{
  "best_metric": 0.9950186799501868,
  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/BdSLW60_10_Fold/VideoMAE_Kinetics_fold__2__BdSLW60_SKF/checkpoint-4517",
  "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": 8.555875778198242,
      "learning_rate": 4.9889258028792915e-05,
      "loss": 8.3956,
      "step": 903
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.9601494396014943,
      "eval_loss": 0.3171994686126709,
      "eval_runtime": 378.9606,
      "eval_samples_per_second": 2.119,
      "eval_steps_per_second": 1.061,
      "step": 903
    },
    {
      "epoch": 1.1000553709856036,
      "grad_norm": 3.0393295288085938,
      "learning_rate": 4.44567491079119e-05,
      "loss": 0.408,
      "step": 1807
    },
    {
      "epoch": 1.1000553709856036,
      "eval_accuracy": 0.9887920298879203,
      "eval_loss": 0.04258830100297928,
      "eval_runtime": 200.677,
      "eval_samples_per_second": 4.001,
      "eval_steps_per_second": 2.003,
      "step": 1807
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.02424738183617592,
      "learning_rate": 3.890734588409007e-05,
      "loss": 0.0963,
      "step": 2710
    },
    {
      "epoch": 2.1,
      "eval_accuracy": 0.9900373599003736,
      "eval_loss": 0.04030231013894081,
      "eval_runtime": 255.2279,
      "eval_samples_per_second": 3.146,
      "eval_steps_per_second": 1.575,
      "step": 2710
    },
    {
      "epoch": 3.1000553709856034,
      "grad_norm": 0.08256613463163376,
      "learning_rate": 3.334563799680079e-05,
      "loss": 0.051,
      "step": 3614
    },
    {
      "epoch": 3.1000553709856034,
      "eval_accuracy": 0.9813200498132005,
      "eval_loss": 0.06109996885061264,
      "eval_runtime": 243.7147,
      "eval_samples_per_second": 3.295,
      "eval_steps_per_second": 1.649,
      "step": 3614
    },
    {
      "epoch": 4.1,
      "grad_norm": 0.026312392204999924,
      "learning_rate": 2.7796234772978964e-05,
      "loss": 0.0393,
      "step": 4517
    },
    {
      "epoch": 4.1,
      "eval_accuracy": 0.9950186799501868,
      "eval_loss": 0.029840152710676193,
      "eval_runtime": 225.1541,
      "eval_samples_per_second": 3.566,
      "eval_steps_per_second": 1.785,
      "step": 4517
    },
    {
      "epoch": 5.100055370985603,
      "grad_norm": 0.18683549761772156,
      "learning_rate": 2.2234526885689677e-05,
      "loss": 0.0309,
      "step": 5421
    },
    {
      "epoch": 5.100055370985603,
      "eval_accuracy": 0.9863013698630136,
      "eval_loss": 0.04532131925225258,
      "eval_runtime": 297.4191,
      "eval_samples_per_second": 2.7,
      "eval_steps_per_second": 1.352,
      "step": 5421
    },
    {
      "epoch": 6.1,
      "grad_norm": 0.004661477170884609,
      "learning_rate": 1.668512366186785e-05,
      "loss": 0.0061,
      "step": 6324
    },
    {
      "epoch": 6.1,
      "eval_accuracy": 0.987546699875467,
      "eval_loss": 0.04091913625597954,
      "eval_runtime": 279.4171,
      "eval_samples_per_second": 2.874,
      "eval_steps_per_second": 1.439,
      "step": 6324
    },
    {
      "epoch": 7.100055370985603,
      "grad_norm": 0.001828859793022275,
      "learning_rate": 1.1123415774578566e-05,
      "loss": 0.0122,
      "step": 7228
    },
    {
      "epoch": 7.100055370985603,
      "eval_accuracy": 0.9912826899128269,
      "eval_loss": 0.05522552877664566,
      "eval_runtime": 314.8243,
      "eval_samples_per_second": 2.551,
      "eval_steps_per_second": 1.277,
      "step": 7228
    },
    {
      "epoch": 8.1,
      "grad_norm": 0.3854459226131439,
      "learning_rate": 5.56786021902301e-06,
      "loss": 0.0039,
      "step": 8131
    },
    {
      "epoch": 8.1,
      "eval_accuracy": 0.9937733499377335,
      "eval_loss": 0.027218027040362358,
      "eval_runtime": 335.4026,
      "eval_samples_per_second": 2.394,
      "eval_steps_per_second": 1.199,
      "step": 8131
    },
    {
      "epoch": 9.099501661129569,
      "grad_norm": 0.0014946144074201584,
      "learning_rate": 3.691399040236249e-08,
      "loss": 0.0066,
      "step": 9030
    },
    {
      "epoch": 9.099501661129569,
      "eval_accuracy": 0.9925280199252802,
      "eval_loss": 0.030716385692358017,
      "eval_runtime": 363.5719,
      "eval_samples_per_second": 2.209,
      "eval_steps_per_second": 1.106,
      "step": 9030
    },
    {
      "epoch": 9.099501661129569,
      "step": 9030,
      "total_flos": 9.006226676074414e+19,
      "train_loss": 0.9050431965989528,
      "train_runtime": 29808.1205,
      "train_samples_per_second": 2.424,
      "train_steps_per_second": 0.303
    }
  ],
  "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": 5
      }
    },
    "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
}