{
  "best_metric": 0.9285714285714286,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
  "epoch": 3.22972972972973,
  "eval_steps": 500,
  "global_step": 148,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 6.539665222167969,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3542,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 7.234946250915527,
      "learning_rate": 4.81203007518797e-05,
      "loss": 2.1979,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 8.571228981018066,
      "learning_rate": 4.43609022556391e-05,
      "loss": 2.1805,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.5714285714285714,
      "eval_loss": 1.6700714826583862,
      "eval_runtime": 18.6986,
      "eval_samples_per_second": 3.744,
      "eval_steps_per_second": 0.481,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 10.858766555786133,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 1.9165,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 16.22592544555664,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 1.4679,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 9.49629020690918,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 1.1633,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 5.7353596687316895,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.8236,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.7571428571428571,
      "eval_loss": 0.8164817094802856,
      "eval_runtime": 19.5813,
      "eval_samples_per_second": 3.575,
      "eval_steps_per_second": 0.46,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 5.357788562774658,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.7898,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 6.431110858917236,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.6124,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 12.532500267028809,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.542,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 6.320024490356445,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.3931,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.4499624967575073,
      "eval_runtime": 18.5731,
      "eval_samples_per_second": 3.769,
      "eval_steps_per_second": 0.485,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 3.994394540786743,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.3434,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 3.0500664710998535,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.2757,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 6.201582908630371,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.2707,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.9285714285714286,
      "eval_loss": 0.35308223962783813,
      "eval_runtime": 20.5547,
      "eval_samples_per_second": 3.406,
      "eval_steps_per_second": 0.438,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 1.460491890402263e+18,
      "train_loss": 1.0507738187506392,
      "train_runtime": 1048.5557,
      "train_samples_per_second": 1.129,
      "train_steps_per_second": 0.141
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8129032258064516,
      "eval_loss": 0.4544946551322937,
      "eval_runtime": 42.5004,
      "eval_samples_per_second": 3.647,
      "eval_steps_per_second": 0.471,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8129032258064516,
      "eval_loss": 0.4544946849346161,
      "eval_runtime": 41.9192,
      "eval_samples_per_second": 3.698,
      "eval_steps_per_second": 0.477,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8129032258064516,
      "eval_loss": 0.4544946551322937,
      "eval_runtime": 41.9266,
      "eval_samples_per_second": 3.697,
      "eval_steps_per_second": 0.477,
      "step": 148
    }
  ],
  "logging_steps": 10,
  "max_steps": 148,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.460491890402263e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}