{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 331,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015105740181268883,
      "grad_norm": 65.32524871826172,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 1.7699,
      "step": 5
    },
    {
      "epoch": 0.030211480362537766,
      "grad_norm": 1.1226208209991455,
      "learning_rate": 5.294117647058824e-06,
      "loss": 0.3128,
      "step": 10
    },
    {
      "epoch": 0.045317220543806644,
      "grad_norm": 1.0650861263275146,
      "learning_rate": 8.23529411764706e-06,
      "loss": 0.0691,
      "step": 15
    },
    {
      "epoch": 0.06042296072507553,
      "grad_norm": 0.5207144021987915,
      "learning_rate": 1.1176470588235295e-05,
      "loss": 0.0675,
      "step": 20
    },
    {
      "epoch": 0.0755287009063444,
      "grad_norm": 0.518444299697876,
      "learning_rate": 1.4117647058823532e-05,
      "loss": 0.0669,
      "step": 25
    },
    {
      "epoch": 0.09063444108761329,
      "grad_norm": 0.43817996978759766,
      "learning_rate": 1.7058823529411767e-05,
      "loss": 0.0658,
      "step": 30
    },
    {
      "epoch": 0.10574018126888217,
      "grad_norm": 1.0586720705032349,
      "learning_rate": 2e-05,
      "loss": 0.0648,
      "step": 35
    },
    {
      "epoch": 0.12084592145015106,
      "grad_norm": 1.3109872341156006,
      "learning_rate": 1.9986017152454497e-05,
      "loss": 0.0657,
      "step": 40
    },
    {
      "epoch": 0.13595166163141995,
      "grad_norm": 0.48269444704055786,
      "learning_rate": 1.9944107713823068e-05,
      "loss": 0.0609,
      "step": 45
    },
    {
      "epoch": 0.1510574018126888,
      "grad_norm": 0.9956803917884827,
      "learning_rate": 1.9874388886763944e-05,
      "loss": 0.0712,
      "step": 50
    },
    {
      "epoch": 0.1661631419939577,
      "grad_norm": 0.8316070437431335,
      "learning_rate": 1.9777055644823087e-05,
      "loss": 0.0669,
      "step": 55
    },
    {
      "epoch": 0.18126888217522658,
      "grad_norm": 0.09602731466293335,
      "learning_rate": 1.9652380187177128e-05,
      "loss": 0.0623,
      "step": 60
    },
    {
      "epoch": 0.19637462235649547,
      "grad_norm": 0.23348145186901093,
      "learning_rate": 1.9500711177409456e-05,
      "loss": 0.0561,
      "step": 65
    },
    {
      "epoch": 0.21148036253776434,
      "grad_norm": 0.1733577698469162,
      "learning_rate": 1.932247276844826e-05,
      "loss": 0.0614,
      "step": 70
    },
    {
      "epoch": 0.22658610271903323,
      "grad_norm": 0.21881505846977234,
      "learning_rate": 1.9118163416393392e-05,
      "loss": 0.0567,
      "step": 75
    },
    {
      "epoch": 0.24169184290030213,
      "grad_norm": 0.3463956117630005,
      "learning_rate": 1.8888354486549238e-05,
      "loss": 0.0598,
      "step": 80
    },
    {
      "epoch": 0.256797583081571,
      "grad_norm": 0.11425940692424774,
      "learning_rate": 1.863368865556191e-05,
      "loss": 0.0564,
      "step": 85
    },
    {
      "epoch": 0.2719033232628399,
      "grad_norm": 0.15162110328674316,
      "learning_rate": 1.8354878114129368e-05,
      "loss": 0.056,
      "step": 90
    },
    {
      "epoch": 0.28700906344410876,
      "grad_norm": 0.1482110172510147,
      "learning_rate": 1.8052702575310588e-05,
      "loss": 0.0493,
      "step": 95
    },
    {
      "epoch": 0.3021148036253776,
      "grad_norm": 0.36696767807006836,
      "learning_rate": 1.772800709400383e-05,
      "loss": 0.048,
      "step": 100
    },
    {
      "epoch": 0.31722054380664655,
      "grad_norm": 0.25465500354766846,
      "learning_rate": 1.7381699703691866e-05,
      "loss": 0.0537,
      "step": 105
    },
    {
      "epoch": 0.3323262839879154,
      "grad_norm": 0.38290655612945557,
      "learning_rate": 1.7014748877063212e-05,
      "loss": 0.0537,
      "step": 110
    },
    {
      "epoch": 0.3474320241691843,
      "grad_norm": 0.3702133297920227,
      "learning_rate": 1.6628180817610963e-05,
      "loss": 0.051,
      "step": 115
    },
    {
      "epoch": 0.36253776435045315,
      "grad_norm": 0.1437833160161972,
      "learning_rate": 1.6223076589783368e-05,
      "loss": 0.0473,
      "step": 120
    },
    {
      "epoch": 0.3776435045317221,
      "grad_norm": 0.15008145570755005,
      "learning_rate": 1.5800569095711983e-05,
      "loss": 0.0509,
      "step": 125
    },
    {
      "epoch": 0.39274924471299094,
      "grad_norm": 0.15623906254768372,
      "learning_rate": 1.5361839906972095e-05,
      "loss": 0.0577,
      "step": 130
    },
    {
      "epoch": 0.4078549848942598,
      "grad_norm": 0.10994814336299896,
      "learning_rate": 1.4908115960235683e-05,
      "loss": 0.0513,
      "step": 135
    },
    {
      "epoch": 0.4229607250755287,
      "grad_norm": 0.15456193685531616,
      "learning_rate": 1.4440666126057743e-05,
      "loss": 0.0572,
      "step": 140
    },
    {
      "epoch": 0.4380664652567976,
      "grad_norm": 0.16252553462982178,
      "learning_rate": 1.396079766039157e-05,
      "loss": 0.0538,
      "step": 145
    },
    {
      "epoch": 0.45317220543806647,
      "grad_norm": 0.4133623540401459,
      "learning_rate": 1.3469852548756626e-05,
      "loss": 0.0512,
      "step": 150
    },
    {
      "epoch": 0.46827794561933533,
      "grad_norm": 0.1537550389766693,
      "learning_rate": 1.296920375328275e-05,
      "loss": 0.0494,
      "step": 155
    },
    {
      "epoch": 0.48338368580060426,
      "grad_norm": 0.5091661214828491,
      "learning_rate": 1.2460251373126136e-05,
      "loss": 0.0513,
      "step": 160
    },
    {
      "epoch": 0.4984894259818731,
      "grad_norm": 0.18158994615077972,
      "learning_rate": 1.194441872899471e-05,
      "loss": 0.046,
      "step": 165
    },
    {
      "epoch": 0.513595166163142,
      "grad_norm": 0.39592429995536804,
      "learning_rate": 1.1423148382732854e-05,
      "loss": 0.05,
      "step": 170
    },
    {
      "epoch": 0.5287009063444109,
      "grad_norm": 0.22556884586811066,
      "learning_rate": 1.0897898103096917e-05,
      "loss": 0.0485,
      "step": 175
    },
    {
      "epoch": 0.5438066465256798,
      "grad_norm": 0.35634785890579224,
      "learning_rate": 1.0370136789003582e-05,
      "loss": 0.0458,
      "step": 180
    },
    {
      "epoch": 0.5589123867069486,
      "grad_norm": 0.5002294778823853,
      "learning_rate": 9.841340361651921e-06,
      "loss": 0.0471,
      "step": 185
    },
    {
      "epoch": 0.5740181268882175,
      "grad_norm": 0.1892608106136322,
      "learning_rate": 9.312987637007191e-06,
      "loss": 0.0397,
      "step": 190
    },
    {
      "epoch": 0.5891238670694864,
      "grad_norm": 0.2997090816497803,
      "learning_rate": 8.786556190189183e-06,
      "loss": 0.0432,
      "step": 195
    },
    {
      "epoch": 0.6042296072507553,
      "grad_norm": 0.10828253626823425,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.0456,
      "step": 200
    },
    {
      "epoch": 0.6193353474320241,
      "grad_norm": 0.11140269786119461,
      "learning_rate": 7.745336448461958e-06,
      "loss": 0.0464,
      "step": 205
    },
    {
      "epoch": 0.6344410876132931,
      "grad_norm": 0.21382257342338562,
      "learning_rate": 7.233459996934731e-06,
      "loss": 0.0436,
      "step": 210
    },
    {
      "epoch": 0.649546827794562,
      "grad_norm": 0.22236904501914978,
      "learning_rate": 6.729320366825785e-06,
      "loss": 0.0395,
      "step": 215
    },
    {
      "epoch": 0.6646525679758308,
      "grad_norm": 0.18689888715744019,
      "learning_rate": 6.234327419653013e-06,
      "loss": 0.0434,
      "step": 220
    },
    {
      "epoch": 0.6797583081570997,
      "grad_norm": 0.11527472734451294,
      "learning_rate": 5.749865437599703e-06,
      "loss": 0.0448,
      "step": 225
    },
    {
      "epoch": 0.6948640483383686,
      "grad_norm": 0.12977807223796844,
      "learning_rate": 5.277289252273175e-06,
      "loss": 0.0443,
      "step": 230
    },
    {
      "epoch": 0.7099697885196374,
      "grad_norm": 0.28918567299842834,
      "learning_rate": 4.817920455824045e-06,
      "loss": 0.042,
      "step": 235
    },
    {
      "epoch": 0.7250755287009063,
      "grad_norm": 0.1708402782678604,
      "learning_rate": 4.373043705021899e-06,
      "loss": 0.036,
      "step": 240
    },
    {
      "epoch": 0.7401812688821753,
      "grad_norm": 0.2525939345359802,
      "learning_rate": 3.943903128623336e-06,
      "loss": 0.0392,
      "step": 245
    },
    {
      "epoch": 0.7552870090634441,
      "grad_norm": 0.3220805525779724,
      "learning_rate": 3.5316988480794255e-06,
      "loss": 0.036,
      "step": 250
    },
    {
      "epoch": 0.770392749244713,
      "grad_norm": 0.3768947422504425,
      "learning_rate": 3.1375836213126653e-06,
      "loss": 0.0373,
      "step": 255
    },
    {
      "epoch": 0.7854984894259819,
      "grad_norm": 0.15737439692020416,
      "learning_rate": 2.7626596189492983e-06,
      "loss": 0.0363,
      "step": 260
    },
    {
      "epoch": 0.8006042296072508,
      "grad_norm": 0.24124516546726227,
      "learning_rate": 2.4079753420225694e-06,
      "loss": 0.0345,
      "step": 265
    },
    {
      "epoch": 0.8157099697885196,
      "grad_norm": 0.2828380763530731,
      "learning_rate": 2.0745226897666858e-06,
      "loss": 0.0427,
      "step": 270
    },
    {
      "epoch": 0.8308157099697885,
      "grad_norm": 0.4477688670158386,
      "learning_rate": 1.7632341857016733e-06,
      "loss": 0.0382,
      "step": 275
    },
    {
      "epoch": 0.8459214501510574,
      "grad_norm": 0.35590699315071106,
      "learning_rate": 1.4749803697665366e-06,
      "loss": 0.0423,
      "step": 280
    },
    {
      "epoch": 0.8610271903323263,
      "grad_norm": 0.5138667821884155,
      "learning_rate": 1.2105673637938054e-06,
      "loss": 0.0411,
      "step": 285
    },
    {
      "epoch": 0.8761329305135952,
      "grad_norm": 0.2003919929265976,
      "learning_rate": 9.707346171337895e-07,
      "loss": 0.0366,
      "step": 290
    },
    {
      "epoch": 0.8912386706948641,
      "grad_norm": 0.4709911346435547,
      "learning_rate": 7.561528387330797e-07,
      "loss": 0.036,
      "step": 295
    },
    {
      "epoch": 0.9063444108761329,
      "grad_norm": 0.14394928514957428,
      "learning_rate": 5.674221214503639e-07,
      "loss": 0.0324,
      "step": 300
    },
    {
      "epoch": 0.9214501510574018,
      "grad_norm": 0.2846868932247162,
      "learning_rate": 4.0507026385502747e-07,
      "loss": 0.036,
      "step": 305
    },
    {
      "epoch": 0.9365558912386707,
      "grad_norm": 0.2303285300731659,
      "learning_rate": 2.6955129420176193e-07,
      "loss": 0.0389,
      "step": 310
    },
    {
      "epoch": 0.9516616314199395,
      "grad_norm": 0.27734264731407166,
      "learning_rate": 1.612442007090076e-07,
      "loss": 0.038,
      "step": 315
    },
    {
      "epoch": 0.9667673716012085,
      "grad_norm": 0.17142164707183838,
      "learning_rate": 8.04518716920466e-08,
      "loss": 0.0294,
      "step": 320
    },
    {
      "epoch": 0.9818731117824774,
      "grad_norm": 0.14783106744289398,
      "learning_rate": 2.7400248514776184e-08,
      "loss": 0.0394,
      "step": 325
    },
    {
      "epoch": 0.9969788519637462,
      "grad_norm": 0.2399517148733139,
      "learning_rate": 2.237693728981416e-09,
      "loss": 0.0394,
      "step": 330
    },
    {
      "epoch": 1.0,
      "step": 331,
      "total_flos": 3.732036479342346e+17,
      "train_loss": 0.07862781884086817,
      "train_runtime": 1853.8902,
      "train_samples_per_second": 11.415,
      "train_steps_per_second": 0.179
    }
  ],
  "logging_steps": 5,
  "max_steps": 331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.732036479342346e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}