{
  "best_metric": 0.9142857142857143,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-225",
  "epoch": 3.25,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.3558,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.293,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 2.3089,
      "step": 30
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.814814814814815e-05,
      "loss": 2.1925,
      "step": 40
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.62962962962963e-05,
      "loss": 1.9868,
      "step": 50
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 2.0795,
      "step": 60
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.259259259259259e-05,
      "loss": 1.835,
      "step": 70
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.4142857142857143,
      "eval_loss": 1.5383577346801758,
      "eval_runtime": 14.5132,
      "eval_samples_per_second": 4.823,
      "eval_steps_per_second": 1.24,
      "step": 75
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.074074074074074e-05,
      "loss": 1.5051,
      "step": 80
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.888888888888889e-05,
      "loss": 1.0974,
      "step": 90
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.0559,
      "step": 100
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.9881,
      "step": 110
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.1758,
      "step": 120
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.148148148148148e-05,
      "loss": 0.9197,
      "step": 130
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.6825,
      "step": 140
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.5822,
      "step": 150
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 0.8,
      "eval_loss": 0.6967638731002808,
      "eval_runtime": 14.2672,
      "eval_samples_per_second": 4.906,
      "eval_steps_per_second": 1.262,
      "step": 150
    },
    {
      "epoch": 2.03,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.4962,
      "step": 160
    },
    {
      "epoch": 2.07,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.6887,
      "step": 170
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.3894,
      "step": 180
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.037037037037037e-05,
      "loss": 0.6543,
      "step": 190
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.3451,
      "step": 200
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.4634,
      "step": 210
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.2967,
      "step": 220
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 0.9142857142857143,
      "eval_loss": 0.36007827520370483,
      "eval_runtime": 14.3031,
      "eval_samples_per_second": 4.894,
      "eval_steps_per_second": 1.258,
      "step": 225
    },
    {
      "epoch": 3.02,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 0.2401,
      "step": 230
    },
    {
      "epoch": 3.05,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.181,
      "step": 240
    },
    {
      "epoch": 3.08,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.2992,
      "step": 250
    },
    {
      "epoch": 3.12,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.1978,
      "step": 260
    },
    {
      "epoch": 3.15,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.1838,
      "step": 270
    },
    {
      "epoch": 3.18,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.1787,
      "step": 280
    },
    {
      "epoch": 3.22,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.1258,
      "step": 290
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0,
      "loss": 0.0952,
      "step": 300
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.9,
      "eval_loss": 0.2772606909275055,
      "eval_runtime": 14.5007,
      "eval_samples_per_second": 4.827,
      "eval_steps_per_second": 1.241,
      "step": 300
    },
    {
      "epoch": 3.25,
      "step": 300,
      "total_flos": 1.495384188125184e+18,
      "train_loss": 0.9297949550549189,
      "train_runtime": 631.9789,
      "train_samples_per_second": 1.899,
      "train_steps_per_second": 0.475
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.896774193548387,
      "eval_loss": 0.40425971150398254,
      "eval_runtime": 32.9264,
      "eval_samples_per_second": 4.707,
      "eval_steps_per_second": 1.184,
      "step": 300
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.896774193548387,
      "eval_loss": 0.40425965189933777,
      "eval_runtime": 32.1373,
      "eval_samples_per_second": 4.823,
      "eval_steps_per_second": 1.214,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 300,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 1.495384188125184e+18,
  "trial_name": null,
  "trial_params": null
}