{
  "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": 0.11547923931567391,
      "eval_loss": 5.788015365600586,
      "eval_runtime": 62.6523,
      "eval_samples_per_second": 24.772,
      "eval_steps_per_second": 0.782,
      "step": 100
    },
    {
      "epoch": 0.20161290322580644,
      "eval_accuracy": 0.13370151290913876,
      "eval_loss": 5.176546573638916,
      "eval_runtime": 62.6565,
      "eval_samples_per_second": 24.77,
      "eval_steps_per_second": 0.782,
      "step": 200
    },
    {
      "epoch": 0.3024193548387097,
      "eval_accuracy": 0.14643068888524466,
      "eval_loss": 5.0183634757995605,
      "eval_runtime": 62.7024,
      "eval_samples_per_second": 24.752,
      "eval_steps_per_second": 0.781,
      "step": 300
    },
    {
      "epoch": 0.4032258064516129,
      "eval_accuracy": 0.15548253881621393,
      "eval_loss": 4.92139196395874,
      "eval_runtime": 62.7305,
      "eval_samples_per_second": 24.741,
      "eval_steps_per_second": 0.781,
      "step": 400
    },
    {
      "epoch": 0.5040322580645161,
      "grad_norm": 1.78125,
      "learning_rate": 4.1599462365591404e-05,
      "loss": 5.3217,
      "step": 500
    },
    {
      "epoch": 0.5040322580645161,
      "eval_accuracy": 0.15949499500603373,
      "eval_loss": 4.852448463439941,
      "eval_runtime": 62.7108,
      "eval_samples_per_second": 24.749,
      "eval_steps_per_second": 0.781,
      "step": 500
    },
    {
      "epoch": 0.6048387096774194,
      "eval_accuracy": 0.16651773824214028,
      "eval_loss": 4.782216548919678,
      "eval_runtime": 62.7083,
      "eval_samples_per_second": 24.75,
      "eval_steps_per_second": 0.781,
      "step": 600
    },
    {
      "epoch": 0.7056451612903226,
      "eval_accuracy": 0.17252706374876267,
      "eval_loss": 4.736791133880615,
      "eval_runtime": 62.7624,
      "eval_samples_per_second": 24.728,
      "eval_steps_per_second": 0.781,
      "step": 700
    },
    {
      "epoch": 0.8064516129032258,
      "eval_accuracy": 0.17507433383625723,
      "eval_loss": 4.693298816680908,
      "eval_runtime": 62.7389,
      "eval_samples_per_second": 24.737,
      "eval_steps_per_second": 0.781,
      "step": 800
    },
    {
      "epoch": 0.907258064516129,
      "eval_accuracy": 0.17554612653604237,
      "eval_loss": 4.677834987640381,
      "eval_runtime": 62.7903,
      "eval_samples_per_second": 24.717,
      "eval_steps_per_second": 0.78,
      "step": 900
    },
    {
      "epoch": 1.0080645161290323,
      "grad_norm": 2.21875,
      "learning_rate": 3.31989247311828e-05,
      "loss": 4.7636,
      "step": 1000
    },
    {
      "epoch": 1.0080645161290323,
      "eval_accuracy": 0.17953083885533383,
      "eval_loss": 4.65625,
      "eval_runtime": 62.7838,
      "eval_samples_per_second": 24.72,
      "eval_steps_per_second": 0.78,
      "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
}