{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "global_step": 67130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.000297765529569492,
      "loss": 4.2198,
      "step": 500
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00029553105913898405,
      "loss": 3.702,
      "step": 1000
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00029329658870847603,
      "loss": 3.5122,
      "step": 1500
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00029106211827796807,
      "loss": 3.4147,
      "step": 2000
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002888276478474601,
      "loss": 3.3907,
      "step": 2500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002865931774169522,
      "loss": 3.3163,
      "step": 3000
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002843587069864442,
      "loss": 3.253,
      "step": 3500
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002821242365559362,
      "loss": 3.248,
      "step": 4000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00027988976612542825,
      "loss": 3.2532,
      "step": 4500
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002776552956949203,
      "loss": 3.2179,
      "step": 5000
    },
    {
      "epoch": 0.74,
      "eval_gen_len": 13.5337,
      "eval_loss": 2.7812678813934326,
      "eval_rouge1": 25.8006,
      "eval_rouge2": 9.3551,
      "eval_rougeL": 23.386,
      "eval_rougeLsum": 23.5287,
      "eval_runtime": 531.59,
      "eval_samples_per_second": 18.811,
      "eval_steps_per_second": 2.351,
      "step": 5000
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002754208252644123,
      "loss": 3.1697,
      "step": 5500
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002731863548339043,
      "loss": 3.1744,
      "step": 6000
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00027095188440339634,
      "loss": 3.1526,
      "step": 6500
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002687174139728884,
      "loss": 3.0155,
      "step": 7000
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002664829435423804,
      "loss": 2.9585,
      "step": 7500
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00026424847311187245,
      "loss": 2.9227,
      "step": 8000
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002620140026813645,
      "loss": 2.9469,
      "step": 8500
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00025977953225085653,
      "loss": 2.9259,
      "step": 9000
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00025754506182034857,
      "loss": 2.9517,
      "step": 9500
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002553105913898406,
      "loss": 2.9248,
      "step": 10000
    },
    {
      "epoch": 1.49,
      "eval_gen_len": 13.243,
      "eval_loss": 2.691446542739868,
      "eval_rouge1": 27.0409,
      "eval_rouge2": 10.0228,
      "eval_rougeL": 24.4581,
      "eval_rougeLsum": 24.6197,
      "eval_runtime": 528.3278,
      "eval_samples_per_second": 18.928,
      "eval_steps_per_second": 2.366,
      "step": 10000
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002530761209593326,
      "loss": 2.9173,
      "step": 10500
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002508416505288246,
      "loss": 2.923,
      "step": 11000
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00024860718009831666,
      "loss": 2.9318,
      "step": 11500
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002463727096678087,
      "loss": 2.901,
      "step": 12000
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00024413823923730073,
      "loss": 2.8678,
      "step": 12500
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00024190376880679277,
      "loss": 2.8576,
      "step": 13000
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0002396692983762848,
      "loss": 2.8734,
      "step": 13500
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00023743482794577684,
      "loss": 2.6712,
      "step": 14000
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00023520035751526885,
      "loss": 2.6779,
      "step": 14500
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0002329658870847609,
      "loss": 2.6813,
      "step": 15000
    },
    {
      "epoch": 2.23,
      "eval_gen_len": 14.3052,
      "eval_loss": 2.6461832523345947,
      "eval_rouge1": 27.5333,
      "eval_rouge2": 10.3641,
      "eval_rougeL": 24.8696,
      "eval_rougeLsum": 25.0564,
      "eval_runtime": 527.1253,
      "eval_samples_per_second": 18.971,
      "eval_steps_per_second": 2.371,
      "step": 15000
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00023073141665425293,
      "loss": 2.6964,
      "step": 15500
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00022849694622374496,
      "loss": 2.6816,
      "step": 16000
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.000226262475793237,
      "loss": 2.669,
      "step": 16500
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.000224028005362729,
      "loss": 2.6871,
      "step": 17000
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00022179353493222105,
      "loss": 2.6783,
      "step": 17500
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.00021955906450171308,
      "loss": 2.7131,
      "step": 18000
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.00021732459407120512,
      "loss": 2.7029,
      "step": 18500
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.00021509012364069713,
      "loss": 2.7081,
      "step": 19000
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.00021285565321018917,
      "loss": 2.6989,
      "step": 19500
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0002106211827796812,
      "loss": 2.691,
      "step": 20000
    },
    {
      "epoch": 2.98,
      "eval_gen_len": 14.5279,
      "eval_loss": 2.6205477714538574,
      "eval_rouge1": 28.3681,
      "eval_rouge2": 10.8961,
      "eval_rougeL": 25.5144,
      "eval_rougeLsum": 25.722,
      "eval_runtime": 530.0749,
      "eval_samples_per_second": 18.865,
      "eval_steps_per_second": 2.358,
      "step": 20000
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.00020838671234917324,
      "loss": 2.5377,
      "step": 20500
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.00020615224191866528,
      "loss": 2.4832,
      "step": 21000
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0002039177714881573,
      "loss": 2.4958,
      "step": 21500
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.00020168330105764932,
      "loss": 2.4949,
      "step": 22000
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.00019944883062714136,
      "loss": 2.4796,
      "step": 22500
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0001972143601966334,
      "loss": 2.5323,
      "step": 23000
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0001949798897661254,
      "loss": 2.515,
      "step": 23500
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.00019274541933561744,
      "loss": 2.5291,
      "step": 24000
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.00019051094890510948,
      "loss": 2.5206,
      "step": 24500
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.00018827647847460152,
      "loss": 2.5127,
      "step": 25000
    },
    {
      "epoch": 3.72,
      "eval_gen_len": 14.0721,
      "eval_loss": 2.6042990684509277,
      "eval_rouge1": 28.5979,
      "eval_rouge2": 11.0477,
      "eval_rougeL": 25.759,
      "eval_rougeLsum": 25.9605,
      "eval_runtime": 523.9369,
      "eval_samples_per_second": 19.086,
      "eval_steps_per_second": 2.386,
      "step": 25000
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.00018604200804409355,
      "loss": 2.5203,
      "step": 25500
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.00018380753761358556,
      "loss": 2.5064,
      "step": 26000
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.0001815730671830776,
      "loss": 2.4892,
      "step": 26500
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.00017933859675256964,
      "loss": 2.4728,
      "step": 27000
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.00017710412632206167,
      "loss": 2.319,
      "step": 27500
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.00017486965589155368,
      "loss": 2.3135,
      "step": 28000
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.00017263518546104572,
      "loss": 2.339,
      "step": 28500
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.00017040071503053776,
      "loss": 2.3818,
      "step": 29000
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.0001681662446000298,
      "loss": 2.3551,
      "step": 29500
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.00016593177416952183,
      "loss": 2.3331,
      "step": 30000
    },
    {
      "epoch": 4.47,
      "eval_gen_len": 14.4519,
      "eval_loss": 2.6282742023468018,
      "eval_rouge1": 28.9106,
      "eval_rouge2": 11.3727,
      "eval_rougeL": 25.9338,
      "eval_rougeLsum": 26.1387,
      "eval_runtime": 544.5243,
      "eval_samples_per_second": 18.365,
      "eval_steps_per_second": 2.296,
      "step": 30000
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.00016369730373901384,
      "loss": 2.3632,
      "step": 30500
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.00016146283330850588,
      "loss": 2.3592,
      "step": 31000
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.00015922836287799791,
      "loss": 2.3468,
      "step": 31500
    },
    {
      "epoch": 4.77,
      "learning_rate": 0.00015699389244748995,
      "loss": 2.361,
      "step": 32000
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.00015475942201698196,
      "loss": 2.3444,
      "step": 32500
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.000152524951586474,
      "loss": 2.3435,
      "step": 33000
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.00015029048115596604,
      "loss": 2.3755,
      "step": 33500
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.00014805601072545804,
      "loss": 2.2407,
      "step": 34000
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.00014582154029495008,
      "loss": 2.2036,
      "step": 34500
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.00014358706986444212,
      "loss": 2.2034,
      "step": 35000
    },
    {
      "epoch": 5.21,
      "eval_gen_len": 13.8715,
      "eval_loss": 2.6400413513183594,
      "eval_rouge1": 29.099,
      "eval_rouge2": 11.2376,
      "eval_rougeL": 26.1221,
      "eval_rougeLsum": 26.3568,
      "eval_runtime": 529.9312,
      "eval_samples_per_second": 18.87,
      "eval_steps_per_second": 2.359,
      "step": 35000
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.00014135259943393416,
      "loss": 2.1988,
      "step": 35500
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.0001391181290034262,
      "loss": 2.2228,
      "step": 36000
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.0001368836585729182,
      "loss": 2.2078,
      "step": 36500
    },
    {
      "epoch": 5.51,
      "learning_rate": 0.00013464918814241024,
      "loss": 2.2399,
      "step": 37000
    },
    {
      "epoch": 5.59,
      "learning_rate": 0.00013241471771190228,
      "loss": 2.2287,
      "step": 37500
    },
    {
      "epoch": 5.66,
      "learning_rate": 0.0001301802472813943,
      "loss": 2.2174,
      "step": 38000
    },
    {
      "epoch": 5.74,
      "learning_rate": 0.00012794577685088632,
      "loss": 2.2216,
      "step": 38500
    },
    {
      "epoch": 5.81,
      "learning_rate": 0.00012571130642037836,
      "loss": 2.2196,
      "step": 39000
    },
    {
      "epoch": 5.88,
      "learning_rate": 0.00012347683598987037,
      "loss": 2.2432,
      "step": 39500
    },
    {
      "epoch": 5.96,
      "learning_rate": 0.00012124236555936242,
      "loss": 2.2137,
      "step": 40000
    },
    {
      "epoch": 5.96,
      "eval_gen_len": 14.5981,
      "eval_loss": 2.634021759033203,
      "eval_rouge1": 29.2641,
      "eval_rouge2": 11.3565,
      "eval_rougeL": 26.2012,
      "eval_rougeLsum": 26.4214,
      "eval_runtime": 532.2281,
      "eval_samples_per_second": 18.789,
      "eval_steps_per_second": 2.349,
      "step": 40000
    },
    {
      "epoch": 6.03,
      "learning_rate": 0.00011900789512885446,
      "loss": 2.1445,
      "step": 40500
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.00011677342469834648,
      "loss": 2.0664,
      "step": 41000
    },
    {
      "epoch": 6.18,
      "learning_rate": 0.00011453895426783852,
      "loss": 2.094,
      "step": 41500
    },
    {
      "epoch": 6.26,
      "learning_rate": 0.00011230448383733054,
      "loss": 2.1048,
      "step": 42000
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.00011007001340682258,
      "loss": 2.1001,
      "step": 42500
    },
    {
      "epoch": 6.41,
      "learning_rate": 0.0001078355429763146,
      "loss": 2.1141,
      "step": 43000
    },
    {
      "epoch": 6.48,
      "learning_rate": 0.00010560107254580664,
      "loss": 2.0866,
      "step": 43500
    },
    {
      "epoch": 6.55,
      "learning_rate": 0.00010336660211529866,
      "loss": 2.0916,
      "step": 44000
    },
    {
      "epoch": 6.63,
      "learning_rate": 0.0001011321316847907,
      "loss": 2.1056,
      "step": 44500
    },
    {
      "epoch": 6.7,
      "learning_rate": 9.889766125428273e-05,
      "loss": 2.1104,
      "step": 45000
    },
    {
      "epoch": 6.7,
      "eval_gen_len": 13.888,
      "eval_loss": 2.6362199783325195,
      "eval_rouge1": 29.6204,
      "eval_rouge2": 11.6807,
      "eval_rougeL": 26.5976,
      "eval_rougeLsum": 26.8261,
      "eval_runtime": 537.398,
      "eval_samples_per_second": 18.608,
      "eval_steps_per_second": 2.326,
      "step": 45000
    },
    {
      "epoch": 6.78,
      "learning_rate": 9.666319082377476e-05,
      "loss": 2.1206,
      "step": 45500
    },
    {
      "epoch": 6.85,
      "learning_rate": 9.44287203932668e-05,
      "loss": 2.1124,
      "step": 46000
    },
    {
      "epoch": 6.93,
      "learning_rate": 9.219424996275882e-05,
      "loss": 2.1211,
      "step": 46500
    },
    {
      "epoch": 7.0,
      "learning_rate": 8.995977953225085e-05,
      "loss": 2.1063,
      "step": 47000
    },
    {
      "epoch": 7.08,
      "learning_rate": 8.772530910174288e-05,
      "loss": 1.9698,
      "step": 47500
    },
    {
      "epoch": 7.15,
      "learning_rate": 8.549083867123491e-05,
      "loss": 1.9693,
      "step": 48000
    },
    {
      "epoch": 7.22,
      "learning_rate": 8.325636824072694e-05,
      "loss": 2.0098,
      "step": 48500
    },
    {
      "epoch": 7.3,
      "learning_rate": 8.102189781021897e-05,
      "loss": 1.9976,
      "step": 49000
    },
    {
      "epoch": 7.37,
      "learning_rate": 7.8787427379711e-05,
      "loss": 2.0059,
      "step": 49500
    },
    {
      "epoch": 7.45,
      "learning_rate": 7.655295694920303e-05,
      "loss": 2.003,
      "step": 50000
    },
    {
      "epoch": 7.45,
      "eval_gen_len": 14.2246,
      "eval_loss": 2.6541028022766113,
      "eval_rouge1": 29.5679,
      "eval_rouge2": 11.6334,
      "eval_rougeL": 26.5095,
      "eval_rougeLsum": 26.7418,
      "eval_runtime": 534.455,
      "eval_samples_per_second": 18.711,
      "eval_steps_per_second": 2.339,
      "step": 50000
    },
    {
      "epoch": 7.52,
      "learning_rate": 7.431848651869506e-05,
      "loss": 1.9752,
      "step": 50500
    },
    {
      "epoch": 7.6,
      "learning_rate": 7.20840160881871e-05,
      "loss": 2.0409,
      "step": 51000
    },
    {
      "epoch": 7.67,
      "learning_rate": 6.984954565767912e-05,
      "loss": 2.0181,
      "step": 51500
    },
    {
      "epoch": 7.75,
      "learning_rate": 6.761507522717115e-05,
      "loss": 1.9967,
      "step": 52000
    },
    {
      "epoch": 7.82,
      "learning_rate": 6.538060479666319e-05,
      "loss": 1.9883,
      "step": 52500
    },
    {
      "epoch": 7.9,
      "learning_rate": 6.314613436615521e-05,
      "loss": 2.0096,
      "step": 53000
    },
    {
      "epoch": 7.97,
      "learning_rate": 6.091166393564725e-05,
      "loss": 2.0075,
      "step": 53500
    },
    {
      "epoch": 8.04,
      "learning_rate": 5.867719350513928e-05,
      "loss": 1.9409,
      "step": 54000
    },
    {
      "epoch": 8.12,
      "learning_rate": 5.6442723074631304e-05,
      "loss": 1.9271,
      "step": 54500
    },
    {
      "epoch": 8.19,
      "learning_rate": 5.4208252644123334e-05,
      "loss": 1.8955,
      "step": 55000
    },
    {
      "epoch": 8.19,
      "eval_gen_len": 14.3902,
      "eval_loss": 2.694044828414917,
      "eval_rouge1": 29.6748,
      "eval_rouge2": 11.5897,
      "eval_rougeL": 26.4862,
      "eval_rougeLsum": 26.7581,
      "eval_runtime": 535.4767,
      "eval_samples_per_second": 18.675,
      "eval_steps_per_second": 2.334,
      "step": 55000
    },
    {
      "epoch": 8.27,
      "learning_rate": 5.1973782213615364e-05,
      "loss": 1.9114,
      "step": 55500
    },
    {
      "epoch": 8.34,
      "learning_rate": 4.9739311783107394e-05,
      "loss": 1.9337,
      "step": 56000
    },
    {
      "epoch": 8.42,
      "learning_rate": 4.7504841352599425e-05,
      "loss": 1.9088,
      "step": 56500
    },
    {
      "epoch": 8.49,
      "learning_rate": 4.5270370922091455e-05,
      "loss": 1.9104,
      "step": 57000
    },
    {
      "epoch": 8.57,
      "learning_rate": 4.303590049158349e-05,
      "loss": 1.9167,
      "step": 57500
    },
    {
      "epoch": 8.64,
      "learning_rate": 4.080143006107552e-05,
      "loss": 1.9146,
      "step": 58000
    },
    {
      "epoch": 8.71,
      "learning_rate": 3.856695963056755e-05,
      "loss": 1.8965,
      "step": 58500
    },
    {
      "epoch": 8.79,
      "learning_rate": 3.633248920005958e-05,
      "loss": 1.9186,
      "step": 59000
    },
    {
      "epoch": 8.86,
      "learning_rate": 3.409801876955161e-05,
      "loss": 1.9153,
      "step": 59500
    },
    {
      "epoch": 8.94,
      "learning_rate": 3.186354833904364e-05,
      "loss": 1.912,
      "step": 60000
    },
    {
      "epoch": 8.94,
      "eval_gen_len": 14.3574,
      "eval_loss": 2.6882503032684326,
      "eval_rouge1": 29.7285,
      "eval_rouge2": 11.6448,
      "eval_rougeL": 26.5368,
      "eval_rougeLsum": 26.7806,
      "eval_runtime": 531.6791,
      "eval_samples_per_second": 18.808,
      "eval_steps_per_second": 2.351,
      "step": 60000
    },
    {
      "epoch": 9.01,
      "learning_rate": 2.9629077908535672e-05,
      "loss": 1.9182,
      "step": 60500
    },
    {
      "epoch": 9.09,
      "learning_rate": 2.7394607478027705e-05,
      "loss": 1.8865,
      "step": 61000
    },
    {
      "epoch": 9.16,
      "learning_rate": 2.5160137047519735e-05,
      "loss": 1.8585,
      "step": 61500
    },
    {
      "epoch": 9.24,
      "learning_rate": 2.2925666617011765e-05,
      "loss": 1.8478,
      "step": 62000
    },
    {
      "epoch": 9.31,
      "learning_rate": 2.0691196186503795e-05,
      "loss": 1.8604,
      "step": 62500
    },
    {
      "epoch": 9.38,
      "learning_rate": 1.845672575599583e-05,
      "loss": 1.8599,
      "step": 63000
    },
    {
      "epoch": 9.46,
      "learning_rate": 1.622225532548786e-05,
      "loss": 1.8661,
      "step": 63500
    },
    {
      "epoch": 9.53,
      "learning_rate": 1.3987784894979889e-05,
      "loss": 1.8651,
      "step": 64000
    },
    {
      "epoch": 9.61,
      "learning_rate": 1.1753314464471919e-05,
      "loss": 1.8657,
      "step": 64500
    },
    {
      "epoch": 9.68,
      "learning_rate": 9.518844033963949e-06,
      "loss": 1.8581,
      "step": 65000
    },
    {
      "epoch": 9.68,
      "eval_gen_len": 14.3821,
      "eval_loss": 2.687427282333374,
      "eval_rouge1": 29.7373,
      "eval_rouge2": 11.6532,
      "eval_rougeL": 26.4799,
      "eval_rougeLsum": 26.738,
      "eval_runtime": 539.441,
      "eval_samples_per_second": 18.538,
      "eval_steps_per_second": 2.317,
      "step": 65000
    },
    {
      "epoch": 9.76,
      "learning_rate": 7.284373603455981e-06,
      "loss": 1.8359,
      "step": 65500
    },
    {
      "epoch": 9.83,
      "learning_rate": 5.04990317294801e-06,
      "loss": 1.8372,
      "step": 66000
    },
    {
      "epoch": 9.91,
      "learning_rate": 2.815432742440042e-06,
      "loss": 1.8536,
      "step": 66500
    },
    {
      "epoch": 9.98,
      "learning_rate": 5.809623119320721e-07,
      "loss": 1.8537,
      "step": 67000
    },
    {
      "epoch": 10.0,
      "step": 67130,
      "total_flos": 2.0718221980336128e+17,
      "train_loss": 2.3931242498576544,
      "train_runtime": 39455.2858,
      "train_samples_per_second": 13.611,
      "train_steps_per_second": 1.701
    }
  ],
  "max_steps": 67130,
  "num_train_epochs": 10,
  "total_flos": 2.0718221980336128e+17,
  "trial_name": null,
  "trial_params": null
}