{
  "best_metric": 0.25752508361204013,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-465",
  "epoch": 15.03125,
  "eval_steps": 500,
  "global_step": 480,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020833333333333332,
      "grad_norm": 4.865664958953857,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 4.2486,
      "step": 10
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 5.374879837036133,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 4.2806,
      "step": 20
    },
    {
      "epoch": 0.0625,
      "grad_norm": 4.254001140594482,
      "learning_rate": 3.125e-05,
      "loss": 4.2682,
      "step": 30
    },
    {
      "epoch": 0.06458333333333334,
      "eval_accuracy": 0.0033444816053511705,
      "eval_loss": 4.24931526184082,
      "eval_runtime": 156.0528,
      "eval_samples_per_second": 1.916,
      "eval_steps_per_second": 0.064,
      "step": 31
    },
    {
      "epoch": 1.01875,
      "grad_norm": 3.580606698989868,
      "learning_rate": 4.166666666666667e-05,
      "loss": 4.249,
      "step": 40
    },
    {
      "epoch": 1.0395833333333333,
      "grad_norm": 3.6750593185424805,
      "learning_rate": 4.976851851851852e-05,
      "loss": 4.2497,
      "step": 50
    },
    {
      "epoch": 1.0604166666666666,
      "grad_norm": 3.427530527114868,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 4.2584,
      "step": 60
    },
    {
      "epoch": 1.0645833333333334,
      "eval_accuracy": 0.013377926421404682,
      "eval_loss": 4.243381023406982,
      "eval_runtime": 184.9,
      "eval_samples_per_second": 1.617,
      "eval_steps_per_second": 0.054,
      "step": 62
    },
    {
      "epoch": 2.0166666666666666,
      "grad_norm": 3.5070836544036865,
      "learning_rate": 4.745370370370371e-05,
      "loss": 4.221,
      "step": 70
    },
    {
      "epoch": 2.0375,
      "grad_norm": 3.814365863800049,
      "learning_rate": 4.62962962962963e-05,
      "loss": 4.249,
      "step": 80
    },
    {
      "epoch": 2.058333333333333,
      "grad_norm": 3.279081344604492,
      "learning_rate": 4.5138888888888894e-05,
      "loss": 4.2518,
      "step": 90
    },
    {
      "epoch": 2.064583333333333,
      "eval_accuracy": 0.016722408026755852,
      "eval_loss": 4.224606990814209,
      "eval_runtime": 182.615,
      "eval_samples_per_second": 1.637,
      "eval_steps_per_second": 0.055,
      "step": 93
    },
    {
      "epoch": 3.0145833333333334,
      "grad_norm": 2.9108073711395264,
      "learning_rate": 4.3981481481481486e-05,
      "loss": 4.2168,
      "step": 100
    },
    {
      "epoch": 3.035416666666667,
      "grad_norm": 3.1853749752044678,
      "learning_rate": 4.282407407407408e-05,
      "loss": 4.2103,
      "step": 110
    },
    {
      "epoch": 3.05625,
      "grad_norm": 3.1384546756744385,
      "learning_rate": 4.166666666666667e-05,
      "loss": 4.2445,
      "step": 120
    },
    {
      "epoch": 3.064583333333333,
      "eval_accuracy": 0.006688963210702341,
      "eval_loss": 4.220835208892822,
      "eval_runtime": 172.1522,
      "eval_samples_per_second": 1.737,
      "eval_steps_per_second": 0.058,
      "step": 124
    },
    {
      "epoch": 4.0125,
      "grad_norm": 2.7196435928344727,
      "learning_rate": 4.0509259259259265e-05,
      "loss": 4.2159,
      "step": 130
    },
    {
      "epoch": 4.033333333333333,
      "grad_norm": 2.6634223461151123,
      "learning_rate": 3.935185185185186e-05,
      "loss": 4.2063,
      "step": 140
    },
    {
      "epoch": 4.054166666666666,
      "grad_norm": 2.5531411170959473,
      "learning_rate": 3.8194444444444444e-05,
      "loss": 4.2272,
      "step": 150
    },
    {
      "epoch": 4.064583333333333,
      "eval_accuracy": 0.010033444816053512,
      "eval_loss": 4.223015308380127,
      "eval_runtime": 163.7094,
      "eval_samples_per_second": 1.826,
      "eval_steps_per_second": 0.061,
      "step": 155
    },
    {
      "epoch": 5.010416666666667,
      "grad_norm": 2.824289321899414,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 4.2151,
      "step": 160
    },
    {
      "epoch": 5.03125,
      "grad_norm": 2.8366966247558594,
      "learning_rate": 3.587962962962963e-05,
      "loss": 4.183,
      "step": 170
    },
    {
      "epoch": 5.052083333333333,
      "grad_norm": 3.340677499771118,
      "learning_rate": 3.472222222222222e-05,
      "loss": 4.205,
      "step": 180
    },
    {
      "epoch": 5.064583333333333,
      "eval_accuracy": 0.023411371237458192,
      "eval_loss": 4.211067199707031,
      "eval_runtime": 166.937,
      "eval_samples_per_second": 1.791,
      "eval_steps_per_second": 0.06,
      "step": 186
    },
    {
      "epoch": 6.008333333333334,
      "grad_norm": 2.784593105316162,
      "learning_rate": 3.3564814814814815e-05,
      "loss": 4.1898,
      "step": 190
    },
    {
      "epoch": 6.029166666666667,
      "grad_norm": 3.389150381088257,
      "learning_rate": 3.240740740740741e-05,
      "loss": 4.1386,
      "step": 200
    },
    {
      "epoch": 6.05,
      "grad_norm": 3.5054867267608643,
      "learning_rate": 3.125e-05,
      "loss": 4.1238,
      "step": 210
    },
    {
      "epoch": 6.064583333333333,
      "eval_accuracy": 0.03678929765886288,
      "eval_loss": 4.111179828643799,
      "eval_runtime": 161.8854,
      "eval_samples_per_second": 1.847,
      "eval_steps_per_second": 0.062,
      "step": 217
    },
    {
      "epoch": 7.00625,
      "grad_norm": 4.150498867034912,
      "learning_rate": 3.0092592592592593e-05,
      "loss": 4.0898,
      "step": 220
    },
    {
      "epoch": 7.027083333333334,
      "grad_norm": 4.683104038238525,
      "learning_rate": 2.8935185185185186e-05,
      "loss": 4.0073,
      "step": 230
    },
    {
      "epoch": 7.047916666666667,
      "grad_norm": 4.379587650299072,
      "learning_rate": 2.777777777777778e-05,
      "loss": 3.9136,
      "step": 240
    },
    {
      "epoch": 7.064583333333333,
      "eval_accuracy": 0.07357859531772576,
      "eval_loss": 3.8529512882232666,
      "eval_runtime": 164.2718,
      "eval_samples_per_second": 1.82,
      "eval_steps_per_second": 0.061,
      "step": 248
    },
    {
      "epoch": 8.004166666666666,
      "grad_norm": 5.4900078773498535,
      "learning_rate": 2.6620370370370372e-05,
      "loss": 3.8304,
      "step": 250
    },
    {
      "epoch": 8.025,
      "grad_norm": 4.974089622497559,
      "learning_rate": 2.5462962962962965e-05,
      "loss": 3.7169,
      "step": 260
    },
    {
      "epoch": 8.045833333333333,
      "grad_norm": 5.386253833770752,
      "learning_rate": 2.4305555555555558e-05,
      "loss": 3.6241,
      "step": 270
    },
    {
      "epoch": 8.064583333333333,
      "eval_accuracy": 0.11705685618729098,
      "eval_loss": 3.6734354496002197,
      "eval_runtime": 159.295,
      "eval_samples_per_second": 1.877,
      "eval_steps_per_second": 0.063,
      "step": 279
    },
    {
      "epoch": 9.002083333333333,
      "grad_norm": 5.429062843322754,
      "learning_rate": 2.314814814814815e-05,
      "loss": 3.4885,
      "step": 280
    },
    {
      "epoch": 9.022916666666667,
      "grad_norm": 5.275113105773926,
      "learning_rate": 2.1990740740740743e-05,
      "loss": 3.4022,
      "step": 290
    },
    {
      "epoch": 9.04375,
      "grad_norm": 6.2369704246521,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 3.2977,
      "step": 300
    },
    {
      "epoch": 9.064583333333333,
      "grad_norm": 13.635384559631348,
      "learning_rate": 1.967592592592593e-05,
      "loss": 3.3103,
      "step": 310
    },
    {
      "epoch": 9.064583333333333,
      "eval_accuracy": 0.10702341137123746,
      "eval_loss": 3.5260610580444336,
      "eval_runtime": 170.757,
      "eval_samples_per_second": 1.751,
      "eval_steps_per_second": 0.059,
      "step": 310
    },
    {
      "epoch": 10.020833333333334,
      "grad_norm": 6.099160194396973,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 3.1017,
      "step": 320
    },
    {
      "epoch": 10.041666666666666,
      "grad_norm": 8.271078109741211,
      "learning_rate": 1.736111111111111e-05,
      "loss": 3.0604,
      "step": 330
    },
    {
      "epoch": 10.0625,
      "grad_norm": 6.345729827880859,
      "learning_rate": 1.6203703703703704e-05,
      "loss": 3.0981,
      "step": 340
    },
    {
      "epoch": 10.064583333333333,
      "eval_accuracy": 0.16387959866220736,
      "eval_loss": 3.3859572410583496,
      "eval_runtime": 165.4502,
      "eval_samples_per_second": 1.807,
      "eval_steps_per_second": 0.06,
      "step": 341
    },
    {
      "epoch": 11.01875,
      "grad_norm": 6.985031604766846,
      "learning_rate": 1.5046296296296297e-05,
      "loss": 2.9706,
      "step": 350
    },
    {
      "epoch": 11.039583333333333,
      "grad_norm": 6.81059455871582,
      "learning_rate": 1.388888888888889e-05,
      "loss": 2.916,
      "step": 360
    },
    {
      "epoch": 11.060416666666667,
      "grad_norm": 6.5202436447143555,
      "learning_rate": 1.2731481481481482e-05,
      "loss": 2.8216,
      "step": 370
    },
    {
      "epoch": 11.064583333333333,
      "eval_accuracy": 0.2140468227424749,
      "eval_loss": 3.179076671600342,
      "eval_runtime": 163.8066,
      "eval_samples_per_second": 1.825,
      "eval_steps_per_second": 0.061,
      "step": 372
    },
    {
      "epoch": 12.016666666666667,
      "grad_norm": 5.686159610748291,
      "learning_rate": 1.1574074074074075e-05,
      "loss": 2.7755,
      "step": 380
    },
    {
      "epoch": 12.0375,
      "grad_norm": 6.596237659454346,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 2.824,
      "step": 390
    },
    {
      "epoch": 12.058333333333334,
      "grad_norm": 7.551661968231201,
      "learning_rate": 9.259259259259259e-06,
      "loss": 2.6108,
      "step": 400
    },
    {
      "epoch": 12.064583333333333,
      "eval_accuracy": 0.24414715719063546,
      "eval_loss": 3.1618316173553467,
      "eval_runtime": 177.1262,
      "eval_samples_per_second": 1.688,
      "eval_steps_per_second": 0.056,
      "step": 403
    },
    {
      "epoch": 13.014583333333333,
      "grad_norm": 6.725275039672852,
      "learning_rate": 8.101851851851852e-06,
      "loss": 2.7309,
      "step": 410
    },
    {
      "epoch": 13.035416666666666,
      "grad_norm": 7.1535563468933105,
      "learning_rate": 6.944444444444445e-06,
      "loss": 2.6451,
      "step": 420
    },
    {
      "epoch": 13.05625,
      "grad_norm": 7.705063819885254,
      "learning_rate": 5.787037037037038e-06,
      "loss": 2.598,
      "step": 430
    },
    {
      "epoch": 13.064583333333333,
      "eval_accuracy": 0.23411371237458195,
      "eval_loss": 3.0792758464813232,
      "eval_runtime": 186.6022,
      "eval_samples_per_second": 1.602,
      "eval_steps_per_second": 0.054,
      "step": 434
    },
    {
      "epoch": 14.0125,
      "grad_norm": 5.5132927894592285,
      "learning_rate": 4.6296296296296296e-06,
      "loss": 2.5532,
      "step": 440
    },
    {
      "epoch": 14.033333333333333,
      "grad_norm": 6.853929042816162,
      "learning_rate": 3.4722222222222224e-06,
      "loss": 2.56,
      "step": 450
    },
    {
      "epoch": 14.054166666666667,
      "grad_norm": 6.731771469116211,
      "learning_rate": 2.3148148148148148e-06,
      "loss": 2.5023,
      "step": 460
    },
    {
      "epoch": 14.064583333333333,
      "eval_accuracy": 0.25752508361204013,
      "eval_loss": 3.019373893737793,
      "eval_runtime": 155.2839,
      "eval_samples_per_second": 1.926,
      "eval_steps_per_second": 0.064,
      "step": 465
    },
    {
      "epoch": 15.010416666666666,
      "grad_norm": 6.570545673370361,
      "learning_rate": 1.1574074074074074e-06,
      "loss": 2.5538,
      "step": 470
    },
    {
      "epoch": 15.03125,
      "grad_norm": 6.480160236358643,
      "learning_rate": 0.0,
      "loss": 2.513,
      "step": 480
    },
    {
      "epoch": 15.03125,
      "eval_accuracy": 0.23745819397993312,
      "eval_loss": 3.0668206214904785,
      "eval_runtime": 187.3659,
      "eval_samples_per_second": 1.596,
      "eval_steps_per_second": 0.053,
      "step": 480
    },
    {
      "epoch": 15.03125,
      "step": 480,
      "total_flos": 1.8664399999458017e+19,
      "train_loss": 3.5868410070737204,
      "train_runtime": 12231.8484,
      "train_samples_per_second": 1.256,
      "train_steps_per_second": 0.039
    },
    {
      "epoch": 15.03125,
      "eval_accuracy": 0.25752508361204013,
      "eval_loss": 3.0240976810455322,
      "eval_runtime": 158.7962,
      "eval_samples_per_second": 1.883,
      "eval_steps_per_second": 0.063,
      "step": 480
    },
    {
      "epoch": 15.03125,
      "eval_accuracy": 0.25752508361204013,
      "eval_loss": 3.0235204696655273,
      "eval_runtime": 157.8403,
      "eval_samples_per_second": 1.894,
      "eval_steps_per_second": 0.063,
      "step": 480
    }
  ],
  "logging_steps": 10,
  "max_steps": 480,
  "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": 1.8664399999458017e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}