{
  "best_metric": 0.8838017754864972,
  "best_model_checkpoint": "videomae-surf-analytics-runpod/checkpoint-372",
  "epoch": 9.085245901639345,
  "eval_steps": 500,
  "global_step": 610,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01639344262295082,
      "grad_norm": 14.228123664855957,
      "learning_rate": 8.196721311475409e-06,
      "loss": 1.5374,
      "step": 10
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 8.263284683227539,
      "learning_rate": 1.6393442622950818e-05,
      "loss": 1.33,
      "step": 20
    },
    {
      "epoch": 0.04918032786885246,
      "grad_norm": 10.129837989807129,
      "learning_rate": 2.459016393442623e-05,
      "loss": 1.1214,
      "step": 30
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 5.447906017303467,
      "learning_rate": 3.2786885245901635e-05,
      "loss": 1.023,
      "step": 40
    },
    {
      "epoch": 0.08196721311475409,
      "grad_norm": 5.764439105987549,
      "learning_rate": 4.098360655737705e-05,
      "loss": 0.7497,
      "step": 50
    },
    {
      "epoch": 0.09836065573770492,
      "grad_norm": 6.531442165374756,
      "learning_rate": 4.918032786885246e-05,
      "loss": 0.6712,
      "step": 60
    },
    {
      "epoch": 0.10163934426229508,
      "eval_accuracy": 0.6680497925311203,
      "eval_f1": 0.6623298693885865,
      "eval_loss": 0.8671284317970276,
      "eval_runtime": 81.9529,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 0.256,
      "step": 62
    },
    {
      "epoch": 1.0131147540983607,
      "grad_norm": 6.3692240715026855,
      "learning_rate": 4.918032786885246e-05,
      "loss": 0.5055,
      "step": 70
    },
    {
      "epoch": 1.0295081967213116,
      "grad_norm": 7.524365425109863,
      "learning_rate": 4.8269581056466304e-05,
      "loss": 0.4465,
      "step": 80
    },
    {
      "epoch": 1.0459016393442624,
      "grad_norm": 3.4210591316223145,
      "learning_rate": 4.7358834244080144e-05,
      "loss": 0.3804,
      "step": 90
    },
    {
      "epoch": 1.0622950819672132,
      "grad_norm": 7.561025619506836,
      "learning_rate": 4.644808743169399e-05,
      "loss": 0.4557,
      "step": 100
    },
    {
      "epoch": 1.0786885245901638,
      "grad_norm": 2.567615509033203,
      "learning_rate": 4.553734061930783e-05,
      "loss": 0.3558,
      "step": 110
    },
    {
      "epoch": 1.0950819672131147,
      "grad_norm": 5.366397380828857,
      "learning_rate": 4.462659380692168e-05,
      "loss": 0.3119,
      "step": 120
    },
    {
      "epoch": 1.1016393442622952,
      "eval_accuracy": 0.7883817427385892,
      "eval_f1": 0.7887466325291007,
      "eval_loss": 0.5910844802856445,
      "eval_runtime": 82.6936,
      "eval_samples_per_second": 2.914,
      "eval_steps_per_second": 0.254,
      "step": 124
    },
    {
      "epoch": 2.0098360655737704,
      "grad_norm": 2.0202689170837402,
      "learning_rate": 4.371584699453552e-05,
      "loss": 0.2248,
      "step": 130
    },
    {
      "epoch": 2.0262295081967214,
      "grad_norm": 5.155245780944824,
      "learning_rate": 4.280510018214937e-05,
      "loss": 0.2797,
      "step": 140
    },
    {
      "epoch": 2.042622950819672,
      "grad_norm": 8.79983139038086,
      "learning_rate": 4.189435336976321e-05,
      "loss": 0.2696,
      "step": 150
    },
    {
      "epoch": 2.059016393442623,
      "grad_norm": 2.6221516132354736,
      "learning_rate": 4.098360655737705e-05,
      "loss": 0.2733,
      "step": 160
    },
    {
      "epoch": 2.0754098360655737,
      "grad_norm": 1.32801353931427,
      "learning_rate": 4.007285974499089e-05,
      "loss": 0.159,
      "step": 170
    },
    {
      "epoch": 2.091803278688525,
      "grad_norm": 7.7792792320251465,
      "learning_rate": 3.916211293260474e-05,
      "loss": 0.2505,
      "step": 180
    },
    {
      "epoch": 2.101639344262295,
      "eval_accuracy": 0.8008298755186722,
      "eval_f1": 0.8002014090167812,
      "eval_loss": 0.5296825170516968,
      "eval_runtime": 80.6025,
      "eval_samples_per_second": 2.99,
      "eval_steps_per_second": 0.261,
      "step": 186
    },
    {
      "epoch": 3.0065573770491802,
      "grad_norm": 6.463658332824707,
      "learning_rate": 3.825136612021858e-05,
      "loss": 0.3667,
      "step": 190
    },
    {
      "epoch": 3.0229508196721313,
      "grad_norm": 7.710232257843018,
      "learning_rate": 3.7340619307832425e-05,
      "loss": 0.1461,
      "step": 200
    },
    {
      "epoch": 3.039344262295082,
      "grad_norm": 8.827251434326172,
      "learning_rate": 3.6429872495446266e-05,
      "loss": 0.1328,
      "step": 210
    },
    {
      "epoch": 3.055737704918033,
      "grad_norm": 14.754895210266113,
      "learning_rate": 3.551912568306011e-05,
      "loss": 0.4213,
      "step": 220
    },
    {
      "epoch": 3.0721311475409836,
      "grad_norm": 7.798481464385986,
      "learning_rate": 3.4608378870673954e-05,
      "loss": 0.2256,
      "step": 230
    },
    {
      "epoch": 3.088524590163934,
      "grad_norm": 1.4291377067565918,
      "learning_rate": 3.36976320582878e-05,
      "loss": 0.207,
      "step": 240
    },
    {
      "epoch": 3.101639344262295,
      "eval_accuracy": 0.7800829875518672,
      "eval_f1": 0.778687519310884,
      "eval_loss": 0.5970368981361389,
      "eval_runtime": 76.1019,
      "eval_samples_per_second": 3.167,
      "eval_steps_per_second": 0.276,
      "step": 248
    },
    {
      "epoch": 4.00327868852459,
      "grad_norm": 6.123374938964844,
      "learning_rate": 3.2786885245901635e-05,
      "loss": 0.1879,
      "step": 250
    },
    {
      "epoch": 4.019672131147541,
      "grad_norm": 2.9475815296173096,
      "learning_rate": 3.187613843351548e-05,
      "loss": 0.0801,
      "step": 260
    },
    {
      "epoch": 4.036065573770492,
      "grad_norm": 0.0647067278623581,
      "learning_rate": 3.096539162112932e-05,
      "loss": 0.0925,
      "step": 270
    },
    {
      "epoch": 4.052459016393443,
      "grad_norm": 2.0591495037078857,
      "learning_rate": 3.005464480874317e-05,
      "loss": 0.1952,
      "step": 280
    },
    {
      "epoch": 4.0688524590163935,
      "grad_norm": 9.379964828491211,
      "learning_rate": 2.9143897996357018e-05,
      "loss": 0.2213,
      "step": 290
    },
    {
      "epoch": 4.085245901639344,
      "grad_norm": 0.2886744737625122,
      "learning_rate": 2.823315118397086e-05,
      "loss": 0.1651,
      "step": 300
    },
    {
      "epoch": 4.101639344262295,
      "grad_norm": 10.280256271362305,
      "learning_rate": 2.7322404371584703e-05,
      "loss": 0.1743,
      "step": 310
    },
    {
      "epoch": 4.101639344262295,
      "eval_accuracy": 0.8049792531120332,
      "eval_f1": 0.7984134204702362,
      "eval_loss": 0.5612084865570068,
      "eval_runtime": 76.7892,
      "eval_samples_per_second": 3.138,
      "eval_steps_per_second": 0.273,
      "step": 310
    },
    {
      "epoch": 5.016393442622951,
      "grad_norm": 0.10767544060945511,
      "learning_rate": 2.6411657559198543e-05,
      "loss": 0.1745,
      "step": 320
    },
    {
      "epoch": 5.032786885245901,
      "grad_norm": 0.31735455989837646,
      "learning_rate": 2.550091074681239e-05,
      "loss": 0.0893,
      "step": 330
    },
    {
      "epoch": 5.049180327868853,
      "grad_norm": 0.657698392868042,
      "learning_rate": 2.459016393442623e-05,
      "loss": 0.0209,
      "step": 340
    },
    {
      "epoch": 5.065573770491803,
      "grad_norm": 6.128834247589111,
      "learning_rate": 2.3679417122040072e-05,
      "loss": 0.0931,
      "step": 350
    },
    {
      "epoch": 5.081967213114754,
      "grad_norm": 3.8232431411743164,
      "learning_rate": 2.2768670309653916e-05,
      "loss": 0.1862,
      "step": 360
    },
    {
      "epoch": 5.098360655737705,
      "grad_norm": 0.28946903347969055,
      "learning_rate": 2.185792349726776e-05,
      "loss": 0.1005,
      "step": 370
    },
    {
      "epoch": 5.101639344262295,
      "eval_accuracy": 0.8838174273858921,
      "eval_f1": 0.8838017754864972,
      "eval_loss": 0.40273839235305786,
      "eval_runtime": 79.1005,
      "eval_samples_per_second": 3.047,
      "eval_steps_per_second": 0.265,
      "step": 372
    },
    {
      "epoch": 6.0131147540983605,
      "grad_norm": 7.813482761383057,
      "learning_rate": 2.0947176684881604e-05,
      "loss": 0.1164,
      "step": 380
    },
    {
      "epoch": 6.029508196721311,
      "grad_norm": 4.695272445678711,
      "learning_rate": 2.0036429872495445e-05,
      "loss": 0.128,
      "step": 390
    },
    {
      "epoch": 6.045901639344263,
      "grad_norm": 0.22056636214256287,
      "learning_rate": 1.912568306010929e-05,
      "loss": 0.1201,
      "step": 400
    },
    {
      "epoch": 6.062295081967213,
      "grad_norm": 0.24654638767242432,
      "learning_rate": 1.8214936247723133e-05,
      "loss": 0.0823,
      "step": 410
    },
    {
      "epoch": 6.078688524590164,
      "grad_norm": 1.5276825428009033,
      "learning_rate": 1.7304189435336977e-05,
      "loss": 0.0994,
      "step": 420
    },
    {
      "epoch": 6.0950819672131145,
      "grad_norm": 5.22976016998291,
      "learning_rate": 1.6393442622950818e-05,
      "loss": 0.0147,
      "step": 430
    },
    {
      "epoch": 6.101639344262295,
      "eval_accuracy": 0.8589211618257261,
      "eval_f1": 0.8572866763193951,
      "eval_loss": 0.4360053241252899,
      "eval_runtime": 76.601,
      "eval_samples_per_second": 3.146,
      "eval_steps_per_second": 0.274,
      "step": 434
    },
    {
      "epoch": 7.00983606557377,
      "grad_norm": 0.01562822423875332,
      "learning_rate": 1.548269581056466e-05,
      "loss": 0.0178,
      "step": 440
    },
    {
      "epoch": 7.026229508196721,
      "grad_norm": 0.15828734636306763,
      "learning_rate": 1.4571948998178509e-05,
      "loss": 0.1265,
      "step": 450
    },
    {
      "epoch": 7.0426229508196725,
      "grad_norm": 0.9054508805274963,
      "learning_rate": 1.3661202185792351e-05,
      "loss": 0.0251,
      "step": 460
    },
    {
      "epoch": 7.059016393442623,
      "grad_norm": 0.2960349917411804,
      "learning_rate": 1.2750455373406195e-05,
      "loss": 0.0241,
      "step": 470
    },
    {
      "epoch": 7.075409836065574,
      "grad_norm": 0.08049295842647552,
      "learning_rate": 1.1839708561020036e-05,
      "loss": 0.0518,
      "step": 480
    },
    {
      "epoch": 7.091803278688524,
      "grad_norm": 0.25148022174835205,
      "learning_rate": 1.092896174863388e-05,
      "loss": 0.0573,
      "step": 490
    },
    {
      "epoch": 7.101639344262295,
      "eval_accuracy": 0.8713692946058091,
      "eval_f1": 0.8697143392786835,
      "eval_loss": 0.4450831115245819,
      "eval_runtime": 75.7767,
      "eval_samples_per_second": 3.18,
      "eval_steps_per_second": 0.277,
      "step": 496
    },
    {
      "epoch": 8.00655737704918,
      "grad_norm": 0.028504155576229095,
      "learning_rate": 1.0018214936247722e-05,
      "loss": 0.0705,
      "step": 500
    },
    {
      "epoch": 8.02295081967213,
      "grad_norm": 0.7975661158561707,
      "learning_rate": 9.107468123861566e-06,
      "loss": 0.0547,
      "step": 510
    },
    {
      "epoch": 8.039344262295081,
      "grad_norm": 0.035094812512397766,
      "learning_rate": 8.196721311475409e-06,
      "loss": 0.0484,
      "step": 520
    },
    {
      "epoch": 8.055737704918032,
      "grad_norm": 4.1898651123046875,
      "learning_rate": 7.2859744990892545e-06,
      "loss": 0.0834,
      "step": 530
    },
    {
      "epoch": 8.072131147540984,
      "grad_norm": 0.8504851460456848,
      "learning_rate": 6.375227686703098e-06,
      "loss": 0.1502,
      "step": 540
    },
    {
      "epoch": 8.088524590163935,
      "grad_norm": 0.8113920092582703,
      "learning_rate": 5.46448087431694e-06,
      "loss": 0.0143,
      "step": 550
    },
    {
      "epoch": 8.101639344262296,
      "eval_accuracy": 0.8672199170124482,
      "eval_f1": 0.8666497215968316,
      "eval_loss": 0.40985623002052307,
      "eval_runtime": 79.8008,
      "eval_samples_per_second": 3.02,
      "eval_steps_per_second": 0.263,
      "step": 558
    },
    {
      "epoch": 9.00327868852459,
      "grad_norm": 6.550829887390137,
      "learning_rate": 4.553734061930783e-06,
      "loss": 0.067,
      "step": 560
    },
    {
      "epoch": 9.01967213114754,
      "grad_norm": 2.0722174644470215,
      "learning_rate": 3.6429872495446273e-06,
      "loss": 0.0158,
      "step": 570
    },
    {
      "epoch": 9.036065573770491,
      "grad_norm": 0.09152109175920486,
      "learning_rate": 2.73224043715847e-06,
      "loss": 0.0203,
      "step": 580
    },
    {
      "epoch": 9.052459016393442,
      "grad_norm": 0.12251006811857224,
      "learning_rate": 1.8214936247723136e-06,
      "loss": 0.0169,
      "step": 590
    },
    {
      "epoch": 9.068852459016393,
      "grad_norm": 0.1367557793855667,
      "learning_rate": 9.107468123861568e-07,
      "loss": 0.0043,
      "step": 600
    },
    {
      "epoch": 9.085245901639345,
      "grad_norm": 6.975312232971191,
      "learning_rate": 0.0,
      "loss": 0.1311,
      "step": 610
    },
    {
      "epoch": 9.085245901639345,
      "eval_accuracy": 0.8755186721991701,
      "eval_f1": 0.8751571381793353,
      "eval_loss": 0.40564292669296265,
      "eval_runtime": 76.4754,
      "eval_samples_per_second": 3.151,
      "eval_steps_per_second": 0.275,
      "step": 610
    },
    {
      "epoch": 9.085245901639345,
      "step": 610,
      "total_flos": 6.389823367042892e+18,
      "train_loss": 0.24862837887933997,
      "train_runtime": 3777.5727,
      "train_samples_per_second": 1.938,
      "train_steps_per_second": 0.161
    },
    {
      "epoch": 9.085245901639345,
      "eval_accuracy": 0.9824561403508771,
      "eval_f1": 0.9824594539682324,
      "eval_loss": 0.04523608461022377,
      "eval_runtime": 250.7162,
      "eval_samples_per_second": 2.956,
      "eval_steps_per_second": 0.247,
      "step": 610
    },
    {
      "epoch": 9.085245901639345,
      "eval_accuracy": 0.8337078651685393,
      "eval_f1": 0.8322580739791249,
      "eval_loss": 0.6123429536819458,
      "eval_runtime": 140.7823,
      "eval_samples_per_second": 3.161,
      "eval_steps_per_second": 0.27,
      "step": 610
    },
    {
      "epoch": 9.085245901639345,
      "eval_accuracy": 0.8838174273858921,
      "eval_f1": 0.8838017754864972,
      "eval_loss": 0.40273845195770264,
      "eval_runtime": 76.8071,
      "eval_samples_per_second": 3.138,
      "eval_steps_per_second": 0.273,
      "step": 610
    }
  ],
  "logging_steps": 10,
  "max_steps": 610,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.389823367042892e+18,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}