{
  "best_metric": 0.8857142857142857,
  "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": 6.447524070739746,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3807,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 7.273045539855957,
      "learning_rate": 4.81203007518797e-05,
      "loss": 2.2314,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 8.625303268432617,
      "learning_rate": 4.43609022556391e-05,
      "loss": 2.1403,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.5142857142857142,
      "eval_loss": 1.731579065322876,
      "eval_runtime": 20.0887,
      "eval_samples_per_second": 3.485,
      "eval_steps_per_second": 0.448,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 8.90733528137207,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 1.968,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 10.461448669433594,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 1.5209,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 68.34122467041016,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 1.2307,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 10.887399673461914,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.8431,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.7285714285714285,
      "eval_loss": 0.8928426504135132,
      "eval_runtime": 20.3734,
      "eval_samples_per_second": 3.436,
      "eval_steps_per_second": 0.442,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 5.018065452575684,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.8045,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 4.78250789642334,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.5899,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 10.711965560913086,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.5134,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 7.2737650871276855,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.3876,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.8285714285714286,
      "eval_loss": 0.40636110305786133,
      "eval_runtime": 19.4773,
      "eval_samples_per_second": 3.594,
      "eval_steps_per_second": 0.462,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 2.563310146331787,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.3354,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 5.6177215576171875,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.2464,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 9.905891418457031,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.2913,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8857142857142857,
      "eval_loss": 0.3383012115955353,
      "eval_runtime": 20.5339,
      "eval_samples_per_second": 3.409,
      "eval_steps_per_second": 0.438,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 1.460491890402263e+18,
      "train_loss": 1.0594123150851276,
      "train_runtime": 875.9405,
      "train_samples_per_second": 1.352,
      "train_steps_per_second": 0.169
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8387096774193549,
      "eval_loss": 0.409178227186203,
      "eval_runtime": 47.1559,
      "eval_samples_per_second": 3.287,
      "eval_steps_per_second": 0.424,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8387096774193549,
      "eval_loss": 0.409178227186203,
      "eval_runtime": 47.0636,
      "eval_samples_per_second": 3.293,
      "eval_steps_per_second": 0.425,
      "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
}