{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 24489,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 1.959165339540202e-05,
      "loss": 3.1241,
      "step": 500
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9183306790804037e-05,
      "loss": 2.5382,
      "step": 1000
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8774960186206054e-05,
      "loss": 2.2802,
      "step": 1500
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.8366613581608072e-05,
      "loss": 2.0981,
      "step": 2000
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.795826697701009e-05,
      "loss": 1.9806,
      "step": 2500
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.7549920372412107e-05,
      "loss": 1.8749,
      "step": 3000
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.714157376781412e-05,
      "loss": 1.7845,
      "step": 3500
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.673322716321614e-05,
      "loss": 1.7693,
      "step": 4000
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.6324880558618156e-05,
      "loss": 1.6563,
      "step": 4500
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.5916533954020174e-05,
      "loss": 1.6036,
      "step": 5000
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.550818734942219e-05,
      "loss": 1.572,
      "step": 5500
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.5099840744824207e-05,
      "loss": 1.547,
      "step": 6000
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.4691494140226225e-05,
      "loss": 1.5027,
      "step": 6500
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.4283147535628244e-05,
      "loss": 1.4847,
      "step": 7000
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.3874800931030258e-05,
      "loss": 1.4495,
      "step": 7500
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3466454326432276e-05,
      "loss": 1.4558,
      "step": 8000
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.3058107721834295e-05,
      "loss": 1.3089,
      "step": 8500
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.2649761117236313e-05,
      "loss": 1.2217,
      "step": 9000
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.2241414512638327e-05,
      "loss": 1.255,
      "step": 9500
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.1833067908040346e-05,
      "loss": 1.1977,
      "step": 10000
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.1424721303442364e-05,
      "loss": 1.209,
      "step": 10500
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.1016374698844381e-05,
      "loss": 1.1799,
      "step": 11000
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.0608028094246397e-05,
      "loss": 1.1807,
      "step": 11500
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.0199681489648415e-05,
      "loss": 1.1597,
      "step": 12000
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.791334885050432e-06,
      "loss": 1.1603,
      "step": 12500
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.382988280452448e-06,
      "loss": 1.1847,
      "step": 13000
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.974641675854466e-06,
      "loss": 1.1543,
      "step": 13500
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.566295071256483e-06,
      "loss": 1.1336,
      "step": 14000
    },
    {
      "epoch": 1.78,
      "learning_rate": 8.157948466658501e-06,
      "loss": 1.1141,
      "step": 14500
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.749601862060517e-06,
      "loss": 1.1361,
      "step": 15000
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.341255257462535e-06,
      "loss": 1.142,
      "step": 15500
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.932908652864552e-06,
      "loss": 1.1296,
      "step": 16000
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.5245620482665695e-06,
      "loss": 1.0464,
      "step": 16500
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.116215443668586e-06,
      "loss": 0.9281,
      "step": 17000
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.707868839070604e-06,
      "loss": 0.9222,
      "step": 17500
    },
    {
      "epoch": 2.21,
      "learning_rate": 5.2995222344726205e-06,
      "loss": 0.9243,
      "step": 18000
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.891175629874638e-06,
      "loss": 0.93,
      "step": 18500
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.482829025276656e-06,
      "loss": 0.9329,
      "step": 19000
    },
    {
      "epoch": 2.39,
      "learning_rate": 4.074482420678672e-06,
      "loss": 0.9151,
      "step": 19500
    },
    {
      "epoch": 2.45,
      "learning_rate": 3.66613581608069e-06,
      "loss": 0.8925,
      "step": 20000
    },
    {
      "epoch": 2.51,
      "learning_rate": 3.257789211482707e-06,
      "loss": 0.9195,
      "step": 20500
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.849442606884724e-06,
      "loss": 0.9131,
      "step": 21000
    },
    {
      "epoch": 2.63,
      "learning_rate": 2.441096002286741e-06,
      "loss": 0.8965,
      "step": 21500
    },
    {
      "epoch": 2.7,
      "learning_rate": 2.0327493976887585e-06,
      "loss": 0.9158,
      "step": 22000
    },
    {
      "epoch": 2.76,
      "learning_rate": 1.6244027930907754e-06,
      "loss": 0.9219,
      "step": 22500
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.2160561884927927e-06,
      "loss": 0.9128,
      "step": 23000
    },
    {
      "epoch": 2.88,
      "learning_rate": 8.0770958389481e-07,
      "loss": 0.9106,
      "step": 23500
    },
    {
      "epoch": 2.94,
      "learning_rate": 3.993629792968272e-07,
      "loss": 0.9122,
      "step": 24000
    },
    {
      "epoch": 3.0,
      "step": 24489,
      "total_flos": 9.597903475284864e+16,
      "train_loss": 1.3127011176813441,
      "train_runtime": 19384.6994,
      "train_samples_per_second": 20.212,
      "train_steps_per_second": 1.263
    }
  ],
  "max_steps": 24489,
  "num_train_epochs": 3,
  "total_flos": 9.597903475284864e+16,
  "trial_name": null,
  "trial_params": null
}