{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1736111111111111,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034722222222222224,
      "grad_norm": 2.5287952423095703,
      "learning_rate": 1.6379310344827587e-06,
      "loss": 2.4451,
      "step": 20
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 1.9236105680465698,
      "learning_rate": 3.362068965517242e-06,
      "loss": 2.2698,
      "step": 40
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 1.7310758829116821,
      "learning_rate": 5.086206896551724e-06,
      "loss": 2.1239,
      "step": 60
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 1.6232755184173584,
      "learning_rate": 6.810344827586207e-06,
      "loss": 1.9686,
      "step": 80
    },
    {
      "epoch": 0.1736111111111111,
      "grad_norm": 2.0284266471862793,
      "learning_rate": 8.53448275862069e-06,
      "loss": 1.8519,
      "step": 100
    }
  ],
  "logging_steps": 20,
  "max_steps": 1152,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.952829443063808e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}