{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 5.838228702545166,
      "learning_rate": 0.0002,
      "loss": 38.8184,
      "step": 1
    },
    {
      "epoch": 0.8,
      "grad_norm": 5.924264430999756,
      "learning_rate": 0.00018333333333333334,
      "loss": 38.1258,
      "step": 2
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.9051806926727295,
      "learning_rate": 0.0001666666666666667,
      "loss": 18.4134,
      "step": 3
    },
    {
      "epoch": 1.4,
      "grad_norm": 9.924675941467285,
      "learning_rate": 0.00015000000000000001,
      "loss": 35.2622,
      "step": 4
    },
    {
      "epoch": 1.8,
      "grad_norm": 9.904117584228516,
      "learning_rate": 0.00013333333333333334,
      "loss": 33.9871,
      "step": 5
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.282042980194092,
      "learning_rate": 0.00011666666666666668,
      "loss": 16.3779,
      "step": 6
    },
    {
      "epoch": 2.4,
      "grad_norm": 9.635658264160156,
      "learning_rate": 0.0001,
      "loss": 31.4271,
      "step": 7
    },
    {
      "epoch": 2.8,
      "grad_norm": 9.389054298400879,
      "learning_rate": 8.333333333333334e-05,
      "loss": 30.4021,
      "step": 8
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.5485405921936035,
      "learning_rate": 6.666666666666667e-05,
      "loss": 14.9654,
      "step": 9
    },
    {
      "epoch": 3.4,
      "grad_norm": 8.596323013305664,
      "learning_rate": 5e-05,
      "loss": 28.9345,
      "step": 10
    },
    {
      "epoch": 3.8,
      "grad_norm": 9.886870384216309,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 29.2833,
      "step": 11
    },
    {
      "epoch": 4.0,
      "grad_norm": 4.780460834503174,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 14.2209,
      "step": 12
    },
    {
      "epoch": 4.0,
      "step": 12,
      "total_flos": 17701968222720.0,
      "train_loss": 27.51817512512207,
      "train_runtime": 296.8319,
      "train_samples_per_second": 0.539,
      "train_steps_per_second": 0.04
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 12,
  "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": 17701968222720.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}