{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9916897506925206,
  "eval_steps": 500,
  "global_step": 675,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0443213296398892,
      "grad_norm": 7.052213448686623,
      "learning_rate": 5e-06,
      "loss": 0.5829,
      "step": 10
    },
    {
      "epoch": 0.0886426592797784,
      "grad_norm": 1.5459335266979457,
      "learning_rate": 5e-06,
      "loss": 0.513,
      "step": 20
    },
    {
      "epoch": 0.1329639889196676,
      "grad_norm": 0.719225680086632,
      "learning_rate": 5e-06,
      "loss": 0.4887,
      "step": 30
    },
    {
      "epoch": 0.1772853185595568,
      "grad_norm": 0.8892381207222515,
      "learning_rate": 5e-06,
      "loss": 0.4649,
      "step": 40
    },
    {
      "epoch": 0.22160664819944598,
      "grad_norm": 0.7186105716522034,
      "learning_rate": 5e-06,
      "loss": 0.4513,
      "step": 50
    },
    {
      "epoch": 0.2659279778393352,
      "grad_norm": 0.6156329427239773,
      "learning_rate": 5e-06,
      "loss": 0.4487,
      "step": 60
    },
    {
      "epoch": 0.31024930747922436,
      "grad_norm": 0.5853871188550711,
      "learning_rate": 5e-06,
      "loss": 0.4406,
      "step": 70
    },
    {
      "epoch": 0.3545706371191136,
      "grad_norm": 0.5482082304131989,
      "learning_rate": 5e-06,
      "loss": 0.4359,
      "step": 80
    },
    {
      "epoch": 0.3988919667590028,
      "grad_norm": 0.4424843900141646,
      "learning_rate": 5e-06,
      "loss": 0.4278,
      "step": 90
    },
    {
      "epoch": 0.44321329639889195,
      "grad_norm": 0.5500270978536973,
      "learning_rate": 5e-06,
      "loss": 0.4266,
      "step": 100
    },
    {
      "epoch": 0.48753462603878117,
      "grad_norm": 0.4890554413822,
      "learning_rate": 5e-06,
      "loss": 0.4198,
      "step": 110
    },
    {
      "epoch": 0.5318559556786704,
      "grad_norm": 0.3929640794177042,
      "learning_rate": 5e-06,
      "loss": 0.4201,
      "step": 120
    },
    {
      "epoch": 0.5761772853185596,
      "grad_norm": 0.5298403296766302,
      "learning_rate": 5e-06,
      "loss": 0.4198,
      "step": 130
    },
    {
      "epoch": 0.6204986149584487,
      "grad_norm": 0.3477088076642203,
      "learning_rate": 5e-06,
      "loss": 0.4181,
      "step": 140
    },
    {
      "epoch": 0.6648199445983379,
      "grad_norm": 0.4351495846909543,
      "learning_rate": 5e-06,
      "loss": 0.4147,
      "step": 150
    },
    {
      "epoch": 0.7091412742382271,
      "grad_norm": 0.381148974745445,
      "learning_rate": 5e-06,
      "loss": 0.412,
      "step": 160
    },
    {
      "epoch": 0.7534626038781164,
      "grad_norm": 0.34662500124731266,
      "learning_rate": 5e-06,
      "loss": 0.4166,
      "step": 170
    },
    {
      "epoch": 0.7977839335180056,
      "grad_norm": 0.45421320442815966,
      "learning_rate": 5e-06,
      "loss": 0.4132,
      "step": 180
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.3659178106228611,
      "learning_rate": 5e-06,
      "loss": 0.4136,
      "step": 190
    },
    {
      "epoch": 0.8864265927977839,
      "grad_norm": 0.6021107216904796,
      "learning_rate": 5e-06,
      "loss": 0.4041,
      "step": 200
    },
    {
      "epoch": 0.9307479224376731,
      "grad_norm": 0.5276638445937896,
      "learning_rate": 5e-06,
      "loss": 0.411,
      "step": 210
    },
    {
      "epoch": 0.9750692520775623,
      "grad_norm": 0.37923132404108995,
      "learning_rate": 5e-06,
      "loss": 0.4061,
      "step": 220
    },
    {
      "epoch": 0.997229916897507,
      "eval_loss": 0.4077036678791046,
      "eval_runtime": 158.0392,
      "eval_samples_per_second": 38.459,
      "eval_steps_per_second": 0.601,
      "step": 225
    },
    {
      "epoch": 1.0193905817174516,
      "grad_norm": 0.4441527989618394,
      "learning_rate": 5e-06,
      "loss": 0.4093,
      "step": 230
    },
    {
      "epoch": 1.0637119113573408,
      "grad_norm": 0.383360121111077,
      "learning_rate": 5e-06,
      "loss": 0.3815,
      "step": 240
    },
    {
      "epoch": 1.10803324099723,
      "grad_norm": 0.3990576858944248,
      "learning_rate": 5e-06,
      "loss": 0.3761,
      "step": 250
    },
    {
      "epoch": 1.1523545706371192,
      "grad_norm": 0.503954633758602,
      "learning_rate": 5e-06,
      "loss": 0.3818,
      "step": 260
    },
    {
      "epoch": 1.1966759002770084,
      "grad_norm": 0.4527787565971453,
      "learning_rate": 5e-06,
      "loss": 0.3792,
      "step": 270
    },
    {
      "epoch": 1.2409972299168974,
      "grad_norm": 0.3939361247356342,
      "learning_rate": 5e-06,
      "loss": 0.3768,
      "step": 280
    },
    {
      "epoch": 1.2853185595567866,
      "grad_norm": 0.41328816849632577,
      "learning_rate": 5e-06,
      "loss": 0.3813,
      "step": 290
    },
    {
      "epoch": 1.3296398891966759,
      "grad_norm": 0.47753446079826084,
      "learning_rate": 5e-06,
      "loss": 0.3819,
      "step": 300
    },
    {
      "epoch": 1.373961218836565,
      "grad_norm": 0.38082453273018374,
      "learning_rate": 5e-06,
      "loss": 0.38,
      "step": 310
    },
    {
      "epoch": 1.4182825484764543,
      "grad_norm": 0.5159796944766167,
      "learning_rate": 5e-06,
      "loss": 0.3755,
      "step": 320
    },
    {
      "epoch": 1.4626038781163435,
      "grad_norm": 0.3829464355523,
      "learning_rate": 5e-06,
      "loss": 0.3808,
      "step": 330
    },
    {
      "epoch": 1.5069252077562327,
      "grad_norm": 0.3492766964963765,
      "learning_rate": 5e-06,
      "loss": 0.3778,
      "step": 340
    },
    {
      "epoch": 1.5512465373961217,
      "grad_norm": 0.36812848860180375,
      "learning_rate": 5e-06,
      "loss": 0.3779,
      "step": 350
    },
    {
      "epoch": 1.595567867036011,
      "grad_norm": 0.41462318446315016,
      "learning_rate": 5e-06,
      "loss": 0.374,
      "step": 360
    },
    {
      "epoch": 1.6398891966759002,
      "grad_norm": 0.42749575402289264,
      "learning_rate": 5e-06,
      "loss": 0.3776,
      "step": 370
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 0.4420757091228596,
      "learning_rate": 5e-06,
      "loss": 0.3805,
      "step": 380
    },
    {
      "epoch": 1.7285318559556786,
      "grad_norm": 0.39320471180120625,
      "learning_rate": 5e-06,
      "loss": 0.3776,
      "step": 390
    },
    {
      "epoch": 1.7728531855955678,
      "grad_norm": 0.4455011162465814,
      "learning_rate": 5e-06,
      "loss": 0.3759,
      "step": 400
    },
    {
      "epoch": 1.817174515235457,
      "grad_norm": 0.3564174208371923,
      "learning_rate": 5e-06,
      "loss": 0.3797,
      "step": 410
    },
    {
      "epoch": 1.8614958448753463,
      "grad_norm": 0.3965273061639582,
      "learning_rate": 5e-06,
      "loss": 0.3736,
      "step": 420
    },
    {
      "epoch": 1.9058171745152355,
      "grad_norm": 0.3593250927656118,
      "learning_rate": 5e-06,
      "loss": 0.3761,
      "step": 430
    },
    {
      "epoch": 1.9501385041551247,
      "grad_norm": 0.38504819696326603,
      "learning_rate": 5e-06,
      "loss": 0.3731,
      "step": 440
    },
    {
      "epoch": 1.994459833795014,
      "grad_norm": 0.3949630765714435,
      "learning_rate": 5e-06,
      "loss": 0.3726,
      "step": 450
    },
    {
      "epoch": 1.9988919667590028,
      "eval_loss": 0.3975733816623688,
      "eval_runtime": 156.1473,
      "eval_samples_per_second": 38.925,
      "eval_steps_per_second": 0.608,
      "step": 451
    },
    {
      "epoch": 2.038781163434903,
      "grad_norm": 0.4124343429602089,
      "learning_rate": 5e-06,
      "loss": 0.3629,
      "step": 460
    },
    {
      "epoch": 2.0831024930747923,
      "grad_norm": 0.43159824833217403,
      "learning_rate": 5e-06,
      "loss": 0.3425,
      "step": 470
    },
    {
      "epoch": 2.1274238227146816,
      "grad_norm": 0.4156394960465829,
      "learning_rate": 5e-06,
      "loss": 0.3458,
      "step": 480
    },
    {
      "epoch": 2.1717451523545708,
      "grad_norm": 0.439672844432952,
      "learning_rate": 5e-06,
      "loss": 0.3487,
      "step": 490
    },
    {
      "epoch": 2.21606648199446,
      "grad_norm": 0.3756131515472198,
      "learning_rate": 5e-06,
      "loss": 0.344,
      "step": 500
    },
    {
      "epoch": 2.260387811634349,
      "grad_norm": 0.4320607459725008,
      "learning_rate": 5e-06,
      "loss": 0.3469,
      "step": 510
    },
    {
      "epoch": 2.3047091412742384,
      "grad_norm": 0.48325455407748324,
      "learning_rate": 5e-06,
      "loss": 0.344,
      "step": 520
    },
    {
      "epoch": 2.349030470914127,
      "grad_norm": 0.509688954969155,
      "learning_rate": 5e-06,
      "loss": 0.3422,
      "step": 530
    },
    {
      "epoch": 2.393351800554017,
      "grad_norm": 0.47004871752405086,
      "learning_rate": 5e-06,
      "loss": 0.3481,
      "step": 540
    },
    {
      "epoch": 2.4376731301939056,
      "grad_norm": 0.37357609406356407,
      "learning_rate": 5e-06,
      "loss": 0.3475,
      "step": 550
    },
    {
      "epoch": 2.481994459833795,
      "grad_norm": 0.37773993115530186,
      "learning_rate": 5e-06,
      "loss": 0.35,
      "step": 560
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 0.3918590091549487,
      "learning_rate": 5e-06,
      "loss": 0.3466,
      "step": 570
    },
    {
      "epoch": 2.5706371191135733,
      "grad_norm": 0.376355539356745,
      "learning_rate": 5e-06,
      "loss": 0.3459,
      "step": 580
    },
    {
      "epoch": 2.6149584487534625,
      "grad_norm": 0.39220517786717213,
      "learning_rate": 5e-06,
      "loss": 0.3448,
      "step": 590
    },
    {
      "epoch": 2.6592797783933517,
      "grad_norm": 0.40029072930864157,
      "learning_rate": 5e-06,
      "loss": 0.3482,
      "step": 600
    },
    {
      "epoch": 2.703601108033241,
      "grad_norm": 0.38197937787666936,
      "learning_rate": 5e-06,
      "loss": 0.3481,
      "step": 610
    },
    {
      "epoch": 2.74792243767313,
      "grad_norm": 0.4857867587877145,
      "learning_rate": 5e-06,
      "loss": 0.3474,
      "step": 620
    },
    {
      "epoch": 2.7922437673130194,
      "grad_norm": 0.4816618353336751,
      "learning_rate": 5e-06,
      "loss": 0.3429,
      "step": 630
    },
    {
      "epoch": 2.8365650969529086,
      "grad_norm": 0.4843151337200677,
      "learning_rate": 5e-06,
      "loss": 0.3491,
      "step": 640
    },
    {
      "epoch": 2.880886426592798,
      "grad_norm": 0.3849874491982438,
      "learning_rate": 5e-06,
      "loss": 0.3479,
      "step": 650
    },
    {
      "epoch": 2.925207756232687,
      "grad_norm": 0.42190162748247967,
      "learning_rate": 5e-06,
      "loss": 0.3472,
      "step": 660
    },
    {
      "epoch": 2.9695290858725762,
      "grad_norm": 0.42143659183843213,
      "learning_rate": 5e-06,
      "loss": 0.3467,
      "step": 670
    },
    {
      "epoch": 2.9916897506925206,
      "eval_loss": 0.39780595898628235,
      "eval_runtime": 154.2343,
      "eval_samples_per_second": 39.408,
      "eval_steps_per_second": 0.616,
      "step": 675
    },
    {
      "epoch": 2.9916897506925206,
      "step": 675,
      "total_flos": 1130440761016320.0,
      "train_loss": 0.3879174453240854,
      "train_runtime": 22444.4408,
      "train_samples_per_second": 15.435,
      "train_steps_per_second": 0.03
    }
  ],
  "logging_steps": 10,
  "max_steps": 675,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1130440761016320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}