{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00041821755677303336,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.364351135460666e-05,
      "grad_norm": 67.74922943115234,
      "learning_rate": 1e-05,
      "loss": 21.6227,
      "step": 1
    },
    {
      "epoch": 8.364351135460666e-05,
      "eval_loss": 1.58735990524292,
      "eval_runtime": 475.0782,
      "eval_samples_per_second": 42.385,
      "eval_steps_per_second": 21.192,
      "step": 1
    },
    {
      "epoch": 0.00016728702270921332,
      "grad_norm": 82.74652099609375,
      "learning_rate": 2e-05,
      "loss": 24.4208,
      "step": 2
    },
    {
      "epoch": 0.00016728702270921332,
      "eval_loss": 1.5150890350341797,
      "eval_runtime": 492.5557,
      "eval_samples_per_second": 40.881,
      "eval_steps_per_second": 20.44,
      "step": 2
    },
    {
      "epoch": 0.00025093053406382,
      "grad_norm": 66.69440460205078,
      "learning_rate": 3e-05,
      "loss": 20.913,
      "step": 3
    },
    {
      "epoch": 0.00033457404541842664,
      "grad_norm": 68.26770782470703,
      "learning_rate": 4e-05,
      "loss": 21.4769,
      "step": 4
    },
    {
      "epoch": 0.00033457404541842664,
      "eval_loss": 1.3836952447891235,
      "eval_runtime": 460.7496,
      "eval_samples_per_second": 43.703,
      "eval_steps_per_second": 21.851,
      "step": 4
    },
    {
      "epoch": 0.00041821755677303336,
      "grad_norm": 45.948394775390625,
      "learning_rate": 5e-05,
      "loss": 19.244,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3680606550491136.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}