{
  "best_metric": 0.45114845037460327,
  "best_model_checkpoint": "/scratch/hlv8980/Attack_Benchmark/models/hyena/H4/origin/checkpoint-600",
  "epoch": 4.0,
  "global_step": 732,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.55,
      "learning_rate": 2.7976539589442814e-05,
      "loss": 0.5934,
      "step": 100
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.3621700879765395e-05,
      "loss": 0.4733,
      "step": 200
    },
    {
      "epoch": 1.09,
      "eval_accuracy": 0.783709787816564,
      "eval_f1": 0.7820629987273366,
      "eval_loss": 0.46442756056785583,
      "eval_matthews_correlation": 0.5666275209389648,
      "eval_precision": 0.7813471940500338,
      "eval_recall": 0.7852940728354479,
      "eval_runtime": 0.1632,
      "eval_samples_per_second": 8952.591,
      "eval_steps_per_second": 140.937,
      "step": 200
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.9266862170087976e-05,
      "loss": 0.4373,
      "step": 300
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.4868035190615837e-05,
      "loss": 0.4401,
      "step": 400
    },
    {
      "epoch": 2.19,
      "eval_accuracy": 0.7994524298425736,
      "eval_f1": 0.7970791971963782,
      "eval_loss": 0.4520949721336365,
      "eval_matthews_correlation": 0.5947143458685524,
      "eval_precision": 0.7961565345524615,
      "eval_recall": 0.7985626787843237,
      "eval_runtime": 0.1607,
      "eval_samples_per_second": 9089.528,
      "eval_steps_per_second": 143.093,
      "step": 400
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.0469208211143696e-05,
      "loss": 0.4015,
      "step": 500
    },
    {
      "epoch": 3.28,
      "learning_rate": 6.070381231671554e-06,
      "loss": 0.3802,
      "step": 600
    },
    {
      "epoch": 3.28,
      "eval_accuracy": 0.7967145790554415,
      "eval_f1": 0.794246915839901,
      "eval_loss": 0.45114845037460327,
      "eval_matthews_correlation": 0.5889689775451196,
      "eval_precision": 0.7933691695301602,
      "eval_recall": 0.7956040481913025,
      "eval_runtime": 0.1626,
      "eval_samples_per_second": 8984.579,
      "eval_steps_per_second": 141.441,
      "step": 600
    },
    {
      "epoch": 3.83,
      "learning_rate": 1.6715542521994134e-06,
      "loss": 0.3652,
      "step": 700
    },
    {
      "epoch": 4.0,
      "step": 732,
      "total_flos": 234927262531584.0,
      "train_loss": 0.4383712818062371,
      "train_runtime": 27.3916,
      "train_samples_per_second": 1705.489,
      "train_steps_per_second": 26.724
    }
  ],
  "max_steps": 732,
  "num_train_epochs": 4,
  "total_flos": 234927262531584.0,
  "trial_name": null,
  "trial_params": null
}