{
  "best_metric": 0.9142857142857143,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-114",
  "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": 6.550330638885498,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3458,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 7.449215888977051,
      "learning_rate": 4.81203007518797e-05,
      "loss": 2.1855,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 7.531116962432861,
      "learning_rate": 4.43609022556391e-05,
      "loss": 2.1208,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.5142857142857142,
      "eval_loss": 1.8455791473388672,
      "eval_runtime": 435.7069,
      "eval_samples_per_second": 0.161,
      "eval_steps_per_second": 0.021,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 11.373128890991211,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 1.8995,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 9.782893180847168,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 1.4718,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 13.6583890914917,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 1.1635,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 9.038268089294434,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.7742,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.7142857142857143,
      "eval_loss": 0.9332746267318726,
      "eval_runtime": 355.2255,
      "eval_samples_per_second": 0.197,
      "eval_steps_per_second": 0.025,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 4.106594085693359,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.8308,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 9.80185604095459,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.5783,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 11.908610343933105,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.5351,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 5.700929164886475,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.411,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.9142857142857143,
      "eval_loss": 0.4463686943054199,
      "eval_runtime": 303.0784,
      "eval_samples_per_second": 0.231,
      "eval_steps_per_second": 0.03,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 4.13948392868042,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.3562,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 3.486126184463501,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.2465,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 9.807132720947266,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.2753,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8857142857142857,
      "eval_loss": 0.3988778591156006,
      "eval_runtime": 404.335,
      "eval_samples_per_second": 0.173,
      "eval_steps_per_second": 0.022,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 1.460491890402263e+18,
      "train_loss": 1.038178684743675,
      "train_runtime": 18545.357,
      "train_samples_per_second": 0.064,
      "train_steps_per_second": 0.008
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8064516129032258,
      "eval_loss": 0.5260129570960999,
      "eval_runtime": 938.2685,
      "eval_samples_per_second": 0.165,
      "eval_steps_per_second": 0.021,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8064516129032258,
      "eval_loss": 0.5260128974914551,
      "eval_runtime": 733.1305,
      "eval_samples_per_second": 0.211,
      "eval_steps_per_second": 0.027,
      "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
}