{
  "best_metric": 0.8571428571428571,
  "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": 6.7914204597473145,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.2959,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 6.899745941162109,
      "learning_rate": 4.81203007518797e-05,
      "loss": 2.2288,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 7.447702884674072,
      "learning_rate": 4.43609022556391e-05,
      "loss": 2.1407,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.5857142857142857,
      "eval_loss": 1.7623026371002197,
      "eval_runtime": 20.2329,
      "eval_samples_per_second": 3.46,
      "eval_steps_per_second": 0.445,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 10.615867614746094,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 1.9706,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 9.991049766540527,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 1.6138,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 10.719650268554688,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 1.33,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 6.1606645584106445,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.9823,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.6714285714285714,
      "eval_loss": 0.980285108089447,
      "eval_runtime": 19.1382,
      "eval_samples_per_second": 3.658,
      "eval_steps_per_second": 0.47,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 6.06564998626709,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.9424,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 9.21993637084961,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.7223,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 9.865941047668457,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.6116,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 4.933745861053467,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.4909,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.8428571428571429,
      "eval_loss": 0.557813286781311,
      "eval_runtime": 18.7496,
      "eval_samples_per_second": 3.733,
      "eval_steps_per_second": 0.48,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 3.717359781265259,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.3753,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 3.7006638050079346,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.3298,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 7.156440258026123,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.302,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.48390454053878784,
      "eval_runtime": 20.1398,
      "eval_samples_per_second": 3.476,
      "eval_steps_per_second": 0.447,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 1.460491890402263e+18,
      "train_loss": 1.1205665726919432,
      "train_runtime": 798.5574,
      "train_samples_per_second": 1.483,
      "train_steps_per_second": 0.185
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.7870967741935484,
      "eval_loss": 0.5018094182014465,
      "eval_runtime": 42.1937,
      "eval_samples_per_second": 3.674,
      "eval_steps_per_second": 0.474,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.7870967741935484,
      "eval_loss": 0.5018094778060913,
      "eval_runtime": 41.413,
      "eval_samples_per_second": 3.743,
      "eval_steps_per_second": 0.483,
      "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
}