{
  "best_metric": 0.9857142857142858,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset\\checkpoint-450",
  "epoch": 7.125,
  "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,
      "learning_rate": 8.333333333333334e-06,
      "loss": 2.2978,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.3358,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.5e-05,
      "loss": 2.2275,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.089,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.166666666666667e-05,
      "loss": 2.1821,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 2.1127,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.9074074074074075e-05,
      "loss": 2.1133,
      "step": 70
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.5714285714285714,
      "eval_loss": 1.7146133184432983,
      "eval_runtime": 11.5588,
      "eval_samples_per_second": 6.056,
      "eval_steps_per_second": 1.557,
      "step": 75
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.814814814814815e-05,
      "loss": 1.8009,
      "step": 80
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.722222222222222e-05,
      "loss": 1.4562,
      "step": 90
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.62962962962963e-05,
      "loss": 1.2443,
      "step": 100
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.5370370370370374e-05,
      "loss": 0.9894,
      "step": 110
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.0393,
      "step": 120
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.351851851851852e-05,
      "loss": 0.8615,
      "step": 130
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.259259259259259e-05,
      "loss": 0.705,
      "step": 140
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.9959,
      "step": 150
    },
    {
      "epoch": 1.12,
      "eval_accuracy": 0.6714285714285714,
      "eval_loss": 0.9590635299682617,
      "eval_runtime": 11.7222,
      "eval_samples_per_second": 5.972,
      "eval_steps_per_second": 1.536,
      "step": 150
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.5548,
      "step": 160
    },
    {
      "epoch": 2.03,
      "learning_rate": 3.981481481481482e-05,
      "loss": 0.616,
      "step": 170
    },
    {
      "epoch": 2.05,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.5153,
      "step": 180
    },
    {
      "epoch": 2.07,
      "learning_rate": 3.7962962962962964e-05,
      "loss": 0.6135,
      "step": 190
    },
    {
      "epoch": 2.08,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.5949,
      "step": 200
    },
    {
      "epoch": 2.1,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.3295,
      "step": 210
    },
    {
      "epoch": 2.12,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.4202,
      "step": 220
    },
    {
      "epoch": 2.12,
      "eval_accuracy": 0.8285714285714286,
      "eval_loss": 0.3952118456363678,
      "eval_runtime": 11.5934,
      "eval_samples_per_second": 6.038,
      "eval_steps_per_second": 1.553,
      "step": 225
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.425925925925926e-05,
      "loss": 0.3022,
      "step": 230
    },
    {
      "epoch": 3.02,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1603,
      "step": 240
    },
    {
      "epoch": 3.04,
      "learning_rate": 3.240740740740741e-05,
      "loss": 0.2083,
      "step": 250
    },
    {
      "epoch": 3.06,
      "learning_rate": 3.148148148148148e-05,
      "loss": 0.2036,
      "step": 260
    },
    {
      "epoch": 3.08,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.539,
      "step": 270
    },
    {
      "epoch": 3.09,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.3139,
      "step": 280
    },
    {
      "epoch": 3.11,
      "learning_rate": 2.8703703703703706e-05,
      "loss": 0.2428,
      "step": 290
    },
    {
      "epoch": 3.12,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.4628,
      "step": 300
    },
    {
      "epoch": 3.12,
      "eval_accuracy": 0.8,
      "eval_loss": 0.5295023322105408,
      "eval_runtime": 11.5777,
      "eval_samples_per_second": 6.046,
      "eval_steps_per_second": 1.555,
      "step": 300
    },
    {
      "epoch": 4.02,
      "learning_rate": 2.6851851851851855e-05,
      "loss": 0.449,
      "step": 310
    },
    {
      "epoch": 4.03,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.2315,
      "step": 320
    },
    {
      "epoch": 4.05,
      "learning_rate": 2.5e-05,
      "loss": 0.0903,
      "step": 330
    },
    {
      "epoch": 4.07,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.1609,
      "step": 340
    },
    {
      "epoch": 4.08,
      "learning_rate": 2.314814814814815e-05,
      "loss": 0.1794,
      "step": 350
    },
    {
      "epoch": 4.1,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.2296,
      "step": 360
    },
    {
      "epoch": 4.12,
      "learning_rate": 2.1296296296296296e-05,
      "loss": 0.0843,
      "step": 370
    },
    {
      "epoch": 4.12,
      "eval_accuracy": 0.8714285714285714,
      "eval_loss": 0.3078978657722473,
      "eval_runtime": 11.9007,
      "eval_samples_per_second": 5.882,
      "eval_steps_per_second": 1.513,
      "step": 375
    },
    {
      "epoch": 5.01,
      "learning_rate": 2.037037037037037e-05,
      "loss": 0.0873,
      "step": 380
    },
    {
      "epoch": 5.03,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.0999,
      "step": 390
    },
    {
      "epoch": 5.04,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.0924,
      "step": 400
    },
    {
      "epoch": 5.06,
      "learning_rate": 1.7592592592592595e-05,
      "loss": 0.0185,
      "step": 410
    },
    {
      "epoch": 5.08,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0142,
      "step": 420
    },
    {
      "epoch": 5.09,
      "learning_rate": 1.574074074074074e-05,
      "loss": 0.089,
      "step": 430
    },
    {
      "epoch": 5.11,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.0472,
      "step": 440
    },
    {
      "epoch": 5.12,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.0793,
      "step": 450
    },
    {
      "epoch": 5.12,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.07852713763713837,
      "eval_runtime": 11.6251,
      "eval_samples_per_second": 6.021,
      "eval_steps_per_second": 1.548,
      "step": 450
    },
    {
      "epoch": 6.02,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 0.0185,
      "step": 460
    },
    {
      "epoch": 6.03,
      "learning_rate": 1.2037037037037037e-05,
      "loss": 0.0899,
      "step": 470
    },
    {
      "epoch": 6.05,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0529,
      "step": 480
    },
    {
      "epoch": 6.07,
      "learning_rate": 1.0185185185185185e-05,
      "loss": 0.0307,
      "step": 490
    },
    {
      "epoch": 6.08,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.0067,
      "step": 500
    },
    {
      "epoch": 6.1,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.0063,
      "step": 510
    },
    {
      "epoch": 6.12,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0059,
      "step": 520
    },
    {
      "epoch": 6.12,
      "eval_accuracy": 0.9571428571428572,
      "eval_loss": 0.06748640537261963,
      "eval_runtime": 11.5299,
      "eval_samples_per_second": 6.071,
      "eval_steps_per_second": 1.561,
      "step": 525
    },
    {
      "epoch": 7.01,
      "learning_rate": 6.481481481481481e-06,
      "loss": 0.0463,
      "step": 530
    },
    {
      "epoch": 7.03,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.007,
      "step": 540
    },
    {
      "epoch": 7.04,
      "learning_rate": 4.6296296296296296e-06,
      "loss": 0.0074,
      "step": 550
    },
    {
      "epoch": 7.06,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.0663,
      "step": 560
    },
    {
      "epoch": 7.08,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.0061,
      "step": 570
    },
    {
      "epoch": 7.09,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.0061,
      "step": 580
    },
    {
      "epoch": 7.11,
      "learning_rate": 9.259259259259259e-07,
      "loss": 0.0072,
      "step": 590
    },
    {
      "epoch": 7.12,
      "learning_rate": 0.0,
      "loss": 0.0065,
      "step": 600
    },
    {
      "epoch": 7.12,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.04862924665212631,
      "eval_runtime": 11.5131,
      "eval_samples_per_second": 6.08,
      "eval_steps_per_second": 1.563,
      "step": 600
    },
    {
      "epoch": 7.12,
      "step": 600,
      "total_flos": 2.990768376250368e+18,
      "train_loss": 0.5474069633024434,
      "train_runtime": 763.2232,
      "train_samples_per_second": 3.145,
      "train_steps_per_second": 0.786
    },
    {
      "epoch": 7.12,
      "eval_accuracy": 0.9290322580645162,
      "eval_loss": 0.2134566754102707,
      "eval_runtime": 26.3905,
      "eval_samples_per_second": 5.873,
      "eval_steps_per_second": 1.478,
      "step": 600
    },
    {
      "epoch": 7.12,
      "eval_accuracy": 0.9290322580645162,
      "eval_loss": 0.21079899370670319,
      "eval_runtime": 27.4106,
      "eval_samples_per_second": 5.655,
      "eval_steps_per_second": 1.423,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 2.990768376250368e+18,
  "trial_name": null,
  "trial_params": null
}