{
  "best_metric": 4.821878974325955e-05,
  "best_model_checkpoint": "data/models/organism/final/checkpoint-4647",
  "epoch": 2.0,
  "global_step": 9294,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 9.679644932214333e-06,
      "loss": 0.0432,
      "step": 500
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.129289864428664e-06,
      "loss": 0.0176,
      "step": 1000
    },
    {
      "epoch": 0.32,
      "learning_rate": 8.578934796642996e-06,
      "loss": 0.0151,
      "step": 1500
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.028579728857327e-06,
      "loss": 0.0124,
      "step": 2000
    },
    {
      "epoch": 0.54,
      "learning_rate": 7.478224661071659e-06,
      "loss": 0.0147,
      "step": 2500
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.927869593285991e-06,
      "loss": 0.0116,
      "step": 3000
    },
    {
      "epoch": 0.75,
      "learning_rate": 6.377514525500323e-06,
      "loss": 0.0136,
      "step": 3500
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.827159457714655e-06,
      "loss": 0.0118,
      "step": 4000
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.276804389928987e-06,
      "loss": 0.0099,
      "step": 4500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 1.0,
      "eval_f1": 0.0,
      "eval_loss": 4.821878974325955e-05,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.532,
      "eval_samples_per_second": 0.653,
      "eval_steps_per_second": 0.653,
      "step": 4647
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.726449322143318e-06,
      "loss": 0.0101,
      "step": 5000
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.17609425435765e-06,
      "loss": 0.0077,
      "step": 5500
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.6257391865719818e-06,
      "loss": 0.0064,
      "step": 6000
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.075384118786314e-06,
      "loss": 0.0059,
      "step": 6500
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.525029051000646e-06,
      "loss": 0.0077,
      "step": 7000
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.9746739832149775e-06,
      "loss": 0.0069,
      "step": 7500
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.4243189154293093e-06,
      "loss": 0.0065,
      "step": 8000
    },
    {
      "epoch": 1.83,
      "learning_rate": 8.73963847643641e-07,
      "loss": 0.0075,
      "step": 8500
    },
    {
      "epoch": 1.94,
      "learning_rate": 3.236087798579729e-07,
      "loss": 0.0085,
      "step": 9000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 1.0,
      "eval_f1": 0.0,
      "eval_loss": 5.289753607939929e-05,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.4357,
      "eval_samples_per_second": 0.697,
      "eval_steps_per_second": 0.697,
      "step": 9294
    }
  ],
  "max_steps": 9294,
  "num_train_epochs": 2,
  "total_flos": 3.885361121605018e+16,
  "trial_name": null,
  "trial_params": null
}