{
  "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": 6.227916240692139,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3634,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 7.001335144042969,
      "learning_rate": 4.81203007518797e-05,
      "loss": 2.1918,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 7.081023216247559,
      "learning_rate": 4.43609022556391e-05,
      "loss": 2.155,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.4,
      "eval_loss": 1.8989312648773193,
      "eval_runtime": 9.7905,
      "eval_samples_per_second": 7.15,
      "eval_steps_per_second": 0.919,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 10.91995906829834,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 1.9415,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 12.066030502319336,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 1.5334,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 11.550034523010254,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 1.1585,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 6.527956962585449,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.8674,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.7571428571428571,
      "eval_loss": 0.8184080719947815,
      "eval_runtime": 6.7525,
      "eval_samples_per_second": 10.367,
      "eval_steps_per_second": 1.333,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 6.4941606521606445,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.8398,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 21.907115936279297,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.5705,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 14.677469253540039,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.549,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 8.632761001586914,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.4134,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.8857142857142857,
      "eval_loss": 0.3970875144004822,
      "eval_runtime": 6.8096,
      "eval_samples_per_second": 10.28,
      "eval_steps_per_second": 1.322,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 5.837729454040527,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.2865,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 3.2212138175964355,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.245,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 6.381491184234619,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.2854,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.3402653932571411,
      "eval_runtime": 6.7509,
      "eval_samples_per_second": 10.369,
      "eval_steps_per_second": 1.333,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 1.460491890402263e+18,
      "train_loss": 1.0525009293813963,
      "train_runtime": 1721.6136,
      "train_samples_per_second": 0.688,
      "train_steps_per_second": 0.086
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.832258064516129,
      "eval_loss": 0.40457773208618164,
      "eval_runtime": 19.5105,
      "eval_samples_per_second": 7.944,
      "eval_steps_per_second": 1.025,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.832258064516129,
      "eval_loss": 0.40457773208618164,
      "eval_runtime": 18.132,
      "eval_samples_per_second": 8.548,
      "eval_steps_per_second": 1.103,
      "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
}