{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 100,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 9.777777777777778e-05,
      "loss": 0.0016,
      "step": 10
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.555555555555557e-05,
      "loss": 0.0002,
      "step": 20
    },
    {
      "epoch": 0.33,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.0176,
      "step": 30
    },
    {
      "epoch": 0.44,
      "learning_rate": 9.111111111111112e-05,
      "loss": 0.0183,
      "step": 40
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.0073,
      "step": 50
    },
    {
      "epoch": 0.67,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.0016,
      "step": 60
    },
    {
      "epoch": 0.78,
      "learning_rate": 8.444444444444444e-05,
      "loss": 0.0278,
      "step": 70
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.222222222222222e-05,
      "loss": 0.0308,
      "step": 80
    },
    {
      "epoch": 1.0,
      "learning_rate": 8e-05,
      "loss": 0.0035,
      "step": 90
    },
    {
      "epoch": 1.11,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.0006,
      "step": 100
    },
    {
      "epoch": 1.11,
      "eval_accuracy": 0.9,
      "eval_loss": 0.6743502020835876,
      "eval_runtime": 12.9158,
      "eval_samples_per_second": 83.618,
      "eval_steps_per_second": 10.452,
      "step": 100
    },
    {
      "epoch": 1.22,
      "learning_rate": 7.555555555555556e-05,
      "loss": 0.0023,
      "step": 110
    },
    {
      "epoch": 1.33,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.0131,
      "step": 120
    },
    {
      "epoch": 1.44,
      "learning_rate": 7.111111111111112e-05,
      "loss": 0.0032,
      "step": 130
    },
    {
      "epoch": 1.56,
      "learning_rate": 6.88888888888889e-05,
      "loss": 0.0019,
      "step": 140
    },
    {
      "epoch": 1.67,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0017,
      "step": 150
    },
    {
      "epoch": 1.78,
      "learning_rate": 6.444444444444446e-05,
      "loss": 0.0151,
      "step": 160
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.222222222222222e-05,
      "loss": 0.0088,
      "step": 170
    },
    {
      "epoch": 2.0,
      "learning_rate": 6e-05,
      "loss": 0.005,
      "step": 180
    },
    {
      "epoch": 2.11,
      "learning_rate": 5.7777777777777776e-05,
      "loss": 0.0012,
      "step": 190
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.0048,
      "step": 200
    },
    {
      "epoch": 2.22,
      "eval_accuracy": 0.899074074074074,
      "eval_loss": 0.660332202911377,
      "eval_runtime": 12.4492,
      "eval_samples_per_second": 86.753,
      "eval_steps_per_second": 10.844,
      "step": 200
    },
    {
      "epoch": 2.33,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.0008,
      "step": 210
    },
    {
      "epoch": 2.44,
      "learning_rate": 5.111111111111111e-05,
      "loss": 0.0017,
      "step": 220
    },
    {
      "epoch": 2.56,
      "learning_rate": 4.888888888888889e-05,
      "loss": 0.0031,
      "step": 230
    },
    {
      "epoch": 2.67,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.0044,
      "step": 240
    },
    {
      "epoch": 2.78,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.0041,
      "step": 250
    },
    {
      "epoch": 2.89,
      "learning_rate": 4.222222222222222e-05,
      "loss": 0.0015,
      "step": 260
    },
    {
      "epoch": 3.0,
      "learning_rate": 4e-05,
      "loss": 0.0256,
      "step": 270
    },
    {
      "epoch": 3.11,
      "learning_rate": 3.777777777777778e-05,
      "loss": 0.0002,
      "step": 280
    },
    {
      "epoch": 3.22,
      "learning_rate": 3.555555555555556e-05,
      "loss": 0.0002,
      "step": 290
    },
    {
      "epoch": 3.33,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0015,
      "step": 300
    },
    {
      "epoch": 3.33,
      "eval_accuracy": 0.9,
      "eval_loss": 0.6311585307121277,
      "eval_runtime": 13.0559,
      "eval_samples_per_second": 82.722,
      "eval_steps_per_second": 10.34,
      "step": 300
    },
    {
      "epoch": 3.44,
      "learning_rate": 3.111111111111111e-05,
      "loss": 0.0036,
      "step": 310
    },
    {
      "epoch": 3.56,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 0.0012,
      "step": 320
    },
    {
      "epoch": 3.67,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.0136,
      "step": 330
    },
    {
      "epoch": 3.78,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 0.0002,
      "step": 340
    },
    {
      "epoch": 3.89,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0045,
      "step": 350
    },
    {
      "epoch": 4.0,
      "learning_rate": 2e-05,
      "loss": 0.0002,
      "step": 360
    },
    {
      "epoch": 4.11,
      "learning_rate": 1.777777777777778e-05,
      "loss": 0.0002,
      "step": 370
    },
    {
      "epoch": 4.22,
      "learning_rate": 1.5555555555555555e-05,
      "loss": 0.0018,
      "step": 380
    },
    {
      "epoch": 4.33,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0002,
      "step": 390
    },
    {
      "epoch": 4.44,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0015,
      "step": 400
    },
    {
      "epoch": 4.44,
      "eval_accuracy": 0.9111111111111111,
      "eval_loss": 0.582186758518219,
      "eval_runtime": 12.1335,
      "eval_samples_per_second": 89.01,
      "eval_steps_per_second": 11.126,
      "step": 400
    },
    {
      "epoch": 4.56,
      "learning_rate": 8.88888888888889e-06,
      "loss": 0.0002,
      "step": 410
    },
    {
      "epoch": 4.67,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.0023,
      "step": 420
    },
    {
      "epoch": 4.78,
      "learning_rate": 4.444444444444445e-06,
      "loss": 0.0042,
      "step": 430
    },
    {
      "epoch": 4.89,
      "learning_rate": 2.2222222222222225e-06,
      "loss": 0.0031,
      "step": 440
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "step": 450
    },
    {
      "epoch": 5.0,
      "step": 450,
      "total_flos": 1.6739319895474176e+18,
      "train_loss": 0.005469957473170427,
      "train_runtime": 432.0933,
      "train_samples_per_second": 49.989,
      "train_steps_per_second": 1.041
    }
  ],
  "logging_steps": 10,
  "max_steps": 450,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "total_flos": 1.6739319895474176e+18,
  "trial_name": null,
  "trial_params": null
}