{
  "best_metric": 0.3429557577659241,
  "best_model_checkpoint": "timesformer-base-finetuned-k400-finetuned-elder/checkpoint-145",
  "epoch": 3.2447916666666665,
  "eval_steps": 500,
  "global_step": 576,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 11.353941917419434,
      "learning_rate": 8.620689655172414e-06,
      "loss": 1.8739,
      "step": 10
    },
    {
      "epoch": 0.03,
      "grad_norm": 11.876654624938965,
      "learning_rate": 1.7241379310344828e-05,
      "loss": 1.7689,
      "step": 20
    },
    {
      "epoch": 0.05,
      "grad_norm": 9.898606300354004,
      "learning_rate": 2.5862068965517244e-05,
      "loss": 1.6938,
      "step": 30
    },
    {
      "epoch": 0.07,
      "grad_norm": 11.877754211425781,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 1.6831,
      "step": 40
    },
    {
      "epoch": 0.09,
      "grad_norm": 11.96393871307373,
      "learning_rate": 4.3103448275862066e-05,
      "loss": 1.8106,
      "step": 50
    },
    {
      "epoch": 0.1,
      "grad_norm": 11.26883316040039,
      "learning_rate": 4.980694980694981e-05,
      "loss": 1.7056,
      "step": 60
    },
    {
      "epoch": 0.12,
      "grad_norm": 10.789453506469727,
      "learning_rate": 4.884169884169885e-05,
      "loss": 1.8426,
      "step": 70
    },
    {
      "epoch": 0.14,
      "grad_norm": 11.942329406738281,
      "learning_rate": 4.787644787644788e-05,
      "loss": 1.8344,
      "step": 80
    },
    {
      "epoch": 0.16,
      "grad_norm": 9.601066589355469,
      "learning_rate": 4.6911196911196914e-05,
      "loss": 1.6152,
      "step": 90
    },
    {
      "epoch": 0.17,
      "grad_norm": 7.940020561218262,
      "learning_rate": 4.594594594594595e-05,
      "loss": 1.661,
      "step": 100
    },
    {
      "epoch": 0.19,
      "grad_norm": 8.261001586914062,
      "learning_rate": 4.498069498069498e-05,
      "loss": 1.7736,
      "step": 110
    },
    {
      "epoch": 0.21,
      "grad_norm": 10.65363883972168,
      "learning_rate": 4.401544401544402e-05,
      "loss": 1.6354,
      "step": 120
    },
    {
      "epoch": 0.23,
      "grad_norm": 7.867549896240234,
      "learning_rate": 4.305019305019305e-05,
      "loss": 1.7635,
      "step": 130
    },
    {
      "epoch": 0.24,
      "grad_norm": 5.6440958976745605,
      "learning_rate": 4.2084942084942086e-05,
      "loss": 1.5696,
      "step": 140
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.3429557577659241,
      "eval_loss": 1.6705849170684814,
      "eval_runtime": 1154.9511,
      "eval_samples_per_second": 2.759,
      "eval_steps_per_second": 0.345,
      "step": 145
    },
    {
      "epoch": 1.01,
      "grad_norm": 10.702627182006836,
      "learning_rate": 4.111969111969112e-05,
      "loss": 1.622,
      "step": 150
    },
    {
      "epoch": 1.03,
      "grad_norm": 8.490106582641602,
      "learning_rate": 4.015444015444015e-05,
      "loss": 1.6023,
      "step": 160
    },
    {
      "epoch": 1.04,
      "grad_norm": 8.917444229125977,
      "learning_rate": 3.918918918918919e-05,
      "loss": 1.553,
      "step": 170
    },
    {
      "epoch": 1.06,
      "grad_norm": 7.563806533813477,
      "learning_rate": 3.822393822393823e-05,
      "loss": 1.7744,
      "step": 180
    },
    {
      "epoch": 1.08,
      "grad_norm": 12.07093334197998,
      "learning_rate": 3.725868725868726e-05,
      "loss": 1.6268,
      "step": 190
    },
    {
      "epoch": 1.1,
      "grad_norm": 10.829654693603516,
      "learning_rate": 3.6293436293436295e-05,
      "loss": 1.7149,
      "step": 200
    },
    {
      "epoch": 1.11,
      "grad_norm": 7.444002628326416,
      "learning_rate": 3.532818532818533e-05,
      "loss": 1.6117,
      "step": 210
    },
    {
      "epoch": 1.13,
      "grad_norm": 8.430509567260742,
      "learning_rate": 3.436293436293436e-05,
      "loss": 1.5871,
      "step": 220
    },
    {
      "epoch": 1.15,
      "grad_norm": 7.962520122528076,
      "learning_rate": 3.33976833976834e-05,
      "loss": 1.6071,
      "step": 230
    },
    {
      "epoch": 1.16,
      "grad_norm": 6.775651454925537,
      "learning_rate": 3.2432432432432436e-05,
      "loss": 1.5901,
      "step": 240
    },
    {
      "epoch": 1.18,
      "grad_norm": 8.024240493774414,
      "learning_rate": 3.1467181467181466e-05,
      "loss": 1.5367,
      "step": 250
    },
    {
      "epoch": 1.2,
      "grad_norm": 6.758663177490234,
      "learning_rate": 3.0501930501930504e-05,
      "loss": 1.5108,
      "step": 260
    },
    {
      "epoch": 1.22,
      "grad_norm": 4.902159690856934,
      "learning_rate": 2.953667953667954e-05,
      "loss": 1.6178,
      "step": 270
    },
    {
      "epoch": 1.23,
      "grad_norm": 8.776327133178711,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.5294,
      "step": 280
    },
    {
      "epoch": 1.25,
      "grad_norm": 7.898609638214111,
      "learning_rate": 2.7606177606177608e-05,
      "loss": 1.5394,
      "step": 290
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 0.3250705993096956,
      "eval_loss": 1.6106971502304077,
      "eval_runtime": 810.1945,
      "eval_samples_per_second": 3.934,
      "eval_steps_per_second": 0.492,
      "step": 290
    },
    {
      "epoch": 2.02,
      "grad_norm": 8.846714973449707,
      "learning_rate": 2.6640926640926645e-05,
      "loss": 1.4717,
      "step": 300
    },
    {
      "epoch": 2.03,
      "grad_norm": 6.829111099243164,
      "learning_rate": 2.5675675675675675e-05,
      "loss": 1.6512,
      "step": 310
    },
    {
      "epoch": 2.05,
      "grad_norm": 7.631171226501465,
      "learning_rate": 2.4710424710424712e-05,
      "loss": 1.5668,
      "step": 320
    },
    {
      "epoch": 2.07,
      "grad_norm": 8.5497465133667,
      "learning_rate": 2.3745173745173746e-05,
      "loss": 1.4588,
      "step": 330
    },
    {
      "epoch": 2.09,
      "grad_norm": 11.353889465332031,
      "learning_rate": 2.277992277992278e-05,
      "loss": 1.531,
      "step": 340
    },
    {
      "epoch": 2.1,
      "grad_norm": 11.622316360473633,
      "learning_rate": 2.1814671814671817e-05,
      "loss": 1.4747,
      "step": 350
    },
    {
      "epoch": 2.12,
      "grad_norm": 5.152277946472168,
      "learning_rate": 2.084942084942085e-05,
      "loss": 1.6246,
      "step": 360
    },
    {
      "epoch": 2.14,
      "grad_norm": 8.466754913330078,
      "learning_rate": 1.9884169884169884e-05,
      "loss": 1.6078,
      "step": 370
    },
    {
      "epoch": 2.16,
      "grad_norm": 9.230478286743164,
      "learning_rate": 1.891891891891892e-05,
      "loss": 1.4345,
      "step": 380
    },
    {
      "epoch": 2.17,
      "grad_norm": 6.181694507598877,
      "learning_rate": 1.7953667953667955e-05,
      "loss": 1.4972,
      "step": 390
    },
    {
      "epoch": 2.19,
      "grad_norm": 5.838415622711182,
      "learning_rate": 1.698841698841699e-05,
      "loss": 1.5436,
      "step": 400
    },
    {
      "epoch": 2.21,
      "grad_norm": 5.769914627075195,
      "learning_rate": 1.6023166023166026e-05,
      "loss": 1.4575,
      "step": 410
    },
    {
      "epoch": 2.23,
      "grad_norm": 13.202679634094238,
      "learning_rate": 1.505791505791506e-05,
      "loss": 1.6595,
      "step": 420
    },
    {
      "epoch": 2.24,
      "grad_norm": 6.772584438323975,
      "learning_rate": 1.4092664092664093e-05,
      "loss": 1.3926,
      "step": 430
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 0.3115782867900847,
      "eval_loss": 1.6140949726104736,
      "eval_runtime": 852.1564,
      "eval_samples_per_second": 3.74,
      "eval_steps_per_second": 0.468,
      "step": 435
    },
    {
      "epoch": 3.01,
      "grad_norm": 14.996703147888184,
      "learning_rate": 1.3127413127413127e-05,
      "loss": 1.4789,
      "step": 440
    },
    {
      "epoch": 3.03,
      "grad_norm": 11.151080131530762,
      "learning_rate": 1.2162162162162164e-05,
      "loss": 1.3946,
      "step": 450
    },
    {
      "epoch": 3.04,
      "grad_norm": 18.826932907104492,
      "learning_rate": 1.1196911196911197e-05,
      "loss": 1.4647,
      "step": 460
    },
    {
      "epoch": 3.06,
      "grad_norm": 7.545161247253418,
      "learning_rate": 1.0231660231660233e-05,
      "loss": 1.4306,
      "step": 470
    },
    {
      "epoch": 3.08,
      "grad_norm": 6.167401313781738,
      "learning_rate": 9.266409266409266e-06,
      "loss": 1.4875,
      "step": 480
    },
    {
      "epoch": 3.1,
      "grad_norm": 6.006252288818359,
      "learning_rate": 8.301158301158302e-06,
      "loss": 1.3679,
      "step": 490
    },
    {
      "epoch": 3.11,
      "grad_norm": 11.11434555053711,
      "learning_rate": 7.335907335907337e-06,
      "loss": 1.3347,
      "step": 500
    },
    {
      "epoch": 3.13,
      "grad_norm": 14.269789695739746,
      "learning_rate": 6.370656370656371e-06,
      "loss": 1.5499,
      "step": 510
    },
    {
      "epoch": 3.15,
      "grad_norm": 10.421883583068848,
      "learning_rate": 5.405405405405406e-06,
      "loss": 1.3448,
      "step": 520
    },
    {
      "epoch": 3.16,
      "grad_norm": 7.902385234832764,
      "learning_rate": 4.4401544401544405e-06,
      "loss": 1.588,
      "step": 530
    },
    {
      "epoch": 3.18,
      "grad_norm": 7.623480796813965,
      "learning_rate": 3.474903474903475e-06,
      "loss": 1.3432,
      "step": 540
    },
    {
      "epoch": 3.2,
      "grad_norm": 8.848978996276855,
      "learning_rate": 2.5096525096525096e-06,
      "loss": 1.5031,
      "step": 550
    },
    {
      "epoch": 3.22,
      "grad_norm": 6.524665355682373,
      "learning_rate": 1.5444015444015445e-06,
      "loss": 1.4014,
      "step": 560
    },
    {
      "epoch": 3.23,
      "grad_norm": 11.393948554992676,
      "learning_rate": 5.791505791505791e-07,
      "loss": 1.5686,
      "step": 570
    },
    {
      "epoch": 3.24,
      "eval_accuracy": 0.30059617194854094,
      "eval_loss": 1.634132981300354,
      "eval_runtime": 934.7118,
      "eval_samples_per_second": 3.41,
      "eval_steps_per_second": 0.427,
      "step": 576
    },
    {
      "epoch": 3.24,
      "step": 576,
      "total_flos": 4.0295036866264105e+18,
      "train_loss": 1.5763822098573048,
      "train_runtime": 8421.9334,
      "train_samples_per_second": 0.547,
      "train_steps_per_second": 0.068
    },
    {
      "epoch": 3.24,
      "eval_accuracy": 0.3428783934548159,
      "eval_loss": 1.694771409034729,
      "eval_runtime": 743.9046,
      "eval_samples_per_second": 3.615,
      "eval_steps_per_second": 0.453,
      "step": 576
    },
    {
      "epoch": 3.24,
      "eval_accuracy": 0.3428783934548159,
      "eval_loss": 1.694771409034729,
      "eval_runtime": 695.3156,
      "eval_samples_per_second": 3.867,
      "eval_steps_per_second": 0.485,
      "step": 576
    }
  ],
  "logging_steps": 10,
  "max_steps": 576,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 4.0295036866264105e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}