{
  "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": 11.058951343144956,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.2662,
      "step": 10
    },
    {
      "epoch": 0.22393282015395383,
      "grad_norm": 1.7729179977186644,
      "learning_rate": 8.444444444444446e-06,
      "loss": 0.4943,
      "step": 20
    },
    {
      "epoch": 0.3358992302309307,
      "grad_norm": 1.6356789772377058,
      "learning_rate": 1.288888888888889e-05,
      "loss": 0.3753,
      "step": 30
    },
    {
      "epoch": 0.44786564030790765,
      "grad_norm": 1.9288368362918538,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 0.3318,
      "step": 40
    },
    {
      "epoch": 0.5598320503848845,
      "grad_norm": 2.1566394022983353,
      "learning_rate": 1.9995186678809513e-05,
      "loss": 0.3098,
      "step": 50
    },
    {
      "epoch": 0.6717984604618614,
      "grad_norm": 1.5733525386121412,
      "learning_rate": 1.9941090015469614e-05,
      "loss": 0.3035,
      "step": 60
    },
    {
      "epoch": 0.7837648705388384,
      "grad_norm": 2.021696511302677,
      "learning_rate": 1.9827206467064133e-05,
      "loss": 0.2911,
      "step": 70
    },
    {
      "epoch": 0.8957312806158153,
      "grad_norm": 1.64083514298774,
      "learning_rate": 1.9654220942653223e-05,
      "loss": 0.2698,
      "step": 80
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.0755102694232246,
      "learning_rate": 1.9423173797534924e-05,
      "loss": 0.2482,
      "step": 90
    },
    {
      "epoch": 1.1119664100769768,
      "grad_norm": 1.5670039755125356,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.2389,
      "step": 100
    },
    {
      "epoch": 1.1119664100769768,
      "eval_loss": 0.2237260341644287,
      "eval_runtime": 285.655,
      "eval_samples_per_second": 12.641,
      "eval_steps_per_second": 3.161,
      "step": 100
    },
    {
      "epoch": 1.2239328201539539,
      "grad_norm": 1.6921808254512753,
      "learning_rate": 1.8792793656576544e-05,
      "loss": 0.2251,
      "step": 110
    },
    {
      "epoch": 1.3358992302309307,
      "grad_norm": 1.560558186606318,
      "learning_rate": 1.83972518410775e-05,
      "loss": 0.2189,
      "step": 120
    },
    {
      "epoch": 1.4478656403079078,
      "grad_norm": 0.9394291704068763,
      "learning_rate": 1.795120796494848e-05,
      "loss": 0.2067,
      "step": 130
    },
    {
      "epoch": 1.5598320503848844,
      "grad_norm": 2.1331931003653395,
      "learning_rate": 1.7457344588544018e-05,
      "loss": 0.1981,
      "step": 140
    },
    {
      "epoch": 1.6717984604618614,
      "grad_norm": 3.225673121051341,
      "learning_rate": 1.691863186431996e-05,
      "loss": 0.191,
      "step": 150
    },
    {
      "epoch": 1.7837648705388385,
      "grad_norm": 2.3207674712564423,
      "learning_rate": 1.63383096739871e-05,
      "loss": 0.1914,
      "step": 160
    },
    {
      "epoch": 1.8957312806158153,
      "grad_norm": 3.0836297952114196,
      "learning_rate": 1.5719868143481385e-05,
      "loss": 0.1903,
      "step": 170
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3852945821310907,
      "learning_rate": 1.5067026652935823e-05,
      "loss": 0.1863,
      "step": 180
    },
    {
      "epoch": 2.111966410076977,
      "grad_norm": 1.0589006786111632,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 0.157,
      "step": 190
    },
    {
      "epoch": 2.2239328201539537,
      "grad_norm": 2.329498577605099,
      "learning_rate": 1.3674032126270982e-05,
      "loss": 0.153,
      "step": 200
    },
    {
      "epoch": 2.2239328201539537,
      "eval_loss": 0.16935566067695618,
      "eval_runtime": 288.0876,
      "eval_samples_per_second": 12.534,
      "eval_steps_per_second": 3.134,
      "step": 200
    },
    {
      "epoch": 2.3358992302309307,
      "grad_norm": 0.9868007174982117,
      "learning_rate": 1.2942256723140951e-05,
      "loss": 0.1498,
      "step": 210
    },
    {
      "epoch": 2.4478656403079078,
      "grad_norm": 1.5238457366552933,
      "learning_rate": 1.2192786241879033e-05,
      "loss": 0.153,
      "step": 220
    },
    {
      "epoch": 2.5598320503848844,
      "grad_norm": 0.8815985449709629,
      "learning_rate": 1.1430128086145542e-05,
      "loss": 0.1444,
      "step": 230
    },
    {
      "epoch": 2.6717984604618614,
      "grad_norm": 0.833209916798623,
      "learning_rate": 1.0658868971826785e-05,
      "loss": 0.1372,
      "step": 240
    },
    {
      "epoch": 2.7837648705388385,
      "grad_norm": 0.9924755156277105,
      "learning_rate": 9.883647341986032e-06,
      "loss": 0.1441,
      "step": 250
    },
    {
      "epoch": 2.8957312806158155,
      "grad_norm": 1.1970263328184974,
      "learning_rate": 9.109125470721141e-06,
      "loss": 0.1387,
      "step": 260
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.2187008058516546,
      "learning_rate": 8.339961423699563e-06,
      "loss": 0.1345,
      "step": 270
    },
    {
      "epoch": 3.111966410076977,
      "grad_norm": 1.4965672421457854,
      "learning_rate": 7.580781044003324e-06,
      "loss": 0.097,
      "step": 280
    },
    {
      "epoch": 3.2239328201539537,
      "grad_norm": 0.8831475425499654,
      "learning_rate": 6.836150131764434e-06,
      "loss": 0.088,
      "step": 290
    },
    {
      "epoch": 3.3358992302309307,
      "grad_norm": 0.8879587999039772,
      "learning_rate": 6.110546984905661e-06,
      "loss": 0.0898,
      "step": 300
    },
    {
      "epoch": 3.3358992302309307,
      "eval_loss": 0.14970648288726807,
      "eval_runtime": 291.8612,
      "eval_samples_per_second": 12.372,
      "eval_steps_per_second": 3.094,
      "step": 300
    },
    {
      "epoch": 3.4478656403079078,
      "grad_norm": 0.8491949718471089,
      "learning_rate": 5.4083354661298816e-06,
      "loss": 0.0921,
      "step": 310
    },
    {
      "epoch": 3.5598320503848844,
      "grad_norm": 0.775153706173452,
      "learning_rate": 4.733738758136327e-06,
      "loss": 0.0875,
      "step": 320
    },
    {
      "epoch": 3.6717984604618614,
      "grad_norm": 1.1706382243625395,
      "learning_rate": 4.090813964902889e-06,
      "loss": 0.0887,
      "step": 330
    },
    {
      "epoch": 3.7837648705388385,
      "grad_norm": 1.0559855410310333,
      "learning_rate": 3.483427711785449e-06,
      "loss": 0.0858,
      "step": 340
    },
    {
      "epoch": 3.8957312806158155,
      "grad_norm": 1.308398909677759,
      "learning_rate": 2.9152328911780027e-06,
      "loss": 0.0852,
      "step": 350
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3436280342202847,
      "learning_rate": 2.3896466935879957e-06,
      "loss": 0.0829,
      "step": 360
    },
    {
      "epoch": 4.111966410076977,
      "grad_norm": 0.7788417599252258,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.0471,
      "step": 370
    },
    {
      "epoch": 4.223932820153954,
      "grad_norm": 0.83462023849128,
      "learning_rate": 1.4786686528798878e-06,
      "loss": 0.0424,
      "step": 380
    },
    {
      "epoch": 4.335899230230931,
      "grad_norm": 0.6901746488051717,
      "learning_rate": 1.0987555388883042e-06,
      "loss": 0.0444,
      "step": 390
    },
    {
      "epoch": 4.447865640307907,
      "grad_norm": 0.7691460507261036,
      "learning_rate": 7.723755564455771e-07,
      "loss": 0.0425,
      "step": 400
    },
    {
      "epoch": 4.447865640307907,
      "eval_loss": 0.16047585010528564,
      "eval_runtime": 289.7811,
      "eval_samples_per_second": 12.461,
      "eval_steps_per_second": 3.116,
      "step": 400
    },
    {
      "epoch": 4.559832050384885,
      "grad_norm": 0.9450968952189513,
      "learning_rate": 5.014915931694253e-07,
      "loss": 0.0447,
      "step": 410
    },
    {
      "epoch": 4.671798460461861,
      "grad_norm": 0.8453038563097014,
      "learning_rate": 2.877327770883964e-07,
      "loss": 0.0428,
      "step": 420
    },
    {
      "epoch": 4.783764870538838,
      "grad_norm": 1.190161410716296,
      "learning_rate": 1.323846788742078e-07,
      "loss": 0.0402,
      "step": 430
    },
    {
      "epoch": 4.8957312806158155,
      "grad_norm": 0.833805533461852,
      "learning_rate": 3.6381580268463056e-08,
      "loss": 0.0424,
      "step": 440
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.3716018188553238,
      "learning_rate": 3.008552023242572e-10,
      "loss": 0.0407,
      "step": 450
    },
    {
      "epoch": 5.0,
      "step": 450,
      "total_flos": 1189207571693568.0,
      "train_loss": 0.2051703871621026,
      "train_runtime": 26030.3068,
      "train_samples_per_second": 13.175,
      "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
}