{
  "best_metric": 0.4878290891647339,
  "best_model_checkpoint": "Meta-Llama-3.1-8B-Instruct new\\checkpoint-100",
  "epoch": 0.28776978417266186,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 0.11506436765193939,
      "learning_rate": 0.0002,
      "loss": 0.7362,
      "step": 100
    },
    {
      "epoch": 0.28776978417266186,
      "eval_loss": 0.4878290891647339,
      "eval_runtime": 1191.2739,
      "eval_samples_per_second": 0.176,
      "eval_steps_per_second": 0.023,
      "step": 100
    }
  ],
  "logging_steps": 100,
  "max_steps": 1041,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.45186623750144e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}