{
  "best_metric": 0.9285714285714286,
  "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": 6.407984733581543,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3019,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 6.60537576675415,
      "learning_rate": 4.81203007518797e-05,
      "loss": 2.2244,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 8.354103088378906,
      "learning_rate": 4.43609022556391e-05,
      "loss": 2.1059,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.37142857142857144,
      "eval_loss": 1.8028706312179565,
      "eval_runtime": 19.014,
      "eval_samples_per_second": 3.682,
      "eval_steps_per_second": 0.473,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 11.592523574829102,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 1.9043,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 12.86607837677002,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 1.4526,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 14.736044883728027,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 1.1666,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 5.918353080749512,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.7321,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.7142857142857143,
      "eval_loss": 0.8727054595947266,
      "eval_runtime": 17.421,
      "eval_samples_per_second": 4.018,
      "eval_steps_per_second": 0.517,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 3.5464766025543213,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.715,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 5.991497993469238,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.4772,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 8.718830108642578,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.4527,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 10.448086738586426,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.3346,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.9285714285714286,
      "eval_loss": 0.4104200601577759,
      "eval_runtime": 18.5415,
      "eval_samples_per_second": 3.775,
      "eval_steps_per_second": 0.485,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 3.4645307064056396,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.2789,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 5.113824844360352,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.2264,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 9.161781311035156,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.2422,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8857142857142857,
      "eval_loss": 0.32087382674217224,
      "eval_runtime": 20.1691,
      "eval_samples_per_second": 3.471,
      "eval_steps_per_second": 0.446,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 1.460491890402263e+18,
      "train_loss": 0.998315043546058,
      "train_runtime": 1775.8681,
      "train_samples_per_second": 0.667,
      "train_steps_per_second": 0.083
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8258064516129032,
      "eval_loss": 0.4799688160419464,
      "eval_runtime": 37.9025,
      "eval_samples_per_second": 4.089,
      "eval_steps_per_second": 0.528,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8258064516129032,
      "eval_loss": 0.4799688458442688,
      "eval_runtime": 38.676,
      "eval_samples_per_second": 4.008,
      "eval_steps_per_second": 0.517,
      "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
}