{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6973804646297346,
  "eval_steps": 4000,
  "global_step": 16000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004358627903935841,
      "grad_norm": 30.40549087524414,
      "learning_rate": 9.991544261866365e-07,
      "loss": 9.7914,
      "step": 100
    },
    {
      "epoch": 0.008717255807871681,
      "grad_norm": 23.055740356445312,
      "learning_rate": 9.982827006058492e-07,
      "loss": 8.5435,
      "step": 200
    },
    {
      "epoch": 0.013075883711807523,
      "grad_norm": 16.28481674194336,
      "learning_rate": 9.97410975025062e-07,
      "loss": 7.9154,
      "step": 300
    },
    {
      "epoch": 0.017434511615743362,
      "grad_norm": 21.263378143310547,
      "learning_rate": 9.96539249444275e-07,
      "loss": 7.3876,
      "step": 400
    },
    {
      "epoch": 0.021793139519679205,
      "grad_norm": 25.245298385620117,
      "learning_rate": 9.956675238634877e-07,
      "loss": 6.3013,
      "step": 500
    },
    {
      "epoch": 0.026151767423615045,
      "grad_norm": 11.57956314086914,
      "learning_rate": 9.947957982827006e-07,
      "loss": 5.6204,
      "step": 600
    },
    {
      "epoch": 0.03051039532755089,
      "grad_norm": 12.328071594238281,
      "learning_rate": 9.939240727019133e-07,
      "loss": 5.0561,
      "step": 700
    },
    {
      "epoch": 0.034869023231486725,
      "grad_norm": 6.695566654205322,
      "learning_rate": 9.930523471211262e-07,
      "loss": 4.6239,
      "step": 800
    },
    {
      "epoch": 0.03922765113542257,
      "grad_norm": 5.218314170837402,
      "learning_rate": 9.921806215403392e-07,
      "loss": 4.3892,
      "step": 900
    },
    {
      "epoch": 0.04358627903935841,
      "grad_norm": 3.0057296752929688,
      "learning_rate": 9.913088959595519e-07,
      "loss": 4.2331,
      "step": 1000
    },
    {
      "epoch": 0.04794490694329425,
      "grad_norm": 5.0231475830078125,
      "learning_rate": 9.904371703787648e-07,
      "loss": 4.1711,
      "step": 1100
    },
    {
      "epoch": 0.05230353484723009,
      "grad_norm": 2.6531741619110107,
      "learning_rate": 9.895654447979775e-07,
      "loss": 4.0637,
      "step": 1200
    },
    {
      "epoch": 0.05666216275116593,
      "grad_norm": 2.5700411796569824,
      "learning_rate": 9.887024364729981e-07,
      "loss": 3.99,
      "step": 1300
    },
    {
      "epoch": 0.06102079065510178,
      "grad_norm": 2.2256696224212646,
      "learning_rate": 9.87830710892211e-07,
      "loss": 4.0391,
      "step": 1400
    },
    {
      "epoch": 0.06537941855903762,
      "grad_norm": 2.429391860961914,
      "learning_rate": 9.86967702567232e-07,
      "loss": 4.0632,
      "step": 1500
    },
    {
      "epoch": 0.06973804646297345,
      "grad_norm": 2.8544466495513916,
      "learning_rate": 9.860959769864446e-07,
      "loss": 4.0077,
      "step": 1600
    },
    {
      "epoch": 0.0740966743669093,
      "grad_norm": 2.9580471515655518,
      "learning_rate": 9.852329686614652e-07,
      "loss": 3.981,
      "step": 1700
    },
    {
      "epoch": 0.07845530227084514,
      "grad_norm": 2.4251883029937744,
      "learning_rate": 9.84369960336486e-07,
      "loss": 3.9854,
      "step": 1800
    },
    {
      "epoch": 0.08281393017478098,
      "grad_norm": 3.6600637435913086,
      "learning_rate": 9.834982347556988e-07,
      "loss": 3.9396,
      "step": 1900
    },
    {
      "epoch": 0.08717255807871682,
      "grad_norm": 2.000615358352661,
      "learning_rate": 9.826265091749117e-07,
      "loss": 3.9047,
      "step": 2000
    },
    {
      "epoch": 0.09153118598265265,
      "grad_norm": 2.1824817657470703,
      "learning_rate": 9.817547835941246e-07,
      "loss": 3.9306,
      "step": 2100
    },
    {
      "epoch": 0.0958898138865885,
      "grad_norm": 2.6124613285064697,
      "learning_rate": 9.809004925249532e-07,
      "loss": 3.9145,
      "step": 2200
    },
    {
      "epoch": 0.10024844179052435,
      "grad_norm": 2.304738998413086,
      "learning_rate": 9.80028766944166e-07,
      "loss": 3.9333,
      "step": 2300
    },
    {
      "epoch": 0.10460706969446018,
      "grad_norm": 2.216799020767212,
      "learning_rate": 9.791570413633788e-07,
      "loss": 3.8542,
      "step": 2400
    },
    {
      "epoch": 0.10896569759839603,
      "grad_norm": 2.139524221420288,
      "learning_rate": 9.782853157825915e-07,
      "loss": 3.8202,
      "step": 2500
    },
    {
      "epoch": 0.11332432550233186,
      "grad_norm": 2.912883996963501,
      "learning_rate": 9.774223074576124e-07,
      "loss": 3.8677,
      "step": 2600
    },
    {
      "epoch": 0.1176829534062677,
      "grad_norm": 2.124760389328003,
      "learning_rate": 9.76550581876825e-07,
      "loss": 3.8609,
      "step": 2700
    },
    {
      "epoch": 0.12204158131020355,
      "grad_norm": 1.7955399751663208,
      "learning_rate": 9.756875735518457e-07,
      "loss": 3.8286,
      "step": 2800
    },
    {
      "epoch": 0.1264002092141394,
      "grad_norm": 2.2948408126831055,
      "learning_rate": 9.748158479710586e-07,
      "loss": 3.8297,
      "step": 2900
    },
    {
      "epoch": 0.13075883711807523,
      "grad_norm": 1.8445340394973755,
      "learning_rate": 9.739441223902716e-07,
      "loss": 3.8535,
      "step": 3000
    },
    {
      "epoch": 0.13511746502201108,
      "grad_norm": 1.911111831665039,
      "learning_rate": 9.730723968094843e-07,
      "loss": 3.8011,
      "step": 3100
    },
    {
      "epoch": 0.1394760929259469,
      "grad_norm": 1.8173906803131104,
      "learning_rate": 9.722006712286972e-07,
      "loss": 3.8245,
      "step": 3200
    },
    {
      "epoch": 0.14383472082988275,
      "grad_norm": NaN,
      "learning_rate": 9.713376629037178e-07,
      "loss": 3.8505,
      "step": 3300
    },
    {
      "epoch": 0.1481933487338186,
      "grad_norm": 1.7375200986862183,
      "learning_rate": 9.704659373229307e-07,
      "loss": 3.8695,
      "step": 3400
    },
    {
      "epoch": 0.15255197663775444,
      "grad_norm": 1.8474202156066895,
      "learning_rate": 9.695942117421434e-07,
      "loss": 3.7777,
      "step": 3500
    },
    {
      "epoch": 0.15691060454169029,
      "grad_norm": 1.6612401008605957,
      "learning_rate": 9.687224861613564e-07,
      "loss": 3.7772,
      "step": 3600
    },
    {
      "epoch": 0.1612692324456261,
      "grad_norm": 2.0957448482513428,
      "learning_rate": 9.678507605805693e-07,
      "loss": 3.8124,
      "step": 3700
    },
    {
      "epoch": 0.16562786034956195,
      "grad_norm": 1.9771664142608643,
      "learning_rate": 9.6698775225559e-07,
      "loss": 3.8018,
      "step": 3800
    },
    {
      "epoch": 0.1699864882534978,
      "grad_norm": 1.731178641319275,
      "learning_rate": 9.661247439306106e-07,
      "loss": 3.8308,
      "step": 3900
    },
    {
      "epoch": 0.17434511615743364,
      "grad_norm": 3.0937631130218506,
      "learning_rate": 9.652530183498235e-07,
      "loss": 3.8204,
      "step": 4000
    },
    {
      "epoch": 0.17434511615743364,
      "eval_gen_len": 258.3977,
      "eval_loss": 3.743095874786377,
      "eval_rouge1": 11.0785,
      "eval_rouge2": 1.4258,
      "eval_rougeL": 9.2011,
      "eval_rougeLsum": 9.7537,
      "eval_runtime": 1000.5304,
      "eval_samples_per_second": 5.443,
      "eval_steps_per_second": 0.086,
      "step": 4000
    },
    {
      "epoch": 0.1787037440613695,
      "grad_norm": 1.7788825035095215,
      "learning_rate": 9.643900100248441e-07,
      "loss": 3.8099,
      "step": 4100
    },
    {
      "epoch": 0.1830623719653053,
      "grad_norm": 1.9720195531845093,
      "learning_rate": 9.635182844440568e-07,
      "loss": 3.7094,
      "step": 4200
    },
    {
      "epoch": 0.18742099986924116,
      "grad_norm": 1.9566844701766968,
      "learning_rate": 9.626465588632697e-07,
      "loss": 3.7826,
      "step": 4300
    },
    {
      "epoch": 0.191779627773177,
      "grad_norm": 1.6677696704864502,
      "learning_rate": 9.617748332824827e-07,
      "loss": 3.7683,
      "step": 4400
    },
    {
      "epoch": 0.19613825567711285,
      "grad_norm": 1.7738280296325684,
      "learning_rate": 9.609031077016956e-07,
      "loss": 3.7828,
      "step": 4500
    },
    {
      "epoch": 0.2004968835810487,
      "grad_norm": 1.6880650520324707,
      "learning_rate": 9.600313821209083e-07,
      "loss": 3.7524,
      "step": 4600
    },
    {
      "epoch": 0.20485551148498451,
      "grad_norm": 2.1983208656311035,
      "learning_rate": 9.591596565401212e-07,
      "loss": 3.752,
      "step": 4700
    },
    {
      "epoch": 0.20921413938892036,
      "grad_norm": 1.9678415060043335,
      "learning_rate": 9.582966482151418e-07,
      "loss": 3.7699,
      "step": 4800
    },
    {
      "epoch": 0.2135727672928562,
      "grad_norm": 2.111438512802124,
      "learning_rate": 9.574336398901625e-07,
      "loss": 3.7878,
      "step": 4900
    },
    {
      "epoch": 0.21793139519679205,
      "grad_norm": 1.5860246419906616,
      "learning_rate": 9.565706315651833e-07,
      "loss": 3.7865,
      "step": 5000
    },
    {
      "epoch": 0.2222900231007279,
      "grad_norm": 1.6452280282974243,
      "learning_rate": 9.55707623240204e-07,
      "loss": 3.7863,
      "step": 5100
    },
    {
      "epoch": 0.22664865100466372,
      "grad_norm": 1.43221116065979,
      "learning_rate": 9.548358976594167e-07,
      "loss": 3.7756,
      "step": 5200
    },
    {
      "epoch": 0.23100727890859957,
      "grad_norm": 1.6508175134658813,
      "learning_rate": 9.539641720786296e-07,
      "loss": 3.7635,
      "step": 5300
    },
    {
      "epoch": 0.2353659068125354,
      "grad_norm": 1.3596303462982178,
      "learning_rate": 9.530924464978425e-07,
      "loss": 3.8022,
      "step": 5400
    },
    {
      "epoch": 0.23972453471647126,
      "grad_norm": 1.434622049331665,
      "learning_rate": 9.522294381728631e-07,
      "loss": 3.8525,
      "step": 5500
    },
    {
      "epoch": 0.2440831626204071,
      "grad_norm": 1.3105734586715698,
      "learning_rate": 9.51357712592076e-07,
      "loss": 3.8133,
      "step": 5600
    },
    {
      "epoch": 0.24844179052434293,
      "grad_norm": 1.3989108800888062,
      "learning_rate": 9.504859870112888e-07,
      "loss": 3.7857,
      "step": 5700
    },
    {
      "epoch": 0.2528004184282788,
      "grad_norm": 0.8452894687652588,
      "learning_rate": 9.496229786863095e-07,
      "loss": 3.7578,
      "step": 5800
    },
    {
      "epoch": 0.2571590463322146,
      "grad_norm": 1.7360140085220337,
      "learning_rate": 9.487686876171381e-07,
      "loss": 3.7573,
      "step": 5900
    },
    {
      "epoch": 0.26151767423615047,
      "grad_norm": 1.5747486352920532,
      "learning_rate": 9.479056792921588e-07,
      "loss": 3.7993,
      "step": 6000
    },
    {
      "epoch": 0.2658763021400863,
      "grad_norm": 1.6522992849349976,
      "learning_rate": 9.470426709671795e-07,
      "loss": 3.7737,
      "step": 6100
    },
    {
      "epoch": 0.27023493004402216,
      "grad_norm": 2.4300875663757324,
      "learning_rate": 9.461709453863923e-07,
      "loss": 3.7746,
      "step": 6200
    },
    {
      "epoch": 0.274593557947958,
      "grad_norm": 1.9024791717529297,
      "learning_rate": 9.452992198056051e-07,
      "loss": 3.786,
      "step": 6300
    },
    {
      "epoch": 0.2789521858518938,
      "grad_norm": 1.8614801168441772,
      "learning_rate": 9.444274942248179e-07,
      "loss": 3.8174,
      "step": 6400
    },
    {
      "epoch": 0.28331081375582967,
      "grad_norm": 2.356868028640747,
      "learning_rate": 9.435644858998388e-07,
      "loss": 3.804,
      "step": 6500
    },
    {
      "epoch": 0.2876694416597655,
      "grad_norm": 2.2077884674072266,
      "learning_rate": 9.427014775748594e-07,
      "loss": 3.7839,
      "step": 6600
    },
    {
      "epoch": 0.29202806956370136,
      "grad_norm": 3.3564858436584473,
      "learning_rate": 9.4183846924988e-07,
      "loss": 3.7923,
      "step": 6700
    },
    {
      "epoch": 0.2963866974676372,
      "grad_norm": 2.885087013244629,
      "learning_rate": 9.409667436690929e-07,
      "loss": 3.8136,
      "step": 6800
    },
    {
      "epoch": 0.300745325371573,
      "grad_norm": 3.5900139808654785,
      "learning_rate": 9.400950180883058e-07,
      "loss": 3.8064,
      "step": 6900
    },
    {
      "epoch": 0.3051039532755089,
      "grad_norm": 3.0556740760803223,
      "learning_rate": 9.392320097633265e-07,
      "loss": 3.7845,
      "step": 7000
    },
    {
      "epoch": 0.3094625811794447,
      "grad_norm": 3.6052465438842773,
      "learning_rate": 9.383602841825393e-07,
      "loss": 3.7735,
      "step": 7100
    },
    {
      "epoch": 0.31382120908338057,
      "grad_norm": 3.893676519393921,
      "learning_rate": 9.374885586017521e-07,
      "loss": 3.7444,
      "step": 7200
    },
    {
      "epoch": 0.3181798369873164,
      "grad_norm": 3.3053371906280518,
      "learning_rate": 9.366168330209649e-07,
      "loss": 3.7802,
      "step": 7300
    },
    {
      "epoch": 0.3225384648912522,
      "grad_norm": 3.144166946411133,
      "learning_rate": 9.357451074401778e-07,
      "loss": 3.7388,
      "step": 7400
    },
    {
      "epoch": 0.3268970927951881,
      "grad_norm": 3.3398513793945312,
      "learning_rate": 9.348733818593906e-07,
      "loss": 3.8147,
      "step": 7500
    },
    {
      "epoch": 0.3312557206991239,
      "grad_norm": 2.581552267074585,
      "learning_rate": 9.340016562786035e-07,
      "loss": 3.7542,
      "step": 7600
    },
    {
      "epoch": 0.3356143486030598,
      "grad_norm": 2.9723496437072754,
      "learning_rate": 9.331299306978163e-07,
      "loss": 3.7923,
      "step": 7700
    },
    {
      "epoch": 0.3399729765069956,
      "grad_norm": 3.501049757003784,
      "learning_rate": 9.322582051170291e-07,
      "loss": 3.7978,
      "step": 7800
    },
    {
      "epoch": 0.3443316044109314,
      "grad_norm": 3.292762279510498,
      "learning_rate": 9.313864795362419e-07,
      "loss": 3.7684,
      "step": 7900
    },
    {
      "epoch": 0.3486902323148673,
      "grad_norm": 7.055439472198486,
      "learning_rate": 9.305409057228783e-07,
      "loss": 3.8167,
      "step": 8000
    },
    {
      "epoch": 0.3486902323148673,
      "eval_gen_len": 182.3386,
      "eval_loss": 3.720294952392578,
      "eval_rouge1": 12.7469,
      "eval_rouge2": 1.7143,
      "eval_rougeL": 10.3719,
      "eval_rougeLsum": 11.2293,
      "eval_runtime": 976.3587,
      "eval_samples_per_second": 5.578,
      "eval_steps_per_second": 0.088,
      "step": 8000
    },
    {
      "epoch": 0.3530488602188031,
      "grad_norm": 0.0,
      "learning_rate": 9.296691801420912e-07,
      "loss": 3.7368,
      "step": 8100
    },
    {
      "epoch": 0.357407488122739,
      "grad_norm": 0.0,
      "learning_rate": 9.288148890729198e-07,
      "loss": 3.8094,
      "step": 8200
    },
    {
      "epoch": 0.3617661160266748,
      "grad_norm": 0.0,
      "learning_rate": 9.279431634921326e-07,
      "loss": 3.806,
      "step": 8300
    },
    {
      "epoch": 0.3661247439306106,
      "grad_norm": 0.0,
      "learning_rate": 9.270714379113454e-07,
      "loss": 3.7526,
      "step": 8400
    },
    {
      "epoch": 0.3704833718345465,
      "grad_norm": 0.0,
      "learning_rate": 9.262084295863662e-07,
      "loss": 3.7902,
      "step": 8500
    },
    {
      "epoch": 0.3748419997384823,
      "grad_norm": 0.0,
      "learning_rate": 9.25336704005579e-07,
      "loss": 3.8063,
      "step": 8600
    },
    {
      "epoch": 0.3792006276424182,
      "grad_norm": 0.0,
      "learning_rate": 9.244649784247919e-07,
      "loss": 3.79,
      "step": 8700
    },
    {
      "epoch": 0.383559255546354,
      "grad_norm": 0.0,
      "learning_rate": 9.235932528440047e-07,
      "loss": 3.8446,
      "step": 8800
    },
    {
      "epoch": 0.3879178834502898,
      "grad_norm": 0.0,
      "learning_rate": 9.227302445190254e-07,
      "loss": 3.8016,
      "step": 8900
    },
    {
      "epoch": 0.3922765113542257,
      "grad_norm": 0.0,
      "learning_rate": 9.218585189382382e-07,
      "loss": 3.789,
      "step": 9000
    },
    {
      "epoch": 0.3966351392581615,
      "grad_norm": 0.0,
      "learning_rate": 9.20986793357451e-07,
      "loss": 3.7935,
      "step": 9100
    },
    {
      "epoch": 0.4009937671620974,
      "grad_norm": 0.0,
      "learning_rate": 9.201150677766638e-07,
      "loss": 3.7818,
      "step": 9200
    },
    {
      "epoch": 0.4053523950660332,
      "grad_norm": 0.0,
      "learning_rate": 9.192520594516846e-07,
      "loss": 3.8178,
      "step": 9300
    },
    {
      "epoch": 0.40971102296996903,
      "grad_norm": 0.0,
      "learning_rate": 9.183803338708975e-07,
      "loss": 3.7768,
      "step": 9400
    },
    {
      "epoch": 0.4140696508739049,
      "grad_norm": 0.0,
      "learning_rate": 9.175086082901103e-07,
      "loss": 3.8288,
      "step": 9500
    },
    {
      "epoch": 0.4184282787778407,
      "grad_norm": 0.0,
      "learning_rate": 9.166455999651309e-07,
      "loss": 3.7903,
      "step": 9600
    },
    {
      "epoch": 0.4227869066817766,
      "grad_norm": 0.0,
      "learning_rate": 9.157738743843437e-07,
      "loss": 3.8076,
      "step": 9700
    },
    {
      "epoch": 0.4271455345857124,
      "grad_norm": 0.0,
      "learning_rate": 9.149108660593646e-07,
      "loss": 3.77,
      "step": 9800
    },
    {
      "epoch": 0.43150416248964824,
      "grad_norm": 0.0,
      "learning_rate": 9.140478577343852e-07,
      "loss": 3.7931,
      "step": 9900
    },
    {
      "epoch": 0.4358627903935841,
      "grad_norm": 0.0,
      "learning_rate": 9.13176132153598e-07,
      "loss": 3.7802,
      "step": 10000
    },
    {
      "epoch": 0.44022141829751993,
      "grad_norm": 0.0,
      "learning_rate": 9.123044065728108e-07,
      "loss": 3.8273,
      "step": 10100
    },
    {
      "epoch": 0.4445800462014558,
      "grad_norm": 0.0,
      "learning_rate": 9.114326809920236e-07,
      "loss": 3.7708,
      "step": 10200
    },
    {
      "epoch": 0.4489386741053916,
      "grad_norm": 0.0,
      "learning_rate": 9.105609554112364e-07,
      "loss": 3.7881,
      "step": 10300
    },
    {
      "epoch": 0.45329730200932744,
      "grad_norm": 0.0,
      "learning_rate": 9.096892298304494e-07,
      "loss": 3.7923,
      "step": 10400
    },
    {
      "epoch": 0.4576559299132633,
      "grad_norm": 0.0,
      "learning_rate": 9.088175042496622e-07,
      "loss": 3.7904,
      "step": 10500
    },
    {
      "epoch": 0.46201455781719913,
      "grad_norm": 0.0,
      "learning_rate": 9.07945778668875e-07,
      "loss": 3.7758,
      "step": 10600
    },
    {
      "epoch": 0.466373185721135,
      "grad_norm": 0.0,
      "learning_rate": 9.070740530880878e-07,
      "loss": 3.7181,
      "step": 10700
    },
    {
      "epoch": 0.4707318136250708,
      "grad_norm": 0.0,
      "learning_rate": 9.062023275073006e-07,
      "loss": 3.82,
      "step": 10800
    },
    {
      "epoch": 0.47509044152900665,
      "grad_norm": 0.0,
      "learning_rate": 9.053306019265134e-07,
      "loss": 3.7387,
      "step": 10900
    },
    {
      "epoch": 0.4794490694329425,
      "grad_norm": 0.0,
      "learning_rate": 9.044588763457263e-07,
      "loss": 3.8448,
      "step": 11000
    },
    {
      "epoch": 0.48380769733687834,
      "grad_norm": 0.0,
      "learning_rate": 9.035958680207471e-07,
      "loss": 3.785,
      "step": 11100
    },
    {
      "epoch": 0.4881663252408142,
      "grad_norm": 0.0,
      "learning_rate": 9.027241424399599e-07,
      "loss": 3.8292,
      "step": 11200
    },
    {
      "epoch": 0.49252495314475003,
      "grad_norm": 0.0,
      "learning_rate": 9.018611341149805e-07,
      "loss": 3.7867,
      "step": 11300
    },
    {
      "epoch": 0.49688358104868585,
      "grad_norm": 0.0,
      "learning_rate": 9.009981257900013e-07,
      "loss": 3.7749,
      "step": 11400
    },
    {
      "epoch": 0.5012422089526217,
      "grad_norm": 0.0,
      "learning_rate": 9.00135117465022e-07,
      "loss": 3.8242,
      "step": 11500
    },
    {
      "epoch": 0.5056008368565575,
      "grad_norm": 0.0,
      "learning_rate": 8.992808263958506e-07,
      "loss": 3.7584,
      "step": 11600
    },
    {
      "epoch": 0.5099594647604934,
      "grad_norm": 0.0,
      "learning_rate": 8.984091008150634e-07,
      "loss": 3.7408,
      "step": 11700
    },
    {
      "epoch": 0.5143180926644292,
      "grad_norm": 0.0,
      "learning_rate": 8.975373752342762e-07,
      "loss": 3.8061,
      "step": 11800
    },
    {
      "epoch": 0.5186767205683651,
      "grad_norm": 0.0,
      "learning_rate": 8.966743669092969e-07,
      "loss": 3.8047,
      "step": 11900
    },
    {
      "epoch": 0.5230353484723009,
      "grad_norm": 0.0,
      "learning_rate": 8.958113585843177e-07,
      "loss": 3.7662,
      "step": 12000
    },
    {
      "epoch": 0.5230353484723009,
      "eval_gen_len": 182.7448,
      "eval_loss": 3.7201850414276123,
      "eval_rouge1": 12.752,
      "eval_rouge2": 1.7119,
      "eval_rougeL": 10.3684,
      "eval_rougeLsum": 11.228,
      "eval_runtime": 973.1101,
      "eval_samples_per_second": 5.596,
      "eval_steps_per_second": 0.088,
      "step": 12000
    },
    {
      "epoch": 0.5273939763762368,
      "grad_norm": 0.0,
      "learning_rate": 8.949483502593384e-07,
      "loss": 3.7775,
      "step": 12100
    },
    {
      "epoch": 0.5317526042801726,
      "grad_norm": 0.0,
      "learning_rate": 8.94085341934359e-07,
      "loss": 3.7863,
      "step": 12200
    },
    {
      "epoch": 0.5361112321841084,
      "grad_norm": 0.0,
      "learning_rate": 8.932136163535718e-07,
      "loss": 3.7689,
      "step": 12300
    },
    {
      "epoch": 0.5404698600880443,
      "grad_norm": 0.0,
      "learning_rate": 8.923418907727846e-07,
      "loss": 3.7787,
      "step": 12400
    },
    {
      "epoch": 0.5448284879919801,
      "grad_norm": 0.0,
      "learning_rate": 8.914701651919974e-07,
      "loss": 3.7484,
      "step": 12500
    },
    {
      "epoch": 0.549187115895916,
      "grad_norm": 0.0,
      "learning_rate": 8.906071568670183e-07,
      "loss": 3.7399,
      "step": 12600
    },
    {
      "epoch": 0.5535457437998518,
      "grad_norm": 0.0,
      "learning_rate": 8.897354312862311e-07,
      "loss": 3.8051,
      "step": 12700
    },
    {
      "epoch": 0.5579043717037876,
      "grad_norm": 0.0,
      "learning_rate": 8.888637057054439e-07,
      "loss": 3.8352,
      "step": 12800
    },
    {
      "epoch": 0.5622629996077235,
      "grad_norm": 0.0,
      "learning_rate": 8.879919801246567e-07,
      "loss": 3.8274,
      "step": 12900
    },
    {
      "epoch": 0.5666216275116593,
      "grad_norm": 0.0,
      "learning_rate": 8.871289717996773e-07,
      "loss": 3.8084,
      "step": 13000
    },
    {
      "epoch": 0.5709802554155952,
      "grad_norm": 0.0,
      "learning_rate": 8.862572462188903e-07,
      "loss": 3.7881,
      "step": 13100
    },
    {
      "epoch": 0.575338883319531,
      "grad_norm": 0.0,
      "learning_rate": 8.85394237893911e-07,
      "loss": 3.7847,
      "step": 13200
    },
    {
      "epoch": 0.5796975112234668,
      "grad_norm": 0.0,
      "learning_rate": 8.845225123131238e-07,
      "loss": 3.8208,
      "step": 13300
    },
    {
      "epoch": 0.5840561391274027,
      "grad_norm": 0.0,
      "learning_rate": 8.836507867323366e-07,
      "loss": 3.8001,
      "step": 13400
    },
    {
      "epoch": 0.5884147670313385,
      "grad_norm": 0.0,
      "learning_rate": 8.827790611515494e-07,
      "loss": 3.7548,
      "step": 13500
    },
    {
      "epoch": 0.5927733949352744,
      "grad_norm": 0.0,
      "learning_rate": 8.819073355707623e-07,
      "loss": 3.7239,
      "step": 13600
    },
    {
      "epoch": 0.5971320228392102,
      "grad_norm": 0.0,
      "learning_rate": 8.810356099899752e-07,
      "loss": 3.7832,
      "step": 13700
    },
    {
      "epoch": 0.601490650743146,
      "grad_norm": 0.0,
      "learning_rate": 8.80163884409188e-07,
      "loss": 3.7644,
      "step": 13800
    },
    {
      "epoch": 0.6058492786470819,
      "grad_norm": 0.0,
      "learning_rate": 8.792921588284008e-07,
      "loss": 3.7871,
      "step": 13900
    },
    {
      "epoch": 0.6102079065510178,
      "grad_norm": 0.0,
      "learning_rate": 8.784204332476136e-07,
      "loss": 3.7594,
      "step": 14000
    },
    {
      "epoch": 0.6145665344549536,
      "grad_norm": 0.0,
      "learning_rate": 8.775487076668264e-07,
      "loss": 3.7967,
      "step": 14100
    },
    {
      "epoch": 0.6189251623588894,
      "grad_norm": 0.0,
      "learning_rate": 8.766769820860392e-07,
      "loss": 3.8017,
      "step": 14200
    },
    {
      "epoch": 0.6232837902628252,
      "grad_norm": 0.0,
      "learning_rate": 8.75805256505252e-07,
      "loss": 3.7972,
      "step": 14300
    },
    {
      "epoch": 0.6276424181667611,
      "grad_norm": 0.0,
      "learning_rate": 8.74933530924465e-07,
      "loss": 3.8165,
      "step": 14400
    },
    {
      "epoch": 0.632001046070697,
      "grad_norm": 0.0,
      "learning_rate": 8.740618053436778e-07,
      "loss": 3.7934,
      "step": 14500
    },
    {
      "epoch": 0.6363596739746328,
      "grad_norm": 0.0,
      "learning_rate": 8.731900797628906e-07,
      "loss": 3.8056,
      "step": 14600
    },
    {
      "epoch": 0.6407183018785686,
      "grad_norm": 0.0,
      "learning_rate": 8.723270714379113e-07,
      "loss": 3.7537,
      "step": 14700
    },
    {
      "epoch": 0.6450769297825044,
      "grad_norm": 0.0,
      "learning_rate": 8.714553458571241e-07,
      "loss": 3.8102,
      "step": 14800
    },
    {
      "epoch": 0.6494355576864403,
      "grad_norm": 0.0,
      "learning_rate": 8.705836202763369e-07,
      "loss": 3.8053,
      "step": 14900
    },
    {
      "epoch": 0.6537941855903762,
      "grad_norm": 0.0,
      "learning_rate": 8.697206119513577e-07,
      "loss": 3.7925,
      "step": 15000
    },
    {
      "epoch": 0.658152813494312,
      "grad_norm": 0.0,
      "learning_rate": 8.688576036263784e-07,
      "loss": 3.7678,
      "step": 15100
    },
    {
      "epoch": 0.6625114413982478,
      "grad_norm": 0.0,
      "learning_rate": 8.679945953013991e-07,
      "loss": 3.7588,
      "step": 15200
    },
    {
      "epoch": 0.6668700693021836,
      "grad_norm": 0.0,
      "learning_rate": 8.671315869764197e-07,
      "loss": 3.7971,
      "step": 15300
    },
    {
      "epoch": 0.6712286972061196,
      "grad_norm": 0.0,
      "learning_rate": 8.662598613956325e-07,
      "loss": 3.8028,
      "step": 15400
    },
    {
      "epoch": 0.6755873251100554,
      "grad_norm": 0.0,
      "learning_rate": 8.653881358148454e-07,
      "loss": 3.8079,
      "step": 15500
    },
    {
      "epoch": 0.6799459530139912,
      "grad_norm": 0.0,
      "learning_rate": 8.645251274898662e-07,
      "loss": 3.7807,
      "step": 15600
    },
    {
      "epoch": 0.684304580917927,
      "grad_norm": 0.0,
      "learning_rate": 8.636708364206948e-07,
      "loss": 3.7709,
      "step": 15700
    },
    {
      "epoch": 0.6886632088218628,
      "grad_norm": 0.0,
      "learning_rate": 8.628078280957154e-07,
      "loss": 3.835,
      "step": 15800
    },
    {
      "epoch": 0.6930218367257988,
      "grad_norm": 0.0,
      "learning_rate": 8.619361025149282e-07,
      "loss": 3.7721,
      "step": 15900
    },
    {
      "epoch": 0.6973804646297346,
      "grad_norm": 0.0,
      "learning_rate": 8.61073094189949e-07,
      "loss": 3.7919,
      "step": 16000
    },
    {
      "epoch": 0.6973804646297346,
      "eval_gen_len": 182.7448,
      "eval_loss": 3.7201850414276123,
      "eval_rouge1": 12.752,
      "eval_rouge2": 1.7119,
      "eval_rougeL": 10.3684,
      "eval_rougeLsum": 11.228,
      "eval_runtime": 973.8648,
      "eval_samples_per_second": 5.592,
      "eval_steps_per_second": 0.088,
      "step": 16000
    }
  ],
  "logging_steps": 100,
  "max_steps": 114715,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 4000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.897330499584e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}