{
  "best_metric": 0.8857142857142857,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset\\checkpoint-114",
  "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": 6.999968528747559,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 2.346,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 6.86763858795166,
      "learning_rate": 4.887218045112782e-05,
      "loss": 2.1753,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 7.643082141876221,
      "learning_rate": 4.511278195488722e-05,
      "loss": 2.1392,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.4142857142857143,
      "eval_loss": 1.876855492591858,
      "eval_runtime": 3.5234,
      "eval_samples_per_second": 19.867,
      "eval_steps_per_second": 2.554,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 9.058841705322266,
      "learning_rate": 4.135338345864662e-05,
      "loss": 1.9952,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 10.277332305908203,
      "learning_rate": 3.759398496240601e-05,
      "loss": 1.638,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 9.70552921295166,
      "learning_rate": 3.3834586466165414e-05,
      "loss": 1.4179,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 6.768729209899902,
      "learning_rate": 3.007518796992481e-05,
      "loss": 1.0079,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.7285714285714285,
      "eval_loss": 0.9862235188484192,
      "eval_runtime": 3.4968,
      "eval_samples_per_second": 20.018,
      "eval_steps_per_second": 2.574,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 5.034950256347656,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.9451,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 5.671147346496582,
      "learning_rate": 2.255639097744361e-05,
      "loss": 0.6736,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 13.149584770202637,
      "learning_rate": 1.8796992481203007e-05,
      "loss": 0.6599,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 6.1240644454956055,
      "learning_rate": 1.5037593984962406e-05,
      "loss": 0.4814,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.8857142857142857,
      "eval_loss": 0.5106483697891235,
      "eval_runtime": 3.4155,
      "eval_samples_per_second": 20.495,
      "eval_steps_per_second": 2.635,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 4.17629337310791,
      "learning_rate": 1.1278195488721805e-05,
      "loss": 0.3934,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 2.653998374938965,
      "learning_rate": 7.518796992481203e-06,
      "loss": 0.3096,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 7.489276885986328,
      "learning_rate": 3.7593984962406014e-06,
      "loss": 0.3286,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8714285714285714,
      "eval_loss": 0.39880502223968506,
      "eval_runtime": 3.4495,
      "eval_samples_per_second": 20.293,
      "eval_steps_per_second": 2.609,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 1.460491890402263e+18,
      "train_loss": 1.129269316389754,
      "train_runtime": 133.7971,
      "train_samples_per_second": 8.849,
      "train_steps_per_second": 1.106
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8258064516129032,
      "eval_loss": 0.5285735130310059,
      "eval_runtime": 7.5064,
      "eval_samples_per_second": 20.649,
      "eval_steps_per_second": 2.664,
      "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
}