{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4500.0,
  "eval_steps": 500,
  "global_step": 4500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 100.0,
      "grad_norm": 0.09399763494729996,
      "learning_rate": 0.00019975640502598244,
      "loss": 0.4328,
      "step": 100
    },
    {
      "epoch": 200.0,
      "grad_norm": 0.008415983989834785,
      "learning_rate": 0.00019902680687415705,
      "loss": 0.0012,
      "step": 200
    },
    {
      "epoch": 300.0,
      "grad_norm": 0.004644488915801048,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.0003,
      "step": 300
    },
    {
      "epoch": 400.0,
      "grad_norm": 0.002689788118004799,
      "learning_rate": 0.0001961261695938319,
      "loss": 0.0002,
      "step": 400
    },
    {
      "epoch": 500.0,
      "grad_norm": 0.0023731214459985495,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.0002,
      "step": 500
    },
    {
      "epoch": 600.0,
      "grad_norm": 0.0013438506284728646,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0001,
      "step": 600
    },
    {
      "epoch": 700.0,
      "grad_norm": 0.0014795837923884392,
      "learning_rate": 0.00018829475928589271,
      "loss": 0.0001,
      "step": 700
    },
    {
      "epoch": 800.0,
      "grad_norm": 0.0012762774713337421,
      "learning_rate": 0.0001848048096156426,
      "loss": 0.0001,
      "step": 800
    },
    {
      "epoch": 900.0,
      "grad_norm": 0.0009800918633118272,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0001,
      "step": 900
    },
    {
      "epoch": 1000.0,
      "grad_norm": 0.001324972603470087,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 1100.0,
      "grad_norm": 0.0007171508623287082,
      "learning_rate": 0.0001719339800338651,
      "loss": 0.0,
      "step": 1100
    },
    {
      "epoch": 1200.0,
      "grad_norm": 0.0006033563986420631,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0,
      "step": 1200
    },
    {
      "epoch": 1300.0,
      "grad_norm": 0.0005752713768742979,
      "learning_rate": 0.0001615661475325658,
      "loss": 0.0,
      "step": 1300
    },
    {
      "epoch": 1400.0,
      "grad_norm": 0.000505088537465781,
      "learning_rate": 0.0001559192903470747,
      "loss": 0.0,
      "step": 1400
    },
    {
      "epoch": 1500.0,
      "grad_norm": 0.0010271323844790459,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 1500
    },
    {
      "epoch": 1600.0,
      "grad_norm": 0.0004594104248099029,
      "learning_rate": 0.00014383711467890774,
      "loss": 0.0,
      "step": 1600
    },
    {
      "epoch": 1700.0,
      "grad_norm": 0.00037568225525319576,
      "learning_rate": 0.00013746065934159123,
      "loss": 0.0,
      "step": 1700
    },
    {
      "epoch": 1800.0,
      "grad_norm": 0.0006100877653807402,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 1800
    },
    {
      "epoch": 1900.0,
      "grad_norm": 0.0006700914236716926,
      "learning_rate": 0.00012419218955996676,
      "loss": 0.0,
      "step": 1900
    },
    {
      "epoch": 2000.0,
      "grad_norm": 0.0004988115979358554,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.0,
      "step": 2000
    },
    {
      "epoch": 2100.0,
      "grad_norm": 0.0003406632167752832,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0,
      "step": 2100
    },
    {
      "epoch": 2200.0,
      "grad_norm": 0.00035023069358430803,
      "learning_rate": 0.00010348994967025012,
      "loss": 0.0,
      "step": 2200
    },
    {
      "epoch": 2300.0,
      "grad_norm": 0.00035629895864985883,
      "learning_rate": 9.657982181634475e-05,
      "loss": 0.0003,
      "step": 2300
    },
    {
      "epoch": 2400.0,
      "grad_norm": 0.00036875385558232665,
      "learning_rate": 8.961658694111929e-05,
      "loss": 0.0,
      "step": 2400
    },
    {
      "epoch": 2500.0,
      "grad_norm": 0.0003993694263044745,
      "learning_rate": 8.270393901057964e-05,
      "loss": 0.0,
      "step": 2500
    },
    {
      "epoch": 2600.0,
      "grad_norm": 0.00030426381272263825,
      "learning_rate": 7.587555575058649e-05,
      "loss": 0.0,
      "step": 2600
    },
    {
      "epoch": 2700.0,
      "grad_norm": 0.0005253420677036047,
      "learning_rate": 6.916470435799587e-05,
      "loss": 0.0,
      "step": 2700
    },
    {
      "epoch": 2800.0,
      "grad_norm": 0.000337547215167433,
      "learning_rate": 6.260407942621998e-05,
      "loss": 0.0,
      "step": 2800
    },
    {
      "epoch": 2900.0,
      "grad_norm": 0.00034444258199073374,
      "learning_rate": 5.622564366045472e-05,
      "loss": 0.0,
      "step": 2900
    },
    {
      "epoch": 3000.0,
      "grad_norm": 0.00015016530232969671,
      "learning_rate": 5.006047215859289e-05,
      "loss": 0.0,
      "step": 3000
    },
    {
      "epoch": 3100.0,
      "grad_norm": 0.00021075463155284524,
      "learning_rate": 4.413860101647055e-05,
      "loss": 0.0,
      "step": 3100
    },
    {
      "epoch": 3200.0,
      "grad_norm": 0.00025653259945102036,
      "learning_rate": 3.8488880995027786e-05,
      "loss": 0.0,
      "step": 3200
    },
    {
      "epoch": 3300.0,
      "grad_norm": 0.00018334439664613456,
      "learning_rate": 3.313883696230119e-05,
      "loss": 0.0,
      "step": 3300
    },
    {
      "epoch": 3400.0,
      "grad_norm": 0.00026421225629746914,
      "learning_rate": 2.8114533795033683e-05,
      "loss": 0.0,
      "step": 3400
    },
    {
      "epoch": 3500.0,
      "grad_norm": 0.00012184748629806563,
      "learning_rate": 2.3440449393214948e-05,
      "loss": 0.0,
      "step": 3500
    },
    {
      "epoch": 3600.0,
      "grad_norm": 0.0003666615521069616,
      "learning_rate": 1.9139355426213347e-05,
      "loss": 0.0,
      "step": 3600
    },
    {
      "epoch": 3700.0,
      "grad_norm": 0.00032034661853685975,
      "learning_rate": 1.5232206391491699e-05,
      "loss": 0.0,
      "step": 3700
    },
    {
      "epoch": 3800.0,
      "grad_norm": 0.000288996787276119,
      "learning_rate": 1.1738037526401857e-05,
      "loss": 0.0,
      "step": 3800
    },
    {
      "epoch": 3900.0,
      "grad_norm": 0.00018436899699736387,
      "learning_rate": 8.67387207042194e-06,
      "loss": 0.0,
      "step": 3900
    },
    {
      "epoch": 4000.0,
      "grad_norm": 0.0004207100428175181,
      "learning_rate": 6.054638329644657e-06,
      "loss": 0.0,
      "step": 4000
    },
    {
      "epoch": 4100.0,
      "grad_norm": 0.0002757696493063122,
      "learning_rate": 3.893096947570618e-06,
      "loss": 0.0,
      "step": 4100
    },
    {
      "epoch": 4200.0,
      "grad_norm": 0.000379523349693045,
      "learning_rate": 2.1997787365358958e-06,
      "loss": 0.0,
      "step": 4200
    },
    {
      "epoch": 4300.0,
      "grad_norm": 0.0002130218199454248,
      "learning_rate": 9.829333726529056e-07,
      "loss": 0.0,
      "step": 4300
    },
    {
      "epoch": 4400.0,
      "grad_norm": 0.00015009118942543864,
      "learning_rate": 2.484892042176279e-07,
      "loss": 0.0,
      "step": 4400
    },
    {
      "epoch": 4500.0,
      "grad_norm": 0.00018362345872446895,
      "learning_rate": 2.4369392592760164e-11,
      "loss": 0.0,
      "step": 4500
    }
  ],
  "logging_steps": 100,
  "max_steps": 4500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4500,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 884950147584000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}