{
  "best_metric": 0.8714285714285714,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
  "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": 6.423978805541992,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3465,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 7.651690483093262,
      "learning_rate": 4.81203007518797e-05,
      "loss": 2.179,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 7.18040657043457,
      "learning_rate": 4.43609022556391e-05,
      "loss": 2.1243,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.38571428571428573,
      "eval_loss": 1.8105360269546509,
      "eval_runtime": 6.708,
      "eval_samples_per_second": 10.435,
      "eval_steps_per_second": 1.342,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 9.158327102661133,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 1.9503,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 10.240347862243652,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 1.5053,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 9.871286392211914,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 1.2446,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 7.637844085693359,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.9539,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.5857142857142857,
      "eval_loss": 0.9814803004264832,
      "eval_runtime": 6.536,
      "eval_samples_per_second": 10.71,
      "eval_steps_per_second": 1.377,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 5.889892101287842,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.8534,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 14.065513610839844,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.6305,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 8.854910850524902,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.5601,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 7.27897834777832,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.4701,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.48053404688835144,
      "eval_runtime": 6.7679,
      "eval_samples_per_second": 10.343,
      "eval_steps_per_second": 1.33,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 3.358264207839966,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.3716,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 3.2281341552734375,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.3068,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 4.061362266540527,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.2869,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8714285714285714,
      "eval_loss": 0.39165422320365906,
      "eval_runtime": 6.849,
      "eval_samples_per_second": 10.22,
      "eval_steps_per_second": 1.314,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 1.460491890402263e+18,
      "train_loss": 1.084407622749741,
      "train_runtime": 223.0988,
      "train_samples_per_second": 5.307,
      "train_steps_per_second": 0.663
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8774193548387097,
      "eval_loss": 0.44974666833877563,
      "eval_runtime": 14.875,
      "eval_samples_per_second": 10.42,
      "eval_steps_per_second": 1.345,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8774193548387097,
      "eval_loss": 0.44974660873413086,
      "eval_runtime": 14.3146,
      "eval_samples_per_second": 10.828,
      "eval_steps_per_second": 1.397,
      "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
}