{
  "best_metric": 0.011764705882352941,
  "best_model_checkpoint": "videomae-base-finetuned-ElderReact-Sadness12/checkpoint-195",
  "epoch": 9.076315789473684,
  "eval_steps": 500,
  "global_step": 380,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "grad_norm": 6.048687934875488,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 0.6582,
      "step": 10
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.6699490547180176,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.53,
      "step": 20
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.7039493322372437,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 0.5312,
      "step": 30
    },
    {
      "epoch": 0.1,
      "eval_f1": 0.0,
      "eval_loss": 0.5029338002204895,
      "eval_runtime": 200.7405,
      "eval_samples_per_second": 3.965,
      "eval_steps_per_second": 0.249,
      "step": 39
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.7121078968048096,
      "learning_rate": 4.970760233918128e-05,
      "loss": 0.463,
      "step": 40
    },
    {
      "epoch": 1.03,
      "grad_norm": 4.501192092895508,
      "learning_rate": 4.824561403508772e-05,
      "loss": 0.5258,
      "step": 50
    },
    {
      "epoch": 1.06,
      "grad_norm": 4.873466491699219,
      "learning_rate": 4.678362573099415e-05,
      "loss": 0.4323,
      "step": 60
    },
    {
      "epoch": 1.08,
      "grad_norm": 3.1683290004730225,
      "learning_rate": 4.5321637426900585e-05,
      "loss": 0.4889,
      "step": 70
    },
    {
      "epoch": 1.1,
      "eval_f1": 0.0,
      "eval_loss": 0.5069170594215393,
      "eval_runtime": 206.7868,
      "eval_samples_per_second": 3.849,
      "eval_steps_per_second": 0.242,
      "step": 78
    },
    {
      "epoch": 2.01,
      "grad_norm": 1.351720929145813,
      "learning_rate": 4.3859649122807014e-05,
      "loss": 0.4661,
      "step": 80
    },
    {
      "epoch": 2.03,
      "grad_norm": 2.8010413646698,
      "learning_rate": 4.239766081871345e-05,
      "loss": 0.48,
      "step": 90
    },
    {
      "epoch": 2.06,
      "grad_norm": 5.665361404418945,
      "learning_rate": 4.093567251461988e-05,
      "loss": 0.559,
      "step": 100
    },
    {
      "epoch": 2.08,
      "grad_norm": 1.190671682357788,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 0.4707,
      "step": 110
    },
    {
      "epoch": 2.1,
      "eval_f1": 0.0,
      "eval_loss": 0.52621990442276,
      "eval_runtime": 214.3958,
      "eval_samples_per_second": 3.713,
      "eval_steps_per_second": 0.233,
      "step": 117
    },
    {
      "epoch": 3.01,
      "grad_norm": 1.8163896799087524,
      "learning_rate": 3.8011695906432746e-05,
      "loss": 0.426,
      "step": 120
    },
    {
      "epoch": 3.03,
      "grad_norm": 1.4688210487365723,
      "learning_rate": 3.654970760233918e-05,
      "loss": 0.4022,
      "step": 130
    },
    {
      "epoch": 3.06,
      "grad_norm": 2.077988386154175,
      "learning_rate": 3.508771929824561e-05,
      "loss": 0.5341,
      "step": 140
    },
    {
      "epoch": 3.09,
      "grad_norm": 1.402732491493225,
      "learning_rate": 3.362573099415205e-05,
      "loss": 0.4758,
      "step": 150
    },
    {
      "epoch": 3.1,
      "eval_f1": 0.0,
      "eval_loss": 0.5054653882980347,
      "eval_runtime": 205.8731,
      "eval_samples_per_second": 3.866,
      "eval_steps_per_second": 0.243,
      "step": 156
    },
    {
      "epoch": 4.01,
      "grad_norm": 1.0033667087554932,
      "learning_rate": 3.216374269005848e-05,
      "loss": 0.4712,
      "step": 160
    },
    {
      "epoch": 4.04,
      "grad_norm": 1.153987169265747,
      "learning_rate": 3.0701754385964913e-05,
      "loss": 0.4766,
      "step": 170
    },
    {
      "epoch": 4.06,
      "grad_norm": 2.2413759231567383,
      "learning_rate": 2.9239766081871346e-05,
      "loss": 0.3828,
      "step": 180
    },
    {
      "epoch": 4.09,
      "grad_norm": 1.6635860204696655,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.5164,
      "step": 190
    },
    {
      "epoch": 4.1,
      "eval_f1": 0.011764705882352941,
      "eval_loss": 0.5524570941925049,
      "eval_runtime": 209.7075,
      "eval_samples_per_second": 3.796,
      "eval_steps_per_second": 0.238,
      "step": 195
    },
    {
      "epoch": 5.01,
      "grad_norm": 5.072777271270752,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.5209,
      "step": 200
    },
    {
      "epoch": 5.04,
      "grad_norm": 1.1866474151611328,
      "learning_rate": 2.485380116959064e-05,
      "loss": 0.4455,
      "step": 210
    },
    {
      "epoch": 5.07,
      "grad_norm": 3.4566450119018555,
      "learning_rate": 2.3391812865497074e-05,
      "loss": 0.4492,
      "step": 220
    },
    {
      "epoch": 5.09,
      "grad_norm": 1.305912971496582,
      "learning_rate": 2.1929824561403507e-05,
      "loss": 0.4793,
      "step": 230
    },
    {
      "epoch": 5.1,
      "eval_f1": 0.0,
      "eval_loss": 0.512092649936676,
      "eval_runtime": 191.2967,
      "eval_samples_per_second": 4.161,
      "eval_steps_per_second": 0.261,
      "step": 234
    },
    {
      "epoch": 6.02,
      "grad_norm": 1.2563284635543823,
      "learning_rate": 2.046783625730994e-05,
      "loss": 0.3722,
      "step": 240
    },
    {
      "epoch": 6.04,
      "grad_norm": 3.25819993019104,
      "learning_rate": 1.9005847953216373e-05,
      "loss": 0.5026,
      "step": 250
    },
    {
      "epoch": 6.07,
      "grad_norm": 1.9585869312286377,
      "learning_rate": 1.7543859649122806e-05,
      "loss": 0.4454,
      "step": 260
    },
    {
      "epoch": 6.09,
      "grad_norm": 5.147015571594238,
      "learning_rate": 1.608187134502924e-05,
      "loss": 0.4872,
      "step": 270
    },
    {
      "epoch": 6.1,
      "eval_f1": 0.0,
      "eval_loss": 0.5168163180351257,
      "eval_runtime": 187.9502,
      "eval_samples_per_second": 4.235,
      "eval_steps_per_second": 0.266,
      "step": 273
    },
    {
      "epoch": 7.02,
      "grad_norm": 3.3504269123077393,
      "learning_rate": 1.4619883040935673e-05,
      "loss": 0.4434,
      "step": 280
    },
    {
      "epoch": 7.04,
      "grad_norm": 2.3411853313446045,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 0.4706,
      "step": 290
    },
    {
      "epoch": 7.07,
      "grad_norm": 1.4593596458435059,
      "learning_rate": 1.1695906432748537e-05,
      "loss": 0.4031,
      "step": 300
    },
    {
      "epoch": 7.1,
      "grad_norm": 3.9099016189575195,
      "learning_rate": 1.023391812865497e-05,
      "loss": 0.3846,
      "step": 310
    },
    {
      "epoch": 7.1,
      "eval_f1": 0.0,
      "eval_loss": 0.548977792263031,
      "eval_runtime": 200.6612,
      "eval_samples_per_second": 3.967,
      "eval_steps_per_second": 0.249,
      "step": 312
    },
    {
      "epoch": 8.02,
      "grad_norm": 2.722304582595825,
      "learning_rate": 8.771929824561403e-06,
      "loss": 0.5456,
      "step": 320
    },
    {
      "epoch": 8.05,
      "grad_norm": 1.7937108278274536,
      "learning_rate": 7.3099415204678366e-06,
      "loss": 0.3438,
      "step": 330
    },
    {
      "epoch": 8.07,
      "grad_norm": 1.8574304580688477,
      "learning_rate": 5.8479532163742686e-06,
      "loss": 0.5481,
      "step": 340
    },
    {
      "epoch": 8.1,
      "grad_norm": 3.4769558906555176,
      "learning_rate": 4.3859649122807014e-06,
      "loss": 0.3796,
      "step": 350
    },
    {
      "epoch": 8.1,
      "eval_f1": 0.0,
      "eval_loss": 0.5376216173171997,
      "eval_runtime": 192.8973,
      "eval_samples_per_second": 4.127,
      "eval_steps_per_second": 0.259,
      "step": 351
    },
    {
      "epoch": 9.02,
      "grad_norm": 2.116058349609375,
      "learning_rate": 2.9239766081871343e-06,
      "loss": 0.416,
      "step": 360
    },
    {
      "epoch": 9.05,
      "grad_norm": 2.9650416374206543,
      "learning_rate": 1.4619883040935671e-06,
      "loss": 0.4537,
      "step": 370
    },
    {
      "epoch": 9.08,
      "grad_norm": 1.7653827667236328,
      "learning_rate": 0.0,
      "loss": 0.3853,
      "step": 380
    },
    {
      "epoch": 9.08,
      "eval_f1": 0.0,
      "eval_loss": 0.5240046977996826,
      "eval_runtime": 200.4262,
      "eval_samples_per_second": 3.972,
      "eval_steps_per_second": 0.249,
      "step": 380
    },
    {
      "epoch": 9.08,
      "step": 380,
      "total_flos": 7.475141472240992e+18,
      "train_loss": 0.4675432085990906,
      "train_runtime": 3759.0695,
      "train_samples_per_second": 1.617,
      "train_steps_per_second": 0.101
    },
    {
      "epoch": 9.08,
      "eval_f1": 0.013333333333333334,
      "eval_loss": 0.5360399484634399,
      "eval_runtime": 179.5545,
      "eval_samples_per_second": 4.177,
      "eval_steps_per_second": 0.262,
      "step": 380
    },
    {
      "epoch": 9.08,
      "eval_f1": 0.013333333333333334,
      "eval_loss": 0.5360399484634399,
      "eval_runtime": 198.4663,
      "eval_samples_per_second": 3.779,
      "eval_steps_per_second": 0.237,
      "step": 380
    }
  ],
  "logging_steps": 10,
  "max_steps": 380,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 7.475141472240992e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}