{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9978401727861771,
  "eval_steps": 500,
  "global_step": 231,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02159827213822894,
      "grad_norm": 4.777818202972412,
      "learning_rate": 1.1903333333333333e-05,
      "loss": 1.7478,
      "mean_token_accuracy": 0.673093843460083,
      "num_tokens": 327041.0,
      "step": 5
    },
    {
      "epoch": 0.04319654427645788,
      "grad_norm": 1.6766164302825928,
      "learning_rate": 2.6782500000000003e-05,
      "loss": 1.1651,
      "mean_token_accuracy": 0.7291636049747467,
      "num_tokens": 654721.0,
      "step": 10
    },
    {
      "epoch": 0.06479481641468683,
      "grad_norm": 1.0733250379562378,
      "learning_rate": 3.570453895221049e-05,
      "loss": 0.6245,
      "mean_token_accuracy": 0.8475371032953263,
      "num_tokens": 981309.0,
      "step": 15
    },
    {
      "epoch": 0.08639308855291576,
      "grad_norm": 0.6415389180183411,
      "learning_rate": 3.5643153305762796e-05,
      "loss": 0.2271,
      "mean_token_accuracy": 0.9391736060380935,
      "num_tokens": 1307298.0,
      "step": 20
    },
    {
      "epoch": 0.1079913606911447,
      "grad_norm": 1.9687130451202393,
      "learning_rate": 3.551386955429542e-05,
      "loss": 0.1078,
      "mean_token_accuracy": 0.9679672092199325,
      "num_tokens": 1634102.0,
      "step": 25
    },
    {
      "epoch": 0.12958963282937366,
      "grad_norm": 0.43518000841140747,
      "learning_rate": 3.531734649817135e-05,
      "loss": 0.0894,
      "mean_token_accuracy": 0.9722483873367309,
      "num_tokens": 1960430.0,
      "step": 30
    },
    {
      "epoch": 0.1511879049676026,
      "grad_norm": 0.3164879381656647,
      "learning_rate": 3.505458557383748e-05,
      "loss": 0.0748,
      "mean_token_accuracy": 0.9752993941307068,
      "num_tokens": 2287205.0,
      "step": 35
    },
    {
      "epoch": 0.17278617710583152,
      "grad_norm": 12.315321922302246,
      "learning_rate": 3.472692575073402e-05,
      "loss": 0.0617,
      "mean_token_accuracy": 0.9788013488054276,
      "num_tokens": 2614608.0,
      "step": 40
    },
    {
      "epoch": 0.19438444924406048,
      "grad_norm": 0.18295283615589142,
      "learning_rate": 3.4336036708213154e-05,
      "loss": 0.0579,
      "mean_token_accuracy": 0.9799674391746521,
      "num_tokens": 2942049.0,
      "step": 45
    },
    {
      "epoch": 0.2159827213822894,
      "grad_norm": 0.10459253937005997,
      "learning_rate": 3.3883910327235794e-05,
      "loss": 0.0456,
      "mean_token_accuracy": 0.9840161263942718,
      "num_tokens": 3268494.0,
      "step": 50
    },
    {
      "epoch": 0.23758099352051837,
      "grad_norm": 0.12234116345643997,
      "learning_rate": 3.337285054020275e-05,
      "loss": 0.0476,
      "mean_token_accuracy": 0.9830995976924897,
      "num_tokens": 3595171.0,
      "step": 55
    },
    {
      "epoch": 0.2591792656587473,
      "grad_norm": 0.12831856310367584,
      "learning_rate": 3.280546159064337e-05,
      "loss": 0.0443,
      "mean_token_accuracy": 0.9843576639890671,
      "num_tokens": 3922203.0,
      "step": 60
    },
    {
      "epoch": 0.28077753779697623,
      "grad_norm": 0.16520845890045166,
      "learning_rate": 3.218463476258741e-05,
      "loss": 0.0414,
      "mean_token_accuracy": 0.9853224068880081,
      "num_tokens": 4249258.0,
      "step": 65
    },
    {
      "epoch": 0.3023758099352052,
      "grad_norm": 0.5860384702682495,
      "learning_rate": 3.151353364724442e-05,
      "loss": 0.044,
      "mean_token_accuracy": 0.9839389264583588,
      "num_tokens": 4576500.0,
      "step": 70
    },
    {
      "epoch": 0.32397408207343414,
      "grad_norm": 0.15807564556598663,
      "learning_rate": 3.0795578022068034e-05,
      "loss": 0.0436,
      "mean_token_accuracy": 0.9843764930963517,
      "num_tokens": 4903657.0,
      "step": 75
    },
    {
      "epoch": 0.34557235421166305,
      "grad_norm": 0.10453962534666061,
      "learning_rate": 3.003442642435402e-05,
      "loss": 0.04,
      "mean_token_accuracy": 0.9854078710079193,
      "num_tokens": 5230081.0,
      "step": 80
    },
    {
      "epoch": 0.367170626349892,
      "grad_norm": 0.11286672949790955,
      "learning_rate": 2.923395750817275e-05,
      "loss": 0.0398,
      "mean_token_accuracy": 0.9855783194303512,
      "num_tokens": 5556925.0,
      "step": 85
    },
    {
      "epoch": 0.38876889848812096,
      "grad_norm": 0.2122899740934372,
      "learning_rate": 2.8398250279637206e-05,
      "loss": 0.0372,
      "mean_token_accuracy": 0.9866322726011276,
      "num_tokens": 5883992.0,
      "step": 90
    },
    {
      "epoch": 0.4103671706263499,
      "grad_norm": 0.12236664444208145,
      "learning_rate": 2.753156331122277e-05,
      "loss": 0.0403,
      "mean_token_accuracy": 0.9852587074041367,
      "num_tokens": 6210605.0,
      "step": 95
    },
    {
      "epoch": 0.4319654427645788,
      "grad_norm": 0.09743868559598923,
      "learning_rate": 2.6638313041058053e-05,
      "loss": 0.0363,
      "mean_token_accuracy": 0.9869196385145187,
      "num_tokens": 6537632.0,
      "step": 100
    },
    {
      "epoch": 0.4535637149028078,
      "grad_norm": 0.12190241366624832,
      "learning_rate": 2.5723051267768538e-05,
      "loss": 0.0357,
      "mean_token_accuracy": 0.9869883239269257,
      "num_tokens": 6864705.0,
      "step": 105
    },
    {
      "epoch": 0.47516198704103674,
      "grad_norm": 0.08914244920015335,
      "learning_rate": 2.4790441955554125e-05,
      "loss": 0.0375,
      "mean_token_accuracy": 0.9862172365188598,
      "num_tokens": 7192178.0,
      "step": 110
    },
    {
      "epoch": 0.49676025917926564,
      "grad_norm": 0.09364324063062668,
      "learning_rate": 2.3845237467696704e-05,
      "loss": 0.042,
      "mean_token_accuracy": 0.9846871644258499,
      "num_tokens": 7518769.0,
      "step": 115
    },
    {
      "epoch": 0.5183585313174947,
      "grad_norm": 0.1068236380815506,
      "learning_rate": 2.2892254349606132e-05,
      "loss": 0.0376,
      "mean_token_accuracy": 0.9862382262945175,
      "num_tokens": 7845781.0,
      "step": 120
    },
    {
      "epoch": 0.5399568034557235,
      "grad_norm": 0.08777054399251938,
      "learning_rate": 2.1936348784808918e-05,
      "loss": 0.041,
      "mean_token_accuracy": 0.9851777613162994,
      "num_tokens": 8172882.0,
      "step": 125
    },
    {
      "epoch": 0.5615550755939525,
      "grad_norm": 0.10713644325733185,
      "learning_rate": 2.0982391848950114e-05,
      "loss": 0.0382,
      "mean_token_accuracy": 0.9860901892185211,
      "num_tokens": 8499891.0,
      "step": 130
    },
    {
      "epoch": 0.5831533477321814,
      "grad_norm": 0.09616448730230331,
      "learning_rate": 2.0035244687908377e-05,
      "loss": 0.0357,
      "mean_token_accuracy": 0.9870383441448212,
      "num_tokens": 8827333.0,
      "step": 135
    },
    {
      "epoch": 0.6047516198704104,
      "grad_norm": 0.11250793933868408,
      "learning_rate": 1.9099733746510814e-05,
      "loss": 0.0373,
      "mean_token_accuracy": 0.9865201264619827,
      "num_tokens": 9153215.0,
      "step": 140
    },
    {
      "epoch": 0.6263498920086393,
      "grad_norm": 0.07551588118076324,
      "learning_rate": 1.818062617407649e-05,
      "loss": 0.0367,
      "mean_token_accuracy": 0.9866218030452728,
      "num_tokens": 9480065.0,
      "step": 145
    },
    {
      "epoch": 0.6479481641468683,
      "grad_norm": 0.15281730890274048,
      "learning_rate": 1.7282605532116228e-05,
      "loss": 0.0357,
      "mean_token_accuracy": 0.9870801359415055,
      "num_tokens": 9806285.0,
      "step": 150
    },
    {
      "epoch": 0.6695464362850972,
      "grad_norm": 0.07491156458854675,
      "learning_rate": 1.641024792797671e-05,
      "loss": 0.0346,
      "mean_token_accuracy": 0.9874009698629379,
      "num_tokens": 10133128.0,
      "step": 155
    },
    {
      "epoch": 0.6911447084233261,
      "grad_norm": 0.08615657687187195,
      "learning_rate": 1.5567998696046392e-05,
      "loss": 0.0328,
      "mean_token_accuracy": 0.9880871474742889,
      "num_tokens": 10459417.0,
      "step": 160
    },
    {
      "epoch": 0.712742980561555,
      "grad_norm": 0.09050696343183517,
      "learning_rate": 1.4760149745350381e-05,
      "loss": 0.0359,
      "mean_token_accuracy": 0.9867339074611664,
      "num_tokens": 10786059.0,
      "step": 165
    },
    {
      "epoch": 0.734341252699784,
      "grad_norm": 0.21551507711410522,
      "learning_rate": 1.3990817688965879e-05,
      "loss": 0.0373,
      "mean_token_accuracy": 0.9864282488822937,
      "num_tokens": 11112457.0,
      "step": 170
    },
    {
      "epoch": 0.755939524838013,
      "grad_norm": 0.07269071042537689,
      "learning_rate": 1.3263922866705542e-05,
      "loss": 0.036,
      "mean_token_accuracy": 0.9867516905069351,
      "num_tokens": 11439674.0,
      "step": 175
    },
    {
      "epoch": 0.7775377969762419,
      "grad_norm": 0.12428650259971619,
      "learning_rate": 1.2583169367964404e-05,
      "loss": 0.0378,
      "mean_token_accuracy": 0.9861906915903091,
      "num_tokens": 11766139.0,
      "step": 180
    },
    {
      "epoch": 0.7991360691144709,
      "grad_norm": 0.0770215094089508,
      "learning_rate": 1.1952026156529388e-05,
      "loss": 0.0362,
      "mean_token_accuracy": 0.986765107512474,
      "num_tokens": 12092848.0,
      "step": 185
    },
    {
      "epoch": 0.8207343412526998,
      "grad_norm": 0.07880507409572601,
      "learning_rate": 1.1373709393535004e-05,
      "loss": 0.0341,
      "mean_token_accuracy": 0.9875539094209671,
      "num_tokens": 12420090.0,
      "step": 190
    },
    {
      "epoch": 0.8423326133909287,
      "grad_norm": 0.09498883038759232,
      "learning_rate": 1.085116604864341e-05,
      "loss": 0.0305,
      "mean_token_accuracy": 0.988871157169342,
      "num_tokens": 12747362.0,
      "step": 195
    },
    {
      "epoch": 0.8639308855291576,
      "grad_norm": 0.10424337536096573,
      "learning_rate": 1.038705888296252e-05,
      "loss": 0.0347,
      "mean_token_accuracy": 0.987392121553421,
      "num_tokens": 13074826.0,
      "step": 200
    },
    {
      "epoch": 0.8855291576673866,
      "grad_norm": 0.09163855761289597,
      "learning_rate": 9.983752880225764e-06,
      "loss": 0.0342,
      "mean_token_accuracy": 0.9873875081539154,
      "num_tokens": 13400958.0,
      "step": 205
    },
    {
      "epoch": 0.9071274298056156,
      "grad_norm": 0.13818813860416412,
      "learning_rate": 9.643303195377083e-06,
      "loss": 0.0391,
      "mean_token_accuracy": 0.9855553776025772,
      "num_tokens": 13727990.0,
      "step": 210
    },
    {
      "epoch": 0.9287257019438445,
      "grad_norm": 0.07480086386203766,
      "learning_rate": 9.367444681972418e-06,
      "loss": 0.0371,
      "mean_token_accuracy": 0.9866992443799972,
      "num_tokens": 14055037.0,
      "step": 215
    },
    {
      "epoch": 0.9503239740820735,
      "grad_norm": 0.07980502396821976,
      "learning_rate": 9.157583051763647e-06,
      "loss": 0.0338,
      "mean_token_accuracy": 0.9877716153860092,
      "num_tokens": 14382589.0,
      "step": 220
    },
    {
      "epoch": 0.9719222462203023,
      "grad_norm": 0.1249043345451355,
      "learning_rate": 9.014787711513727e-06,
      "loss": 0.0328,
      "mean_token_accuracy": 0.9879971414804458,
      "num_tokens": 14709624.0,
      "step": 225
    },
    {
      "epoch": 0.9935205183585313,
      "grad_norm": 0.10734046995639801,
      "learning_rate": 8.939786313544953e-06,
      "loss": 0.0352,
      "mean_token_accuracy": 0.987159937620163,
      "num_tokens": 15036472.0,
      "step": 230
    }
  ],
  "logging_steps": 5,
  "max_steps": 232,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.531691228313682e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}