{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984235417761429,
  "global_step": 475,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.994534068046937e-05,
      "loss": 2.0664,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.978160173317438e-05,
      "loss": 1.2851,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9509499146870236e-05,
      "loss": 0.6483,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.913022275693372e-05,
      "loss": 0.2406,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.864543104251587e-05,
      "loss": 0.0239,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.805724387443462e-05,
      "loss": 0.0034,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.736823324551909e-05,
      "loss": 0.0016,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.6581412023939354e-05,
      "loss": 0.001,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.5700220778700504e-05,
      "loss": 0.0008,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.4728512734909844e-05,
      "loss": 0.0007,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.367053692460385e-05,
      "loss": 0.0006,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.2530919606812216e-05,
      "loss": 0.0006,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.131464403810422e-05,
      "loss": 0.0005,
      "step": 130
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.002702868207563e-05,
      "loss": 0.0005,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.867370395306068e-05,
      "loss": 0.0005,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.726058759576271e-05,
      "loss": 0.0004,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.579385880846232e-05,
      "loss": 0.0004,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.427993122295552e-05,
      "loss": 0.0004,
      "step": 180
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.0004,
      "step": 190
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.1137137178519985e-05,
      "loss": 0.0004,
      "step": 200
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.952201335830275e-05,
      "loss": 0.0003,
      "step": 210
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.788711592423966e-05,
      "loss": 0.0003,
      "step": 220
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.623959386683056e-05,
      "loss": 0.0003,
      "step": 230
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.458665138084104e-05,
      "loss": 0.0003,
      "step": 240
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.2935516363191693e-05,
      "loss": 0.0003,
      "step": 250
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.1293408807203947e-05,
      "loss": 0.0003,
      "step": 260
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.9667509231406334e-05,
      "loss": 0.0003,
      "step": 270
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.806492728095389e-05,
      "loss": 0.0003,
      "step": 280
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.6492670638958924e-05,
      "loss": 0.0003,
      "step": 290
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.495761438367577e-05,
      "loss": 0.0003,
      "step": 300
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.346647092553281e-05,
      "loss": 0.0003,
      "step": 310
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.202576065546963e-05,
      "loss": 0.0003,
      "step": 320
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.064178343292641e-05,
      "loss": 0.0003,
      "step": 330
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.320591038161574e-06,
      "loss": 0.0003,
      "step": 340
    },
    {
      "epoch": 0.74,
      "learning_rate": 8.067960709356478e-06,
      "loss": 0.0003,
      "step": 350
    },
    {
      "epoch": 0.76,
      "learning_rate": 6.889369880222776e-06,
      "loss": 0.0002,
      "step": 360
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.78997222857853e-06,
      "loss": 0.0002,
      "step": 370
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.0002,
      "step": 380
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.847618689476612e-06,
      "loss": 0.0002,
      "step": 390
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.013156219837776e-06,
      "loss": 0.0002,
      "step": 400
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.2748366237709374e-06,
      "loss": 0.0002,
      "step": 410
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.6358883850134816e-06,
      "loss": 0.0002,
      "step": 420
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.0991054616410589e-06,
      "loss": 0.0002,
      "step": 430
    },
    {
      "epoch": 0.92,
      "learning_rate": 6.668350687998565e-07,
      "loss": 0.0002,
      "step": 440
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.4096741493194197e-07,
      "loss": 0.0002,
      "step": 450
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.229274363747146e-07,
      "loss": 0.0002,
      "step": 460
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.3668566476848777e-08,
      "loss": 0.0002,
      "step": 470
    },
    {
      "epoch": 1.0,
      "step": 475,
      "total_flos": 6.826782473972613e+17,
      "train_loss": 0.09018798397804953,
      "train_runtime": 3518.059,
      "train_samples_per_second": 17.302,
      "train_steps_per_second": 0.135
    }
  ],
  "max_steps": 475,
  "num_train_epochs": 1,
  "total_flos": 6.826782473972613e+17,
  "trial_name": null,
  "trial_params": null
}