{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 35889,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0009860681545877568,
      "loss": 6.095,
      "step": 500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0009721363091755134,
      "loss": 2.9616,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0009582044637632701,
      "loss": 2.666,
      "step": 1500
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0009442726183510269,
      "loss": 2.5328,
      "step": 2000
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009303407729387835,
      "loss": 2.497,
      "step": 2500
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0009164089275265401,
      "loss": 2.4232,
      "step": 3000
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0009024770821142969,
      "loss": 2.4132,
      "step": 3500
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0008885452367020536,
      "loss": 2.3761,
      "step": 4000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0008746133912898102,
      "loss": 2.3447,
      "step": 4500
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000860681545877567,
      "loss": 2.2711,
      "step": 5000
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0008467497004653236,
      "loss": 2.2602,
      "step": 5500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0008328178550530803,
      "loss": 2.2645,
      "step": 6000
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0008188860096408371,
      "loss": 2.2384,
      "step": 6500
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0008049541642285937,
      "loss": 2.2474,
      "step": 7000
    },
    {
      "epoch": 0.2,
      "eval_gen_len": 91.9,
      "eval_loss": 1.914839744567871,
      "eval_rouge1": 31.9324,
      "eval_rouge2": 8.9596,
      "eval_rougeL": 18.5991,
      "eval_rougeLsum": 26.8462,
      "eval_runtime": 20609.4374,
      "eval_samples_per_second": 0.649,
      "step": 7000
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0007910223188163504,
      "loss": 2.2039,
      "step": 7500
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0007770904734041071,
      "loss": 2.189,
      "step": 8000
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0007631586279918639,
      "loss": 2.1961,
      "step": 8500
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0007492267825796205,
      "loss": 2.1764,
      "step": 9000
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0007352949371673772,
      "loss": 2.1777,
      "step": 9500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0007213630917551339,
      "loss": 2.1412,
      "step": 10000
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0007074312463428905,
      "loss": 2.1669,
      "step": 10500
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0006934994009306474,
      "loss": 2.1426,
      "step": 11000
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000679567555518404,
      "loss": 2.1428,
      "step": 11500
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0006656357101061606,
      "loss": 2.1108,
      "step": 12000
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0006517038646939174,
      "loss": 2.0903,
      "step": 12500
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000637772019281674,
      "loss": 2.1057,
      "step": 13000
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0006238401738694308,
      "loss": 2.0874,
      "step": 13500
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0006099083284571875,
      "loss": 2.0877,
      "step": 14000
    },
    {
      "epoch": 0.39,
      "eval_gen_len": 99.3,
      "eval_loss": 1.8038697242736816,
      "eval_rouge1": 31.4652,
      "eval_rouge2": 8.6423,
      "eval_rougeL": 18.1808,
      "eval_rougeLsum": 26.2653,
      "eval_runtime": 21262.825,
      "eval_samples_per_second": 0.629,
      "step": 14000
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005959764830449441,
      "loss": 2.0903,
      "step": 14500
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005820446376327009,
      "loss": 2.0628,
      "step": 15000
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005681127922204575,
      "loss": 2.0909,
      "step": 15500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005541809468082142,
      "loss": 2.0258,
      "step": 16000
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000540249101395971,
      "loss": 2.0156,
      "step": 16500
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005263172559837276,
      "loss": 2.0282,
      "step": 17000
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005123854105714843,
      "loss": 2.0559,
      "step": 17500
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000498453565159241,
      "loss": 2.0603,
      "step": 18000
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0004845217197469977,
      "loss": 2.0077,
      "step": 18500
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0004705898743347544,
      "loss": 2.0119,
      "step": 19000
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00045665802892251106,
      "loss": 1.9855,
      "step": 19500
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0004427261835102678,
      "loss": 2.0089,
      "step": 20000
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0004287943380980245,
      "loss": 2.0029,
      "step": 20500
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00041486249268578117,
      "loss": 1.9773,
      "step": 21000
    },
    {
      "epoch": 0.59,
      "eval_gen_len": 101.6,
      "eval_loss": 1.73397696018219,
      "eval_rouge1": 31.1574,
      "eval_rouge2": 8.645,
      "eval_rougeL": 18.096,
      "eval_rougeLsum": 25.9822,
      "eval_runtime": 21624.4917,
      "eval_samples_per_second": 0.618,
      "step": 21000
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00040093064727353785,
      "loss": 1.9632,
      "step": 21500
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00038699880186129454,
      "loss": 1.9768,
      "step": 22000
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003730669564490513,
      "loss": 1.9755,
      "step": 22500
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00035913511103680796,
      "loss": 2.0125,
      "step": 23000
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003452032656245646,
      "loss": 1.9427,
      "step": 23500
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003312714202123213,
      "loss": 1.9776,
      "step": 24000
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000317339574800078,
      "loss": 1.9966,
      "step": 24500
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00030340772938783475,
      "loss": 1.9814,
      "step": 25000
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00028947588397559143,
      "loss": 1.9585,
      "step": 25500
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00027554403856334806,
      "loss": 1.9668,
      "step": 26000
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002616121931511048,
      "loss": 1.9564,
      "step": 26500
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002476803477388615,
      "loss": 1.9231,
      "step": 27000
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00023374850232661817,
      "loss": 1.9078,
      "step": 27500
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00021981665691437488,
      "loss": 1.9032,
      "step": 28000
    },
    {
      "epoch": 0.78,
      "eval_gen_len": 106.8,
      "eval_loss": 1.6808093786239624,
      "eval_rouge1": 31.4328,
      "eval_rouge2": 8.6241,
      "eval_rougeL": 18.0718,
      "eval_rougeLsum": 26.0718,
      "eval_runtime": 21979.649,
      "eval_samples_per_second": 0.608,
      "step": 28000
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00020588481150213156,
      "loss": 1.931,
      "step": 28500
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019195296608988827,
      "loss": 1.9416,
      "step": 29000
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00017802112067764498,
      "loss": 1.963,
      "step": 29500
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016408927526540167,
      "loss": 1.9066,
      "step": 30000
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00015015742985315835,
      "loss": 1.9583,
      "step": 30500
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00013622558444091503,
      "loss": 1.8948,
      "step": 31000
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00012229373902867174,
      "loss": 1.9424,
      "step": 31500
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00010836189361642844,
      "loss": 1.9082,
      "step": 32000
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.443004820418513e-05,
      "loss": 1.9195,
      "step": 32500
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.049820279194182e-05,
      "loss": 1.8821,
      "step": 33000
    },
    {
      "epoch": 0.93,
      "learning_rate": 6.656635737969852e-05,
      "loss": 1.9194,
      "step": 33500
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.263451196745521e-05,
      "loss": 1.902,
      "step": 34000
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.87026665552119e-05,
      "loss": 1.9154,
      "step": 34500
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.4770821142968598e-05,
      "loss": 1.9181,
      "step": 35000
    },
    {
      "epoch": 0.98,
      "eval_gen_len": 107.9,
      "eval_loss": 1.6517904996871948,
      "eval_rouge1": 31.4185,
      "eval_rouge2": 8.601,
      "eval_rougeL": 17.9686,
      "eval_rougeLsum": 26.0844,
      "eval_runtime": 21981.6496,
      "eval_samples_per_second": 0.608,
      "step": 35000
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0838975730725292e-05,
      "loss": 1.9275,
      "step": 35500
    },
    {
      "epoch": 1.0,
      "step": 35889,
      "total_flos": 1069022126774016000,
      "train_runtime": 160064.9582,
      "train_samples_per_second": 0.224
    }
  ],
  "max_steps": 35889,
  "num_train_epochs": 1,
  "total_flos": 1069022126774016000,
  "trial_name": null,
  "trial_params": null
}