{
  "best_metric": 0.9887920298879203,
  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/BdSLW60_10_Fold/VideoMAE_Kinetics_fold__9__BdSLW60_SKF/checkpoint-5421",
  "epoch": 9.099501661129569,
  "eval_steps": 500,
  "global_step": 9030,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 22.186433792114258,
      "learning_rate": 4.9889258028792915e-05,
      "loss": 8.3149,
      "step": 903
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.9489414694894147,
      "eval_loss": 0.29937735199928284,
      "eval_runtime": 342.2841,
      "eval_samples_per_second": 2.346,
      "eval_steps_per_second": 1.174,
      "step": 903
    },
    {
      "epoch": 1.1000553709856036,
      "grad_norm": 0.12669819593429565,
      "learning_rate": 4.44567491079119e-05,
      "loss": 0.3403,
      "step": 1807
    },
    {
      "epoch": 1.1000553709856036,
      "eval_accuracy": 0.9813200498132005,
      "eval_loss": 0.07677984982728958,
      "eval_runtime": 207.0913,
      "eval_samples_per_second": 3.878,
      "eval_steps_per_second": 1.941,
      "step": 1807
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.06953881680965424,
      "learning_rate": 3.8901193552356345e-05,
      "loss": 0.0804,
      "step": 2710
    },
    {
      "epoch": 2.1,
      "eval_accuracy": 0.9726027397260274,
      "eval_loss": 0.12417934834957123,
      "eval_runtime": 476.7989,
      "eval_samples_per_second": 1.684,
      "eval_steps_per_second": 0.843,
      "step": 2710
    },
    {
      "epoch": 3.1000553709856034,
      "grad_norm": 0.236429363489151,
      "learning_rate": 3.334563799680079e-05,
      "loss": 0.0475,
      "step": 3614
    },
    {
      "epoch": 3.1000553709856034,
      "eval_accuracy": 0.9788293897882939,
      "eval_loss": 0.09404890239238739,
      "eval_runtime": 672.4699,
      "eval_samples_per_second": 1.194,
      "eval_steps_per_second": 0.598,
      "step": 3614
    },
    {
      "epoch": 4.1,
      "grad_norm": 0.0323849581182003,
      "learning_rate": 2.7790082441245237e-05,
      "loss": 0.0524,
      "step": 4517
    },
    {
      "epoch": 4.1,
      "eval_accuracy": 0.9863013698630136,
      "eval_loss": 0.06767500191926956,
      "eval_runtime": 798.4348,
      "eval_samples_per_second": 1.006,
      "eval_steps_per_second": 0.503,
      "step": 4517
    },
    {
      "epoch": 5.100055370985603,
      "grad_norm": 0.006273323204368353,
      "learning_rate": 2.222837455395595e-05,
      "loss": 0.0248,
      "step": 5421
    },
    {
      "epoch": 5.100055370985603,
      "eval_accuracy": 0.9887920298879203,
      "eval_loss": 0.054288752377033234,
      "eval_runtime": 317.5597,
      "eval_samples_per_second": 2.529,
      "eval_steps_per_second": 1.266,
      "step": 5421
    },
    {
      "epoch": 6.1,
      "grad_norm": 12.306224822998047,
      "learning_rate": 1.668512366186785e-05,
      "loss": 0.018,
      "step": 6324
    },
    {
      "epoch": 6.1,
      "eval_accuracy": 0.987546699875467,
      "eval_loss": 0.05183647572994232,
      "eval_runtime": 401.9147,
      "eval_samples_per_second": 1.998,
      "eval_steps_per_second": 1.0,
      "step": 6324
    },
    {
      "epoch": 7.100055370985603,
      "grad_norm": 0.0015328280860558152,
      "learning_rate": 1.1123415774578566e-05,
      "loss": 0.0122,
      "step": 7228
    },
    {
      "epoch": 7.100055370985603,
      "eval_accuracy": 0.987546699875467,
      "eval_loss": 0.04793976992368698,
      "eval_runtime": 206.3711,
      "eval_samples_per_second": 3.891,
      "eval_steps_per_second": 1.948,
      "step": 7228
    },
    {
      "epoch": 8.1,
      "grad_norm": 0.0018120441818609834,
      "learning_rate": 5.56786021902301e-06,
      "loss": 0.0103,
      "step": 8131
    },
    {
      "epoch": 8.1,
      "eval_accuracy": 0.987546699875467,
      "eval_loss": 0.04380244016647339,
      "eval_runtime": 225.858,
      "eval_samples_per_second": 3.555,
      "eval_steps_per_second": 1.78,
      "step": 8131
    },
    {
      "epoch": 9.099501661129569,
      "grad_norm": 0.0019097841577604413,
      "learning_rate": 3.691399040236249e-08,
      "loss": 0.0002,
      "step": 9030
    },
    {
      "epoch": 9.099501661129569,
      "eval_accuracy": 0.987546699875467,
      "eval_loss": 0.045518577098846436,
      "eval_runtime": 230.2085,
      "eval_samples_per_second": 3.488,
      "eval_steps_per_second": 1.746,
      "step": 9030
    },
    {
      "epoch": 9.099501661129569,
      "step": 9030,
      "total_flos": 9.006226676074414e+19,
      "train_loss": 0.8901602353104457,
      "train_runtime": 40052.7069,
      "train_samples_per_second": 1.804,
      "train_steps_per_second": 0.225
    }
  ],
  "logging_steps": 500,
  "max_steps": 9030,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 4
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.006226676074414e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}