{
  "best_metric": 0.9665621116174469,
  "best_model_checkpoint": "SwinMark2/checkpoint-693",
  "epoch": 2.996756756756757,
  "eval_steps": 500,
  "global_step": 693,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 7.142857142857143e-06,
      "loss": 1.3098,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.1138,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.8719,
      "step": 30
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.6339,
      "step": 40
    },
    {
      "epoch": 0.22,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.4509,
      "step": 50
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.3485,
      "step": 60
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 0.3103,
      "step": 70
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.919743178170145e-05,
      "loss": 0.2529,
      "step": 80
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.839486356340289e-05,
      "loss": 0.2251,
      "step": 90
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.759229534510434e-05,
      "loss": 0.2148,
      "step": 100
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.678972712680578e-05,
      "loss": 0.2153,
      "step": 110
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.598715890850723e-05,
      "loss": 0.1991,
      "step": 120
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.5184590690208673e-05,
      "loss": 0.1931,
      "step": 130
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.438202247191011e-05,
      "loss": 0.1893,
      "step": 140
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.357945425361156e-05,
      "loss": 0.1806,
      "step": 150
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.2776886035313e-05,
      "loss": 0.1581,
      "step": 160
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.197431781701445e-05,
      "loss": 0.1654,
      "step": 170
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.117174959871589e-05,
      "loss": 0.1606,
      "step": 180
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.036918138041734e-05,
      "loss": 0.1579,
      "step": 190
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.956661316211878e-05,
      "loss": 0.1584,
      "step": 200
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.876404494382023e-05,
      "loss": 0.1931,
      "step": 210
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.796147672552167e-05,
      "loss": 0.1474,
      "step": 220
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.715890850722312e-05,
      "loss": 0.1407,
      "step": 230
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9586317097709652,
      "eval_loss": 0.12301469594240189,
      "eval_runtime": 259.331,
      "eval_samples_per_second": 65.156,
      "eval_steps_per_second": 0.513,
      "step": 231
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.6356340288924564e-05,
      "loss": 0.1519,
      "step": 240
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.555377207062601e-05,
      "loss": 0.1442,
      "step": 250
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.4751203852327454e-05,
      "loss": 0.1409,
      "step": 260
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.394863563402889e-05,
      "loss": 0.1468,
      "step": 270
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.314606741573034e-05,
      "loss": 0.1337,
      "step": 280
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.234349919743178e-05,
      "loss": 0.146,
      "step": 290
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.154093097913323e-05,
      "loss": 0.1486,
      "step": 300
    },
    {
      "epoch": 1.34,
      "learning_rate": 3.073836276083467e-05,
      "loss": 0.1386,
      "step": 310
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.9935794542536115e-05,
      "loss": 0.13,
      "step": 320
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.913322632423756e-05,
      "loss": 0.1192,
      "step": 330
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.8330658105939005e-05,
      "loss": 0.1418,
      "step": 340
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.752808988764045e-05,
      "loss": 0.1171,
      "step": 350
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.6725521669341895e-05,
      "loss": 0.1251,
      "step": 360
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.592295345104334e-05,
      "loss": 0.1261,
      "step": 370
    },
    {
      "epoch": 1.64,
      "learning_rate": 2.5120385232744786e-05,
      "loss": 0.1282,
      "step": 380
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.4317817014446228e-05,
      "loss": 0.1235,
      "step": 390
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.3515248796147673e-05,
      "loss": 0.1269,
      "step": 400
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.2712680577849118e-05,
      "loss": 0.119,
      "step": 410
    },
    {
      "epoch": 1.82,
      "learning_rate": 2.1910112359550563e-05,
      "loss": 0.1296,
      "step": 420
    },
    {
      "epoch": 1.86,
      "learning_rate": 2.1107544141252008e-05,
      "loss": 0.1114,
      "step": 430
    },
    {
      "epoch": 1.9,
      "learning_rate": 2.030497592295345e-05,
      "loss": 0.1334,
      "step": 440
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.9502407704654895e-05,
      "loss": 0.118,
      "step": 450
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.869983948635634e-05,
      "loss": 0.1209,
      "step": 460
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9630111854175297,
      "eval_loss": 0.10658775269985199,
      "eval_runtime": 231.585,
      "eval_samples_per_second": 72.962,
      "eval_steps_per_second": 0.574,
      "step": 462
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.7897271268057786e-05,
      "loss": 0.1038,
      "step": 470
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.709470304975923e-05,
      "loss": 0.1159,
      "step": 480
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.6292134831460676e-05,
      "loss": 0.0992,
      "step": 490
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.548956661316212e-05,
      "loss": 0.1166,
      "step": 500
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.4686998394863563e-05,
      "loss": 0.1046,
      "step": 510
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.3884430176565008e-05,
      "loss": 0.0994,
      "step": 520
    },
    {
      "epoch": 2.29,
      "learning_rate": 1.3081861958266453e-05,
      "loss": 0.124,
      "step": 530
    },
    {
      "epoch": 2.34,
      "learning_rate": 1.2279293739967898e-05,
      "loss": 0.1113,
      "step": 540
    },
    {
      "epoch": 2.38,
      "learning_rate": 1.1476725521669344e-05,
      "loss": 0.1106,
      "step": 550
    },
    {
      "epoch": 2.42,
      "learning_rate": 1.0674157303370787e-05,
      "loss": 0.1083,
      "step": 560
    },
    {
      "epoch": 2.46,
      "learning_rate": 9.871589085072232e-06,
      "loss": 0.1108,
      "step": 570
    },
    {
      "epoch": 2.51,
      "learning_rate": 9.069020866773677e-06,
      "loss": 0.1093,
      "step": 580
    },
    {
      "epoch": 2.55,
      "learning_rate": 8.26645264847512e-06,
      "loss": 0.0975,
      "step": 590
    },
    {
      "epoch": 2.59,
      "learning_rate": 7.463884430176565e-06,
      "loss": 0.1041,
      "step": 600
    },
    {
      "epoch": 2.64,
      "learning_rate": 6.66131621187801e-06,
      "loss": 0.1157,
      "step": 610
    },
    {
      "epoch": 2.68,
      "learning_rate": 5.858747993579455e-06,
      "loss": 0.1005,
      "step": 620
    },
    {
      "epoch": 2.72,
      "learning_rate": 5.056179775280899e-06,
      "loss": 0.1097,
      "step": 630
    },
    {
      "epoch": 2.77,
      "learning_rate": 4.253611556982344e-06,
      "loss": 0.1102,
      "step": 640
    },
    {
      "epoch": 2.81,
      "learning_rate": 3.4510433386837885e-06,
      "loss": 0.111,
      "step": 650
    },
    {
      "epoch": 2.85,
      "learning_rate": 2.648475120385233e-06,
      "loss": 0.0956,
      "step": 660
    },
    {
      "epoch": 2.9,
      "learning_rate": 1.8459069020866775e-06,
      "loss": 0.1079,
      "step": 670
    },
    {
      "epoch": 2.94,
      "learning_rate": 1.043338683788122e-06,
      "loss": 0.1047,
      "step": 680
    },
    {
      "epoch": 2.98,
      "learning_rate": 2.407704654895666e-07,
      "loss": 0.0987,
      "step": 690
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9665621116174469,
      "eval_loss": 0.09518735855817795,
      "eval_runtime": 181.4053,
      "eval_samples_per_second": 93.145,
      "eval_steps_per_second": 0.733,
      "step": 693
    },
    {
      "epoch": 3.0,
      "step": 693,
      "total_flos": 1.1536340155092173e+19,
      "train_loss": 0.19495156454661536,
      "train_runtime": 10434.9174,
      "train_samples_per_second": 34.004,
      "train_steps_per_second": 0.066
    }
  ],
  "logging_steps": 10,
  "max_steps": 693,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.1536340155092173e+19,
  "trial_name": null,
  "trial_params": null
}