{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1968,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02540650406504065,
      "grad_norm": 7.65625,
      "learning_rate": 1.2436548223350254e-05,
      "loss": 1.3736,
      "step": 50
    },
    {
      "epoch": 0.0508130081300813,
      "grad_norm": 2.609375,
      "learning_rate": 2.5126903553299492e-05,
      "loss": 0.9886,
      "step": 100
    },
    {
      "epoch": 0.07621951219512195,
      "grad_norm": 2.25,
      "learning_rate": 3.7817258883248735e-05,
      "loss": 0.7345,
      "step": 150
    },
    {
      "epoch": 0.1016260162601626,
      "grad_norm": 2.015625,
      "learning_rate": 4.994353472614343e-05,
      "loss": 0.6664,
      "step": 200
    },
    {
      "epoch": 0.12703252032520326,
      "grad_norm": 2.078125,
      "learning_rate": 4.853190287972897e-05,
      "loss": 0.6045,
      "step": 250
    },
    {
      "epoch": 0.1524390243902439,
      "grad_norm": 2.046875,
      "learning_rate": 4.7120271033314515e-05,
      "loss": 0.5898,
      "step": 300
    },
    {
      "epoch": 0.17784552845528456,
      "grad_norm": 1.6875,
      "learning_rate": 4.570863918690006e-05,
      "loss": 0.5569,
      "step": 350
    },
    {
      "epoch": 0.2032520325203252,
      "grad_norm": 1.9765625,
      "learning_rate": 4.42970073404856e-05,
      "loss": 0.5396,
      "step": 400
    },
    {
      "epoch": 0.22865853658536586,
      "grad_norm": 1.796875,
      "learning_rate": 4.288537549407115e-05,
      "loss": 0.5298,
      "step": 450
    },
    {
      "epoch": 0.2540650406504065,
      "grad_norm": 1.859375,
      "learning_rate": 4.147374364765669e-05,
      "loss": 0.5257,
      "step": 500
    },
    {
      "epoch": 0.27947154471544716,
      "grad_norm": 1.84375,
      "learning_rate": 4.006211180124224e-05,
      "loss": 0.5151,
      "step": 550
    },
    {
      "epoch": 0.3048780487804878,
      "grad_norm": 1.828125,
      "learning_rate": 3.8650479954827784e-05,
      "loss": 0.5239,
      "step": 600
    },
    {
      "epoch": 0.33028455284552843,
      "grad_norm": 1.8828125,
      "learning_rate": 3.7238848108413324e-05,
      "loss": 0.5169,
      "step": 650
    },
    {
      "epoch": 0.3556910569105691,
      "grad_norm": 1.8359375,
      "learning_rate": 3.5827216261998877e-05,
      "loss": 0.4942,
      "step": 700
    },
    {
      "epoch": 0.38109756097560976,
      "grad_norm": 1.9921875,
      "learning_rate": 3.4415584415584416e-05,
      "loss": 0.4981,
      "step": 750
    },
    {
      "epoch": 0.4065040650406504,
      "grad_norm": 1.7578125,
      "learning_rate": 3.300395256916996e-05,
      "loss": 0.4983,
      "step": 800
    },
    {
      "epoch": 0.43191056910569103,
      "grad_norm": 2.046875,
      "learning_rate": 3.159232072275551e-05,
      "loss": 0.4882,
      "step": 850
    },
    {
      "epoch": 0.4573170731707317,
      "grad_norm": 1.7890625,
      "learning_rate": 3.018068887634105e-05,
      "loss": 0.4869,
      "step": 900
    },
    {
      "epoch": 0.48272357723577236,
      "grad_norm": 1.9375,
      "learning_rate": 2.8769057029926593e-05,
      "loss": 0.4898,
      "step": 950
    },
    {
      "epoch": 0.508130081300813,
      "grad_norm": 1.7265625,
      "learning_rate": 2.7357425183512143e-05,
      "loss": 0.501,
      "step": 1000
    },
    {
      "epoch": 0.5335365853658537,
      "grad_norm": 1.7578125,
      "learning_rate": 2.5945793337097685e-05,
      "loss": 0.4843,
      "step": 1050
    },
    {
      "epoch": 0.5589430894308943,
      "grad_norm": 1.9453125,
      "learning_rate": 2.453416149068323e-05,
      "loss": 0.496,
      "step": 1100
    },
    {
      "epoch": 0.584349593495935,
      "grad_norm": 2.046875,
      "learning_rate": 2.3122529644268774e-05,
      "loss": 0.4878,
      "step": 1150
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 1.875,
      "learning_rate": 2.171089779785432e-05,
      "loss": 0.4892,
      "step": 1200
    },
    {
      "epoch": 0.6351626016260162,
      "grad_norm": 1.8203125,
      "learning_rate": 2.0299265951439866e-05,
      "loss": 0.4915,
      "step": 1250
    },
    {
      "epoch": 0.6605691056910569,
      "grad_norm": 1.890625,
      "learning_rate": 1.888763410502541e-05,
      "loss": 0.4868,
      "step": 1300
    },
    {
      "epoch": 0.6859756097560976,
      "grad_norm": 1.75,
      "learning_rate": 1.7476002258610955e-05,
      "loss": 0.4819,
      "step": 1350
    },
    {
      "epoch": 0.7113821138211383,
      "grad_norm": 1.7890625,
      "learning_rate": 1.60643704121965e-05,
      "loss": 0.486,
      "step": 1400
    },
    {
      "epoch": 0.7367886178861789,
      "grad_norm": 1.7265625,
      "learning_rate": 1.4652738565782046e-05,
      "loss": 0.4875,
      "step": 1450
    },
    {
      "epoch": 0.7621951219512195,
      "grad_norm": 1.9921875,
      "learning_rate": 1.3241106719367592e-05,
      "loss": 0.4874,
      "step": 1500
    },
    {
      "epoch": 0.7876016260162602,
      "grad_norm": 1.796875,
      "learning_rate": 1.1829474872953134e-05,
      "loss": 0.4725,
      "step": 1550
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 1.8359375,
      "learning_rate": 1.0417843026538679e-05,
      "loss": 0.4819,
      "step": 1600
    },
    {
      "epoch": 0.8384146341463414,
      "grad_norm": 1.8125,
      "learning_rate": 9.006211180124225e-06,
      "loss": 0.4808,
      "step": 1650
    },
    {
      "epoch": 0.8638211382113821,
      "grad_norm": 1.8125,
      "learning_rate": 7.594579333709768e-06,
      "loss": 0.4797,
      "step": 1700
    },
    {
      "epoch": 0.8892276422764228,
      "grad_norm": 1.71875,
      "learning_rate": 6.1829474872953135e-06,
      "loss": 0.4836,
      "step": 1750
    },
    {
      "epoch": 0.9146341463414634,
      "grad_norm": 1.8359375,
      "learning_rate": 4.771315640880859e-06,
      "loss": 0.4832,
      "step": 1800
    },
    {
      "epoch": 0.9400406504065041,
      "grad_norm": 1.859375,
      "learning_rate": 3.3596837944664035e-06,
      "loss": 0.4945,
      "step": 1850
    },
    {
      "epoch": 0.9654471544715447,
      "grad_norm": 1.6640625,
      "learning_rate": 1.948051948051948e-06,
      "loss": 0.4686,
      "step": 1900
    },
    {
      "epoch": 0.9908536585365854,
      "grad_norm": 1.796875,
      "learning_rate": 5.364201016374929e-07,
      "loss": 0.4889,
      "step": 1950
    }
  ],
  "logging_steps": 50,
  "max_steps": 1968,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}