{
  "best_metric": 2.9018115997314453,
  "best_model_checkpoint": "mammals_45_types_image_classification/checkpoint-6030",
  "epoch": 30.0,
  "eval_steps": 500,
  "global_step": 6030,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.08114856429463171,
      "eval_loss": 3.75849986076355,
      "eval_runtime": 30.5405,
      "eval_samples_per_second": 104.91,
      "eval_steps_per_second": 3.307,
      "step": 201
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2075530586766542,
      "eval_loss": 3.7100367546081543,
      "eval_runtime": 29.9814,
      "eval_samples_per_second": 106.866,
      "eval_steps_per_second": 3.369,
      "step": 402
    },
    {
      "epoch": 2.49,
      "learning_rate": 9.247491638795987e-07,
      "loss": 3.7416,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3611111111111111,
      "eval_loss": 3.656773567199707,
      "eval_runtime": 30.4974,
      "eval_samples_per_second": 105.058,
      "eval_steps_per_second": 3.312,
      "step": 603
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5074906367041199,
      "eval_loss": 3.599795341491699,
      "eval_runtime": 30.7929,
      "eval_samples_per_second": 104.05,
      "eval_steps_per_second": 3.28,
      "step": 804
    },
    {
      "epoch": 4.98,
      "learning_rate": 8.411371237458194e-07,
      "loss": 3.584,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6448189762796505,
      "eval_loss": 3.5441219806671143,
      "eval_runtime": 31.0865,
      "eval_samples_per_second": 103.067,
      "eval_steps_per_second": 3.249,
      "step": 1005
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7471910112359551,
      "eval_loss": 3.491813898086548,
      "eval_runtime": 30.1716,
      "eval_samples_per_second": 106.192,
      "eval_steps_per_second": 3.348,
      "step": 1206
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8074282147315855,
      "eval_loss": 3.4418811798095703,
      "eval_runtime": 29.0772,
      "eval_samples_per_second": 110.189,
      "eval_steps_per_second": 3.474,
      "step": 1407
    },
    {
      "epoch": 7.46,
      "learning_rate": 7.575250836120402e-07,
      "loss": 3.4263,
      "step": 1500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8433208489388264,
      "eval_loss": 3.394082546234131,
      "eval_runtime": 30.2291,
      "eval_samples_per_second": 105.991,
      "eval_steps_per_second": 3.341,
      "step": 1608
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8664169787765293,
      "eval_loss": 3.349376916885376,
      "eval_runtime": 29.5587,
      "eval_samples_per_second": 108.395,
      "eval_steps_per_second": 3.417,
      "step": 1809
    },
    {
      "epoch": 9.95,
      "learning_rate": 6.739130434782609e-07,
      "loss": 3.2922,
      "step": 2000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8820224719101124,
      "eval_loss": 3.305469512939453,
      "eval_runtime": 29.4868,
      "eval_samples_per_second": 108.659,
      "eval_steps_per_second": 3.425,
      "step": 2010
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.8948189762796505,
      "eval_loss": 3.2643473148345947,
      "eval_runtime": 29.5531,
      "eval_samples_per_second": 108.415,
      "eval_steps_per_second": 3.418,
      "step": 2211
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9054307116104869,
      "eval_loss": 3.225986957550049,
      "eval_runtime": 30.7268,
      "eval_samples_per_second": 104.274,
      "eval_steps_per_second": 3.287,
      "step": 2412
    },
    {
      "epoch": 12.44,
      "learning_rate": 5.903010033444817e-07,
      "loss": 3.1728,
      "step": 2500
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9113607990012484,
      "eval_loss": 3.1893086433410645,
      "eval_runtime": 30.7156,
      "eval_samples_per_second": 104.312,
      "eval_steps_per_second": 3.288,
      "step": 2613
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9147940074906367,
      "eval_loss": 3.1561264991760254,
      "eval_runtime": 29.1629,
      "eval_samples_per_second": 109.866,
      "eval_steps_per_second": 3.463,
      "step": 2814
    },
    {
      "epoch": 14.93,
      "learning_rate": 5.066889632107023e-07,
      "loss": 3.0729,
      "step": 3000
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9210362047440699,
      "eval_loss": 3.1243045330047607,
      "eval_runtime": 29.6226,
      "eval_samples_per_second": 108.161,
      "eval_steps_per_second": 3.41,
      "step": 3015
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.9244694132334582,
      "eval_loss": 3.0949244499206543,
      "eval_runtime": 29.2749,
      "eval_samples_per_second": 109.445,
      "eval_steps_per_second": 3.45,
      "step": 3216
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.9269662921348315,
      "eval_loss": 3.0683112144470215,
      "eval_runtime": 29.1985,
      "eval_samples_per_second": 109.732,
      "eval_steps_per_second": 3.459,
      "step": 3417
    },
    {
      "epoch": 17.41,
      "learning_rate": 4.2307692307692304e-07,
      "loss": 2.9872,
      "step": 3500
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.931023720349563,
      "eval_loss": 3.0429186820983887,
      "eval_runtime": 29.3871,
      "eval_samples_per_second": 109.027,
      "eval_steps_per_second": 3.437,
      "step": 3618
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.9353932584269663,
      "eval_loss": 3.02020263671875,
      "eval_runtime": 30.5734,
      "eval_samples_per_second": 104.797,
      "eval_steps_per_second": 3.304,
      "step": 3819
    },
    {
      "epoch": 19.9,
      "learning_rate": 3.394648829431438e-07,
      "loss": 2.9179,
      "step": 4000
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.936641697877653,
      "eval_loss": 2.998936176300049,
      "eval_runtime": 29.6935,
      "eval_samples_per_second": 107.902,
      "eval_steps_per_second": 3.401,
      "step": 4020
    },
    {
      "epoch": 21.0,
      "eval_accuracy": 0.9382022471910112,
      "eval_loss": 2.98030424118042,
      "eval_runtime": 29.567,
      "eval_samples_per_second": 108.364,
      "eval_steps_per_second": 3.416,
      "step": 4221
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.9391385767790262,
      "eval_loss": 2.963463544845581,
      "eval_runtime": 29.139,
      "eval_samples_per_second": 109.956,
      "eval_steps_per_second": 3.466,
      "step": 4422
    },
    {
      "epoch": 22.39,
      "learning_rate": 2.5585284280936454e-07,
      "loss": 2.8631,
      "step": 4500
    },
    {
      "epoch": 23.0,
      "eval_accuracy": 0.9397627965043696,
      "eval_loss": 2.948824882507324,
      "eval_runtime": 29.1663,
      "eval_samples_per_second": 109.853,
      "eval_steps_per_second": 3.463,
      "step": 4623
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.9406991260923845,
      "eval_loss": 2.9361581802368164,
      "eval_runtime": 29.4311,
      "eval_samples_per_second": 108.865,
      "eval_steps_per_second": 3.432,
      "step": 4824
    },
    {
      "epoch": 24.88,
      "learning_rate": 1.7224080267558528e-07,
      "loss": 2.8232,
      "step": 5000
    },
    {
      "epoch": 25.0,
      "eval_accuracy": 0.9410112359550562,
      "eval_loss": 2.925414800643921,
      "eval_runtime": 29.1531,
      "eval_samples_per_second": 109.902,
      "eval_steps_per_second": 3.464,
      "step": 5025
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.9410112359550562,
      "eval_loss": 2.9169344902038574,
      "eval_runtime": 29.0329,
      "eval_samples_per_second": 110.358,
      "eval_steps_per_second": 3.479,
      "step": 5226
    },
    {
      "epoch": 27.0,
      "eval_accuracy": 0.9413233458177278,
      "eval_loss": 2.910374402999878,
      "eval_runtime": 29.9412,
      "eval_samples_per_second": 107.01,
      "eval_steps_per_second": 3.373,
      "step": 5427
    },
    {
      "epoch": 27.36,
      "learning_rate": 8.862876254180602e-08,
      "loss": 2.7973,
      "step": 5500
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.9416354556803995,
      "eval_loss": 2.905684232711792,
      "eval_runtime": 29.9557,
      "eval_samples_per_second": 106.958,
      "eval_steps_per_second": 3.372,
      "step": 5628
    },
    {
      "epoch": 29.0,
      "eval_accuracy": 0.9416354556803995,
      "eval_loss": 2.9027676582336426,
      "eval_runtime": 29.4346,
      "eval_samples_per_second": 108.851,
      "eval_steps_per_second": 3.431,
      "step": 5829
    },
    {
      "epoch": 29.85,
      "learning_rate": 5.016722408026756e-09,
      "loss": 2.7825,
      "step": 6000
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.9416354556803995,
      "eval_loss": 2.9018115997314453,
      "eval_runtime": 29.2154,
      "eval_samples_per_second": 109.668,
      "eval_steps_per_second": 3.457,
      "step": 6030
    }
  ],
  "logging_steps": 500,
  "max_steps": 6030,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 2.980560268384764e+19,
  "trial_name": null,
  "trial_params": null
}