{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 394,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05098789037603569,
      "grad_norm": 3.2492356282403603,
      "learning_rate": 2.25e-06,
      "loss": 1.1767307281494142,
      "step": 10
    },
    {
      "epoch": 0.10197578075207138,
      "grad_norm": 1.1621664757269161,
      "learning_rate": 4.75e-06,
      "loss": 0.9224685668945313,
      "step": 20
    },
    {
      "epoch": 0.15296367112810708,
      "grad_norm": 0.618135311791871,
      "learning_rate": 4.992859235371958e-06,
      "loss": 0.7603800773620606,
      "step": 30
    },
    {
      "epoch": 0.20395156150414276,
      "grad_norm": 0.7167015013694569,
      "learning_rate": 4.968227477476554e-06,
      "loss": 0.7024473667144775,
      "step": 40
    },
    {
      "epoch": 0.25493945188017847,
      "grad_norm": 0.5148951707505551,
      "learning_rate": 4.9261902259453616e-06,
      "loss": 0.6715839385986329,
      "step": 50
    },
    {
      "epoch": 0.30592734225621415,
      "grad_norm": 0.477046493005402,
      "learning_rate": 4.867043919871076e-06,
      "loss": 0.653109073638916,
      "step": 60
    },
    {
      "epoch": 0.35691523263224983,
      "grad_norm": 0.520330062474811,
      "learning_rate": 4.791205648303775e-06,
      "loss": 0.6378322124481202,
      "step": 70
    },
    {
      "epoch": 0.4079031230082855,
      "grad_norm": 0.5732517201561727,
      "learning_rate": 4.699210209014394e-06,
      "loss": 0.6366817474365234,
      "step": 80
    },
    {
      "epoch": 0.4588910133843212,
      "grad_norm": 0.5024963518483637,
      "learning_rate": 4.591706337197597e-06,
      "loss": 0.6303482055664062,
      "step": 90
    },
    {
      "epoch": 0.5098789037603569,
      "grad_norm": 0.5155325213216256,
      "learning_rate": 4.469452130708544e-06,
      "loss": 0.6213236808776855,
      "step": 100
    },
    {
      "epoch": 0.5608667941363926,
      "grad_norm": 0.5141540510006203,
      "learning_rate": 4.333309704093977e-06,
      "loss": 0.6146619319915771,
      "step": 110
    },
    {
      "epoch": 0.6118546845124283,
      "grad_norm": 0.5104846204482004,
      "learning_rate": 4.184239109116393e-06,
      "loss": 0.610722827911377,
      "step": 120
    },
    {
      "epoch": 0.662842574888464,
      "grad_norm": 0.5021872967989851,
      "learning_rate": 4.023291564642711e-06,
      "loss": 0.6106809139251709,
      "step": 130
    },
    {
      "epoch": 0.7138304652644997,
      "grad_norm": 0.49285536993550605,
      "learning_rate": 3.8516020436389945e-06,
      "loss": 0.6058969497680664,
      "step": 140
    },
    {
      "epoch": 0.7648183556405354,
      "grad_norm": 0.4820278347141643,
      "learning_rate": 3.670381269546429e-06,
      "loss": 0.6030803203582764,
      "step": 150
    },
    {
      "epoch": 0.815806246016571,
      "grad_norm": 0.49458534348246663,
      "learning_rate": 3.480907178478654e-06,
      "loss": 0.597698450088501,
      "step": 160
    },
    {
      "epoch": 0.8667941363926067,
      "grad_norm": 0.48676711975229414,
      "learning_rate": 3.284515907447481e-06,
      "loss": 0.5992435932159423,
      "step": 170
    },
    {
      "epoch": 0.9177820267686424,
      "grad_norm": 0.47163990999812405,
      "learning_rate": 3.082592372166412e-06,
      "loss": 0.5955633163452149,
      "step": 180
    },
    {
      "epoch": 0.9687699171446782,
      "grad_norm": 0.49090983524169035,
      "learning_rate": 2.8765605008755805e-06,
      "loss": 0.5960547924041748,
      "step": 190
    },
    {
      "epoch": 1.0152963671128108,
      "grad_norm": 0.4578500935152833,
      "learning_rate": 2.667873193057407e-06,
      "loss": 0.587281608581543,
      "step": 200
    },
    {
      "epoch": 1.0662842574888465,
      "grad_norm": 0.49776312577119936,
      "learning_rate": 2.4580020738523e-06,
      "loss": 0.5690115928649903,
      "step": 210
    },
    {
      "epoch": 1.1172721478648822,
      "grad_norm": 0.4841707543116845,
      "learning_rate": 2.2484271164244e-06,
      "loss": 0.5661553382873535,
      "step": 220
    },
    {
      "epoch": 1.1682600382409178,
      "grad_norm": 0.5103410025287574,
      "learning_rate": 2.040626205458574e-06,
      "loss": 0.5658913612365722,
      "step": 230
    },
    {
      "epoch": 1.2192479286169535,
      "grad_norm": 0.45768070002398564,
      "learning_rate": 1.8360647153849893e-06,
      "loss": 0.5660049438476562,
      "step": 240
    },
    {
      "epoch": 1.2702358189929892,
      "grad_norm": 0.43218717804376544,
      "learning_rate": 1.6361851768237325e-06,
      "loss": 0.5648796081542968,
      "step": 250
    },
    {
      "epoch": 1.321223709369025,
      "grad_norm": 0.4514346856488029,
      "learning_rate": 1.4423971041198556e-06,
      "loss": 0.5651669025421142,
      "step": 260
    },
    {
      "epoch": 1.3722115997450606,
      "grad_norm": 0.42512165484169306,
      "learning_rate": 1.256067055703211e-06,
      "loss": 0.5659438133239746,
      "step": 270
    },
    {
      "epoch": 1.4231994901210963,
      "grad_norm": 0.4348211877036809,
      "learning_rate": 1.0785089973656337e-06,
      "loss": 0.5646496772766113,
      "step": 280
    },
    {
      "epoch": 1.474187380497132,
      "grad_norm": 0.4268153975456876,
      "learning_rate": 9.109750364118924e-07,
      "loss": 0.559828519821167,
      "step": 290
    },
    {
      "epoch": 1.5251752708731676,
      "grad_norm": 0.4347816009906328,
      "learning_rate": 7.546465920254975e-07,
      "loss": 0.5672780990600585,
      "step": 300
    },
    {
      "epoch": 1.5761631612492033,
      "grad_norm": 0.41380413581001874,
      "learning_rate": 6.106260641143547e-07,
      "loss": 0.557223129272461,
      "step": 310
    },
    {
      "epoch": 1.627151051625239,
      "grad_norm": 0.40431587996323254,
      "learning_rate": 4.799290593860525e-07,
      "loss": 0.5616373538970947,
      "step": 320
    },
    {
      "epoch": 1.6781389420012747,
      "grad_norm": 0.424245009178222,
      "learning_rate": 3.634772294730984e-07,
      "loss": 0.5575815677642822,
      "step": 330
    },
    {
      "epoch": 1.7291268323773104,
      "grad_norm": 0.4342091026769172,
      "learning_rate": 2.620917716123444e-07,
      "loss": 0.5654561042785644,
      "step": 340
    },
    {
      "epoch": 1.780114722753346,
      "grad_norm": 0.409379475129272,
      "learning_rate": 1.7648763771063837e-07,
      "loss": 0.5648223876953125,
      "step": 350
    },
    {
      "epoch": 1.8311026131293817,
      "grad_norm": 0.3973433847927349,
      "learning_rate": 1.0726849263332257e-07,
      "loss": 0.5617156028747559,
      "step": 360
    },
    {
      "epoch": 1.8820905035054176,
      "grad_norm": 0.39525754442233196,
      "learning_rate": 5.492245726881201e-08,
      "loss": 0.5615170478820801,
      "step": 370
    },
    {
      "epoch": 1.9330783938814533,
      "grad_norm": 0.4368035774597164,
      "learning_rate": 1.981866638839952e-08,
      "loss": 0.5589813232421875,
      "step": 380
    },
    {
      "epoch": 1.984066284257489,
      "grad_norm": 0.402833990698094,
      "learning_rate": 2.2046655746280064e-09,
      "loss": 0.5635379791259766,
      "step": 390
    }
  ],
  "logging_steps": 10,
  "max_steps": 394,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.7229398914629632e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}