{
  "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": 21.06309415699912,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.8571,
      "step": 10
    },
    {
      "epoch": 0.22393282015395383,
      "grad_norm": 1.9727286004327564,
      "learning_rate": 8.444444444444446e-06,
      "loss": 0.6148,
      "step": 20
    },
    {
      "epoch": 0.3358992302309307,
      "grad_norm": 2.2884377083477645,
      "learning_rate": 1.288888888888889e-05,
      "loss": 0.3928,
      "step": 30
    },
    {
      "epoch": 0.44786564030790765,
      "grad_norm": 1.647085854397205,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 0.3458,
      "step": 40
    },
    {
      "epoch": 0.5598320503848845,
      "grad_norm": 2.329816835595036,
      "learning_rate": 1.9995186678809513e-05,
      "loss": 0.3267,
      "step": 50
    },
    {
      "epoch": 0.6717984604618614,
      "grad_norm": 1.519218251845277,
      "learning_rate": 1.9941090015469614e-05,
      "loss": 0.3158,
      "step": 60
    },
    {
      "epoch": 0.7837648705388384,
      "grad_norm": 1.3244908123467292,
      "learning_rate": 1.9827206467064133e-05,
      "loss": 0.3016,
      "step": 70
    },
    {
      "epoch": 0.8957312806158153,
      "grad_norm": 1.0638147560775397,
      "learning_rate": 1.9654220942653223e-05,
      "loss": 0.278,
      "step": 80
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.3750398954831957,
      "learning_rate": 1.9423173797534924e-05,
      "loss": 0.2639,
      "step": 90
    },
    {
      "epoch": 1.1119664100769768,
      "grad_norm": 1.4059952043975563,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.2532,
      "step": 100
    },
    {
      "epoch": 1.1119664100769768,
      "eval_loss": 0.2309780865907669,
      "eval_runtime": 334.81,
      "eval_samples_per_second": 10.785,
      "eval_steps_per_second": 2.697,
      "step": 100
    },
    {
      "epoch": 1.2239328201539539,
      "grad_norm": 0.7770380776412505,
      "learning_rate": 1.8792793656576544e-05,
      "loss": 0.2366,
      "step": 110
    },
    {
      "epoch": 1.3358992302309307,
      "grad_norm": 1.053613780680287,
      "learning_rate": 1.83972518410775e-05,
      "loss": 0.2316,
      "step": 120
    },
    {
      "epoch": 1.4478656403079078,
      "grad_norm": 0.8850308205683671,
      "learning_rate": 1.795120796494848e-05,
      "loss": 0.2216,
      "step": 130
    },
    {
      "epoch": 1.5598320503848844,
      "grad_norm": 1.080177617549634,
      "learning_rate": 1.7457344588544018e-05,
      "loss": 0.2155,
      "step": 140
    },
    {
      "epoch": 1.6717984604618614,
      "grad_norm": 0.8218548086924884,
      "learning_rate": 1.691863186431996e-05,
      "loss": 0.2122,
      "step": 150
    },
    {
      "epoch": 1.7837648705388385,
      "grad_norm": 0.6988372786589893,
      "learning_rate": 1.63383096739871e-05,
      "loss": 0.2059,
      "step": 160
    },
    {
      "epoch": 1.8957312806158153,
      "grad_norm": 0.7684849910572107,
      "learning_rate": 1.5719868143481385e-05,
      "loss": 0.2034,
      "step": 170
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2808833317754085,
      "learning_rate": 1.5067026652935823e-05,
      "loss": 0.1995,
      "step": 180
    },
    {
      "epoch": 2.111966410076977,
      "grad_norm": 0.9108986394736251,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 0.1764,
      "step": 190
    },
    {
      "epoch": 2.2239328201539537,
      "grad_norm": 1.0633553433425496,
      "learning_rate": 1.3674032126270982e-05,
      "loss": 0.1713,
      "step": 200
    },
    {
      "epoch": 2.2239328201539537,
      "eval_loss": 0.18000730872154236,
      "eval_runtime": 337.0653,
      "eval_samples_per_second": 10.713,
      "eval_steps_per_second": 2.679,
      "step": 200
    },
    {
      "epoch": 2.3358992302309307,
      "grad_norm": 0.8859214091666336,
      "learning_rate": 1.2942256723140951e-05,
      "loss": 0.1671,
      "step": 210
    },
    {
      "epoch": 2.4478656403079078,
      "grad_norm": 0.849493216288489,
      "learning_rate": 1.2192786241879033e-05,
      "loss": 0.1703,
      "step": 220
    },
    {
      "epoch": 2.5598320503848844,
      "grad_norm": 1.0004480128274726,
      "learning_rate": 1.1430128086145542e-05,
      "loss": 0.1642,
      "step": 230
    },
    {
      "epoch": 2.6717984604618614,
      "grad_norm": 0.9096432098561809,
      "learning_rate": 1.0658868971826785e-05,
      "loss": 0.1553,
      "step": 240
    },
    {
      "epoch": 2.7837648705388385,
      "grad_norm": 0.7475626808919502,
      "learning_rate": 9.883647341986032e-06,
      "loss": 0.1616,
      "step": 250
    },
    {
      "epoch": 2.8957312806158155,
      "grad_norm": 0.7289602464956204,
      "learning_rate": 9.109125470721141e-06,
      "loss": 0.157,
      "step": 260
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9343429127547538,
      "learning_rate": 8.339961423699563e-06,
      "loss": 0.1528,
      "step": 270
    },
    {
      "epoch": 3.111966410076977,
      "grad_norm": 0.8272491815261758,
      "learning_rate": 7.580781044003324e-06,
      "loss": 0.1249,
      "step": 280
    },
    {
      "epoch": 3.2239328201539537,
      "grad_norm": 0.8785316150577709,
      "learning_rate": 6.836150131764434e-06,
      "loss": 0.1168,
      "step": 290
    },
    {
      "epoch": 3.3358992302309307,
      "grad_norm": 0.8757974207894819,
      "learning_rate": 6.110546984905661e-06,
      "loss": 0.1178,
      "step": 300
    },
    {
      "epoch": 3.3358992302309307,
      "eval_loss": 0.15590140223503113,
      "eval_runtime": 335.9835,
      "eval_samples_per_second": 10.748,
      "eval_steps_per_second": 2.688,
      "step": 300
    },
    {
      "epoch": 3.4478656403079078,
      "grad_norm": 0.8970654870881085,
      "learning_rate": 5.4083354661298816e-06,
      "loss": 0.1208,
      "step": 310
    },
    {
      "epoch": 3.5598320503848844,
      "grad_norm": 0.7754639069886827,
      "learning_rate": 4.733738758136327e-06,
      "loss": 0.1144,
      "step": 320
    },
    {
      "epoch": 3.6717984604618614,
      "grad_norm": 1.892274710129508,
      "learning_rate": 4.090813964902889e-06,
      "loss": 0.1156,
      "step": 330
    },
    {
      "epoch": 3.7837648705388385,
      "grad_norm": 1.2589854864442425,
      "learning_rate": 3.483427711785449e-06,
      "loss": 0.1132,
      "step": 340
    },
    {
      "epoch": 3.8957312806158155,
      "grad_norm": 0.8837972275737342,
      "learning_rate": 2.9152328911780027e-06,
      "loss": 0.1116,
      "step": 350
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.2328227938809153,
      "learning_rate": 2.3896466935879957e-06,
      "loss": 0.1115,
      "step": 360
    },
    {
      "epoch": 4.111966410076977,
      "grad_norm": 0.9921573733470108,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.0792,
      "step": 370
    },
    {
      "epoch": 4.223932820153954,
      "grad_norm": 2.590495365853637,
      "learning_rate": 1.4786686528798878e-06,
      "loss": 0.0739,
      "step": 380
    },
    {
      "epoch": 4.335899230230931,
      "grad_norm": 1.172303338637939,
      "learning_rate": 1.0987555388883042e-06,
      "loss": 0.0777,
      "step": 390
    },
    {
      "epoch": 4.447865640307907,
      "grad_norm": 0.9032745376031973,
      "learning_rate": 7.723755564455771e-07,
      "loss": 0.0765,
      "step": 400
    },
    {
      "epoch": 4.447865640307907,
      "eval_loss": 0.16239598393440247,
      "eval_runtime": 335.8645,
      "eval_samples_per_second": 10.751,
      "eval_steps_per_second": 2.689,
      "step": 400
    },
    {
      "epoch": 4.559832050384885,
      "grad_norm": 1.200437444817232,
      "learning_rate": 5.014915931694253e-07,
      "loss": 0.0784,
      "step": 410
    },
    {
      "epoch": 4.671798460461861,
      "grad_norm": 2.214432160562882,
      "learning_rate": 2.877327770883964e-07,
      "loss": 0.0774,
      "step": 420
    },
    {
      "epoch": 4.783764870538838,
      "grad_norm": 0.7916736334089312,
      "learning_rate": 1.323846788742078e-07,
      "loss": 0.0736,
      "step": 430
    },
    {
      "epoch": 4.8957312806158155,
      "grad_norm": 0.8181788452191515,
      "learning_rate": 3.6381580268463056e-08,
      "loss": 0.0748,
      "step": 440
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.445524032141444,
      "learning_rate": 3.008552023242572e-10,
      "loss": 0.0727,
      "step": 450
    },
    {
      "epoch": 5.0,
      "step": 450,
      "total_flos": 1141497040732160.0,
      "train_loss": 0.24183495627509224,
      "train_runtime": 30070.9864,
      "train_samples_per_second": 11.405,
      "train_steps_per_second": 0.015
    }
  ],
  "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": 1141497040732160.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}