{
  "best_metric": 0.6436170212765957,
  "best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-conflab-traj-direction-lh-v1/checkpoint-630",
  "epoch": 6.134615384615385,
  "eval_steps": 500,
  "global_step": 728,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013736263736263736,
      "grad_norm": 7.975502967834473,
      "learning_rate": 6.849315068493151e-06,
      "loss": 2.1354,
      "step": 10
    },
    {
      "epoch": 0.027472527472527472,
      "grad_norm": 6.625336647033691,
      "learning_rate": 1.3698630136986302e-05,
      "loss": 2.0408,
      "step": 20
    },
    {
      "epoch": 0.04120879120879121,
      "grad_norm": 6.562021732330322,
      "learning_rate": 2.0547945205479453e-05,
      "loss": 1.9823,
      "step": 30
    },
    {
      "epoch": 0.054945054945054944,
      "grad_norm": 6.1020612716674805,
      "learning_rate": 2.7397260273972603e-05,
      "loss": 1.8703,
      "step": 40
    },
    {
      "epoch": 0.06868131868131869,
      "grad_norm": 5.716378211975098,
      "learning_rate": 3.424657534246575e-05,
      "loss": 1.938,
      "step": 50
    },
    {
      "epoch": 0.08241758241758242,
      "grad_norm": 10.489607810974121,
      "learning_rate": 4.1095890410958905e-05,
      "loss": 1.9538,
      "step": 60
    },
    {
      "epoch": 0.09615384615384616,
      "grad_norm": 7.923999786376953,
      "learning_rate": 4.794520547945205e-05,
      "loss": 1.8729,
      "step": 70
    },
    {
      "epoch": 0.10989010989010989,
      "grad_norm": 6.225552082061768,
      "learning_rate": 4.9465648854961834e-05,
      "loss": 1.8932,
      "step": 80
    },
    {
      "epoch": 0.12362637362637363,
      "grad_norm": 5.54323673248291,
      "learning_rate": 4.8702290076335885e-05,
      "loss": 1.785,
      "step": 90
    },
    {
      "epoch": 0.13736263736263737,
      "grad_norm": 8.549125671386719,
      "learning_rate": 4.793893129770993e-05,
      "loss": 1.6395,
      "step": 100
    },
    {
      "epoch": 0.14423076923076922,
      "eval_accuracy": 0.3723404255319149,
      "eval_loss": 1.6255276203155518,
      "eval_runtime": 26.9945,
      "eval_samples_per_second": 6.964,
      "eval_steps_per_second": 0.889,
      "step": 105
    },
    {
      "epoch": 1.0068681318681318,
      "grad_norm": 5.713430404663086,
      "learning_rate": 4.717557251908397e-05,
      "loss": 1.6571,
      "step": 110
    },
    {
      "epoch": 1.0206043956043955,
      "grad_norm": 10.411270141601562,
      "learning_rate": 4.641221374045801e-05,
      "loss": 1.7831,
      "step": 120
    },
    {
      "epoch": 1.0343406593406594,
      "grad_norm": 7.114817142486572,
      "learning_rate": 4.5648854961832065e-05,
      "loss": 1.4513,
      "step": 130
    },
    {
      "epoch": 1.0480769230769231,
      "grad_norm": 8.18074893951416,
      "learning_rate": 4.488549618320611e-05,
      "loss": 1.6207,
      "step": 140
    },
    {
      "epoch": 1.0618131868131868,
      "grad_norm": 8.822683334350586,
      "learning_rate": 4.4122137404580154e-05,
      "loss": 1.6768,
      "step": 150
    },
    {
      "epoch": 1.0755494505494505,
      "grad_norm": 9.030908584594727,
      "learning_rate": 4.33587786259542e-05,
      "loss": 1.4562,
      "step": 160
    },
    {
      "epoch": 1.0892857142857142,
      "grad_norm": 7.88232421875,
      "learning_rate": 4.2595419847328244e-05,
      "loss": 1.4371,
      "step": 170
    },
    {
      "epoch": 1.103021978021978,
      "grad_norm": 10.967424392700195,
      "learning_rate": 4.1832061068702296e-05,
      "loss": 1.5417,
      "step": 180
    },
    {
      "epoch": 1.1167582417582418,
      "grad_norm": 6.950323104858398,
      "learning_rate": 4.106870229007634e-05,
      "loss": 1.3942,
      "step": 190
    },
    {
      "epoch": 1.1304945054945055,
      "grad_norm": 8.856796264648438,
      "learning_rate": 4.0305343511450385e-05,
      "loss": 1.3338,
      "step": 200
    },
    {
      "epoch": 1.1442307692307692,
      "grad_norm": 8.829967498779297,
      "learning_rate": 3.954198473282443e-05,
      "loss": 1.4009,
      "step": 210
    },
    {
      "epoch": 1.1442307692307692,
      "eval_accuracy": 0.5053191489361702,
      "eval_loss": 1.4288405179977417,
      "eval_runtime": 21.3032,
      "eval_samples_per_second": 8.825,
      "eval_steps_per_second": 1.127,
      "step": 210
    },
    {
      "epoch": 2.0137362637362637,
      "grad_norm": 7.487637519836426,
      "learning_rate": 3.8778625954198475e-05,
      "loss": 1.2009,
      "step": 220
    },
    {
      "epoch": 2.0274725274725274,
      "grad_norm": 6.921274662017822,
      "learning_rate": 3.801526717557252e-05,
      "loss": 0.8766,
      "step": 230
    },
    {
      "epoch": 2.041208791208791,
      "grad_norm": 8.127293586730957,
      "learning_rate": 3.7251908396946565e-05,
      "loss": 1.0099,
      "step": 240
    },
    {
      "epoch": 2.0549450549450547,
      "grad_norm": 13.09719467163086,
      "learning_rate": 3.648854961832061e-05,
      "loss": 1.2435,
      "step": 250
    },
    {
      "epoch": 2.068681318681319,
      "grad_norm": 9.744394302368164,
      "learning_rate": 3.5725190839694654e-05,
      "loss": 0.9877,
      "step": 260
    },
    {
      "epoch": 2.0824175824175826,
      "grad_norm": 10.143108367919922,
      "learning_rate": 3.4961832061068706e-05,
      "loss": 1.1423,
      "step": 270
    },
    {
      "epoch": 2.0961538461538463,
      "grad_norm": 11.305399894714355,
      "learning_rate": 3.419847328244275e-05,
      "loss": 1.0389,
      "step": 280
    },
    {
      "epoch": 2.10989010989011,
      "grad_norm": 11.219425201416016,
      "learning_rate": 3.3435114503816796e-05,
      "loss": 0.8836,
      "step": 290
    },
    {
      "epoch": 2.1236263736263736,
      "grad_norm": 8.758235931396484,
      "learning_rate": 3.267175572519084e-05,
      "loss": 0.8425,
      "step": 300
    },
    {
      "epoch": 2.1373626373626373,
      "grad_norm": 11.10839557647705,
      "learning_rate": 3.190839694656489e-05,
      "loss": 1.0856,
      "step": 310
    },
    {
      "epoch": 2.144230769230769,
      "eval_accuracy": 0.574468085106383,
      "eval_loss": 1.2734872102737427,
      "eval_runtime": 25.3393,
      "eval_samples_per_second": 7.419,
      "eval_steps_per_second": 0.947,
      "step": 315
    },
    {
      "epoch": 3.006868131868132,
      "grad_norm": 6.112276077270508,
      "learning_rate": 3.114503816793894e-05,
      "loss": 1.0481,
      "step": 320
    },
    {
      "epoch": 3.0206043956043955,
      "grad_norm": 3.976270914077759,
      "learning_rate": 3.038167938931298e-05,
      "loss": 0.6704,
      "step": 330
    },
    {
      "epoch": 3.034340659340659,
      "grad_norm": 6.606512069702148,
      "learning_rate": 2.9618320610687023e-05,
      "loss": 0.6002,
      "step": 340
    },
    {
      "epoch": 3.048076923076923,
      "grad_norm": 8.499869346618652,
      "learning_rate": 2.885496183206107e-05,
      "loss": 0.576,
      "step": 350
    },
    {
      "epoch": 3.061813186813187,
      "grad_norm": 4.2253499031066895,
      "learning_rate": 2.8091603053435116e-05,
      "loss": 0.4514,
      "step": 360
    },
    {
      "epoch": 3.0755494505494507,
      "grad_norm": 8.19430923461914,
      "learning_rate": 2.732824427480916e-05,
      "loss": 0.6574,
      "step": 370
    },
    {
      "epoch": 3.0892857142857144,
      "grad_norm": 16.499576568603516,
      "learning_rate": 2.6564885496183206e-05,
      "loss": 0.7088,
      "step": 380
    },
    {
      "epoch": 3.103021978021978,
      "grad_norm": 15.13383960723877,
      "learning_rate": 2.580152671755725e-05,
      "loss": 0.7706,
      "step": 390
    },
    {
      "epoch": 3.116758241758242,
      "grad_norm": 10.932879447937012,
      "learning_rate": 2.50381679389313e-05,
      "loss": 0.3813,
      "step": 400
    },
    {
      "epoch": 3.1304945054945055,
      "grad_norm": 7.318915843963623,
      "learning_rate": 2.4274809160305344e-05,
      "loss": 0.4513,
      "step": 410
    },
    {
      "epoch": 3.144230769230769,
      "grad_norm": 11.104874610900879,
      "learning_rate": 2.351145038167939e-05,
      "loss": 0.6975,
      "step": 420
    },
    {
      "epoch": 3.144230769230769,
      "eval_accuracy": 0.6063829787234043,
      "eval_loss": 1.2628591060638428,
      "eval_runtime": 22.8443,
      "eval_samples_per_second": 8.23,
      "eval_steps_per_second": 1.051,
      "step": 420
    },
    {
      "epoch": 4.013736263736264,
      "grad_norm": 5.155519008636475,
      "learning_rate": 2.2748091603053437e-05,
      "loss": 0.2989,
      "step": 430
    },
    {
      "epoch": 4.027472527472527,
      "grad_norm": 2.615933656692505,
      "learning_rate": 2.198473282442748e-05,
      "loss": 0.3818,
      "step": 440
    },
    {
      "epoch": 4.041208791208791,
      "grad_norm": 9.644124031066895,
      "learning_rate": 2.122137404580153e-05,
      "loss": 0.4455,
      "step": 450
    },
    {
      "epoch": 4.054945054945055,
      "grad_norm": 5.017002105712891,
      "learning_rate": 2.0458015267175575e-05,
      "loss": 0.3644,
      "step": 460
    },
    {
      "epoch": 4.068681318681318,
      "grad_norm": 10.373658180236816,
      "learning_rate": 1.969465648854962e-05,
      "loss": 0.3132,
      "step": 470
    },
    {
      "epoch": 4.082417582417582,
      "grad_norm": 11.175583839416504,
      "learning_rate": 1.8931297709923664e-05,
      "loss": 0.3601,
      "step": 480
    },
    {
      "epoch": 4.096153846153846,
      "grad_norm": 6.8020172119140625,
      "learning_rate": 1.816793893129771e-05,
      "loss": 0.3351,
      "step": 490
    },
    {
      "epoch": 4.1098901098901095,
      "grad_norm": 6.1250810623168945,
      "learning_rate": 1.7404580152671757e-05,
      "loss": 0.3077,
      "step": 500
    },
    {
      "epoch": 4.123626373626374,
      "grad_norm": 20.65755844116211,
      "learning_rate": 1.6641221374045802e-05,
      "loss": 0.3634,
      "step": 510
    },
    {
      "epoch": 4.137362637362638,
      "grad_norm": 20.21697235107422,
      "learning_rate": 1.5877862595419847e-05,
      "loss": 0.3574,
      "step": 520
    },
    {
      "epoch": 4.144230769230769,
      "eval_accuracy": 0.6170212765957447,
      "eval_loss": 1.2030434608459473,
      "eval_runtime": 24.5243,
      "eval_samples_per_second": 7.666,
      "eval_steps_per_second": 0.979,
      "step": 525
    },
    {
      "epoch": 5.006868131868132,
      "grad_norm": 10.236026763916016,
      "learning_rate": 1.5114503816793894e-05,
      "loss": 0.2425,
      "step": 530
    },
    {
      "epoch": 5.020604395604396,
      "grad_norm": 3.8250298500061035,
      "learning_rate": 1.435114503816794e-05,
      "loss": 0.1923,
      "step": 540
    },
    {
      "epoch": 5.03434065934066,
      "grad_norm": 6.404925346374512,
      "learning_rate": 1.3587786259541985e-05,
      "loss": 0.1586,
      "step": 550
    },
    {
      "epoch": 5.048076923076923,
      "grad_norm": 4.29252815246582,
      "learning_rate": 1.2824427480916032e-05,
      "loss": 0.1486,
      "step": 560
    },
    {
      "epoch": 5.061813186813187,
      "grad_norm": 3.185380220413208,
      "learning_rate": 1.2061068702290076e-05,
      "loss": 0.1221,
      "step": 570
    },
    {
      "epoch": 5.075549450549451,
      "grad_norm": 6.5659918785095215,
      "learning_rate": 1.1297709923664123e-05,
      "loss": 0.2548,
      "step": 580
    },
    {
      "epoch": 5.089285714285714,
      "grad_norm": 4.746553897857666,
      "learning_rate": 1.0534351145038168e-05,
      "loss": 0.1904,
      "step": 590
    },
    {
      "epoch": 5.103021978021978,
      "grad_norm": 2.2111618518829346,
      "learning_rate": 9.770992366412214e-06,
      "loss": 0.2278,
      "step": 600
    },
    {
      "epoch": 5.116758241758242,
      "grad_norm": 0.6979553699493408,
      "learning_rate": 9.00763358778626e-06,
      "loss": 0.071,
      "step": 610
    },
    {
      "epoch": 5.1304945054945055,
      "grad_norm": 1.7735334634780884,
      "learning_rate": 8.244274809160306e-06,
      "loss": 0.218,
      "step": 620
    },
    {
      "epoch": 5.144230769230769,
      "grad_norm": 29.469202041625977,
      "learning_rate": 7.480916030534352e-06,
      "loss": 0.1654,
      "step": 630
    },
    {
      "epoch": 5.144230769230769,
      "eval_accuracy": 0.6436170212765957,
      "eval_loss": 1.2649437189102173,
      "eval_runtime": 33.5955,
      "eval_samples_per_second": 5.596,
      "eval_steps_per_second": 0.714,
      "step": 630
    },
    {
      "epoch": 6.013736263736264,
      "grad_norm": 0.3265649080276489,
      "learning_rate": 6.717557251908398e-06,
      "loss": 0.0701,
      "step": 640
    },
    {
      "epoch": 6.027472527472527,
      "grad_norm": 4.214682102203369,
      "learning_rate": 5.954198473282443e-06,
      "loss": 0.0474,
      "step": 650
    },
    {
      "epoch": 6.041208791208791,
      "grad_norm": 4.0008697509765625,
      "learning_rate": 5.190839694656488e-06,
      "loss": 0.1185,
      "step": 660
    },
    {
      "epoch": 6.054945054945055,
      "grad_norm": 16.712289810180664,
      "learning_rate": 4.427480916030535e-06,
      "loss": 0.0714,
      "step": 670
    },
    {
      "epoch": 6.068681318681318,
      "grad_norm": 1.800746202468872,
      "learning_rate": 3.6641221374045806e-06,
      "loss": 0.1259,
      "step": 680
    },
    {
      "epoch": 6.082417582417582,
      "grad_norm": 2.648703098297119,
      "learning_rate": 2.900763358778626e-06,
      "loss": 0.0904,
      "step": 690
    },
    {
      "epoch": 6.096153846153846,
      "grad_norm": 0.37296178936958313,
      "learning_rate": 2.137404580152672e-06,
      "loss": 0.0844,
      "step": 700
    },
    {
      "epoch": 6.1098901098901095,
      "grad_norm": 3.3622076511383057,
      "learning_rate": 1.3740458015267176e-06,
      "loss": 0.0761,
      "step": 710
    },
    {
      "epoch": 6.123626373626374,
      "grad_norm": 17.910383224487305,
      "learning_rate": 6.106870229007634e-07,
      "loss": 0.1179,
      "step": 720
    },
    {
      "epoch": 6.134615384615385,
      "eval_accuracy": 0.6329787234042553,
      "eval_loss": 1.2938581705093384,
      "eval_runtime": 21.981,
      "eval_samples_per_second": 8.553,
      "eval_steps_per_second": 1.092,
      "step": 728
    },
    {
      "epoch": 6.134615384615385,
      "step": 728,
      "total_flos": 7.220084549098144e+18,
      "train_loss": 0.8182922416663432,
      "train_runtime": 1426.9497,
      "train_samples_per_second": 4.081,
      "train_steps_per_second": 0.51
    },
    {
      "epoch": 6.134615384615385,
      "eval_accuracy": 0.6096256684491979,
      "eval_loss": 1.3609111309051514,
      "eval_runtime": 26.248,
      "eval_samples_per_second": 7.124,
      "eval_steps_per_second": 0.914,
      "step": 728
    },
    {
      "epoch": 6.134615384615385,
      "eval_accuracy": 0.6096256684491979,
      "eval_loss": 1.3609113693237305,
      "eval_runtime": 22.0997,
      "eval_samples_per_second": 8.462,
      "eval_steps_per_second": 1.086,
      "step": 728
    }
  ],
  "logging_steps": 10,
  "max_steps": 728,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 7.220084549098144e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}