{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6403927742348641,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 5.555555555555555e-05,
      "loss": 20.8315,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001111111111111111,
      "loss": 16.4875,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016666666666666666,
      "loss": 10.6503,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002222222222222222,
      "loss": 6.6236,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002777777777777778,
      "loss": 5.2548,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003333333333333333,
      "loss": 4.6801,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003888888888888889,
      "loss": 4.3374,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004444444444444444,
      "loss": 3.9614,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0005,
      "loss": 3.9704,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004977797513321492,
      "loss": 3.8112,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004955595026642984,
      "loss": 3.6272,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004933392539964477,
      "loss": 3.5572,
      "step": 120
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004911190053285969,
      "loss": 3.3966,
      "step": 130
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000488898756660746,
      "loss": 3.4632,
      "step": 140
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004866785079928952,
      "loss": 3.4591,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004844582593250444,
      "loss": 3.2218,
      "step": 160
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004822380106571936,
      "loss": 3.4101,
      "step": 170
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00048001776198934283,
      "loss": 3.2787,
      "step": 180
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000477797513321492,
      "loss": 3.1043,
      "step": 190
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004755772646536412,
      "loss": 3.2435,
      "step": 200
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00047335701598579037,
      "loss": 3.2286,
      "step": 210
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00047113676731793964,
      "loss": 3.1484,
      "step": 220
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00046891651865008885,
      "loss": 3.1817,
      "step": 230
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000466696269982238,
      "loss": 3.1608,
      "step": 240
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00046447602131438723,
      "loss": 3.1457,
      "step": 250
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004622557726465364,
      "loss": 3.1212,
      "step": 260
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00046003552397868566,
      "loss": 2.9937,
      "step": 270
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004578152753108348,
      "loss": 3.2031,
      "step": 280
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00045559502664298403,
      "loss": 3.0713,
      "step": 290
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004533747779751332,
      "loss": 3.0352,
      "step": 300
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004511545293072824,
      "loss": 3.0872,
      "step": 310
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004489342806394316,
      "loss": 3.0049,
      "step": 320
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00044671403197158084,
      "loss": 3.0659,
      "step": 330
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00044449378330373,
      "loss": 3.0852,
      "step": 340
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0004422735346358792,
      "loss": 2.9506,
      "step": 350
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00044005328596802843,
      "loss": 3.027,
      "step": 360
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00043783303730017764,
      "loss": 2.8812,
      "step": 370
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00043561278863232686,
      "loss": 2.9738,
      "step": 380
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000433392539964476,
      "loss": 3.0504,
      "step": 390
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00043117229129662523,
      "loss": 3.0195,
      "step": 400
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0004289520426287744,
      "loss": 2.968,
      "step": 410
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00042673179396092366,
      "loss": 3.0864,
      "step": 420
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0004245115452930728,
      "loss": 2.8735,
      "step": 430
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00042229129662522204,
      "loss": 3.0391,
      "step": 440
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0004200710479573712,
      "loss": 2.8288,
      "step": 450
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0004178507992895204,
      "loss": 3.0182,
      "step": 460
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0004156305506216697,
      "loss": 3.0606,
      "step": 470
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00041341030195381884,
      "loss": 2.9467,
      "step": 480
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00041119005328596806,
      "loss": 2.7842,
      "step": 490
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0004089698046181172,
      "loss": 2.8472,
      "step": 500
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00040674955595026643,
      "loss": 2.7883,
      "step": 510
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00040452930728241565,
      "loss": 2.8592,
      "step": 520
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00040230905861456486,
      "loss": 2.9186,
      "step": 530
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000400088809946714,
      "loss": 2.911,
      "step": 540
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00039786856127886324,
      "loss": 2.8355,
      "step": 550
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003956483126110124,
      "loss": 2.9385,
      "step": 560
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00039342806394316167,
      "loss": 2.8465,
      "step": 570
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003912078152753108,
      "loss": 2.8408,
      "step": 580
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00038898756660746004,
      "loss": 2.767,
      "step": 590
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00038676731793960926,
      "loss": 2.9691,
      "step": 600
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003845470692717584,
      "loss": 2.7348,
      "step": 610
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003823268206039077,
      "loss": 2.7477,
      "step": 620
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00038010657193605685,
      "loss": 2.8142,
      "step": 630
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00037788632326820606,
      "loss": 2.7522,
      "step": 640
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003756660746003552,
      "loss": 2.9403,
      "step": 650
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00037344582593250444,
      "loss": 2.8956,
      "step": 660
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00037122557726465365,
      "loss": 2.7331,
      "step": 670
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00036900532859680287,
      "loss": 2.8265,
      "step": 680
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000366785079928952,
      "loss": 2.8919,
      "step": 690
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00036456483126110124,
      "loss": 2.8362,
      "step": 700
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003623445825932504,
      "loss": 2.7282,
      "step": 710
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00036012433392539967,
      "loss": 2.7628,
      "step": 720
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003579040852575489,
      "loss": 2.8508,
      "step": 730
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00035568383658969805,
      "loss": 2.8603,
      "step": 740
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00035346358792184726,
      "loss": 2.6765,
      "step": 750
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003512433392539964,
      "loss": 2.8767,
      "step": 760
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003490230905861457,
      "loss": 2.8446,
      "step": 770
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00034680284191829485,
      "loss": 2.8524,
      "step": 780
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00034458259325044407,
      "loss": 2.778,
      "step": 790
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003423623445825932,
      "loss": 2.7359,
      "step": 800
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00034014209591474244,
      "loss": 2.7803,
      "step": 810
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00033792184724689166,
      "loss": 2.7631,
      "step": 820
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00033570159857904087,
      "loss": 2.7818,
      "step": 830
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00033348134991119003,
      "loss": 2.6591,
      "step": 840
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00033126110124333925,
      "loss": 2.6843,
      "step": 850
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00032904085257548846,
      "loss": 2.7299,
      "step": 860
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003268206039076377,
      "loss": 2.6928,
      "step": 870
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003246003552397869,
      "loss": 2.8512,
      "step": 880
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00032238010657193605,
      "loss": 2.7944,
      "step": 890
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00032015985790408526,
      "loss": 2.7365,
      "step": 900
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003179396092362344,
      "loss": 2.6992,
      "step": 910
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003157193605683837,
      "loss": 2.743,
      "step": 920
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00031349911190053285,
      "loss": 2.8022,
      "step": 930
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00031127886323268207,
      "loss": 2.6603,
      "step": 940
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00030905861456483123,
      "loss": 2.6277,
      "step": 950
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00030683836589698044,
      "loss": 2.7652,
      "step": 960
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003046181172291297,
      "loss": 2.7063,
      "step": 970
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003023978685612789,
      "loss": 2.6602,
      "step": 980
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003001776198934281,
      "loss": 2.7592,
      "step": 990
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00029795737122557725,
      "loss": 2.6628,
      "step": 1000
    },
    {
      "epoch": 0.43,
      "eval_loss": 0.51519775390625,
      "eval_rouge1": 0.8067071482496617,
      "eval_rouge2": 0.7472387953801375,
      "eval_rougeL": 0.7071393649432568,
      "eval_rougeLsum": 0.8209607917685595,
      "eval_runtime": 1807.8081,
      "eval_samples_per_second": 0.553,
      "eval_steps_per_second": 0.553,
      "step": 1000
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00029573712255772646,
      "loss": 2.6164,
      "step": 1010
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002935168738898757,
      "loss": 2.6947,
      "step": 1020
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002912966252220249,
      "loss": 2.4547,
      "step": 1030
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00028907637655417405,
      "loss": 2.7347,
      "step": 1040
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00028685612788632327,
      "loss": 2.6491,
      "step": 1050
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00028463587921847243,
      "loss": 2.6778,
      "step": 1060
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002824156305506217,
      "loss": 2.7157,
      "step": 1070
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00028019538188277086,
      "loss": 2.6445,
      "step": 1080
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002779751332149201,
      "loss": 2.7732,
      "step": 1090
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002757548845470693,
      "loss": 2.6777,
      "step": 1100
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00027353463587921845,
      "loss": 2.6231,
      "step": 1110
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002713143872113677,
      "loss": 2.6003,
      "step": 1120
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002690941385435169,
      "loss": 2.7226,
      "step": 1130
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002668738898756661,
      "loss": 2.8623,
      "step": 1140
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00026465364120781525,
      "loss": 2.7391,
      "step": 1150
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00026243339253996447,
      "loss": 2.6836,
      "step": 1160
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002602131438721137,
      "loss": 2.6357,
      "step": 1170
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002579928952042629,
      "loss": 2.5891,
      "step": 1180
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00025577264653641206,
      "loss": 2.7383,
      "step": 1190
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00025355239786856127,
      "loss": 2.738,
      "step": 1200
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00025133214920071043,
      "loss": 2.62,
      "step": 1210
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002491119005328597,
      "loss": 2.5796,
      "step": 1220
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002468916518650089,
      "loss": 2.5744,
      "step": 1230
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002446714031971581,
      "loss": 2.5047,
      "step": 1240
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002424511545293073,
      "loss": 2.5233,
      "step": 1250
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00024023090586145648,
      "loss": 2.5248,
      "step": 1260
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00023801065719360567,
      "loss": 2.6073,
      "step": 1270
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002357904085257549,
      "loss": 2.596,
      "step": 1280
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002335701598579041,
      "loss": 2.6899,
      "step": 1290
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002313499111900533,
      "loss": 2.6293,
      "step": 1300
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002291296625222025,
      "loss": 2.639,
      "step": 1310
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002269094138543517,
      "loss": 2.7105,
      "step": 1320
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002246891651865009,
      "loss": 2.723,
      "step": 1330
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002224689165186501,
      "loss": 2.5697,
      "step": 1340
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002202486678507993,
      "loss": 2.715,
      "step": 1350
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002180284191829485,
      "loss": 2.6387,
      "step": 1360
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00021580817051509768,
      "loss": 2.5276,
      "step": 1370
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002135879218472469,
      "loss": 2.627,
      "step": 1380
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00021136767317939608,
      "loss": 2.5249,
      "step": 1390
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002091474245115453,
      "loss": 2.629,
      "step": 1400
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002069271758436945,
      "loss": 2.703,
      "step": 1410
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002047069271758437,
      "loss": 2.544,
      "step": 1420
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002024866785079929,
      "loss": 2.5992,
      "step": 1430
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002002664298401421,
      "loss": 2.6988,
      "step": 1440
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019804618117229132,
      "loss": 2.6195,
      "step": 1450
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001958259325044405,
      "loss": 2.6247,
      "step": 1460
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001936056838365897,
      "loss": 2.5853,
      "step": 1470
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001913854351687389,
      "loss": 2.6298,
      "step": 1480
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001891651865008881,
      "loss": 2.6378,
      "step": 1490
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001869449378330373,
      "loss": 2.5682,
      "step": 1500
    }
  ],
  "max_steps": 2342,
  "num_train_epochs": 1,
  "total_flos": 3.54937584731136e+16,
  "trial_name": null,
  "trial_params": null
}