{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.330556481172943,
  "eval_steps": 500,
  "global_step": 25000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16661112962345884,
      "grad_norm": 2.0231502056121826,
      "learning_rate": 2.776852160390981e-06,
      "loss": 8.4699,
      "step": 500
    },
    {
      "epoch": 0.3332222592469177,
      "grad_norm": 1.640729546546936,
      "learning_rate": 5.553704320781962e-06,
      "loss": 7.446,
      "step": 1000
    },
    {
      "epoch": 0.49983338887037654,
      "grad_norm": 1.6770328283309937,
      "learning_rate": 8.330556481172942e-06,
      "loss": 6.6034,
      "step": 1500
    },
    {
      "epoch": 0.6664445184938353,
      "grad_norm": 2.338146924972534,
      "learning_rate": 1.1107408641563923e-05,
      "loss": 5.9787,
      "step": 2000
    },
    {
      "epoch": 0.8330556481172943,
      "grad_norm": 2.557213068008423,
      "learning_rate": 1.3884260801954905e-05,
      "loss": 5.5732,
      "step": 2500
    },
    {
      "epoch": 0.9996667777407531,
      "grad_norm": 1.7546786069869995,
      "learning_rate": 1.6661112962345883e-05,
      "loss": 5.2881,
      "step": 3000
    },
    {
      "epoch": 1.166277907364212,
      "grad_norm": 1.7593083381652832,
      "learning_rate": 1.9437965122736867e-05,
      "loss": 5.0771,
      "step": 3500
    },
    {
      "epoch": 1.3328890369876707,
      "grad_norm": 1.860612392425537,
      "learning_rate": 2.2214817283127847e-05,
      "loss": 4.8991,
      "step": 4000
    },
    {
      "epoch": 1.4995001666111296,
      "grad_norm": 2.036371946334839,
      "learning_rate": 2.4991669443518826e-05,
      "loss": 4.7465,
      "step": 4500
    },
    {
      "epoch": 1.6661112962345883,
      "grad_norm": 1.8470864295959473,
      "learning_rate": 2.776852160390981e-05,
      "loss": 4.5925,
      "step": 5000
    },
    {
      "epoch": 1.8327224258580475,
      "grad_norm": 1.9861804246902466,
      "learning_rate": 3.0545373764300786e-05,
      "loss": 4.4767,
      "step": 5500
    },
    {
      "epoch": 1.9993335554815062,
      "grad_norm": 2.018094062805176,
      "learning_rate": 3.3322225924691766e-05,
      "loss": 4.3708,
      "step": 6000
    },
    {
      "epoch": 2.165944685104965,
      "grad_norm": 1.8410370349884033,
      "learning_rate": 3.609352438076197e-05,
      "loss": 4.2741,
      "step": 6500
    },
    {
      "epoch": 2.332555814728424,
      "grad_norm": 1.7712337970733643,
      "learning_rate": 3.887037654115295e-05,
      "loss": 4.192,
      "step": 7000
    },
    {
      "epoch": 2.4991669443518827,
      "grad_norm": 1.7352423667907715,
      "learning_rate": 4.164722870154393e-05,
      "loss": 4.1192,
      "step": 7500
    },
    {
      "epoch": 2.6657780739753414,
      "grad_norm": 1.8459163904190063,
      "learning_rate": 4.442408086193491e-05,
      "loss": 4.0351,
      "step": 8000
    },
    {
      "epoch": 2.8323892035988005,
      "grad_norm": 2.009974956512451,
      "learning_rate": 4.719537931800511e-05,
      "loss": 3.9709,
      "step": 8500
    },
    {
      "epoch": 2.9990003332222592,
      "grad_norm": 1.7068768739700317,
      "learning_rate": 4.997223147839609e-05,
      "loss": 3.899,
      "step": 9000
    },
    {
      "epoch": 3.165611462845718,
      "grad_norm": 1.6234753131866455,
      "learning_rate": 5.274908363878708e-05,
      "loss": 3.8237,
      "step": 9500
    },
    {
      "epoch": 3.332222592469177,
      "grad_norm": 1.786528468132019,
      "learning_rate": 5.552593579917805e-05,
      "loss": 3.7704,
      "step": 10000
    },
    {
      "epoch": 3.4988337220926358,
      "grad_norm": 1.7539526224136353,
      "learning_rate": 5.829723425524826e-05,
      "loss": 3.7183,
      "step": 10500
    },
    {
      "epoch": 3.665444851716095,
      "grad_norm": 1.6715501546859741,
      "learning_rate": 6.107408641563923e-05,
      "loss": 3.6671,
      "step": 11000
    },
    {
      "epoch": 3.8320559813395536,
      "grad_norm": 1.7561357021331787,
      "learning_rate": 6.385093857603022e-05,
      "loss": 3.6214,
      "step": 11500
    },
    {
      "epoch": 3.9986671109630123,
      "grad_norm": 1.5936201810836792,
      "learning_rate": 6.662779073642119e-05,
      "loss": 3.5782,
      "step": 12000
    },
    {
      "epoch": 4.1652782405864714,
      "grad_norm": 1.7363481521606445,
      "learning_rate": 6.940464289681218e-05,
      "loss": 3.5291,
      "step": 12500
    },
    {
      "epoch": 4.33188937020993,
      "grad_norm": 1.5552008152008057,
      "learning_rate": 7.217594135288238e-05,
      "loss": 3.5017,
      "step": 13000
    },
    {
      "epoch": 4.498500499833389,
      "grad_norm": 1.4608962535858154,
      "learning_rate": 7.495279351327336e-05,
      "loss": 3.4685,
      "step": 13500
    },
    {
      "epoch": 4.665111629456848,
      "grad_norm": 1.470942735671997,
      "learning_rate": 7.772964567366434e-05,
      "loss": 3.4407,
      "step": 14000
    },
    {
      "epoch": 4.831722759080306,
      "grad_norm": 1.4744900465011597,
      "learning_rate": 8.050649783405532e-05,
      "loss": 3.4156,
      "step": 14500
    },
    {
      "epoch": 4.998333888703765,
      "grad_norm": 1.449549913406372,
      "learning_rate": 8.32833499944463e-05,
      "loss": 3.3933,
      "step": 15000
    },
    {
      "epoch": 5.1649450183272245,
      "grad_norm": 1.4103004932403564,
      "learning_rate": 8.606020215483728e-05,
      "loss": 3.355,
      "step": 15500
    },
    {
      "epoch": 5.331556147950683,
      "grad_norm": 1.3490815162658691,
      "learning_rate": 8.883705431522826e-05,
      "loss": 3.335,
      "step": 16000
    },
    {
      "epoch": 5.498167277574142,
      "grad_norm": 1.3762222528457642,
      "learning_rate": 9.161390647561924e-05,
      "loss": 3.3183,
      "step": 16500
    },
    {
      "epoch": 5.664778407197601,
      "grad_norm": 1.3008846044540405,
      "learning_rate": 9.438520493168944e-05,
      "loss": 3.3013,
      "step": 17000
    },
    {
      "epoch": 5.831389536821059,
      "grad_norm": 1.3132846355438232,
      "learning_rate": 9.716205709208043e-05,
      "loss": 3.2846,
      "step": 17500
    },
    {
      "epoch": 5.9980006664445185,
      "grad_norm": 1.194407343864441,
      "learning_rate": 9.99389092524714e-05,
      "loss": 3.2706,
      "step": 18000
    },
    {
      "epoch": 6.164611796067978,
      "grad_norm": 1.1745057106018066,
      "learning_rate": 9.996657887827809e-05,
      "loss": 3.2324,
      "step": 18500
    },
    {
      "epoch": 6.331222925691436,
      "grad_norm": 1.1769245862960815,
      "learning_rate": 9.986361454903414e-05,
      "loss": 3.2237,
      "step": 19000
    },
    {
      "epoch": 6.497834055314895,
      "grad_norm": 1.1529046297073364,
      "learning_rate": 9.969082137309689e-05,
      "loss": 3.2103,
      "step": 19500
    },
    {
      "epoch": 6.664445184938354,
      "grad_norm": 1.1225526332855225,
      "learning_rate": 9.944857739312099e-05,
      "loss": 3.1936,
      "step": 20000
    },
    {
      "epoch": 6.831056314561812,
      "grad_norm": 1.1167833805084229,
      "learning_rate": 9.913722118348934e-05,
      "loss": 3.1818,
      "step": 20500
    },
    {
      "epoch": 6.9976674441852715,
      "grad_norm": 1.093309998512268,
      "learning_rate": 9.875801618300155e-05,
      "loss": 3.1733,
      "step": 21000
    },
    {
      "epoch": 7.164278573808731,
      "grad_norm": 1.1539673805236816,
      "learning_rate": 9.83099727084671e-05,
      "loss": 3.1342,
      "step": 21500
    },
    {
      "epoch": 7.330889703432189,
      "grad_norm": 1.1930997371673584,
      "learning_rate": 9.779440838491111e-05,
      "loss": 3.1356,
      "step": 22000
    },
    {
      "epoch": 7.497500833055648,
      "grad_norm": 1.0827438831329346,
      "learning_rate": 9.721204379524642e-05,
      "loss": 3.1231,
      "step": 22500
    },
    {
      "epoch": 7.664111962679107,
      "grad_norm": 1.0850555896759033,
      "learning_rate": 9.656505485544595e-05,
      "loss": 3.1126,
      "step": 23000
    },
    {
      "epoch": 7.8307230923025655,
      "grad_norm": 1.0119590759277344,
      "learning_rate": 9.585175299579849e-05,
      "loss": 3.1049,
      "step": 23500
    },
    {
      "epoch": 7.997334221926025,
      "grad_norm": 1.0027412176132202,
      "learning_rate": 9.507436603906176e-05,
      "loss": 3.1004,
      "step": 24000
    },
    {
      "epoch": 8.163945351549483,
      "grad_norm": 1.0899256467819214,
      "learning_rate": 9.423398050680459e-05,
      "loss": 3.0591,
      "step": 24500
    },
    {
      "epoch": 8.330556481172943,
      "grad_norm": 1.0424436330795288,
      "learning_rate": 9.333363626660517e-05,
      "loss": 3.0582,
      "step": 25000
    }
  ],
  "logging_steps": 500,
  "max_steps": 60020,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.046659236626432e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}