{
  "best_metric": 1.0,
  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/MY DATA/ViViT_LSA64_SR_6/checkpoint-1152",
  "epoch": 8.033333333333333,
  "eval_steps": 500,
  "global_step": 2592,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011574074074074073,
      "grad_norm": 44.73263931274414,
      "learning_rate": 5.613425925925926e-06,
      "loss": 17.0729,
      "step": 100
    },
    {
      "epoch": 0.023148148148148147,
      "grad_norm": 47.833282470703125,
      "learning_rate": 1.1400462962962963e-05,
      "loss": 15.7817,
      "step": 200
    },
    {
      "epoch": 0.03333333333333333,
      "eval_accuracy": 0.4609375,
      "eval_f1": 0.43072370107622715,
      "eval_loss": 2.8823623657226562,
      "eval_precision": 0.5308730476699226,
      "eval_recall": 0.4609375,
      "eval_runtime": 294.5123,
      "eval_samples_per_second": 0.869,
      "eval_steps_per_second": 0.435,
      "step": 288
    },
    {
      "epoch": 1.0013888888888889,
      "grad_norm": 49.69872283935547,
      "learning_rate": 1.71875e-05,
      "loss": 12.8142,
      "step": 300
    },
    {
      "epoch": 1.012962962962963,
      "grad_norm": 53.043094635009766,
      "learning_rate": 2.297453703703704e-05,
      "loss": 8.4497,
      "step": 400
    },
    {
      "epoch": 1.024537037037037,
      "grad_norm": 30.541913986206055,
      "learning_rate": 2.8761574074074076e-05,
      "loss": 4.7558,
      "step": 500
    },
    {
      "epoch": 1.0333333333333334,
      "eval_accuracy": 0.94921875,
      "eval_f1": 0.9469866071428571,
      "eval_loss": 0.5581986904144287,
      "eval_precision": 0.9585937499999999,
      "eval_recall": 0.94921875,
      "eval_runtime": 294.5325,
      "eval_samples_per_second": 0.869,
      "eval_steps_per_second": 0.435,
      "step": 576
    },
    {
      "epoch": 2.0027777777777778,
      "grad_norm": 16.023212432861328,
      "learning_rate": 3.454861111111111e-05,
      "loss": 2.1506,
      "step": 600
    },
    {
      "epoch": 2.0143518518518517,
      "grad_norm": 9.642929077148438,
      "learning_rate": 4.033564814814815e-05,
      "loss": 0.968,
      "step": 700
    },
    {
      "epoch": 2.025925925925926,
      "grad_norm": 2.5669755935668945,
      "learning_rate": 4.612268518518519e-05,
      "loss": 0.5173,
      "step": 800
    },
    {
      "epoch": 2.033333333333333,
      "eval_accuracy": 0.98046875,
      "eval_f1": 0.9797619047619047,
      "eval_loss": 0.09987345337867737,
      "eval_precision": 0.9854166666666667,
      "eval_recall": 0.98046875,
      "eval_runtime": 293.8692,
      "eval_samples_per_second": 0.871,
      "eval_steps_per_second": 0.436,
      "step": 864
    },
    {
      "epoch": 3.004166666666667,
      "grad_norm": 49.025569915771484,
      "learning_rate": 4.978780864197531e-05,
      "loss": 0.2348,
      "step": 900
    },
    {
      "epoch": 3.015740740740741,
      "grad_norm": 4.306143283843994,
      "learning_rate": 4.9144804526748975e-05,
      "loss": 0.0649,
      "step": 1000
    },
    {
      "epoch": 3.027314814814815,
      "grad_norm": 52.926971435546875,
      "learning_rate": 4.850180041152263e-05,
      "loss": 0.1244,
      "step": 1100
    },
    {
      "epoch": 3.033333333333333,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.010159317404031754,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 358.4985,
      "eval_samples_per_second": 0.714,
      "eval_steps_per_second": 0.357,
      "step": 1152
    },
    {
      "epoch": 4.0055555555555555,
      "grad_norm": 0.2205909937620163,
      "learning_rate": 4.78587962962963e-05,
      "loss": 0.0688,
      "step": 1200
    },
    {
      "epoch": 4.01712962962963,
      "grad_norm": 0.06853680312633514,
      "learning_rate": 4.721579218106996e-05,
      "loss": 0.018,
      "step": 1300
    },
    {
      "epoch": 4.0287037037037035,
      "grad_norm": 0.06609813868999481,
      "learning_rate": 4.657278806584363e-05,
      "loss": 0.0043,
      "step": 1400
    },
    {
      "epoch": 4.033333333333333,
      "eval_accuracy": 0.9921875,
      "eval_f1": 0.9920634920634921,
      "eval_loss": 0.026480242609977722,
      "eval_precision": 0.99375,
      "eval_recall": 0.9921875,
      "eval_runtime": 327.6241,
      "eval_samples_per_second": 0.781,
      "eval_steps_per_second": 0.391,
      "step": 1440
    },
    {
      "epoch": 5.006944444444445,
      "grad_norm": 0.09487422555685043,
      "learning_rate": 4.5929783950617286e-05,
      "loss": 0.0178,
      "step": 1500
    },
    {
      "epoch": 5.018518518518518,
      "grad_norm": 0.06308699399232864,
      "learning_rate": 4.5286779835390944e-05,
      "loss": 0.0033,
      "step": 1600
    },
    {
      "epoch": 5.030092592592593,
      "grad_norm": 0.4189186692237854,
      "learning_rate": 4.464377572016461e-05,
      "loss": 0.021,
      "step": 1700
    },
    {
      "epoch": 5.033333333333333,
      "eval_accuracy": 0.9921875,
      "eval_f1": 0.9920634920634921,
      "eval_loss": 0.019995149224996567,
      "eval_precision": 0.99375,
      "eval_recall": 0.9921875,
      "eval_runtime": 314.0145,
      "eval_samples_per_second": 0.815,
      "eval_steps_per_second": 0.408,
      "step": 1728
    },
    {
      "epoch": 6.008333333333334,
      "grad_norm": 0.022702256217598915,
      "learning_rate": 4.4000771604938274e-05,
      "loss": 0.0144,
      "step": 1800
    },
    {
      "epoch": 6.019907407407407,
      "grad_norm": 0.019604824483394623,
      "learning_rate": 4.335776748971194e-05,
      "loss": 0.0016,
      "step": 1900
    },
    {
      "epoch": 6.031481481481482,
      "grad_norm": 0.017143510282039642,
      "learning_rate": 4.27147633744856e-05,
      "loss": 0.0014,
      "step": 2000
    },
    {
      "epoch": 6.033333333333333,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0011858218349516392,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 318.1849,
      "eval_samples_per_second": 0.805,
      "eval_steps_per_second": 0.402,
      "step": 2016
    },
    {
      "epoch": 7.009722222222222,
      "grad_norm": 0.1380627602338791,
      "learning_rate": 4.207175925925926e-05,
      "loss": 0.0017,
      "step": 2100
    },
    {
      "epoch": 7.021296296296296,
      "grad_norm": 0.02778031677007675,
      "learning_rate": 4.142875514403292e-05,
      "loss": 0.0251,
      "step": 2200
    },
    {
      "epoch": 7.032870370370371,
      "grad_norm": 0.0441974513232708,
      "learning_rate": 4.0785751028806585e-05,
      "loss": 0.0414,
      "step": 2300
    },
    {
      "epoch": 7.033333333333333,
      "eval_accuracy": 0.99609375,
      "eval_f1": 0.996031746031746,
      "eval_loss": 0.007463962305337191,
      "eval_precision": 0.996875,
      "eval_recall": 0.99609375,
      "eval_runtime": 362.0912,
      "eval_samples_per_second": 0.707,
      "eval_steps_per_second": 0.354,
      "step": 2304
    },
    {
      "epoch": 8.011111111111111,
      "grad_norm": 0.018177902325987816,
      "learning_rate": 4.0149176954732515e-05,
      "loss": 0.0836,
      "step": 2400
    },
    {
      "epoch": 8.022685185185185,
      "grad_norm": 0.04126301780343056,
      "learning_rate": 3.950617283950617e-05,
      "loss": 0.0386,
      "step": 2500
    },
    {
      "epoch": 8.033333333333333,
      "eval_accuracy": 0.99609375,
      "eval_f1": 0.996031746031746,
      "eval_loss": 0.018984569236636162,
      "eval_precision": 0.996875,
      "eval_recall": 0.99609375,
      "eval_runtime": 313.7776,
      "eval_samples_per_second": 0.816,
      "eval_steps_per_second": 0.408,
      "step": 2592
    },
    {
      "epoch": 8.033333333333333,
      "step": 2592,
      "total_flos": 5.3155188007162085e+19,
      "train_loss": 2.444476819677669,
      "train_runtime": 29887.626,
      "train_samples_per_second": 2.313,
      "train_steps_per_second": 0.289
    }
  ],
  "logging_steps": 100,
  "max_steps": 8640,
  "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": 5.3155188007162085e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}