{
  "best_metric": 0.436241610738255,
  "best_model_checkpoint": "timesformer-base-finetuned-k400-finetuned-ucf101-subset/checkpoint-2700",
  "epoch": 9.1,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.3924,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.9129,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-06,
      "loss": 1.3532,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.12,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.14,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 1e-05,
      "loss": 1.9799,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 1.6834,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.7657,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.5e-05,
      "loss": 0.8917,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.8642,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 2.9366,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 2e-05,
      "loss": 1.7314,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.1666666666666667e-05,
      "loss": 1.2063,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 2.1836,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.5e-05,
      "loss": 2.3437,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 3.0346,
      "step": 160
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.8333333333333335e-05,
      "loss": 1.5671,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 3e-05,
      "loss": 0.9069,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.1666666666666666e-05,
      "loss": 2.7771,
      "step": 190
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.5606,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.5e-05,
      "loss": 2.1344,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 2.5326,
      "step": 220
    },
    {
      "epoch": 0.08,
      "learning_rate": 3.8333333333333334e-05,
      "loss": 3.2706,
      "step": 230
    },
    {
      "epoch": 0.08,
      "learning_rate": 4e-05,
      "loss": 1.9432,
      "step": 240
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.166666666666667e-05,
      "loss": 2.5327,
      "step": 250
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 2.7838,
      "step": 260
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.5e-05,
      "loss": 1.2561,
      "step": 270
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.666666666666667e-05,
      "loss": 2.3613,
      "step": 280
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8333333333333334e-05,
      "loss": 4.2268,
      "step": 290
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 1.4112,
      "step": 300
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.11409395973154363,
      "eval_loss": 4.316457748413086,
      "eval_runtime": 11.8355,
      "eval_samples_per_second": 12.589,
      "eval_steps_per_second": 12.589,
      "step": 300
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.981481481481482e-05,
      "loss": 3.9062,
      "step": 310
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.962962962962963e-05,
      "loss": 1.7452,
      "step": 320
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.9444444444444446e-05,
      "loss": 2.8437,
      "step": 330
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.925925925925926e-05,
      "loss": 2.381,
      "step": 340
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.9074074074074075e-05,
      "loss": 2.7739,
      "step": 350
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.888888888888889e-05,
      "loss": 1.9838,
      "step": 360
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.8703703703703704e-05,
      "loss": 2.6442,
      "step": 370
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.851851851851852e-05,
      "loss": 2.4327,
      "step": 380
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.8333333333333334e-05,
      "loss": 1.7824,
      "step": 390
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.814814814814815e-05,
      "loss": 2.5717,
      "step": 400
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.796296296296296e-05,
      "loss": 2.0453,
      "step": 410
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.7777777777777784e-05,
      "loss": 0.9527,
      "step": 420
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.759259259259259e-05,
      "loss": 1.9192,
      "step": 430
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.740740740740741e-05,
      "loss": 1.8401,
      "step": 440
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.722222222222222e-05,
      "loss": 1.7712,
      "step": 450
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.703703703703704e-05,
      "loss": 1.7476,
      "step": 460
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.685185185185185e-05,
      "loss": 3.8317,
      "step": 470
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.8526,
      "step": 480
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.648148148148148e-05,
      "loss": 1.9277,
      "step": 490
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.62962962962963e-05,
      "loss": 1.5954,
      "step": 500
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.6111111111111115e-05,
      "loss": 1.4111,
      "step": 510
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.592592592592593e-05,
      "loss": 2.5728,
      "step": 520
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.5740740740740745e-05,
      "loss": 2.1665,
      "step": 530
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.555555555555556e-05,
      "loss": 1.7534,
      "step": 540
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.5370370370370374e-05,
      "loss": 2.4386,
      "step": 550
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.518518518518519e-05,
      "loss": 1.9791,
      "step": 560
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.5e-05,
      "loss": 2.5686,
      "step": 570
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.481481481481482e-05,
      "loss": 1.7416,
      "step": 580
    },
    {
      "epoch": 1.1,
      "learning_rate": 4.462962962962963e-05,
      "loss": 2.3083,
      "step": 590
    },
    {
      "epoch": 1.1,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 2.1452,
      "step": 600
    },
    {
      "epoch": 1.1,
      "eval_accuracy": 0.37583892617449666,
      "eval_loss": 2.0348801612854004,
      "eval_runtime": 11.9169,
      "eval_samples_per_second": 12.503,
      "eval_steps_per_second": 12.503,
      "step": 600
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.425925925925926e-05,
      "loss": 2.1612,
      "step": 610
    },
    {
      "epoch": 2.01,
      "learning_rate": 4.4074074074074076e-05,
      "loss": 2.1526,
      "step": 620
    },
    {
      "epoch": 2.01,
      "learning_rate": 4.388888888888889e-05,
      "loss": 2.0271,
      "step": 630
    },
    {
      "epoch": 2.01,
      "learning_rate": 4.3703703703703705e-05,
      "loss": 0.9482,
      "step": 640
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.351851851851852e-05,
      "loss": 2.8068,
      "step": 650
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 1.6808,
      "step": 660
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.314814814814815e-05,
      "loss": 3.8616,
      "step": 670
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.296296296296296e-05,
      "loss": 0.9547,
      "step": 680
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.277777777777778e-05,
      "loss": 1.786,
      "step": 690
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.259259259259259e-05,
      "loss": 2.885,
      "step": 700
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.240740740740741e-05,
      "loss": 1.6305,
      "step": 710
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.222222222222222e-05,
      "loss": 2.182,
      "step": 720
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.203703703703704e-05,
      "loss": 2.5439,
      "step": 730
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.185185185185185e-05,
      "loss": 1.4649,
      "step": 740
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.6346,
      "step": 750
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.148148148148148e-05,
      "loss": 2.7063,
      "step": 760
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.12962962962963e-05,
      "loss": 1.6567,
      "step": 770
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.111111111111111e-05,
      "loss": 2.4469,
      "step": 780
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.092592592592593e-05,
      "loss": 0.9031,
      "step": 790
    },
    {
      "epoch": 2.07,
      "learning_rate": 4.074074074074074e-05,
      "loss": 1.6897,
      "step": 800
    },
    {
      "epoch": 2.07,
      "learning_rate": 4.055555555555556e-05,
      "loss": 2.0307,
      "step": 810
    },
    {
      "epoch": 2.07,
      "learning_rate": 4.0370370370370374e-05,
      "loss": 2.1667,
      "step": 820
    },
    {
      "epoch": 2.08,
      "learning_rate": 4.018518518518519e-05,
      "loss": 0.8811,
      "step": 830
    },
    {
      "epoch": 2.08,
      "learning_rate": 4e-05,
      "loss": 2.7105,
      "step": 840
    },
    {
      "epoch": 2.08,
      "learning_rate": 3.981481481481482e-05,
      "loss": 2.8756,
      "step": 850
    },
    {
      "epoch": 2.09,
      "learning_rate": 3.962962962962963e-05,
      "loss": 1.3152,
      "step": 860
    },
    {
      "epoch": 2.09,
      "learning_rate": 3.944444444444445e-05,
      "loss": 1.4837,
      "step": 870
    },
    {
      "epoch": 2.09,
      "learning_rate": 3.925925925925926e-05,
      "loss": 2.2555,
      "step": 880
    },
    {
      "epoch": 2.1,
      "learning_rate": 3.9074074074074076e-05,
      "loss": 1.9877,
      "step": 890
    },
    {
      "epoch": 2.1,
      "learning_rate": 3.888888888888889e-05,
      "loss": 2.156,
      "step": 900
    },
    {
      "epoch": 2.1,
      "eval_accuracy": 0.2751677852348993,
      "eval_loss": 1.9145618677139282,
      "eval_runtime": 11.9012,
      "eval_samples_per_second": 12.52,
      "eval_steps_per_second": 12.52,
      "step": 900
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.8703703703703705e-05,
      "loss": 1.5921,
      "step": 910
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.851851851851852e-05,
      "loss": 1.7994,
      "step": 920
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.8333333333333334e-05,
      "loss": 2.6093,
      "step": 930
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.814814814814815e-05,
      "loss": 1.5036,
      "step": 940
    },
    {
      "epoch": 3.02,
      "learning_rate": 3.7962962962962964e-05,
      "loss": 1.6625,
      "step": 950
    },
    {
      "epoch": 3.02,
      "learning_rate": 3.777777777777778e-05,
      "loss": 1.7184,
      "step": 960
    },
    {
      "epoch": 3.02,
      "learning_rate": 3.759259259259259e-05,
      "loss": 1.3917,
      "step": 970
    },
    {
      "epoch": 3.03,
      "learning_rate": 3.740740740740741e-05,
      "loss": 1.2039,
      "step": 980
    },
    {
      "epoch": 3.03,
      "learning_rate": 3.722222222222222e-05,
      "loss": 0.7643,
      "step": 990
    },
    {
      "epoch": 3.03,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 2.1679,
      "step": 1000
    },
    {
      "epoch": 3.04,
      "learning_rate": 3.685185185185185e-05,
      "loss": 1.7749,
      "step": 1010
    },
    {
      "epoch": 3.04,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 2.1065,
      "step": 1020
    },
    {
      "epoch": 3.04,
      "learning_rate": 3.648148148148148e-05,
      "loss": 1.6983,
      "step": 1030
    },
    {
      "epoch": 3.05,
      "learning_rate": 3.62962962962963e-05,
      "loss": 1.1671,
      "step": 1040
    },
    {
      "epoch": 3.05,
      "learning_rate": 3.611111111111111e-05,
      "loss": 3.9637,
      "step": 1050
    },
    {
      "epoch": 3.05,
      "learning_rate": 3.592592592592593e-05,
      "loss": 1.8483,
      "step": 1060
    },
    {
      "epoch": 3.06,
      "learning_rate": 3.574074074074074e-05,
      "loss": 1.6249,
      "step": 1070
    },
    {
      "epoch": 3.06,
      "learning_rate": 3.555555555555556e-05,
      "loss": 4.3664,
      "step": 1080
    },
    {
      "epoch": 3.06,
      "learning_rate": 3.537037037037037e-05,
      "loss": 1.3076,
      "step": 1090
    },
    {
      "epoch": 3.07,
      "learning_rate": 3.518518518518519e-05,
      "loss": 1.6146,
      "step": 1100
    },
    {
      "epoch": 3.07,
      "learning_rate": 3.5e-05,
      "loss": 2.7497,
      "step": 1110
    },
    {
      "epoch": 3.07,
      "learning_rate": 3.481481481481482e-05,
      "loss": 1.2038,
      "step": 1120
    },
    {
      "epoch": 3.08,
      "learning_rate": 3.4629629629629626e-05,
      "loss": 1.6241,
      "step": 1130
    },
    {
      "epoch": 3.08,
      "learning_rate": 3.444444444444445e-05,
      "loss": 1.3569,
      "step": 1140
    },
    {
      "epoch": 3.08,
      "learning_rate": 3.425925925925926e-05,
      "loss": 1.6633,
      "step": 1150
    },
    {
      "epoch": 3.09,
      "learning_rate": 3.4074074074074077e-05,
      "loss": 1.2731,
      "step": 1160
    },
    {
      "epoch": 3.09,
      "learning_rate": 3.388888888888889e-05,
      "loss": 0.6022,
      "step": 1170
    },
    {
      "epoch": 3.09,
      "learning_rate": 3.3703703703703706e-05,
      "loss": 0.8256,
      "step": 1180
    },
    {
      "epoch": 3.1,
      "learning_rate": 3.351851851851852e-05,
      "loss": 1.4921,
      "step": 1190
    },
    {
      "epoch": 3.1,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7848,
      "step": 1200
    },
    {
      "epoch": 3.1,
      "eval_accuracy": 0.2550335570469799,
      "eval_loss": 2.933370590209961,
      "eval_runtime": 11.7529,
      "eval_samples_per_second": 12.678,
      "eval_steps_per_second": 12.678,
      "step": 1200
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.314814814814815e-05,
      "loss": 2.8528,
      "step": 1210
    },
    {
      "epoch": 4.01,
      "learning_rate": 3.2962962962962964e-05,
      "loss": 2.5306,
      "step": 1220
    },
    {
      "epoch": 4.01,
      "learning_rate": 3.277777777777778e-05,
      "loss": 1.8899,
      "step": 1230
    },
    {
      "epoch": 4.01,
      "learning_rate": 3.25925925925926e-05,
      "loss": 0.9383,
      "step": 1240
    },
    {
      "epoch": 4.02,
      "learning_rate": 3.240740740740741e-05,
      "loss": 1.5755,
      "step": 1250
    },
    {
      "epoch": 4.02,
      "learning_rate": 3.222222222222223e-05,
      "loss": 1.2614,
      "step": 1260
    },
    {
      "epoch": 4.02,
      "learning_rate": 3.203703703703704e-05,
      "loss": 2.0738,
      "step": 1270
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.185185185185185e-05,
      "loss": 1.7824,
      "step": 1280
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.1666666666666666e-05,
      "loss": 0.779,
      "step": 1290
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.148148148148148e-05,
      "loss": 4.432,
      "step": 1300
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.1296296296296295e-05,
      "loss": 1.934,
      "step": 1310
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.111111111111111e-05,
      "loss": 2.0968,
      "step": 1320
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.0925925925925924e-05,
      "loss": 1.7849,
      "step": 1330
    },
    {
      "epoch": 4.05,
      "learning_rate": 3.074074074074074e-05,
      "loss": 1.3378,
      "step": 1340
    },
    {
      "epoch": 4.05,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.8933,
      "step": 1350
    },
    {
      "epoch": 4.05,
      "learning_rate": 3.037037037037037e-05,
      "loss": 0.8768,
      "step": 1360
    },
    {
      "epoch": 4.06,
      "learning_rate": 3.018518518518519e-05,
      "loss": 1.1746,
      "step": 1370
    },
    {
      "epoch": 4.06,
      "learning_rate": 3e-05,
      "loss": 2.3593,
      "step": 1380
    },
    {
      "epoch": 4.06,
      "learning_rate": 2.981481481481482e-05,
      "loss": 2.9821,
      "step": 1390
    },
    {
      "epoch": 4.07,
      "learning_rate": 2.962962962962963e-05,
      "loss": 2.0901,
      "step": 1400
    },
    {
      "epoch": 4.07,
      "learning_rate": 2.9444444444444448e-05,
      "loss": 1.8877,
      "step": 1410
    },
    {
      "epoch": 4.07,
      "learning_rate": 2.925925925925926e-05,
      "loss": 1.3303,
      "step": 1420
    },
    {
      "epoch": 4.08,
      "learning_rate": 2.9074074074074077e-05,
      "loss": 1.0231,
      "step": 1430
    },
    {
      "epoch": 4.08,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 1.271,
      "step": 1440
    },
    {
      "epoch": 4.08,
      "learning_rate": 2.8703703703703706e-05,
      "loss": 1.4303,
      "step": 1450
    },
    {
      "epoch": 4.09,
      "learning_rate": 2.851851851851852e-05,
      "loss": 1.4579,
      "step": 1460
    },
    {
      "epoch": 4.09,
      "learning_rate": 2.8333333333333335e-05,
      "loss": 1.1311,
      "step": 1470
    },
    {
      "epoch": 4.09,
      "learning_rate": 2.814814814814815e-05,
      "loss": 1.2384,
      "step": 1480
    },
    {
      "epoch": 4.1,
      "learning_rate": 2.7962962962962965e-05,
      "loss": 1.3813,
      "step": 1490
    },
    {
      "epoch": 4.1,
      "learning_rate": 2.777777777777778e-05,
      "loss": 3.2405,
      "step": 1500
    },
    {
      "epoch": 4.1,
      "eval_accuracy": 0.35570469798657717,
      "eval_loss": 2.689954996109009,
      "eval_runtime": 11.9635,
      "eval_samples_per_second": 12.455,
      "eval_steps_per_second": 12.455,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "learning_rate": 2.7592592592592594e-05,
      "loss": 1.1833,
      "step": 1510
    },
    {
      "epoch": 5.01,
      "learning_rate": 2.7407407407407408e-05,
      "loss": 0.7545,
      "step": 1520
    },
    {
      "epoch": 5.01,
      "learning_rate": 2.7222222222222223e-05,
      "loss": 0.6151,
      "step": 1530
    },
    {
      "epoch": 5.01,
      "learning_rate": 2.7037037037037037e-05,
      "loss": 1.5773,
      "step": 1540
    },
    {
      "epoch": 5.02,
      "learning_rate": 2.6851851851851855e-05,
      "loss": 0.6904,
      "step": 1550
    },
    {
      "epoch": 5.02,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.0375,
      "step": 1560
    },
    {
      "epoch": 5.02,
      "learning_rate": 2.6481481481481485e-05,
      "loss": 1.0612,
      "step": 1570
    },
    {
      "epoch": 5.03,
      "learning_rate": 2.6296296296296296e-05,
      "loss": 1.7255,
      "step": 1580
    },
    {
      "epoch": 5.03,
      "learning_rate": 2.6111111111111114e-05,
      "loss": 1.8048,
      "step": 1590
    },
    {
      "epoch": 5.03,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.8129,
      "step": 1600
    },
    {
      "epoch": 5.04,
      "learning_rate": 2.5740740740740743e-05,
      "loss": 2.9754,
      "step": 1610
    },
    {
      "epoch": 5.04,
      "learning_rate": 2.5555555555555554e-05,
      "loss": 1.661,
      "step": 1620
    },
    {
      "epoch": 5.04,
      "learning_rate": 2.5370370370370372e-05,
      "loss": 1.0065,
      "step": 1630
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.5185185185185183e-05,
      "loss": 1.6616,
      "step": 1640
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.5e-05,
      "loss": 1.8583,
      "step": 1650
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.4814814814814816e-05,
      "loss": 0.9394,
      "step": 1660
    },
    {
      "epoch": 5.06,
      "learning_rate": 2.462962962962963e-05,
      "loss": 0.7979,
      "step": 1670
    },
    {
      "epoch": 5.06,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 2.1306,
      "step": 1680
    },
    {
      "epoch": 5.06,
      "learning_rate": 2.425925925925926e-05,
      "loss": 1.2191,
      "step": 1690
    },
    {
      "epoch": 5.07,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.7189,
      "step": 1700
    },
    {
      "epoch": 5.07,
      "learning_rate": 2.3888888888888892e-05,
      "loss": 2.9497,
      "step": 1710
    },
    {
      "epoch": 5.07,
      "learning_rate": 2.3703703703703707e-05,
      "loss": 1.1491,
      "step": 1720
    },
    {
      "epoch": 5.08,
      "learning_rate": 2.351851851851852e-05,
      "loss": 3.3826,
      "step": 1730
    },
    {
      "epoch": 5.08,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 1.846,
      "step": 1740
    },
    {
      "epoch": 5.08,
      "learning_rate": 2.314814814814815e-05,
      "loss": 1.1924,
      "step": 1750
    },
    {
      "epoch": 5.09,
      "learning_rate": 2.2962962962962965e-05,
      "loss": 1.1331,
      "step": 1760
    },
    {
      "epoch": 5.09,
      "learning_rate": 2.277777777777778e-05,
      "loss": 1.4474,
      "step": 1770
    },
    {
      "epoch": 5.09,
      "learning_rate": 2.2592592592592594e-05,
      "loss": 1.565,
      "step": 1780
    },
    {
      "epoch": 5.1,
      "learning_rate": 2.240740740740741e-05,
      "loss": 2.0442,
      "step": 1790
    },
    {
      "epoch": 5.1,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 2.6131,
      "step": 1800
    },
    {
      "epoch": 5.1,
      "eval_accuracy": 0.3691275167785235,
      "eval_loss": 2.5973401069641113,
      "eval_runtime": 11.8379,
      "eval_samples_per_second": 12.587,
      "eval_steps_per_second": 12.587,
      "step": 1800
    },
    {
      "epoch": 6.0,
      "learning_rate": 2.2037037037037038e-05,
      "loss": 1.1066,
      "step": 1810
    },
    {
      "epoch": 6.01,
      "learning_rate": 2.1851851851851852e-05,
      "loss": 1.4162,
      "step": 1820
    },
    {
      "epoch": 6.01,
      "learning_rate": 2.1666666666666667e-05,
      "loss": 1.5759,
      "step": 1830
    },
    {
      "epoch": 6.01,
      "learning_rate": 2.148148148148148e-05,
      "loss": 2.3782,
      "step": 1840
    },
    {
      "epoch": 6.02,
      "learning_rate": 2.1296296296296296e-05,
      "loss": 0.8711,
      "step": 1850
    },
    {
      "epoch": 6.02,
      "learning_rate": 2.111111111111111e-05,
      "loss": 0.997,
      "step": 1860
    },
    {
      "epoch": 6.02,
      "learning_rate": 2.0925925925925925e-05,
      "loss": 1.8742,
      "step": 1870
    },
    {
      "epoch": 6.03,
      "learning_rate": 2.074074074074074e-05,
      "loss": 1.3593,
      "step": 1880
    },
    {
      "epoch": 6.03,
      "learning_rate": 2.0555555555555555e-05,
      "loss": 1.1478,
      "step": 1890
    },
    {
      "epoch": 6.03,
      "learning_rate": 2.037037037037037e-05,
      "loss": 1.1945,
      "step": 1900
    },
    {
      "epoch": 6.04,
      "learning_rate": 2.0185185185185187e-05,
      "loss": 1.4263,
      "step": 1910
    },
    {
      "epoch": 6.04,
      "learning_rate": 2e-05,
      "loss": 0.8273,
      "step": 1920
    },
    {
      "epoch": 6.04,
      "learning_rate": 1.9814814814814816e-05,
      "loss": 1.0158,
      "step": 1930
    },
    {
      "epoch": 6.05,
      "learning_rate": 1.962962962962963e-05,
      "loss": 0.6081,
      "step": 1940
    },
    {
      "epoch": 6.05,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 2.2851,
      "step": 1950
    },
    {
      "epoch": 6.05,
      "learning_rate": 1.925925925925926e-05,
      "loss": 1.5421,
      "step": 1960
    },
    {
      "epoch": 6.06,
      "learning_rate": 1.9074074074074075e-05,
      "loss": 1.5585,
      "step": 1970
    },
    {
      "epoch": 6.06,
      "learning_rate": 1.888888888888889e-05,
      "loss": 1.721,
      "step": 1980
    },
    {
      "epoch": 6.06,
      "learning_rate": 1.8703703703703704e-05,
      "loss": 0.8218,
      "step": 1990
    },
    {
      "epoch": 6.07,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.8604,
      "step": 2000
    },
    {
      "epoch": 6.07,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 1.4615,
      "step": 2010
    },
    {
      "epoch": 6.07,
      "learning_rate": 1.814814814814815e-05,
      "loss": 0.4951,
      "step": 2020
    },
    {
      "epoch": 6.08,
      "learning_rate": 1.7962962962962965e-05,
      "loss": 1.5857,
      "step": 2030
    },
    {
      "epoch": 6.08,
      "learning_rate": 1.777777777777778e-05,
      "loss": 0.1666,
      "step": 2040
    },
    {
      "epoch": 6.08,
      "learning_rate": 1.7592592592592595e-05,
      "loss": 0.3136,
      "step": 2050
    },
    {
      "epoch": 6.09,
      "learning_rate": 1.740740740740741e-05,
      "loss": 0.5031,
      "step": 2060
    },
    {
      "epoch": 6.09,
      "learning_rate": 1.7222222222222224e-05,
      "loss": 1.0772,
      "step": 2070
    },
    {
      "epoch": 6.09,
      "learning_rate": 1.7037037037037038e-05,
      "loss": 1.581,
      "step": 2080
    },
    {
      "epoch": 6.1,
      "learning_rate": 1.6851851851851853e-05,
      "loss": 1.8657,
      "step": 2090
    },
    {
      "epoch": 6.1,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.5998,
      "step": 2100
    },
    {
      "epoch": 6.1,
      "eval_accuracy": 0.42953020134228187,
      "eval_loss": 3.1545114517211914,
      "eval_runtime": 11.9443,
      "eval_samples_per_second": 12.475,
      "eval_steps_per_second": 12.475,
      "step": 2100
    },
    {
      "epoch": 7.0,
      "learning_rate": 1.6481481481481482e-05,
      "loss": 1.1743,
      "step": 2110
    },
    {
      "epoch": 7.01,
      "learning_rate": 1.62962962962963e-05,
      "loss": 0.6246,
      "step": 2120
    },
    {
      "epoch": 7.01,
      "learning_rate": 1.6111111111111115e-05,
      "loss": 1.1438,
      "step": 2130
    },
    {
      "epoch": 7.01,
      "learning_rate": 1.5925925925925926e-05,
      "loss": 1.7971,
      "step": 2140
    },
    {
      "epoch": 7.02,
      "learning_rate": 1.574074074074074e-05,
      "loss": 2.8378,
      "step": 2150
    },
    {
      "epoch": 7.02,
      "learning_rate": 1.5555555555555555e-05,
      "loss": 0.6635,
      "step": 2160
    },
    {
      "epoch": 7.02,
      "learning_rate": 1.537037037037037e-05,
      "loss": 0.7129,
      "step": 2170
    },
    {
      "epoch": 7.03,
      "learning_rate": 1.5185185185185186e-05,
      "loss": 1.2923,
      "step": 2180
    },
    {
      "epoch": 7.03,
      "learning_rate": 1.5e-05,
      "loss": 0.9154,
      "step": 2190
    },
    {
      "epoch": 7.03,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 1.2448,
      "step": 2200
    },
    {
      "epoch": 7.04,
      "learning_rate": 1.462962962962963e-05,
      "loss": 1.1172,
      "step": 2210
    },
    {
      "epoch": 7.04,
      "learning_rate": 1.4444444444444444e-05,
      "loss": 2.2937,
      "step": 2220
    },
    {
      "epoch": 7.04,
      "learning_rate": 1.425925925925926e-05,
      "loss": 0.7835,
      "step": 2230
    },
    {
      "epoch": 7.05,
      "learning_rate": 1.4074074074074075e-05,
      "loss": 0.0882,
      "step": 2240
    },
    {
      "epoch": 7.05,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.2712,
      "step": 2250
    },
    {
      "epoch": 7.05,
      "learning_rate": 1.3703703703703704e-05,
      "loss": 2.0246,
      "step": 2260
    },
    {
      "epoch": 7.06,
      "learning_rate": 1.3518518518518519e-05,
      "loss": 0.2939,
      "step": 2270
    },
    {
      "epoch": 7.06,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.2676,
      "step": 2280
    },
    {
      "epoch": 7.06,
      "learning_rate": 1.3148148148148148e-05,
      "loss": 2.1027,
      "step": 2290
    },
    {
      "epoch": 7.07,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 1.2775,
      "step": 2300
    },
    {
      "epoch": 7.07,
      "learning_rate": 1.2777777777777777e-05,
      "loss": 2.663,
      "step": 2310
    },
    {
      "epoch": 7.07,
      "learning_rate": 1.2592592592592592e-05,
      "loss": 0.8683,
      "step": 2320
    },
    {
      "epoch": 7.08,
      "learning_rate": 1.2407407407407408e-05,
      "loss": 1.361,
      "step": 2330
    },
    {
      "epoch": 7.08,
      "learning_rate": 1.2222222222222222e-05,
      "loss": 2.4195,
      "step": 2340
    },
    {
      "epoch": 7.08,
      "learning_rate": 1.2037037037037037e-05,
      "loss": 1.2075,
      "step": 2350
    },
    {
      "epoch": 7.09,
      "learning_rate": 1.1851851851851853e-05,
      "loss": 2.6057,
      "step": 2360
    },
    {
      "epoch": 7.09,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 1.0114,
      "step": 2370
    },
    {
      "epoch": 7.09,
      "learning_rate": 1.1481481481481482e-05,
      "loss": 1.1405,
      "step": 2380
    },
    {
      "epoch": 7.1,
      "learning_rate": 1.1296296296296297e-05,
      "loss": 0.8811,
      "step": 2390
    },
    {
      "epoch": 7.1,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 1.1689,
      "step": 2400
    },
    {
      "epoch": 7.1,
      "eval_accuracy": 0.2953020134228188,
      "eval_loss": 3.3012382984161377,
      "eval_runtime": 11.9208,
      "eval_samples_per_second": 12.499,
      "eval_steps_per_second": 12.499,
      "step": 2400
    },
    {
      "epoch": 8.0,
      "learning_rate": 1.0925925925925926e-05,
      "loss": 1.3559,
      "step": 2410
    },
    {
      "epoch": 8.01,
      "learning_rate": 1.074074074074074e-05,
      "loss": 0.6597,
      "step": 2420
    },
    {
      "epoch": 8.01,
      "learning_rate": 1.0555555555555555e-05,
      "loss": 1.0085,
      "step": 2430
    },
    {
      "epoch": 8.01,
      "learning_rate": 1.037037037037037e-05,
      "loss": 0.5666,
      "step": 2440
    },
    {
      "epoch": 8.02,
      "learning_rate": 1.0185185185185185e-05,
      "loss": 0.1961,
      "step": 2450
    },
    {
      "epoch": 8.02,
      "learning_rate": 1e-05,
      "loss": 1.4929,
      "step": 2460
    },
    {
      "epoch": 8.02,
      "learning_rate": 9.814814814814815e-06,
      "loss": 1.2987,
      "step": 2470
    },
    {
      "epoch": 8.03,
      "learning_rate": 9.62962962962963e-06,
      "loss": 1.113,
      "step": 2480
    },
    {
      "epoch": 8.03,
      "learning_rate": 9.444444444444445e-06,
      "loss": 2.0659,
      "step": 2490
    },
    {
      "epoch": 8.03,
      "learning_rate": 9.259259259259259e-06,
      "loss": 1.2915,
      "step": 2500
    },
    {
      "epoch": 8.04,
      "learning_rate": 9.074074074074075e-06,
      "loss": 1.2701,
      "step": 2510
    },
    {
      "epoch": 8.04,
      "learning_rate": 8.88888888888889e-06,
      "loss": 1.2432,
      "step": 2520
    },
    {
      "epoch": 8.04,
      "learning_rate": 8.703703703703705e-06,
      "loss": 0.7502,
      "step": 2530
    },
    {
      "epoch": 8.05,
      "learning_rate": 8.518518518518519e-06,
      "loss": 0.6665,
      "step": 2540
    },
    {
      "epoch": 8.05,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.2312,
      "step": 2550
    },
    {
      "epoch": 8.05,
      "learning_rate": 8.14814814814815e-06,
      "loss": 0.4243,
      "step": 2560
    },
    {
      "epoch": 8.06,
      "learning_rate": 7.962962962962963e-06,
      "loss": 0.8543,
      "step": 2570
    },
    {
      "epoch": 8.06,
      "learning_rate": 7.777777777777777e-06,
      "loss": 2.307,
      "step": 2580
    },
    {
      "epoch": 8.06,
      "learning_rate": 7.592592592592593e-06,
      "loss": 1.0244,
      "step": 2590
    },
    {
      "epoch": 8.07,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.9076,
      "step": 2600
    },
    {
      "epoch": 8.07,
      "learning_rate": 7.222222222222222e-06,
      "loss": 0.6468,
      "step": 2610
    },
    {
      "epoch": 8.07,
      "learning_rate": 7.0370370370370375e-06,
      "loss": 0.8508,
      "step": 2620
    },
    {
      "epoch": 8.08,
      "learning_rate": 6.851851851851852e-06,
      "loss": 0.118,
      "step": 2630
    },
    {
      "epoch": 8.08,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.6374,
      "step": 2640
    },
    {
      "epoch": 8.08,
      "learning_rate": 6.481481481481481e-06,
      "loss": 0.6333,
      "step": 2650
    },
    {
      "epoch": 8.09,
      "learning_rate": 6.296296296296296e-06,
      "loss": 2.5795,
      "step": 2660
    },
    {
      "epoch": 8.09,
      "learning_rate": 6.111111111111111e-06,
      "loss": 2.5085,
      "step": 2670
    },
    {
      "epoch": 8.09,
      "learning_rate": 5.925925925925927e-06,
      "loss": 1.2708,
      "step": 2680
    },
    {
      "epoch": 8.1,
      "learning_rate": 5.740740740740741e-06,
      "loss": 0.1959,
      "step": 2690
    },
    {
      "epoch": 8.1,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.2398,
      "step": 2700
    },
    {
      "epoch": 8.1,
      "eval_accuracy": 0.436241610738255,
      "eval_loss": 2.723142385482788,
      "eval_runtime": 11.9115,
      "eval_samples_per_second": 12.509,
      "eval_steps_per_second": 12.509,
      "step": 2700
    },
    {
      "epoch": 9.0,
      "learning_rate": 5.37037037037037e-06,
      "loss": 0.6692,
      "step": 2710
    },
    {
      "epoch": 9.01,
      "learning_rate": 5.185185185185185e-06,
      "loss": 0.4314,
      "step": 2720
    },
    {
      "epoch": 9.01,
      "learning_rate": 5e-06,
      "loss": 1.6368,
      "step": 2730
    },
    {
      "epoch": 9.01,
      "learning_rate": 4.814814814814815e-06,
      "loss": 0.4331,
      "step": 2740
    },
    {
      "epoch": 9.02,
      "learning_rate": 4.6296296296296296e-06,
      "loss": 0.5237,
      "step": 2750
    },
    {
      "epoch": 9.02,
      "learning_rate": 4.444444444444445e-06,
      "loss": 1.5999,
      "step": 2760
    },
    {
      "epoch": 9.02,
      "learning_rate": 4.2592592592592596e-06,
      "loss": 1.7222,
      "step": 2770
    },
    {
      "epoch": 9.03,
      "learning_rate": 4.074074074074075e-06,
      "loss": 0.5853,
      "step": 2780
    },
    {
      "epoch": 9.03,
      "learning_rate": 3.888888888888889e-06,
      "loss": 1.5566,
      "step": 2790
    },
    {
      "epoch": 9.03,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.5217,
      "step": 2800
    },
    {
      "epoch": 9.04,
      "learning_rate": 3.5185185185185187e-06,
      "loss": 0.373,
      "step": 2810
    },
    {
      "epoch": 9.04,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.9443,
      "step": 2820
    },
    {
      "epoch": 9.04,
      "learning_rate": 3.148148148148148e-06,
      "loss": 0.2011,
      "step": 2830
    },
    {
      "epoch": 9.05,
      "learning_rate": 2.9629629629629633e-06,
      "loss": 0.6479,
      "step": 2840
    },
    {
      "epoch": 9.05,
      "learning_rate": 2.777777777777778e-06,
      "loss": 1.0128,
      "step": 2850
    },
    {
      "epoch": 9.05,
      "learning_rate": 2.5925925925925925e-06,
      "loss": 1.3453,
      "step": 2860
    },
    {
      "epoch": 9.06,
      "learning_rate": 2.4074074074074075e-06,
      "loss": 1.9262,
      "step": 2870
    },
    {
      "epoch": 9.06,
      "learning_rate": 2.2222222222222225e-06,
      "loss": 0.9785,
      "step": 2880
    },
    {
      "epoch": 9.06,
      "learning_rate": 2.0370370370370375e-06,
      "loss": 0.6525,
      "step": 2890
    },
    {
      "epoch": 9.07,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.6206,
      "step": 2900
    },
    {
      "epoch": 9.07,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.7492,
      "step": 2910
    },
    {
      "epoch": 9.07,
      "learning_rate": 1.4814814814814817e-06,
      "loss": 1.004,
      "step": 2920
    },
    {
      "epoch": 9.08,
      "learning_rate": 1.2962962962962962e-06,
      "loss": 2.0529,
      "step": 2930
    },
    {
      "epoch": 9.08,
      "learning_rate": 1.1111111111111112e-06,
      "loss": 1.3948,
      "step": 2940
    },
    {
      "epoch": 9.08,
      "learning_rate": 9.259259259259259e-07,
      "loss": 1.0218,
      "step": 2950
    },
    {
      "epoch": 9.09,
      "learning_rate": 7.407407407407408e-07,
      "loss": 1.5455,
      "step": 2960
    },
    {
      "epoch": 9.09,
      "learning_rate": 5.555555555555556e-07,
      "loss": 0.1965,
      "step": 2970
    },
    {
      "epoch": 9.09,
      "learning_rate": 3.703703703703704e-07,
      "loss": 0.3648,
      "step": 2980
    },
    {
      "epoch": 9.1,
      "learning_rate": 1.851851851851852e-07,
      "loss": 0.4616,
      "step": 2990
    },
    {
      "epoch": 9.1,
      "learning_rate": 0.0,
      "loss": 1.2448,
      "step": 3000
    },
    {
      "epoch": 9.1,
      "eval_accuracy": 0.42953020134228187,
      "eval_loss": 2.694873809814453,
      "eval_runtime": 11.9402,
      "eval_samples_per_second": 12.479,
      "eval_steps_per_second": 12.479,
      "step": 3000
    },
    {
      "epoch": 9.1,
      "step": 3000,
      "total_flos": 2.635076136075264e+18,
      "train_loss": 1.5726345704197884,
      "train_runtime": 705.2236,
      "train_samples_per_second": 4.254,
      "train_steps_per_second": 4.254
    },
    {
      "epoch": 9.1,
      "eval_accuracy": 0.6005747126436781,
      "eval_loss": 1.64243745803833,
      "eval_runtime": 28.1079,
      "eval_samples_per_second": 12.381,
      "eval_steps_per_second": 12.381,
      "step": 3000
    },
    {
      "epoch": 9.1,
      "eval_accuracy": 0.5994236311239193,
      "eval_loss": 1.647168755531311,
      "eval_runtime": 27.7986,
      "eval_samples_per_second": 12.483,
      "eval_steps_per_second": 12.483,
      "step": 3000
    }
  ],
  "logging_steps": 10,
  "max_steps": 3000,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 2.635076136075264e+18,
  "trial_name": null,
  "trial_params": null
}