{
  "best_metric": 0.8571428571428571,
  "best_model_checkpoint": "videomae-base-finetuned1-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": 7.62527322769165,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3299,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 6.930262565612793,
      "learning_rate": 4.81203007518797e-05,
      "loss": 2.2199,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 7.573678493499756,
      "learning_rate": 4.43609022556391e-05,
      "loss": 2.0478,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.4,
      "eval_loss": 1.8259150981903076,
      "eval_runtime": 18.2364,
      "eval_samples_per_second": 3.838,
      "eval_steps_per_second": 0.494,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 12.643692970275879,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 1.9327,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 40.31084442138672,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 1.4959,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 10.329468727111816,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 1.1244,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 6.792415142059326,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.7537,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.7857142857142857,
      "eval_loss": 0.8738226294517517,
      "eval_runtime": 18.2158,
      "eval_samples_per_second": 3.843,
      "eval_steps_per_second": 0.494,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 6.619019985198975,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.8278,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 12.499926567077637,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.6225,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 10.988991737365723,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.5226,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 6.538438320159912,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.4527,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.8142857142857143,
      "eval_loss": 0.5163326859474182,
      "eval_runtime": 18.7532,
      "eval_samples_per_second": 3.733,
      "eval_steps_per_second": 0.48,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 4.150028228759766,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.3893,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 4.461132049560547,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.2452,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 14.221858978271484,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.2563,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.44479623436927795,
      "eval_runtime": 18.7317,
      "eval_samples_per_second": 3.737,
      "eval_steps_per_second": 0.48,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 1.460491890402263e+18,
      "train_loss": 1.04203813462644,
      "train_runtime": 846.3919,
      "train_samples_per_second": 1.399,
      "train_steps_per_second": 0.175
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.896774193548387,
      "eval_loss": 0.4164496660232544,
      "eval_runtime": 49.6546,
      "eval_samples_per_second": 3.122,
      "eval_steps_per_second": 0.403,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.896774193548387,
      "eval_loss": 0.41644972562789917,
      "eval_runtime": 40.1847,
      "eval_samples_per_second": 3.857,
      "eval_steps_per_second": 0.498,
      "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
}