{
  "best_metric": 0.4446921147952076,
  "best_model_checkpoint": "microsoft/resnet-50/checkpoint-1260",
  "epoch": 4.99009900990099,
  "global_step": 1260,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 3.968253968253968e-06,
      "loss": 1.7784,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 7.936507936507936e-06,
      "loss": 1.786,
      "step": 20
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 1.8132,
      "step": 30
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 1.7916,
      "step": 40
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.984126984126984e-05,
      "loss": 1.7859,
      "step": 50
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.7751,
      "step": 60
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.777777777777778e-05,
      "loss": 1.8154,
      "step": 70
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 1.7868,
      "step": 80
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.7624,
      "step": 90
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.968253968253968e-05,
      "loss": 1.7823,
      "step": 100
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.3650793650793655e-05,
      "loss": 1.7823,
      "step": 110
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.7932,
      "step": 120
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.982363315696649e-05,
      "loss": 1.7863,
      "step": 130
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.938271604938271e-05,
      "loss": 1.7806,
      "step": 140
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.894179894179895e-05,
      "loss": 1.7706,
      "step": 150
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.850088183421517e-05,
      "loss": 1.7629,
      "step": 160
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.8059964726631394e-05,
      "loss": 1.7731,
      "step": 170
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.7435,
      "step": 180
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.717813051146385e-05,
      "loss": 1.7371,
      "step": 190
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.673721340388007e-05,
      "loss": 1.729,
      "step": 200
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.62962962962963e-05,
      "loss": 1.7516,
      "step": 210
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.585537918871252e-05,
      "loss": 1.7337,
      "step": 220
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.541446208112875e-05,
      "loss": 1.7118,
      "step": 230
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.4973544973544974e-05,
      "loss": 1.7141,
      "step": 240
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.45326278659612e-05,
      "loss": 1.7252,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.27528559487322374,
      "eval_loss": 1.7069034576416016,
      "eval_runtime": 16.7761,
      "eval_samples_per_second": 213.935,
      "eval_steps_per_second": 6.736,
      "step": 252
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.409171075837743e-05,
      "loss": 1.7246,
      "step": 260
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.3650793650793655e-05,
      "loss": 1.7388,
      "step": 270
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.3209876543209875e-05,
      "loss": 1.7169,
      "step": 280
    },
    {
      "epoch": 1.15,
      "learning_rate": 4.27689594356261e-05,
      "loss": 1.6987,
      "step": 290
    },
    {
      "epoch": 1.19,
      "learning_rate": 4.232804232804233e-05,
      "loss": 1.7117,
      "step": 300
    },
    {
      "epoch": 1.23,
      "learning_rate": 4.1887125220458555e-05,
      "loss": 1.7117,
      "step": 310
    },
    {
      "epoch": 1.27,
      "learning_rate": 4.144620811287478e-05,
      "loss": 1.7248,
      "step": 320
    },
    {
      "epoch": 1.31,
      "learning_rate": 4.100529100529101e-05,
      "loss": 1.7123,
      "step": 330
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.056437389770723e-05,
      "loss": 1.7096,
      "step": 340
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.012345679012346e-05,
      "loss": 1.6905,
      "step": 350
    },
    {
      "epoch": 1.43,
      "learning_rate": 3.968253968253968e-05,
      "loss": 1.7309,
      "step": 360
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.924162257495591e-05,
      "loss": 1.7151,
      "step": 370
    },
    {
      "epoch": 1.5,
      "learning_rate": 3.8800705467372136e-05,
      "loss": 1.7067,
      "step": 380
    },
    {
      "epoch": 1.54,
      "learning_rate": 3.835978835978836e-05,
      "loss": 1.6982,
      "step": 390
    },
    {
      "epoch": 1.58,
      "learning_rate": 3.791887125220458e-05,
      "loss": 1.6959,
      "step": 400
    },
    {
      "epoch": 1.62,
      "learning_rate": 3.7477954144620817e-05,
      "loss": 1.6794,
      "step": 410
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.6696,
      "step": 420
    },
    {
      "epoch": 1.7,
      "learning_rate": 3.659611992945326e-05,
      "loss": 1.6761,
      "step": 430
    },
    {
      "epoch": 1.74,
      "learning_rate": 3.615520282186949e-05,
      "loss": 1.6844,
      "step": 440
    },
    {
      "epoch": 1.78,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.6666,
      "step": 450
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.527336860670194e-05,
      "loss": 1.6767,
      "step": 460
    },
    {
      "epoch": 1.86,
      "learning_rate": 3.483245149911817e-05,
      "loss": 1.6578,
      "step": 470
    },
    {
      "epoch": 1.9,
      "learning_rate": 3.439153439153439e-05,
      "loss": 1.6493,
      "step": 480
    },
    {
      "epoch": 1.94,
      "learning_rate": 3.395061728395062e-05,
      "loss": 1.6547,
      "step": 490
    },
    {
      "epoch": 1.98,
      "learning_rate": 3.3509700176366844e-05,
      "loss": 1.6386,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3911953190303706,
      "eval_loss": 1.5798698663711548,
      "eval_runtime": 16.5653,
      "eval_samples_per_second": 216.658,
      "eval_steps_per_second": 6.821,
      "step": 505
    },
    {
      "epoch": 2.02,
      "learning_rate": 3.306878306878307e-05,
      "loss": 1.675,
      "step": 510
    },
    {
      "epoch": 2.06,
      "learning_rate": 3.262786596119929e-05,
      "loss": 1.6512,
      "step": 520
    },
    {
      "epoch": 2.1,
      "learning_rate": 3.2186948853615525e-05,
      "loss": 1.6484,
      "step": 530
    },
    {
      "epoch": 2.14,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 1.6573,
      "step": 540
    },
    {
      "epoch": 2.18,
      "learning_rate": 3.130511463844797e-05,
      "loss": 1.6452,
      "step": 550
    },
    {
      "epoch": 2.22,
      "learning_rate": 3.08641975308642e-05,
      "loss": 1.6462,
      "step": 560
    },
    {
      "epoch": 2.26,
      "learning_rate": 3.0423280423280425e-05,
      "loss": 1.6164,
      "step": 570
    },
    {
      "epoch": 2.3,
      "learning_rate": 2.998236331569665e-05,
      "loss": 1.6062,
      "step": 580
    },
    {
      "epoch": 2.34,
      "learning_rate": 2.954144620811288e-05,
      "loss": 1.6517,
      "step": 590
    },
    {
      "epoch": 2.38,
      "learning_rate": 2.91005291005291e-05,
      "loss": 1.6156,
      "step": 600
    },
    {
      "epoch": 2.42,
      "learning_rate": 2.865961199294533e-05,
      "loss": 1.6497,
      "step": 610
    },
    {
      "epoch": 2.46,
      "learning_rate": 2.8218694885361552e-05,
      "loss": 1.6526,
      "step": 620
    },
    {
      "epoch": 2.5,
      "learning_rate": 2.777777777777778e-05,
      "loss": 1.6249,
      "step": 630
    },
    {
      "epoch": 2.53,
      "learning_rate": 2.7336860670194003e-05,
      "loss": 1.6367,
      "step": 640
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.6895943562610233e-05,
      "loss": 1.6321,
      "step": 650
    },
    {
      "epoch": 2.61,
      "learning_rate": 2.6455026455026456e-05,
      "loss": 1.6255,
      "step": 660
    },
    {
      "epoch": 2.65,
      "learning_rate": 2.6014109347442683e-05,
      "loss": 1.6215,
      "step": 670
    },
    {
      "epoch": 2.69,
      "learning_rate": 2.5573192239858906e-05,
      "loss": 1.6425,
      "step": 680
    },
    {
      "epoch": 2.73,
      "learning_rate": 2.5132275132275137e-05,
      "loss": 1.6064,
      "step": 690
    },
    {
      "epoch": 2.77,
      "learning_rate": 2.4691358024691357e-05,
      "loss": 1.6093,
      "step": 700
    },
    {
      "epoch": 2.81,
      "learning_rate": 2.4250440917107583e-05,
      "loss": 1.6022,
      "step": 710
    },
    {
      "epoch": 2.85,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.6309,
      "step": 720
    },
    {
      "epoch": 2.89,
      "learning_rate": 2.3368606701940034e-05,
      "loss": 1.6112,
      "step": 730
    },
    {
      "epoch": 2.93,
      "learning_rate": 2.292768959435626e-05,
      "loss": 1.6253,
      "step": 740
    },
    {
      "epoch": 2.97,
      "learning_rate": 2.2486772486772487e-05,
      "loss": 1.617,
      "step": 750
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.42741710782947895,
      "eval_loss": 1.5154473781585693,
      "eval_runtime": 17.1814,
      "eval_samples_per_second": 208.889,
      "eval_steps_per_second": 6.577,
      "step": 757
    },
    {
      "epoch": 3.01,
      "learning_rate": 2.2045855379188714e-05,
      "loss": 1.6162,
      "step": 760
    },
    {
      "epoch": 3.05,
      "learning_rate": 2.1604938271604937e-05,
      "loss": 1.6166,
      "step": 770
    },
    {
      "epoch": 3.09,
      "learning_rate": 2.1164021164021164e-05,
      "loss": 1.5919,
      "step": 780
    },
    {
      "epoch": 3.13,
      "learning_rate": 2.072310405643739e-05,
      "loss": 1.6002,
      "step": 790
    },
    {
      "epoch": 3.17,
      "learning_rate": 2.0282186948853614e-05,
      "loss": 1.6324,
      "step": 800
    },
    {
      "epoch": 3.21,
      "learning_rate": 1.984126984126984e-05,
      "loss": 1.5883,
      "step": 810
    },
    {
      "epoch": 3.25,
      "learning_rate": 1.9400352733686068e-05,
      "loss": 1.587,
      "step": 820
    },
    {
      "epoch": 3.29,
      "learning_rate": 1.895943562610229e-05,
      "loss": 1.6264,
      "step": 830
    },
    {
      "epoch": 3.33,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 1.5798,
      "step": 840
    },
    {
      "epoch": 3.37,
      "learning_rate": 1.8077601410934745e-05,
      "loss": 1.6045,
      "step": 850
    },
    {
      "epoch": 3.41,
      "learning_rate": 1.763668430335097e-05,
      "loss": 1.6234,
      "step": 860
    },
    {
      "epoch": 3.45,
      "learning_rate": 1.7195767195767195e-05,
      "loss": 1.5851,
      "step": 870
    },
    {
      "epoch": 3.49,
      "learning_rate": 1.6754850088183422e-05,
      "loss": 1.6007,
      "step": 880
    },
    {
      "epoch": 3.52,
      "learning_rate": 1.6313932980599646e-05,
      "loss": 1.6145,
      "step": 890
    },
    {
      "epoch": 3.56,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 1.5742,
      "step": 900
    },
    {
      "epoch": 3.6,
      "learning_rate": 1.54320987654321e-05,
      "loss": 1.5846,
      "step": 910
    },
    {
      "epoch": 3.64,
      "learning_rate": 1.4991181657848324e-05,
      "loss": 1.5921,
      "step": 920
    },
    {
      "epoch": 3.68,
      "learning_rate": 1.455026455026455e-05,
      "loss": 1.6146,
      "step": 930
    },
    {
      "epoch": 3.72,
      "learning_rate": 1.4109347442680776e-05,
      "loss": 1.5937,
      "step": 940
    },
    {
      "epoch": 3.76,
      "learning_rate": 1.3668430335097001e-05,
      "loss": 1.5761,
      "step": 950
    },
    {
      "epoch": 3.8,
      "learning_rate": 1.3227513227513228e-05,
      "loss": 1.6056,
      "step": 960
    },
    {
      "epoch": 3.84,
      "learning_rate": 1.2786596119929453e-05,
      "loss": 1.5614,
      "step": 970
    },
    {
      "epoch": 3.88,
      "learning_rate": 1.2345679012345678e-05,
      "loss": 1.578,
      "step": 980
    },
    {
      "epoch": 3.92,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 1.5495,
      "step": 990
    },
    {
      "epoch": 3.96,
      "learning_rate": 1.146384479717813e-05,
      "loss": 1.5949,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.1022927689594357e-05,
      "loss": 1.5795,
      "step": 1010
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.43772638617999443,
      "eval_loss": 1.4835728406906128,
      "eval_runtime": 16.6725,
      "eval_samples_per_second": 215.265,
      "eval_steps_per_second": 6.778,
      "step": 1010
    },
    {
      "epoch": 4.04,
      "learning_rate": 1.0582010582010582e-05,
      "loss": 1.5641,
      "step": 1020
    },
    {
      "epoch": 4.08,
      "learning_rate": 1.0141093474426807e-05,
      "loss": 1.5833,
      "step": 1030
    },
    {
      "epoch": 4.12,
      "learning_rate": 9.700176366843034e-06,
      "loss": 1.5865,
      "step": 1040
    },
    {
      "epoch": 4.16,
      "learning_rate": 9.259259259259259e-06,
      "loss": 1.5846,
      "step": 1050
    },
    {
      "epoch": 4.2,
      "learning_rate": 8.818342151675484e-06,
      "loss": 1.5946,
      "step": 1060
    },
    {
      "epoch": 4.24,
      "learning_rate": 8.377425044091711e-06,
      "loss": 1.6151,
      "step": 1070
    },
    {
      "epoch": 4.28,
      "learning_rate": 7.936507936507936e-06,
      "loss": 1.5523,
      "step": 1080
    },
    {
      "epoch": 4.32,
      "learning_rate": 7.495590828924162e-06,
      "loss": 1.5852,
      "step": 1090
    },
    {
      "epoch": 4.36,
      "learning_rate": 7.054673721340388e-06,
      "loss": 1.5802,
      "step": 1100
    },
    {
      "epoch": 4.4,
      "learning_rate": 6.613756613756614e-06,
      "loss": 1.6024,
      "step": 1110
    },
    {
      "epoch": 4.44,
      "learning_rate": 6.172839506172839e-06,
      "loss": 1.5884,
      "step": 1120
    },
    {
      "epoch": 4.48,
      "learning_rate": 5.731922398589065e-06,
      "loss": 1.5436,
      "step": 1130
    },
    {
      "epoch": 4.51,
      "learning_rate": 5.291005291005291e-06,
      "loss": 1.5893,
      "step": 1140
    },
    {
      "epoch": 4.55,
      "learning_rate": 4.850088183421517e-06,
      "loss": 1.5899,
      "step": 1150
    },
    {
      "epoch": 4.59,
      "learning_rate": 4.409171075837742e-06,
      "loss": 1.5784,
      "step": 1160
    },
    {
      "epoch": 4.63,
      "learning_rate": 3.968253968253968e-06,
      "loss": 1.5623,
      "step": 1170
    },
    {
      "epoch": 4.67,
      "learning_rate": 3.527336860670194e-06,
      "loss": 1.586,
      "step": 1180
    },
    {
      "epoch": 4.71,
      "learning_rate": 3.0864197530864196e-06,
      "loss": 1.5778,
      "step": 1190
    },
    {
      "epoch": 4.75,
      "learning_rate": 2.6455026455026455e-06,
      "loss": 1.5501,
      "step": 1200
    },
    {
      "epoch": 4.79,
      "learning_rate": 2.204585537918871e-06,
      "loss": 1.6087,
      "step": 1210
    },
    {
      "epoch": 4.83,
      "learning_rate": 1.763668430335097e-06,
      "loss": 1.5764,
      "step": 1220
    },
    {
      "epoch": 4.87,
      "learning_rate": 1.3227513227513228e-06,
      "loss": 1.5991,
      "step": 1230
    },
    {
      "epoch": 4.91,
      "learning_rate": 8.818342151675485e-07,
      "loss": 1.5643,
      "step": 1240
    },
    {
      "epoch": 4.95,
      "learning_rate": 4.4091710758377425e-07,
      "loss": 1.5688,
      "step": 1250
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0,
      "loss": 1.5645,
      "step": 1260
    },
    {
      "epoch": 4.99,
      "eval_accuracy": 0.4446921147952076,
      "eval_loss": 1.4667332172393799,
      "eval_runtime": 16.8572,
      "eval_samples_per_second": 212.906,
      "eval_steps_per_second": 6.703,
      "step": 1260
    },
    {
      "epoch": 4.99,
      "step": 1260,
      "total_flos": 3.424468651849728e+18,
      "train_loss": 1.653014714377267,
      "train_runtime": 2002.0643,
      "train_samples_per_second": 80.662,
      "train_steps_per_second": 0.629
    }
  ],
  "max_steps": 1260,
  "num_train_epochs": 5,
  "total_flos": 3.424468651849728e+18,
  "trial_name": null,
  "trial_params": null
}