{
  "best_metric": 0.9714285714285714,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-375",
  "epoch": 5.166666666666667,
  "eval_steps": 500,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 9.09181022644043,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 2.3453,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 9.389509201049805,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 2.3958,
      "step": 20
    },
    {
      "epoch": 0.07,
      "grad_norm": 9.11400032043457,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.2492,
      "step": 30
    },
    {
      "epoch": 0.09,
      "grad_norm": 9.454550743103027,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 2.1811,
      "step": 40
    },
    {
      "epoch": 0.11,
      "grad_norm": 12.871296882629395,
      "learning_rate": 4.938271604938271e-05,
      "loss": 2.1261,
      "step": 50
    },
    {
      "epoch": 0.13,
      "grad_norm": 9.507197380065918,
      "learning_rate": 4.814814814814815e-05,
      "loss": 2.0149,
      "step": 60
    },
    {
      "epoch": 0.16,
      "grad_norm": 12.240191459655762,
      "learning_rate": 4.691358024691358e-05,
      "loss": 1.9248,
      "step": 70
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.3142857142857143,
      "eval_loss": 1.6910260915756226,
      "eval_runtime": 13.1007,
      "eval_samples_per_second": 5.343,
      "eval_steps_per_second": 1.374,
      "step": 75
    },
    {
      "epoch": 1.01,
      "grad_norm": 13.400834083557129,
      "learning_rate": 4.567901234567901e-05,
      "loss": 1.4961,
      "step": 80
    },
    {
      "epoch": 1.03,
      "grad_norm": 12.832711219787598,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.4544,
      "step": 90
    },
    {
      "epoch": 1.06,
      "grad_norm": 11.878938674926758,
      "learning_rate": 4.3209876543209875e-05,
      "loss": 1.3226,
      "step": 100
    },
    {
      "epoch": 1.08,
      "grad_norm": 8.267742156982422,
      "learning_rate": 4.197530864197531e-05,
      "loss": 0.9212,
      "step": 110
    },
    {
      "epoch": 1.1,
      "grad_norm": 15.088278770446777,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.8928,
      "step": 120
    },
    {
      "epoch": 1.12,
      "grad_norm": 14.688928604125977,
      "learning_rate": 3.950617283950617e-05,
      "loss": 0.6026,
      "step": 130
    },
    {
      "epoch": 1.14,
      "grad_norm": 10.090428352355957,
      "learning_rate": 3.82716049382716e-05,
      "loss": 0.7323,
      "step": 140
    },
    {
      "epoch": 1.17,
      "grad_norm": 28.017093658447266,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.1184,
      "step": 150
    },
    {
      "epoch": 1.17,
      "eval_accuracy": 0.7,
      "eval_loss": 0.8519060611724854,
      "eval_runtime": 12.8721,
      "eval_samples_per_second": 5.438,
      "eval_steps_per_second": 1.398,
      "step": 150
    },
    {
      "epoch": 2.02,
      "grad_norm": 7.826801776885986,
      "learning_rate": 3.580246913580247e-05,
      "loss": 0.6328,
      "step": 160
    },
    {
      "epoch": 2.04,
      "grad_norm": 17.076839447021484,
      "learning_rate": 3.45679012345679e-05,
      "loss": 0.5843,
      "step": 170
    },
    {
      "epoch": 2.07,
      "grad_norm": 8.304590225219727,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7969,
      "step": 180
    },
    {
      "epoch": 2.09,
      "grad_norm": 7.5533223152160645,
      "learning_rate": 3.209876543209876e-05,
      "loss": 0.5387,
      "step": 190
    },
    {
      "epoch": 2.11,
      "grad_norm": 3.7337615489959717,
      "learning_rate": 3.08641975308642e-05,
      "loss": 0.5673,
      "step": 200
    },
    {
      "epoch": 2.13,
      "grad_norm": 23.18366050720215,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.5191,
      "step": 210
    },
    {
      "epoch": 2.16,
      "grad_norm": 11.092031478881836,
      "learning_rate": 2.839506172839506e-05,
      "loss": 0.3505,
      "step": 220
    },
    {
      "epoch": 2.17,
      "eval_accuracy": 0.7857142857142857,
      "eval_loss": 0.5482387542724609,
      "eval_runtime": 12.8506,
      "eval_samples_per_second": 5.447,
      "eval_steps_per_second": 1.401,
      "step": 225
    },
    {
      "epoch": 3.01,
      "grad_norm": 1.397813320159912,
      "learning_rate": 2.7160493827160493e-05,
      "loss": 0.2652,
      "step": 230
    },
    {
      "epoch": 3.03,
      "grad_norm": 2.130690574645996,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.1691,
      "step": 240
    },
    {
      "epoch": 3.06,
      "grad_norm": 7.323586940765381,
      "learning_rate": 2.4691358024691357e-05,
      "loss": 0.1669,
      "step": 250
    },
    {
      "epoch": 3.08,
      "grad_norm": 5.903147220611572,
      "learning_rate": 2.345679012345679e-05,
      "loss": 0.324,
      "step": 260
    },
    {
      "epoch": 3.1,
      "grad_norm": 24.850133895874023,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.4857,
      "step": 270
    },
    {
      "epoch": 3.12,
      "grad_norm": 1.1520411968231201,
      "learning_rate": 2.0987654320987655e-05,
      "loss": 0.231,
      "step": 280
    },
    {
      "epoch": 3.14,
      "grad_norm": 0.6035730838775635,
      "learning_rate": 1.9753086419753087e-05,
      "loss": 0.3852,
      "step": 290
    },
    {
      "epoch": 3.17,
      "grad_norm": 18.224578857421875,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.2939,
      "step": 300
    },
    {
      "epoch": 3.17,
      "eval_accuracy": 0.8285714285714286,
      "eval_loss": 0.5074731111526489,
      "eval_runtime": 12.6199,
      "eval_samples_per_second": 5.547,
      "eval_steps_per_second": 1.426,
      "step": 300
    },
    {
      "epoch": 4.02,
      "grad_norm": 4.320995330810547,
      "learning_rate": 1.728395061728395e-05,
      "loss": 0.1894,
      "step": 310
    },
    {
      "epoch": 4.04,
      "grad_norm": 4.220107555389404,
      "learning_rate": 1.604938271604938e-05,
      "loss": 0.2997,
      "step": 320
    },
    {
      "epoch": 4.07,
      "grad_norm": 0.14674872159957886,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.2471,
      "step": 330
    },
    {
      "epoch": 4.09,
      "grad_norm": 1.210436224937439,
      "learning_rate": 1.3580246913580247e-05,
      "loss": 0.1045,
      "step": 340
    },
    {
      "epoch": 4.11,
      "grad_norm": 0.28732016682624817,
      "learning_rate": 1.2345679012345678e-05,
      "loss": 0.0638,
      "step": 350
    },
    {
      "epoch": 4.13,
      "grad_norm": 0.1985640674829483,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.1419,
      "step": 360
    },
    {
      "epoch": 4.16,
      "grad_norm": 0.1826096773147583,
      "learning_rate": 9.876543209876543e-06,
      "loss": 0.0447,
      "step": 370
    },
    {
      "epoch": 4.17,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.1740979254245758,
      "eval_runtime": 12.7121,
      "eval_samples_per_second": 5.507,
      "eval_steps_per_second": 1.416,
      "step": 375
    },
    {
      "epoch": 5.01,
      "grad_norm": 0.4490085244178772,
      "learning_rate": 8.641975308641975e-06,
      "loss": 0.0338,
      "step": 380
    },
    {
      "epoch": 5.03,
      "grad_norm": 0.615115761756897,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.1366,
      "step": 390
    },
    {
      "epoch": 5.06,
      "grad_norm": 0.19469819962978363,
      "learning_rate": 6.172839506172839e-06,
      "loss": 0.2805,
      "step": 400
    },
    {
      "epoch": 5.08,
      "grad_norm": 0.10871770232915878,
      "learning_rate": 4.938271604938272e-06,
      "loss": 0.1858,
      "step": 410
    },
    {
      "epoch": 5.1,
      "grad_norm": 1.5411165952682495,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.0189,
      "step": 420
    },
    {
      "epoch": 5.12,
      "grad_norm": 10.748401641845703,
      "learning_rate": 2.469135802469136e-06,
      "loss": 0.0882,
      "step": 430
    },
    {
      "epoch": 5.14,
      "grad_norm": 0.13508407771587372,
      "learning_rate": 1.234567901234568e-06,
      "loss": 0.1669,
      "step": 440
    },
    {
      "epoch": 5.17,
      "grad_norm": 6.92973518371582,
      "learning_rate": 0.0,
      "loss": 0.0643,
      "step": 450
    },
    {
      "epoch": 5.17,
      "eval_accuracy": 0.9571428571428572,
      "eval_loss": 0.1370178759098053,
      "eval_runtime": 12.713,
      "eval_samples_per_second": 5.506,
      "eval_steps_per_second": 1.416,
      "step": 450
    },
    {
      "epoch": 5.17,
      "step": 450,
      "total_flos": 2.243076282187776e+18,
      "train_loss": 0.7145391458272934,
      "train_runtime": 727.1717,
      "train_samples_per_second": 2.475,
      "train_steps_per_second": 0.619
    },
    {
      "epoch": 5.17,
      "eval_accuracy": 0.8516129032258064,
      "eval_loss": 0.6185441613197327,
      "eval_runtime": 29.0205,
      "eval_samples_per_second": 5.341,
      "eval_steps_per_second": 1.344,
      "step": 450
    },
    {
      "epoch": 5.17,
      "eval_accuracy": 0.8516129032258064,
      "eval_loss": 0.6185442209243774,
      "eval_runtime": 28.1289,
      "eval_samples_per_second": 5.51,
      "eval_steps_per_second": 1.386,
      "step": 450
    }
  ],
  "logging_steps": 10,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 2.243076282187776e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}