{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 876,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.5365314483642578,
      "learning_rate": 3.864155251141553e-05,
      "loss": 1.1356,
      "step": 200
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.5107465982437134,
      "learning_rate": 2.7226027397260272e-05,
      "loss": 1.1332,
      "step": 400
    },
    {
      "epoch": 1.3702857142857143,
      "grad_norm": 0.4138275682926178,
      "learning_rate": 1.5810502283105024e-05,
      "loss": 1.0953,
      "step": 600
    },
    {
      "epoch": 1.8274285714285714,
      "grad_norm": 0.4228627681732178,
      "learning_rate": 4.394977168949772e-06,
      "loss": 1.0703,
      "step": 800
    }
  ],
  "logging_steps": 200,
  "max_steps": 876,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 6423185018880000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}