{
  "best_global_step": 686,
  "best_metric": 0.893740902474527,
  "best_model_checkpoint": "deepfake_model_Video-MAE-1/checkpoint-686",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 686,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014577259475218658,
      "grad_norm": 5.3146071434021,
      "learning_rate": 2.608695652173913e-05,
      "loss": 0.6438,
      "step": 10
    },
    {
      "epoch": 0.029154518950437316,
      "grad_norm": 0.1986074000597,
      "learning_rate": 5.507246376811594e-05,
      "loss": 0.4447,
      "step": 20
    },
    {
      "epoch": 0.043731778425655975,
      "grad_norm": 0.06804976612329483,
      "learning_rate": 8.405797101449276e-05,
      "loss": 0.2479,
      "step": 30
    },
    {
      "epoch": 0.05830903790087463,
      "grad_norm": 4.464612007141113,
      "learning_rate": 0.00011304347826086956,
      "loss": 0.7579,
      "step": 40
    },
    {
      "epoch": 0.0728862973760933,
      "grad_norm": 0.01860504038631916,
      "learning_rate": 0.00014202898550724638,
      "loss": 0.2154,
      "step": 50
    },
    {
      "epoch": 0.08746355685131195,
      "grad_norm": 0.0755125880241394,
      "learning_rate": 0.0001710144927536232,
      "loss": 0.3242,
      "step": 60
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 0.4104626476764679,
      "learning_rate": 0.0002,
      "loss": 0.2618,
      "step": 70
    },
    {
      "epoch": 0.11661807580174927,
      "grad_norm": 5.070664882659912,
      "learning_rate": 0.0001967585089141005,
      "loss": 0.4574,
      "step": 80
    },
    {
      "epoch": 0.13119533527696792,
      "grad_norm": 2.585449695587158,
      "learning_rate": 0.00019351701782820098,
      "loss": 0.4542,
      "step": 90
    },
    {
      "epoch": 0.1457725947521866,
      "grad_norm": 0.9481808543205261,
      "learning_rate": 0.00019027552674230147,
      "loss": 0.3373,
      "step": 100
    },
    {
      "epoch": 0.16034985422740525,
      "grad_norm": 0.43055403232574463,
      "learning_rate": 0.00018703403565640197,
      "loss": 0.3928,
      "step": 110
    },
    {
      "epoch": 0.1749271137026239,
      "grad_norm": 0.15950709581375122,
      "learning_rate": 0.00018379254457050244,
      "loss": 0.1172,
      "step": 120
    },
    {
      "epoch": 0.18950437317784258,
      "grad_norm": 8.764716148376465,
      "learning_rate": 0.00018055105348460294,
      "loss": 0.4847,
      "step": 130
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.3541601300239563,
      "learning_rate": 0.00017730956239870343,
      "loss": 0.345,
      "step": 140
    },
    {
      "epoch": 0.21865889212827988,
      "grad_norm": 2.651851177215576,
      "learning_rate": 0.0001740680713128039,
      "loss": 0.6826,
      "step": 150
    },
    {
      "epoch": 0.23323615160349853,
      "grad_norm": 0.5931745171546936,
      "learning_rate": 0.0001708265802269044,
      "loss": 0.2021,
      "step": 160
    },
    {
      "epoch": 0.2478134110787172,
      "grad_norm": 1.8013778924942017,
      "learning_rate": 0.00016758508914100487,
      "loss": 0.7516,
      "step": 170
    },
    {
      "epoch": 0.26239067055393583,
      "grad_norm": 1.0193092823028564,
      "learning_rate": 0.00016434359805510534,
      "loss": 0.405,
      "step": 180
    },
    {
      "epoch": 0.27696793002915454,
      "grad_norm": 1.0689607858657837,
      "learning_rate": 0.00016110210696920584,
      "loss": 0.2898,
      "step": 190
    },
    {
      "epoch": 0.2915451895043732,
      "grad_norm": 3.772040605545044,
      "learning_rate": 0.0001578606158833063,
      "loss": 0.5378,
      "step": 200
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 0.8388488292694092,
      "learning_rate": 0.0001546191247974068,
      "loss": 0.4129,
      "step": 210
    },
    {
      "epoch": 0.3206997084548105,
      "grad_norm": 0.44900116324424744,
      "learning_rate": 0.0001513776337115073,
      "loss": 0.2113,
      "step": 220
    },
    {
      "epoch": 0.33527696793002915,
      "grad_norm": 0.29753178358078003,
      "learning_rate": 0.00014813614262560777,
      "loss": 0.4854,
      "step": 230
    },
    {
      "epoch": 0.3498542274052478,
      "grad_norm": 2.6392834186553955,
      "learning_rate": 0.00014489465153970827,
      "loss": 0.5591,
      "step": 240
    },
    {
      "epoch": 0.36443148688046645,
      "grad_norm": 0.7161630988121033,
      "learning_rate": 0.00014165316045380876,
      "loss": 0.3698,
      "step": 250
    },
    {
      "epoch": 0.37900874635568516,
      "grad_norm": 0.4423307180404663,
      "learning_rate": 0.00013841166936790923,
      "loss": 0.4399,
      "step": 260
    },
    {
      "epoch": 0.3935860058309038,
      "grad_norm": 2.786557197570801,
      "learning_rate": 0.00013517017828200973,
      "loss": 0.3868,
      "step": 270
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 2.5099093914031982,
      "learning_rate": 0.00013192868719611023,
      "loss": 0.4658,
      "step": 280
    },
    {
      "epoch": 0.4227405247813411,
      "grad_norm": 1.9165363311767578,
      "learning_rate": 0.0001286871961102107,
      "loss": 0.8003,
      "step": 290
    },
    {
      "epoch": 0.43731778425655976,
      "grad_norm": 1.3797115087509155,
      "learning_rate": 0.0001254457050243112,
      "loss": 0.3938,
      "step": 300
    },
    {
      "epoch": 0.4518950437317784,
      "grad_norm": 1.7510792016983032,
      "learning_rate": 0.0001222042139384117,
      "loss": 0.3926,
      "step": 310
    },
    {
      "epoch": 0.46647230320699706,
      "grad_norm": 1.488336205482483,
      "learning_rate": 0.00011896272285251216,
      "loss": 0.504,
      "step": 320
    },
    {
      "epoch": 0.48104956268221577,
      "grad_norm": 0.9835926294326782,
      "learning_rate": 0.00011572123176661264,
      "loss": 0.2206,
      "step": 330
    },
    {
      "epoch": 0.4956268221574344,
      "grad_norm": 0.7870058417320251,
      "learning_rate": 0.00011247974068071314,
      "loss": 0.3236,
      "step": 340
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 0.633097767829895,
      "learning_rate": 0.00010923824959481361,
      "loss": 0.4667,
      "step": 350
    },
    {
      "epoch": 0.5247813411078717,
      "grad_norm": 2.2080698013305664,
      "learning_rate": 0.0001059967585089141,
      "loss": 0.3491,
      "step": 360
    },
    {
      "epoch": 0.5393586005830904,
      "grad_norm": 0.6938947439193726,
      "learning_rate": 0.0001027552674230146,
      "loss": 0.497,
      "step": 370
    },
    {
      "epoch": 0.5539358600583091,
      "grad_norm": 0.47899454832077026,
      "learning_rate": 9.951377633711507e-05,
      "loss": 0.0584,
      "step": 380
    },
    {
      "epoch": 0.5685131195335277,
      "grad_norm": 0.3724881410598755,
      "learning_rate": 9.627228525121557e-05,
      "loss": 0.3644,
      "step": 390
    },
    {
      "epoch": 0.5830903790087464,
      "grad_norm": 0.5075926184654236,
      "learning_rate": 9.303079416531605e-05,
      "loss": 0.697,
      "step": 400
    },
    {
      "epoch": 0.597667638483965,
      "grad_norm": 0.6416959166526794,
      "learning_rate": 8.978930307941653e-05,
      "loss": 0.2031,
      "step": 410
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 0.49635839462280273,
      "learning_rate": 8.654781199351703e-05,
      "loss": 0.3355,
      "step": 420
    },
    {
      "epoch": 0.6268221574344023,
      "grad_norm": 0.43995216488838196,
      "learning_rate": 8.330632090761751e-05,
      "loss": 0.3582,
      "step": 430
    },
    {
      "epoch": 0.641399416909621,
      "grad_norm": 4.814486980438232,
      "learning_rate": 8.006482982171798e-05,
      "loss": 0.51,
      "step": 440
    },
    {
      "epoch": 0.6559766763848397,
      "grad_norm": 1.9786182641983032,
      "learning_rate": 7.682333873581848e-05,
      "loss": 0.486,
      "step": 450
    },
    {
      "epoch": 0.6705539358600583,
      "grad_norm": 1.8584587574005127,
      "learning_rate": 7.358184764991896e-05,
      "loss": 0.3977,
      "step": 460
    },
    {
      "epoch": 0.685131195335277,
      "grad_norm": 0.7450128793716431,
      "learning_rate": 7.034035656401945e-05,
      "loss": 0.2681,
      "step": 470
    },
    {
      "epoch": 0.6997084548104956,
      "grad_norm": 0.6749535202980042,
      "learning_rate": 6.709886547811994e-05,
      "loss": 0.2679,
      "step": 480
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.7746213674545288,
      "learning_rate": 6.385737439222043e-05,
      "loss": 0.6622,
      "step": 490
    },
    {
      "epoch": 0.7288629737609329,
      "grad_norm": 1.8850953578948975,
      "learning_rate": 6.061588330632091e-05,
      "loss": 0.2107,
      "step": 500
    },
    {
      "epoch": 0.7434402332361516,
      "grad_norm": 0.5546265840530396,
      "learning_rate": 5.7374392220421394e-05,
      "loss": 0.2717,
      "step": 510
    },
    {
      "epoch": 0.7580174927113703,
      "grad_norm": 0.39889729022979736,
      "learning_rate": 5.4132901134521884e-05,
      "loss": 0.1229,
      "step": 520
    },
    {
      "epoch": 0.7725947521865889,
      "grad_norm": 0.3102359175682068,
      "learning_rate": 5.089141004862237e-05,
      "loss": 0.2076,
      "step": 530
    },
    {
      "epoch": 0.7871720116618076,
      "grad_norm": 2.644927740097046,
      "learning_rate": 4.764991896272286e-05,
      "loss": 0.3011,
      "step": 540
    },
    {
      "epoch": 0.8017492711370262,
      "grad_norm": 0.3060024678707123,
      "learning_rate": 4.440842787682334e-05,
      "loss": 0.3004,
      "step": 550
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.3062104284763336,
      "learning_rate": 4.1166936790923824e-05,
      "loss": 0.1175,
      "step": 560
    },
    {
      "epoch": 0.8309037900874635,
      "grad_norm": 0.3254077434539795,
      "learning_rate": 3.7925445705024314e-05,
      "loss": 0.6553,
      "step": 570
    },
    {
      "epoch": 0.8454810495626822,
      "grad_norm": 5.185217380523682,
      "learning_rate": 3.46839546191248e-05,
      "loss": 0.7195,
      "step": 580
    },
    {
      "epoch": 0.8600583090379009,
      "grad_norm": 2.225529193878174,
      "learning_rate": 3.144246353322529e-05,
      "loss": 0.1991,
      "step": 590
    },
    {
      "epoch": 0.8746355685131195,
      "grad_norm": 0.4137911796569824,
      "learning_rate": 2.820097244732577e-05,
      "loss": 0.2816,
      "step": 600
    },
    {
      "epoch": 0.8892128279883382,
      "grad_norm": 0.3949086368083954,
      "learning_rate": 2.4959481361426257e-05,
      "loss": 0.2029,
      "step": 610
    },
    {
      "epoch": 0.9037900874635568,
      "grad_norm": 2.37062668800354,
      "learning_rate": 2.1717990275526743e-05,
      "loss": 0.609,
      "step": 620
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 2.082977771759033,
      "learning_rate": 1.847649918962723e-05,
      "loss": 1.0544,
      "step": 630
    },
    {
      "epoch": 0.9329446064139941,
      "grad_norm": 0.516295313835144,
      "learning_rate": 1.5235008103727717e-05,
      "loss": 0.0501,
      "step": 640
    },
    {
      "epoch": 0.9475218658892128,
      "grad_norm": 0.4977923035621643,
      "learning_rate": 1.1993517017828202e-05,
      "loss": 0.198,
      "step": 650
    },
    {
      "epoch": 0.9620991253644315,
      "grad_norm": 0.48140740394592285,
      "learning_rate": 8.752025931928688e-06,
      "loss": 0.4284,
      "step": 660
    },
    {
      "epoch": 0.9766763848396501,
      "grad_norm": 0.4845019280910492,
      "learning_rate": 5.510534846029174e-06,
      "loss": 0.2735,
      "step": 670
    },
    {
      "epoch": 0.9912536443148688,
      "grad_norm": 2.2184746265411377,
      "learning_rate": 2.2690437601296597e-06,
      "loss": 0.504,
      "step": 680
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.893740902474527,
      "eval_loss": 0.36989203095436096,
      "eval_runtime": 401.8752,
      "eval_samples_per_second": 1.709,
      "eval_steps_per_second": 0.428,
      "step": 686
    }
  ],
  "logging_steps": 10,
  "max_steps": 686,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.4192012335104655e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}