{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0837464826477288,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001674929652954576,
      "grad_norm": 0.30847179889678955,
      "learning_rate": 2.9983250703470456e-05,
      "loss": 0.5044,
      "step": 50
    },
    {
      "epoch": 0.003349859305909152,
      "grad_norm": 0.04476890340447426,
      "learning_rate": 2.9966501406940907e-05,
      "loss": 0.0044,
      "step": 100
    },
    {
      "epoch": 0.005024788958863728,
      "grad_norm": 0.08374588936567307,
      "learning_rate": 2.9949752110411362e-05,
      "loss": 0.0026,
      "step": 150
    },
    {
      "epoch": 0.006699718611818304,
      "grad_norm": 0.0017046213615685701,
      "learning_rate": 2.9933002813881818e-05,
      "loss": 0.0023,
      "step": 200
    },
    {
      "epoch": 0.008374648264772879,
      "grad_norm": 0.019402090460062027,
      "learning_rate": 2.9916253517352273e-05,
      "loss": 0.0013,
      "step": 250
    },
    {
      "epoch": 0.010049577917727455,
      "grad_norm": 0.010655886493623257,
      "learning_rate": 2.9899504220822728e-05,
      "loss": 0.002,
      "step": 300
    },
    {
      "epoch": 0.011724507570682031,
      "grad_norm": 0.006348441354930401,
      "learning_rate": 2.9882754924293183e-05,
      "loss": 0.0017,
      "step": 350
    },
    {
      "epoch": 0.013399437223636608,
      "grad_norm": 0.06810770183801651,
      "learning_rate": 2.9866005627763634e-05,
      "loss": 0.0015,
      "step": 400
    },
    {
      "epoch": 0.015074366876591184,
      "grad_norm": 0.003874759189784527,
      "learning_rate": 2.984925633123409e-05,
      "loss": 0.0012,
      "step": 450
    },
    {
      "epoch": 0.016749296529545758,
      "grad_norm": 0.003985659219324589,
      "learning_rate": 2.9832507034704544e-05,
      "loss": 0.0012,
      "step": 500
    },
    {
      "epoch": 0.018424226182500336,
      "grad_norm": 0.01902610994875431,
      "learning_rate": 2.9815757738174996e-05,
      "loss": 0.0014,
      "step": 550
    },
    {
      "epoch": 0.02009915583545491,
      "grad_norm": 0.01615321636199951,
      "learning_rate": 2.979900844164545e-05,
      "loss": 0.0013,
      "step": 600
    },
    {
      "epoch": 0.02177408548840949,
      "grad_norm": 0.0055249775759875774,
      "learning_rate": 2.9782259145115903e-05,
      "loss": 0.0008,
      "step": 650
    },
    {
      "epoch": 0.023449015141364063,
      "grad_norm": 0.0019460869953036308,
      "learning_rate": 2.976550984858636e-05,
      "loss": 0.0011,
      "step": 700
    },
    {
      "epoch": 0.025123944794318637,
      "grad_norm": 0.012369350530207157,
      "learning_rate": 2.9748760552056816e-05,
      "loss": 0.0011,
      "step": 750
    },
    {
      "epoch": 0.026798874447273215,
      "grad_norm": 0.00836873333901167,
      "learning_rate": 2.9732011255527268e-05,
      "loss": 0.0013,
      "step": 800
    },
    {
      "epoch": 0.02847380410022779,
      "grad_norm": 0.0034731472842395306,
      "learning_rate": 2.9715261958997723e-05,
      "loss": 0.0016,
      "step": 850
    },
    {
      "epoch": 0.030148733753182368,
      "grad_norm": 0.015365710482001305,
      "learning_rate": 2.9698512662468178e-05,
      "loss": 0.0013,
      "step": 900
    },
    {
      "epoch": 0.031823663406136946,
      "grad_norm": 0.017056584358215332,
      "learning_rate": 2.968176336593863e-05,
      "loss": 0.0013,
      "step": 950
    },
    {
      "epoch": 0.033498593059091517,
      "grad_norm": 0.0038616659585386515,
      "learning_rate": 2.9665014069409085e-05,
      "loss": 0.0009,
      "step": 1000
    },
    {
      "epoch": 0.035173522712046094,
      "grad_norm": 0.0008767916006036103,
      "learning_rate": 2.964826477287954e-05,
      "loss": 0.0006,
      "step": 1050
    },
    {
      "epoch": 0.03684845236500067,
      "grad_norm": 0.050677187740802765,
      "learning_rate": 2.963151547634999e-05,
      "loss": 0.0014,
      "step": 1100
    },
    {
      "epoch": 0.03852338201795524,
      "grad_norm": 0.011451843194663525,
      "learning_rate": 2.961476617982045e-05,
      "loss": 0.0008,
      "step": 1150
    },
    {
      "epoch": 0.04019831167090982,
      "grad_norm": 0.00335301854647696,
      "learning_rate": 2.9598016883290905e-05,
      "loss": 0.0013,
      "step": 1200
    },
    {
      "epoch": 0.0418732413238644,
      "grad_norm": 0.01707889698445797,
      "learning_rate": 2.9581267586761356e-05,
      "loss": 0.0005,
      "step": 1250
    },
    {
      "epoch": 0.04354817097681898,
      "grad_norm": 0.0004460318305063993,
      "learning_rate": 2.956451829023181e-05,
      "loss": 0.0011,
      "step": 1300
    },
    {
      "epoch": 0.04522310062977355,
      "grad_norm": 0.00859643705189228,
      "learning_rate": 2.9547768993702266e-05,
      "loss": 0.0007,
      "step": 1350
    },
    {
      "epoch": 0.046898030282728126,
      "grad_norm": 0.012995535507798195,
      "learning_rate": 2.9531019697172718e-05,
      "loss": 0.0009,
      "step": 1400
    },
    {
      "epoch": 0.048572959935682704,
      "grad_norm": 0.004834771156311035,
      "learning_rate": 2.9514270400643173e-05,
      "loss": 0.0009,
      "step": 1450
    },
    {
      "epoch": 0.050247889588637275,
      "grad_norm": 0.006121751386672258,
      "learning_rate": 2.9497521104113628e-05,
      "loss": 0.0009,
      "step": 1500
    },
    {
      "epoch": 0.05192281924159185,
      "grad_norm": 0.004112472757697105,
      "learning_rate": 2.9480771807584083e-05,
      "loss": 0.0007,
      "step": 1550
    },
    {
      "epoch": 0.05359774889454643,
      "grad_norm": 0.0025941322091966867,
      "learning_rate": 2.9464022511054538e-05,
      "loss": 0.0008,
      "step": 1600
    },
    {
      "epoch": 0.055272678547501,
      "grad_norm": 0.0033354111947119236,
      "learning_rate": 2.9447273214524993e-05,
      "loss": 0.0014,
      "step": 1650
    },
    {
      "epoch": 0.05694760820045558,
      "grad_norm": 0.0006163300131447613,
      "learning_rate": 2.9430523917995445e-05,
      "loss": 0.0013,
      "step": 1700
    },
    {
      "epoch": 0.05862253785341016,
      "grad_norm": 0.03437214344739914,
      "learning_rate": 2.94137746214659e-05,
      "loss": 0.0011,
      "step": 1750
    },
    {
      "epoch": 0.060297467506364735,
      "grad_norm": 0.004870133940130472,
      "learning_rate": 2.939702532493635e-05,
      "loss": 0.0011,
      "step": 1800
    },
    {
      "epoch": 0.061972397159319306,
      "grad_norm": 0.011027672328054905,
      "learning_rate": 2.9380276028406807e-05,
      "loss": 0.0011,
      "step": 1850
    },
    {
      "epoch": 0.06364732681227389,
      "grad_norm": 0.005804801359772682,
      "learning_rate": 2.936352673187726e-05,
      "loss": 0.0009,
      "step": 1900
    },
    {
      "epoch": 0.06532225646522846,
      "grad_norm": 0.001421495107933879,
      "learning_rate": 2.9346777435347713e-05,
      "loss": 0.0007,
      "step": 1950
    },
    {
      "epoch": 0.06699718611818303,
      "grad_norm": 0.00775284506380558,
      "learning_rate": 2.9330028138818172e-05,
      "loss": 0.0008,
      "step": 2000
    },
    {
      "epoch": 0.06867211577113762,
      "grad_norm": 0.009989109821617603,
      "learning_rate": 2.9313278842288627e-05,
      "loss": 0.0013,
      "step": 2050
    },
    {
      "epoch": 0.07034704542409219,
      "grad_norm": 0.004933220334351063,
      "learning_rate": 2.929652954575908e-05,
      "loss": 0.0008,
      "step": 2100
    },
    {
      "epoch": 0.07202197507704676,
      "grad_norm": 0.0003998636966571212,
      "learning_rate": 2.9279780249229533e-05,
      "loss": 0.0005,
      "step": 2150
    },
    {
      "epoch": 0.07369690473000134,
      "grad_norm": 0.00017748262325767428,
      "learning_rate": 2.926303095269999e-05,
      "loss": 0.0006,
      "step": 2200
    },
    {
      "epoch": 0.07537183438295592,
      "grad_norm": 0.0009646079852245748,
      "learning_rate": 2.924628165617044e-05,
      "loss": 0.0007,
      "step": 2250
    },
    {
      "epoch": 0.07704676403591049,
      "grad_norm": 0.004842822439968586,
      "learning_rate": 2.9229532359640895e-05,
      "loss": 0.0011,
      "step": 2300
    },
    {
      "epoch": 0.07872169368886507,
      "grad_norm": 0.010380016639828682,
      "learning_rate": 2.921278306311135e-05,
      "loss": 0.001,
      "step": 2350
    },
    {
      "epoch": 0.08039662334181964,
      "grad_norm": 0.0021645210217684507,
      "learning_rate": 2.9196033766581802e-05,
      "loss": 0.0009,
      "step": 2400
    },
    {
      "epoch": 0.08207155299477421,
      "grad_norm": 0.0019599520601332188,
      "learning_rate": 2.917928447005226e-05,
      "loss": 0.0009,
      "step": 2450
    },
    {
      "epoch": 0.0837464826477288,
      "grad_norm": 0.03942473977804184,
      "learning_rate": 2.9162535173522715e-05,
      "loss": 0.0011,
      "step": 2500
    }
  ],
  "logging_steps": 50,
  "max_steps": 89556,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}