{
  "best_metric": 0.8485445976257324,
  "best_model_checkpoint": "saves/LLaMA3-8B/lora/train_1/checkpoint-200",
  "epoch": 0.8750341810226961,
  "eval_steps": 200,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21875854525567404,
      "grad_norm": 0.35418424010276794,
      "learning_rate": 0.00029607910744048336,
      "loss": 0.4516,
      "step": 200
    },
    {
      "epoch": 0.21875854525567404,
      "eval_loss": 0.8485445976257324,
      "eval_runtime": 2750.7214,
      "eval_samples_per_second": 17.13,
      "eval_steps_per_second": 2.141,
      "step": 200
    },
    {
      "epoch": 0.4375170905113481,
      "grad_norm": 0.5339328050613403,
      "learning_rate": 0.0002845214084081106,
      "loss": 0.3476,
      "step": 400
    },
    {
      "epoch": 0.4375170905113481,
      "eval_loss": 0.942602813243866,
      "eval_runtime": 2751.79,
      "eval_samples_per_second": 17.123,
      "eval_steps_per_second": 2.14,
      "step": 400
    },
    {
      "epoch": 0.6562756357670222,
      "grad_norm": 0.8146499991416931,
      "learning_rate": 0.0002659311228514304,
      "loss": 0.242,
      "step": 600
    },
    {
      "epoch": 0.6562756357670222,
      "eval_loss": 1.1040745973587036,
      "eval_runtime": 2753.4367,
      "eval_samples_per_second": 17.113,
      "eval_steps_per_second": 2.139,
      "step": 600
    },
    {
      "epoch": 0.8750341810226961,
      "grad_norm": 0.6436634659767151,
      "learning_rate": 0.00024128012426802252,
      "loss": 0.1079,
      "step": 800
    },
    {
      "epoch": 0.8750341810226961,
      "eval_loss": 1.2781555652618408,
      "eval_runtime": 2752.5163,
      "eval_samples_per_second": 17.119,
      "eval_steps_per_second": 2.14,
      "step": 800
    },
    {
      "epoch": 0.8750341810226961,
      "step": 800,
      "total_flos": 1.42367896045722e+18,
      "train_loss": 0.2872779941558838,
      "train_runtime": 45542.6556,
      "train_samples_per_second": 15.417,
      "train_steps_per_second": 0.06
    }
  ],
  "logging_steps": 200,
  "max_steps": 2742,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.42367896045722e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}