{
  "best_metric": 1.0,
  "best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-ucf101-subset/checkpoint-150",
  "epoch": 3.25,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 7.598509788513184,
      "learning_rate": 8.333333333333334e-06,
      "loss": 2.4116,
      "step": 10
    },
    {
      "epoch": 0.03,
      "grad_norm": 6.791835784912109,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.2528,
      "step": 20
    },
    {
      "epoch": 0.05,
      "grad_norm": 9.211247444152832,
      "learning_rate": 2.5e-05,
      "loss": 2.174,
      "step": 30
    },
    {
      "epoch": 0.07,
      "grad_norm": 10.301217079162598,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.9476,
      "step": 40
    },
    {
      "epoch": 0.08,
      "grad_norm": 18.361513137817383,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.6291,
      "step": 50
    },
    {
      "epoch": 0.1,
      "grad_norm": 11.685999870300293,
      "learning_rate": 5e-05,
      "loss": 1.2668,
      "step": 60
    },
    {
      "epoch": 0.12,
      "grad_norm": 11.85254955291748,
      "learning_rate": 4.9074074074074075e-05,
      "loss": 0.8018,
      "step": 70
    },
    {
      "epoch": 0.13,
      "grad_norm": 15.740757942199707,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.5169,
      "step": 80
    },
    {
      "epoch": 0.15,
      "grad_norm": 16.708358764648438,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.3612,
      "step": 90
    },
    {
      "epoch": 0.17,
      "grad_norm": 15.277067184448242,
      "learning_rate": 4.62962962962963e-05,
      "loss": 0.4588,
      "step": 100
    },
    {
      "epoch": 0.18,
      "grad_norm": 4.0264573097229,
      "learning_rate": 4.5370370370370374e-05,
      "loss": 0.4226,
      "step": 110
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.7405049204826355,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.2647,
      "step": 120
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.2769283354282379,
      "learning_rate": 4.351851851851852e-05,
      "loss": 0.1133,
      "step": 130
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.122069001197815,
      "learning_rate": 4.259259259259259e-05,
      "loss": 0.0637,
      "step": 140
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.7566676735877991,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.3086,
      "step": 150
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 1.0,
      "eval_loss": 0.052310943603515625,
      "eval_runtime": 14.6446,
      "eval_samples_per_second": 4.78,
      "eval_steps_per_second": 2.39,
      "step": 150
    },
    {
      "epoch": 1.02,
      "grad_norm": 1.8432053327560425,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.0807,
      "step": 160
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.3134633004665375,
      "learning_rate": 3.981481481481482e-05,
      "loss": 0.0536,
      "step": 170
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.6924269795417786,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.0177,
      "step": 180
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.4824039936065674,
      "learning_rate": 3.7962962962962964e-05,
      "loss": 0.0314,
      "step": 190
    },
    {
      "epoch": 1.08,
      "grad_norm": 1.2150177955627441,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.0142,
      "step": 200
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.16798992455005646,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.011,
      "step": 210
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.1268429458141327,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.028,
      "step": 220
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.17692790925502777,
      "learning_rate": 3.425925925925926e-05,
      "loss": 0.0136,
      "step": 230
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.0800652801990509,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0587,
      "step": 240
    },
    {
      "epoch": 1.17,
      "grad_norm": 23.463430404663086,
      "learning_rate": 3.240740740740741e-05,
      "loss": 0.0419,
      "step": 250
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.05798088386654854,
      "learning_rate": 3.148148148148148e-05,
      "loss": 0.0091,
      "step": 260
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.07833866775035858,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.0042,
      "step": 270
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.056700050830841064,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.0043,
      "step": 280
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.09460578858852386,
      "learning_rate": 2.8703703703703706e-05,
      "loss": 0.0606,
      "step": 290
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.11867497116327286,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.015,
      "step": 300
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 1.0,
      "eval_loss": 0.015603234060108662,
      "eval_runtime": 14.8429,
      "eval_samples_per_second": 4.716,
      "eval_steps_per_second": 2.358,
      "step": 300
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.030253833159804344,
      "learning_rate": 2.6851851851851855e-05,
      "loss": 0.0034,
      "step": 310
    },
    {
      "epoch": 2.03,
      "grad_norm": 0.6162285208702087,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.0037,
      "step": 320
    },
    {
      "epoch": 2.05,
      "grad_norm": 6.138050079345703,
      "learning_rate": 2.5e-05,
      "loss": 0.0217,
      "step": 330
    },
    {
      "epoch": 2.07,
      "grad_norm": 3.782101631164551,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.0083,
      "step": 340
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.1350020319223404,
      "learning_rate": 2.314814814814815e-05,
      "loss": 0.0031,
      "step": 350
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.02877243421971798,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0056,
      "step": 360
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.031173015013337135,
      "learning_rate": 2.1296296296296296e-05,
      "loss": 0.0024,
      "step": 370
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.06308965384960175,
      "learning_rate": 2.037037037037037e-05,
      "loss": 0.0023,
      "step": 380
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.0642421543598175,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.0026,
      "step": 390
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.06370634585618973,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.0037,
      "step": 400
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.04718124493956566,
      "learning_rate": 1.7592592592592595e-05,
      "loss": 0.0021,
      "step": 410
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.1230979934334755,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0025,
      "step": 420
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.033714938908815384,
      "learning_rate": 1.574074074074074e-05,
      "loss": 0.0024,
      "step": 430
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.2393726110458374,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.0021,
      "step": 440
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.032503824681043625,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.0021,
      "step": 450
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0036879994440823793,
      "eval_runtime": 14.7718,
      "eval_samples_per_second": 4.739,
      "eval_steps_per_second": 2.369,
      "step": 450
    },
    {
      "epoch": 3.02,
      "grad_norm": 0.03539320081472397,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 0.002,
      "step": 460
    },
    {
      "epoch": 3.03,
      "grad_norm": 0.033613573759794235,
      "learning_rate": 1.2037037037037037e-05,
      "loss": 0.0022,
      "step": 470
    },
    {
      "epoch": 3.05,
      "grad_norm": 0.023656120523810387,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0019,
      "step": 480
    },
    {
      "epoch": 3.07,
      "grad_norm": 0.022654222324490547,
      "learning_rate": 1.0185185185185185e-05,
      "loss": 0.0017,
      "step": 490
    },
    {
      "epoch": 3.08,
      "grad_norm": 0.022414449602365494,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.0015,
      "step": 500
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.023360515013337135,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.0019,
      "step": 510
    },
    {
      "epoch": 3.12,
      "grad_norm": 0.028055280447006226,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0025,
      "step": 520
    },
    {
      "epoch": 3.13,
      "grad_norm": 0.060272928327322006,
      "learning_rate": 6.481481481481481e-06,
      "loss": 0.0033,
      "step": 530
    },
    {
      "epoch": 3.15,
      "grad_norm": 0.03611369803547859,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.0075,
      "step": 540
    },
    {
      "epoch": 3.17,
      "grad_norm": 0.041965924203395844,
      "learning_rate": 4.6296296296296296e-06,
      "loss": 0.002,
      "step": 550
    },
    {
      "epoch": 3.18,
      "grad_norm": 0.019477233290672302,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.002,
      "step": 560
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.0196684617549181,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.0015,
      "step": 570
    },
    {
      "epoch": 3.22,
      "grad_norm": 0.03391743823885918,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.0024,
      "step": 580
    },
    {
      "epoch": 3.23,
      "grad_norm": 0.0371902659535408,
      "learning_rate": 9.259259259259259e-07,
      "loss": 0.0024,
      "step": 590
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.1518806666135788,
      "learning_rate": 0.0,
      "loss": 0.0063,
      "step": 600
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 1.0,
      "eval_loss": 0.003852277062833309,
      "eval_runtime": 15.3031,
      "eval_samples_per_second": 4.574,
      "eval_steps_per_second": 2.287,
      "step": 600
    },
    {
      "epoch": 3.25,
      "step": 600,
      "total_flos": 1.495384188125184e+18,
      "train_loss": 0.2591129653466245,
      "train_runtime": 638.4667,
      "train_samples_per_second": 1.88,
      "train_steps_per_second": 0.94
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.9870967741935484,
      "eval_loss": 0.07424493879079819,
      "eval_runtime": 33.2975,
      "eval_samples_per_second": 4.655,
      "eval_steps_per_second": 2.343,
      "step": 600
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.9870967741935484,
      "eval_loss": 0.07424493879079819,
      "eval_runtime": 33.4434,
      "eval_samples_per_second": 4.635,
      "eval_steps_per_second": 2.332,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 1.495384188125184e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}