{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 886,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0451913571529445,
      "grad_norm": 1.2982341051101685,
      "learning_rate": 9.5e-05,
      "loss": 2.2395,
      "step": 20
    },
    {
      "epoch": 0.090382714305889,
      "grad_norm": 0.2602206766605377,
      "learning_rate": 0.000195,
      "loss": 0.3192,
      "step": 40
    },
    {
      "epoch": 0.1355740714588335,
      "grad_norm": 0.11576834321022034,
      "learning_rate": 0.000199892800315311,
      "loss": 0.0387,
      "step": 60
    },
    {
      "epoch": 0.180765428611778,
      "grad_norm": 0.08919216692447662,
      "learning_rate": 0.0001995485952541953,
      "loss": 0.0283,
      "step": 80
    },
    {
      "epoch": 0.2259567857647225,
      "grad_norm": 0.07938820868730545,
      "learning_rate": 0.00019896790549505508,
      "loss": 0.027,
      "step": 100
    },
    {
      "epoch": 0.271148142917667,
      "grad_norm": 0.10239128768444061,
      "learning_rate": 0.00019815211050730418,
      "loss": 0.0268,
      "step": 120
    },
    {
      "epoch": 0.3163395000706115,
      "grad_norm": 0.07505609840154648,
      "learning_rate": 0.00019710314826938252,
      "loss": 0.0265,
      "step": 140
    },
    {
      "epoch": 0.361530857223556,
      "grad_norm": 0.07303870469331741,
      "learning_rate": 0.00019582351066495192,
      "loss": 0.0263,
      "step": 160
    },
    {
      "epoch": 0.40672221437650047,
      "grad_norm": 0.0660228356719017,
      "learning_rate": 0.0001943162375632511,
      "loss": 0.0262,
      "step": 180
    },
    {
      "epoch": 0.451913571529445,
      "grad_norm": 0.06548438221216202,
      "learning_rate": 0.000192584909597672,
      "loss": 0.026,
      "step": 200
    },
    {
      "epoch": 0.4971049286823895,
      "grad_norm": 0.06231554225087166,
      "learning_rate": 0.0001906336396597133,
      "loss": 0.0257,
      "step": 220
    },
    {
      "epoch": 0.542296285835334,
      "grad_norm": 0.05514415726065636,
      "learning_rate": 0.00018846706312851684,
      "loss": 0.026,
      "step": 240
    },
    {
      "epoch": 0.5874876429882785,
      "grad_norm": 0.04507150128483772,
      "learning_rate": 0.00018609032685919813,
      "loss": 0.026,
      "step": 260
    },
    {
      "epoch": 0.632679000141223,
      "grad_norm": 0.04801488667726517,
      "learning_rate": 0.00018350907695612961,
      "loss": 0.0257,
      "step": 280
    },
    {
      "epoch": 0.6778703572941674,
      "grad_norm": 0.05931699648499489,
      "learning_rate": 0.00018072944536022211,
      "loss": 0.0254,
      "step": 300
    },
    {
      "epoch": 0.723061714447112,
      "grad_norm": 0.04856206849217415,
      "learning_rate": 0.00017775803528206736,
      "loss": 0.0255,
      "step": 320
    },
    {
      "epoch": 0.7682530716000565,
      "grad_norm": 0.04942520335316658,
      "learning_rate": 0.00017460190551554634,
      "loss": 0.0256,
      "step": 340
    },
    {
      "epoch": 0.8134444287530009,
      "grad_norm": 0.04102044925093651,
      "learning_rate": 0.0001712685536691673,
      "loss": 0.0254,
      "step": 360
    },
    {
      "epoch": 0.8586357859059455,
      "grad_norm": 0.04938124492764473,
      "learning_rate": 0.00016776589835496876,
      "loss": 0.0258,
      "step": 380
    },
    {
      "epoch": 0.90382714305889,
      "grad_norm": 0.03212631866335869,
      "learning_rate": 0.00016410226037729908,
      "loss": 0.0256,
      "step": 400
    },
    {
      "epoch": 0.9490185002118345,
      "grad_norm": 0.03286610171198845,
      "learning_rate": 0.00016028634296615972,
      "loss": 0.0254,
      "step": 420
    },
    {
      "epoch": 0.994209857364779,
      "grad_norm": 0.03531966730952263,
      "learning_rate": 0.00015632721110206958,
      "loss": 0.0252,
      "step": 440
    },
    {
      "epoch": 1.038412653580003,
      "grad_norm": 0.046482112258672714,
      "learning_rate": 0.0001522342699815653,
      "loss": 0.0257,
      "step": 460
    },
    {
      "epoch": 1.0836040107329472,
      "grad_norm": 0.05457223206758499,
      "learning_rate": 0.00014801724267449477,
      "loss": 0.0256,
      "step": 480
    },
    {
      "epoch": 1.1287953678858917,
      "grad_norm": 0.040691521018743515,
      "learning_rate": 0.00014368614702617996,
      "loss": 0.0248,
      "step": 500
    },
    {
      "epoch": 1.1739867250388363,
      "grad_norm": 0.042198147624731064,
      "learning_rate": 0.00013925127185931993,
      "loss": 0.0254,
      "step": 520
    },
    {
      "epoch": 1.2191780821917808,
      "grad_norm": 0.03628581762313843,
      "learning_rate": 0.0001347231525321678,
      "loss": 0.0253,
      "step": 540
    },
    {
      "epoch": 1.2643694393447253,
      "grad_norm": 0.038468316197395325,
      "learning_rate": 0.00013011254591104577,
      "loss": 0.0252,
      "step": 560
    },
    {
      "epoch": 1.3095607964976699,
      "grad_norm": 0.046080492436885834,
      "learning_rate": 0.00012543040481665133,
      "loss": 0.0256,
      "step": 580
    },
    {
      "epoch": 1.3547521536506144,
      "grad_norm": 0.03800000995397568,
      "learning_rate": 0.00012068785200486044,
      "loss": 0.0254,
      "step": 600
    },
    {
      "epoch": 1.399943510803559,
      "grad_norm": 0.03493132442235947,
      "learning_rate": 0.00011589615374383794,
      "loss": 0.0253,
      "step": 620
    },
    {
      "epoch": 1.4451348679565033,
      "grad_norm": 0.04193327575922012,
      "learning_rate": 0.00011106669305022396,
      "loss": 0.025,
      "step": 640
    },
    {
      "epoch": 1.4903262251094478,
      "grad_norm": 0.03124556504189968,
      "learning_rate": 0.00010621094264797647,
      "loss": 0.0254,
      "step": 660
    },
    {
      "epoch": 1.5355175822623923,
      "grad_norm": 0.03751407563686371,
      "learning_rate": 0.00010134043771410743,
      "loss": 0.0252,
      "step": 680
    },
    {
      "epoch": 1.5807089394153369,
      "grad_norm": 0.034240107983350754,
      "learning_rate": 9.646674847605779e-05,
      "loss": 0.0251,
      "step": 700
    },
    {
      "epoch": 1.6259002965682812,
      "grad_norm": 0.03505250811576843,
      "learning_rate": 9.160145272580727e-05,
      "loss": 0.0249,
      "step": 720
    },
    {
      "epoch": 1.6710916537212257,
      "grad_norm": 0.03779418393969536,
      "learning_rate": 8.675610831601423e-05,
      "loss": 0.025,
      "step": 740
    },
    {
      "epoch": 1.7162830108741702,
      "grad_norm": 0.037357985973358154,
      "learning_rate": 8.194222570352295e-05,
      "loss": 0.025,
      "step": 760
    },
    {
      "epoch": 1.7614743680271148,
      "grad_norm": 0.03674224391579628,
      "learning_rate": 7.717124060546254e-05,
      "loss": 0.0249,
      "step": 780
    },
    {
      "epoch": 1.8066657251800593,
      "grad_norm": 0.03422726318240166,
      "learning_rate": 7.245448683289604e-05,
      "loss": 0.0248,
      "step": 800
    },
    {
      "epoch": 1.8518570823330038,
      "grad_norm": 0.03446003794670105,
      "learning_rate": 6.780316936655382e-05,
      "loss": 0.0249,
      "step": 820
    },
    {
      "epoch": 1.8970484394859484,
      "grad_norm": 0.03549942001700401,
      "learning_rate": 6.322833773861297e-05,
      "loss": 0.0248,
      "step": 840
    },
    {
      "epoch": 1.942239796638893,
      "grad_norm": 0.03940591961145401,
      "learning_rate": 5.874085978375547e-05,
      "loss": 0.0249,
      "step": 860
    },
    {
      "epoch": 1.9874311537918374,
      "grad_norm": 0.029423682019114494,
      "learning_rate": 5.4351395821861665e-05,
      "loss": 0.0248,
      "step": 880
    }
  ],
  "logging_steps": 20,
  "max_steps": 1329,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.363379718268518e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}