{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2017,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.9350311723351479,
      "epoch": 0.02479082739386427,
      "grad_norm": 2.921875,
      "learning_rate": 7.277227722772277e-06,
      "loss": 1.9223,
      "mean_token_accuracy": 0.6512195858359336,
      "num_tokens": 12987057.0,
      "step": 50
    },
    {
      "entropy": 1.3992473047971725,
      "epoch": 0.04958165478772854,
      "grad_norm": 0.5859375,
      "learning_rate": 1.4702970297029704e-05,
      "loss": 1.4095,
      "mean_token_accuracy": 0.6870005157589912,
      "num_tokens": 25982341.0,
      "step": 100
    },
    {
      "entropy": 1.2823992617428304,
      "epoch": 0.07437248218159281,
      "grad_norm": 0.546875,
      "learning_rate": 2.212871287128713e-05,
      "loss": 1.2825,
      "mean_token_accuracy": 0.7077956217527389,
      "num_tokens": 38965652.0,
      "step": 150
    },
    {
      "entropy": 1.2264368762075901,
      "epoch": 0.09916330957545708,
      "grad_norm": 0.58203125,
      "learning_rate": 2.9554455445544555e-05,
      "loss": 1.2252,
      "mean_token_accuracy": 0.7175403034687042,
      "num_tokens": 51955113.0,
      "step": 200
    },
    {
      "entropy": 1.1745939214527608,
      "epoch": 0.12395413696932135,
      "grad_norm": 0.5625,
      "learning_rate": 2.9950390604994976e-05,
      "loss": 1.1733,
      "mean_token_accuracy": 0.7261676301062107,
      "num_tokens": 64940008.0,
      "step": 250
    },
    {
      "entropy": 1.1452814097702504,
      "epoch": 0.14874496436318563,
      "grad_norm": 0.56640625,
      "learning_rate": 2.978907368725783e-05,
      "loss": 1.1429,
      "mean_token_accuracy": 0.7316162596642971,
      "num_tokens": 77929904.0,
      "step": 300
    },
    {
      "entropy": 1.1280623151361941,
      "epoch": 0.1735357917570499,
      "grad_norm": 0.58984375,
      "learning_rate": 2.9517054537806585e-05,
      "loss": 1.1256,
      "mean_token_accuracy": 0.7344555719196797,
      "num_tokens": 90917917.0,
      "step": 350
    },
    {
      "entropy": 1.106316467821598,
      "epoch": 0.19832661915091415,
      "grad_norm": 0.5546875,
      "learning_rate": 2.9136369330613327e-05,
      "loss": 1.104,
      "mean_token_accuracy": 0.7381731517612934,
      "num_tokens": 103911070.0,
      "step": 400
    },
    {
      "entropy": 1.0862759150564671,
      "epoch": 0.22311744654477844,
      "grad_norm": 0.5625,
      "learning_rate": 2.864986764929012e-05,
      "loss": 1.0831,
      "mean_token_accuracy": 0.7422050322592258,
      "num_tokens": 116908048.0,
      "step": 450
    },
    {
      "entropy": 1.071421894133091,
      "epoch": 0.2479082739386427,
      "grad_norm": 0.578125,
      "learning_rate": 2.8061191156796658e-05,
      "loss": 1.0683,
      "mean_token_accuracy": 0.7446134378015995,
      "num_tokens": 129891292.0,
      "step": 500
    },
    {
      "entropy": 1.0597773297131061,
      "epoch": 0.27269910133250697,
      "grad_norm": 0.55859375,
      "learning_rate": 2.737474633611185e-05,
      "loss": 1.0563,
      "mean_token_accuracy": 0.7466570647060871,
      "num_tokens": 142876112.0,
      "step": 550
    },
    {
      "entropy": 1.0568923234939576,
      "epoch": 0.29748992872637126,
      "grad_norm": 0.546875,
      "learning_rate": 2.6595671505916456e-05,
      "loss": 1.0532,
      "mean_token_accuracy": 0.747249816954136,
      "num_tokens": 155871785.0,
      "step": 600
    },
    {
      "entropy": 1.051955975741148,
      "epoch": 0.3222807561202355,
      "grad_norm": 0.578125,
      "learning_rate": 2.5729798358187858e-05,
      "loss": 1.0482,
      "mean_token_accuracy": 0.7482274283468723,
      "num_tokens": 168864657.0,
      "step": 650
    },
    {
      "entropy": 1.0347797067463398,
      "epoch": 0.3470715835140998,
      "grad_norm": 0.55859375,
      "learning_rate": 2.478360830561368e-05,
      "loss": 1.0308,
      "mean_token_accuracy": 0.7513435909152031,
      "num_tokens": 181847527.0,
      "step": 700
    },
    {
      "entropy": 1.0355973771214486,
      "epoch": 0.37186241090796407,
      "grad_norm": 0.53515625,
      "learning_rate": 2.376418396558165e-05,
      "loss": 1.0314,
      "mean_token_accuracy": 0.7509755866229534,
      "num_tokens": 194832579.0,
      "step": 750
    },
    {
      "entropy": 1.0291439467668533,
      "epoch": 0.3966532383018283,
      "grad_norm": 0.5546875,
      "learning_rate": 2.2679156143907717e-05,
      "loss": 1.0251,
      "mean_token_accuracy": 0.7523766578733921,
      "num_tokens": 207819397.0,
      "step": 800
    },
    {
      "entropy": 1.0309783019125462,
      "epoch": 0.4214440656956926,
      "grad_norm": 0.515625,
      "learning_rate": 2.153664671515084e-05,
      "loss": 1.0268,
      "mean_token_accuracy": 0.7517271949350834,
      "num_tokens": 220806448.0,
      "step": 850
    },
    {
      "entropy": 1.0233621565997602,
      "epoch": 0.4462348930895569,
      "grad_norm": 0.51953125,
      "learning_rate": 2.0345207827078517e-05,
      "loss": 1.0188,
      "mean_token_accuracy": 0.7533569988608361,
      "num_tokens": 233800554.0,
      "step": 900
    },
    {
      "entropy": 1.0196293856203555,
      "epoch": 0.4710257204834211,
      "grad_norm": 0.53125,
      "learning_rate": 1.9113757884362315e-05,
      "loss": 1.0156,
      "mean_token_accuracy": 0.7541334366798401,
      "num_tokens": 246788996.0,
      "step": 950
    },
    {
      "entropy": 1.023166581392288,
      "epoch": 0.4958165478772854,
      "grad_norm": 0.53125,
      "learning_rate": 1.7851514790691512e-05,
      "loss": 1.0183,
      "mean_token_accuracy": 0.7532591855525971,
      "num_tokens": 259781274.0,
      "step": 1000
    },
    {
      "entropy": 1.0117680232226849,
      "epoch": 0.5206073752711496,
      "grad_norm": 0.52734375,
      "learning_rate": 1.6567926949014805e-05,
      "loss": 1.0079,
      "mean_token_accuracy": 0.755366503894329,
      "num_tokens": 272766654.0,
      "step": 1050
    },
    {
      "entropy": 1.0149836498498916,
      "epoch": 0.5453982026650139,
      "grad_norm": 0.53125,
      "learning_rate": 1.5272602536401258e-05,
      "loss": 1.0105,
      "mean_token_accuracy": 0.7547966828942299,
      "num_tokens": 285761894.0,
      "step": 1100
    },
    {
      "entropy": 1.0172268342971802,
      "epoch": 0.5701890300588782,
      "grad_norm": 0.515625,
      "learning_rate": 1.3975237582927023e-05,
      "loss": 1.0126,
      "mean_token_accuracy": 0.7544859103858471,
      "num_tokens": 298753069.0,
      "step": 1150
    },
    {
      "entropy": 1.0113342855870724,
      "epoch": 0.5949798574527425,
      "grad_norm": 0.515625,
      "learning_rate": 1.2685543392946551e-05,
      "loss": 1.0072,
      "mean_token_accuracy": 0.7554229401051998,
      "num_tokens": 311750957.0,
      "step": 1200
    },
    {
      "entropy": 1.0141666044294835,
      "epoch": 0.6197706848466068,
      "grad_norm": 0.546875,
      "learning_rate": 1.1413173852029593e-05,
      "loss": 1.0096,
      "mean_token_accuracy": 0.7549486918747426,
      "num_tokens": 324739809.0,
      "step": 1250
    },
    {
      "entropy": 1.011275120228529,
      "epoch": 0.644561512240471,
      "grad_norm": 0.51171875,
      "learning_rate": 1.0167653163701218e-05,
      "loss": 1.0066,
      "mean_token_accuracy": 0.755563808530569,
      "num_tokens": 337733441.0,
      "step": 1300
    },
    {
      "entropy": 1.0095749548077584,
      "epoch": 0.6693523396343353,
      "grad_norm": 0.52734375,
      "learning_rate": 8.958304556904608e-06,
      "loss": 1.0051,
      "mean_token_accuracy": 0.7557943074405193,
      "num_tokens": 350729616.0,
      "step": 1350
    },
    {
      "entropy": 1.0063166113197803,
      "epoch": 0.6941431670281996,
      "grad_norm": 0.52734375,
      "learning_rate": 7.794180497840417e-06,
      "loss": 1.0018,
      "mean_token_accuracy": 0.7565754729509354,
      "num_tokens": 363726550.0,
      "step": 1400
    },
    {
      "entropy": 1.0057007387280463,
      "epoch": 0.7189339944220638,
      "grad_norm": 0.52734375,
      "learning_rate": 6.683994928575307e-06,
      "loss": 1.001,
      "mean_token_accuracy": 0.75655224904418,
      "num_tokens": 376715458.0,
      "step": 1450
    },
    {
      "entropy": 1.010465783327818,
      "epoch": 0.7437248218159281,
      "grad_norm": 0.515625,
      "learning_rate": 5.636058039641382e-06,
      "loss": 1.0057,
      "mean_token_accuracy": 0.7555474500358105,
      "num_tokens": 389703743.0,
      "step": 1500
    },
    {
      "entropy": 1.0062365026772022,
      "epoch": 0.7685156492097924,
      "grad_norm": 0.5078125,
      "learning_rate": 4.6582140648800434e-06,
      "loss": 1.0012,
      "mean_token_accuracy": 0.7565624009072781,
      "num_tokens": 402693509.0,
      "step": 1550
    },
    {
      "entropy": 1.0175788636505603,
      "epoch": 0.7933064766036566,
      "grad_norm": 0.5078125,
      "learning_rate": 3.7577825641611918e-06,
      "loss": 1.0135,
      "mean_token_accuracy": 0.754096201211214,
      "num_tokens": 415676636.0,
      "step": 1600
    },
    {
      "entropy": 1.0108901219069957,
      "epoch": 0.8180973039975209,
      "grad_norm": 0.51171875,
      "learning_rate": 2.941503633500518e-06,
      "loss": 1.0067,
      "mean_token_accuracy": 0.7554244147241116,
      "num_tokens": 428672727.0,
      "step": 1650
    },
    {
      "entropy": 1.005025475025177,
      "epoch": 0.8428881313913852,
      "grad_norm": 0.51171875,
      "learning_rate": 2.215487452699424e-06,
      "loss": 0.9997,
      "mean_token_accuracy": 0.7569046394526958,
      "num_tokens": 441658704.0,
      "step": 1700
    },
    {
      "entropy": 1.0120447267591954,
      "epoch": 0.8676789587852495,
      "grad_norm": 0.5234375,
      "learning_rate": 1.5851685481640143e-06,
      "loss": 1.0064,
      "mean_token_accuracy": 0.7556189036369324,
      "num_tokens": 454644190.0,
      "step": 1750
    },
    {
      "entropy": 1.0109828931093217,
      "epoch": 0.8924697861791138,
      "grad_norm": 0.51953125,
      "learning_rate": 1.0552651132645602e-06,
      "loss": 1.0065,
      "mean_token_accuracy": 0.7554912100732326,
      "num_tokens": 467637106.0,
      "step": 1800
    },
    {
      "entropy": 1.013734626173973,
      "epoch": 0.917260613572978,
      "grad_norm": 0.51953125,
      "learning_rate": 6.297436907390885e-07,
      "loss": 1.0082,
      "mean_token_accuracy": 0.7551266106963158,
      "num_tokens": 480637699.0,
      "step": 1850
    },
    {
      "entropy": 1.0092887429893016,
      "epoch": 0.9420514409668422,
      "grad_norm": 0.52734375,
      "learning_rate": 3.117894815076755e-07,
      "loss": 1.0051,
      "mean_token_accuracy": 0.7559835283458233,
      "num_tokens": 493631966.0,
      "step": 1900
    },
    {
      "entropy": 1.0152117817103863,
      "epoch": 0.9668422683607065,
      "grad_norm": 0.51171875,
      "learning_rate": 1.0378250214803986e-07,
      "loss": 1.0102,
      "mean_token_accuracy": 0.7547811089456081,
      "num_tokens": 506610108.0,
      "step": 1950
    },
    {
      "entropy": 1.0181812508404255,
      "epoch": 0.9916330957545708,
      "grad_norm": 0.51953125,
      "learning_rate": 7.2797695034398924e-09,
      "loss": 1.0127,
      "mean_token_accuracy": 0.7541768151521683,
      "num_tokens": 519598174.0,
      "step": 2000
    }
  ],
  "logging_steps": 50,
  "max_steps": 2017,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.431062590428283e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}