{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6246719160104988,
  "eval_steps": 250,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.66,
      "learning_rate": 9.78477690288714e-06,
      "loss": 0.1544,
      "step": 250
    },
    {
      "epoch": 0.66,
      "eval_accuracy": 0.999459669335349,
      "eval_f1": 0.9975467196003112,
      "eval_loss": 0.0030309667345136404,
      "eval_precision": 0.9982040980913408,
      "eval_recall": 0.9968902063873818,
      "eval_runtime": 60.0322,
      "eval_samples_per_second": 86.853,
      "eval_steps_per_second": 2.715,
      "step": 250
    },
    {
      "epoch": 1.31,
      "learning_rate": 9.566054243219597e-06,
      "loss": 0.0031,
      "step": 500
    },
    {
      "epoch": 1.31,
      "eval_accuracy": 0.9995871243828395,
      "eval_f1": 0.9981561132582728,
      "eval_loss": 0.0018471144139766693,
      "eval_precision": 0.9981616961615619,
      "eval_recall": 0.9981505304174357,
      "eval_runtime": 60.151,
      "eval_samples_per_second": 86.682,
      "eval_steps_per_second": 2.71,
      "step": 500
    },
    {
      "epoch": 1.97,
      "learning_rate": 9.347331583552057e-06,
      "loss": 0.0018,
      "step": 750
    },
    {
      "epoch": 1.97,
      "eval_accuracy": 0.9996776715980452,
      "eval_f1": 0.9985476091483844,
      "eval_loss": 0.0015591623960062861,
      "eval_precision": 0.9985718121205793,
      "eval_recall": 0.9985234073494044,
      "eval_runtime": 60.3172,
      "eval_samples_per_second": 86.443,
      "eval_steps_per_second": 2.702,
      "step": 750
    },
    {
      "epoch": 2.62,
      "learning_rate": 9.128608923884515e-06,
      "loss": 0.0013,
      "step": 1000
    },
    {
      "epoch": 2.62,
      "eval_accuracy": 0.9997411530695752,
      "eval_f1": 0.9989185399543549,
      "eval_loss": 0.0013504341477528214,
      "eval_precision": 0.99902658068751,
      "eval_recall": 0.9988105225870202,
      "eval_runtime": 60.0207,
      "eval_samples_per_second": 86.87,
      "eval_steps_per_second": 2.716,
      "step": 1000
    }
  ],
  "logging_steps": 250,
  "max_steps": 11430,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 250,
  "total_flos": 6990933228122340.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}