{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6587844845467745,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.41485169052063886,
      "grad_norm": 2.554873466491699,
      "learning_rate": 8.619640387275243e-05,
      "loss": 25.7277,
      "step": 500
    },
    {
      "epoch": 0.8297033810412777,
      "grad_norm": 2.1250674724578857,
      "learning_rate": 7.236514522821577e-05,
      "loss": 2.6779,
      "step": 1000
    },
    {
      "epoch": 1.2439327940261355,
      "grad_norm": 1.5062010288238525,
      "learning_rate": 5.853388658367912e-05,
      "loss": 2.2977,
      "step": 1500
    },
    {
      "epoch": 1.6587844845467745,
      "grad_norm": 1.5647008419036865,
      "learning_rate": 4.470262793914247e-05,
      "loss": 0.999,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 3615,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0941393389776457e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}