{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.114575496670289,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011145476329794645,
      "learning_rate": 9.999000000000001e-05,
      "loss": 8.06905746459961,
      "step": 1
    },
    {
      "epoch": 0.011145476329794644,
      "learning_rate": 9.900000000000001e-05,
      "loss": 1.7745859165384312,
      "step": 100
    },
    {
      "epoch": 0.02229095265958929,
      "learning_rate": 9.8e-05,
      "loss": 1.4695932006835937,
      "step": 200
    },
    {
      "epoch": 0.03343642898938393,
      "learning_rate": 9.7e-05,
      "loss": 1.471973876953125,
      "step": 300
    },
    {
      "epoch": 0.04458190531917858,
      "learning_rate": 9.6e-05,
      "loss": 1.4246876525878907,
      "step": 400
    },
    {
      "epoch": 0.05572738164897322,
      "learning_rate": 9.5e-05,
      "loss": 1.4235630798339844,
      "step": 500
    },
    {
      "epoch": 0.06687285797876787,
      "learning_rate": 9.4e-05,
      "loss": 1.4458001708984376,
      "step": 600
    },
    {
      "epoch": 0.07801833430856252,
      "learning_rate": 9.300000000000001e-05,
      "loss": 1.4168995666503905,
      "step": 700
    },
    {
      "epoch": 0.08916381063835715,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.432281494140625,
      "step": 800
    },
    {
      "epoch": 0.1003092869681518,
      "learning_rate": 9.1e-05,
      "loss": 1.3954049682617187,
      "step": 900
    },
    {
      "epoch": 0.11145476329794644,
      "learning_rate": 9e-05,
      "loss": 1.41295654296875,
      "step": 1000
    },
    {
      "epoch": 0.1226002396277411,
      "learning_rate": 8.900000000000001e-05,
      "loss": 1.4206352233886719,
      "step": 1100
    },
    {
      "epoch": 0.13374571595753573,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.4066107177734375,
      "step": 1200
    },
    {
      "epoch": 0.14489119228733038,
      "learning_rate": 8.7e-05,
      "loss": 1.3928131103515624,
      "step": 1300
    },
    {
      "epoch": 0.15603666861712503,
      "learning_rate": 8.6e-05,
      "loss": 1.4154879760742187,
      "step": 1400
    },
    {
      "epoch": 0.16718214494691966,
      "learning_rate": 8.5e-05,
      "loss": 1.4014813232421874,
      "step": 1500
    },
    {
      "epoch": 0.1783276212767143,
      "learning_rate": 8.4e-05,
      "loss": 1.3965155029296874,
      "step": 1600
    },
    {
      "epoch": 0.18947309760650896,
      "learning_rate": 8.3e-05,
      "loss": 1.3976228332519531,
      "step": 1700
    },
    {
      "epoch": 0.2006185739363036,
      "learning_rate": 8.2e-05,
      "loss": 1.3655722045898437,
      "step": 1800
    },
    {
      "epoch": 0.21176405026609824,
      "learning_rate": 8.1e-05,
      "loss": 1.3941130065917968,
      "step": 1900
    },
    {
      "epoch": 0.2229095265958929,
      "learning_rate": 8e-05,
      "loss": 1.389833984375,
      "step": 2000
    },
    {
      "epoch": 0.23405500292568754,
      "learning_rate": 7.900000000000001e-05,
      "loss": 1.3948770141601563,
      "step": 2100
    },
    {
      "epoch": 0.2452004792554822,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.3855517578125,
      "step": 2200
    },
    {
      "epoch": 0.25634595558527684,
      "learning_rate": 7.7e-05,
      "loss": 1.4055433654785157,
      "step": 2300
    },
    {
      "epoch": 0.26749143191507146,
      "learning_rate": 7.6e-05,
      "loss": 1.3657418823242187,
      "step": 2400
    },
    {
      "epoch": 0.2786369082448661,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3927548217773438,
      "step": 2500
    },
    {
      "epoch": 0.2786369082448661,
      "eval_gen_len": 50.3,
      "eval_loss": 1.3837015628814697,
      "eval_rouge1": 35.4891,
      "eval_rouge2": 15.6119,
      "eval_rougeL": 26.4862,
      "eval_rougeLsum": 32.3041,
      "eval_runtime": 163.7005,
      "eval_samples_per_second": 3.054,
      "step": 2500
    },
    {
      "epoch": 0.28978238457466077,
      "learning_rate": 7.4e-05,
      "loss": 1.3879615783691406,
      "step": 2600
    },
    {
      "epoch": 0.3009278609044554,
      "learning_rate": 7.3e-05,
      "loss": 1.3767970275878907,
      "step": 2700
    },
    {
      "epoch": 0.31207333723425007,
      "learning_rate": 7.2e-05,
      "loss": 1.3870814514160157,
      "step": 2800
    },
    {
      "epoch": 0.3232188135640447,
      "learning_rate": 7.1e-05,
      "loss": 1.3717910766601562,
      "step": 2900
    },
    {
      "epoch": 0.3343642898938393,
      "learning_rate": 7e-05,
      "loss": 1.3754934692382812,
      "step": 3000
    },
    {
      "epoch": 0.345509766223634,
      "learning_rate": 6.9e-05,
      "loss": 1.3606668090820313,
      "step": 3100
    },
    {
      "epoch": 0.3566552425534286,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.359674530029297,
      "step": 3200
    },
    {
      "epoch": 0.3678007188832233,
      "learning_rate": 6.7e-05,
      "loss": 1.37053955078125,
      "step": 3300
    },
    {
      "epoch": 0.3789461952130179,
      "learning_rate": 6.6e-05,
      "loss": 1.3728164672851562,
      "step": 3400
    },
    {
      "epoch": 0.39009167154281255,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.3717462158203124,
      "step": 3500
    },
    {
      "epoch": 0.4012371478726072,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.3698835754394532,
      "step": 3600
    },
    {
      "epoch": 0.41238262420240185,
      "learning_rate": 6.3e-05,
      "loss": 1.3624909973144532,
      "step": 3700
    },
    {
      "epoch": 0.42352810053219647,
      "learning_rate": 6.2e-05,
      "loss": 1.365331268310547,
      "step": 3800
    },
    {
      "epoch": 0.43467357686199115,
      "learning_rate": 6.1e-05,
      "loss": 1.3554270935058594,
      "step": 3900
    },
    {
      "epoch": 0.4458190531917858,
      "learning_rate": 6e-05,
      "loss": 1.3769105529785157,
      "step": 4000
    },
    {
      "epoch": 0.45696452952158045,
      "learning_rate": 5.9e-05,
      "loss": 1.3486868286132812,
      "step": 4100
    },
    {
      "epoch": 0.4681100058513751,
      "learning_rate": 5.8e-05,
      "loss": 1.3736349487304687,
      "step": 4200
    },
    {
      "epoch": 0.4792554821811697,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 1.3558815002441407,
      "step": 4300
    },
    {
      "epoch": 0.4904009585109644,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.3559271240234374,
      "step": 4400
    },
    {
      "epoch": 0.501546434840759,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.349674530029297,
      "step": 4500
    },
    {
      "epoch": 0.5126919111705537,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.3654806518554687,
      "step": 4600
    },
    {
      "epoch": 0.5238373875003483,
      "learning_rate": 5.300000000000001e-05,
      "loss": 1.359230499267578,
      "step": 4700
    },
    {
      "epoch": 0.5349828638301429,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.359907684326172,
      "step": 4800
    },
    {
      "epoch": 0.5461283401599376,
      "learning_rate": 5.1000000000000006e-05,
      "loss": 1.3600314331054688,
      "step": 4900
    },
    {
      "epoch": 0.5572738164897322,
      "learning_rate": 5e-05,
      "loss": 1.3618020629882812,
      "step": 5000
    },
    {
      "epoch": 0.5572738164897322,
      "eval_gen_len": 49.3,
      "eval_loss": 1.3626569509506226,
      "eval_rouge1": 35.3235,
      "eval_rouge2": 15.308,
      "eval_rougeL": 26.6971,
      "eval_rougeLsum": 32.2475,
      "eval_runtime": 163.5583,
      "eval_samples_per_second": 3.057,
      "step": 5000
    },
    {
      "epoch": 0.5684192928195269,
      "learning_rate": 4.9e-05,
      "loss": 1.3476010131835938,
      "step": 5100
    },
    {
      "epoch": 0.5795647691493215,
      "learning_rate": 4.8e-05,
      "loss": 1.3705815124511718,
      "step": 5200
    },
    {
      "epoch": 0.5907102454791162,
      "learning_rate": 4.7e-05,
      "loss": 1.3650910949707031,
      "step": 5300
    },
    {
      "epoch": 0.6018557218089108,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.3458297729492188,
      "step": 5400
    },
    {
      "epoch": 0.6130011981387055,
      "learning_rate": 4.5e-05,
      "loss": 1.3574575805664062,
      "step": 5500
    },
    {
      "epoch": 0.6241466744685001,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.3446278381347656,
      "step": 5600
    },
    {
      "epoch": 0.6352921507982947,
      "learning_rate": 4.3e-05,
      "loss": 1.3720254516601562,
      "step": 5700
    },
    {
      "epoch": 0.6464376271280894,
      "learning_rate": 4.2e-05,
      "loss": 1.3550611877441405,
      "step": 5800
    },
    {
      "epoch": 0.6575831034578841,
      "learning_rate": 4.1e-05,
      "loss": 1.3649459838867188,
      "step": 5900
    },
    {
      "epoch": 0.6687285797876786,
      "learning_rate": 4e-05,
      "loss": 1.3249327087402343,
      "step": 6000
    },
    {
      "epoch": 0.6798740561174733,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 1.3522917175292968,
      "step": 6100
    },
    {
      "epoch": 0.691019532447268,
      "learning_rate": 3.8e-05,
      "loss": 1.3376327514648438,
      "step": 6200
    },
    {
      "epoch": 0.7021650087770626,
      "learning_rate": 3.7e-05,
      "loss": 1.3476719665527344,
      "step": 6300
    },
    {
      "epoch": 0.7133104851068572,
      "learning_rate": 3.6e-05,
      "loss": 1.3413494873046874,
      "step": 6400
    },
    {
      "epoch": 0.7244559614366519,
      "learning_rate": 3.5e-05,
      "loss": 1.3463385009765625,
      "step": 6500
    },
    {
      "epoch": 0.7356014377664466,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.346422882080078,
      "step": 6600
    },
    {
      "epoch": 0.7467469140962412,
      "learning_rate": 3.3e-05,
      "loss": 1.3565861511230468,
      "step": 6700
    },
    {
      "epoch": 0.7578923904260358,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.3385652160644532,
      "step": 6800
    },
    {
      "epoch": 0.7690378667558305,
      "learning_rate": 3.1e-05,
      "loss": 1.3510641479492187,
      "step": 6900
    },
    {
      "epoch": 0.7801833430856251,
      "learning_rate": 3e-05,
      "loss": 1.3658317565917968,
      "step": 7000
    },
    {
      "epoch": 0.7913288194154198,
      "learning_rate": 2.9e-05,
      "loss": 1.3442698669433595,
      "step": 7100
    },
    {
      "epoch": 0.8024742957452144,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.3289457702636718,
      "step": 7200
    },
    {
      "epoch": 0.813619772075009,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 1.3627702331542968,
      "step": 7300
    },
    {
      "epoch": 0.8247652484048037,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.3569662475585937,
      "step": 7400
    },
    {
      "epoch": 0.8359107247345984,
      "learning_rate": 2.5e-05,
      "loss": 1.3445625305175781,
      "step": 7500
    },
    {
      "epoch": 0.8359107247345984,
      "eval_gen_len": 49.5,
      "eval_loss": 1.3491926193237305,
      "eval_rouge1": 34.7061,
      "eval_rouge2": 15.2333,
      "eval_rougeL": 26.1848,
      "eval_rougeLsum": 31.7067,
      "eval_runtime": 162.9659,
      "eval_samples_per_second": 3.068,
      "step": 7500
    },
    {
      "epoch": 0.8470562010643929,
      "learning_rate": 2.4e-05,
      "loss": 1.3476835632324218,
      "step": 7600
    },
    {
      "epoch": 0.8582016773941876,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 1.329300079345703,
      "step": 7700
    },
    {
      "epoch": 0.8693471537239823,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.3521742248535156,
      "step": 7800
    },
    {
      "epoch": 0.8804926300537769,
      "learning_rate": 2.1e-05,
      "loss": 1.3405534362792968,
      "step": 7900
    },
    {
      "epoch": 0.8916381063835715,
      "learning_rate": 2e-05,
      "loss": 1.3501358032226562,
      "step": 8000
    },
    {
      "epoch": 0.9027835827133662,
      "learning_rate": 1.9e-05,
      "loss": 1.3406822204589843,
      "step": 8100
    },
    {
      "epoch": 0.9139290590431609,
      "learning_rate": 1.8e-05,
      "loss": 1.3406187438964843,
      "step": 8200
    },
    {
      "epoch": 0.9250745353729555,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 1.3410650634765624,
      "step": 8300
    },
    {
      "epoch": 0.9362200117027502,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.3546810913085938,
      "step": 8400
    },
    {
      "epoch": 0.9473654880325448,
      "learning_rate": 1.5e-05,
      "loss": 1.330055694580078,
      "step": 8500
    },
    {
      "epoch": 0.9585109643623394,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.325668487548828,
      "step": 8600
    },
    {
      "epoch": 0.9696564406921341,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.331268310546875,
      "step": 8700
    },
    {
      "epoch": 0.9808019170219288,
      "learning_rate": 1.2e-05,
      "loss": 1.346514892578125,
      "step": 8800
    },
    {
      "epoch": 0.9919473933517233,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.3515042114257811,
      "step": 8900
    },
    {
      "epoch": 1.0031207333723424,
      "learning_rate": 1e-05,
      "loss": 1.3323361206054687,
      "step": 9000
    },
    {
      "epoch": 1.014266209702137,
      "learning_rate": 9e-06,
      "loss": 1.2915484619140625,
      "step": 9100
    },
    {
      "epoch": 1.0254116860319318,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.2769253540039063,
      "step": 9200
    },
    {
      "epoch": 1.0365571623617265,
      "learning_rate": 7.000000000000001e-06,
      "loss": 1.2951361083984374,
      "step": 9300
    },
    {
      "epoch": 1.0477026386915211,
      "learning_rate": 6e-06,
      "loss": 1.30968505859375,
      "step": 9400
    },
    {
      "epoch": 1.0588481150213158,
      "learning_rate": 5e-06,
      "loss": 1.2824142456054688,
      "step": 9500
    },
    {
      "epoch": 1.0699935913511103,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.2977745056152343,
      "step": 9600
    },
    {
      "epoch": 1.081139067680905,
      "learning_rate": 3e-06,
      "loss": 1.296290283203125,
      "step": 9700
    },
    {
      "epoch": 1.0922845440106996,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.301255645751953,
      "step": 9800
    },
    {
      "epoch": 1.1034300203404943,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.28552490234375,
      "step": 9900
    },
    {
      "epoch": 1.114575496670289,
      "learning_rate": 0.0,
      "loss": 1.2935409545898438,
      "step": 10000
    },
    {
      "epoch": 1.114575496670289,
      "eval_gen_len": 48.8,
      "eval_loss": 1.3494852781295776,
      "eval_rouge1": 35.2792,
      "eval_rouge2": 15.3645,
      "eval_rougeL": 26.3329,
      "eval_rougeLsum": 32.2724,
      "eval_runtime": 161.2437,
      "eval_samples_per_second": 3.101,
      "step": 10000
    },
    {
      "epoch": 1.114575496670289,
      "step": 10000,
      "train_runtime": 28429.155,
      "train_samples_per_second": 0.352
    }
  ],
  "max_steps": 10000,
  "num_train_epochs": 2,
  "total_flos": 454127617474172928,
  "trial_name": null,
  "trial_params": null
}