{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990680335507922,
  "eval_steps": 500,
  "global_step": 268,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01863932898415657,
      "grad_norm": 1.7573972317970177,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.8497,
      "num_tokens": 10465392.0,
      "step": 5
    },
    {
      "epoch": 0.03727865796831314,
      "grad_norm": 0.7814164461382908,
      "learning_rate": 3.2142857142857144e-05,
      "loss": 0.7788,
      "num_tokens": 20951152.0,
      "step": 10
    },
    {
      "epoch": 0.05591798695246971,
      "grad_norm": 0.4971840947687821,
      "learning_rate": 5e-05,
      "loss": 0.7096,
      "num_tokens": 31436912.0,
      "step": 15
    },
    {
      "epoch": 0.07455731593662628,
      "grad_norm": 0.4104663829493778,
      "learning_rate": 4.995698831799242e-05,
      "loss": 0.6707,
      "num_tokens": 41909269.0,
      "step": 20
    },
    {
      "epoch": 0.09319664492078285,
      "grad_norm": 0.378224237110894,
      "learning_rate": 4.982811771683982e-05,
      "loss": 0.6517,
      "num_tokens": 52353719.0,
      "step": 25
    },
    {
      "epoch": 0.11183597390493942,
      "grad_norm": 0.27264995346014925,
      "learning_rate": 4.9613880902437035e-05,
      "loss": 0.6363,
      "num_tokens": 62792124.0,
      "step": 30
    },
    {
      "epoch": 0.13047530288909598,
      "grad_norm": 0.25488038499432786,
      "learning_rate": 4.931509695796055e-05,
      "loss": 0.6217,
      "num_tokens": 73260442.0,
      "step": 35
    },
    {
      "epoch": 0.14911463187325255,
      "grad_norm": 0.2475293398276613,
      "learning_rate": 4.8932908212300035e-05,
      "loss": 0.6053,
      "num_tokens": 83727556.0,
      "step": 40
    },
    {
      "epoch": 0.16775396085740912,
      "grad_norm": 0.2763844980958693,
      "learning_rate": 4.846877587263728e-05,
      "loss": 0.6041,
      "num_tokens": 94201938.0,
      "step": 45
    },
    {
      "epoch": 0.1863932898415657,
      "grad_norm": 0.3232566590307947,
      "learning_rate": 4.792447443787034e-05,
      "loss": 0.5967,
      "num_tokens": 104670740.0,
      "step": 50
    },
    {
      "epoch": 0.20503261882572227,
      "grad_norm": 0.3499333864597863,
      "learning_rate": 4.730208491424174e-05,
      "loss": 0.5998,
      "num_tokens": 115151933.0,
      "step": 55
    },
    {
      "epoch": 0.22367194780987884,
      "grad_norm": 0.3933865267179061,
      "learning_rate": 4.660398685910928e-05,
      "loss": 0.5906,
      "num_tokens": 125607410.0,
      "step": 60
    },
    {
      "epoch": 0.2423112767940354,
      "grad_norm": 0.3915672585619426,
      "learning_rate": 4.583284928327805e-05,
      "loss": 0.5884,
      "num_tokens": 136036466.0,
      "step": 65
    },
    {
      "epoch": 0.26095060577819196,
      "grad_norm": 0.4195837025490587,
      "learning_rate": 4.499162044667658e-05,
      "loss": 0.5849,
      "num_tokens": 146502251.0,
      "step": 70
    },
    {
      "epoch": 0.27958993476234856,
      "grad_norm": 0.3381612617240059,
      "learning_rate": 4.4083516586390694e-05,
      "loss": 0.5821,
      "num_tokens": 156977308.0,
      "step": 75
    },
    {
      "epoch": 0.2982292637465051,
      "grad_norm": 0.2551239560014803,
      "learning_rate": 4.3112009620150904e-05,
      "loss": 0.576,
      "num_tokens": 167423794.0,
      "step": 80
    },
    {
      "epoch": 0.3168685927306617,
      "grad_norm": 0.30592698170937993,
      "learning_rate": 4.208081387228612e-05,
      "loss": 0.5685,
      "num_tokens": 177900466.0,
      "step": 85
    },
    {
      "epoch": 0.33550792171481825,
      "grad_norm": 0.281492013111172,
      "learning_rate": 4.099387187289365e-05,
      "loss": 0.5724,
      "num_tokens": 188373813.0,
      "step": 90
    },
    {
      "epoch": 0.35414725069897485,
      "grad_norm": 0.26672187272505754,
      "learning_rate": 3.985533928451914e-05,
      "loss": 0.5706,
      "num_tokens": 198859382.0,
      "step": 95
    },
    {
      "epoch": 0.3727865796831314,
      "grad_norm": 0.2923857402012376,
      "learning_rate": 3.866956901397559e-05,
      "loss": 0.5676,
      "num_tokens": 209345142.0,
      "step": 100
    },
    {
      "epoch": 0.391425908667288,
      "grad_norm": 0.2780198681024584,
      "learning_rate": 3.74410945700462e-05,
      "loss": 0.5668,
      "num_tokens": 219820636.0,
      "step": 105
    },
    {
      "epoch": 0.41006523765144454,
      "grad_norm": 0.3103372433812494,
      "learning_rate": 3.617461273069867e-05,
      "loss": 0.559,
      "num_tokens": 230306396.0,
      "step": 110
    },
    {
      "epoch": 0.42870456663560114,
      "grad_norm": 0.32943677203389876,
      "learning_rate": 3.487496558607898e-05,
      "loss": 0.5627,
      "num_tokens": 240792156.0,
      "step": 115
    },
    {
      "epoch": 0.4473438956197577,
      "grad_norm": 0.2903244983178175,
      "learning_rate": 3.354712202593882e-05,
      "loss": 0.5611,
      "num_tokens": 251259365.0,
      "step": 120
    },
    {
      "epoch": 0.4659832246039143,
      "grad_norm": 0.27649466725394467,
      "learning_rate": 3.219615874227504e-05,
      "loss": 0.5644,
      "num_tokens": 261736444.0,
      "step": 125
    },
    {
      "epoch": 0.4846225535880708,
      "grad_norm": 0.28234984702886096,
      "learning_rate": 3.082724081981306e-05,
      "loss": 0.563,
      "num_tokens": 272205866.0,
      "step": 130
    },
    {
      "epoch": 0.5032618825722274,
      "grad_norm": 0.2766528639933286,
      "learning_rate": 2.9445601988541782e-05,
      "loss": 0.5587,
      "num_tokens": 282683327.0,
      "step": 135
    },
    {
      "epoch": 0.5219012115563839,
      "grad_norm": 0.2685787031695611,
      "learning_rate": 2.8056524613799888e-05,
      "loss": 0.5612,
      "num_tokens": 293122806.0,
      "step": 140
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.2101892722509089,
      "learning_rate": 2.6665319500416385e-05,
      "loss": 0.5606,
      "num_tokens": 303598947.0,
      "step": 145
    },
    {
      "epoch": 0.5591798695246971,
      "grad_norm": 0.2589895951146755,
      "learning_rate": 2.527730558811963e-05,
      "loss": 0.5579,
      "num_tokens": 314077641.0,
      "step": 150
    },
    {
      "epoch": 0.5778191985088537,
      "grad_norm": 0.21518960674848625,
      "learning_rate": 2.3897789615844557e-05,
      "loss": 0.5488,
      "num_tokens": 324545386.0,
      "step": 155
    },
    {
      "epoch": 0.5964585274930102,
      "grad_norm": 0.18657627443004557,
      "learning_rate": 2.2532045832686615e-05,
      "loss": 0.5609,
      "num_tokens": 335031146.0,
      "step": 160
    },
    {
      "epoch": 0.6150978564771669,
      "grad_norm": 0.20944107327672593,
      "learning_rate": 2.1185295833072914e-05,
      "loss": 0.5412,
      "num_tokens": 345504904.0,
      "step": 165
    },
    {
      "epoch": 0.6337371854613234,
      "grad_norm": 0.18523084293093703,
      "learning_rate": 1.9862688593245853e-05,
      "loss": 0.5508,
      "num_tokens": 355956520.0,
      "step": 170
    },
    {
      "epoch": 0.65237651444548,
      "grad_norm": 0.16744206090364774,
      "learning_rate": 1.8569280785385046e-05,
      "loss": 0.5515,
      "num_tokens": 366434348.0,
      "step": 175
    },
    {
      "epoch": 0.6710158434296365,
      "grad_norm": 0.19529463948190923,
      "learning_rate": 1.731001744463161e-05,
      "loss": 0.5543,
      "num_tokens": 376908695.0,
      "step": 180
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.18569828701168353,
      "learning_rate": 1.6089713062930108e-05,
      "loss": 0.5571,
      "num_tokens": 387384301.0,
      "step": 185
    },
    {
      "epoch": 0.7082945013979497,
      "grad_norm": 0.1713285501371151,
      "learning_rate": 1.4913033181971056e-05,
      "loss": 0.548,
      "num_tokens": 397835323.0,
      "step": 190
    },
    {
      "epoch": 0.7269338303821062,
      "grad_norm": 0.16294932839233475,
      "learning_rate": 1.3784476555609077e-05,
      "loss": 0.5467,
      "num_tokens": 408298322.0,
      "step": 195
    },
    {
      "epoch": 0.7455731593662628,
      "grad_norm": 0.16147697817221135,
      "learning_rate": 1.2708357949954441e-05,
      "loss": 0.5526,
      "num_tokens": 418781566.0,
      "step": 200
    },
    {
      "epoch": 0.7642124883504194,
      "grad_norm": 0.17353407502301713,
      "learning_rate": 1.1688791646897726e-05,
      "loss": 0.5484,
      "num_tokens": 429246222.0,
      "step": 205
    },
    {
      "epoch": 0.782851817334576,
      "grad_norm": 0.16962668393783945,
      "learning_rate": 1.0729675714137831e-05,
      "loss": 0.5426,
      "num_tokens": 439717644.0,
      "step": 210
    },
    {
      "epoch": 0.8014911463187325,
      "grad_norm": 0.15859375239694778,
      "learning_rate": 9.834677101853265e-06,
      "loss": 0.5517,
      "num_tokens": 450170885.0,
      "step": 215
    },
    {
      "epoch": 0.8201304753028891,
      "grad_norm": 0.1772198182052593,
      "learning_rate": 9.007217622995933e-06,
      "loss": 0.5478,
      "num_tokens": 460656645.0,
      "step": 220
    },
    {
      "epoch": 0.8387698042870456,
      "grad_norm": 0.18021101189312388,
      "learning_rate": 8.250460870808394e-06,
      "loss": 0.5401,
      "num_tokens": 471142405.0,
      "step": 225
    },
    {
      "epoch": 0.8574091332712023,
      "grad_norm": 0.14833153298429916,
      "learning_rate": 7.567300123582388e-06,
      "loss": 0.5444,
      "num_tokens": 481616409.0,
      "step": 230
    },
    {
      "epoch": 0.8760484622553588,
      "grad_norm": 0.1675362976580094,
      "learning_rate": 6.960347282901894e-06,
      "loss": 0.5437,
      "num_tokens": 492097674.0,
      "step": 235
    },
    {
      "epoch": 0.8946877912395154,
      "grad_norm": 0.14741844256042477,
      "learning_rate": 6.431922887662643e-06,
      "loss": 0.5414,
      "num_tokens": 502555042.0,
      "step": 240
    },
    {
      "epoch": 0.9133271202236719,
      "grad_norm": 0.1496978314112162,
      "learning_rate": 5.984047242047134e-06,
      "loss": 0.5394,
      "num_tokens": 513031521.0,
      "step": 245
    },
    {
      "epoch": 0.9319664492078286,
      "grad_norm": 0.14094412621251864,
      "learning_rate": 5.6184326913751945e-06,
      "loss": 0.5477,
      "num_tokens": 523517281.0,
      "step": 250
    },
    {
      "epoch": 0.9506057781919851,
      "grad_norm": 0.1478294431106662,
      "learning_rate": 5.336477075361577e-06,
      "loss": 0.544,
      "num_tokens": 533998146.0,
      "step": 255
    },
    {
      "epoch": 0.9692451071761417,
      "grad_norm": 0.13882538385053997,
      "learning_rate": 5.139258383810381e-06,
      "loss": 0.54,
      "num_tokens": 544470561.0,
      "step": 260
    },
    {
      "epoch": 0.9878844361602982,
      "grad_norm": 0.14673471750521358,
      "learning_rate": 5.027530635179121e-06,
      "loss": 0.5362,
      "num_tokens": 554934577.0,
      "step": 265
    },
    {
      "epoch": 0.9990680335507922,
      "num_tokens": 561226033.0,
      "step": 268,
      "total_flos": 488165445992448.0,
      "train_loss": 0.5790879526245061,
      "train_runtime": 25119.8538,
      "train_samples_per_second": 1.366,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 5,
  "max_steps": 268,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 488165445992448.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}