{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.37114015221595764,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.5820552825927734,
      "step": 5
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.28937986493110657,
      "learning_rate": 0.00019948693233918952,
      "loss": 1.6350902557373046,
      "step": 10
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.3877090811729431,
      "learning_rate": 0.00019377521321470805,
      "loss": 1.5212254524230957,
      "step": 15
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3809593915939331,
      "learning_rate": 0.00018207634412072764,
      "loss": 1.522021198272705,
      "step": 20
    },
    {
      "epoch": 1.0888888888888888,
      "grad_norm": 0.5326193571090698,
      "learning_rate": 0.00016513724827222227,
      "loss": 1.592656707763672,
      "step": 25
    },
    {
      "epoch": 1.3111111111111111,
      "grad_norm": 0.4104065001010895,
      "learning_rate": 0.00014403941515576344,
      "loss": 1.438854694366455,
      "step": 30
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 0.3773227632045746,
      "learning_rate": 0.00012012985200886602,
      "loss": 1.4366189956665039,
      "step": 35
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.41420406103134155,
      "learning_rate": 9.493508311612874e-05,
      "loss": 1.4379773139953613,
      "step": 40
    },
    {
      "epoch": 1.9777777777777779,
      "grad_norm": 0.368633508682251,
      "learning_rate": 7.006368770266421e-05,
      "loss": 1.401620101928711,
      "step": 45
    },
    {
      "epoch": 2.1777777777777776,
      "grad_norm": 0.512729287147522,
      "learning_rate": 4.710359896730379e-05,
      "loss": 1.3366747856140138,
      "step": 50
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.43342044949531555,
      "learning_rate": 2.7520721277088024e-05,
      "loss": 1.4051382064819335,
      "step": 55
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.41076287627220154,
      "learning_rate": 1.2565338385541792e-05,
      "loss": 1.4281869888305665,
      "step": 60
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.3187236189842224,
      "learning_rate": 3.1922881133795825e-06,
      "loss": 1.3669097900390625,
      "step": 65
    }
  ],
  "logging_steps": 5,
  "max_steps": 69,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2194604485263360.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}