{
  "best_global_step": 686,
  "best_metric": 0.8981077147016011,
  "best_model_checkpoint": "deepfake_model_Video/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": 2.724184274673462,
      "learning_rate": 2.608695652173913e-05,
      "loss": 0.4693,
      "step": 10
    },
    {
      "epoch": 0.029154518950437316,
      "grad_norm": 10.216765403747559,
      "learning_rate": 5.507246376811594e-05,
      "loss": 0.322,
      "step": 20
    },
    {
      "epoch": 0.043731778425655975,
      "grad_norm": 0.018568186089396477,
      "learning_rate": 8.405797101449276e-05,
      "loss": 0.0035,
      "step": 30
    },
    {
      "epoch": 0.05830903790087463,
      "grad_norm": 0.2876422107219696,
      "learning_rate": 0.00011304347826086956,
      "loss": 0.5114,
      "step": 40
    },
    {
      "epoch": 0.0728862973760933,
      "grad_norm": 2.348113775253296,
      "learning_rate": 0.00014202898550724638,
      "loss": 0.8287,
      "step": 50
    },
    {
      "epoch": 0.08746355685131195,
      "grad_norm": 0.8497326374053955,
      "learning_rate": 0.0001710144927536232,
      "loss": 0.5513,
      "step": 60
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 0.12729506194591522,
      "learning_rate": 0.0002,
      "loss": 0.4225,
      "step": 70
    },
    {
      "epoch": 0.11661807580174927,
      "grad_norm": 3.1875579357147217,
      "learning_rate": 0.0001967585089141005,
      "loss": 0.4569,
      "step": 80
    },
    {
      "epoch": 0.13119533527696792,
      "grad_norm": 1.4104351997375488,
      "learning_rate": 0.00019351701782820098,
      "loss": 0.3362,
      "step": 90
    },
    {
      "epoch": 0.1457725947521866,
      "grad_norm": 0.14223401248455048,
      "learning_rate": 0.00019027552674230147,
      "loss": 0.7051,
      "step": 100
    },
    {
      "epoch": 0.16034985422740525,
      "grad_norm": 0.7365072965621948,
      "learning_rate": 0.00018703403565640197,
      "loss": 0.4635,
      "step": 110
    },
    {
      "epoch": 0.1749271137026239,
      "grad_norm": 0.7738670110702515,
      "learning_rate": 0.00018379254457050244,
      "loss": 0.7349,
      "step": 120
    },
    {
      "epoch": 0.18950437317784258,
      "grad_norm": 6.134955406188965,
      "learning_rate": 0.00018055105348460294,
      "loss": 0.3386,
      "step": 130
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.16075269877910614,
      "learning_rate": 0.00017730956239870343,
      "loss": 0.136,
      "step": 140
    },
    {
      "epoch": 0.21865889212827988,
      "grad_norm": 0.19563227891921997,
      "learning_rate": 0.0001740680713128039,
      "loss": 0.2569,
      "step": 150
    },
    {
      "epoch": 0.23323615160349853,
      "grad_norm": 0.43381619453430176,
      "learning_rate": 0.0001708265802269044,
      "loss": 0.3598,
      "step": 160
    },
    {
      "epoch": 0.2478134110787172,
      "grad_norm": 0.20831279456615448,
      "learning_rate": 0.00016758508914100487,
      "loss": 0.3577,
      "step": 170
    },
    {
      "epoch": 0.26239067055393583,
      "grad_norm": 0.5809088349342346,
      "learning_rate": 0.00016434359805510534,
      "loss": 0.5734,
      "step": 180
    },
    {
      "epoch": 0.27696793002915454,
      "grad_norm": 0.6877456307411194,
      "learning_rate": 0.00016110210696920584,
      "loss": 0.4703,
      "step": 190
    },
    {
      "epoch": 0.2915451895043732,
      "grad_norm": 0.15826986730098724,
      "learning_rate": 0.0001578606158833063,
      "loss": 0.1318,
      "step": 200
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 0.09976640343666077,
      "learning_rate": 0.0001546191247974068,
      "loss": 0.2712,
      "step": 210
    },
    {
      "epoch": 0.3206997084548105,
      "grad_norm": 0.45126938819885254,
      "learning_rate": 0.0001513776337115073,
      "loss": 0.9022,
      "step": 220
    },
    {
      "epoch": 0.33527696793002915,
      "grad_norm": 0.7453478574752808,
      "learning_rate": 0.00014813614262560777,
      "loss": 0.2994,
      "step": 230
    },
    {
      "epoch": 0.3498542274052478,
      "grad_norm": 0.34547126293182373,
      "learning_rate": 0.00014489465153970827,
      "loss": 0.4878,
      "step": 240
    },
    {
      "epoch": 0.36443148688046645,
      "grad_norm": 18.5524845123291,
      "learning_rate": 0.00014165316045380876,
      "loss": 0.6802,
      "step": 250
    },
    {
      "epoch": 0.37900874635568516,
      "grad_norm": 5.613125801086426,
      "learning_rate": 0.00013841166936790923,
      "loss": 0.4106,
      "step": 260
    },
    {
      "epoch": 0.3935860058309038,
      "grad_norm": 0.8488842844963074,
      "learning_rate": 0.00013517017828200973,
      "loss": 0.38,
      "step": 270
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 0.3382226526737213,
      "learning_rate": 0.00013192868719611023,
      "loss": 0.7335,
      "step": 280
    },
    {
      "epoch": 0.4227405247813411,
      "grad_norm": 5.387007713317871,
      "learning_rate": 0.0001286871961102107,
      "loss": 0.7114,
      "step": 290
    },
    {
      "epoch": 0.43731778425655976,
      "grad_norm": 1.3219224214553833,
      "learning_rate": 0.0001254457050243112,
      "loss": 0.3487,
      "step": 300
    },
    {
      "epoch": 0.4518950437317784,
      "grad_norm": 0.82120680809021,
      "learning_rate": 0.0001222042139384117,
      "loss": 0.4498,
      "step": 310
    },
    {
      "epoch": 0.46647230320699706,
      "grad_norm": 0.4810117483139038,
      "learning_rate": 0.00011896272285251216,
      "loss": 0.3031,
      "step": 320
    },
    {
      "epoch": 0.48104956268221577,
      "grad_norm": 0.8590919971466064,
      "learning_rate": 0.00011572123176661264,
      "loss": 0.7898,
      "step": 330
    },
    {
      "epoch": 0.4956268221574344,
      "grad_norm": 1.1319375038146973,
      "learning_rate": 0.00011247974068071314,
      "loss": 0.3422,
      "step": 340
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 0.4909662902355194,
      "learning_rate": 0.00010923824959481361,
      "loss": 0.4842,
      "step": 350
    },
    {
      "epoch": 0.5247813411078717,
      "grad_norm": 4.840802192687988,
      "learning_rate": 0.0001059967585089141,
      "loss": 0.5004,
      "step": 360
    },
    {
      "epoch": 0.5393586005830904,
      "grad_norm": 0.5355204343795776,
      "learning_rate": 0.0001027552674230146,
      "loss": 0.4121,
      "step": 370
    },
    {
      "epoch": 0.5539358600583091,
      "grad_norm": 1.1683344841003418,
      "learning_rate": 9.951377633711507e-05,
      "loss": 0.4711,
      "step": 380
    },
    {
      "epoch": 0.5685131195335277,
      "grad_norm": 0.8916622996330261,
      "learning_rate": 9.627228525121557e-05,
      "loss": 0.36,
      "step": 390
    },
    {
      "epoch": 0.5830903790087464,
      "grad_norm": 0.9914713501930237,
      "learning_rate": 9.303079416531605e-05,
      "loss": 0.5393,
      "step": 400
    },
    {
      "epoch": 0.597667638483965,
      "grad_norm": 11.216221809387207,
      "learning_rate": 8.978930307941653e-05,
      "loss": 0.5356,
      "step": 410
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 5.649008274078369,
      "learning_rate": 8.654781199351703e-05,
      "loss": 0.3985,
      "step": 420
    },
    {
      "epoch": 0.6268221574344023,
      "grad_norm": 0.3093053102493286,
      "learning_rate": 8.330632090761751e-05,
      "loss": 0.23,
      "step": 430
    },
    {
      "epoch": 0.641399416909621,
      "grad_norm": 0.27090609073638916,
      "learning_rate": 8.006482982171798e-05,
      "loss": 0.2396,
      "step": 440
    },
    {
      "epoch": 0.6559766763848397,
      "grad_norm": 0.25726521015167236,
      "learning_rate": 7.682333873581848e-05,
      "loss": 0.3565,
      "step": 450
    },
    {
      "epoch": 0.6705539358600583,
      "grad_norm": 0.3185364902019501,
      "learning_rate": 7.358184764991896e-05,
      "loss": 0.3444,
      "step": 460
    },
    {
      "epoch": 0.685131195335277,
      "grad_norm": 0.4198283851146698,
      "learning_rate": 7.034035656401945e-05,
      "loss": 0.878,
      "step": 470
    },
    {
      "epoch": 0.6997084548104956,
      "grad_norm": 0.5446736812591553,
      "learning_rate": 6.709886547811994e-05,
      "loss": 0.3185,
      "step": 480
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.406738817691803,
      "learning_rate": 6.385737439222043e-05,
      "loss": 0.5122,
      "step": 490
    },
    {
      "epoch": 0.7288629737609329,
      "grad_norm": 5.690066814422607,
      "learning_rate": 6.061588330632091e-05,
      "loss": 0.6518,
      "step": 500
    },
    {
      "epoch": 0.7434402332361516,
      "grad_norm": 0.5698899030685425,
      "learning_rate": 5.7374392220421394e-05,
      "loss": 0.3108,
      "step": 510
    },
    {
      "epoch": 0.7580174927113703,
      "grad_norm": 5.527081489562988,
      "learning_rate": 5.4132901134521884e-05,
      "loss": 0.2211,
      "step": 520
    },
    {
      "epoch": 0.7725947521865889,
      "grad_norm": 0.535829484462738,
      "learning_rate": 5.089141004862237e-05,
      "loss": 0.6102,
      "step": 530
    },
    {
      "epoch": 0.7871720116618076,
      "grad_norm": 0.5557084083557129,
      "learning_rate": 4.764991896272286e-05,
      "loss": 0.1212,
      "step": 540
    },
    {
      "epoch": 0.8017492711370262,
      "grad_norm": 5.698299884796143,
      "learning_rate": 4.440842787682334e-05,
      "loss": 0.5097,
      "step": 550
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 11.246345520019531,
      "learning_rate": 4.1166936790923824e-05,
      "loss": 0.5777,
      "step": 560
    },
    {
      "epoch": 0.8309037900874635,
      "grad_norm": 0.7025650143623352,
      "learning_rate": 3.7925445705024314e-05,
      "loss": 0.3704,
      "step": 570
    },
    {
      "epoch": 0.8454810495626822,
      "grad_norm": 5.281637191772461,
      "learning_rate": 3.46839546191248e-05,
      "loss": 0.206,
      "step": 580
    },
    {
      "epoch": 0.8600583090379009,
      "grad_norm": 5.373584747314453,
      "learning_rate": 3.144246353322529e-05,
      "loss": 0.5973,
      "step": 590
    },
    {
      "epoch": 0.8746355685131195,
      "grad_norm": 5.383228302001953,
      "learning_rate": 2.820097244732577e-05,
      "loss": 0.3115,
      "step": 600
    },
    {
      "epoch": 0.8892128279883382,
      "grad_norm": 0.5011938214302063,
      "learning_rate": 2.4959481361426257e-05,
      "loss": 0.4949,
      "step": 610
    },
    {
      "epoch": 0.9037900874635568,
      "grad_norm": 5.465159893035889,
      "learning_rate": 2.1717990275526743e-05,
      "loss": 0.5924,
      "step": 620
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 5.241404056549072,
      "learning_rate": 1.847649918962723e-05,
      "loss": 0.6572,
      "step": 630
    },
    {
      "epoch": 0.9329446064139941,
      "grad_norm": 0.7366176843643188,
      "learning_rate": 1.5235008103727717e-05,
      "loss": 0.2869,
      "step": 640
    },
    {
      "epoch": 0.9475218658892128,
      "grad_norm": 0.7882825136184692,
      "learning_rate": 1.1993517017828202e-05,
      "loss": 0.4657,
      "step": 650
    },
    {
      "epoch": 0.9620991253644315,
      "grad_norm": 5.200745105743408,
      "learning_rate": 8.752025931928688e-06,
      "loss": 0.551,
      "step": 660
    },
    {
      "epoch": 0.9766763848396501,
      "grad_norm": 5.204548358917236,
      "learning_rate": 5.510534846029174e-06,
      "loss": 0.7113,
      "step": 670
    },
    {
      "epoch": 0.9912536443148688,
      "grad_norm": 0.7551112174987793,
      "learning_rate": 2.2690437601296597e-06,
      "loss": 0.2969,
      "step": 680
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8981077147016011,
      "eval_loss": 0.3790549635887146,
      "eval_runtime": 408.3125,
      "eval_samples_per_second": 1.683,
      "eval_steps_per_second": 0.421,
      "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": 3,
        "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
}