{
  "best_metric": 0.7875,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-95",
  "epoch": 3.242021276595745,
  "eval_steps": 500,
  "global_step": 376,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.026595744680851064,
      "grad_norm": 12.626161575317383,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 1.6196,
      "step": 10
    },
    {
      "epoch": 0.05319148936170213,
      "grad_norm": 5.767611980438232,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.9827,
      "step": 20
    },
    {
      "epoch": 0.0797872340425532,
      "grad_norm": 4.556581497192383,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 0.9375,
      "step": 30
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 5.054460525512695,
      "learning_rate": 4.970414201183432e-05,
      "loss": 0.8402,
      "step": 40
    },
    {
      "epoch": 0.13297872340425532,
      "grad_norm": 4.505584239959717,
      "learning_rate": 4.822485207100592e-05,
      "loss": 0.582,
      "step": 50
    },
    {
      "epoch": 0.1595744680851064,
      "grad_norm": 3.063162088394165,
      "learning_rate": 4.674556213017752e-05,
      "loss": 1.1131,
      "step": 60
    },
    {
      "epoch": 0.18617021276595744,
      "grad_norm": 2.564850330352783,
      "learning_rate": 4.5266272189349114e-05,
      "loss": 0.6761,
      "step": 70
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 2.2109172344207764,
      "learning_rate": 4.378698224852072e-05,
      "loss": 0.5614,
      "step": 80
    },
    {
      "epoch": 0.2393617021276596,
      "grad_norm": 1.6165765523910522,
      "learning_rate": 4.230769230769231e-05,
      "loss": 0.8026,
      "step": 90
    },
    {
      "epoch": 0.2526595744680851,
      "eval_accuracy": 0.7875,
      "eval_loss": 0.8083112835884094,
      "eval_runtime": 16.3601,
      "eval_samples_per_second": 9.78,
      "eval_steps_per_second": 1.222,
      "step": 95
    },
    {
      "epoch": 1.0132978723404256,
      "grad_norm": 1.8220001459121704,
      "learning_rate": 4.0828402366863904e-05,
      "loss": 0.6855,
      "step": 100
    },
    {
      "epoch": 1.0398936170212767,
      "grad_norm": 2.690967321395874,
      "learning_rate": 3.934911242603551e-05,
      "loss": 0.8036,
      "step": 110
    },
    {
      "epoch": 1.0664893617021276,
      "grad_norm": 2.7666921615600586,
      "learning_rate": 3.7869822485207104e-05,
      "loss": 0.7408,
      "step": 120
    },
    {
      "epoch": 1.0930851063829787,
      "grad_norm": 2.5995383262634277,
      "learning_rate": 3.63905325443787e-05,
      "loss": 0.7017,
      "step": 130
    },
    {
      "epoch": 1.1196808510638299,
      "grad_norm": 7.389265537261963,
      "learning_rate": 3.49112426035503e-05,
      "loss": 0.6631,
      "step": 140
    },
    {
      "epoch": 1.1462765957446808,
      "grad_norm": 1.8834972381591797,
      "learning_rate": 3.3431952662721895e-05,
      "loss": 0.8175,
      "step": 150
    },
    {
      "epoch": 1.172872340425532,
      "grad_norm": 1.4516174793243408,
      "learning_rate": 3.195266272189349e-05,
      "loss": 0.6888,
      "step": 160
    },
    {
      "epoch": 1.199468085106383,
      "grad_norm": 3.942476272583008,
      "learning_rate": 3.047337278106509e-05,
      "loss": 0.7102,
      "step": 170
    },
    {
      "epoch": 1.226063829787234,
      "grad_norm": 1.646263837814331,
      "learning_rate": 2.8994082840236685e-05,
      "loss": 0.7908,
      "step": 180
    },
    {
      "epoch": 1.252659574468085,
      "grad_norm": 5.147498607635498,
      "learning_rate": 2.751479289940829e-05,
      "loss": 0.8728,
      "step": 190
    },
    {
      "epoch": 1.252659574468085,
      "eval_accuracy": 0.7875,
      "eval_loss": 0.7828324437141418,
      "eval_runtime": 16.1891,
      "eval_samples_per_second": 9.883,
      "eval_steps_per_second": 1.235,
      "step": 190
    },
    {
      "epoch": 2.026595744680851,
      "grad_norm": 1.3614023923873901,
      "learning_rate": 2.6035502958579882e-05,
      "loss": 0.7153,
      "step": 200
    },
    {
      "epoch": 2.0531914893617023,
      "grad_norm": 1.6865636110305786,
      "learning_rate": 2.4556213017751482e-05,
      "loss": 0.7114,
      "step": 210
    },
    {
      "epoch": 2.0797872340425534,
      "grad_norm": 2.2771339416503906,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.8898,
      "step": 220
    },
    {
      "epoch": 2.106382978723404,
      "grad_norm": 2.0663363933563232,
      "learning_rate": 2.1597633136094676e-05,
      "loss": 0.8524,
      "step": 230
    },
    {
      "epoch": 2.132978723404255,
      "grad_norm": 4.288294792175293,
      "learning_rate": 2.0118343195266273e-05,
      "loss": 0.6944,
      "step": 240
    },
    {
      "epoch": 2.1595744680851063,
      "grad_norm": 3.9807941913604736,
      "learning_rate": 1.8639053254437873e-05,
      "loss": 0.7094,
      "step": 250
    },
    {
      "epoch": 2.1861702127659575,
      "grad_norm": 3.6395652294158936,
      "learning_rate": 1.7159763313609466e-05,
      "loss": 0.7492,
      "step": 260
    },
    {
      "epoch": 2.2127659574468086,
      "grad_norm": 4.759531021118164,
      "learning_rate": 1.5680473372781066e-05,
      "loss": 0.5475,
      "step": 270
    },
    {
      "epoch": 2.2393617021276597,
      "grad_norm": 2.811213970184326,
      "learning_rate": 1.4201183431952663e-05,
      "loss": 0.952,
      "step": 280
    },
    {
      "epoch": 2.252659574468085,
      "eval_accuracy": 0.7875,
      "eval_loss": 0.7974634170532227,
      "eval_runtime": 12.6508,
      "eval_samples_per_second": 12.647,
      "eval_steps_per_second": 1.581,
      "step": 285
    },
    {
      "epoch": 3.0132978723404253,
      "grad_norm": 2.360816240310669,
      "learning_rate": 1.2721893491124262e-05,
      "loss": 0.6142,
      "step": 290
    },
    {
      "epoch": 3.0398936170212765,
      "grad_norm": 3.2934021949768066,
      "learning_rate": 1.1242603550295859e-05,
      "loss": 0.6263,
      "step": 300
    },
    {
      "epoch": 3.0664893617021276,
      "grad_norm": 2.3915889263153076,
      "learning_rate": 9.763313609467455e-06,
      "loss": 0.6514,
      "step": 310
    },
    {
      "epoch": 3.0930851063829787,
      "grad_norm": 3.9150514602661133,
      "learning_rate": 8.284023668639054e-06,
      "loss": 0.8365,
      "step": 320
    },
    {
      "epoch": 3.11968085106383,
      "grad_norm": 3.9853973388671875,
      "learning_rate": 6.8047337278106515e-06,
      "loss": 0.7772,
      "step": 330
    },
    {
      "epoch": 3.146276595744681,
      "grad_norm": 1.9402360916137695,
      "learning_rate": 5.325443786982249e-06,
      "loss": 0.8747,
      "step": 340
    },
    {
      "epoch": 3.172872340425532,
      "grad_norm": 3.0497424602508545,
      "learning_rate": 3.846153846153847e-06,
      "loss": 0.5998,
      "step": 350
    },
    {
      "epoch": 3.199468085106383,
      "grad_norm": 4.310546875,
      "learning_rate": 2.366863905325444e-06,
      "loss": 0.8328,
      "step": 360
    },
    {
      "epoch": 3.226063829787234,
      "grad_norm": 3.943880796432495,
      "learning_rate": 8.875739644970415e-07,
      "loss": 0.8287,
      "step": 370
    },
    {
      "epoch": 3.242021276595745,
      "eval_accuracy": 0.7875,
      "eval_loss": 0.7972937822341919,
      "eval_runtime": 11.2004,
      "eval_samples_per_second": 14.285,
      "eval_steps_per_second": 1.786,
      "step": 376
    },
    {
      "epoch": 3.242021276595745,
      "step": 376,
      "total_flos": 3.7220613152994755e+18,
      "train_loss": 0.7813464815312243,
      "train_runtime": 603.3994,
      "train_samples_per_second": 4.985,
      "train_steps_per_second": 0.623
    },
    {
      "epoch": 3.242021276595745,
      "eval_accuracy": 0.7633136094674556,
      "eval_loss": 0.8937366008758545,
      "eval_runtime": 12.7948,
      "eval_samples_per_second": 13.209,
      "eval_steps_per_second": 1.719,
      "step": 376
    },
    {
      "epoch": 3.242021276595745,
      "eval_accuracy": 0.7633136094674556,
      "eval_loss": 0.893736720085144,
      "eval_runtime": 11.4267,
      "eval_samples_per_second": 14.79,
      "eval_steps_per_second": 1.925,
      "step": 376
    }
  ],
  "logging_steps": 10,
  "max_steps": 376,
  "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": 3.7220613152994755e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}