{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.921671018276763,
  "global_step": 57000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 1.9825935596170586e-05,
      "loss": 2.4238,
      "step": 500
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9651871192341167e-05,
      "loss": 2.1067,
      "step": 1000
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.947780678851175e-05,
      "loss": 1.9034,
      "step": 1500
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.9303742384682335e-05,
      "loss": 1.8061,
      "step": 2000
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.9129677980852916e-05,
      "loss": 1.7317,
      "step": 2500
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.89556135770235e-05,
      "loss": 1.6795,
      "step": 3000
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.8781549173194084e-05,
      "loss": 1.6346,
      "step": 3500
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.8607484769364665e-05,
      "loss": 1.5838,
      "step": 4000
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.843342036553525e-05,
      "loss": 1.5477,
      "step": 4500
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.8259355961705833e-05,
      "loss": 1.5084,
      "step": 5000
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.8085291557876417e-05,
      "loss": 1.4765,
      "step": 5500
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.2889001369476318,
      "eval_runtime": 523.3258,
      "eval_samples_per_second": 126.487,
      "eval_steps_per_second": 1.978,
      "step": 5745
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.7911227154046998e-05,
      "loss": 1.4277,
      "step": 6000
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.7737162750217582e-05,
      "loss": 1.3842,
      "step": 6500
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.7563098346388167e-05,
      "loss": 1.3659,
      "step": 7000
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.7389033942558747e-05,
      "loss": 1.346,
      "step": 7500
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.721496953872933e-05,
      "loss": 1.3252,
      "step": 8000
    },
    {
      "epoch": 1.48,
      "learning_rate": 1.7040905134899916e-05,
      "loss": 1.3148,
      "step": 8500
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.6866840731070497e-05,
      "loss": 1.3071,
      "step": 9000
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.669277632724108e-05,
      "loss": 1.287,
      "step": 9500
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.6518711923411665e-05,
      "loss": 1.2802,
      "step": 10000
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.6344647519582246e-05,
      "loss": 1.2637,
      "step": 10500
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.617058311575283e-05,
      "loss": 1.2451,
      "step": 11000
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.1364690065383911,
      "eval_runtime": 527.405,
      "eval_samples_per_second": 125.509,
      "eval_steps_per_second": 1.962,
      "step": 11490
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.599651871192341e-05,
      "loss": 1.2384,
      "step": 11500
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.5822454308093995e-05,
      "loss": 1.1927,
      "step": 12000
    },
    {
      "epoch": 2.18,
      "learning_rate": 1.564838990426458e-05,
      "loss": 1.1753,
      "step": 12500
    },
    {
      "epoch": 2.26,
      "learning_rate": 1.5474325500435163e-05,
      "loss": 1.1781,
      "step": 13000
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.5300261096605747e-05,
      "loss": 1.1705,
      "step": 13500
    },
    {
      "epoch": 2.44,
      "learning_rate": 1.512619669277633e-05,
      "loss": 1.1653,
      "step": 14000
    },
    {
      "epoch": 2.52,
      "learning_rate": 1.4952132288946912e-05,
      "loss": 1.1541,
      "step": 14500
    },
    {
      "epoch": 2.61,
      "learning_rate": 1.4778067885117495e-05,
      "loss": 1.1485,
      "step": 15000
    },
    {
      "epoch": 2.7,
      "learning_rate": 1.4604003481288079e-05,
      "loss": 1.1479,
      "step": 15500
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.4429939077458661e-05,
      "loss": 1.1399,
      "step": 16000
    },
    {
      "epoch": 2.87,
      "learning_rate": 1.4255874673629244e-05,
      "loss": 1.1355,
      "step": 16500
    },
    {
      "epoch": 2.96,
      "learning_rate": 1.4081810269799826e-05,
      "loss": 1.1291,
      "step": 17000
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.0703651905059814,
      "eval_runtime": 523.7516,
      "eval_samples_per_second": 126.384,
      "eval_steps_per_second": 1.976,
      "step": 17235
    },
    {
      "epoch": 3.05,
      "learning_rate": 1.390774586597041e-05,
      "loss": 1.1075,
      "step": 17500
    },
    {
      "epoch": 3.13,
      "learning_rate": 1.3733681462140993e-05,
      "loss": 1.0931,
      "step": 18000
    },
    {
      "epoch": 3.22,
      "learning_rate": 1.3559617058311576e-05,
      "loss": 1.0864,
      "step": 18500
    },
    {
      "epoch": 3.31,
      "learning_rate": 1.338555265448216e-05,
      "loss": 1.0822,
      "step": 19000
    },
    {
      "epoch": 3.39,
      "learning_rate": 1.3211488250652742e-05,
      "loss": 1.0847,
      "step": 19500
    },
    {
      "epoch": 3.48,
      "learning_rate": 1.3037423846823325e-05,
      "loss": 1.0795,
      "step": 20000
    },
    {
      "epoch": 3.57,
      "learning_rate": 1.2863359442993907e-05,
      "loss": 1.0704,
      "step": 20500
    },
    {
      "epoch": 3.66,
      "learning_rate": 1.2689295039164491e-05,
      "loss": 1.072,
      "step": 21000
    },
    {
      "epoch": 3.74,
      "learning_rate": 1.2515230635335076e-05,
      "loss": 1.0704,
      "step": 21500
    },
    {
      "epoch": 3.83,
      "learning_rate": 1.234116623150566e-05,
      "loss": 1.0623,
      "step": 22000
    },
    {
      "epoch": 3.92,
      "learning_rate": 1.2167101827676242e-05,
      "loss": 1.0657,
      "step": 22500
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0373072624206543,
      "eval_runtime": 524.067,
      "eval_samples_per_second": 126.308,
      "eval_steps_per_second": 1.975,
      "step": 22980
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.1993037423846825e-05,
      "loss": 1.0612,
      "step": 23000
    },
    {
      "epoch": 4.09,
      "learning_rate": 1.1818973020017407e-05,
      "loss": 1.0267,
      "step": 23500
    },
    {
      "epoch": 4.18,
      "learning_rate": 1.1644908616187991e-05,
      "loss": 1.035,
      "step": 24000
    },
    {
      "epoch": 4.26,
      "learning_rate": 1.1470844212358574e-05,
      "loss": 1.0298,
      "step": 24500
    },
    {
      "epoch": 4.35,
      "learning_rate": 1.1296779808529156e-05,
      "loss": 1.0265,
      "step": 25000
    },
    {
      "epoch": 4.44,
      "learning_rate": 1.112271540469974e-05,
      "loss": 1.0337,
      "step": 25500
    },
    {
      "epoch": 4.53,
      "learning_rate": 1.0948651000870323e-05,
      "loss": 1.0265,
      "step": 26000
    },
    {
      "epoch": 4.61,
      "learning_rate": 1.0774586597040905e-05,
      "loss": 1.0264,
      "step": 26500
    },
    {
      "epoch": 4.7,
      "learning_rate": 1.0600522193211488e-05,
      "loss": 1.0181,
      "step": 27000
    },
    {
      "epoch": 4.79,
      "learning_rate": 1.0426457789382072e-05,
      "loss": 1.021,
      "step": 27500
    },
    {
      "epoch": 4.87,
      "learning_rate": 1.0252393385552655e-05,
      "loss": 1.0249,
      "step": 28000
    },
    {
      "epoch": 4.96,
      "learning_rate": 1.0078328981723237e-05,
      "loss": 1.0205,
      "step": 28500
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.0189781188964844,
      "eval_runtime": 521.0752,
      "eval_samples_per_second": 127.033,
      "eval_steps_per_second": 1.986,
      "step": 28725
    },
    {
      "epoch": 5.05,
      "learning_rate": 9.904264577893821e-06,
      "loss": 1.0044,
      "step": 29000
    },
    {
      "epoch": 5.13,
      "learning_rate": 9.730200174064405e-06,
      "loss": 0.9887,
      "step": 29500
    },
    {
      "epoch": 5.22,
      "learning_rate": 9.556135770234988e-06,
      "loss": 0.993,
      "step": 30000
    },
    {
      "epoch": 5.31,
      "learning_rate": 9.38207136640557e-06,
      "loss": 0.9946,
      "step": 30500
    },
    {
      "epoch": 5.4,
      "learning_rate": 9.208006962576153e-06,
      "loss": 0.9898,
      "step": 31000
    },
    {
      "epoch": 5.48,
      "learning_rate": 9.033942558746737e-06,
      "loss": 0.9902,
      "step": 31500
    },
    {
      "epoch": 5.57,
      "learning_rate": 8.85987815491732e-06,
      "loss": 0.9899,
      "step": 32000
    },
    {
      "epoch": 5.66,
      "learning_rate": 8.685813751087904e-06,
      "loss": 0.9884,
      "step": 32500
    },
    {
      "epoch": 5.74,
      "learning_rate": 8.511749347258486e-06,
      "loss": 0.9906,
      "step": 33000
    },
    {
      "epoch": 5.83,
      "learning_rate": 8.33768494342907e-06,
      "loss": 0.9856,
      "step": 33500
    },
    {
      "epoch": 5.92,
      "learning_rate": 8.163620539599653e-06,
      "loss": 0.9923,
      "step": 34000
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.0085190534591675,
      "eval_runtime": 521.5738,
      "eval_samples_per_second": 126.912,
      "eval_steps_per_second": 1.984,
      "step": 34470
    },
    {
      "epoch": 6.01,
      "learning_rate": 7.989556135770235e-06,
      "loss": 0.9843,
      "step": 34500
    },
    {
      "epoch": 6.09,
      "learning_rate": 7.815491731940818e-06,
      "loss": 0.9674,
      "step": 35000
    },
    {
      "epoch": 6.18,
      "learning_rate": 7.641427328111402e-06,
      "loss": 0.9647,
      "step": 35500
    },
    {
      "epoch": 6.27,
      "learning_rate": 7.4673629242819845e-06,
      "loss": 0.9664,
      "step": 36000
    },
    {
      "epoch": 6.35,
      "learning_rate": 7.293298520452569e-06,
      "loss": 0.9689,
      "step": 36500
    },
    {
      "epoch": 6.44,
      "learning_rate": 7.119234116623151e-06,
      "loss": 0.9668,
      "step": 37000
    },
    {
      "epoch": 6.53,
      "learning_rate": 6.9451697127937345e-06,
      "loss": 0.9617,
      "step": 37500
    },
    {
      "epoch": 6.61,
      "learning_rate": 6.771105308964318e-06,
      "loss": 0.962,
      "step": 38000
    },
    {
      "epoch": 6.7,
      "learning_rate": 6.5970409051349e-06,
      "loss": 0.9633,
      "step": 38500
    },
    {
      "epoch": 6.79,
      "learning_rate": 6.422976501305484e-06,
      "loss": 0.9611,
      "step": 39000
    },
    {
      "epoch": 6.88,
      "learning_rate": 6.248912097476066e-06,
      "loss": 0.9617,
      "step": 39500
    },
    {
      "epoch": 6.96,
      "learning_rate": 6.0748476936466495e-06,
      "loss": 0.959,
      "step": 40000
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.0030972957611084,
      "eval_runtime": 523.5292,
      "eval_samples_per_second": 126.438,
      "eval_steps_per_second": 1.977,
      "step": 40215
    },
    {
      "epoch": 7.05,
      "learning_rate": 5.900783289817232e-06,
      "loss": 0.9511,
      "step": 40500
    },
    {
      "epoch": 7.14,
      "learning_rate": 5.726718885987816e-06,
      "loss": 0.9432,
      "step": 41000
    },
    {
      "epoch": 7.22,
      "learning_rate": 5.5526544821583995e-06,
      "loss": 0.942,
      "step": 41500
    },
    {
      "epoch": 7.31,
      "learning_rate": 5.378590078328983e-06,
      "loss": 0.9415,
      "step": 42000
    },
    {
      "epoch": 7.4,
      "learning_rate": 5.204525674499565e-06,
      "loss": 0.9427,
      "step": 42500
    },
    {
      "epoch": 7.48,
      "learning_rate": 5.030461270670149e-06,
      "loss": 0.9477,
      "step": 43000
    },
    {
      "epoch": 7.57,
      "learning_rate": 4.856396866840731e-06,
      "loss": 0.9439,
      "step": 43500
    },
    {
      "epoch": 7.66,
      "learning_rate": 4.682332463011314e-06,
      "loss": 0.945,
      "step": 44000
    },
    {
      "epoch": 7.75,
      "learning_rate": 4.508268059181898e-06,
      "loss": 0.9456,
      "step": 44500
    },
    {
      "epoch": 7.83,
      "learning_rate": 4.334203655352481e-06,
      "loss": 0.9436,
      "step": 45000
    },
    {
      "epoch": 7.92,
      "learning_rate": 4.1601392515230636e-06,
      "loss": 0.9447,
      "step": 45500
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.0001778602600098,
      "eval_runtime": 520.9721,
      "eval_samples_per_second": 127.059,
      "eval_steps_per_second": 1.987,
      "step": 45960
    },
    {
      "epoch": 8.01,
      "learning_rate": 3.986074847693647e-06,
      "loss": 0.9459,
      "step": 46000
    },
    {
      "epoch": 8.09,
      "learning_rate": 3.8120104438642302e-06,
      "loss": 0.9265,
      "step": 46500
    },
    {
      "epoch": 8.18,
      "learning_rate": 3.637946040034813e-06,
      "loss": 0.9271,
      "step": 47000
    },
    {
      "epoch": 8.27,
      "learning_rate": 3.463881636205396e-06,
      "loss": 0.9286,
      "step": 47500
    },
    {
      "epoch": 8.36,
      "learning_rate": 3.2898172323759794e-06,
      "loss": 0.9302,
      "step": 48000
    },
    {
      "epoch": 8.44,
      "learning_rate": 3.1157528285465627e-06,
      "loss": 0.933,
      "step": 48500
    },
    {
      "epoch": 8.53,
      "learning_rate": 2.9416884247171456e-06,
      "loss": 0.9272,
      "step": 49000
    },
    {
      "epoch": 8.62,
      "learning_rate": 2.7676240208877285e-06,
      "loss": 0.9266,
      "step": 49500
    },
    {
      "epoch": 8.7,
      "learning_rate": 2.5935596170583114e-06,
      "loss": 0.9294,
      "step": 50000
    },
    {
      "epoch": 8.79,
      "learning_rate": 2.4194952132288948e-06,
      "loss": 0.9312,
      "step": 50500
    },
    {
      "epoch": 8.88,
      "learning_rate": 2.245430809399478e-06,
      "loss": 0.9306,
      "step": 51000
    },
    {
      "epoch": 8.96,
      "learning_rate": 2.071366405570061e-06,
      "loss": 0.9278,
      "step": 51500
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.9995460510253906,
      "eval_runtime": 522.976,
      "eval_samples_per_second": 126.572,
      "eval_steps_per_second": 1.979,
      "step": 51705
    },
    {
      "epoch": 9.05,
      "learning_rate": 1.8973020017406443e-06,
      "loss": 0.92,
      "step": 52000
    },
    {
      "epoch": 9.14,
      "learning_rate": 1.7232375979112272e-06,
      "loss": 0.9178,
      "step": 52500
    },
    {
      "epoch": 9.23,
      "learning_rate": 1.5491731940818103e-06,
      "loss": 0.9189,
      "step": 53000
    },
    {
      "epoch": 9.31,
      "learning_rate": 1.3751087902523935e-06,
      "loss": 0.9164,
      "step": 53500
    },
    {
      "epoch": 9.4,
      "learning_rate": 1.2010443864229766e-06,
      "loss": 0.9186,
      "step": 54000
    },
    {
      "epoch": 9.49,
      "learning_rate": 1.0269799825935597e-06,
      "loss": 0.9199,
      "step": 54500
    },
    {
      "epoch": 9.57,
      "learning_rate": 8.529155787641428e-07,
      "loss": 0.918,
      "step": 55000
    },
    {
      "epoch": 9.66,
      "learning_rate": 6.788511749347259e-07,
      "loss": 0.9229,
      "step": 55500
    },
    {
      "epoch": 9.75,
      "learning_rate": 5.04786771105309e-07,
      "loss": 0.9203,
      "step": 56000
    },
    {
      "epoch": 9.83,
      "learning_rate": 3.3072236727589213e-07,
      "loss": 0.9202,
      "step": 56500
    },
    {
      "epoch": 9.92,
      "learning_rate": 1.566579634464752e-07,
      "loss": 0.9168,
      "step": 57000
    }
  ],
  "max_steps": 57450,
  "num_train_epochs": 10,
  "total_flos": 8.267810851042099e+18,
  "trial_name": null,
  "trial_params": null
}