{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.2239328201539537,
  "eval_steps": 100,
  "global_step": 200,
  "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
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 528944837165056.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}