{
  "best_metric": 0.8346934110853106,
  "best_model_checkpoint": "videomae-surf-analytics-runpod/checkpoint-370",
  "epoch": 4.1891891891891895,
  "eval_steps": 500,
  "global_step": 370,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 17.739418029785156,
      "learning_rate": 1.3513513513513515e-05,
      "loss": 1.4705,
      "step": 10
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 6.248379707336426,
      "learning_rate": 2.702702702702703e-05,
      "loss": 1.1378,
      "step": 20
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 6.359808444976807,
      "learning_rate": 4.0540540540540545e-05,
      "loss": 1.0852,
      "step": 30
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 7.196521282196045,
      "learning_rate": 4.954954954954955e-05,
      "loss": 0.7478,
      "step": 40
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 7.588693141937256,
      "learning_rate": 4.804804804804805e-05,
      "loss": 0.653,
      "step": 50
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 9.380898475646973,
      "learning_rate": 4.654654654654655e-05,
      "loss": 0.7808,
      "step": 60
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 9.640559196472168,
      "learning_rate": 4.5045045045045046e-05,
      "loss": 0.6213,
      "step": 70
    },
    {
      "epoch": 0.20270270270270271,
      "eval_accuracy": 0.6970954356846473,
      "eval_f1": 0.6901963848053563,
      "eval_loss": 0.7773587703704834,
      "eval_runtime": 77.0947,
      "eval_samples_per_second": 3.126,
      "eval_steps_per_second": 0.324,
      "step": 75
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 4.199209690093994,
      "learning_rate": 4.354354354354355e-05,
      "loss": 0.4215,
      "step": 80
    },
    {
      "epoch": 1.0405405405405406,
      "grad_norm": 3.8096096515655518,
      "learning_rate": 4.204204204204204e-05,
      "loss": 0.391,
      "step": 90
    },
    {
      "epoch": 1.0675675675675675,
      "grad_norm": 13.743525505065918,
      "learning_rate": 4.0540540540540545e-05,
      "loss": 0.4713,
      "step": 100
    },
    {
      "epoch": 1.0945945945945945,
      "grad_norm": 3.954926013946533,
      "learning_rate": 3.903903903903904e-05,
      "loss": 0.4197,
      "step": 110
    },
    {
      "epoch": 1.1216216216216217,
      "grad_norm": 7.9359211921691895,
      "learning_rate": 3.7537537537537536e-05,
      "loss": 0.3719,
      "step": 120
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 10.24318790435791,
      "learning_rate": 3.603603603603604e-05,
      "loss": 0.3922,
      "step": 130
    },
    {
      "epoch": 1.1756756756756757,
      "grad_norm": 13.8519926071167,
      "learning_rate": 3.453453453453453e-05,
      "loss": 0.4027,
      "step": 140
    },
    {
      "epoch": 1.2027027027027026,
      "grad_norm": 1.3211474418640137,
      "learning_rate": 3.3033033033033035e-05,
      "loss": 0.3269,
      "step": 150
    },
    {
      "epoch": 1.2027027027027026,
      "eval_accuracy": 0.7593360995850622,
      "eval_f1": 0.7561505755143376,
      "eval_loss": 0.6851304173469543,
      "eval_runtime": 78.2702,
      "eval_samples_per_second": 3.079,
      "eval_steps_per_second": 0.319,
      "step": 150
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 6.484254360198975,
      "learning_rate": 3.153153153153153e-05,
      "loss": 0.1699,
      "step": 160
    },
    {
      "epoch": 2.054054054054054,
      "grad_norm": 4.243548393249512,
      "learning_rate": 3.0030030030030033e-05,
      "loss": 0.1404,
      "step": 170
    },
    {
      "epoch": 2.081081081081081,
      "grad_norm": 4.49724006652832,
      "learning_rate": 2.852852852852853e-05,
      "loss": 0.2383,
      "step": 180
    },
    {
      "epoch": 2.108108108108108,
      "grad_norm": 5.5315632820129395,
      "learning_rate": 2.702702702702703e-05,
      "loss": 0.3597,
      "step": 190
    },
    {
      "epoch": 2.135135135135135,
      "grad_norm": 7.347559452056885,
      "learning_rate": 2.552552552552553e-05,
      "loss": 0.1501,
      "step": 200
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 0.20061562955379486,
      "learning_rate": 2.4024024024024024e-05,
      "loss": 0.1769,
      "step": 210
    },
    {
      "epoch": 2.189189189189189,
      "grad_norm": 0.2758616507053375,
      "learning_rate": 2.2522522522522523e-05,
      "loss": 0.2339,
      "step": 220
    },
    {
      "epoch": 2.2027027027027026,
      "eval_accuracy": 0.8008298755186722,
      "eval_f1": 0.7992975614249908,
      "eval_loss": 0.5251602530479431,
      "eval_runtime": 75.07,
      "eval_samples_per_second": 3.21,
      "eval_steps_per_second": 0.333,
      "step": 225
    },
    {
      "epoch": 3.0135135135135136,
      "grad_norm": 8.580607414245605,
      "learning_rate": 2.102102102102102e-05,
      "loss": 0.8979,
      "step": 230
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 0.5315948724746704,
      "learning_rate": 1.951951951951952e-05,
      "loss": 0.0559,
      "step": 240
    },
    {
      "epoch": 3.0675675675675675,
      "grad_norm": 0.13150528073310852,
      "learning_rate": 1.801801801801802e-05,
      "loss": 0.1062,
      "step": 250
    },
    {
      "epoch": 3.0945945945945947,
      "grad_norm": 19.857810974121094,
      "learning_rate": 1.6516516516516518e-05,
      "loss": 0.1066,
      "step": 260
    },
    {
      "epoch": 3.1216216216216215,
      "grad_norm": 1.9958362579345703,
      "learning_rate": 1.5015015015015016e-05,
      "loss": 0.1944,
      "step": 270
    },
    {
      "epoch": 3.1486486486486487,
      "grad_norm": 16.243772506713867,
      "learning_rate": 1.3513513513513515e-05,
      "loss": 0.137,
      "step": 280
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 3.6971592903137207,
      "learning_rate": 1.2012012012012012e-05,
      "loss": 0.1812,
      "step": 290
    },
    {
      "epoch": 3.2027027027027026,
      "grad_norm": 1.1694248914718628,
      "learning_rate": 1.051051051051051e-05,
      "loss": 0.1931,
      "step": 300
    },
    {
      "epoch": 3.2027027027027026,
      "eval_accuracy": 0.8340248962655602,
      "eval_f1": 0.8341831246711504,
      "eval_loss": 0.4942285716533661,
      "eval_runtime": 73.8969,
      "eval_samples_per_second": 3.261,
      "eval_steps_per_second": 0.338,
      "step": 300
    },
    {
      "epoch": 4.027027027027027,
      "grad_norm": 2.825990915298462,
      "learning_rate": 9.00900900900901e-06,
      "loss": 0.0731,
      "step": 310
    },
    {
      "epoch": 4.054054054054054,
      "grad_norm": 0.2709617614746094,
      "learning_rate": 7.507507507507508e-06,
      "loss": 0.0751,
      "step": 320
    },
    {
      "epoch": 4.081081081081081,
      "grad_norm": 0.10882856696844101,
      "learning_rate": 6.006006006006006e-06,
      "loss": 0.0774,
      "step": 330
    },
    {
      "epoch": 4.108108108108108,
      "grad_norm": 0.09481658786535263,
      "learning_rate": 4.504504504504505e-06,
      "loss": 0.0567,
      "step": 340
    },
    {
      "epoch": 4.135135135135135,
      "grad_norm": 0.3658810257911682,
      "learning_rate": 3.003003003003003e-06,
      "loss": 0.0438,
      "step": 350
    },
    {
      "epoch": 4.162162162162162,
      "grad_norm": 0.9697806239128113,
      "learning_rate": 1.5015015015015015e-06,
      "loss": 0.098,
      "step": 360
    },
    {
      "epoch": 4.1891891891891895,
      "grad_norm": 0.357666552066803,
      "learning_rate": 0.0,
      "loss": 0.1037,
      "step": 370
    },
    {
      "epoch": 4.1891891891891895,
      "eval_accuracy": 0.8340248962655602,
      "eval_f1": 0.8346934110853106,
      "eval_loss": 0.47942548990249634,
      "eval_runtime": 73.9617,
      "eval_samples_per_second": 3.258,
      "eval_steps_per_second": 0.338,
      "step": 370
    },
    {
      "epoch": 4.1891891891891895,
      "step": 370,
      "total_flos": 3.2102444558954004e+18,
      "train_loss": 0.36656422937238536,
      "train_runtime": 1888.2958,
      "train_samples_per_second": 1.959,
      "train_steps_per_second": 0.196
    },
    {
      "epoch": 4.1891891891891895,
      "eval_accuracy": 0.9784075573549258,
      "eval_f1": 0.9783996585344938,
      "eval_loss": 0.06370694935321808,
      "eval_runtime": 252.958,
      "eval_samples_per_second": 2.929,
      "eval_steps_per_second": 0.296,
      "step": 370
    },
    {
      "epoch": 4.1891891891891895,
      "eval_accuracy": 0.8067415730337079,
      "eval_f1": 0.8059471321937128,
      "eval_loss": 0.6186416745185852,
      "eval_runtime": 137.3351,
      "eval_samples_per_second": 3.24,
      "eval_steps_per_second": 0.328,
      "step": 370
    },
    {
      "epoch": 4.1891891891891895,
      "eval_accuracy": 0.8340248962655602,
      "eval_f1": 0.8346934110853106,
      "eval_loss": 0.47942548990249634,
      "eval_runtime": 73.4732,
      "eval_samples_per_second": 3.28,
      "eval_steps_per_second": 0.34,
      "step": 370
    }
  ],
  "logging_steps": 10,
  "max_steps": 370,
  "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": 3.2102444558954004e+18,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}