{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 100,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11196641007697691,
      "grad_norm": 33.81226137131406,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.7358,
      "step": 10
    },
    {
      "epoch": 0.22393282015395383,
      "grad_norm": 3.126971357941473,
      "learning_rate": 8.444444444444446e-06,
      "loss": 0.527,
      "step": 20
    },
    {
      "epoch": 0.3358992302309307,
      "grad_norm": 1.6515920436614058,
      "learning_rate": 1.288888888888889e-05,
      "loss": 0.3884,
      "step": 30
    },
    {
      "epoch": 0.44786564030790765,
      "grad_norm": 0.9474838344715308,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 0.3406,
      "step": 40
    },
    {
      "epoch": 0.5598320503848845,
      "grad_norm": 5.128129734480829,
      "learning_rate": 1.9995186678809513e-05,
      "loss": 0.311,
      "step": 50
    },
    {
      "epoch": 0.6717984604618614,
      "grad_norm": 1.6245368590343587,
      "learning_rate": 1.9941090015469614e-05,
      "loss": 0.2988,
      "step": 60
    },
    {
      "epoch": 0.7837648705388384,
      "grad_norm": 1.611763809071587,
      "learning_rate": 1.9827206467064133e-05,
      "loss": 0.2809,
      "step": 70
    },
    {
      "epoch": 0.8957312806158153,
      "grad_norm": 1.668412741711298,
      "learning_rate": 1.9654220942653223e-05,
      "loss": 0.2657,
      "step": 80
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.1431570423104263,
      "learning_rate": 1.9423173797534924e-05,
      "loss": 0.2516,
      "step": 90
    },
    {
      "epoch": 1.1119664100769768,
      "grad_norm": 1.484525869599161,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.2454,
      "step": 100
    },
    {
      "epoch": 1.1119664100769768,
      "eval_loss": 0.22891120612621307,
      "eval_runtime": 286.3307,
      "eval_samples_per_second": 12.611,
      "eval_steps_per_second": 3.154,
      "step": 100
    },
    {
      "epoch": 1.2239328201539539,
      "grad_norm": 0.9405329027791991,
      "learning_rate": 1.8792793656576544e-05,
      "loss": 0.2278,
      "step": 110
    },
    {
      "epoch": 1.3358992302309307,
      "grad_norm": 0.9185178253042293,
      "learning_rate": 1.83972518410775e-05,
      "loss": 0.2255,
      "step": 120
    },
    {
      "epoch": 1.4478656403079078,
      "grad_norm": 0.9372739726044865,
      "learning_rate": 1.795120796494848e-05,
      "loss": 0.2077,
      "step": 130
    },
    {
      "epoch": 1.5598320503848844,
      "grad_norm": 0.925740357050994,
      "learning_rate": 1.7457344588544018e-05,
      "loss": 0.1993,
      "step": 140
    },
    {
      "epoch": 1.6717984604618614,
      "grad_norm": 0.7697996358485442,
      "learning_rate": 1.691863186431996e-05,
      "loss": 0.1939,
      "step": 150
    },
    {
      "epoch": 1.7837648705388385,
      "grad_norm": 0.8197178548611251,
      "learning_rate": 1.63383096739871e-05,
      "loss": 0.1893,
      "step": 160
    },
    {
      "epoch": 1.8957312806158153,
      "grad_norm": 0.9757358666800248,
      "learning_rate": 1.5719868143481385e-05,
      "loss": 0.1884,
      "step": 170
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2912361931178282,
      "learning_rate": 1.5067026652935823e-05,
      "loss": 0.1853,
      "step": 180
    },
    {
      "epoch": 2.111966410076977,
      "grad_norm": 1.474922245397056,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 0.1573,
      "step": 190
    },
    {
      "epoch": 2.2239328201539537,
      "grad_norm": 0.9986943692773409,
      "learning_rate": 1.3674032126270982e-05,
      "loss": 0.1529,
      "step": 200
    },
    {
      "epoch": 2.2239328201539537,
      "eval_loss": 0.16729743778705597,
      "eval_runtime": 285.6086,
      "eval_samples_per_second": 12.643,
      "eval_steps_per_second": 3.162,
      "step": 200
    },
    {
      "epoch": 2.3358992302309307,
      "grad_norm": 0.9859620630820712,
      "learning_rate": 1.2942256723140951e-05,
      "loss": 0.1463,
      "step": 210
    },
    {
      "epoch": 2.4478656403079078,
      "grad_norm": 1.024082621214941,
      "learning_rate": 1.2192786241879033e-05,
      "loss": 0.1483,
      "step": 220
    },
    {
      "epoch": 2.5598320503848844,
      "grad_norm": 1.598786152428906,
      "learning_rate": 1.1430128086145542e-05,
      "loss": 0.1427,
      "step": 230
    },
    {
      "epoch": 2.6717984604618614,
      "grad_norm": 1.144250546323373,
      "learning_rate": 1.0658868971826785e-05,
      "loss": 0.1396,
      "step": 240
    },
    {
      "epoch": 2.7837648705388385,
      "grad_norm": 1.3171148556460246,
      "learning_rate": 9.883647341986032e-06,
      "loss": 0.1435,
      "step": 250
    },
    {
      "epoch": 2.8957312806158155,
      "grad_norm": 1.3050297429331412,
      "learning_rate": 9.109125470721141e-06,
      "loss": 0.1376,
      "step": 260
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.0588600615076165,
      "learning_rate": 8.339961423699563e-06,
      "loss": 0.1316,
      "step": 270
    },
    {
      "epoch": 3.111966410076977,
      "grad_norm": 0.8592010481316492,
      "learning_rate": 7.580781044003324e-06,
      "loss": 0.0971,
      "step": 280
    },
    {
      "epoch": 3.2239328201539537,
      "grad_norm": 0.8577283238163106,
      "learning_rate": 6.836150131764434e-06,
      "loss": 0.091,
      "step": 290
    },
    {
      "epoch": 3.3358992302309307,
      "grad_norm": 0.9724458618856975,
      "learning_rate": 6.110546984905661e-06,
      "loss": 0.092,
      "step": 300
    },
    {
      "epoch": 3.3358992302309307,
      "eval_loss": 0.15226292610168457,
      "eval_runtime": 287.4988,
      "eval_samples_per_second": 12.56,
      "eval_steps_per_second": 3.141,
      "step": 300
    },
    {
      "epoch": 3.4478656403079078,
      "grad_norm": 0.8936150624163902,
      "learning_rate": 5.4083354661298816e-06,
      "loss": 0.0946,
      "step": 310
    },
    {
      "epoch": 3.5598320503848844,
      "grad_norm": 1.0679426174534363,
      "learning_rate": 4.733738758136327e-06,
      "loss": 0.0903,
      "step": 320
    },
    {
      "epoch": 3.6717984604618614,
      "grad_norm": 0.8111210923652022,
      "learning_rate": 4.090813964902889e-06,
      "loss": 0.0902,
      "step": 330
    },
    {
      "epoch": 3.7837648705388385,
      "grad_norm": 0.7703375424111073,
      "learning_rate": 3.483427711785449e-06,
      "loss": 0.0889,
      "step": 340
    },
    {
      "epoch": 3.8957312806158155,
      "grad_norm": 0.7695783263553115,
      "learning_rate": 2.9152328911780027e-06,
      "loss": 0.0887,
      "step": 350
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.2361026171433047,
      "learning_rate": 2.3896466935879957e-06,
      "loss": 0.0869,
      "step": 360
    },
    {
      "epoch": 4.111966410076977,
      "grad_norm": 0.9550292309615054,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.0511,
      "step": 370
    },
    {
      "epoch": 4.223932820153954,
      "grad_norm": 1.0697797184845586,
      "learning_rate": 1.4786686528798878e-06,
      "loss": 0.0463,
      "step": 380
    },
    {
      "epoch": 4.335899230230931,
      "grad_norm": 0.8865827700265828,
      "learning_rate": 1.0987555388883042e-06,
      "loss": 0.0489,
      "step": 390
    },
    {
      "epoch": 4.447865640307907,
      "grad_norm": 0.7124572654292929,
      "learning_rate": 7.723755564455771e-07,
      "loss": 0.0468,
      "step": 400
    },
    {
      "epoch": 4.447865640307907,
      "eval_loss": 0.16100895404815674,
      "eval_runtime": 287.4696,
      "eval_samples_per_second": 12.561,
      "eval_steps_per_second": 3.141,
      "step": 400
    },
    {
      "epoch": 4.559832050384885,
      "grad_norm": 0.9828904035166229,
      "learning_rate": 5.014915931694253e-07,
      "loss": 0.0489,
      "step": 410
    },
    {
      "epoch": 4.671798460461861,
      "grad_norm": 1.0769307241878894,
      "learning_rate": 2.877327770883964e-07,
      "loss": 0.0468,
      "step": 420
    },
    {
      "epoch": 4.783764870538838,
      "grad_norm": 0.6207039011889628,
      "learning_rate": 1.323846788742078e-07,
      "loss": 0.0451,
      "step": 430
    },
    {
      "epoch": 4.8957312806158155,
      "grad_norm": 0.6680279322413308,
      "learning_rate": 3.6381580268463056e-08,
      "loss": 0.0453,
      "step": 440
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.2204562214644834,
      "learning_rate": 3.008552023242572e-10,
      "loss": 0.0437,
      "step": 450
    },
    {
      "epoch": 5.0,
      "step": 450,
      "total_flos": 1189207571693568.0,
      "train_loss": 0.21788453512721592,
      "train_runtime": 25758.9773,
      "train_samples_per_second": 13.314,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1189207571693568.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}