{
  "best_metric": 0.9571428571428572,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-133",
  "epoch": 7.101351351351352,
  "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": 6.901234149932861,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.0115,
      "step": 10
    },
    {
      "epoch": 0.12837837837837837,
      "eval_accuracy": 0.5428571428571428,
      "eval_loss": 1.546947956085205,
      "eval_runtime": 10.0454,
      "eval_samples_per_second": 6.968,
      "eval_steps_per_second": 0.498,
      "step": 19
    },
    {
      "epoch": 1.0067567567567568,
      "grad_norm": 7.984360218048096,
      "learning_rate": 4.81203007518797e-05,
      "loss": 1.6913,
      "step": 20
    },
    {
      "epoch": 1.0743243243243243,
      "grad_norm": 6.522056579589844,
      "learning_rate": 4.43609022556391e-05,
      "loss": 1.2145,
      "step": 30
    },
    {
      "epoch": 1.1283783783783783,
      "eval_accuracy": 0.7,
      "eval_loss": 0.9201391935348511,
      "eval_runtime": 10.5435,
      "eval_samples_per_second": 6.639,
      "eval_steps_per_second": 0.474,
      "step": 38
    },
    {
      "epoch": 2.0135135135135136,
      "grad_norm": 6.391108989715576,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 0.8009,
      "step": 40
    },
    {
      "epoch": 2.081081081081081,
      "grad_norm": 8.276566505432129,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 0.6166,
      "step": 50
    },
    {
      "epoch": 2.1283783783783785,
      "eval_accuracy": 0.8285714285714286,
      "eval_loss": 0.5547969341278076,
      "eval_runtime": 11.9084,
      "eval_samples_per_second": 5.878,
      "eval_steps_per_second": 0.42,
      "step": 57
    },
    {
      "epoch": 3.02027027027027,
      "grad_norm": 21.176633834838867,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 0.4484,
      "step": 60
    },
    {
      "epoch": 3.0878378378378377,
      "grad_norm": 3.571500062942505,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.3255,
      "step": 70
    },
    {
      "epoch": 3.1283783783783785,
      "eval_accuracy": 0.9,
      "eval_loss": 0.35559970140457153,
      "eval_runtime": 11.9471,
      "eval_samples_per_second": 5.859,
      "eval_steps_per_second": 0.419,
      "step": 76
    },
    {
      "epoch": 4.027027027027027,
      "grad_norm": 3.0831594467163086,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.2372,
      "step": 80
    },
    {
      "epoch": 4.094594594594595,
      "grad_norm": 1.0621541738510132,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.1945,
      "step": 90
    },
    {
      "epoch": 4.128378378378378,
      "eval_accuracy": 0.8857142857142857,
      "eval_loss": 0.2917786240577698,
      "eval_runtime": 11.1985,
      "eval_samples_per_second": 6.251,
      "eval_steps_per_second": 0.446,
      "step": 95
    },
    {
      "epoch": 5.033783783783784,
      "grad_norm": 7.335643291473389,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.1863,
      "step": 100
    },
    {
      "epoch": 5.101351351351352,
      "grad_norm": 3.736997604370117,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.098,
      "step": 110
    },
    {
      "epoch": 5.128378378378378,
      "eval_accuracy": 0.8714285714285714,
      "eval_loss": 0.38738560676574707,
      "eval_runtime": 11.6146,
      "eval_samples_per_second": 6.027,
      "eval_steps_per_second": 0.43,
      "step": 114
    },
    {
      "epoch": 6.04054054054054,
      "grad_norm": 4.334865570068359,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.0613,
      "step": 120
    },
    {
      "epoch": 6.108108108108108,
      "grad_norm": 6.393611907958984,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.0571,
      "step": 130
    },
    {
      "epoch": 6.128378378378378,
      "eval_accuracy": 0.9571428571428572,
      "eval_loss": 0.1539522409439087,
      "eval_runtime": 11.8139,
      "eval_samples_per_second": 5.925,
      "eval_steps_per_second": 0.423,
      "step": 133
    },
    {
      "epoch": 7.047297297297297,
      "grad_norm": 0.5439800024032593,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.0387,
      "step": 140
    },
    {
      "epoch": 7.101351351351352,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.25466597080230713,
      "eval_runtime": 12.6936,
      "eval_samples_per_second": 5.515,
      "eval_steps_per_second": 0.394,
      "step": 148
    },
    {
      "epoch": 7.101351351351352,
      "step": 148,
      "total_flos": 2.915999166844109e+18,
      "train_loss": 0.5411020509294562,
      "train_runtime": 849.4097,
      "train_samples_per_second": 2.788,
      "train_steps_per_second": 0.174
    },
    {
      "epoch": 7.101351351351352,
      "eval_accuracy": 0.9096774193548387,
      "eval_loss": 0.25891318917274475,
      "eval_runtime": 26.949,
      "eval_samples_per_second": 5.752,
      "eval_steps_per_second": 0.371,
      "step": 148
    },
    {
      "epoch": 7.101351351351352,
      "eval_accuracy": 0.9096774193548387,
      "eval_loss": 0.26174646615982056,
      "eval_runtime": 27.2537,
      "eval_samples_per_second": 5.687,
      "eval_steps_per_second": 0.367,
      "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": 2.915999166844109e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}