{
  "best_metric": 0.719188596491228,
  "best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-shoplifting-dataset/checkpoint-353",
  "epoch": 9.098863636363637,
  "eval_steps": 500,
  "global_step": 880,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011363636363636364,
      "grad_norm": 0.7822037935256958,
      "learning_rate": 5.681818181818182e-06,
      "loss": 0.1251,
      "step": 10
    },
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 6.924298286437988,
      "learning_rate": 1.1363636363636365e-05,
      "loss": 0.2906,
      "step": 20
    },
    {
      "epoch": 0.03409090909090909,
      "grad_norm": 0.3597455322742462,
      "learning_rate": 1.7045454545454546e-05,
      "loss": 0.1046,
      "step": 30
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 20.039451599121094,
      "learning_rate": 2.272727272727273e-05,
      "loss": 0.3495,
      "step": 40
    },
    {
      "epoch": 0.056818181818181816,
      "grad_norm": 19.18282127380371,
      "learning_rate": 2.8409090909090912e-05,
      "loss": 0.3138,
      "step": 50
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 6.543797016143799,
      "learning_rate": 3.409090909090909e-05,
      "loss": 0.2203,
      "step": 60
    },
    {
      "epoch": 0.07954545454545454,
      "grad_norm": 9.147849082946777,
      "learning_rate": 3.9772727272727275e-05,
      "loss": 0.3068,
      "step": 70
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.336655616760254,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.1824,
      "step": 80
    },
    {
      "epoch": 0.10113636363636364,
      "eval_f1": 0.6832431989511635,
      "eval_loss": 1.0067527294158936,
      "eval_runtime": 76.7216,
      "eval_samples_per_second": 2.503,
      "eval_steps_per_second": 0.313,
      "step": 89
    },
    {
      "epoch": 1.0011363636363637,
      "grad_norm": 8.309718132019043,
      "learning_rate": 4.9873737373737375e-05,
      "loss": 0.2712,
      "step": 90
    },
    {
      "epoch": 1.0125,
      "grad_norm": 1.4587355852127075,
      "learning_rate": 4.9242424242424245e-05,
      "loss": 0.1706,
      "step": 100
    },
    {
      "epoch": 1.0238636363636364,
      "grad_norm": 24.91333770751953,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 0.2993,
      "step": 110
    },
    {
      "epoch": 1.0352272727272727,
      "grad_norm": 2.1657192707061768,
      "learning_rate": 4.797979797979798e-05,
      "loss": 0.1297,
      "step": 120
    },
    {
      "epoch": 1.0465909090909091,
      "grad_norm": 0.5277124643325806,
      "learning_rate": 4.7348484848484855e-05,
      "loss": 0.2617,
      "step": 130
    },
    {
      "epoch": 1.0579545454545454,
      "grad_norm": 1.7243237495422363,
      "learning_rate": 4.671717171717172e-05,
      "loss": 0.1424,
      "step": 140
    },
    {
      "epoch": 1.0693181818181818,
      "grad_norm": 1.7403205633163452,
      "learning_rate": 4.608585858585859e-05,
      "loss": 0.5873,
      "step": 150
    },
    {
      "epoch": 1.080681818181818,
      "grad_norm": 2.7504332065582275,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.2966,
      "step": 160
    },
    {
      "epoch": 1.0920454545454545,
      "grad_norm": 6.052179336547852,
      "learning_rate": 4.482323232323233e-05,
      "loss": 0.334,
      "step": 170
    },
    {
      "epoch": 1.1,
      "eval_f1": 0.6804519337964154,
      "eval_loss": 0.9260269999504089,
      "eval_runtime": 73.8445,
      "eval_samples_per_second": 2.6,
      "eval_steps_per_second": 0.325,
      "step": 177
    },
    {
      "epoch": 2.003409090909091,
      "grad_norm": 0.761626124382019,
      "learning_rate": 4.41919191919192e-05,
      "loss": 0.6221,
      "step": 180
    },
    {
      "epoch": 2.014772727272727,
      "grad_norm": 0.5840346813201904,
      "learning_rate": 4.356060606060606e-05,
      "loss": 0.1877,
      "step": 190
    },
    {
      "epoch": 2.026136363636364,
      "grad_norm": 1.2796881198883057,
      "learning_rate": 4.292929292929293e-05,
      "loss": 0.1515,
      "step": 200
    },
    {
      "epoch": 2.0375,
      "grad_norm": 14.390783309936523,
      "learning_rate": 4.2297979797979795e-05,
      "loss": 0.1208,
      "step": 210
    },
    {
      "epoch": 2.0488636363636363,
      "grad_norm": 8.565354347229004,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.1364,
      "step": 220
    },
    {
      "epoch": 2.0602272727272726,
      "grad_norm": 39.79494094848633,
      "learning_rate": 4.1035353535353535e-05,
      "loss": 0.2243,
      "step": 230
    },
    {
      "epoch": 2.0715909090909093,
      "grad_norm": 11.125761985778809,
      "learning_rate": 4.0404040404040405e-05,
      "loss": 0.1289,
      "step": 240
    },
    {
      "epoch": 2.0829545454545455,
      "grad_norm": 0.10636977106332779,
      "learning_rate": 3.9772727272727275e-05,
      "loss": 0.2634,
      "step": 250
    },
    {
      "epoch": 2.0943181818181817,
      "grad_norm": 6.6989617347717285,
      "learning_rate": 3.9141414141414145e-05,
      "loss": 0.2202,
      "step": 260
    },
    {
      "epoch": 2.1,
      "eval_f1": 0.7139075032998273,
      "eval_loss": 0.9855768084526062,
      "eval_runtime": 80.7383,
      "eval_samples_per_second": 2.378,
      "eval_steps_per_second": 0.297,
      "step": 265
    },
    {
      "epoch": 3.0056818181818183,
      "grad_norm": 7.529367446899414,
      "learning_rate": 3.8510101010101015e-05,
      "loss": 0.1857,
      "step": 270
    },
    {
      "epoch": 3.0170454545454546,
      "grad_norm": 1.7394098043441772,
      "learning_rate": 3.787878787878788e-05,
      "loss": 0.1633,
      "step": 280
    },
    {
      "epoch": 3.028409090909091,
      "grad_norm": 35.92728805541992,
      "learning_rate": 3.724747474747475e-05,
      "loss": 0.147,
      "step": 290
    },
    {
      "epoch": 3.039772727272727,
      "grad_norm": 6.699644565582275,
      "learning_rate": 3.661616161616162e-05,
      "loss": 0.1791,
      "step": 300
    },
    {
      "epoch": 3.0511363636363638,
      "grad_norm": 7.0385894775390625,
      "learning_rate": 3.598484848484849e-05,
      "loss": 0.148,
      "step": 310
    },
    {
      "epoch": 3.0625,
      "grad_norm": 3.4319474697113037,
      "learning_rate": 3.535353535353535e-05,
      "loss": 0.1414,
      "step": 320
    },
    {
      "epoch": 3.0738636363636362,
      "grad_norm": 1.3963415622711182,
      "learning_rate": 3.472222222222222e-05,
      "loss": 0.0888,
      "step": 330
    },
    {
      "epoch": 3.085227272727273,
      "grad_norm": 0.17751815915107727,
      "learning_rate": 3.409090909090909e-05,
      "loss": 0.1007,
      "step": 340
    },
    {
      "epoch": 3.096590909090909,
      "grad_norm": 8.843611717224121,
      "learning_rate": 3.345959595959596e-05,
      "loss": 0.2074,
      "step": 350
    },
    {
      "epoch": 3.1,
      "eval_f1": 0.719188596491228,
      "eval_loss": 0.9494466781616211,
      "eval_runtime": 66.0371,
      "eval_samples_per_second": 2.907,
      "eval_steps_per_second": 0.363,
      "step": 353
    },
    {
      "epoch": 4.007954545454545,
      "grad_norm": 0.11681011319160461,
      "learning_rate": 3.282828282828283e-05,
      "loss": 0.1654,
      "step": 360
    },
    {
      "epoch": 4.019318181818182,
      "grad_norm": 0.03579840064048767,
      "learning_rate": 3.2196969696969696e-05,
      "loss": 0.0781,
      "step": 370
    },
    {
      "epoch": 4.030681818181818,
      "grad_norm": 0.28152555227279663,
      "learning_rate": 3.1565656565656566e-05,
      "loss": 0.0961,
      "step": 380
    },
    {
      "epoch": 4.0420454545454545,
      "grad_norm": 0.36765220761299133,
      "learning_rate": 3.0934343434343436e-05,
      "loss": 0.0591,
      "step": 390
    },
    {
      "epoch": 4.053409090909091,
      "grad_norm": 13.338018417358398,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 0.0945,
      "step": 400
    },
    {
      "epoch": 4.064772727272727,
      "grad_norm": 9.662626266479492,
      "learning_rate": 2.9671717171717172e-05,
      "loss": 0.1343,
      "step": 410
    },
    {
      "epoch": 4.076136363636364,
      "grad_norm": 1.916236400604248,
      "learning_rate": 2.904040404040404e-05,
      "loss": 0.3043,
      "step": 420
    },
    {
      "epoch": 4.0875,
      "grad_norm": 12.770139694213867,
      "learning_rate": 2.8409090909090912e-05,
      "loss": 0.2391,
      "step": 430
    },
    {
      "epoch": 4.098863636363636,
      "grad_norm": 7.032412052154541,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.0916,
      "step": 440
    },
    {
      "epoch": 4.1,
      "eval_f1": 0.671078431372549,
      "eval_loss": 1.3867233991622925,
      "eval_runtime": 69.8609,
      "eval_samples_per_second": 2.748,
      "eval_steps_per_second": 0.344,
      "step": 441
    },
    {
      "epoch": 5.010227272727272,
      "grad_norm": 9.611908912658691,
      "learning_rate": 2.714646464646465e-05,
      "loss": 0.1568,
      "step": 450
    },
    {
      "epoch": 5.021590909090909,
      "grad_norm": 3.7834885120391846,
      "learning_rate": 2.6515151515151516e-05,
      "loss": 0.3173,
      "step": 460
    },
    {
      "epoch": 5.032954545454546,
      "grad_norm": 0.057657867670059204,
      "learning_rate": 2.5883838383838382e-05,
      "loss": 0.1004,
      "step": 470
    },
    {
      "epoch": 5.0443181818181815,
      "grad_norm": 1.133195161819458,
      "learning_rate": 2.5252525252525256e-05,
      "loss": 0.0869,
      "step": 480
    },
    {
      "epoch": 5.055681818181818,
      "grad_norm": 6.4852166175842285,
      "learning_rate": 2.4621212121212123e-05,
      "loss": 0.0964,
      "step": 490
    },
    {
      "epoch": 5.067045454545455,
      "grad_norm": 0.01637670025229454,
      "learning_rate": 2.398989898989899e-05,
      "loss": 0.0511,
      "step": 500
    },
    {
      "epoch": 5.078409090909091,
      "grad_norm": 20.669986724853516,
      "learning_rate": 2.335858585858586e-05,
      "loss": 0.2204,
      "step": 510
    },
    {
      "epoch": 5.089772727272727,
      "grad_norm": 0.07228785008192062,
      "learning_rate": 2.272727272727273e-05,
      "loss": 0.1092,
      "step": 520
    },
    {
      "epoch": 5.1,
      "eval_f1": 0.6919812909064125,
      "eval_loss": 1.3757562637329102,
      "eval_runtime": 68.2311,
      "eval_samples_per_second": 2.814,
      "eval_steps_per_second": 0.352,
      "step": 529
    },
    {
      "epoch": 6.0011363636363635,
      "grad_norm": 0.03453134745359421,
      "learning_rate": 2.20959595959596e-05,
      "loss": 0.1523,
      "step": 530
    },
    {
      "epoch": 6.0125,
      "grad_norm": 0.4955722689628601,
      "learning_rate": 2.1464646464646466e-05,
      "loss": 0.1371,
      "step": 540
    },
    {
      "epoch": 6.023863636363636,
      "grad_norm": 0.6915594339370728,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 0.0278,
      "step": 550
    },
    {
      "epoch": 6.035227272727273,
      "grad_norm": 0.030776426196098328,
      "learning_rate": 2.0202020202020203e-05,
      "loss": 0.0441,
      "step": 560
    },
    {
      "epoch": 6.046590909090909,
      "grad_norm": 0.008703567087650299,
      "learning_rate": 1.9570707070707073e-05,
      "loss": 0.0117,
      "step": 570
    },
    {
      "epoch": 6.057954545454545,
      "grad_norm": 12.471619606018066,
      "learning_rate": 1.893939393939394e-05,
      "loss": 0.0576,
      "step": 580
    },
    {
      "epoch": 6.069318181818182,
      "grad_norm": 0.023786788806319237,
      "learning_rate": 1.830808080808081e-05,
      "loss": 0.0282,
      "step": 590
    },
    {
      "epoch": 6.0806818181818185,
      "grad_norm": 0.24424441158771515,
      "learning_rate": 1.7676767676767676e-05,
      "loss": 0.1136,
      "step": 600
    },
    {
      "epoch": 6.092045454545454,
      "grad_norm": 0.014285405166447163,
      "learning_rate": 1.7045454545454546e-05,
      "loss": 0.0804,
      "step": 610
    },
    {
      "epoch": 6.1,
      "eval_f1": 0.6967864271457085,
      "eval_loss": 1.3787533044815063,
      "eval_runtime": 70.4409,
      "eval_samples_per_second": 2.726,
      "eval_steps_per_second": 0.341,
      "step": 617
    },
    {
      "epoch": 7.0034090909090905,
      "grad_norm": 0.14964497089385986,
      "learning_rate": 1.6414141414141416e-05,
      "loss": 0.0217,
      "step": 620
    },
    {
      "epoch": 7.014772727272727,
      "grad_norm": 22.6522274017334,
      "learning_rate": 1.5782828282828283e-05,
      "loss": 0.2281,
      "step": 630
    },
    {
      "epoch": 7.026136363636364,
      "grad_norm": 0.24736760556697845,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 0.0425,
      "step": 640
    },
    {
      "epoch": 7.0375,
      "grad_norm": 0.11569665372371674,
      "learning_rate": 1.452020202020202e-05,
      "loss": 0.004,
      "step": 650
    },
    {
      "epoch": 7.048863636363636,
      "grad_norm": 7.235473155975342,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.0268,
      "step": 660
    },
    {
      "epoch": 7.060227272727273,
      "grad_norm": 0.006639318075031042,
      "learning_rate": 1.3257575757575758e-05,
      "loss": 0.0387,
      "step": 670
    },
    {
      "epoch": 7.071590909090909,
      "grad_norm": 0.07593043893575668,
      "learning_rate": 1.2626262626262628e-05,
      "loss": 0.0685,
      "step": 680
    },
    {
      "epoch": 7.0829545454545455,
      "grad_norm": 0.02903686836361885,
      "learning_rate": 1.1994949494949495e-05,
      "loss": 0.0889,
      "step": 690
    },
    {
      "epoch": 7.094318181818182,
      "grad_norm": 0.10437527298927307,
      "learning_rate": 1.1363636363636365e-05,
      "loss": 0.0654,
      "step": 700
    },
    {
      "epoch": 7.1,
      "eval_f1": 0.697334455667789,
      "eval_loss": 1.2969599962234497,
      "eval_runtime": 75.4359,
      "eval_samples_per_second": 2.545,
      "eval_steps_per_second": 0.318,
      "step": 705
    },
    {
      "epoch": 8.005681818181818,
      "grad_norm": 0.3526234030723572,
      "learning_rate": 1.0732323232323233e-05,
      "loss": 0.1004,
      "step": 710
    },
    {
      "epoch": 8.017045454545455,
      "grad_norm": 0.544172465801239,
      "learning_rate": 1.0101010101010101e-05,
      "loss": 0.0323,
      "step": 720
    },
    {
      "epoch": 8.028409090909092,
      "grad_norm": 27.582374572753906,
      "learning_rate": 9.46969696969697e-06,
      "loss": 0.0817,
      "step": 730
    },
    {
      "epoch": 8.039772727272727,
      "grad_norm": 0.03466358035802841,
      "learning_rate": 8.838383838383838e-06,
      "loss": 0.033,
      "step": 740
    },
    {
      "epoch": 8.051136363636363,
      "grad_norm": 0.2677808105945587,
      "learning_rate": 8.207070707070708e-06,
      "loss": 0.0078,
      "step": 750
    },
    {
      "epoch": 8.0625,
      "grad_norm": 0.026267457753419876,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 0.1072,
      "step": 760
    },
    {
      "epoch": 8.073863636363637,
      "grad_norm": 0.036878038197755814,
      "learning_rate": 6.944444444444445e-06,
      "loss": 0.175,
      "step": 770
    },
    {
      "epoch": 8.085227272727273,
      "grad_norm": 3.7212748527526855,
      "learning_rate": 6.313131313131314e-06,
      "loss": 0.0646,
      "step": 780
    },
    {
      "epoch": 8.096590909090908,
      "grad_norm": 0.06381477415561676,
      "learning_rate": 5.681818181818182e-06,
      "loss": 0.0065,
      "step": 790
    },
    {
      "epoch": 8.1,
      "eval_f1": 0.7006284557943339,
      "eval_loss": 1.4780327081680298,
      "eval_runtime": 71.4359,
      "eval_samples_per_second": 2.688,
      "eval_steps_per_second": 0.336,
      "step": 793
    },
    {
      "epoch": 9.007954545454545,
      "grad_norm": 0.14042355120182037,
      "learning_rate": 5.050505050505051e-06,
      "loss": 0.0604,
      "step": 800
    },
    {
      "epoch": 9.019318181818182,
      "grad_norm": 0.007114021107554436,
      "learning_rate": 4.419191919191919e-06,
      "loss": 0.1103,
      "step": 810
    },
    {
      "epoch": 9.030681818181819,
      "grad_norm": 3.3601884841918945,
      "learning_rate": 3.7878787878787882e-06,
      "loss": 0.1139,
      "step": 820
    },
    {
      "epoch": 9.042045454545455,
      "grad_norm": 0.0043687219731509686,
      "learning_rate": 3.156565656565657e-06,
      "loss": 0.0034,
      "step": 830
    },
    {
      "epoch": 9.05340909090909,
      "grad_norm": 0.04162032902240753,
      "learning_rate": 2.5252525252525253e-06,
      "loss": 0.0108,
      "step": 840
    },
    {
      "epoch": 9.064772727272727,
      "grad_norm": 1.4939607381820679,
      "learning_rate": 1.8939393939393941e-06,
      "loss": 0.0889,
      "step": 850
    },
    {
      "epoch": 9.076136363636364,
      "grad_norm": 0.6243687868118286,
      "learning_rate": 1.2626262626262627e-06,
      "loss": 0.0082,
      "step": 860
    },
    {
      "epoch": 9.0875,
      "grad_norm": 0.010640038177371025,
      "learning_rate": 6.313131313131313e-07,
      "loss": 0.0318,
      "step": 870
    },
    {
      "epoch": 9.098863636363637,
      "grad_norm": 0.6547775864601135,
      "learning_rate": 0.0,
      "loss": 0.0024,
      "step": 880
    },
    {
      "epoch": 9.098863636363637,
      "eval_f1": 0.7006284557943339,
      "eval_loss": 1.4463977813720703,
      "eval_runtime": 70.5842,
      "eval_samples_per_second": 2.72,
      "eval_steps_per_second": 0.34,
      "step": 880
    },
    {
      "epoch": 9.098863636363637,
      "step": 880,
      "total_flos": 8.763572257754776e+18,
      "train_loss": 0.14181382804474033,
      "train_runtime": 4562.3352,
      "train_samples_per_second": 1.543,
      "train_steps_per_second": 0.193
    },
    {
      "epoch": 9.098863636363637,
      "eval_f1": 0.719188596491228,
      "eval_loss": 0.9494466781616211,
      "eval_runtime": 71.753,
      "eval_samples_per_second": 2.676,
      "eval_steps_per_second": 0.334,
      "step": 880
    },
    {
      "epoch": 9.098863636363637,
      "eval_f1": 0.719188596491228,
      "eval_loss": 0.9494466781616211,
      "eval_runtime": 72.4119,
      "eval_samples_per_second": 2.651,
      "eval_steps_per_second": 0.331,
      "step": 880
    }
  ],
  "logging_steps": 10,
  "max_steps": 880,
  "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": 8.763572257754776e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}