{
  "best_metric": 0.6854754440961337,
  "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-0.0001/checkpoint-606",
  "epoch": 3.0,
  "global_step": 606,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 1.6393442622950818e-05,
      "loss": 1.9514,
      "step": 10
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.2786885245901635e-05,
      "loss": 1.7098,
      "step": 20
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.918032786885246e-05,
      "loss": 1.5711,
      "step": 30
    },
    {
      "epoch": 0.2,
      "learning_rate": 6.557377049180327e-05,
      "loss": 1.4081,
      "step": 40
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.19672131147541e-05,
      "loss": 1.4072,
      "step": 50
    },
    {
      "epoch": 0.3,
      "learning_rate": 9.836065573770493e-05,
      "loss": 1.382,
      "step": 60
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.834862385321102e-05,
      "loss": 1.3336,
      "step": 70
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.651376146788991e-05,
      "loss": 1.3143,
      "step": 80
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.467889908256882e-05,
      "loss": 1.3,
      "step": 90
    },
    {
      "epoch": 0.5,
      "learning_rate": 9.284403669724772e-05,
      "loss": 1.3335,
      "step": 100
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.100917431192661e-05,
      "loss": 1.291,
      "step": 110
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.917431192660551e-05,
      "loss": 1.2489,
      "step": 120
    },
    {
      "epoch": 0.64,
      "learning_rate": 8.733944954128442e-05,
      "loss": 1.2776,
      "step": 130
    },
    {
      "epoch": 0.69,
      "learning_rate": 8.550458715596331e-05,
      "loss": 1.2443,
      "step": 140
    },
    {
      "epoch": 0.74,
      "learning_rate": 8.366972477064221e-05,
      "loss": 1.214,
      "step": 150
    },
    {
      "epoch": 0.79,
      "learning_rate": 8.183486238532112e-05,
      "loss": 1.2379,
      "step": 160
    },
    {
      "epoch": 0.84,
      "learning_rate": 8e-05,
      "loss": 1.1672,
      "step": 170
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.816513761467891e-05,
      "loss": 1.1764,
      "step": 180
    },
    {
      "epoch": 0.94,
      "learning_rate": 7.63302752293578e-05,
      "loss": 1.2006,
      "step": 190
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.44954128440367e-05,
      "loss": 1.1632,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6290491118077325,
      "eval_loss": 0.9974912405014038,
      "eval_runtime": 25.6751,
      "eval_samples_per_second": 111.821,
      "eval_steps_per_second": 3.505,
      "step": 202
    },
    {
      "epoch": 1.04,
      "learning_rate": 7.266055045871561e-05,
      "loss": 1.1413,
      "step": 210
    },
    {
      "epoch": 1.09,
      "learning_rate": 7.08256880733945e-05,
      "loss": 1.1803,
      "step": 220
    },
    {
      "epoch": 1.14,
      "learning_rate": 6.89908256880734e-05,
      "loss": 1.1526,
      "step": 230
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.715596330275231e-05,
      "loss": 1.0817,
      "step": 240
    },
    {
      "epoch": 1.24,
      "learning_rate": 6.53211009174312e-05,
      "loss": 1.1358,
      "step": 250
    },
    {
      "epoch": 1.29,
      "learning_rate": 6.34862385321101e-05,
      "loss": 1.1496,
      "step": 260
    },
    {
      "epoch": 1.34,
      "learning_rate": 6.165137614678899e-05,
      "loss": 1.1992,
      "step": 270
    },
    {
      "epoch": 1.39,
      "learning_rate": 5.9816513761467896e-05,
      "loss": 1.1061,
      "step": 280
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.798165137614679e-05,
      "loss": 1.1059,
      "step": 290
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.61467889908257e-05,
      "loss": 1.1208,
      "step": 300
    },
    {
      "epoch": 1.53,
      "learning_rate": 5.4311926605504594e-05,
      "loss": 1.1173,
      "step": 310
    },
    {
      "epoch": 1.58,
      "learning_rate": 5.247706422018349e-05,
      "loss": 1.1132,
      "step": 320
    },
    {
      "epoch": 1.63,
      "learning_rate": 5.064220183486239e-05,
      "loss": 1.0441,
      "step": 330
    },
    {
      "epoch": 1.68,
      "learning_rate": 4.880733944954129e-05,
      "loss": 1.0603,
      "step": 340
    },
    {
      "epoch": 1.73,
      "learning_rate": 4.697247706422019e-05,
      "loss": 1.1201,
      "step": 350
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.513761467889909e-05,
      "loss": 1.0933,
      "step": 360
    },
    {
      "epoch": 1.83,
      "learning_rate": 4.3302752293577984e-05,
      "loss": 1.0863,
      "step": 370
    },
    {
      "epoch": 1.88,
      "learning_rate": 4.146788990825689e-05,
      "loss": 1.0781,
      "step": 380
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.9633027522935785e-05,
      "loss": 1.1139,
      "step": 390
    },
    {
      "epoch": 1.98,
      "learning_rate": 3.779816513761468e-05,
      "loss": 1.0563,
      "step": 400
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6614420062695925,
      "eval_loss": 0.9350310564041138,
      "eval_runtime": 27.29,
      "eval_samples_per_second": 105.203,
      "eval_steps_per_second": 3.298,
      "step": 404
    },
    {
      "epoch": 2.03,
      "learning_rate": 3.596330275229358e-05,
      "loss": 1.0391,
      "step": 410
    },
    {
      "epoch": 2.08,
      "learning_rate": 3.4128440366972484e-05,
      "loss": 0.974,
      "step": 420
    },
    {
      "epoch": 2.13,
      "learning_rate": 3.229357798165138e-05,
      "loss": 1.0585,
      "step": 430
    },
    {
      "epoch": 2.18,
      "learning_rate": 3.0458715596330278e-05,
      "loss": 1.0451,
      "step": 440
    },
    {
      "epoch": 2.23,
      "learning_rate": 2.862385321100918e-05,
      "loss": 0.9934,
      "step": 450
    },
    {
      "epoch": 2.28,
      "learning_rate": 2.6788990825688076e-05,
      "loss": 1.015,
      "step": 460
    },
    {
      "epoch": 2.33,
      "learning_rate": 2.4954128440366977e-05,
      "loss": 1.0505,
      "step": 470
    },
    {
      "epoch": 2.38,
      "learning_rate": 2.3119266055045874e-05,
      "loss": 1.0035,
      "step": 480
    },
    {
      "epoch": 2.43,
      "learning_rate": 2.1284403669724774e-05,
      "loss": 0.9752,
      "step": 490
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.944954128440367e-05,
      "loss": 1.0124,
      "step": 500
    },
    {
      "epoch": 2.52,
      "learning_rate": 1.7614678899082572e-05,
      "loss": 1.0122,
      "step": 510
    },
    {
      "epoch": 2.57,
      "learning_rate": 1.577981651376147e-05,
      "loss": 1.0435,
      "step": 520
    },
    {
      "epoch": 2.62,
      "learning_rate": 1.3944954128440368e-05,
      "loss": 1.0102,
      "step": 530
    },
    {
      "epoch": 2.67,
      "learning_rate": 1.2110091743119267e-05,
      "loss": 1.0476,
      "step": 540
    },
    {
      "epoch": 2.72,
      "learning_rate": 1.0275229357798166e-05,
      "loss": 0.9989,
      "step": 550
    },
    {
      "epoch": 2.77,
      "learning_rate": 8.440366972477065e-06,
      "loss": 0.9549,
      "step": 560
    },
    {
      "epoch": 2.82,
      "learning_rate": 6.605504587155964e-06,
      "loss": 0.9696,
      "step": 570
    },
    {
      "epoch": 2.87,
      "learning_rate": 4.7706422018348626e-06,
      "loss": 1.0032,
      "step": 580
    },
    {
      "epoch": 2.92,
      "learning_rate": 2.935779816513762e-06,
      "loss": 0.9941,
      "step": 590
    },
    {
      "epoch": 2.97,
      "learning_rate": 1.1009174311926608e-06,
      "loss": 0.9564,
      "step": 600
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6854754440961337,
      "eval_loss": 0.8600627183914185,
      "eval_runtime": 25.8777,
      "eval_samples_per_second": 110.945,
      "eval_steps_per_second": 3.478,
      "step": 606
    },
    {
      "epoch": 3.0,
      "step": 606,
      "total_flos": 6.004415924974301e+18,
      "train_loss": 1.1543370756772484,
      "train_runtime": 1817.3296,
      "train_samples_per_second": 42.653,
      "train_steps_per_second": 0.333
    }
  ],
  "max_steps": 606,
  "num_train_epochs": 3,
  "total_flos": 6.004415924974301e+18,
  "trial_name": null,
  "trial_params": null
}