{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 2.0762882232666016,
      "learning_rate": 0.0001952,
      "loss": 2.921174430847168,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.494314432144165,
      "learning_rate": 0.00018986666666666668,
      "loss": 0.8493177413940429,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.8940829634666443,
      "learning_rate": 0.00018453333333333334,
      "loss": 0.29891698360443114,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.6761481761932373,
      "learning_rate": 0.00017920000000000002,
      "loss": 0.24503071308135987,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8483666181564331,
      "learning_rate": 0.00017386666666666667,
      "loss": 0.23532724380493164,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5320708751678467,
      "learning_rate": 0.00016853333333333336,
      "loss": 0.2238381624221802,
      "step": 60
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.544127345085144,
      "learning_rate": 0.0001632,
      "loss": 0.1873299241065979,
      "step": 70
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3120693266391754,
      "learning_rate": 0.00015786666666666666,
      "loss": 0.1958820104598999,
      "step": 80
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.4256227910518646,
      "learning_rate": 0.00015253333333333335,
      "loss": 0.17537823915481568,
      "step": 90
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.49074727296829224,
      "learning_rate": 0.0001472,
      "loss": 0.16229361295700073,
      "step": 100
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.3502003252506256,
      "learning_rate": 0.00014186666666666668,
      "loss": 0.17495042085647583,
      "step": 110
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.4211275279521942,
      "learning_rate": 0.00013653333333333334,
      "loss": 0.15660312175750732,
      "step": 120
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.9018304944038391,
      "learning_rate": 0.00013120000000000002,
      "loss": 0.16269407272338868,
      "step": 130
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.3671622574329376,
      "learning_rate": 0.00012586666666666667,
      "loss": 0.14469131231307983,
      "step": 140
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.3512709438800812,
      "learning_rate": 0.00012053333333333334,
      "loss": 0.15323718786239623,
      "step": 150
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.2616237699985504,
      "learning_rate": 0.0001152,
      "loss": 0.14424238204956055,
      "step": 160
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.2642329931259155,
      "learning_rate": 0.00010986666666666668,
      "loss": 0.14813388586044313,
      "step": 170
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.4799720346927643,
      "learning_rate": 0.00010453333333333333,
      "loss": 0.1565908670425415,
      "step": 180
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.341293066740036,
      "learning_rate": 9.92e-05,
      "loss": 0.14870073795318603,
      "step": 190
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.44224610924720764,
      "learning_rate": 9.386666666666667e-05,
      "loss": 0.14998830556869508,
      "step": 200
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.24533942341804504,
      "learning_rate": 8.853333333333333e-05,
      "loss": 0.14851131439208984,
      "step": 210
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.24691356718540192,
      "learning_rate": 8.32e-05,
      "loss": 0.1555757999420166,
      "step": 220
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.27265557646751404,
      "learning_rate": 7.786666666666667e-05,
      "loss": 0.14096293449401856,
      "step": 230
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.33905982971191406,
      "learning_rate": 7.253333333333334e-05,
      "loss": 0.15663959980010986,
      "step": 240
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.32767701148986816,
      "learning_rate": 6.720000000000001e-05,
      "loss": 0.15287188291549683,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.149061361081088e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}