{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9746588693957114,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01949317738791423,
      "grad_norm": 9.292141914367676,
      "learning_rate": 4.967511371020143e-05,
      "loss": 6.2548,
      "step": 10
    },
    {
      "epoch": 0.03898635477582846,
      "grad_norm": 7.766495227813721,
      "learning_rate": 4.935022742040286e-05,
      "loss": 5.0175,
      "step": 20
    },
    {
      "epoch": 0.05847953216374269,
      "grad_norm": 6.4375128746032715,
      "learning_rate": 4.902534113060429e-05,
      "loss": 4.59,
      "step": 30
    },
    {
      "epoch": 0.07797270955165692,
      "grad_norm": 7.395759105682373,
      "learning_rate": 4.8700454840805724e-05,
      "loss": 4.2891,
      "step": 40
    },
    {
      "epoch": 0.09746588693957114,
      "grad_norm": 5.542599678039551,
      "learning_rate": 4.837556855100715e-05,
      "loss": 4.1904,
      "step": 50
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 8.749999046325684,
      "learning_rate": 4.805068226120858e-05,
      "loss": 4.1512,
      "step": 60
    },
    {
      "epoch": 0.1364522417153996,
      "grad_norm": 6.6702446937561035,
      "learning_rate": 4.772579597141001e-05,
      "loss": 3.9695,
      "step": 70
    },
    {
      "epoch": 0.15594541910331383,
      "grad_norm": 13.8934326171875,
      "learning_rate": 4.740090968161144e-05,
      "loss": 3.9657,
      "step": 80
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 15.161931037902832,
      "learning_rate": 4.707602339181287e-05,
      "loss": 3.9312,
      "step": 90
    },
    {
      "epoch": 0.1949317738791423,
      "grad_norm": 8.096311569213867,
      "learning_rate": 4.67511371020143e-05,
      "loss": 3.9407,
      "step": 100
    },
    {
      "epoch": 0.21442495126705652,
      "grad_norm": 6.077565670013428,
      "learning_rate": 4.642625081221573e-05,
      "loss": 3.7438,
      "step": 110
    },
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 5.909548282623291,
      "learning_rate": 4.610136452241716e-05,
      "loss": 3.8495,
      "step": 120
    },
    {
      "epoch": 0.253411306042885,
      "grad_norm": 6.919253349304199,
      "learning_rate": 4.577647823261859e-05,
      "loss": 3.8178,
      "step": 130
    },
    {
      "epoch": 0.2729044834307992,
      "grad_norm": 5.3416218757629395,
      "learning_rate": 4.545159194282001e-05,
      "loss": 3.6388,
      "step": 140
    },
    {
      "epoch": 0.29239766081871343,
      "grad_norm": 6.484707832336426,
      "learning_rate": 4.512670565302144e-05,
      "loss": 3.8361,
      "step": 150
    },
    {
      "epoch": 0.31189083820662766,
      "grad_norm": 6.068100929260254,
      "learning_rate": 4.480181936322287e-05,
      "loss": 3.7164,
      "step": 160
    },
    {
      "epoch": 0.3313840155945419,
      "grad_norm": 6.298447608947754,
      "learning_rate": 4.4476933073424304e-05,
      "loss": 3.6589,
      "step": 170
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 4.752441883087158,
      "learning_rate": 4.4152046783625734e-05,
      "loss": 3.7328,
      "step": 180
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 5.050961971282959,
      "learning_rate": 4.3827160493827164e-05,
      "loss": 3.7162,
      "step": 190
    },
    {
      "epoch": 0.3898635477582846,
      "grad_norm": 4.73190975189209,
      "learning_rate": 4.3502274204028594e-05,
      "loss": 3.6748,
      "step": 200
    },
    {
      "epoch": 0.4093567251461988,
      "grad_norm": 10.872115135192871,
      "learning_rate": 4.3177387914230025e-05,
      "loss": 3.7618,
      "step": 210
    },
    {
      "epoch": 0.42884990253411304,
      "grad_norm": 6.119602680206299,
      "learning_rate": 4.285250162443145e-05,
      "loss": 3.747,
      "step": 220
    },
    {
      "epoch": 0.44834307992202727,
      "grad_norm": 5.332015514373779,
      "learning_rate": 4.252761533463288e-05,
      "loss": 3.6214,
      "step": 230
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 5.08021354675293,
      "learning_rate": 4.220272904483431e-05,
      "loss": 3.5122,
      "step": 240
    },
    {
      "epoch": 0.4873294346978557,
      "grad_norm": 4.609364986419678,
      "learning_rate": 4.187784275503574e-05,
      "loss": 3.5281,
      "step": 250
    },
    {
      "epoch": 0.50682261208577,
      "grad_norm": 24.73488998413086,
      "learning_rate": 4.155295646523717e-05,
      "loss": 3.7142,
      "step": 260
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 5.869173526763916,
      "learning_rate": 4.12280701754386e-05,
      "loss": 3.577,
      "step": 270
    },
    {
      "epoch": 0.5458089668615984,
      "grad_norm": 5.6849470138549805,
      "learning_rate": 4.090318388564003e-05,
      "loss": 3.6146,
      "step": 280
    },
    {
      "epoch": 0.5653021442495126,
      "grad_norm": 5.919517517089844,
      "learning_rate": 4.057829759584146e-05,
      "loss": 3.5417,
      "step": 290
    },
    {
      "epoch": 0.5847953216374269,
      "grad_norm": 5.177787780761719,
      "learning_rate": 4.025341130604289e-05,
      "loss": 3.5453,
      "step": 300
    },
    {
      "epoch": 0.6042884990253411,
      "grad_norm": 5.569265842437744,
      "learning_rate": 3.9928525016244314e-05,
      "loss": 3.5203,
      "step": 310
    },
    {
      "epoch": 0.6237816764132553,
      "grad_norm": 6.63994026184082,
      "learning_rate": 3.9603638726445744e-05,
      "loss": 3.5504,
      "step": 320
    },
    {
      "epoch": 0.6432748538011696,
      "grad_norm": 5.785546779632568,
      "learning_rate": 3.9278752436647174e-05,
      "loss": 3.5587,
      "step": 330
    },
    {
      "epoch": 0.6627680311890838,
      "grad_norm": 5.489815711975098,
      "learning_rate": 3.8953866146848605e-05,
      "loss": 3.5612,
      "step": 340
    },
    {
      "epoch": 0.682261208576998,
      "grad_norm": 4.650988578796387,
      "learning_rate": 3.8628979857050035e-05,
      "loss": 3.5062,
      "step": 350
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 5.7823872566223145,
      "learning_rate": 3.8304093567251465e-05,
      "loss": 3.5819,
      "step": 360
    },
    {
      "epoch": 0.7212475633528265,
      "grad_norm": 7.364371299743652,
      "learning_rate": 3.7979207277452896e-05,
      "loss": 3.5845,
      "step": 370
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 6.099256992340088,
      "learning_rate": 3.7654320987654326e-05,
      "loss": 3.5787,
      "step": 380
    },
    {
      "epoch": 0.7602339181286549,
      "grad_norm": 5.115094184875488,
      "learning_rate": 3.7329434697855756e-05,
      "loss": 3.5901,
      "step": 390
    },
    {
      "epoch": 0.7797270955165692,
      "grad_norm": 5.4442830085754395,
      "learning_rate": 3.700454840805718e-05,
      "loss": 3.4565,
      "step": 400
    },
    {
      "epoch": 0.7992202729044834,
      "grad_norm": 6.6567816734313965,
      "learning_rate": 3.667966211825861e-05,
      "loss": 3.5481,
      "step": 410
    },
    {
      "epoch": 0.8187134502923976,
      "grad_norm": 5.831213474273682,
      "learning_rate": 3.635477582846004e-05,
      "loss": 3.4274,
      "step": 420
    },
    {
      "epoch": 0.8382066276803118,
      "grad_norm": 5.754021167755127,
      "learning_rate": 3.602988953866147e-05,
      "loss": 3.423,
      "step": 430
    },
    {
      "epoch": 0.8576998050682261,
      "grad_norm": 5.590385437011719,
      "learning_rate": 3.57050032488629e-05,
      "loss": 3.6208,
      "step": 440
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 4.159304141998291,
      "learning_rate": 3.538011695906433e-05,
      "loss": 3.4107,
      "step": 450
    },
    {
      "epoch": 0.8966861598440545,
      "grad_norm": 5.699474334716797,
      "learning_rate": 3.505523066926576e-05,
      "loss": 3.3759,
      "step": 460
    },
    {
      "epoch": 0.9161793372319688,
      "grad_norm": 5.0284929275512695,
      "learning_rate": 3.473034437946719e-05,
      "loss": 3.4719,
      "step": 470
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 4.884040832519531,
      "learning_rate": 3.440545808966862e-05,
      "loss": 3.5534,
      "step": 480
    },
    {
      "epoch": 0.9551656920077972,
      "grad_norm": 5.428916931152344,
      "learning_rate": 3.4080571799870045e-05,
      "loss": 3.3919,
      "step": 490
    },
    {
      "epoch": 0.9746588693957114,
      "grad_norm": 5.549111843109131,
      "learning_rate": 3.3755685510071476e-05,
      "loss": 3.2799,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1539,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1045168128000000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}