{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0080645161290323,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10080645161290322,
      "eval_accuracy": 0.08417928653841922,
      "eval_loss": 5.752899646759033,
      "eval_runtime": 62.0962,
      "eval_samples_per_second": 24.993,
      "eval_steps_per_second": 0.789,
      "step": 100
    },
    {
      "epoch": 0.20161290322580644,
      "eval_accuracy": 0.08268329015442163,
      "eval_loss": 5.443298816680908,
      "eval_runtime": 62.0622,
      "eval_samples_per_second": 25.007,
      "eval_steps_per_second": 0.79,
      "step": 200
    },
    {
      "epoch": 0.3024193548387097,
      "eval_accuracy": 0.07856146899875044,
      "eval_loss": 5.327319622039795,
      "eval_runtime": 62.0439,
      "eval_samples_per_second": 25.015,
      "eval_steps_per_second": 0.79,
      "step": 300
    },
    {
      "epoch": 0.4032258064516129,
      "eval_accuracy": 0.07751066609990712,
      "eval_loss": 5.258698463439941,
      "eval_runtime": 62.0664,
      "eval_samples_per_second": 25.005,
      "eval_steps_per_second": 0.789,
      "step": 400
    },
    {
      "epoch": 0.5040322580645161,
      "grad_norm": 1.46875,
      "learning_rate": 4.1599462365591404e-05,
      "loss": 5.571,
      "step": 500
    },
    {
      "epoch": 0.5040322580645161,
      "eval_accuracy": 0.07672025056131017,
      "eval_loss": 5.229703426361084,
      "eval_runtime": 62.0987,
      "eval_samples_per_second": 24.992,
      "eval_steps_per_second": 0.789,
      "step": 500
    },
    {
      "epoch": 0.6048387096774194,
      "eval_accuracy": 0.0763650434369539,
      "eval_loss": 5.196520805358887,
      "eval_runtime": 62.0653,
      "eval_samples_per_second": 25.006,
      "eval_steps_per_second": 0.789,
      "step": 600
    },
    {
      "epoch": 0.7056451612903226,
      "eval_accuracy": 0.077187363334036,
      "eval_loss": 5.175901889801025,
      "eval_runtime": 62.0756,
      "eval_samples_per_second": 25.002,
      "eval_steps_per_second": 0.789,
      "step": 700
    },
    {
      "epoch": 0.8064516129032258,
      "eval_accuracy": 0.07545865092754048,
      "eval_loss": 5.157538890838623,
      "eval_runtime": 62.0379,
      "eval_samples_per_second": 25.017,
      "eval_steps_per_second": 0.79,
      "step": 800
    },
    {
      "epoch": 0.907258064516129,
      "eval_accuracy": 0.07520929443264239,
      "eval_loss": 5.153995037078857,
      "eval_runtime": 62.0048,
      "eval_samples_per_second": 25.03,
      "eval_steps_per_second": 0.79,
      "step": 900
    },
    {
      "epoch": 1.0080645161290323,
      "grad_norm": 1.546875,
      "learning_rate": 3.31989247311828e-05,
      "loss": 5.1997,
      "step": 1000
    },
    {
      "epoch": 1.0080645161290323,
      "eval_accuracy": 0.07693396983438175,
      "eval_loss": 5.134342670440674,
      "eval_runtime": 62.0173,
      "eval_samples_per_second": 25.025,
      "eval_steps_per_second": 0.79,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2976,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "total_flos": 3.010369166298317e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}