{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.84,
  "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": 1.016900658607483,
      "learning_rate": 0.00018333333333333334,
      "loss": 9.5861,
      "step": 2
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.7372517585754395,
      "learning_rate": 0.0001666666666666667,
      "loss": 9.2056,
      "step": 4
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.0075902938842773,
      "learning_rate": 0.00015000000000000001,
      "loss": 8.5072,
      "step": 6
    },
    {
      "epoch": 1.28,
      "grad_norm": 2.0754647254943848,
      "learning_rate": 0.00013333333333333334,
      "loss": 8.0374,
      "step": 8
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.2964591979980469,
      "learning_rate": 0.00011666666666666668,
      "loss": 7.6874,
      "step": 10
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.9893752336502075,
      "learning_rate": 0.0001,
      "loss": 7.4668,
      "step": 12
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.9852508306503296,
      "learning_rate": 8.333333333333334e-05,
      "loss": 7.4002,
      "step": 14
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.9375394582748413,
      "learning_rate": 6.666666666666667e-05,
      "loss": 7.3329,
      "step": 16
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.8562221527099609,
      "learning_rate": 5e-05,
      "loss": 7.2785,
      "step": 18
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.663221538066864,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 7.2907,
      "step": 20
    },
    {
      "epoch": 3.52,
      "grad_norm": 1.024126648902893,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 7.2383,
      "step": 22
    },
    {
      "epoch": 3.84,
      "grad_norm": 0.7755734920501709,
      "learning_rate": 0.0,
      "loss": 7.2692,
      "step": 24
    },
    {
      "epoch": 3.84,
      "step": 24,
      "total_flos": 92571267829680.0,
      "train_loss": 7.858357032140096,
      "train_runtime": 664.0524,
      "train_samples_per_second": 0.602,
      "train_steps_per_second": 0.036
    }
  ],
  "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": 92571267829680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}