{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 29.78494623655914,
  "global_step": 13850,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.22,
      "learning_rate": 4.964157706093191e-06,
      "loss": 2.9056,
      "step": 100
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.928315412186381e-06,
      "loss": 2.7058,
      "step": 200
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.89247311827957e-06,
      "loss": 2.6284,
      "step": 300
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.85663082437276e-06,
      "loss": 2.6307,
      "step": 400
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.32030987739563,
      "eval_rouge1": 0.32786127224568706,
      "eval_rouge2": 0.19018098494575836,
      "eval_rougeL": 0.2859655333642799,
      "eval_rougeLsum": 0.2934811385373408,
      "eval_runtime": 123.7208,
      "eval_samples_per_second": 3.758,
      "eval_steps_per_second": 0.946,
      "step": 465
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.8207885304659505e-06,
      "loss": 2.5668,
      "step": 500
    },
    {
      "epoch": 1.29,
      "learning_rate": 4.78494623655914e-06,
      "loss": 2.5604,
      "step": 600
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.74910394265233e-06,
      "loss": 2.5143,
      "step": 700
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.71326164874552e-06,
      "loss": 2.4849,
      "step": 800
    },
    {
      "epoch": 1.94,
      "learning_rate": 4.67741935483871e-06,
      "loss": 2.5315,
      "step": 900
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.240959644317627,
      "eval_rouge1": 0.3420570918954662,
      "eval_rouge2": 0.2060604177908008,
      "eval_rougeL": 0.3043927804421642,
      "eval_rougeLsum": 0.31155659054764084,
      "eval_runtime": 120.8082,
      "eval_samples_per_second": 3.849,
      "eval_steps_per_second": 0.968,
      "step": 930
    },
    {
      "epoch": 2.15,
      "learning_rate": 4.6415770609319e-06,
      "loss": 2.4132,
      "step": 1000
    },
    {
      "epoch": 2.37,
      "learning_rate": 4.60573476702509e-06,
      "loss": 2.4667,
      "step": 1100
    },
    {
      "epoch": 2.58,
      "learning_rate": 4.56989247311828e-06,
      "loss": 2.4937,
      "step": 1200
    },
    {
      "epoch": 2.8,
      "learning_rate": 4.5340501792114695e-06,
      "loss": 2.4156,
      "step": 1300
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.1922943592071533,
      "eval_rouge1": 0.34994978899734663,
      "eval_rouge2": 0.21185951083528443,
      "eval_rougeL": 0.31353678054844464,
      "eval_rougeLsum": 0.3205520009823804,
      "eval_runtime": 128.6775,
      "eval_samples_per_second": 3.614,
      "eval_steps_per_second": 0.909,
      "step": 1395
    },
    {
      "epoch": 3.01,
      "learning_rate": 4.49820788530466e-06,
      "loss": 2.3945,
      "step": 1400
    },
    {
      "epoch": 3.23,
      "learning_rate": 4.46236559139785e-06,
      "loss": 2.4332,
      "step": 1500
    },
    {
      "epoch": 3.44,
      "learning_rate": 4.42652329749104e-06,
      "loss": 2.3549,
      "step": 1600
    },
    {
      "epoch": 3.66,
      "learning_rate": 4.39068100358423e-06,
      "loss": 2.3908,
      "step": 1700
    },
    {
      "epoch": 3.87,
      "learning_rate": 4.35483870967742e-06,
      "loss": 2.3961,
      "step": 1800
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.15604567527771,
      "eval_rouge1": 0.35503098444416914,
      "eval_rouge2": 0.21345222912541117,
      "eval_rougeL": 0.3183951453816757,
      "eval_rougeLsum": 0.3245199945586198,
      "eval_runtime": 120.7681,
      "eval_samples_per_second": 3.85,
      "eval_steps_per_second": 0.969,
      "step": 1860
    },
    {
      "epoch": 4.09,
      "learning_rate": 4.31899641577061e-06,
      "loss": 2.3369,
      "step": 1900
    },
    {
      "epoch": 4.3,
      "learning_rate": 4.2831541218638e-06,
      "loss": 2.3171,
      "step": 2000
    },
    {
      "epoch": 4.52,
      "learning_rate": 4.2473118279569895e-06,
      "loss": 2.3699,
      "step": 2100
    },
    {
      "epoch": 4.73,
      "learning_rate": 4.211469534050179e-06,
      "loss": 2.3445,
      "step": 2200
    },
    {
      "epoch": 4.95,
      "learning_rate": 4.17562724014337e-06,
      "loss": 2.3595,
      "step": 2300
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.128229856491089,
      "eval_rouge1": 0.35828380214110583,
      "eval_rouge2": 0.2154697652390767,
      "eval_rougeL": 0.32071886194683874,
      "eval_rougeLsum": 0.326832484203238,
      "eval_runtime": 121.0509,
      "eval_samples_per_second": 3.841,
      "eval_steps_per_second": 0.967,
      "step": 2325
    },
    {
      "epoch": 5.16,
      "learning_rate": 4.139784946236559e-06,
      "loss": 2.2672,
      "step": 2400
    },
    {
      "epoch": 5.38,
      "learning_rate": 4.103942652329749e-06,
      "loss": 2.2787,
      "step": 2500
    },
    {
      "epoch": 5.59,
      "learning_rate": 4.0681003584229395e-06,
      "loss": 2.2953,
      "step": 2600
    },
    {
      "epoch": 5.81,
      "learning_rate": 4.032258064516129e-06,
      "loss": 2.3433,
      "step": 2700
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.1061463356018066,
      "eval_rouge1": 0.3602290098399774,
      "eval_rouge2": 0.21720084816876015,
      "eval_rougeL": 0.321761715180238,
      "eval_rougeLsum": 0.3282393870616483,
      "eval_runtime": 120.1834,
      "eval_samples_per_second": 3.869,
      "eval_steps_per_second": 0.974,
      "step": 2790
    },
    {
      "epoch": 6.02,
      "learning_rate": 3.996415770609319e-06,
      "loss": 2.2877,
      "step": 2800
    },
    {
      "epoch": 6.24,
      "learning_rate": 3.960573476702509e-06,
      "loss": 2.245,
      "step": 2900
    },
    {
      "epoch": 6.45,
      "learning_rate": 3.924731182795699e-06,
      "loss": 2.3009,
      "step": 3000
    },
    {
      "epoch": 6.67,
      "learning_rate": 3.88888888888889e-06,
      "loss": 2.2201,
      "step": 3100
    },
    {
      "epoch": 6.88,
      "learning_rate": 3.853046594982079e-06,
      "loss": 2.2686,
      "step": 3200
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.085155487060547,
      "eval_rouge1": 0.36126040343454235,
      "eval_rouge2": 0.21547432955733056,
      "eval_rougeL": 0.3220760761874921,
      "eval_rougeLsum": 0.3290219607741144,
      "eval_runtime": 123.1351,
      "eval_samples_per_second": 3.776,
      "eval_steps_per_second": 0.95,
      "step": 3255
    },
    {
      "epoch": 7.1,
      "learning_rate": 3.817204301075269e-06,
      "loss": 2.2865,
      "step": 3300
    },
    {
      "epoch": 7.31,
      "learning_rate": 3.7813620071684594e-06,
      "loss": 2.2324,
      "step": 3400
    },
    {
      "epoch": 7.53,
      "learning_rate": 3.7455197132616487e-06,
      "loss": 2.1958,
      "step": 3500
    },
    {
      "epoch": 7.74,
      "learning_rate": 3.7096774193548392e-06,
      "loss": 2.247,
      "step": 3600
    },
    {
      "epoch": 7.96,
      "learning_rate": 3.6738351254480293e-06,
      "loss": 2.1938,
      "step": 3700
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.067925214767456,
      "eval_rouge1": 0.3693846075750796,
      "eval_rouge2": 0.21744552490349583,
      "eval_rougeL": 0.33008227975421506,
      "eval_rougeLsum": 0.3366887788509312,
      "eval_runtime": 122.9004,
      "eval_samples_per_second": 3.784,
      "eval_steps_per_second": 0.952,
      "step": 3720
    },
    {
      "epoch": 8.17,
      "learning_rate": 3.637992831541219e-06,
      "loss": 2.2624,
      "step": 3800
    },
    {
      "epoch": 8.39,
      "learning_rate": 3.602150537634409e-06,
      "loss": 2.1922,
      "step": 3900
    },
    {
      "epoch": 8.6,
      "learning_rate": 3.5663082437275988e-06,
      "loss": 2.1876,
      "step": 4000
    },
    {
      "epoch": 8.82,
      "learning_rate": 3.530465949820789e-06,
      "loss": 2.2504,
      "step": 4100
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.0534462928771973,
      "eval_rouge1": 0.3699290195093533,
      "eval_rouge2": 0.21788826762887392,
      "eval_rougeL": 0.3292248508798441,
      "eval_rougeLsum": 0.3357683304940864,
      "eval_runtime": 120.1177,
      "eval_samples_per_second": 3.871,
      "eval_steps_per_second": 0.974,
      "step": 4185
    },
    {
      "epoch": 9.03,
      "learning_rate": 3.494623655913979e-06,
      "loss": 2.1819,
      "step": 4200
    },
    {
      "epoch": 9.25,
      "learning_rate": 3.4587813620071686e-06,
      "loss": 2.1755,
      "step": 4300
    },
    {
      "epoch": 9.46,
      "learning_rate": 3.4229390681003587e-06,
      "loss": 2.2398,
      "step": 4400
    },
    {
      "epoch": 9.68,
      "learning_rate": 3.3870967741935484e-06,
      "loss": 2.0979,
      "step": 4500
    },
    {
      "epoch": 9.89,
      "learning_rate": 3.3512544802867385e-06,
      "loss": 2.2245,
      "step": 4600
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.0405704975128174,
      "eval_rouge1": 0.36982395276855895,
      "eval_rouge2": 0.21943719038802345,
      "eval_rougeL": 0.32884583320308947,
      "eval_rougeLsum": 0.3352203622134837,
      "eval_runtime": 120.0171,
      "eval_samples_per_second": 3.874,
      "eval_steps_per_second": 0.975,
      "step": 4650
    },
    {
      "epoch": 10.11,
      "learning_rate": 3.3154121863799286e-06,
      "loss": 2.1732,
      "step": 4700
    },
    {
      "epoch": 10.32,
      "learning_rate": 3.2795698924731183e-06,
      "loss": 2.1806,
      "step": 4800
    },
    {
      "epoch": 10.54,
      "learning_rate": 3.2437275985663088e-06,
      "loss": 2.1288,
      "step": 4900
    },
    {
      "epoch": 10.75,
      "learning_rate": 3.207885304659498e-06,
      "loss": 2.1696,
      "step": 5000
    },
    {
      "epoch": 10.97,
      "learning_rate": 3.1720430107526885e-06,
      "loss": 2.2101,
      "step": 5100
    },
    {
      "epoch": 11.0,
      "eval_loss": 2.0279901027679443,
      "eval_rouge1": 0.3734606050199662,
      "eval_rouge2": 0.21830269894292892,
      "eval_rougeL": 0.33251263790168706,
      "eval_rougeLsum": 0.338738236025534,
      "eval_runtime": 123.6661,
      "eval_samples_per_second": 3.76,
      "eval_steps_per_second": 0.946,
      "step": 5115
    },
    {
      "epoch": 11.18,
      "learning_rate": 3.1362007168458786e-06,
      "loss": 2.184,
      "step": 5200
    },
    {
      "epoch": 11.4,
      "learning_rate": 3.1003584229390683e-06,
      "loss": 2.1577,
      "step": 5300
    },
    {
      "epoch": 11.61,
      "learning_rate": 3.0645161290322584e-06,
      "loss": 2.1454,
      "step": 5400
    },
    {
      "epoch": 11.83,
      "learning_rate": 3.0286738351254485e-06,
      "loss": 2.1668,
      "step": 5500
    },
    {
      "epoch": 12.0,
      "eval_loss": 2.019313335418701,
      "eval_rouge1": 0.3712265009866553,
      "eval_rouge2": 0.2205852840916728,
      "eval_rougeL": 0.33092303917646704,
      "eval_rougeLsum": 0.3368955402181135,
      "eval_runtime": 123.2988,
      "eval_samples_per_second": 3.771,
      "eval_steps_per_second": 0.949,
      "step": 5580
    },
    {
      "epoch": 12.04,
      "learning_rate": 2.992831541218638e-06,
      "loss": 2.1253,
      "step": 5600
    },
    {
      "epoch": 12.26,
      "learning_rate": 2.9569892473118283e-06,
      "loss": 2.1418,
      "step": 5700
    },
    {
      "epoch": 12.47,
      "learning_rate": 2.921146953405018e-06,
      "loss": 2.1566,
      "step": 5800
    },
    {
      "epoch": 12.69,
      "learning_rate": 2.885304659498208e-06,
      "loss": 2.0878,
      "step": 5900
    },
    {
      "epoch": 12.9,
      "learning_rate": 2.849462365591398e-06,
      "loss": 2.1043,
      "step": 6000
    },
    {
      "epoch": 13.0,
      "eval_loss": 2.0104010105133057,
      "eval_rouge1": 0.37304680542883845,
      "eval_rouge2": 0.21933710465212664,
      "eval_rougeL": 0.3330043221849929,
      "eval_rougeLsum": 0.3386272891983395,
      "eval_runtime": 122.5914,
      "eval_samples_per_second": 3.793,
      "eval_steps_per_second": 0.954,
      "step": 6045
    },
    {
      "epoch": 13.12,
      "learning_rate": 2.813620071684588e-06,
      "loss": 2.1112,
      "step": 6100
    },
    {
      "epoch": 13.33,
      "learning_rate": 2.7777777777777783e-06,
      "loss": 2.1108,
      "step": 6200
    },
    {
      "epoch": 13.55,
      "learning_rate": 2.7419354838709676e-06,
      "loss": 2.0588,
      "step": 6300
    },
    {
      "epoch": 13.76,
      "learning_rate": 2.706093189964158e-06,
      "loss": 2.1374,
      "step": 6400
    },
    {
      "epoch": 13.98,
      "learning_rate": 2.670250896057348e-06,
      "loss": 2.1105,
      "step": 6500
    },
    {
      "epoch": 14.0,
      "eval_loss": 2.0007288455963135,
      "eval_rouge1": 0.3726819527146452,
      "eval_rouge2": 0.21762553499708942,
      "eval_rougeL": 0.3318504683532579,
      "eval_rougeLsum": 0.33850204873356216,
      "eval_runtime": 121.8594,
      "eval_samples_per_second": 3.816,
      "eval_steps_per_second": 0.96,
      "step": 6510
    },
    {
      "epoch": 14.19,
      "learning_rate": 2.634408602150538e-06,
      "loss": 2.0344,
      "step": 6600
    },
    {
      "epoch": 14.41,
      "learning_rate": 2.598566308243728e-06,
      "loss": 2.132,
      "step": 6700
    },
    {
      "epoch": 14.62,
      "learning_rate": 2.5627240143369176e-06,
      "loss": 2.0991,
      "step": 6800
    },
    {
      "epoch": 14.84,
      "learning_rate": 2.5268817204301077e-06,
      "loss": 2.1107,
      "step": 6900
    },
    {
      "epoch": 15.0,
      "eval_loss": 1.9940224885940552,
      "eval_rouge1": 0.3706106479406549,
      "eval_rouge2": 0.21664139194802018,
      "eval_rougeL": 0.3308301392858899,
      "eval_rougeLsum": 0.33710889659653737,
      "eval_runtime": 122.4456,
      "eval_samples_per_second": 3.798,
      "eval_steps_per_second": 0.956,
      "step": 6975
    },
    {
      "epoch": 15.05,
      "learning_rate": 2.4910394265232974e-06,
      "loss": 2.0848,
      "step": 7000
    },
    {
      "epoch": 15.27,
      "learning_rate": 2.455197132616488e-06,
      "loss": 2.0577,
      "step": 7100
    },
    {
      "epoch": 15.48,
      "learning_rate": 2.4193548387096776e-06,
      "loss": 2.1239,
      "step": 7200
    },
    {
      "epoch": 15.7,
      "learning_rate": 2.3835125448028677e-06,
      "loss": 2.0806,
      "step": 7300
    },
    {
      "epoch": 15.91,
      "learning_rate": 2.3476702508960574e-06,
      "loss": 2.0414,
      "step": 7400
    },
    {
      "epoch": 16.0,
      "eval_loss": 1.9866129159927368,
      "eval_rouge1": 0.37225097720253997,
      "eval_rouge2": 0.21677008547624982,
      "eval_rougeL": 0.33223185563868907,
      "eval_rougeLsum": 0.3386777282958562,
      "eval_runtime": 121.6974,
      "eval_samples_per_second": 3.821,
      "eval_steps_per_second": 0.961,
      "step": 7440
    },
    {
      "epoch": 16.13,
      "learning_rate": 2.3118279569892475e-06,
      "loss": 2.1197,
      "step": 7500
    },
    {
      "epoch": 16.34,
      "learning_rate": 2.2759856630824376e-06,
      "loss": 2.0408,
      "step": 7600
    },
    {
      "epoch": 16.56,
      "learning_rate": 2.2401433691756277e-06,
      "loss": 2.1108,
      "step": 7700
    },
    {
      "epoch": 16.77,
      "learning_rate": 2.2043010752688173e-06,
      "loss": 2.0352,
      "step": 7800
    },
    {
      "epoch": 16.99,
      "learning_rate": 2.1684587813620074e-06,
      "loss": 2.0967,
      "step": 7900
    },
    {
      "epoch": 17.0,
      "eval_loss": 1.9800302982330322,
      "eval_rouge1": 0.3727733319379002,
      "eval_rouge2": 0.21755161592237982,
      "eval_rougeL": 0.3335382496389028,
      "eval_rougeLsum": 0.33953249788570733,
      "eval_runtime": 121.0282,
      "eval_samples_per_second": 3.842,
      "eval_steps_per_second": 0.967,
      "step": 7905
    },
    {
      "epoch": 17.2,
      "learning_rate": 2.132616487455197e-06,
      "loss": 1.9761,
      "step": 8000
    },
    {
      "epoch": 17.42,
      "learning_rate": 2.096774193548387e-06,
      "loss": 2.1014,
      "step": 8100
    },
    {
      "epoch": 17.63,
      "learning_rate": 2.0609318996415773e-06,
      "loss": 2.0746,
      "step": 8200
    },
    {
      "epoch": 17.85,
      "learning_rate": 2.025089605734767e-06,
      "loss": 2.0348,
      "step": 8300
    },
    {
      "epoch": 18.0,
      "eval_loss": 1.9747109413146973,
      "eval_rouge1": 0.37309307818896603,
      "eval_rouge2": 0.21910694351175308,
      "eval_rougeL": 0.3335975489248736,
      "eval_rougeLsum": 0.3397532162946465,
      "eval_runtime": 121.7383,
      "eval_samples_per_second": 3.82,
      "eval_steps_per_second": 0.961,
      "step": 8370
    },
    {
      "epoch": 18.06,
      "learning_rate": 1.989247311827957e-06,
      "loss": 2.0409,
      "step": 8400
    },
    {
      "epoch": 18.28,
      "learning_rate": 1.953405017921147e-06,
      "loss": 2.0045,
      "step": 8500
    },
    {
      "epoch": 18.49,
      "learning_rate": 1.9175627240143373e-06,
      "loss": 2.0677,
      "step": 8600
    },
    {
      "epoch": 18.71,
      "learning_rate": 1.881720430107527e-06,
      "loss": 2.0458,
      "step": 8700
    },
    {
      "epoch": 18.92,
      "learning_rate": 1.845878136200717e-06,
      "loss": 2.0386,
      "step": 8800
    },
    {
      "epoch": 19.0,
      "eval_loss": 1.9697682857513428,
      "eval_rouge1": 0.37437363802915335,
      "eval_rouge2": 0.22043247557418233,
      "eval_rougeL": 0.3341597802534484,
      "eval_rougeLsum": 0.34031460529982227,
      "eval_runtime": 126.0543,
      "eval_samples_per_second": 3.689,
      "eval_steps_per_second": 0.928,
      "step": 8835
    },
    {
      "epoch": 19.14,
      "learning_rate": 1.810035842293907e-06,
      "loss": 2.0449,
      "step": 8900
    },
    {
      "epoch": 19.35,
      "learning_rate": 1.774193548387097e-06,
      "loss": 2.0316,
      "step": 9000
    },
    {
      "epoch": 19.57,
      "learning_rate": 1.7383512544802869e-06,
      "loss": 2.0353,
      "step": 9100
    },
    {
      "epoch": 19.78,
      "learning_rate": 1.7025089605734768e-06,
      "loss": 2.0114,
      "step": 9200
    },
    {
      "epoch": 20.0,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 2.0455,
      "step": 9300
    },
    {
      "epoch": 20.0,
      "eval_loss": 1.9655319452285767,
      "eval_rouge1": 0.3742240497073518,
      "eval_rouge2": 0.22064343083294777,
      "eval_rougeL": 0.33460487470233025,
      "eval_rougeLsum": 0.340864806277791,
      "eval_runtime": 125.1186,
      "eval_samples_per_second": 3.716,
      "eval_steps_per_second": 0.935,
      "step": 9300
    },
    {
      "epoch": 20.22,
      "learning_rate": 1.630824372759857e-06,
      "loss": 2.0064,
      "step": 9400
    },
    {
      "epoch": 20.43,
      "learning_rate": 1.5949820788530469e-06,
      "loss": 2.0474,
      "step": 9500
    },
    {
      "epoch": 20.65,
      "learning_rate": 1.5591397849462367e-06,
      "loss": 2.0682,
      "step": 9600
    },
    {
      "epoch": 20.86,
      "learning_rate": 1.5232974910394266e-06,
      "loss": 1.9697,
      "step": 9700
    },
    {
      "epoch": 21.0,
      "eval_loss": 1.9609689712524414,
      "eval_rouge1": 0.3746966258892264,
      "eval_rouge2": 0.21941379395076405,
      "eval_rougeL": 0.3355003953460309,
      "eval_rougeLsum": 0.34172515637886314,
      "eval_runtime": 128.3527,
      "eval_samples_per_second": 3.623,
      "eval_steps_per_second": 0.912,
      "step": 9765
    },
    {
      "epoch": 21.08,
      "learning_rate": 1.4874551971326165e-06,
      "loss": 2.0284,
      "step": 9800
    },
    {
      "epoch": 21.29,
      "learning_rate": 1.4516129032258066e-06,
      "loss": 2.073,
      "step": 9900
    },
    {
      "epoch": 21.51,
      "learning_rate": 1.4157706093189965e-06,
      "loss": 2.0222,
      "step": 10000
    },
    {
      "epoch": 21.72,
      "learning_rate": 1.3799283154121864e-06,
      "loss": 2.0401,
      "step": 10100
    },
    {
      "epoch": 21.94,
      "learning_rate": 1.3440860215053765e-06,
      "loss": 2.0002,
      "step": 10200
    },
    {
      "epoch": 22.0,
      "eval_loss": 1.957392692565918,
      "eval_rouge1": 0.37462712554849187,
      "eval_rouge2": 0.21992028420969706,
      "eval_rougeL": 0.33560886975550064,
      "eval_rougeLsum": 0.34162973068900326,
      "eval_runtime": 122.27,
      "eval_samples_per_second": 3.803,
      "eval_steps_per_second": 0.957,
      "step": 10230
    },
    {
      "epoch": 22.15,
      "learning_rate": 1.3082437275985666e-06,
      "loss": 1.9805,
      "step": 10300
    },
    {
      "epoch": 22.37,
      "learning_rate": 1.2724014336917565e-06,
      "loss": 2.0016,
      "step": 10400
    },
    {
      "epoch": 22.58,
      "learning_rate": 1.2365591397849463e-06,
      "loss": 2.0184,
      "step": 10500
    },
    {
      "epoch": 22.8,
      "learning_rate": 1.2007168458781362e-06,
      "loss": 2.0238,
      "step": 10600
    },
    {
      "epoch": 23.0,
      "eval_loss": 1.9541218280792236,
      "eval_rouge1": 0.37477500267736275,
      "eval_rouge2": 0.21863545453296632,
      "eval_rougeL": 0.3354338958099685,
      "eval_rougeLsum": 0.3414596818505722,
      "eval_runtime": 120.9729,
      "eval_samples_per_second": 3.844,
      "eval_steps_per_second": 0.967,
      "step": 10695
    },
    {
      "epoch": 23.01,
      "learning_rate": 1.1648745519713263e-06,
      "loss": 2.0737,
      "step": 10700
    },
    {
      "epoch": 23.23,
      "learning_rate": 1.1290322580645162e-06,
      "loss": 2.013,
      "step": 10800
    },
    {
      "epoch": 23.44,
      "learning_rate": 1.0931899641577063e-06,
      "loss": 1.9844,
      "step": 10900
    },
    {
      "epoch": 23.66,
      "learning_rate": 1.0573476702508962e-06,
      "loss": 2.014,
      "step": 11000
    },
    {
      "epoch": 23.87,
      "learning_rate": 1.021505376344086e-06,
      "loss": 2.0421,
      "step": 11100
    },
    {
      "epoch": 24.0,
      "eval_loss": 1.9520260095596313,
      "eval_rouge1": 0.3771021997183883,
      "eval_rouge2": 0.21990144851690735,
      "eval_rougeL": 0.3374010954787996,
      "eval_rougeLsum": 0.3439051210524349,
      "eval_runtime": 119.9413,
      "eval_samples_per_second": 3.877,
      "eval_steps_per_second": 0.975,
      "step": 11160
    },
    {
      "epoch": 24.09,
      "learning_rate": 9.856630824372762e-07,
      "loss": 1.9993,
      "step": 11200
    },
    {
      "epoch": 24.3,
      "learning_rate": 9.498207885304659e-07,
      "loss": 2.0148,
      "step": 11300
    },
    {
      "epoch": 24.52,
      "learning_rate": 9.13978494623656e-07,
      "loss": 2.0094,
      "step": 11400
    },
    {
      "epoch": 24.73,
      "learning_rate": 8.781362007168459e-07,
      "loss": 2.0395,
      "step": 11500
    },
    {
      "epoch": 24.95,
      "learning_rate": 8.422939068100359e-07,
      "loss": 2.0001,
      "step": 11600
    },
    {
      "epoch": 25.0,
      "eval_loss": 1.9496192932128906,
      "eval_rouge1": 0.3773377632907566,
      "eval_rouge2": 0.2204940276436899,
      "eval_rougeL": 0.33747034227999706,
      "eval_rougeLsum": 0.34393368298115334,
      "eval_runtime": 120.2791,
      "eval_samples_per_second": 3.866,
      "eval_steps_per_second": 0.973,
      "step": 11625
    },
    {
      "epoch": 25.16,
      "learning_rate": 8.064516129032258e-07,
      "loss": 2.0302,
      "step": 11700
    },
    {
      "epoch": 25.38,
      "learning_rate": 7.706093189964159e-07,
      "loss": 2.045,
      "step": 11800
    },
    {
      "epoch": 25.59,
      "learning_rate": 7.347670250896058e-07,
      "loss": 1.9614,
      "step": 11900
    },
    {
      "epoch": 25.81,
      "learning_rate": 6.989247311827957e-07,
      "loss": 1.93,
      "step": 12000
    },
    {
      "epoch": 26.0,
      "eval_loss": 1.9484126567840576,
      "eval_rouge1": 0.37597520520383987,
      "eval_rouge2": 0.21986201392787488,
      "eval_rougeL": 0.3357415231000408,
      "eval_rougeLsum": 0.34205147158317384,
      "eval_runtime": 121.7783,
      "eval_samples_per_second": 3.818,
      "eval_steps_per_second": 0.961,
      "step": 12090
    },
    {
      "epoch": 26.02,
      "learning_rate": 6.630824372759858e-07,
      "loss": 2.0524,
      "step": 12100
    },
    {
      "epoch": 26.24,
      "learning_rate": 6.272401433691756e-07,
      "loss": 1.9644,
      "step": 12200
    },
    {
      "epoch": 26.45,
      "learning_rate": 5.913978494623656e-07,
      "loss": 2.0117,
      "step": 12300
    },
    {
      "epoch": 26.67,
      "learning_rate": 5.555555555555555e-07,
      "loss": 1.9847,
      "step": 12400
    },
    {
      "epoch": 26.88,
      "learning_rate": 5.197132616487455e-07,
      "loss": 2.0453,
      "step": 12500
    },
    {
      "epoch": 27.0,
      "eval_loss": 1.9469475746154785,
      "eval_rouge1": 0.3740165446355651,
      "eval_rouge2": 0.21772737050061053,
      "eval_rougeL": 0.333510117519976,
      "eval_rougeLsum": 0.34028741836853005,
      "eval_runtime": 119.9633,
      "eval_samples_per_second": 3.876,
      "eval_steps_per_second": 0.975,
      "step": 12555
    },
    {
      "epoch": 27.1,
      "learning_rate": 4.838709677419355e-07,
      "loss": 2.0035,
      "step": 12600
    },
    {
      "epoch": 27.31,
      "learning_rate": 4.480286738351255e-07,
      "loss": 1.9638,
      "step": 12700
    },
    {
      "epoch": 27.53,
      "learning_rate": 4.1218637992831543e-07,
      "loss": 1.9471,
      "step": 12800
    },
    {
      "epoch": 27.74,
      "learning_rate": 3.763440860215054e-07,
      "loss": 2.0266,
      "step": 12900
    },
    {
      "epoch": 27.96,
      "learning_rate": 3.405017921146954e-07,
      "loss": 1.9894,
      "step": 13000
    },
    {
      "epoch": 28.0,
      "eval_loss": 1.9458811283111572,
      "eval_rouge1": 0.3742795595221444,
      "eval_rouge2": 0.21805194369064132,
      "eval_rougeL": 0.3337992892424988,
      "eval_rougeLsum": 0.34075989492689374,
      "eval_runtime": 125.2596,
      "eval_samples_per_second": 3.712,
      "eval_steps_per_second": 0.934,
      "step": 13020
    },
    {
      "epoch": 28.17,
      "learning_rate": 3.0465949820788535e-07,
      "loss": 1.9882,
      "step": 13100
    },
    {
      "epoch": 28.39,
      "learning_rate": 2.688172043010753e-07,
      "loss": 2.0092,
      "step": 13200
    },
    {
      "epoch": 28.6,
      "learning_rate": 2.3297491039426527e-07,
      "loss": 2.0301,
      "step": 13300
    },
    {
      "epoch": 28.82,
      "learning_rate": 1.971326164874552e-07,
      "loss": 2.0282,
      "step": 13400
    },
    {
      "epoch": 29.0,
      "eval_loss": 1.9454594850540161,
      "eval_rouge1": 0.3743638040177606,
      "eval_rouge2": 0.21796734115768185,
      "eval_rougeL": 0.33380358105146785,
      "eval_rougeLsum": 0.3407996691800308,
      "eval_runtime": 123.622,
      "eval_samples_per_second": 3.761,
      "eval_steps_per_second": 0.946,
      "step": 13485
    },
    {
      "epoch": 29.03,
      "learning_rate": 1.6129032258064518e-07,
      "loss": 1.9566,
      "step": 13500
    },
    {
      "epoch": 29.25,
      "learning_rate": 1.2544802867383514e-07,
      "loss": 1.9519,
      "step": 13600
    },
    {
      "epoch": 29.46,
      "learning_rate": 8.960573476702509e-08,
      "loss": 1.9502,
      "step": 13700
    },
    {
      "epoch": 29.68,
      "learning_rate": 5.376344086021506e-08,
      "loss": 2.0183,
      "step": 13800
    }
  ],
  "max_steps": 13950,
  "num_train_epochs": 30,
  "total_flos": 2196944996493312.0,
  "trial_name": null,
  "trial_params": null
}