{
  "best_metric": 0.8571428571428571,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-19",
  "epoch": 3.2083333333333335,
  "eval_steps": 500,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 4.645142078399658,
      "learning_rate": 4.8437500000000005e-05,
      "loss": 0.6033,
      "step": 10
    },
    {
      "epoch": 0.2638888888888889,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.4074406027793884,
      "eval_runtime": 98.6257,
      "eval_samples_per_second": 1.916,
      "eval_steps_per_second": 0.243,
      "step": 19
    },
    {
      "epoch": 1.0138888888888888,
      "grad_norm": 1.9824458360671997,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 0.4803,
      "step": 20
    },
    {
      "epoch": 1.1527777777777777,
      "grad_norm": 3.7689878940582275,
      "learning_rate": 3.2812500000000005e-05,
      "loss": 0.4788,
      "step": 30
    },
    {
      "epoch": 1.2638888888888888,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.394088476896286,
      "eval_runtime": 98.7086,
      "eval_samples_per_second": 1.915,
      "eval_steps_per_second": 0.243,
      "step": 38
    },
    {
      "epoch": 2.0277777777777777,
      "grad_norm": 2.8333206176757812,
      "learning_rate": 2.5e-05,
      "loss": 0.4364,
      "step": 40
    },
    {
      "epoch": 2.1666666666666665,
      "grad_norm": 5.9353437423706055,
      "learning_rate": 1.71875e-05,
      "loss": 0.6026,
      "step": 50
    },
    {
      "epoch": 2.263888888888889,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.3900613486766815,
      "eval_runtime": 98.4982,
      "eval_samples_per_second": 1.919,
      "eval_steps_per_second": 0.244,
      "step": 57
    },
    {
      "epoch": 3.0416666666666665,
      "grad_norm": 2.219437837600708,
      "learning_rate": 9.375000000000001e-06,
      "loss": 0.3754,
      "step": 60
    },
    {
      "epoch": 3.1805555555555554,
      "grad_norm": 3.425725221633911,
      "learning_rate": 1.5625e-06,
      "loss": 0.3941,
      "step": 70
    },
    {
      "epoch": 3.2083333333333335,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.3870747983455658,
      "eval_runtime": 98.2584,
      "eval_samples_per_second": 1.923,
      "eval_steps_per_second": 0.244,
      "step": 72
    },
    {
      "epoch": 3.2083333333333335,
      "step": 72,
      "total_flos": 7.065186222304788e+17,
      "train_loss": 0.48999224934313035,
      "train_runtime": 758.8617,
      "train_samples_per_second": 0.759,
      "train_steps_per_second": 0.095
    },
    {
      "epoch": 3.2083333333333335,
      "eval_accuracy": 0.8125,
      "eval_loss": 0.4971349537372589,
      "eval_runtime": 76.4707,
      "eval_samples_per_second": 1.883,
      "eval_steps_per_second": 0.235,
      "step": 72
    },
    {
      "epoch": 3.2083333333333335,
      "eval_accuracy": 0.8125,
      "eval_loss": 0.49713489413261414,
      "eval_runtime": 76.9137,
      "eval_samples_per_second": 1.872,
      "eval_steps_per_second": 0.234,
      "step": 72
    }
  ],
  "logging_steps": 10,
  "max_steps": 72,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 7.065186222304788e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}