{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 22678,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 1.9823617602963227e-05,
      "loss": 1.393,
      "step": 500
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.964723520592645e-05,
      "loss": 1.3599,
      "step": 1000
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9470852808889677e-05,
      "loss": 1.3453,
      "step": 1500
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.92944704118529e-05,
      "loss": 1.3328,
      "step": 2000
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9118088014816124e-05,
      "loss": 1.3271,
      "step": 2500
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.8941705617779345e-05,
      "loss": 1.3291,
      "step": 3000
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.876532322074257e-05,
      "loss": 1.3199,
      "step": 3500
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.8588940823705796e-05,
      "loss": 1.3173,
      "step": 4000
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.841255842666902e-05,
      "loss": 1.3141,
      "step": 4500
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.8236176029632246e-05,
      "loss": 1.3151,
      "step": 5000
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.8059793632595468e-05,
      "loss": 1.3105,
      "step": 5500
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7883411235558693e-05,
      "loss": 1.3042,
      "step": 6000
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.7707028838521918e-05,
      "loss": 1.2985,
      "step": 6500
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.7530646441485143e-05,
      "loss": 1.2946,
      "step": 7000
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.7354264044448365e-05,
      "loss": 1.2958,
      "step": 7500
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.717788164741159e-05,
      "loss": 1.2867,
      "step": 8000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.7001499250374815e-05,
      "loss": 1.2938,
      "step": 8500
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.682511685333804e-05,
      "loss": 1.2934,
      "step": 9000
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.664873445630126e-05,
      "loss": 1.2892,
      "step": 9500
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.6472352059264487e-05,
      "loss": 1.2835,
      "step": 10000
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.6295969662227712e-05,
      "loss": 1.2838,
      "step": 10500
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.6119587265190934e-05,
      "loss": 1.2842,
      "step": 11000
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.2190536260604858,
      "eval_runtime": 28.9964,
      "eval_samples_per_second": 30.728,
      "eval_steps_per_second": 1.931,
      "step": 11339
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.594320486815416e-05,
      "loss": 1.2845,
      "step": 11500
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.5766822471117384e-05,
      "loss": 1.276,
      "step": 12000
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.559044007408061e-05,
      "loss": 1.2702,
      "step": 12500
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.541405767704383e-05,
      "loss": 1.2726,
      "step": 13000
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.5237675280007056e-05,
      "loss": 1.2744,
      "step": 13500
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.5061292882970279e-05,
      "loss": 1.2741,
      "step": 14000
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.4884910485933506e-05,
      "loss": 1.2642,
      "step": 14500
    },
    {
      "epoch": 1.32,
      "learning_rate": 1.470852808889673e-05,
      "loss": 1.2635,
      "step": 15000
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.4532145691859953e-05,
      "loss": 1.2656,
      "step": 15500
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.4355763294823178e-05,
      "loss": 1.2606,
      "step": 16000
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.4179380897786401e-05,
      "loss": 1.2652,
      "step": 16500
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.4002998500749626e-05,
      "loss": 1.2636,
      "step": 17000
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.3826616103712851e-05,
      "loss": 1.2712,
      "step": 17500
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.3650233706676075e-05,
      "loss": 1.2634,
      "step": 18000
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.3473851309639298e-05,
      "loss": 1.2585,
      "step": 18500
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.3297468912602522e-05,
      "loss": 1.2556,
      "step": 19000
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.3121086515565748e-05,
      "loss": 1.2595,
      "step": 19500
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.2944704118528972e-05,
      "loss": 1.2609,
      "step": 20000
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.2768321721492197e-05,
      "loss": 1.2552,
      "step": 20500
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.259193932445542e-05,
      "loss": 1.2548,
      "step": 21000
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.2415556927418644e-05,
      "loss": 1.2599,
      "step": 21500
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.223917453038187e-05,
      "loss": 1.2582,
      "step": 22000
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.2062792133345094e-05,
      "loss": 1.2563,
      "step": 22500
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.1791033744812012,
      "eval_runtime": 29.0168,
      "eval_samples_per_second": 30.706,
      "eval_steps_per_second": 1.93,
      "step": 22678
    }
  ],
  "logging_steps": 500,
  "max_steps": 56695,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 9.552148881938842e+16,
  "trial_name": null,
  "trial_params": null
}