{
  "best_metric": 0.8714285714285714,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-600",
  "epoch": 3.25,
  "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": 2.2826,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.4128,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.5e-05,
      "loss": 2.3951,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.2778,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.166666666666667e-05,
      "loss": 2.1629,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 2.1963,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.9074074074074075e-05,
      "loss": 2.1437,
      "step": 70
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.814814814814815e-05,
      "loss": 1.8533,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.722222222222222e-05,
      "loss": 2.0496,
      "step": 90
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.62962962962963e-05,
      "loss": 1.7592,
      "step": 100
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.5370370370370374e-05,
      "loss": 1.6138,
      "step": 110
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.6146,
      "step": 120
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.351851851851852e-05,
      "loss": 1.6792,
      "step": 130
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.259259259259259e-05,
      "loss": 1.3033,
      "step": 140
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.3732,
      "step": 150
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.6142857142857143,
      "eval_loss": 1.0708065032958984,
      "eval_runtime": 20.1369,
      "eval_samples_per_second": 3.476,
      "eval_steps_per_second": 1.738,
      "step": 150
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.074074074074074e-05,
      "loss": 1.0212,
      "step": 160
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.981481481481482e-05,
      "loss": 1.053,
      "step": 170
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.888888888888889e-05,
      "loss": 1.3217,
      "step": 180
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.7962962962962964e-05,
      "loss": 1.0151,
      "step": 190
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.6903,
      "step": 200
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.6952,
      "step": 210
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.5794,
      "step": 220
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.425925925925926e-05,
      "loss": 0.929,
      "step": 230
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.618,
      "step": 240
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.240740740740741e-05,
      "loss": 0.3954,
      "step": 250
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.148148148148148e-05,
      "loss": 0.8701,
      "step": 260
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.9002,
      "step": 270
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.1855,
      "step": 280
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.8703703703703706e-05,
      "loss": 0.9844,
      "step": 290
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.9248,
      "step": 300
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 0.7428571428571429,
      "eval_loss": 0.6272522211074829,
      "eval_runtime": 20.1501,
      "eval_samples_per_second": 3.474,
      "eval_steps_per_second": 1.737,
      "step": 300
    },
    {
      "epoch": 2.02,
      "learning_rate": 2.6851851851851855e-05,
      "loss": 0.2409,
      "step": 310
    },
    {
      "epoch": 2.03,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.2265,
      "step": 320
    },
    {
      "epoch": 2.05,
      "learning_rate": 2.5e-05,
      "loss": 0.5069,
      "step": 330
    },
    {
      "epoch": 2.07,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.227,
      "step": 340
    },
    {
      "epoch": 2.08,
      "learning_rate": 2.314814814814815e-05,
      "loss": 0.3053,
      "step": 350
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.4336,
      "step": 360
    },
    {
      "epoch": 2.12,
      "learning_rate": 2.1296296296296296e-05,
      "loss": 0.4666,
      "step": 370
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.037037037037037e-05,
      "loss": 0.1686,
      "step": 380
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.271,
      "step": 390
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.3373,
      "step": 400
    },
    {
      "epoch": 2.18,
      "learning_rate": 1.7592592592592595e-05,
      "loss": 0.0656,
      "step": 410
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.2359,
      "step": 420
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.574074074074074e-05,
      "loss": 0.6904,
      "step": 430
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.18,
      "step": 440
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.3947,
      "step": 450
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 0.8285714285714286,
      "eval_loss": 0.30347004532814026,
      "eval_runtime": 19.593,
      "eval_samples_per_second": 3.573,
      "eval_steps_per_second": 1.786,
      "step": 450
    },
    {
      "epoch": 3.02,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 0.0868,
      "step": 460
    },
    {
      "epoch": 3.03,
      "learning_rate": 1.2037037037037037e-05,
      "loss": 0.058,
      "step": 470
    },
    {
      "epoch": 3.05,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.1011,
      "step": 480
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.0185185185185185e-05,
      "loss": 0.1359,
      "step": 490
    },
    {
      "epoch": 3.08,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.15,
      "step": 500
    },
    {
      "epoch": 3.1,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.1515,
      "step": 510
    },
    {
      "epoch": 3.12,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0745,
      "step": 520
    },
    {
      "epoch": 3.13,
      "learning_rate": 6.481481481481481e-06,
      "loss": 0.2648,
      "step": 530
    },
    {
      "epoch": 3.15,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.1668,
      "step": 540
    },
    {
      "epoch": 3.17,
      "learning_rate": 4.6296296296296296e-06,
      "loss": 0.2389,
      "step": 550
    },
    {
      "epoch": 3.18,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.3036,
      "step": 560
    },
    {
      "epoch": 3.2,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.1208,
      "step": 570
    },
    {
      "epoch": 3.22,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.2227,
      "step": 580
    },
    {
      "epoch": 3.23,
      "learning_rate": 9.259259259259259e-07,
      "loss": 0.4805,
      "step": 590
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0,
      "loss": 0.4861,
      "step": 600
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.8714285714285714,
      "eval_loss": 0.31074512004852295,
      "eval_runtime": 19.9181,
      "eval_samples_per_second": 3.514,
      "eval_steps_per_second": 1.757,
      "step": 600
    },
    {
      "epoch": 3.25,
      "step": 600,
      "total_flos": 1.495384188125184e+18,
      "train_loss": 0.8182205562790235,
      "train_runtime": 891.158,
      "train_samples_per_second": 1.347,
      "train_steps_per_second": 0.673
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.9032258064516129,
      "eval_loss": 0.29851803183555603,
      "eval_runtime": 45.5693,
      "eval_samples_per_second": 3.401,
      "eval_steps_per_second": 1.712,
      "step": 600
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.9032258064516129,
      "eval_loss": 0.2985180616378784,
      "eval_runtime": 44.9739,
      "eval_samples_per_second": 3.446,
      "eval_steps_per_second": 1.734,
      "step": 600
    }
  ],
  "max_steps": 600,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 1.495384188125184e+18,
  "trial_name": null,
  "trial_params": null
}