{
  "best_metric": 0.03457961231470108,
  "best_model_checkpoint": "/workspace/training_output/age-gender-vit-huge-patch14-224-in21k/checkpoint-12110",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 12110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21,
      "learning_rate": 1.9174236168455824e-05,
      "loss": 0.5738,
      "step": 500
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.8348472336911643e-05,
      "loss": 0.2735,
      "step": 1000
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.752270850536747e-05,
      "loss": 0.2086,
      "step": 1500
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6696944673823288e-05,
      "loss": 0.1848,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9798245614035088,
      "eval_loss": 0.07774332165718079,
      "eval_runtime": 301.719,
      "eval_samples_per_second": 11.335,
      "eval_steps_per_second": 1.419,
      "step": 2422
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.587118084227911e-05,
      "loss": 0.1711,
      "step": 2500
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.5045417010734931e-05,
      "loss": 0.1395,
      "step": 3000
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.4219653179190754e-05,
      "loss": 0.1458,
      "step": 3500
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3393889347646574e-05,
      "loss": 0.1443,
      "step": 4000
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.2568125516102397e-05,
      "loss": 0.1055,
      "step": 4500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9818713450292398,
      "eval_loss": 0.07078994810581207,
      "eval_runtime": 295.694,
      "eval_samples_per_second": 11.566,
      "eval_steps_per_second": 1.447,
      "step": 4844
    },
    {
      "epoch": 2.06,
      "learning_rate": 1.1742361684558218e-05,
      "loss": 0.1188,
      "step": 5000
    },
    {
      "epoch": 2.27,
      "learning_rate": 1.091659785301404e-05,
      "loss": 0.1165,
      "step": 5500
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.0090834021469859e-05,
      "loss": 0.0936,
      "step": 6000
    },
    {
      "epoch": 2.68,
      "learning_rate": 9.265070189925683e-06,
      "loss": 0.0949,
      "step": 6500
    },
    {
      "epoch": 2.89,
      "learning_rate": 8.439306358381504e-06,
      "loss": 0.0949,
      "step": 7000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.987719298245614,
      "eval_loss": 0.04404451325535774,
      "eval_runtime": 290.6652,
      "eval_samples_per_second": 11.766,
      "eval_steps_per_second": 1.472,
      "step": 7266
    },
    {
      "epoch": 3.1,
      "learning_rate": 7.6135425268373255e-06,
      "loss": 0.0905,
      "step": 7500
    },
    {
      "epoch": 3.3,
      "learning_rate": 6.787778695293147e-06,
      "loss": 0.0775,
      "step": 8000
    },
    {
      "epoch": 3.51,
      "learning_rate": 5.962014863748969e-06,
      "loss": 0.0863,
      "step": 8500
    },
    {
      "epoch": 3.72,
      "learning_rate": 5.13625103220479e-06,
      "loss": 0.0953,
      "step": 9000
    },
    {
      "epoch": 3.92,
      "learning_rate": 4.310487200660611e-06,
      "loss": 0.08,
      "step": 9500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9883040935672515,
      "eval_loss": 0.037327177822589874,
      "eval_runtime": 290.2942,
      "eval_samples_per_second": 11.781,
      "eval_steps_per_second": 1.474,
      "step": 9688
    },
    {
      "epoch": 4.13,
      "learning_rate": 3.484723369116433e-06,
      "loss": 0.0631,
      "step": 10000
    },
    {
      "epoch": 4.34,
      "learning_rate": 2.658959537572254e-06,
      "loss": 0.0806,
      "step": 10500
    },
    {
      "epoch": 4.54,
      "learning_rate": 1.8331957060280761e-06,
      "loss": 0.0599,
      "step": 11000
    },
    {
      "epoch": 4.75,
      "learning_rate": 1.0074318744838975e-06,
      "loss": 0.066,
      "step": 11500
    },
    {
      "epoch": 4.95,
      "learning_rate": 1.8166804293971927e-07,
      "loss": 0.063,
      "step": 12000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9894736842105263,
      "eval_loss": 0.03457961231470108,
      "eval_runtime": 291.7746,
      "eval_samples_per_second": 11.721,
      "eval_steps_per_second": 1.467,
      "step": 12110
    },
    {
      "epoch": 5.0,
      "step": 12110,
      "total_flos": 5.518609965691362e+19,
      "train_loss": 0.1336743047668558,
      "train_runtime": 13157.6621,
      "train_samples_per_second": 7.362,
      "train_steps_per_second": 0.92
    }
  ],
  "logging_steps": 500,
  "max_steps": 12110,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 5.518609965691362e+19,
  "trial_name": null,
  "trial_params": null
}