{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.939195509822264,
  "global_step": 42500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12,
      "learning_rate": 4.9415341440598695e-05,
      "loss": 4.3211,
      "step": 500
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.883068288119738e-05,
      "loss": 3.4901,
      "step": 1000
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.8246024321796074e-05,
      "loss": 3.1921,
      "step": 1500
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.766136576239477e-05,
      "loss": 2.967,
      "step": 2000
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.7076707202993454e-05,
      "loss": 2.8175,
      "step": 2500
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.6492048643592146e-05,
      "loss": 2.7129,
      "step": 3000
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.590739008419083e-05,
      "loss": 2.6442,
      "step": 3500
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.5322731524789526e-05,
      "loss": 2.5971,
      "step": 4000
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.473807296538822e-05,
      "loss": 2.4775,
      "step": 4500
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.4153414405986905e-05,
      "loss": 2.3784,
      "step": 5000
    },
    {
      "epoch": 1.29,
      "learning_rate": 4.35687558465856e-05,
      "loss": 2.3465,
      "step": 5500
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.298409728718429e-05,
      "loss": 2.3377,
      "step": 6000
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.239943872778298e-05,
      "loss": 2.3163,
      "step": 6500
    },
    {
      "epoch": 1.64,
      "learning_rate": 4.181478016838167e-05,
      "loss": 2.3037,
      "step": 7000
    },
    {
      "epoch": 1.75,
      "learning_rate": 4.123012160898036e-05,
      "loss": 2.2963,
      "step": 7500
    },
    {
      "epoch": 1.87,
      "learning_rate": 4.064546304957905e-05,
      "loss": 2.279,
      "step": 8000
    },
    {
      "epoch": 1.99,
      "learning_rate": 4.006080449017774e-05,
      "loss": 2.2744,
      "step": 8500
    },
    {
      "epoch": 2.1,
      "learning_rate": 3.947614593077643e-05,
      "loss": 2.0997,
      "step": 9000
    },
    {
      "epoch": 2.22,
      "learning_rate": 3.889148737137512e-05,
      "loss": 2.0715,
      "step": 9500
    },
    {
      "epoch": 2.34,
      "learning_rate": 3.8306828811973814e-05,
      "loss": 2.0789,
      "step": 10000
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.77221702525725e-05,
      "loss": 2.075,
      "step": 10500
    },
    {
      "epoch": 2.57,
      "learning_rate": 3.713751169317119e-05,
      "loss": 2.0657,
      "step": 11000
    },
    {
      "epoch": 2.69,
      "learning_rate": 3.655285313376988e-05,
      "loss": 2.0795,
      "step": 11500
    },
    {
      "epoch": 2.81,
      "learning_rate": 3.596819457436857e-05,
      "loss": 2.0503,
      "step": 12000
    },
    {
      "epoch": 2.92,
      "learning_rate": 3.538353601496726e-05,
      "loss": 2.0637,
      "step": 12500
    },
    {
      "epoch": 3.04,
      "learning_rate": 3.479887745556595e-05,
      "loss": 1.9936,
      "step": 13000
    },
    {
      "epoch": 3.16,
      "learning_rate": 3.421421889616464e-05,
      "loss": 1.8791,
      "step": 13500
    },
    {
      "epoch": 3.27,
      "learning_rate": 3.362956033676333e-05,
      "loss": 1.8823,
      "step": 14000
    },
    {
      "epoch": 3.39,
      "learning_rate": 3.304490177736202e-05,
      "loss": 1.8947,
      "step": 14500
    },
    {
      "epoch": 3.51,
      "learning_rate": 3.246024321796071e-05,
      "loss": 1.8993,
      "step": 15000
    },
    {
      "epoch": 3.62,
      "learning_rate": 3.18755846585594e-05,
      "loss": 1.8999,
      "step": 15500
    },
    {
      "epoch": 3.74,
      "learning_rate": 3.129092609915809e-05,
      "loss": 1.8917,
      "step": 16000
    },
    {
      "epoch": 3.86,
      "learning_rate": 3.070626753975678e-05,
      "loss": 1.9039,
      "step": 16500
    },
    {
      "epoch": 3.98,
      "learning_rate": 3.0121608980355477e-05,
      "loss": 1.8958,
      "step": 17000
    },
    {
      "epoch": 4.09,
      "learning_rate": 2.9536950420954164e-05,
      "loss": 1.7626,
      "step": 17500
    },
    {
      "epoch": 4.21,
      "learning_rate": 2.8952291861552856e-05,
      "loss": 1.7527,
      "step": 18000
    },
    {
      "epoch": 4.33,
      "learning_rate": 2.8367633302151546e-05,
      "loss": 1.7416,
      "step": 18500
    },
    {
      "epoch": 4.44,
      "learning_rate": 2.7782974742750236e-05,
      "loss": 1.7483,
      "step": 19000
    },
    {
      "epoch": 4.56,
      "learning_rate": 2.7198316183348925e-05,
      "loss": 1.7518,
      "step": 19500
    },
    {
      "epoch": 4.68,
      "learning_rate": 2.6613657623947615e-05,
      "loss": 1.7548,
      "step": 20000
    },
    {
      "epoch": 4.79,
      "learning_rate": 2.6028999064546304e-05,
      "loss": 1.7542,
      "step": 20500
    },
    {
      "epoch": 4.91,
      "learning_rate": 2.5444340505144997e-05,
      "loss": 1.7547,
      "step": 21000
    },
    {
      "epoch": 5.03,
      "learning_rate": 2.4859681945743687e-05,
      "loss": 1.7305,
      "step": 21500
    },
    {
      "epoch": 5.14,
      "learning_rate": 2.4275023386342376e-05,
      "loss": 1.6149,
      "step": 22000
    },
    {
      "epoch": 5.26,
      "learning_rate": 2.3690364826941066e-05,
      "loss": 1.6119,
      "step": 22500
    },
    {
      "epoch": 5.38,
      "learning_rate": 2.310570626753976e-05,
      "loss": 1.6279,
      "step": 23000
    },
    {
      "epoch": 5.5,
      "learning_rate": 2.2521047708138448e-05,
      "loss": 1.6463,
      "step": 23500
    },
    {
      "epoch": 5.61,
      "learning_rate": 2.1936389148737138e-05,
      "loss": 1.6341,
      "step": 24000
    },
    {
      "epoch": 5.73,
      "learning_rate": 2.1351730589335827e-05,
      "loss": 1.6401,
      "step": 24500
    },
    {
      "epoch": 5.85,
      "learning_rate": 2.076707202993452e-05,
      "loss": 1.647,
      "step": 25000
    },
    {
      "epoch": 5.96,
      "learning_rate": 2.018241347053321e-05,
      "loss": 1.6439,
      "step": 25500
    },
    {
      "epoch": 6.08,
      "learning_rate": 1.95977549111319e-05,
      "loss": 1.5445,
      "step": 26000
    },
    {
      "epoch": 6.2,
      "learning_rate": 1.9013096351730592e-05,
      "loss": 1.5145,
      "step": 26500
    },
    {
      "epoch": 6.31,
      "learning_rate": 1.8428437792329282e-05,
      "loss": 1.5314,
      "step": 27000
    },
    {
      "epoch": 6.43,
      "learning_rate": 1.784377923292797e-05,
      "loss": 1.534,
      "step": 27500
    },
    {
      "epoch": 6.55,
      "learning_rate": 1.725912067352666e-05,
      "loss": 1.5329,
      "step": 28000
    },
    {
      "epoch": 6.67,
      "learning_rate": 1.6674462114125354e-05,
      "loss": 1.5302,
      "step": 28500
    },
    {
      "epoch": 6.78,
      "learning_rate": 1.6089803554724043e-05,
      "loss": 1.5467,
      "step": 29000
    },
    {
      "epoch": 6.9,
      "learning_rate": 1.5505144995322733e-05,
      "loss": 1.5472,
      "step": 29500
    },
    {
      "epoch": 7.02,
      "learning_rate": 1.492048643592142e-05,
      "loss": 1.5257,
      "step": 30000
    },
    {
      "epoch": 7.13,
      "learning_rate": 1.4335827876520114e-05,
      "loss": 1.4319,
      "step": 30500
    },
    {
      "epoch": 7.25,
      "learning_rate": 1.3751169317118803e-05,
      "loss": 1.4378,
      "step": 31000
    },
    {
      "epoch": 7.37,
      "learning_rate": 1.3166510757717493e-05,
      "loss": 1.4506,
      "step": 31500
    },
    {
      "epoch": 7.48,
      "learning_rate": 1.2581852198316186e-05,
      "loss": 1.4453,
      "step": 32000
    },
    {
      "epoch": 7.6,
      "learning_rate": 1.1997193638914875e-05,
      "loss": 1.4588,
      "step": 32500
    },
    {
      "epoch": 7.72,
      "learning_rate": 1.1412535079513565e-05,
      "loss": 1.4601,
      "step": 33000
    },
    {
      "epoch": 7.83,
      "learning_rate": 1.0827876520112256e-05,
      "loss": 1.4585,
      "step": 33500
    },
    {
      "epoch": 7.95,
      "learning_rate": 1.0243217960710946e-05,
      "loss": 1.4664,
      "step": 34000
    },
    {
      "epoch": 8.07,
      "learning_rate": 9.658559401309635e-06,
      "loss": 1.3973,
      "step": 34500
    },
    {
      "epoch": 8.19,
      "learning_rate": 9.073900841908325e-06,
      "loss": 1.3694,
      "step": 35000
    },
    {
      "epoch": 8.3,
      "learning_rate": 8.489242282507016e-06,
      "loss": 1.3876,
      "step": 35500
    },
    {
      "epoch": 8.42,
      "learning_rate": 7.904583723105706e-06,
      "loss": 1.3896,
      "step": 36000
    },
    {
      "epoch": 8.54,
      "learning_rate": 7.319925163704397e-06,
      "loss": 1.3918,
      "step": 36500
    },
    {
      "epoch": 8.65,
      "learning_rate": 6.735266604303088e-06,
      "loss": 1.382,
      "step": 37000
    },
    {
      "epoch": 8.77,
      "learning_rate": 6.1506080449017775e-06,
      "loss": 1.3942,
      "step": 37500
    },
    {
      "epoch": 8.89,
      "learning_rate": 5.565949485500468e-06,
      "loss": 1.3889,
      "step": 38000
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.981290926099158e-06,
      "loss": 1.3951,
      "step": 38500
    },
    {
      "epoch": 9.12,
      "learning_rate": 4.396632366697849e-06,
      "loss": 1.3346,
      "step": 39000
    },
    {
      "epoch": 9.24,
      "learning_rate": 3.811973807296539e-06,
      "loss": 1.3361,
      "step": 39500
    },
    {
      "epoch": 9.35,
      "learning_rate": 3.2273152478952295e-06,
      "loss": 1.3329,
      "step": 40000
    },
    {
      "epoch": 9.47,
      "learning_rate": 2.64265668849392e-06,
      "loss": 1.3371,
      "step": 40500
    },
    {
      "epoch": 9.59,
      "learning_rate": 2.0579981290926103e-06,
      "loss": 1.3442,
      "step": 41000
    },
    {
      "epoch": 9.71,
      "learning_rate": 1.4733395696913004e-06,
      "loss": 1.3402,
      "step": 41500
    },
    {
      "epoch": 9.82,
      "learning_rate": 8.886810102899906e-07,
      "loss": 1.3439,
      "step": 42000
    },
    {
      "epoch": 9.94,
      "learning_rate": 3.04022450888681e-07,
      "loss": 1.3374,
      "step": 42500
    }
  ],
  "max_steps": 42760,
  "num_train_epochs": 10,
  "total_flos": 1687120822272000.0,
  "trial_name": null,
  "trial_params": null
}