{
  "best_metric": 0.0413714237511158,
  "best_model_checkpoint": "./Birds-Or-Not/checkpoint-225",
  "epoch": 5.813953488372093,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23,
      "learning_rate": 0.0001922480620155039,
      "loss": 0.512,
      "step": 10
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00018449612403100774,
      "loss": 0.1901,
      "step": 20
    },
    {
      "epoch": 0.58,
      "eval_accuracy": 0.9685863874345549,
      "eval_loss": 0.10355287045240402,
      "eval_runtime": 3.6181,
      "eval_samples_per_second": 52.791,
      "eval_steps_per_second": 6.633,
      "step": 25
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017674418604651164,
      "loss": 0.3262,
      "step": 30
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001689922480620155,
      "loss": 0.1114,
      "step": 40
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00016124031007751937,
      "loss": 0.0367,
      "step": 50
    },
    {
      "epoch": 1.16,
      "eval_accuracy": 0.9738219895287958,
      "eval_loss": 0.06718893349170685,
      "eval_runtime": 3.0958,
      "eval_samples_per_second": 61.697,
      "eval_steps_per_second": 7.753,
      "step": 50
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00015348837209302327,
      "loss": 0.0738,
      "step": 60
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00014573643410852714,
      "loss": 0.0101,
      "step": 70
    },
    {
      "epoch": 1.74,
      "eval_accuracy": 0.9790575916230366,
      "eval_loss": 0.060171037912368774,
      "eval_runtime": 3.0912,
      "eval_samples_per_second": 61.789,
      "eval_steps_per_second": 7.764,
      "step": 75
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.000137984496124031,
      "loss": 0.0982,
      "step": 80
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0001302325581395349,
      "loss": 0.0409,
      "step": 90
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00012248062015503876,
      "loss": 0.0079,
      "step": 100
    },
    {
      "epoch": 2.33,
      "eval_accuracy": 0.9790575916230366,
      "eval_loss": 0.06641152501106262,
      "eval_runtime": 3.0752,
      "eval_samples_per_second": 62.11,
      "eval_steps_per_second": 7.804,
      "step": 100
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00011472868217054265,
      "loss": 0.0075,
      "step": 110
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00010697674418604651,
      "loss": 0.0295,
      "step": 120
    },
    {
      "epoch": 2.91,
      "eval_accuracy": 0.9685863874345549,
      "eval_loss": 0.09663180261850357,
      "eval_runtime": 3.2748,
      "eval_samples_per_second": 58.325,
      "eval_steps_per_second": 7.329,
      "step": 125
    },
    {
      "epoch": 3.02,
      "learning_rate": 9.92248062015504e-05,
      "loss": 0.0301,
      "step": 130
    },
    {
      "epoch": 3.26,
      "learning_rate": 9.147286821705426e-05,
      "loss": 0.0095,
      "step": 140
    },
    {
      "epoch": 3.49,
      "learning_rate": 8.372093023255814e-05,
      "loss": 0.0066,
      "step": 150
    },
    {
      "epoch": 3.49,
      "eval_accuracy": 0.9790575916230366,
      "eval_loss": 0.04968209192156792,
      "eval_runtime": 3.1516,
      "eval_samples_per_second": 60.603,
      "eval_steps_per_second": 7.615,
      "step": 150
    },
    {
      "epoch": 3.72,
      "learning_rate": 7.596899224806202e-05,
      "loss": 0.0037,
      "step": 160
    },
    {
      "epoch": 3.95,
      "learning_rate": 6.821705426356589e-05,
      "loss": 0.0036,
      "step": 170
    },
    {
      "epoch": 4.07,
      "eval_accuracy": 0.9842931937172775,
      "eval_loss": 0.06203766167163849,
      "eval_runtime": 3.6519,
      "eval_samples_per_second": 52.302,
      "eval_steps_per_second": 6.572,
      "step": 175
    },
    {
      "epoch": 4.19,
      "learning_rate": 6.0465116279069765e-05,
      "loss": 0.0034,
      "step": 180
    },
    {
      "epoch": 4.42,
      "learning_rate": 5.271317829457365e-05,
      "loss": 0.0033,
      "step": 190
    },
    {
      "epoch": 4.65,
      "learning_rate": 4.496124031007753e-05,
      "loss": 0.0063,
      "step": 200
    },
    {
      "epoch": 4.65,
      "eval_accuracy": 0.9842931937172775,
      "eval_loss": 0.0426977165043354,
      "eval_runtime": 3.2933,
      "eval_samples_per_second": 57.997,
      "eval_steps_per_second": 7.288,
      "step": 200
    },
    {
      "epoch": 4.88,
      "learning_rate": 3.7209302325581394e-05,
      "loss": 0.003,
      "step": 210
    },
    {
      "epoch": 5.12,
      "learning_rate": 2.9457364341085275e-05,
      "loss": 0.0029,
      "step": 220
    },
    {
      "epoch": 5.23,
      "eval_accuracy": 0.9842931937172775,
      "eval_loss": 0.0413714237511158,
      "eval_runtime": 3.0838,
      "eval_samples_per_second": 61.937,
      "eval_steps_per_second": 7.783,
      "step": 225
    },
    {
      "epoch": 5.35,
      "learning_rate": 2.170542635658915e-05,
      "loss": 0.0029,
      "step": 230
    },
    {
      "epoch": 5.58,
      "learning_rate": 1.3953488372093024e-05,
      "loss": 0.0028,
      "step": 240
    },
    {
      "epoch": 5.81,
      "learning_rate": 6.2015503875969e-06,
      "loss": 0.0028,
      "step": 250
    },
    {
      "epoch": 5.81,
      "eval_accuracy": 0.9842931937172775,
      "eval_loss": 0.041494447737932205,
      "eval_runtime": 3.5969,
      "eval_samples_per_second": 53.102,
      "eval_steps_per_second": 6.672,
      "step": 250
    }
  ],
  "max_steps": 258,
  "num_train_epochs": 6,
  "total_flos": 3.09967958458368e+17,
  "trial_name": null,
  "trial_params": null
}