{
  "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": 0.0003911111111111111,
      "loss": 0.0127,
      "step": 10
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003822222222222223,
      "loss": 0.1644,
      "step": 20
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003733333333333334,
      "loss": 0.2691,
      "step": 30
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00036444444444444447,
      "loss": 0.2196,
      "step": 40
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00035555555555555557,
      "loss": 0.1119,
      "step": 50
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00034666666666666667,
      "loss": 0.1708,
      "step": 60
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00033777777777777777,
      "loss": 0.2104,
      "step": 70
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00032888888888888887,
      "loss": 0.1343,
      "step": 80
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00032,
      "loss": 0.1185,
      "step": 90
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003111111111111111,
      "loss": 0.1059,
      "step": 100
    },
    {
      "epoch": 1.11,
      "eval_accuracy": 0.8546296296296296,
      "eval_loss": 0.693325936794281,
      "eval_runtime": 12.9043,
      "eval_samples_per_second": 83.693,
      "eval_steps_per_second": 10.462,
      "step": 100
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0003022222222222222,
      "loss": 0.0944,
      "step": 110
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002933333333333333,
      "loss": 0.1009,
      "step": 120
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002844444444444445,
      "loss": 0.0579,
      "step": 130
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002755555555555556,
      "loss": 0.093,
      "step": 140
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002666666666666667,
      "loss": 0.054,
      "step": 150
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00025777777777777783,
      "loss": 0.0366,
      "step": 160
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002488888888888889,
      "loss": 0.027,
      "step": 170
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00024,
      "loss": 0.0369,
      "step": 180
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002311111111111111,
      "loss": 0.0354,
      "step": 190
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00022222222222222223,
      "loss": 0.02,
      "step": 200
    },
    {
      "epoch": 2.22,
      "eval_accuracy": 0.875,
      "eval_loss": 0.656458854675293,
      "eval_runtime": 12.7588,
      "eval_samples_per_second": 84.647,
      "eval_steps_per_second": 10.581,
      "step": 200
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00021333333333333333,
      "loss": 0.0236,
      "step": 210
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00020444444444444443,
      "loss": 0.032,
      "step": 220
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00019555555555555556,
      "loss": 0.0369,
      "step": 230
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0001866666666666667,
      "loss": 0.0339,
      "step": 240
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.0207,
      "step": 250
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00016888888888888889,
      "loss": 0.0291,
      "step": 260
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00016,
      "loss": 0.0237,
      "step": 270
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0001511111111111111,
      "loss": 0.0023,
      "step": 280
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.00014222222222222224,
      "loss": 0.0072,
      "step": 290
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.001,
      "step": 300
    },
    {
      "epoch": 3.33,
      "eval_accuracy": 0.8888888888888888,
      "eval_loss": 0.5975281000137329,
      "eval_runtime": 12.7539,
      "eval_samples_per_second": 84.68,
      "eval_steps_per_second": 10.585,
      "step": 300
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.00012444444444444444,
      "loss": 0.0209,
      "step": 310
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.00011555555555555555,
      "loss": 0.0208,
      "step": 320
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.00010666666666666667,
      "loss": 0.0064,
      "step": 330
    },
    {
      "epoch": 3.78,
      "learning_rate": 9.777777777777778e-05,
      "loss": 0.0011,
      "step": 340
    },
    {
      "epoch": 3.89,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.004,
      "step": 350
    },
    {
      "epoch": 4.0,
      "learning_rate": 8e-05,
      "loss": 0.0097,
      "step": 360
    },
    {
      "epoch": 4.11,
      "learning_rate": 7.111111111111112e-05,
      "loss": 0.0004,
      "step": 370
    },
    {
      "epoch": 4.22,
      "learning_rate": 6.222222222222222e-05,
      "loss": 0.0015,
      "step": 380
    },
    {
      "epoch": 4.33,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.0004,
      "step": 390
    },
    {
      "epoch": 4.44,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.0027,
      "step": 400
    },
    {
      "epoch": 4.44,
      "eval_accuracy": 0.9064814814814814,
      "eval_loss": 0.5585721731185913,
      "eval_runtime": 13.4691,
      "eval_samples_per_second": 80.184,
      "eval_steps_per_second": 10.023,
      "step": 400
    },
    {
      "epoch": 4.56,
      "learning_rate": 3.555555555555556e-05,
      "loss": 0.0003,
      "step": 410
    },
    {
      "epoch": 4.67,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.0018,
      "step": 420
    },
    {
      "epoch": 4.78,
      "learning_rate": 1.777777777777778e-05,
      "loss": 0.0054,
      "step": 430
    },
    {
      "epoch": 4.89,
      "learning_rate": 8.88888888888889e-06,
      "loss": 0.0057,
      "step": 440
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.0004,
      "step": 450
    },
    {
      "epoch": 5.0,
      "step": 450,
      "total_flos": 1.6739319895474176e+18,
      "train_loss": 0.0525758553068671,
      "train_runtime": 438.9135,
      "train_samples_per_second": 49.212,
      "train_steps_per_second": 1.025
    }
  ],
  "logging_steps": 10,
  "max_steps": 450,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "total_flos": 1.6739319895474176e+18,
  "trial_name": null,
  "trial_params": null
}