      "learning_rate": 3.830104482872382e-05,
      "loss": 1.755,
      "step": 13500
    },
    {
      "epoch": 3.83,
      "learning_rate": 3.764633455785513e-05,
      "loss": 1.7267,
      "step": 13600
    },
    {
      "epoch": 3.86,
      "learning_rate": 3.697976905779984e-05,
      "loss": 1.7325,
      "step": 13700
    },
    {
      "epoch": 3.89,
      "learning_rate": 3.630197567667534e-05,
      "loss": 1.7396,
      "step": 13800
    },
    {
      "epoch": 3.92,
      "learning_rate": 3.5613592329887714e-05,
      "loss": 1.7154,
      "step": 13900
    },
    {
      "epoch": 3.95,
      "learning_rate": 3.491526689974802e-05,
      "loss": 1.7372,
      "step": 14000
    },
    {
      "epoch": 3.95,
      "eval_gen_len": 20.0,
      "eval_loss": 1.9770143032073975,
      "eval_rouge1": 22.273,
      "eval_rouge2": 5.7637,
      "eval_rougeL": 22.1,
      "eval_rougeLsum": 22.0813,
      "eval_runtime": 163.6202,
      "eval_samples_per_second": 42.831,
      "eval_steps_per_second": 2.677,
      "step": 14000
    },
    {
      "epoch": 3.97,
      "learning_rate": 3.42076566257082e-05,
      "loss": 1.756,
      "step": 14100
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.349142748579026e-05,
      "loss": 1.7312,
      "step": 14200
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.276725356979111e-05,
      "loss": 1.4431,
      "step": 14300
    },
    {
      "epoch": 4.06,
      "learning_rate": 3.2035816444852827e-05,
      "loss": 1.4696,
      "step": 14400
    },
    {
      "epoch": 4.09,
      "learning_rate": 3.1297804513995484e-05,
      "loss": 1.4713,
      "step": 14500
    },
    {
      "epoch": 4.11,
      "learning_rate": 3.055391236821639e-05,
      "loss": 1.4552,
      "step": 14600
    },
    {
      "epoch": 4.14,
      "learning_rate": 2.9804840132765305e-05,
      "loss": 1.4596,
      "step": 14700
    },
    {
      "epoch": 4.17,
      "learning_rate": 2.905129280821106e-05,
      "loss": 1.4558,
      "step": 14800
    },
    {
      "epoch": 4.2,
      "learning_rate": 2.8293979606919723e-05,
      "loss": 1.4785,
      "step": 14900
    },
    {
      "epoch": 4.23,
      "learning_rate": 2.7533613285568734e-05,
      "loss": 1.4652,
      "step": 15000
    },
    {
      "epoch": 4.26,
      "learning_rate": 2.6778545727506706e-05,
      "loss": 1.4952,
      "step": 15100
    },
    {
      "epoch": 4.28,
      "learning_rate": 2.6014234894273854e-05,
      "loss": 1.4794,
      "step": 15200
    },
    {
      "epoch": 4.31,
      "learning_rate": 2.5249016556908847e-05,
      "loss": 1.4764,
      "step": 15300
    },
    {
      "epoch": 4.34,
      "learning_rate": 2.448361091212649e-05,
      "loss": 1.4685,
      "step": 15400
    },
    {
      "epoch": 4.37,
      "learning_rate": 2.3718738332928784e-05,
      "loss": 1.4858,
      "step": 15500
    },
    {
      "epoch": 4.4,
      "learning_rate": 2.295511869061505e-05,
      "loss": 1.4953,
      "step": 15600
    },
    {
      "epoch": 4.43,
      "learning_rate": 2.219347067726429e-05,
      "loss": 1.4836,
      "step": 15700
    },
    {
      "epoch": 4.45,
      "learning_rate": 2.143451112932731e-05,
      "loss": 1.4926,
      "step": 15800
    },
    {
      "epoch": 4.48,
      "learning_rate": 2.0678954352965396e-05,
      "loss": 1.4652,
      "step": 15900
    },
    {
      "epoch": 4.51,
      "learning_rate": 1.992751145177032e-05,
      "loss": 1.4724,
      "step": 16000
    },
    {
      "epoch": 4.51,
      "eval_gen_len": 20.0,
      "eval_loss": 2.019371509552002,
      "eval_rouge1": 22.0979,
      "eval_rouge2": 5.7144,
      "eval_rougeL": 21.9045,
      "eval_rougeLsum": 21.8765,
      "eval_runtime": 162.8312,
      "eval_samples_per_second": 43.038,
      "eval_steps_per_second": 2.69,
      "step": 16000
    },
    {
      "epoch": 4.54,
      "learning_rate": 1.9180889657498532e-05,
      "loss": 1.4723,
      "step": 16100
    },
    {
      "epoch": 4.57,
      "learning_rate": 1.843979166444942e-05,
      "loss": 1.475,
      "step": 16200
    },
    {
      "epoch": 4.59,
      "learning_rate": 1.770491496811398e-05,
      "loss": 1.4657,
      "step": 16300
    },
    {
      "epoch": 4.62,
      "learning_rate": 1.6976951208716527e-05,
      "loss": 1.466,
      "step": 16400
    },
    {
      "epoch": 4.65,
      "learning_rate": 1.625658552026706e-05,
      "loss": 1.4649,
      "step": 16500
    },
    {
      "epoch": 4.68,
      "learning_rate": 1.554449588573719e-05,
      "loss": 1.4792,
      "step": 16600
    },
    {
      "epoch": 4.71,
      "learning_rate": 1.4841352498966237e-05,
      "loss": 1.4477,
      "step": 16700
    },
    {
      "epoch": 4.74,
      "learning_rate": 1.4147817133898276e-05,
      "loss": 1.4744,
      "step": 16800
    },
    {
      "epoch": 4.76,
      "learning_rate": 1.346454252174365e-05,
      "loss": 1.4915,
      "step": 16900
    },
    {
      "epoch": 4.79,
      "learning_rate": 1.2792171736651217e-05,
      "loss": 1.4767,
      "step": 17000
    },
    {
      "epoch": 4.82,
      "learning_rate": 1.213133759046946e-05,
      "loss": 1.483,
      "step": 17100
    },
    {
      "epoch": 4.85,
      "learning_rate": 1.148908659327833e-05,
      "loss": 1.4579,
      "step": 17200
    },
    {
      "epoch": 4.88,
      "learning_rate": 1.0853049469504679e-05,
      "loss": 1.4791,
      "step": 17300
    },
    {
      "epoch": 4.9,
      "learning_rate": 1.0230374018646024e-05,
      "loss": 1.4593,
      "step": 17400
    },
    {
      "epoch": 4.93,
      "learning_rate": 9.621646281041709e-06,
      "loss": 1.4629,
      "step": 17500
    },
    {
      "epoch": 4.96,
      "learning_rate": 9.027439169931561e-06,
      "loss": 1.4677,
      "step": 17600
    },
    {
      "epoch": 4.99,
      "learning_rate": 8.448311932250029e-06,
      "loss": 1.4382,
      "step": 17700
    },
    {
      "epoch": 5.02,
      "learning_rate": 7.884809622282473e-06,
      "loss": 1.369,
      "step": 17800
    },
    {
      "epoch": 5.05,
      "learning_rate": 7.337462588679232e-06,
      "loss": 1.3049,
      "step": 17900
    },
    {
      "epoch": 5.07,
      "learning_rate": 6.806785975309991e-06,
      "loss": 1.3297,
      "step": 18000
    },
    {
      "epoch": 5.07,
      "eval_gen_len": 20.0,
      "eval_loss": 2.037019729614258,
      "eval_rouge1": 21.9,
      "eval_rouge2": 5.533,
      "eval_rougeL": 21.7042,
      "eval_rougeLsum": 21.7021,
      "eval_runtime": 162.394,
      "eval_samples_per_second": 43.154,
      "eval_steps_per_second": 2.697,
      "step": 18000
    },
    {
      "epoch": 5.1,
      "learning_rate": 6.293279236428415e-06,
      "loss": 1.3197,
      "step": 18100
    },
    {
      "epoch": 5.13,
      "learning_rate": 5.7974256666032834e-06,
      "loss": 1.2993,
      "step": 18200
    },
    {
      "epoch": 5.16,
      "learning_rate": 5.31969194585855e-06,
      "loss": 1.3202,
      "step": 18300
    },
    {
      "epoch": 5.19,
      "learning_rate": 4.8605277004504475e-06,
      "loss": 1.2897,
      "step": 18400
    },
    {
      "epoch": 5.21,
      "learning_rate": 4.42036507969501e-06,
      "loss": 1.3157,
      "step": 18500
    },
    {
      "epoch": 5.24,
      "learning_rate": 3.999618349244242e-06,
      "loss": 1.3208,
      "step": 18600
    },
    {
      "epoch": 5.27,
      "learning_rate": 3.5986835011937814e-06,
      "loss": 1.3238,
      "step": 18700
    },
    {
      "epoch": 5.3,
      "learning_rate": 3.2179378813890276e-06,
      "loss": 1.3285,
      "step": 18800
    },
    {
      "epoch": 5.33,
      "learning_rate": 2.857739834280396e-06,
      "loss": 1.3075,
      "step": 18900
    },
    {
      "epoch": 5.36,
      "learning_rate": 2.5184283656621174e-06,
      "loss": 1.3187,
      "step": 19000
    },
    {
      "epoch": 5.38,
      "learning_rate": 2.2003228236118087e-06,
      "loss": 1.3019,
      "step": 19100
    },
    {
      "epoch": 5.41,
      "learning_rate": 1.9037225979312562e-06,
      "loss": 1.3156,
      "step": 19200
    },
    {
      "epoch": 5.44,
      "learning_rate": 1.631546296469755e-06,
      "loss": 1.2991,
      "step": 19300
    },
    {
      "epoch": 5.47,
      "learning_rate": 1.3785520064985022e-06,
      "loss": 1.2969,
      "step": 19400
    },
    {
      "epoch": 5.5,
      "learning_rate": 1.1478364548263003e-06,
      "loss": 1.3149,
      "step": 19500
    },
    {
      "epoch": 5.52,
      "learning_rate": 9.396167828548325e-07,
      "loss": 1.2895,
      "step": 19600
    },
    {
      "epoch": 5.55,
      "learning_rate": 7.540889596512168e-07,
      "loss": 1.3152,
      "step": 19700
    },
    {
      "epoch": 5.58,
      "learning_rate": 5.914275975087762e-07,
      "loss": 1.3272,
      "step": 19800
    },
    {
      "epoch": 5.61,
      "learning_rate": 4.517857876080481e-07,
      "loss": 1.3142,
      "step": 19900
    },
    {
      "epoch": 5.64,
      "learning_rate": 3.352949559327476e-07,
      "loss": 1.3186,
      "step": 20000
    },
    {
      "epoch": 5.64,
      "eval_gen_len": 20.0,
      "eval_loss": 2.039311170578003,
      "eval_rouge1": 21.585,
      "eval_rouge2": 5.4626,
      "eval_rougeL": 21.4273,
      "eval_rougeLsum": 21.4329,
      "eval_runtime": 162.2232,
      "eval_samples_per_second": 43.2,
      "eval_steps_per_second": 2.7,
      "step": 20000
    },
    {
      "epoch": 5.67,
      "learning_rate": 2.4206473957621197e-07,
      "loss": 1.3001,
      "step": 20100
    },
    {
      "epoch": 5.69,
      "learning_rate": 1.721828835548135e-07,
      "loss": 1.3033,
      "step": 20200
    },
    {
      "epoch": 5.72,
      "learning_rate": 1.2571515822542734e-07,
      "loss": 1.3053,
      "step": 20300
    },
    {
      "epoch": 5.75,
      "learning_rate": 1.0270529738465452e-07,
      "loss": 1.3123,
      "step": 20400
    },
    {
      "epoch": 5.78,
      "learning_rate": 4.9999206248096876e-05,
      "loss": 1.3399,
      "step": 20500
    },
    {
      "epoch": 5.81,
      "learning_rate": 4.999321815444586e-05,
      "loss": 1.3654,
      "step": 20600
    },
    {
      "epoch": 5.83,
      "learning_rate": 4.9981360794562834e-05,
      "loss": 1.3834,
      "step": 20700
    },
    {
      "epoch": 5.86,
      "learning_rate": 4.996363695854496e-05,
      "loss": 1.4284,
      "step": 20800
    },
    {
      "epoch": 5.89,
      "learning_rate": 4.994005081690109e-05,
      "loss": 1.4216,
      "step": 20900
    },
    {
      "epoch": 5.92,
      "learning_rate": 4.991060791957044e-05,
      "loss": 1.4262,
      "step": 21000
    },
    {
      "epoch": 5.95,
      "learning_rate": 4.987531519461667e-05,
      "loss": 1.4331,
      "step": 21100
    },
    {
      "epoch": 5.98,
      "learning_rate": 4.983418094659765e-05,
      "loss": 1.4425,
      "step": 21200
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.978721485461138e-05,
      "loss": 1.4284,
      "step": 21300
    },
    {
      "epoch": 6.03,
      "learning_rate": 4.973554067339494e-05,
      "loss": 1.3686,
      "step": 21400
    },
    {
      "epoch": 6.06,
      "learning_rate": 4.967706145407849e-05,
      "loss": 1.3545,
      "step": 21500
    },
    {
      "epoch": 6.09,
      "learning_rate": 4.961278736181136e-05,
      "loss": 1.3899,
      "step": 21600
    },
    {
      "epoch": 6.12,
      "learning_rate": 4.954273352061473e-05,
      "loss": 1.3801,
      "step": 21700
    },
    {
      "epoch": 6.14,
      "learning_rate": 4.946691641451411e-05,
      "loss": 1.3902,
      "step": 21800
    },
    {
      "epoch": 6.17,
      "learning_rate": 4.938535388366059e-05,
      "loss": 1.3836,
      "step": 21900
    },
    {
      "epoch": 6.2,
      "learning_rate": 4.9298065120132974e-05,
      "loss": 1.3839,
      "step": 22000
    },
    {
      "epoch": 6.2,
      "eval_gen_len": 20.0,
      "eval_loss": 2.1140034198760986,
      "eval_rouge1": 20.6468,
      "eval_rouge2": 5.2318,
      "eval_rougeL": 20.4445,
      "eval_rougeLsum": 20.4398,
      "eval_runtime": 162.2862,
      "eval_samples_per_second": 43.183,
      "eval_steps_per_second": 2.699,
      "step": 22000
    },
    {
      "epoch": 6.23,
      "learning_rate": 4.920507066342175e-05,
      "loss": 1.4005,
      "step": 22100
    },
    {
      "epoch": 6.26,
      "learning_rate": 4.910639239559606e-05,
      "loss": 1.3887,
      "step": 22200
    },
    {
      "epoch": 6.29,
      "learning_rate": 4.900205353615477e-05,
      "loss": 1.4081,
      "step": 22300
    },
    {
      "epoch": 6.31,
      "learning_rate": 4.889207863656274e-05,
      "loss": 1.4239,
      "step": 22400
    },
    {
      "epoch": 6.34,
      "learning_rate": 4.87764935744738e-05,
      "loss": 1.4332,
      "step": 22500
    },
    {
      "epoch": 6.37,
      "learning_rate": 4.865532554764157e-05,
      "loss": 1.4264,
      "step": 22600
    },
    {
      "epoch": 6.4,
      "learning_rate": 4.852860306751969e-05,
      "loss": 1.4465,
      "step": 22700
    },
    {
      "epoch": 6.43,
      "learning_rate": 4.839635595255296e-05,
      "loss": 1.4339,
      "step": 22800
    },
    {
      "epoch": 6.45,
      "learning_rate": 4.825861532116087e-05,
      "loss": 1.4463,
      "step": 22900
    },
    {
      "epoch": 6.48,
      "learning_rate": 4.811541358441531e-05,
      "loss": 1.447,
      "step": 23000
    },
    {
      "epoch": 6.51,
      "learning_rate": 4.796678443841405e-05,
      "loss": 1.4343,
      "step": 23100
    },
    {
      "epoch": 6.54,
      "learning_rate": 4.78127628563519e-05,
      "loss": 1.4502,
      "step": 23200
    },
    {
      "epoch": 6.57,
      "learning_rate": 4.765338508029135e-05,
      "loss": 1.4459,
      "step": 23300
    },
    {
      "epoch": 6.6,
      "learning_rate": 4.748868861263457e-05,
      "loss": 1.4448,
      "step": 23400
    },
    {
      "epoch": 6.62,
      "learning_rate": 4.731871220729898e-05,
      "loss": 1.4377,
      "step": 23500
    },
    {
      "epoch": 6.65,
      "learning_rate": 4.714349586059819e-05,
      "loss": 1.4549,
      "step": 23600
    },
    {
      "epoch": 6.68,
      "learning_rate": 4.696308080183071e-05,
      "loss": 1.4393,
      "step": 23700
    },
    {
      "epoch": 6.71,
      "learning_rate": 4.677750948357847e-05,
      "loss": 1.4678,
      "step": 23800
    },
    {
      "epoch": 6.74,
      "learning_rate": 4.65868255717175e-05,
      "loss": 1.4629,
      "step": 23900
    },
    {
      "epoch": 6.76,
      "learning_rate": 4.639107393514314e-05,
      "loss": 1.4605,
      "step": 24000
    },
    {
      "epoch": 6.76,
      "eval_gen_len": 20.0,
      "eval_loss": 2.088627815246582,
      "eval_rouge1": 21.2304,
      "eval_rouge2": 5.2346,
      "eval_rougeL": 21.0611,
      "eval_rougeLsum": 21.0649,
      "eval_runtime": 163.3508,
      "eval_samples_per_second": 42.902,
      "eval_steps_per_second": 2.681,
      "step": 24000
    },
    {
      "epoch": 6.79,
      "learning_rate": 4.619030063521217e-05,
      "loss": 1.4447,
      "step": 24100
    },
    {
      "epoch": 6.82,
      "learning_rate": 4.5984552914904304e-05,
      "loss": 1.4733,
      "step": 24200
    },
    {
      "epoch": 6.85,
      "learning_rate": 4.5773879187705715e-05,
      "loss": 1.4607,
      "step": 24300
    },
    {
      "epoch": 6.88,
      "learning_rate": 4.555832902621708e-05,
      "loss": 1.4659,
      "step": 24400
    },
    {
      "epoch": 6.91,
      "learning_rate": 4.533795315048888e-05,
      "loss": 1.482,
      "step": 24500
    },
    {
      "epoch": 6.93,
      "learning_rate": 4.511280341608673e-05,
      "loss": 1.4645,
      "step": 24600
    },
    {
      "epoch": 6.96,
      "learning_rate": 4.488293280188952e-05,
      "loss": 1.4645,
      "step": 24700
    },
    {
      "epoch": 6.99,
      "learning_rate": 4.464839539762315e-05,
      "loss": 1.4573,
      "step": 24800
    },
    {
      "epoch": 7.02,
      "learning_rate": 4.4409246391133016e-05,
      "loss": 1.3075,
      "step": 24900
    },
    {
      "epoch": 7.05,
      "learning_rate": 4.416554205539801e-05,
      "loss": 1.2172,
      "step": 25000
    },
    {
      "epoch": 7.07,
      "learning_rate": 4.391733973528915e-05,
      "loss": 1.1984,
      "step": 25100
    },
    {
      "epoch": 7.1,
      "learning_rate": 4.3664697834076095e-05,
      "loss": 1.2395,
      "step": 25200
    },
    {
      "epoch": 7.13,
      "learning_rate": 4.340767579968456e-05,
      "loss": 1.2372,
      "step": 25300
    },
    {
      "epoch": 7.16,
      "learning_rate": 4.314896870880448e-05,
      "loss": 1.2366,
      "step": 25400
    },
    {
      "epoch": 7.19,
      "learning_rate": 4.288341113416578e-05,
      "loss": 1.2374,
      "step": 25500
    },
    {
      "epoch": 7.22,
      "learning_rate": 4.261365726708706e-05,
      "loss": 1.2235,
      "step": 25600
    },
    {
      "epoch": 7.24,
      "learning_rate": 4.2339770582026725e-05,
      "loss": 1.2633,
      "step": 25700
    },
    {
      "epoch": 7.27,
      "learning_rate": 4.206181552591627e-05,
      "loss": 1.2347,
      "step": 25800
    },
    {
      "epoch": 7.3,
      "learning_rate": 4.1779857502995634e-05,
      "loss": 1.2533,
      "step": 25900
    },
    {
      "epoch": 7.33,
      "learning_rate": 4.1493962859423225e-05,
      "loss": 1.2594,
      "step": 26000
    },
    {
      "epoch": 7.33,
      "eval_gen_len": 20.0,
      "eval_loss": 2.1528804302215576,
      "eval_rouge1": 21.6885,
      "eval_rouge2": 5.3904,
      "eval_rougeL": 21.4125,
      "eval_rougeLsum": 21.4342,
      "eval_runtime": 162.2811,
      "eval_samples_per_second": 43.184,
      "eval_steps_per_second": 2.699,
      "step": 26000
    },
    {
      "epoch": 7.36,
      "learning_rate": 4.120419886766432e-05,
      "loss": 1.2742,
      "step": 26100
    },
    {
      "epoch": 7.38,
      "learning_rate": 4.091063371066154e-05,
      "loss": 1.246,
      "step": 26200
    },
    {
      "epoch": 7.41,
      "learning_rate": 4.061632768309558e-05,
      "loss": 1.2496,
      "step": 26300
    },
    {
      "epoch": 7.44,
      "learning_rate": 4.03154045781127e-05,
      "loss": 1.2608,
      "step": 26400
    },
    {
      "epoch": 7.47,
      "learning_rate": 4.001088944570764e-05,
      "loss": 1.2696,
      "step": 26500
    },
    {
      "epoch": 7.5,
      "learning_rate": 3.9702853939841514e-05,
      "loss": 1.2624,
      "step": 26600
    },
    {
      "epoch": 7.53,
      "learning_rate": 3.939137054283725e-05,
      "loss": 1.2809,
      "step": 26700
    },
    {
      "epoch": 7.55,
      "learning_rate": 3.9076512548324085e-05,
      "loss": 1.2533,
      "step": 26800
    },
    {
      "epoch": 7.58,
      "learning_rate": 3.875835404399126e-05,
      "loss": 1.2811,
      "step": 26900
    },
    {
      "epoch": 7.61,
      "learning_rate": 3.843696989415477e-05,
      "loss": 1.2851,
      "step": 27000
    },
    {
      "epoch": 7.64,
      "learning_rate": 3.811243572214143e-05,
      "loss": 1.2661,
      "step": 27100
    },
    {
      "epoch": 7.67,
      "learning_rate": 3.7784827892494295e-05,
      "loss": 1.2661,
      "step": 27200
    },
    {
      "epoch": 7.69,
      "learning_rate": 3.745422349300373e-05,
      "loss": 1.2525,
      "step": 27300
    },
    {
      "epoch": 7.72,
      "learning_rate": 3.712070031656822e-05,
      "loss": 1.2864,
      "step": 27400
    },
    {
      "epoch": 7.75,
      "learning_rate": 3.6784336842889355e-05,
      "loss": 1.2801,
      "step": 27500
    },
    {
      "epoch": 7.78,
      "learning_rate": 3.64452122200051e-05,
      "loss": 1.2888,
      "step": 27600
    },
    {
      "epoch": 7.81,
      "learning_rate": 3.6103406245665894e-05,
      "loss": 1.2825,
      "step": 27700
    },
    {
      "epoch": 7.84,
      "learning_rate": 3.575899934855785e-05,
      "loss": 1.2791,
      "step": 27800
    },
    {
      "epoch": 7.86,
      "learning_rate": 3.5412072569377407e-05,
      "loss": 1.2704,
      "step": 27900
    },
    {
      "epoch": 7.89,
      "learning_rate": 3.506270754176212e-05,
      "loss": 1.2809,
      "step": 28000
    },
    {
      "epoch": 7.89,
      "eval_gen_len": 20.0,
      "eval_loss": 2.155640125274658,
      "eval_rouge1": 20.7036,
      "eval_rouge2": 5.3801,
      "eval_rougeL": 20.5265,
      "eval_rougeLsum": 20.5209,
      "eval_runtime": 163.3415,
      "eval_samples_per_second": 42.904,
      "eval_steps_per_second": 2.681,
      "step": 28000
    },
    {
      "epoch": 7.92,
      "learning_rate": 3.471098647308181e-05,
      "loss": 1.2758,
      "step": 28100
    },
    {
      "epoch": 7.95,
      "learning_rate": 3.4356992125094747e-05,
      "loss": 1.2923,
      "step": 28200
    },
    {
      "epoch": 7.98,
      "learning_rate": 3.40008077944734e-05,
      "loss": 1.2823,
      "step": 28300
    },
    {
      "epoch": 8.0,
      "learning_rate": 3.3642517293204305e-05,
      "loss": 1.265,
      "step": 28400
    },
    {
      "epoch": 8.03,
      "learning_rate": 3.328220492886667e-05,
      "loss": 1.0506,
      "step": 28500
    },
    {
      "epoch": 8.06,
      "learning_rate": 3.291995548479439e-05,
      "loss": 1.0599,
      "step": 28600
    },
    {
      "epoch": 8.09,
      "learning_rate": 3.255585420012606e-05,
      "loss": 1.07,
      "step": 28700
    },
    {
      "epoch": 8.12,
      "learning_rate": 3.2189986749747835e-05,
      "loss": 1.0685,
      "step": 28800
    },
    {
      "epoch": 8.15,
      "learning_rate": 3.182243922413361e-05,
      "loss": 1.088,
      "step": 28900
    },
    {
      "epoch": 8.17,
      "learning_rate": 3.145329810908756e-05,
      "loss": 1.0686,
      "step": 29000
    },
    {
      "epoch": 8.2,
      "learning_rate": 3.1082650265393565e-05,
      "loss": 1.0841,
      "step": 29100
    },
    {
      "epoch": 8.23,
      "learning_rate": 3.071058290837644e-05,
      "loss": 1.0808,
      "step": 29200
    },
    {
      "epoch": 8.26,
      "learning_rate": 3.0337183587379695e-05,
      "loss": 1.0797,
      "step": 29300
    },
    {
      "epoch": 8.29,
      "learning_rate": 2.9962540165164753e-05,
      "loss": 1.0824,
      "step": 29400
    },
    {
      "epoch": 8.31,
      "learning_rate": 2.958674079723637e-05,
      "loss": 1.0767,
      "step": 29500
    },
    {
      "epoch": 8.34,
      "learning_rate": 2.9209873911099242e-05,
      "loss": 1.0872,
      "step": 29600
    },
    {
      "epoch": 8.37,
      "learning_rate": 2.8832028185450523e-05,
      "loss": 1.0726,
      "step": 29700
    },
    {
      "epoch": 8.4,
      "learning_rate": 2.845329252931329e-05,
      "loss": 1.0763,
      "step": 29800
    },
    {
      "epoch": 8.43,
      "learning_rate": 2.8073756061115794e-05,
      "loss": 1.1097,
      "step": 29900
    },
    {
      "epoch": 8.46,
      "learning_rate": 2.7693508087721433e-05,
      "loss": 1.0819,
      "step": 30000
    },
    {
      "epoch": 8.46,
      "eval_gen_len": 20.0,
      "eval_loss": 2.23087477684021,
      "eval_rouge1": 20.9622,
      "eval_rouge2": 5.3019,
      "eval_rougeL": 20.7446,
      "eval_rougeLsum": 20.7429,
      "eval_runtime": 162.5566,
      "eval_samples_per_second": 43.111,
      "eval_steps_per_second": 2.694,
      "step": 30000
    },
    {
      "epoch": 8.48,
      "learning_rate": 2.731263808341441e-05,
      "loss": 1.1006,
      "step": 30100
    },
    {
      "epoch": 8.51,
      "learning_rate": 2.6931235668845973e-05,
      "loss": 1.0997,
      "step": 30200
    },
    {
      "epoch": 8.54,
      "learning_rate": 2.65493905899462e-05,
      "loss": 1.1084,
      "step": 30300
    },
    {
      "epoch": 8.57,
      "learning_rate": 2.6167192696806356e-05,
      "loss": 1.0907,
      "step": 30400
    },
    {
      "epoch": 8.6,
      "learning_rate": 2.5784731922536687e-05,
      "loss": 1.0974,
      "step": 30500
    },
    {
      "epoch": 8.62,
      "learning_rate": 2.540592515888669e-05,
      "loss": 1.1108,
      "step": 30600
    },
    {
      "epoch": 8.65,
      "learning_rate": 2.5023209030687986e-05,
      "loss": 1.1082,
      "step": 30700
    },
    {
      "epoch": 8.68,
      "learning_rate": 2.4640499206540774e-05,
      "loss": 1.0964,
      "step": 30800
    },
    {
      "epoch": 8.71,
      "learning_rate": 2.425788574001527e-05,
      "loss": 1.1008,
      "step": 30900
    },
    {
      "epoch": 8.74,
      "learning_rate": 2.3875458662008246e-05,
      "loss": 1.0956,
      "step": 31000
    },
    {
      "epoch": 8.77,
      "learning_rate": 2.3493307959558313e-05,
      "loss": 1.1051,
      "step": 31100
    },
    {
      "epoch": 8.79,
      "learning_rate": 2.3111523554671516e-05,
      "loss": 1.1033,
      "step": 31200
    },
    {
      "epoch": 8.82,
      "learning_rate": 2.2730195283162194e-05,
      "loss": 1.1003,
      "step": 31300
    },
    {
      "epoch": 8.85,
      "learning_rate": 2.2349412873514212e-05,
      "loss": 1.1031,
      "step": 31400
    },
    {
      "epoch": 8.88,
      "learning_rate": 2.1969265925767334e-05,
      "loss": 1.1195,
      "step": 31500
    },
    {
      "epoch": 8.91,
      "learning_rate": 2.158984389043391e-05,
      "loss": 1.0978,
      "step": 31600
    },
    {
      "epoch": 8.93,
      "learning_rate": 2.1211236047450704e-05,
      "loss": 1.1105,
      "step": 31700
    },
    {
      "epoch": 8.96,
      "learning_rate": 2.08335314851709e-05,
      "loss": 1.1088,
      "step": 31800
    },
    {
      "epoch": 8.99,
      "learning_rate": 2.0456819079401094e-05,
      "loss": 1.1241,
      "step": 31900
    },
    {
      "epoch": 9.02,
      "learning_rate": 2.008118747248843e-05,
      "loss": 0.9814,
      "step": 32000
    },
    {
      "epoch": 9.02,
      "eval_gen_len": 20.0,
      "eval_loss": 2.2810895442962646,
      "eval_rouge1": 20.6296,
      "eval_rouge2": 5.1936,
      "eval_rougeL": 20.4403,
      "eval_rougeLsum": 20.4304,
      "eval_runtime": 162.301,
      "eval_samples_per_second": 43.179,
      "eval_steps_per_second": 2.699,
      "step": 32000
    },
    {
      "epoch": 9.05,
      "learning_rate": 1.9706725052462575e-05,
      "loss": 0.9353,
      "step": 32100
    },
    {
      "epoch": 9.08,
      "learning_rate": 1.933351993223755e-05,
      "loss": 0.9372,
      "step": 32200
    },
    {
      "epoch": 9.1,
      "learning_rate": 1.8961659928878366e-05,
      "loss": 0.9601,
      "step": 32300
    },
    {
      "epoch": 9.13,
      "learning_rate": 1.859123254293715e-05,
      "loss": 0.9461,
      "step": 32400
    },
    {
      "epoch": 9.16,
      "learning_rate": 1.8222324937863884e-05,
      "loss": 0.9575,
      "step": 32500
    },
    {
      "epoch": 9.19,
      "learning_rate": 1.7858688692966636e-05,
      "loss": 0.951,
      "step": 32600
    },
    {
      "epoch": 9.22,
      "learning_rate": 1.74930633324332e-05,
      "loss": 0.9606,
      "step": 32700
    },
    {
      "epoch": 9.24,
      "learning_rate": 1.712921615757434e-05,
      "loss": 0.9316,
      "step": 32800
    },
    {
      "epoch": 9.27,
      "learning_rate": 1.676723278348288e-05,
      "loss": 0.9447,
      "step": 32900
    },
    {
      "epoch": 9.3,
      "learning_rate": 1.640719838668979e-05,
      "loss": 0.9591,
      "step": 33000
    },
    {
      "epoch": 9.33,
      "learning_rate": 1.604919768512179e-05,
      "loss": 0.9629,
      "step": 33100
    },
    {
      "epoch": 9.36,
      "learning_rate": 1.569331491816673e-05,
      "loss": 0.9541,
      "step": 33200
    },
    {
      "epoch": 9.39,
      "learning_rate": 1.53396338268517e-05,
      "loss": 0.9409,
      "step": 33300
    },
    {
      "epoch": 9.41,
      "learning_rate": 1.4988237634138258e-05,
      "loss": 0.9517,
      "step": 33400
    },
    {
      "epoch": 9.44,
      "learning_rate": 1.4639209025339731e-05,
      "loss": 0.9569,
      "step": 33500
    },
    {
      "epoch": 9.47,
      "learning_rate": 1.4292630128664853e-05,
      "loss": 0.9421,
      "step": 33600
    },
    {
      "epoch": 9.5,
      "learning_rate": 1.3948582495892665e-05,
      "loss": 0.9455,
      "step": 33700
    },
    {
      "epoch": 9.53,
      "learning_rate": 1.3610548242500389e-05,
      "loss": 0.9553,
      "step": 33800
    },
    {
      "epoch": 9.55,
      "learning_rate": 1.3271778070102909e-05,
      "loss": 0.9668,
      "step": 33900
    },
    {
      "epoch": 9.58,
      "learning_rate": 1.2935779373295224e-05,
      "loss": 0.9403,
      "step": 34000
    },
    {
      "epoch": 9.58,
      "eval_gen_len": 20.0,
      "eval_loss": 2.29062819480896,
      "eval_rouge1": 21.0701,
      "eval_rouge2": 5.1666,
      "eval_rougeL": 20.8587,
      "eval_rougeLsum": 20.8463,
      "eval_runtime": 162.5034,
      "eval_samples_per_second": 43.125,
      "eval_steps_per_second": 2.695,
      "step": 34000
    },
    {
      "epoch": 9.61,
      "learning_rate": 1.2602631214281477e-05,
      "loss": 0.9553,
      "step": 34100
    },
    {
      "epoch": 9.64,
      "learning_rate": 1.2272411984519708e-05,
      "loss": 0.9575,
      "step": 34200
    },
    {
      "epoch": 9.67,
      "learning_rate": 1.1945199386276041e-05,
      "loss": 0.9545,
      "step": 34300
    },
    {
      "epoch": 9.7,
      "learning_rate": 1.1621070414340846e-05,
      "loss": 0.9406,
      "step": 34400
    },
    {
      "epoch": 9.72,
      "learning_rate": 1.1300101337911568e-05,
      "loss": 0.9689,
      "step": 34500
    },
    {
      "epoch": 9.75,
      "learning_rate": 1.0982367682646119e-05,
      "loss": 0.9576,
      "step": 34600
    },
    {
      "epoch": 9.78,
      "learning_rate": 1.0667944212891339e-05,
      "loss": 0.9547,
      "step": 34700
    },
    {
      "epoch": 9.81,
      "learning_rate": 1.0356904914090589e-05,
      "loss": 0.9619,
      "step": 34800
    },
    {
      "epoch": 9.84,
      "learning_rate": 1.0049322975374548e-05,
      "loss": 0.9578,
      "step": 34900
    },
    {
      "epoch": 9.86,
      "learning_rate": 9.745270772339474e-06,
      "loss": 0.9509,
      "step": 35000
    },
    {
      "epoch": 9.89,
      "learning_rate": 9.447806300054016e-06,
      "loss": 0.9593,
      "step": 35100
    },
    {
      "epoch": 9.92,
      "learning_rate": 9.15099028916227e-06,
      "loss": 0.9576,
      "step": 35200
    },
    {
      "epoch": 9.95,
      "learning_rate": 8.857915396206473e-06,
      "loss": 0.9653,
      "step": 35300
    },
    {
      "epoch": 9.98,
      "learning_rate": 8.56865058320117e-06,
      "loss": 0.958,
      "step": 35400
    },
    {
      "epoch": 10.0,
      "step": 35480,
      "total_flos": 2.3762843604025344e+17,
      "train_loss": 1.5038130920392954,
      "train_runtime": 13804.3068,
      "train_samples_per_second": 41.118,
      "train_steps_per_second": 2.57
    }
  ],
  "max_steps": 35480,
  "num_train_epochs": 10,
  "total_flos": 2.3762843604025344e+17,
  "trial_name": null,
  "trial_params": null
}