{
  "best_metric": 0.7309060096740723,
  "best_model_checkpoint": "falcon_xsum_finetuned_train/checkpoint-57991",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 57991,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.999828938973289e-05,
      "loss": 1.4588,
      "step": 500
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9996564984221692e-05,
      "loss": 1.2058,
      "step": 1000
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.999484057871049e-05,
      "loss": 1.137,
      "step": 1500
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9993116173199292e-05,
      "loss": 1.0897,
      "step": 2000
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.999139176768809e-05,
      "loss": 1.0655,
      "step": 2500
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.998966736217689e-05,
      "loss": 1.027,
      "step": 3000
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9987942956665693e-05,
      "loss": 1.001,
      "step": 3500
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.998621855115449e-05,
      "loss": 0.9981,
      "step": 4000
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9984494145643292e-05,
      "loss": 0.9752,
      "step": 4500
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.998276974013209e-05,
      "loss": 0.966,
      "step": 5000
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.998104533462089e-05,
      "loss": 0.9455,
      "step": 5500
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9979320929109693e-05,
      "loss": 0.9479,
      "step": 6000
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.997759652359849e-05,
      "loss": 0.9377,
      "step": 6500
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9975872118087292e-05,
      "loss": 0.9212,
      "step": 7000
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.997414771257609e-05,
      "loss": 0.9081,
      "step": 7500
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.997242330706489e-05,
      "loss": 0.9099,
      "step": 8000
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9970702350364713e-05,
      "loss": 0.9045,
      "step": 8500
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9968981393664535e-05,
      "loss": 0.8895,
      "step": 9000
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9967256988153336e-05,
      "loss": 0.8937,
      "step": 9500
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9965532582642134e-05,
      "loss": 0.8799,
      "step": 10000
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9963808177130936e-05,
      "loss": 0.8905,
      "step": 10500
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9962083771619737e-05,
      "loss": 0.8712,
      "step": 11000
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9960359366108535e-05,
      "loss": 0.8617,
      "step": 11500
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9958634960597337e-05,
      "loss": 0.859,
      "step": 12000
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9956910555086135e-05,
      "loss": 0.8615,
      "step": 12500
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9955186149574936e-05,
      "loss": 0.8544,
      "step": 13000
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.9953461744063737e-05,
      "loss": 0.8607,
      "step": 13500
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.995174078736356e-05,
      "loss": 0.8518,
      "step": 14000
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.995001983066338e-05,
      "loss": 0.8461,
      "step": 14500
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.994829542515218e-05,
      "loss": 0.84,
      "step": 15000
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.994657101964098e-05,
      "loss": 0.8414,
      "step": 15500
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.994484661412978e-05,
      "loss": 0.8337,
      "step": 16000
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.994312220861858e-05,
      "loss": 0.8288,
      "step": 16500
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.994139780310738e-05,
      "loss": 0.8347,
      "step": 17000
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.993967339759618e-05,
      "loss": 0.8216,
      "step": 17500
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.993794899208498e-05,
      "loss": 0.8263,
      "step": 18000
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9936228035384805e-05,
      "loss": 0.823,
      "step": 18500
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.9934503629873603e-05,
      "loss": 0.8172,
      "step": 19000
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.9932782673173425e-05,
      "loss": 0.8264,
      "step": 19500
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.9931058267662223e-05,
      "loss": 0.8127,
      "step": 20000
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.9929337310962048e-05,
      "loss": 0.8138,
      "step": 20500
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.992761290545085e-05,
      "loss": 0.8158,
      "step": 21000
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.9925888499939648e-05,
      "loss": 0.8012,
      "step": 21500
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.9924164094428446e-05,
      "loss": 0.8067,
      "step": 22000
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.9922439688917247e-05,
      "loss": 0.8007,
      "step": 22500
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.9920715283406048e-05,
      "loss": 0.8057,
      "step": 23000
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.991899087789485e-05,
      "loss": 0.8087,
      "step": 23500
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.9917266472383648e-05,
      "loss": 0.8046,
      "step": 24000
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.9915542066872446e-05,
      "loss": 0.802,
      "step": 24500
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.9913817661361247e-05,
      "loss": 0.798,
      "step": 25000
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.991209325585005e-05,
      "loss": 0.7953,
      "step": 25500
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.9910368850338846e-05,
      "loss": 0.7916,
      "step": 26000
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.9908644444827648e-05,
      "loss": 0.7985,
      "step": 26500
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.9906920039316446e-05,
      "loss": 0.7964,
      "step": 27000
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.9905195633805247e-05,
      "loss": 0.7938,
      "step": 27500
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.9903471228294045e-05,
      "loss": 0.7936,
      "step": 28000
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.990175027159387e-05,
      "loss": 0.7911,
      "step": 28500
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.9900025866082672e-05,
      "loss": 0.7822,
      "step": 29000
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.989830146057147e-05,
      "loss": 0.784,
      "step": 29500
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.9896577055060268e-05,
      "loss": 0.7843,
      "step": 30000
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.989485264954907e-05,
      "loss": 0.7844,
      "step": 30500
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.989312824403787e-05,
      "loss": 0.7849,
      "step": 31000
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.9891403838526672e-05,
      "loss": 0.7691,
      "step": 31500
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.988967943301547e-05,
      "loss": 0.7805,
      "step": 32000
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.988795847631529e-05,
      "loss": 0.7792,
      "step": 32500
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.988623407080409e-05,
      "loss": 0.7799,
      "step": 33000
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.988450966529289e-05,
      "loss": 0.7714,
      "step": 33500
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.9882785259781692e-05,
      "loss": 0.7713,
      "step": 34000
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.9881071200703558e-05,
      "loss": 0.7725,
      "step": 34500
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.987934679519236e-05,
      "loss": 0.769,
      "step": 35000
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.987762238968116e-05,
      "loss": 0.7708,
      "step": 35500
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.987589798416996e-05,
      "loss": 0.761,
      "step": 36000
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.987417357865876e-05,
      "loss": 0.7642,
      "step": 36500
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.9872449173147558e-05,
      "loss": 0.7598,
      "step": 37000
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.9870724767636356e-05,
      "loss": 0.7639,
      "step": 37500
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.9869000362125158e-05,
      "loss": 0.7662,
      "step": 38000
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.986727595661396e-05,
      "loss": 0.7724,
      "step": 38500
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.986555155110276e-05,
      "loss": 0.7658,
      "step": 39000
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.986382714559156e-05,
      "loss": 0.7525,
      "step": 39500
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.9862102740080356e-05,
      "loss": 0.76,
      "step": 40000
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.9860378334569158e-05,
      "loss": 0.7632,
      "step": 40500
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.9858657377868983e-05,
      "loss": 0.7544,
      "step": 41000
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.985693297235778e-05,
      "loss": 0.7561,
      "step": 41500
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.9855208566846582e-05,
      "loss": 0.7553,
      "step": 42000
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.985348416133538e-05,
      "loss": 0.752,
      "step": 42500
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.9851759755824182e-05,
      "loss": 0.7571,
      "step": 43000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.9850035350312983e-05,
      "loss": 0.7496,
      "step": 43500
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.984831094480178e-05,
      "loss": 0.7563,
      "step": 44000
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.9846586539290583e-05,
      "loss": 0.751,
      "step": 44500
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.9844865582590404e-05,
      "loss": 0.7488,
      "step": 45000
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.9843141177079202e-05,
      "loss": 0.7488,
      "step": 45500
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.9841420220379027e-05,
      "loss": 0.7486,
      "step": 46000
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9839695814867825e-05,
      "loss": 0.7511,
      "step": 46500
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.9837971409356627e-05,
      "loss": 0.7492,
      "step": 47000
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9836247003845425e-05,
      "loss": 0.7439,
      "step": 47500
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.9834522598334226e-05,
      "loss": 0.7419,
      "step": 48000
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.9832801641634048e-05,
      "loss": 0.7467,
      "step": 48500
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.983107723612285e-05,
      "loss": 0.7479,
      "step": 49000
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.982935627942267e-05,
      "loss": 0.7399,
      "step": 49500
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.982763187391147e-05,
      "loss": 0.7414,
      "step": 50000
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.982590746840027e-05,
      "loss": 0.7464,
      "step": 50500
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.982418306288907e-05,
      "loss": 0.7444,
      "step": 51000
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.982245865737787e-05,
      "loss": 0.7363,
      "step": 51500
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.982073425186667e-05,
      "loss": 0.7474,
      "step": 52000
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.981900984635547e-05,
      "loss": 0.7414,
      "step": 52500
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.981728544084427e-05,
      "loss": 0.7391,
      "step": 53000
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.9815564484144092e-05,
      "loss": 0.7377,
      "step": 53500
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.9813840078632894e-05,
      "loss": 0.7417,
      "step": 54000
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.981211567312169e-05,
      "loss": 0.7374,
      "step": 54500
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.9810391267610493e-05,
      "loss": 0.7394,
      "step": 55000
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.9808666862099294e-05,
      "loss": 0.7366,
      "step": 55500
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.9806942456588092e-05,
      "loss": 0.7349,
      "step": 56000
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.9805218051076894e-05,
      "loss": 0.7329,
      "step": 56500
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.9803493645565692e-05,
      "loss": 0.7344,
      "step": 57000
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.9801769240054493e-05,
      "loss": 0.7368,
      "step": 57500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7309060096740723,
      "eval_runtime": 152.8898,
      "eval_samples_per_second": 84.342,
      "eval_steps_per_second": 21.087,
      "step": 57991
    }
  ],
  "logging_steps": 500,
  "max_steps": 5799100,
  "num_train_epochs": 100,
  "save_steps": 500,
  "total_flos": 2.1530778106802995e+17,
  "trial_name": null,
  "trial_params": null
}