{
  "best_metric": 0.6818181818181818,
  "best_model_checkpoint": "videomae-base-finetuned-Custom_Dataset_Finetune/checkpoint-126",
  "epoch": 3.2439999999999998,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 4.941892147064209,
      "learning_rate": 2.4e-05,
      "loss": 1.8353,
      "step": 10
    },
    {
      "epoch": 0.08,
      "grad_norm": 6.511570453643799,
      "learning_rate": 4.8e-05,
      "loss": 1.7037,
      "step": 20
    },
    {
      "epoch": 0.12,
      "grad_norm": 5.7441301345825195,
      "learning_rate": 5.8666666666666665e-05,
      "loss": 1.4799,
      "step": 30
    },
    {
      "epoch": 0.16,
      "grad_norm": 6.4645514488220215,
      "learning_rate": 5.6e-05,
      "loss": 1.2797,
      "step": 40
    },
    {
      "epoch": 0.2,
      "grad_norm": 6.132994651794434,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.1603,
      "step": 50
    },
    {
      "epoch": 0.24,
      "grad_norm": 4.506332874298096,
      "learning_rate": 5.066666666666667e-05,
      "loss": 0.9284,
      "step": 60
    },
    {
      "epoch": 0.252,
      "eval_accuracy": 0.5151515151515151,
      "eval_loss": 0.9844135046005249,
      "eval_runtime": 60.7277,
      "eval_samples_per_second": 1.087,
      "eval_steps_per_second": 0.082,
      "step": 63
    },
    {
      "epoch": 1.028,
      "grad_norm": 6.4644880294799805,
      "learning_rate": 4.8e-05,
      "loss": 0.918,
      "step": 70
    },
    {
      "epoch": 1.068,
      "grad_norm": 10.729351997375488,
      "learning_rate": 4.5333333333333335e-05,
      "loss": 0.9294,
      "step": 80
    },
    {
      "epoch": 1.108,
      "grad_norm": 8.79098129272461,
      "learning_rate": 4.266666666666667e-05,
      "loss": 0.9386,
      "step": 90
    },
    {
      "epoch": 1.148,
      "grad_norm": 4.564964294433594,
      "learning_rate": 3.9999999999999996e-05,
      "loss": 1.0353,
      "step": 100
    },
    {
      "epoch": 1.188,
      "grad_norm": 6.161099433898926,
      "learning_rate": 3.733333333333334e-05,
      "loss": 0.9968,
      "step": 110
    },
    {
      "epoch": 1.228,
      "grad_norm": 4.650356292724609,
      "learning_rate": 3.4666666666666665e-05,
      "loss": 0.9402,
      "step": 120
    },
    {
      "epoch": 1.252,
      "eval_accuracy": 0.6818181818181818,
      "eval_loss": 0.9521052241325378,
      "eval_runtime": 62.8381,
      "eval_samples_per_second": 1.05,
      "eval_steps_per_second": 0.08,
      "step": 126
    },
    {
      "epoch": 2.016,
      "grad_norm": 3.565009117126465,
      "learning_rate": 3.2e-05,
      "loss": 0.8584,
      "step": 130
    },
    {
      "epoch": 2.056,
      "grad_norm": 5.3584489822387695,
      "learning_rate": 2.9333333333333333e-05,
      "loss": 0.8446,
      "step": 140
    },
    {
      "epoch": 2.096,
      "grad_norm": 9.390802383422852,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.8279,
      "step": 150
    },
    {
      "epoch": 2.136,
      "grad_norm": 7.512342929840088,
      "learning_rate": 2.4e-05,
      "loss": 0.8049,
      "step": 160
    },
    {
      "epoch": 2.176,
      "grad_norm": 4.40623664855957,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 0.8291,
      "step": 170
    },
    {
      "epoch": 2.216,
      "grad_norm": 6.4893059730529785,
      "learning_rate": 1.866666666666667e-05,
      "loss": 0.8639,
      "step": 180
    },
    {
      "epoch": 2.252,
      "eval_accuracy": 0.6060606060606061,
      "eval_loss": 0.7931472063064575,
      "eval_runtime": 63.7339,
      "eval_samples_per_second": 1.036,
      "eval_steps_per_second": 0.078,
      "step": 189
    },
    {
      "epoch": 3.004,
      "grad_norm": 5.078976154327393,
      "learning_rate": 1.6e-05,
      "loss": 0.7345,
      "step": 190
    },
    {
      "epoch": 3.044,
      "grad_norm": 2.724031925201416,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.7462,
      "step": 200
    },
    {
      "epoch": 3.084,
      "grad_norm": 3.8141984939575195,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 0.7004,
      "step": 210
    },
    {
      "epoch": 3.124,
      "grad_norm": 3.8294148445129395,
      "learning_rate": 8e-06,
      "loss": 0.7095,
      "step": 220
    },
    {
      "epoch": 3.164,
      "grad_norm": 5.064866065979004,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.7274,
      "step": 230
    },
    {
      "epoch": 3.204,
      "grad_norm": 3.320218801498413,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.6674,
      "step": 240
    },
    {
      "epoch": 3.2439999999999998,
      "grad_norm": 3.968177080154419,
      "learning_rate": 0.0,
      "loss": 0.6195,
      "step": 250
    },
    {
      "epoch": 3.2439999999999998,
      "eval_accuracy": 0.6363636363636364,
      "eval_loss": 0.910934329032898,
      "eval_runtime": 73.6738,
      "eval_samples_per_second": 0.896,
      "eval_steps_per_second": 0.068,
      "step": 250
    },
    {
      "epoch": 3.2439999999999998,
      "step": 250,
      "total_flos": 4.9769595049134e+18,
      "train_loss": 0.9631701583862304,
      "train_runtime": 5330.9549,
      "train_samples_per_second": 0.75,
      "train_steps_per_second": 0.047
    },
    {
      "epoch": 3.2439999999999998,
      "eval_accuracy": 0.7586206896551724,
      "eval_loss": 0.8059645295143127,
      "eval_runtime": 63.0154,
      "eval_samples_per_second": 0.92,
      "eval_steps_per_second": 0.063,
      "step": 250
    },
    {
      "epoch": 3.2439999999999998,
      "eval_accuracy": 0.7586206896551724,
      "eval_loss": 0.8059644103050232,
      "eval_runtime": 62.6184,
      "eval_samples_per_second": 0.926,
      "eval_steps_per_second": 0.064,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "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": 4.9769595049134e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}