{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.48,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32,
      "grad_norm": 20.783666610717773,
      "learning_rate": 9.166666666666667e-05,
      "loss": 9.056,
      "step": 2
    },
    {
      "epoch": 0.64,
      "grad_norm": 8.394305229187012,
      "learning_rate": 8.333333333333334e-05,
      "loss": 7.8186,
      "step": 4
    },
    {
      "epoch": 0.96,
      "grad_norm": 118.83284759521484,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.813,
      "step": 6
    },
    {
      "epoch": 1.16,
      "grad_norm": 2.4560327529907227,
      "learning_rate": 6.666666666666667e-05,
      "loss": 4.6111,
      "step": 8
    },
    {
      "epoch": 1.48,
      "grad_norm": 1.5673390626907349,
      "learning_rate": 5.833333333333334e-05,
      "loss": 7.3,
      "step": 10
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.7503612637519836,
      "learning_rate": 5e-05,
      "loss": 7.2109,
      "step": 12
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3985859155654907,
      "learning_rate": 4.166666666666667e-05,
      "loss": 4.4783,
      "step": 14
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.75257807970047,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 7.1595,
      "step": 16
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.9470282793045044,
      "learning_rate": 2.5e-05,
      "loss": 7.0686,
      "step": 18
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.8260803818702698,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 7.1408,
      "step": 20
    },
    {
      "epoch": 3.16,
      "grad_norm": 0.8250037431716919,
      "learning_rate": 8.333333333333334e-06,
      "loss": 4.3964,
      "step": 22
    },
    {
      "epoch": 3.48,
      "grad_norm": 0.704397976398468,
      "learning_rate": 0.0,
      "loss": 7.0209,
      "step": 24
    },
    {
      "epoch": 3.48,
      "step": 24,
      "total_flos": 8125245367344.0,
      "train_loss": 6.756168842315674,
      "train_runtime": 57.8175,
      "train_samples_per_second": 6.918,
      "train_steps_per_second": 0.415
    }
  ],
  "logging_steps": 2,
  "max_steps": 24,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 8125245367344.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}