{
  "best_metric": 1.0,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-375",
  "epoch": 4.2,
  "eval_steps": 500,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "grad_norm": 14.895779609680176,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 1.3822,
      "step": 10
    },
    {
      "epoch": 0.05,
      "grad_norm": 15.425480842590332,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 1.1621,
      "step": 20
    },
    {
      "epoch": 0.08,
      "grad_norm": 11.494285583496094,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 1.0609,
      "step": 30
    },
    {
      "epoch": 0.11,
      "grad_norm": 14.816349983215332,
      "learning_rate": 4.9703264094955494e-05,
      "loss": 0.8414,
      "step": 40
    },
    {
      "epoch": 0.13,
      "grad_norm": 18.69601058959961,
      "learning_rate": 4.821958456973294e-05,
      "loss": 0.7904,
      "step": 50
    },
    {
      "epoch": 0.16,
      "grad_norm": 11.910196304321289,
      "learning_rate": 4.673590504451038e-05,
      "loss": 0.9924,
      "step": 60
    },
    {
      "epoch": 0.19,
      "grad_norm": 12.124129295349121,
      "learning_rate": 4.525222551928784e-05,
      "loss": 0.9101,
      "step": 70
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.6285714285714286,
      "eval_loss": 0.8777225017547607,
      "eval_runtime": 13.2025,
      "eval_samples_per_second": 5.302,
      "eval_steps_per_second": 1.363,
      "step": 75
    },
    {
      "epoch": 1.01,
      "grad_norm": 14.571742057800293,
      "learning_rate": 4.3768545994065286e-05,
      "loss": 0.5606,
      "step": 80
    },
    {
      "epoch": 1.04,
      "grad_norm": 9.837146759033203,
      "learning_rate": 4.228486646884273e-05,
      "loss": 0.5213,
      "step": 90
    },
    {
      "epoch": 1.07,
      "grad_norm": 18.2418212890625,
      "learning_rate": 4.080118694362018e-05,
      "loss": 0.6293,
      "step": 100
    },
    {
      "epoch": 1.09,
      "grad_norm": 10.92044734954834,
      "learning_rate": 3.9317507418397627e-05,
      "loss": 0.6146,
      "step": 110
    },
    {
      "epoch": 1.12,
      "grad_norm": 10.466025352478027,
      "learning_rate": 3.783382789317508e-05,
      "loss": 0.5081,
      "step": 120
    },
    {
      "epoch": 1.15,
      "grad_norm": 34.30221176147461,
      "learning_rate": 3.635014836795252e-05,
      "loss": 0.4598,
      "step": 130
    },
    {
      "epoch": 1.17,
      "grad_norm": 2.5953423976898193,
      "learning_rate": 3.4866468842729974e-05,
      "loss": 0.5664,
      "step": 140
    },
    {
      "epoch": 1.2,
      "grad_norm": 2.9291703701019287,
      "learning_rate": 3.338278931750742e-05,
      "loss": 0.2332,
      "step": 150
    },
    {
      "epoch": 1.2,
      "eval_accuracy": 0.8285714285714286,
      "eval_loss": 0.3904847800731659,
      "eval_runtime": 12.86,
      "eval_samples_per_second": 5.443,
      "eval_steps_per_second": 1.4,
      "step": 150
    },
    {
      "epoch": 2.03,
      "grad_norm": 11.46927261352539,
      "learning_rate": 3.189910979228487e-05,
      "loss": 0.2465,
      "step": 160
    },
    {
      "epoch": 2.05,
      "grad_norm": 1.3007924556732178,
      "learning_rate": 3.0415430267062318e-05,
      "loss": 0.5288,
      "step": 170
    },
    {
      "epoch": 2.08,
      "grad_norm": 30.475011825561523,
      "learning_rate": 2.8931750741839762e-05,
      "loss": 0.4022,
      "step": 180
    },
    {
      "epoch": 2.11,
      "grad_norm": 0.40067318081855774,
      "learning_rate": 2.744807121661721e-05,
      "loss": 0.3373,
      "step": 190
    },
    {
      "epoch": 2.13,
      "grad_norm": 6.692281723022461,
      "learning_rate": 2.5964391691394662e-05,
      "loss": 0.2017,
      "step": 200
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.8030463457107544,
      "learning_rate": 2.4480712166172106e-05,
      "loss": 0.2078,
      "step": 210
    },
    {
      "epoch": 2.19,
      "grad_norm": 4.740080833435059,
      "learning_rate": 2.2997032640949558e-05,
      "loss": 0.1484,
      "step": 220
    },
    {
      "epoch": 2.2,
      "eval_accuracy": 0.9428571428571428,
      "eval_loss": 0.2271830290555954,
      "eval_runtime": 12.9105,
      "eval_samples_per_second": 5.422,
      "eval_steps_per_second": 1.394,
      "step": 225
    },
    {
      "epoch": 3.01,
      "grad_norm": 12.664633750915527,
      "learning_rate": 2.1513353115727002e-05,
      "loss": 0.0884,
      "step": 230
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.1440916657447815,
      "learning_rate": 2.0029673590504454e-05,
      "loss": 0.1236,
      "step": 240
    },
    {
      "epoch": 3.07,
      "grad_norm": 3.6163482666015625,
      "learning_rate": 1.85459940652819e-05,
      "loss": 0.3029,
      "step": 250
    },
    {
      "epoch": 3.09,
      "grad_norm": 0.2636096179485321,
      "learning_rate": 1.706231454005935e-05,
      "loss": 0.125,
      "step": 260
    },
    {
      "epoch": 3.12,
      "grad_norm": 12.344978332519531,
      "learning_rate": 1.5578635014836794e-05,
      "loss": 0.2013,
      "step": 270
    },
    {
      "epoch": 3.15,
      "grad_norm": 18.149120330810547,
      "learning_rate": 1.4094955489614246e-05,
      "loss": 0.085,
      "step": 280
    },
    {
      "epoch": 3.17,
      "grad_norm": 2.8482699394226074,
      "learning_rate": 1.2611275964391692e-05,
      "loss": 0.112,
      "step": 290
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.20341695845127106,
      "learning_rate": 1.112759643916914e-05,
      "loss": 0.0183,
      "step": 300
    },
    {
      "epoch": 3.2,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.06157089024782181,
      "eval_runtime": 13.0386,
      "eval_samples_per_second": 5.369,
      "eval_steps_per_second": 1.381,
      "step": 300
    },
    {
      "epoch": 4.03,
      "grad_norm": 32.8179817199707,
      "learning_rate": 9.643916913946588e-06,
      "loss": 0.0328,
      "step": 310
    },
    {
      "epoch": 4.05,
      "grad_norm": 0.15981259942054749,
      "learning_rate": 8.160237388724036e-06,
      "loss": 0.0132,
      "step": 320
    },
    {
      "epoch": 4.08,
      "grad_norm": 16.473556518554688,
      "learning_rate": 6.676557863501484e-06,
      "loss": 0.0534,
      "step": 330
    },
    {
      "epoch": 4.11,
      "grad_norm": 0.11358954757452011,
      "learning_rate": 5.192878338278932e-06,
      "loss": 0.0142,
      "step": 340
    },
    {
      "epoch": 4.13,
      "grad_norm": 0.09973251819610596,
      "learning_rate": 3.7091988130563796e-06,
      "loss": 0.0977,
      "step": 350
    },
    {
      "epoch": 4.16,
      "grad_norm": 1.2808237075805664,
      "learning_rate": 2.225519287833828e-06,
      "loss": 0.011,
      "step": 360
    },
    {
      "epoch": 4.19,
      "grad_norm": 0.34775447845458984,
      "learning_rate": 7.41839762611276e-07,
      "loss": 0.0393,
      "step": 370
    },
    {
      "epoch": 4.2,
      "eval_accuracy": 1.0,
      "eval_loss": 0.03910655900835991,
      "eval_runtime": 13.2105,
      "eval_samples_per_second": 5.299,
      "eval_steps_per_second": 1.363,
      "step": 375
    },
    {
      "epoch": 4.2,
      "step": 375,
      "total_flos": 1.86923023515648e+18,
      "train_loss": 0.39019181327025093,
      "train_runtime": 577.3468,
      "train_samples_per_second": 2.598,
      "train_steps_per_second": 0.65
    },
    {
      "epoch": 4.2,
      "eval_accuracy": 0.967741935483871,
      "eval_loss": 0.10572722554206848,
      "eval_runtime": 28.9857,
      "eval_samples_per_second": 5.347,
      "eval_steps_per_second": 1.345,
      "step": 375
    },
    {
      "epoch": 4.2,
      "eval_accuracy": 0.967741935483871,
      "eval_loss": 0.10572721064090729,
      "eval_runtime": 28.3051,
      "eval_samples_per_second": 5.476,
      "eval_steps_per_second": 1.378,
      "step": 375
    },
    {
      "epoch": 4.2,
      "eval_accuracy": 0.967741935483871,
      "eval_loss": 0.10572722554206848,
      "eval_runtime": 28.4074,
      "eval_samples_per_second": 5.456,
      "eval_steps_per_second": 1.373,
      "step": 375
    }
  ],
  "logging_steps": 10,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 1.86923023515648e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}