{
  "best_metric": 3.0774757862091064,
  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-80324",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 80324,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 4.5056,
      "step": 500
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.9999957472774e-05,
      "loss": 3.8512,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.999982989116833e-05,
      "loss": 3.6498,
      "step": 1500
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.999961725540003e-05,
      "loss": 3.6328,
      "step": 2000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.999931956583082e-05,
      "loss": 3.6162,
      "step": 2500
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.999893682296706e-05,
      "loss": 3.6415,
      "step": 3000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.999846902745986e-05,
      "loss": 3.6273,
      "step": 3500
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.999791618010498e-05,
      "loss": 3.5555,
      "step": 4000
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.999727828184285e-05,
      "loss": 3.5176,
      "step": 4500
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.99965553337586e-05,
      "loss": 3.4374,
      "step": 5000
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.999574733708204e-05,
      "loss": 3.5565,
      "step": 5500
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.999485429318763e-05,
      "loss": 3.4639,
      "step": 6000
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.99938762035945e-05,
      "loss": 3.3833,
      "step": 6500
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.999281306996651e-05,
      "loss": 3.4726,
      "step": 7000
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.999166489411211e-05,
      "loss": 3.4132,
      "step": 7500
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.999043167798448e-05,
      "loss": 3.3754,
      "step": 8000
    },
    {
      "epoch": 0.21,
      "learning_rate": 9.99891134236814e-05,
      "loss": 3.4333,
      "step": 8500
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.998771013344535e-05,
      "loss": 3.3313,
      "step": 9000
    },
    {
      "epoch": 0.24,
      "learning_rate": 9.998622180966344e-05,
      "loss": 3.3758,
      "step": 9500
    },
    {
      "epoch": 0.25,
      "learning_rate": 9.998464845486746e-05,
      "loss": 3.3814,
      "step": 10000
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.998299007173383e-05,
      "loss": 3.429,
      "step": 10500
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.99812466630836e-05,
      "loss": 3.4547,
      "step": 11000
    },
    {
      "epoch": 0.29,
      "learning_rate": 9.997941823188243e-05,
      "loss": 3.4204,
      "step": 11500
    },
    {
      "epoch": 0.3,
      "learning_rate": 9.99775047812407e-05,
      "loss": 3.3807,
      "step": 12000
    },
    {
      "epoch": 0.31,
      "learning_rate": 9.997550631441332e-05,
      "loss": 3.3749,
      "step": 12500
    },
    {
      "epoch": 0.32,
      "learning_rate": 9.997342283479989e-05,
      "loss": 3.326,
      "step": 13000
    },
    {
      "epoch": 0.34,
      "learning_rate": 9.997125434594458e-05,
      "loss": 3.3626,
      "step": 13500
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.996900085153617e-05,
      "loss": 3.304,
      "step": 14000
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.996666235540808e-05,
      "loss": 3.3671,
      "step": 14500
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.996423886153828e-05,
      "loss": 3.3667,
      "step": 15000
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.996173037404934e-05,
      "loss": 3.321,
      "step": 15500
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.995913689720844e-05,
      "loss": 3.2639,
      "step": 16000
    },
    {
      "epoch": 0.41,
      "learning_rate": 9.995645843542732e-05,
      "loss": 3.3529,
      "step": 16500
    },
    {
      "epoch": 0.42,
      "learning_rate": 9.995369499326228e-05,
      "loss": 3.2607,
      "step": 17000
    },
    {
      "epoch": 0.44,
      "learning_rate": 9.995084657541416e-05,
      "loss": 3.2858,
      "step": 17500
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.994791318672838e-05,
      "loss": 3.3516,
      "step": 18000
    },
    {
      "epoch": 0.46,
      "learning_rate": 9.994489483219492e-05,
      "loss": 3.2944,
      "step": 18500
    },
    {
      "epoch": 0.47,
      "learning_rate": 9.994179151694824e-05,
      "loss": 3.278,
      "step": 19000
    },
    {
      "epoch": 0.49,
      "learning_rate": 9.993860324626737e-05,
      "loss": 3.2557,
      "step": 19500
    },
    {
      "epoch": 0.5,
      "learning_rate": 9.993533002557585e-05,
      "loss": 3.366,
      "step": 20000
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.99319718604417e-05,
      "loss": 3.2581,
      "step": 20500
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.992852875657746e-05,
      "loss": 3.3302,
      "step": 21000
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.992500071984017e-05,
      "loss": 3.334,
      "step": 21500
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.992138775623132e-05,
      "loss": 3.3146,
      "step": 22000
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.991768987189688e-05,
      "loss": 3.3315,
      "step": 22500
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.991390707312733e-05,
      "loss": 3.3853,
      "step": 23000
    },
    {
      "epoch": 0.59,
      "learning_rate": 9.991003936635747e-05,
      "loss": 3.3447,
      "step": 23500
    },
    {
      "epoch": 0.6,
      "learning_rate": 9.990608675816668e-05,
      "loss": 3.1906,
      "step": 24000
    },
    {
      "epoch": 0.61,
      "learning_rate": 9.990204925527867e-05,
      "loss": 3.3639,
      "step": 24500
    },
    {
      "epoch": 0.62,
      "learning_rate": 9.989792686456158e-05,
      "loss": 3.2723,
      "step": 25000
    },
    {
      "epoch": 0.63,
      "learning_rate": 9.989371959302797e-05,
      "loss": 3.2156,
      "step": 25500
    },
    {
      "epoch": 0.65,
      "learning_rate": 9.988942744783481e-05,
      "loss": 3.3264,
      "step": 26000
    },
    {
      "epoch": 0.66,
      "learning_rate": 9.988505043628337e-05,
      "loss": 3.2336,
      "step": 26500
    },
    {
      "epoch": 0.67,
      "learning_rate": 9.98805885658194e-05,
      "loss": 3.2806,
      "step": 27000
    },
    {
      "epoch": 0.68,
      "learning_rate": 9.98760418440329e-05,
      "loss": 3.3251,
      "step": 27500
    },
    {
      "epoch": 0.7,
      "learning_rate": 9.987141027865825e-05,
      "loss": 3.2188,
      "step": 28000
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.986669387757414e-05,
      "loss": 3.2981,
      "step": 28500
    },
    {
      "epoch": 0.72,
      "learning_rate": 9.986189264880364e-05,
      "loss": 3.3023,
      "step": 29000
    },
    {
      "epoch": 0.73,
      "learning_rate": 9.985700660051403e-05,
      "loss": 3.3271,
      "step": 29500
    },
    {
      "epoch": 0.75,
      "learning_rate": 9.985203574101691e-05,
      "loss": 3.2955,
      "step": 30000
    },
    {
      "epoch": 0.76,
      "learning_rate": 9.984698007876816e-05,
      "loss": 3.3756,
      "step": 30500
    },
    {
      "epoch": 0.77,
      "learning_rate": 9.984183962236792e-05,
      "loss": 3.2936,
      "step": 31000
    },
    {
      "epoch": 0.78,
      "learning_rate": 9.983661438056056e-05,
      "loss": 3.3248,
      "step": 31500
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.983130436223469e-05,
      "loss": 3.2569,
      "step": 32000
    },
    {
      "epoch": 0.81,
      "learning_rate": 9.98259095764231e-05,
      "loss": 3.3616,
      "step": 32500
    },
    {
      "epoch": 0.82,
      "learning_rate": 9.982043003230282e-05,
      "loss": 3.2892,
      "step": 33000
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.981486573919504e-05,
      "loss": 3.2331,
      "step": 33500
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.98092167065651e-05,
      "loss": 3.3242,
      "step": 34000
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.980348294402255e-05,
      "loss": 3.3123,
      "step": 34500
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.9797664461321e-05,
      "loss": 3.2869,
      "step": 35000
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.979176126835821e-05,
      "loss": 3.2566,
      "step": 35500
    },
    {
      "epoch": 0.9,
      "learning_rate": 9.978577337517603e-05,
      "loss": 3.3036,
      "step": 36000
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.977970079196041e-05,
      "loss": 3.299,
      "step": 36500
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.977354352904136e-05,
      "loss": 3.31,
      "step": 37000
    },
    {
      "epoch": 0.93,
      "learning_rate": 9.976730159689292e-05,
      "loss": 3.2459,
      "step": 37500
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.976097500613318e-05,
      "loss": 3.3162,
      "step": 38000
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.975456376752424e-05,
      "loss": 3.3056,
      "step": 38500
    },
    {
      "epoch": 0.97,
      "learning_rate": 9.974806789197216e-05,
      "loss": 3.2404,
      "step": 39000
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.974148739052703e-05,
      "loss": 3.2376,
      "step": 39500
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.973482227438287e-05,
      "loss": 3.356,
      "step": 40000
    },
    {
      "epoch": 1.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 3.1455512046813965,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 4569600,
      "eval_runtime": 8741.384,
      "eval_samples_per_second": 1.021,
      "eval_steps_per_second": 0.511,
      "eval_translation_length": 4569600,
      "step": 40162
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.972807255487761e-05,
      "loss": 3.2504,
      "step": 40500
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.972123824349316e-05,
      "loss": 3.23,
      "step": 41000
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.971431935185526e-05,
      "loss": 3.1975,
      "step": 41500
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.970731589173359e-05,
      "loss": 3.2147,
      "step": 42000
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.970022787504163e-05,
      "loss": 3.1061,
      "step": 42500
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.969305531383673e-05,
      "loss": 3.1693,
      "step": 43000
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.968579822032009e-05,
      "loss": 3.1406,
      "step": 43500
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.967845660683664e-05,
      "loss": 3.28,
      "step": 44000
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.967103048587511e-05,
      "loss": 3.1341,
      "step": 44500
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.966351987006803e-05,
      "loss": 3.1911,
      "step": 45000
    },
    {
      "epoch": 1.13,
      "learning_rate": 9.965592477219158e-05,
      "loss": 3.2183,
      "step": 45500
    },
    {
      "epoch": 1.15,
      "learning_rate": 9.964824520516576e-05,
      "loss": 3.1452,
      "step": 46000
    },
    {
      "epoch": 1.16,
      "learning_rate": 9.964048118205414e-05,
      "loss": 3.2294,
      "step": 46500
    },
    {
      "epoch": 1.17,
      "learning_rate": 9.963263271606403e-05,
      "loss": 3.2148,
      "step": 47000
    },
    {
      "epoch": 1.18,
      "learning_rate": 9.962469982054638e-05,
      "loss": 3.2715,
      "step": 47500
    },
    {
      "epoch": 1.2,
      "learning_rate": 9.961668250899575e-05,
      "loss": 3.1949,
      "step": 48000
    },
    {
      "epoch": 1.21,
      "learning_rate": 9.96085807950503e-05,
      "loss": 3.1926,
      "step": 48500
    },
    {
      "epoch": 1.22,
      "learning_rate": 9.960039469249177e-05,
      "loss": 3.2328,
      "step": 49000
    },
    {
      "epoch": 1.23,
      "learning_rate": 9.959212421524542e-05,
      "loss": 3.121,
      "step": 49500
    },
    {
      "epoch": 1.24,
      "learning_rate": 9.95837693773801e-05,
      "loss": 3.1933,
      "step": 50000
    },
    {
      "epoch": 1.26,
      "learning_rate": 9.957533019310813e-05,
      "loss": 3.1807,
      "step": 50500
    },
    {
      "epoch": 1.27,
      "learning_rate": 9.956680667678531e-05,
      "loss": 3.2696,
      "step": 51000
    },
    {
      "epoch": 1.28,
      "learning_rate": 9.955819884291088e-05,
      "loss": 3.1498,
      "step": 51500
    },
    {
      "epoch": 1.29,
      "learning_rate": 9.954950670612758e-05,
      "loss": 3.1895,
      "step": 52000
    },
    {
      "epoch": 1.31,
      "learning_rate": 9.954073028122147e-05,
      "loss": 3.2206,
      "step": 52500
    },
    {
      "epoch": 1.32,
      "learning_rate": 9.953186958312204e-05,
      "loss": 3.1473,
      "step": 53000
    },
    {
      "epoch": 1.33,
      "learning_rate": 9.952292462690212e-05,
      "loss": 3.2062,
      "step": 53500
    },
    {
      "epoch": 1.34,
      "learning_rate": 9.951389542777789e-05,
      "loss": 3.2043,
      "step": 54000
    },
    {
      "epoch": 1.36,
      "learning_rate": 9.95047820011088e-05,
      "loss": 3.1293,
      "step": 54500
    },
    {
      "epoch": 1.37,
      "learning_rate": 9.949558436239762e-05,
      "loss": 3.2194,
      "step": 55000
    },
    {
      "epoch": 1.38,
      "learning_rate": 9.948630252729036e-05,
      "loss": 3.2101,
      "step": 55500
    },
    {
      "epoch": 1.39,
      "learning_rate": 9.947693651157621e-05,
      "loss": 3.2321,
      "step": 56000
    },
    {
      "epoch": 1.41,
      "learning_rate": 9.946748633118766e-05,
      "loss": 3.2132,
      "step": 56500
    },
    {
      "epoch": 1.42,
      "learning_rate": 9.945795200220022e-05,
      "loss": 3.2587,
      "step": 57000
    },
    {
      "epoch": 1.43,
      "learning_rate": 9.944833354083273e-05,
      "loss": 3.1798,
      "step": 57500
    },
    {
      "epoch": 1.44,
      "learning_rate": 9.943863096344698e-05,
      "loss": 3.2519,
      "step": 58000
    },
    {
      "epoch": 1.46,
      "learning_rate": 9.942884428654794e-05,
      "loss": 3.1065,
      "step": 58500
    },
    {
      "epoch": 1.47,
      "learning_rate": 9.941897352678362e-05,
      "loss": 3.3128,
      "step": 59000
    },
    {
      "epoch": 1.48,
      "learning_rate": 9.940901870094506e-05,
      "loss": 3.2352,
      "step": 59500
    },
    {
      "epoch": 1.49,
      "learning_rate": 9.939897982596631e-05,
      "loss": 3.1773,
      "step": 60000
    },
    {
      "epoch": 1.51,
      "learning_rate": 9.938885691892437e-05,
      "loss": 3.2472,
      "step": 60500
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.937864999703925e-05,
      "loss": 3.0983,
      "step": 61000
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.936835907767378e-05,
      "loss": 3.2046,
      "step": 61500
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.935798417833376e-05,
      "loss": 3.1239,
      "step": 62000
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.934752531666782e-05,
      "loss": 3.2518,
      "step": 62500
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.933698251046739e-05,
      "loss": 3.2518,
      "step": 63000
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.932635577766676e-05,
      "loss": 3.0939,
      "step": 63500
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.931564513634291e-05,
      "loss": 3.2243,
      "step": 64000
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.930485060471562e-05,
      "loss": 3.196,
      "step": 64500
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.929397220114736e-05,
      "loss": 3.2016,
      "step": 65000
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.928300994414321e-05,
      "loss": 3.1955,
      "step": 65500
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.9271963852351e-05,
      "loss": 3.2093,
      "step": 66000
    },
    {
      "epoch": 1.66,
      "learning_rate": 9.92608339445611e-05,
      "loss": 3.2283,
      "step": 66500
    },
    {
      "epoch": 1.67,
      "learning_rate": 9.924962023970646e-05,
      "loss": 3.2368,
      "step": 67000
    },
    {
      "epoch": 1.68,
      "learning_rate": 9.92383227568626e-05,
      "loss": 3.1782,
      "step": 67500
    },
    {
      "epoch": 1.69,
      "learning_rate": 9.922694151524756e-05,
      "loss": 3.1762,
      "step": 68000
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.921547653422182e-05,
      "loss": 3.2227,
      "step": 68500
    },
    {
      "epoch": 1.72,
      "learning_rate": 9.920392783328834e-05,
      "loss": 3.1744,
      "step": 69000
    },
    {
      "epoch": 1.73,
      "learning_rate": 9.91922954320925e-05,
      "loss": 3.1868,
      "step": 69500
    },
    {
      "epoch": 1.74,
      "learning_rate": 9.918057935042204e-05,
      "loss": 3.1313,
      "step": 70000
    },
    {
      "epoch": 1.76,
      "learning_rate": 9.916877960820705e-05,
      "loss": 3.1623,
      "step": 70500
    },
    {
      "epoch": 1.77,
      "learning_rate": 9.915689622551996e-05,
      "loss": 3.0594,
      "step": 71000
    },
    {
      "epoch": 1.78,
      "learning_rate": 9.914492922257546e-05,
      "loss": 3.2163,
      "step": 71500
    },
    {
      "epoch": 1.79,
      "learning_rate": 9.913287861973049e-05,
      "loss": 3.0811,
      "step": 72000
    },
    {
      "epoch": 1.81,
      "learning_rate": 9.912074443748416e-05,
      "loss": 3.2226,
      "step": 72500
    },
    {
      "epoch": 1.82,
      "learning_rate": 9.910852669647785e-05,
      "loss": 3.2876,
      "step": 73000
    },
    {
      "epoch": 1.83,
      "learning_rate": 9.909622541749499e-05,
      "loss": 3.2285,
      "step": 73500
    },
    {
      "epoch": 1.84,
      "learning_rate": 9.908384062146118e-05,
      "loss": 3.1274,
      "step": 74000
    },
    {
      "epoch": 1.85,
      "learning_rate": 9.907137232944404e-05,
      "loss": 3.1894,
      "step": 74500
    },
    {
      "epoch": 1.87,
      "learning_rate": 9.905882056265323e-05,
      "loss": 3.1468,
      "step": 75000
    },
    {
      "epoch": 1.88,
      "learning_rate": 9.904618534244044e-05,
      "loss": 3.2397,
      "step": 75500
    },
    {
      "epoch": 1.89,
      "learning_rate": 9.903346669029932e-05,
      "loss": 3.0135,
      "step": 76000
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.90206646278654e-05,
      "loss": 3.2206,
      "step": 76500
    },
    {
      "epoch": 1.92,
      "learning_rate": 9.900777917691615e-05,
      "loss": 3.1868,
      "step": 77000
    },
    {
      "epoch": 1.93,
      "learning_rate": 9.899481035937086e-05,
      "loss": 3.2184,
      "step": 77500
    },
    {
      "epoch": 1.94,
      "learning_rate": 9.898175819729063e-05,
      "loss": 3.1739,
      "step": 78000
    },
    {
      "epoch": 1.95,
      "learning_rate": 9.896862271287839e-05,
      "loss": 3.2227,
      "step": 78500
    },
    {
      "epoch": 1.97,
      "learning_rate": 9.895540392847874e-05,
      "loss": 3.2236,
      "step": 79000
    },
    {
      "epoch": 1.98,
      "learning_rate": 9.8942101866578e-05,
      "loss": 3.1321,
      "step": 79500
    },
    {
      "epoch": 1.99,
      "learning_rate": 9.892871654980418e-05,
      "loss": 3.1849,
      "step": 80000
    },
    {
      "epoch": 2.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 3.0774757862091064,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 4569600,
      "eval_runtime": 8605.765,
      "eval_samples_per_second": 1.037,
      "eval_steps_per_second": 0.519,
      "eval_translation_length": 4569600,
      "step": 80324
    }
  ],
  "logging_steps": 500,
  "max_steps": 1204860,
  "num_train_epochs": 30,
  "save_steps": 1000,
  "total_flos": 1.3785697922643395e+18,
  "trial_name": null,
  "trial_params": null
}