{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 43750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.4176286458969116,
      "learning_rate": 1.600137142857143e-05,
      "loss": 2.6585,
      "step": 8750
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.657306671142578,
      "eval_runtime": 127.3226,
      "eval_samples_per_second": 235.622,
      "eval_steps_per_second": 29.453,
      "step": 8750
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.0878936052322388,
      "learning_rate": 1.2002285714285716e-05,
      "loss": 2.6535,
      "step": 17500
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.653296947479248,
      "eval_runtime": 139.0848,
      "eval_samples_per_second": 215.696,
      "eval_steps_per_second": 26.962,
      "step": 17500
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0684641599655151,
      "learning_rate": 8.00457142857143e-06,
      "loss": 2.6505,
      "step": 26250
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.653186798095703,
      "eval_runtime": 133.9609,
      "eval_samples_per_second": 223.946,
      "eval_steps_per_second": 27.993,
      "step": 26250
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.061199188232422,
      "learning_rate": 4.0064e-06,
      "loss": 2.6439,
      "step": 35000
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.6521787643432617,
      "eval_runtime": 131.624,
      "eval_samples_per_second": 227.922,
      "eval_steps_per_second": 28.49,
      "step": 35000
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.321831226348877,
      "learning_rate": 7.3142857142857155e-09,
      "loss": 2.6401,
      "step": 43750
    }
  ],
  "logging_steps": 8750,
  "max_steps": 43750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 5333657398730976.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}