{
  "best_metric": 0.9714285714285714,
  "best_model_checkpoint": "videomae-small-finetuned-kinetics-finetuned-ucf101-subset/checkpoint-1200",
  "epoch": 3.25,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 15.566545486450195,
      "learning_rate": 4.166666666666667e-06,
      "loss": 2.3603,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 14.607881546020508,
      "learning_rate": 8.333333333333334e-06,
      "loss": 2.3165,
      "step": 20
    },
    {
      "epoch": 0.03,
      "grad_norm": 13.733409881591797,
      "learning_rate": 1.25e-05,
      "loss": 2.2965,
      "step": 30
    },
    {
      "epoch": 0.03,
      "grad_norm": 11.29304027557373,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.126,
      "step": 40
    },
    {
      "epoch": 0.04,
      "grad_norm": 9.99641227722168,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 2.2969,
      "step": 50
    },
    {
      "epoch": 0.05,
      "grad_norm": 10.398500442504883,
      "learning_rate": 2.5e-05,
      "loss": 2.2344,
      "step": 60
    },
    {
      "epoch": 0.06,
      "grad_norm": 19.230289459228516,
      "learning_rate": 2.916666666666667e-05,
      "loss": 2.0098,
      "step": 70
    },
    {
      "epoch": 0.07,
      "grad_norm": 19.157608032226562,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.0368,
      "step": 80
    },
    {
      "epoch": 0.07,
      "grad_norm": 16.360591888427734,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.8206,
      "step": 90
    },
    {
      "epoch": 0.08,
      "grad_norm": 20.42489242553711,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.8453,
      "step": 100
    },
    {
      "epoch": 0.09,
      "grad_norm": 24.402835845947266,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 1.8986,
      "step": 110
    },
    {
      "epoch": 0.1,
      "grad_norm": 17.82651710510254,
      "learning_rate": 5e-05,
      "loss": 1.6124,
      "step": 120
    },
    {
      "epoch": 0.11,
      "grad_norm": 18.78799819946289,
      "learning_rate": 4.9537037037037035e-05,
      "loss": 1.5551,
      "step": 130
    },
    {
      "epoch": 0.12,
      "grad_norm": 17.022598266601562,
      "learning_rate": 4.9074074074074075e-05,
      "loss": 1.503,
      "step": 140
    },
    {
      "epoch": 0.12,
      "grad_norm": 17.275959014892578,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 1.4129,
      "step": 150
    },
    {
      "epoch": 0.13,
      "grad_norm": 24.9034423828125,
      "learning_rate": 4.814814814814815e-05,
      "loss": 1.2563,
      "step": 160
    },
    {
      "epoch": 0.14,
      "grad_norm": 14.254481315612793,
      "learning_rate": 4.768518518518519e-05,
      "loss": 1.2807,
      "step": 170
    },
    {
      "epoch": 0.15,
      "grad_norm": 22.42249298095703,
      "learning_rate": 4.722222222222222e-05,
      "loss": 1.3364,
      "step": 180
    },
    {
      "epoch": 0.16,
      "grad_norm": 13.118966102600098,
      "learning_rate": 4.675925925925926e-05,
      "loss": 1.4398,
      "step": 190
    },
    {
      "epoch": 0.17,
      "grad_norm": 10.908171653747559,
      "learning_rate": 4.62962962962963e-05,
      "loss": 0.945,
      "step": 200
    },
    {
      "epoch": 0.17,
      "grad_norm": 10.181930541992188,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 1.2498,
      "step": 210
    },
    {
      "epoch": 0.18,
      "grad_norm": 20.386661529541016,
      "learning_rate": 4.5370370370370374e-05,
      "loss": 1.0773,
      "step": 220
    },
    {
      "epoch": 0.19,
      "grad_norm": 15.680155754089355,
      "learning_rate": 4.490740740740741e-05,
      "loss": 0.9573,
      "step": 230
    },
    {
      "epoch": 0.2,
      "grad_norm": 14.58272933959961,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.0516,
      "step": 240
    },
    {
      "epoch": 0.21,
      "grad_norm": 8.87700080871582,
      "learning_rate": 4.3981481481481486e-05,
      "loss": 0.9562,
      "step": 250
    },
    {
      "epoch": 0.22,
      "grad_norm": 10.340452194213867,
      "learning_rate": 4.351851851851852e-05,
      "loss": 0.832,
      "step": 260
    },
    {
      "epoch": 0.23,
      "grad_norm": 20.359683990478516,
      "learning_rate": 4.305555555555556e-05,
      "loss": 0.8898,
      "step": 270
    },
    {
      "epoch": 0.23,
      "grad_norm": 11.624580383300781,
      "learning_rate": 4.259259259259259e-05,
      "loss": 0.7074,
      "step": 280
    },
    {
      "epoch": 0.24,
      "grad_norm": 12.319985389709473,
      "learning_rate": 4.212962962962963e-05,
      "loss": 0.6718,
      "step": 290
    },
    {
      "epoch": 0.25,
      "grad_norm": 10.40351390838623,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.7637,
      "step": 300
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.9285714285714286,
      "eval_loss": 0.6597293615341187,
      "eval_runtime": 17.0748,
      "eval_samples_per_second": 4.1,
      "eval_steps_per_second": 4.1,
      "step": 300
    },
    {
      "epoch": 1.01,
      "grad_norm": 9.951855659484863,
      "learning_rate": 4.1203703703703705e-05,
      "loss": 0.7042,
      "step": 310
    },
    {
      "epoch": 1.02,
      "grad_norm": 9.25134563446045,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.3955,
      "step": 320
    },
    {
      "epoch": 1.02,
      "grad_norm": 25.354598999023438,
      "learning_rate": 4.027777777777778e-05,
      "loss": 0.6692,
      "step": 330
    },
    {
      "epoch": 1.03,
      "grad_norm": 9.671762466430664,
      "learning_rate": 3.981481481481482e-05,
      "loss": 0.5101,
      "step": 340
    },
    {
      "epoch": 1.04,
      "grad_norm": 2.988225221633911,
      "learning_rate": 3.935185185185186e-05,
      "loss": 0.3187,
      "step": 350
    },
    {
      "epoch": 1.05,
      "grad_norm": 6.8107829093933105,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.4615,
      "step": 360
    },
    {
      "epoch": 1.06,
      "grad_norm": 23.338829040527344,
      "learning_rate": 3.8425925925925924e-05,
      "loss": 0.3835,
      "step": 370
    },
    {
      "epoch": 1.07,
      "grad_norm": 7.323309421539307,
      "learning_rate": 3.7962962962962964e-05,
      "loss": 0.3547,
      "step": 380
    },
    {
      "epoch": 1.07,
      "grad_norm": 4.660543441772461,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.2491,
      "step": 390
    },
    {
      "epoch": 1.08,
      "grad_norm": 4.3633012771606445,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.2851,
      "step": 400
    },
    {
      "epoch": 1.09,
      "grad_norm": 5.248176097869873,
      "learning_rate": 3.6574074074074076e-05,
      "loss": 0.1751,
      "step": 410
    },
    {
      "epoch": 1.1,
      "grad_norm": 1.8538141250610352,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.4174,
      "step": 420
    },
    {
      "epoch": 1.11,
      "grad_norm": 3.1465137004852295,
      "learning_rate": 3.564814814814815e-05,
      "loss": 0.3802,
      "step": 430
    },
    {
      "epoch": 1.12,
      "grad_norm": 5.7329912185668945,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.2329,
      "step": 440
    },
    {
      "epoch": 1.12,
      "grad_norm": 37.63209915161133,
      "learning_rate": 3.472222222222222e-05,
      "loss": 0.3905,
      "step": 450
    },
    {
      "epoch": 1.13,
      "grad_norm": 4.17129373550415,
      "learning_rate": 3.425925925925926e-05,
      "loss": 0.5252,
      "step": 460
    },
    {
      "epoch": 1.14,
      "grad_norm": 5.6671462059021,
      "learning_rate": 3.3796296296296295e-05,
      "loss": 0.2377,
      "step": 470
    },
    {
      "epoch": 1.15,
      "grad_norm": 1.0317806005477905,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.5215,
      "step": 480
    },
    {
      "epoch": 1.16,
      "grad_norm": 4.563450813293457,
      "learning_rate": 3.2870370370370375e-05,
      "loss": 0.2337,
      "step": 490
    },
    {
      "epoch": 1.17,
      "grad_norm": 44.28984069824219,
      "learning_rate": 3.240740740740741e-05,
      "loss": 0.5828,
      "step": 500
    },
    {
      "epoch": 1.18,
      "grad_norm": 4.3612260818481445,
      "learning_rate": 3.194444444444444e-05,
      "loss": 0.1757,
      "step": 510
    },
    {
      "epoch": 1.18,
      "grad_norm": 3.157717227935791,
      "learning_rate": 3.148148148148148e-05,
      "loss": 0.2369,
      "step": 520
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.7239309549331665,
      "learning_rate": 3.101851851851852e-05,
      "loss": 0.378,
      "step": 530
    },
    {
      "epoch": 1.2,
      "grad_norm": 8.372401237487793,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.131,
      "step": 540
    },
    {
      "epoch": 1.21,
      "grad_norm": 1.4280123710632324,
      "learning_rate": 3.0092592592592593e-05,
      "loss": 0.1566,
      "step": 550
    },
    {
      "epoch": 1.22,
      "grad_norm": 1.6428464651107788,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.1315,
      "step": 560
    },
    {
      "epoch": 1.23,
      "grad_norm": 1.2491836547851562,
      "learning_rate": 2.916666666666667e-05,
      "loss": 0.3698,
      "step": 570
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.8162739872932434,
      "learning_rate": 2.8703703703703706e-05,
      "loss": 0.1631,
      "step": 580
    },
    {
      "epoch": 1.24,
      "grad_norm": 3.682142972946167,
      "learning_rate": 2.824074074074074e-05,
      "loss": 0.4162,
      "step": 590
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.344789981842041,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.512,
      "step": 600
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 0.9142857142857143,
      "eval_loss": 0.28013283014297485,
      "eval_runtime": 17.3712,
      "eval_samples_per_second": 4.03,
      "eval_steps_per_second": 4.03,
      "step": 600
    },
    {
      "epoch": 2.01,
      "grad_norm": 1.431007981300354,
      "learning_rate": 2.7314814814814816e-05,
      "loss": 0.104,
      "step": 610
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.896948516368866,
      "learning_rate": 2.6851851851851855e-05,
      "loss": 0.078,
      "step": 620
    },
    {
      "epoch": 2.02,
      "grad_norm": 4.150156021118164,
      "learning_rate": 2.6388888888888892e-05,
      "loss": 0.0748,
      "step": 630
    },
    {
      "epoch": 2.03,
      "grad_norm": 0.5186155438423157,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.0979,
      "step": 640
    },
    {
      "epoch": 2.04,
      "grad_norm": 4.285228252410889,
      "learning_rate": 2.5462962962962965e-05,
      "loss": 0.1827,
      "step": 650
    },
    {
      "epoch": 2.05,
      "grad_norm": 60.02833557128906,
      "learning_rate": 2.5e-05,
      "loss": 0.1822,
      "step": 660
    },
    {
      "epoch": 2.06,
      "grad_norm": 5.049980640411377,
      "learning_rate": 2.4537037037037038e-05,
      "loss": 0.0794,
      "step": 670
    },
    {
      "epoch": 2.07,
      "grad_norm": 7.939412593841553,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.0854,
      "step": 680
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.5244776606559753,
      "learning_rate": 2.361111111111111e-05,
      "loss": 0.0561,
      "step": 690
    },
    {
      "epoch": 2.08,
      "grad_norm": 1.540111780166626,
      "learning_rate": 2.314814814814815e-05,
      "loss": 0.3101,
      "step": 700
    },
    {
      "epoch": 2.09,
      "grad_norm": 1.268227458000183,
      "learning_rate": 2.2685185185185187e-05,
      "loss": 0.0772,
      "step": 710
    },
    {
      "epoch": 2.1,
      "grad_norm": 3.848170280456543,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0756,
      "step": 720
    },
    {
      "epoch": 2.11,
      "grad_norm": 0.4123232662677765,
      "learning_rate": 2.175925925925926e-05,
      "loss": 0.0551,
      "step": 730
    },
    {
      "epoch": 2.12,
      "grad_norm": 1.0512717962265015,
      "learning_rate": 2.1296296296296296e-05,
      "loss": 0.0531,
      "step": 740
    },
    {
      "epoch": 2.12,
      "grad_norm": 1.3583945035934448,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 0.0664,
      "step": 750
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.6737596988677979,
      "learning_rate": 2.037037037037037e-05,
      "loss": 0.047,
      "step": 760
    },
    {
      "epoch": 2.14,
      "grad_norm": 2.3283467292785645,
      "learning_rate": 1.990740740740741e-05,
      "loss": 0.0639,
      "step": 770
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.4911932945251465,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.0508,
      "step": 780
    },
    {
      "epoch": 2.16,
      "grad_norm": 12.502443313598633,
      "learning_rate": 1.8981481481481482e-05,
      "loss": 0.0937,
      "step": 790
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.463198721408844,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.0593,
      "step": 800
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.4377615749835968,
      "learning_rate": 1.8055555555555555e-05,
      "loss": 0.04,
      "step": 810
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.7480078339576721,
      "learning_rate": 1.7592592592592595e-05,
      "loss": 0.0491,
      "step": 820
    },
    {
      "epoch": 2.19,
      "grad_norm": 1.6011290550231934,
      "learning_rate": 1.712962962962963e-05,
      "loss": 0.0384,
      "step": 830
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.36971336603164673,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.1024,
      "step": 840
    },
    {
      "epoch": 2.21,
      "grad_norm": 1.1993064880371094,
      "learning_rate": 1.6203703703703704e-05,
      "loss": 0.0484,
      "step": 850
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.5378360152244568,
      "learning_rate": 1.574074074074074e-05,
      "loss": 0.0816,
      "step": 860
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.3339988589286804,
      "learning_rate": 1.527777777777778e-05,
      "loss": 0.0409,
      "step": 870
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.35232287645339966,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.05,
      "step": 880
    },
    {
      "epoch": 2.24,
      "grad_norm": 1.5304961204528809,
      "learning_rate": 1.4351851851851853e-05,
      "loss": 0.0407,
      "step": 890
    },
    {
      "epoch": 2.25,
      "grad_norm": 2.890812873840332,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.0404,
      "step": 900
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.4797164797782898,
      "eval_runtime": 19.7535,
      "eval_samples_per_second": 3.544,
      "eval_steps_per_second": 3.544,
      "step": 900
    },
    {
      "epoch": 3.01,
      "grad_norm": 0.30314165353775024,
      "learning_rate": 1.3425925925925928e-05,
      "loss": 0.0451,
      "step": 910
    },
    {
      "epoch": 3.02,
      "grad_norm": 0.8032521605491638,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 0.0301,
      "step": 920
    },
    {
      "epoch": 3.02,
      "grad_norm": 0.33515045046806335,
      "learning_rate": 1.25e-05,
      "loss": 0.0343,
      "step": 930
    },
    {
      "epoch": 3.03,
      "grad_norm": 2.0815067291259766,
      "learning_rate": 1.2037037037037037e-05,
      "loss": 0.041,
      "step": 940
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.49005648493766785,
      "learning_rate": 1.1574074074074075e-05,
      "loss": 0.0319,
      "step": 950
    },
    {
      "epoch": 3.05,
      "grad_norm": 0.4375312030315399,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0367,
      "step": 960
    },
    {
      "epoch": 3.06,
      "grad_norm": 0.27408626675605774,
      "learning_rate": 1.0648148148148148e-05,
      "loss": 0.0273,
      "step": 970
    },
    {
      "epoch": 3.07,
      "grad_norm": 0.2981482446193695,
      "learning_rate": 1.0185185185185185e-05,
      "loss": 0.0319,
      "step": 980
    },
    {
      "epoch": 3.08,
      "grad_norm": 0.4230247735977173,
      "learning_rate": 9.722222222222223e-06,
      "loss": 0.0338,
      "step": 990
    },
    {
      "epoch": 3.08,
      "grad_norm": 0.37668561935424805,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.256,
      "step": 1000
    },
    {
      "epoch": 3.09,
      "grad_norm": 2.5758321285247803,
      "learning_rate": 8.796296296296297e-06,
      "loss": 0.0417,
      "step": 1010
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.5381589531898499,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.038,
      "step": 1020
    },
    {
      "epoch": 3.11,
      "grad_norm": 0.45010364055633545,
      "learning_rate": 7.87037037037037e-06,
      "loss": 0.0422,
      "step": 1030
    },
    {
      "epoch": 3.12,
      "grad_norm": 0.579723596572876,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0264,
      "step": 1040
    },
    {
      "epoch": 3.12,
      "grad_norm": 0.37265080213546753,
      "learning_rate": 6.944444444444445e-06,
      "loss": 0.0289,
      "step": 1050
    },
    {
      "epoch": 3.13,
      "grad_norm": 0.85558021068573,
      "learning_rate": 6.481481481481481e-06,
      "loss": 0.0442,
      "step": 1060
    },
    {
      "epoch": 3.14,
      "grad_norm": 0.4955598711967468,
      "learning_rate": 6.0185185185185185e-06,
      "loss": 0.0429,
      "step": 1070
    },
    {
      "epoch": 3.15,
      "grad_norm": 0.3474845886230469,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.0323,
      "step": 1080
    },
    {
      "epoch": 3.16,
      "grad_norm": 1.5767329931259155,
      "learning_rate": 5.092592592592592e-06,
      "loss": 0.0352,
      "step": 1090
    },
    {
      "epoch": 3.17,
      "grad_norm": 0.396416574716568,
      "learning_rate": 4.6296296296296296e-06,
      "loss": 0.0256,
      "step": 1100
    },
    {
      "epoch": 3.17,
      "grad_norm": 0.38486164808273315,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.0286,
      "step": 1110
    },
    {
      "epoch": 3.18,
      "grad_norm": 0.31546345353126526,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.0593,
      "step": 1120
    },
    {
      "epoch": 3.19,
      "grad_norm": 0.4107477068901062,
      "learning_rate": 3.2407407407407406e-06,
      "loss": 0.03,
      "step": 1130
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.29505640268325806,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.0289,
      "step": 1140
    },
    {
      "epoch": 3.21,
      "grad_norm": 0.41277098655700684,
      "learning_rate": 2.3148148148148148e-06,
      "loss": 0.0355,
      "step": 1150
    },
    {
      "epoch": 3.22,
      "grad_norm": 0.515819787979126,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.0273,
      "step": 1160
    },
    {
      "epoch": 3.23,
      "grad_norm": 0.34232866764068604,
      "learning_rate": 1.388888888888889e-06,
      "loss": 0.1049,
      "step": 1170
    },
    {
      "epoch": 3.23,
      "grad_norm": 0.36424246430397034,
      "learning_rate": 9.259259259259259e-07,
      "loss": 0.0722,
      "step": 1180
    },
    {
      "epoch": 3.24,
      "grad_norm": 0.5086659789085388,
      "learning_rate": 4.6296296296296297e-07,
      "loss": 0.0257,
      "step": 1190
    },
    {
      "epoch": 3.25,
      "grad_norm": 1.790651798248291,
      "learning_rate": 0.0,
      "loss": 0.4026,
      "step": 1200
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.12024375051259995,
      "eval_runtime": 21.114,
      "eval_samples_per_second": 3.315,
      "eval_steps_per_second": 3.315,
      "step": 1200
    },
    {
      "epoch": 3.25,
      "step": 1200,
      "total_flos": 3.794829164937216e+17,
      "train_loss": 0.49671098495523136,
      "train_runtime": 661.0871,
      "train_samples_per_second": 1.815,
      "train_steps_per_second": 1.815
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.967741935483871,
      "eval_loss": 0.11705803126096725,
      "eval_runtime": 42.6289,
      "eval_samples_per_second": 3.636,
      "eval_steps_per_second": 3.636,
      "step": 1200
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.967741935483871,
      "eval_loss": 0.11705802381038666,
      "eval_runtime": 38.8628,
      "eval_samples_per_second": 3.988,
      "eval_steps_per_second": 3.988,
      "step": 1200
    }
  ],
  "logging_steps": 10,
  "max_steps": 1200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 3.794829164937216e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}