{
  "best_metric": 0.9076923076923077,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset\\checkpoint-80",
  "epoch": 3.230769230769231,
  "eval_steps": 500,
  "global_step": 156,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0641025641025641,
      "grad_norm": 4.394412994384766,
      "learning_rate": 3.125e-05,
      "loss": 1.0132,
      "step": 10
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 5.420567989349365,
      "learning_rate": 4.8571428571428576e-05,
      "loss": 0.8683,
      "step": 20
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 6.78421688079834,
      "learning_rate": 4.5e-05,
      "loss": 0.5054,
      "step": 30
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 6.155091762542725,
      "learning_rate": 4.1428571428571437e-05,
      "loss": 0.5439,
      "step": 40
    },
    {
      "epoch": 0.2564102564102564,
      "eval_accuracy": 0.8153846153846154,
      "eval_loss": 0.34107062220573425,
      "eval_runtime": 71.8323,
      "eval_samples_per_second": 0.905,
      "eval_steps_per_second": 0.125,
      "step": 40
    },
    {
      "epoch": 1.064102564102564,
      "grad_norm": 5.863360404968262,
      "learning_rate": 3.785714285714286e-05,
      "loss": 0.3668,
      "step": 50
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 9.200115203857422,
      "learning_rate": 3.428571428571429e-05,
      "loss": 0.2457,
      "step": 60
    },
    {
      "epoch": 1.1923076923076923,
      "grad_norm": 5.0272040367126465,
      "learning_rate": 3.071428571428572e-05,
      "loss": 0.1767,
      "step": 70
    },
    {
      "epoch": 1.2564102564102564,
      "grad_norm": 16.482421875,
      "learning_rate": 2.714285714285714e-05,
      "loss": 0.4475,
      "step": 80
    },
    {
      "epoch": 1.2564102564102564,
      "eval_accuracy": 0.9076923076923077,
      "eval_loss": 0.24450990557670593,
      "eval_runtime": 67.8827,
      "eval_samples_per_second": 0.958,
      "eval_steps_per_second": 0.133,
      "step": 80
    },
    {
      "epoch": 2.064102564102564,
      "grad_norm": 0.37460148334503174,
      "learning_rate": 2.357142857142857e-05,
      "loss": 0.2746,
      "step": 90
    },
    {
      "epoch": 2.128205128205128,
      "grad_norm": 10.542753219604492,
      "learning_rate": 2e-05,
      "loss": 0.1803,
      "step": 100
    },
    {
      "epoch": 2.1923076923076925,
      "grad_norm": 1.9386680126190186,
      "learning_rate": 1.642857142857143e-05,
      "loss": 0.0729,
      "step": 110
    },
    {
      "epoch": 2.2564102564102564,
      "grad_norm": 1.4239801168441772,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 0.151,
      "step": 120
    },
    {
      "epoch": 2.2564102564102564,
      "eval_accuracy": 0.8615384615384616,
      "eval_loss": 0.4069540798664093,
      "eval_runtime": 67.5775,
      "eval_samples_per_second": 0.962,
      "eval_steps_per_second": 0.133,
      "step": 120
    },
    {
      "epoch": 3.064102564102564,
      "grad_norm": 0.11065883934497833,
      "learning_rate": 9.285714285714286e-06,
      "loss": 0.136,
      "step": 130
    },
    {
      "epoch": 3.128205128205128,
      "grad_norm": 0.9843647480010986,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 0.0397,
      "step": 140
    },
    {
      "epoch": 3.1923076923076925,
      "grad_norm": 0.10109780728816986,
      "learning_rate": 2.142857142857143e-06,
      "loss": 0.0314,
      "step": 150
    },
    {
      "epoch": 3.230769230769231,
      "eval_accuracy": 0.8769230769230769,
      "eval_loss": 0.4337887167930603,
      "eval_runtime": 72.43,
      "eval_samples_per_second": 0.897,
      "eval_steps_per_second": 0.124,
      "step": 156
    },
    {
      "epoch": 3.230769230769231,
      "step": 156,
      "total_flos": 1.5476260219471135e+18,
      "train_loss": 0.32558026298498494,
      "train_runtime": 3518.9902,
      "train_samples_per_second": 0.355,
      "train_steps_per_second": 0.044
    },
    {
      "epoch": 3.230769230769231,
      "eval_accuracy": 0.4925373134328358,
      "eval_loss": 2.203362226486206,
      "eval_runtime": 169.2326,
      "eval_samples_per_second": 0.396,
      "eval_steps_per_second": 0.053,
      "step": 156
    },
    {
      "epoch": 3.230769230769231,
      "eval_accuracy": 0.4925373134328358,
      "eval_loss": 2.203362226486206,
      "eval_runtime": 52.0119,
      "eval_samples_per_second": 1.288,
      "eval_steps_per_second": 0.173,
      "step": 156
    }
  ],
  "logging_steps": 10,
  "max_steps": 156,
  "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": 1.5476260219471135e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}