{
  "best_metric": 0.9285714285714286,
  "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": 5.9695892333984375,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.2555,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 7.333020210266113,
      "learning_rate": 4.81203007518797e-05,
      "loss": 2.194,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 7.8304924964904785,
      "learning_rate": 4.43609022556391e-05,
      "loss": 2.0939,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.6142857142857143,
      "eval_loss": 1.7894561290740967,
      "eval_runtime": 19.1096,
      "eval_samples_per_second": 3.663,
      "eval_steps_per_second": 0.471,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 11.512001991271973,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 1.9222,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 11.58191204071045,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 1.5144,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 11.013785362243652,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 1.2189,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 6.518862724304199,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.809,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.7142857142857143,
      "eval_loss": 0.863375723361969,
      "eval_runtime": 21.6507,
      "eval_samples_per_second": 3.233,
      "eval_steps_per_second": 0.416,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 3.865056037902832,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.816,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 4.4963507652282715,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.5543,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 14.640573501586914,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.5415,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 7.324181079864502,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.4345,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.8285714285714286,
      "eval_loss": 0.48698174953460693,
      "eval_runtime": 20.0639,
      "eval_samples_per_second": 3.489,
      "eval_steps_per_second": 0.449,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 2.440977096557617,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.3595,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 3.9098780155181885,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.2598,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 6.780401706695557,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.2773,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.9285714285714286,
      "eval_loss": 0.3680180609226227,
      "eval_runtime": 19.7281,
      "eval_samples_per_second": 3.548,
      "eval_steps_per_second": 0.456,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 1.460491890402263e+18,
      "train_loss": 1.042902792627747,
      "train_runtime": 790.3603,
      "train_samples_per_second": 1.498,
      "train_steps_per_second": 0.187
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8516129032258064,
      "eval_loss": 0.4854612350463867,
      "eval_runtime": 43.1791,
      "eval_samples_per_second": 3.59,
      "eval_steps_per_second": 0.463,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8516129032258064,
      "eval_loss": 0.48546117544174194,
      "eval_runtime": 42.6258,
      "eval_samples_per_second": 3.636,
      "eval_steps_per_second": 0.469,
      "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
}