{
  "best_metric": 0.024446744471788406,
  "best_model_checkpoint": "/workspace/training_output/age-gender/checkpoint-9688",
  "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": 0.5499,
      "step": 500
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.8348472336911643e-05,
      "loss": 0.257,
      "step": 1000
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.752270850536747e-05,
      "loss": 0.1934,
      "step": 1500
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6696944673823288e-05,
      "loss": 0.167,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9780701754385965,
      "eval_loss": 0.07958254218101501,
      "eval_runtime": 242.567,
      "eval_samples_per_second": 14.099,
      "eval_steps_per_second": 1.764,
      "step": 2422
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.587118084227911e-05,
      "loss": 0.1596,
      "step": 2500
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.5045417010734931e-05,
      "loss": 0.1339,
      "step": 3000
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.4219653179190754e-05,
      "loss": 0.1357,
      "step": 3500
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3393889347646574e-05,
      "loss": 0.1377,
      "step": 4000
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.2568125516102397e-05,
      "loss": 0.1169,
      "step": 4500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9883040935672515,
      "eval_loss": 0.047995880246162415,
      "eval_runtime": 232.2727,
      "eval_samples_per_second": 14.724,
      "eval_steps_per_second": 1.843,
      "step": 4844
    },
    {
      "epoch": 2.06,
      "learning_rate": 1.1742361684558218e-05,
      "loss": 0.116,
      "step": 5000
    },
    {
      "epoch": 2.27,
      "learning_rate": 1.091659785301404e-05,
      "loss": 0.1116,
      "step": 5500
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.0090834021469859e-05,
      "loss": 0.0921,
      "step": 6000
    },
    {
      "epoch": 2.68,
      "learning_rate": 9.265070189925683e-06,
      "loss": 0.0897,
      "step": 6500
    },
    {
      "epoch": 2.89,
      "learning_rate": 8.439306358381504e-06,
      "loss": 0.0993,
      "step": 7000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9935672514619883,
      "eval_loss": 0.026438480243086815,
      "eval_runtime": 245.5743,
      "eval_samples_per_second": 13.927,
      "eval_steps_per_second": 1.743,
      "step": 7266
    },
    {
      "epoch": 3.1,
      "learning_rate": 7.6135425268373255e-06,
      "loss": 0.0728,
      "step": 7500
    },
    {
      "epoch": 3.3,
      "learning_rate": 6.787778695293147e-06,
      "loss": 0.083,
      "step": 8000
    },
    {
      "epoch": 3.51,
      "learning_rate": 5.962014863748969e-06,
      "loss": 0.0737,
      "step": 8500
    },
    {
      "epoch": 3.72,
      "learning_rate": 5.13625103220479e-06,
      "loss": 0.0941,
      "step": 9000
    },
    {
      "epoch": 3.92,
      "learning_rate": 4.310487200660611e-06,
      "loss": 0.0738,
      "step": 9500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9941520467836257,
      "eval_loss": 0.024446744471788406,
      "eval_runtime": 255.6848,
      "eval_samples_per_second": 13.376,
      "eval_steps_per_second": 1.674,
      "step": 9688
    },
    {
      "epoch": 4.13,
      "learning_rate": 3.484723369116433e-06,
      "loss": 0.0599,
      "step": 10000
    },
    {
      "epoch": 4.34,
      "learning_rate": 2.658959537572254e-06,
      "loss": 0.0632,
      "step": 10500
    },
    {
      "epoch": 4.54,
      "learning_rate": 1.8331957060280761e-06,
      "loss": 0.0551,
      "step": 11000
    },
    {
      "epoch": 4.75,
      "learning_rate": 1.0074318744838975e-06,
      "loss": 0.0681,
      "step": 11500
    },
    {
      "epoch": 4.95,
      "learning_rate": 1.8166804293971927e-07,
      "loss": 0.0497,
      "step": 12000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9921052631578947,
      "eval_loss": 0.029725175350904465,
      "eval_runtime": 246.957,
      "eval_samples_per_second": 13.849,
      "eval_steps_per_second": 1.733,
      "step": 12110
    },
    {
      "epoch": 5.0,
      "step": 12110,
      "total_flos": 7.506850873128284e+18,
      "train_loss": 0.1264958238326056,
      "train_runtime": 8600.7866,
      "train_samples_per_second": 11.263,
      "train_steps_per_second": 1.408
    }
  ],
  "logging_steps": 500,
  "max_steps": 12110,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 7.506850873128284e+18,
  "trial_name": null,
  "trial_params": null
}