{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.039619651347068144,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 3.846153846153847e-06,
      "loss": 2.7796,
      "theoretical_loss": 3.3518567762894107,
      "tokens_seen": 2969305088
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.846153846153846e-05,
      "loss": 2.4642,
      "theoretical_loss": 3.3517550749686795,
      "tokens_seen": 2970484736
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.692307692307693e-05,
      "loss": 1.9063,
      "theoretical_loss": 3.351642134115535,
      "tokens_seen": 2971795456
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.983987189751803e-05,
      "loss": 1.4437,
      "theoretical_loss": 3.351529257004948,
      "tokens_seen": 2973106176
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.943955164131305e-05,
      "loss": 1.273,
      "theoretical_loss": 3.3514164435728655,
      "tokens_seen": 2974416896
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.90392313851081e-05,
      "loss": 1.2074,
      "theoretical_loss": 3.3513036937553267,
      "tokens_seen": 2975727616
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.863891112890312e-05,
      "loss": 1.2079,
      "theoretical_loss": 3.3511910074884628,
      "tokens_seen": 2977038336
    },
    {
      "epoch": 0.02,
      "objective/train/docs_used": 997783,
      "objective/train/instantaneous_batch_size": 8,
      "objective/train/instantaneous_microbatch_size": 8192,
      "objective/train/original_loss": 0.9412798285484314,
      "objective/train/theoretical_loss": 3.3511628458440637,
      "objective/train/tokens_used": 28650976,
      "theoretical_loss": 3.3511628458440637,
      "tokens_seen": 2977366016
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.823859087269817e-05,
      "loss": 1.2032,
      "theoretical_loss": 3.3510783847084977,
      "tokens_seen": 2978349056
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.78382706164932e-05,
      "loss": 1.2178,
      "theoretical_loss": 3.350965825351748,
      "tokens_seen": 2979659776
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.743795036028824e-05,
      "loss": 1.189,
      "theoretical_loss": 3.3508533293546208,
      "tokens_seen": 2980970496
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.703763010408326e-05,
      "loss": 1.2086,
      "theoretical_loss": 3.3507408966536154,
      "tokens_seen": 2982281216
    }
  ],
  "max_steps": 2524,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 6689076019200000.0,
  "trial_name": null,
  "trial_params": null
}