{
  "best_metric": 0.7939698492462312,
  "best_model_checkpoint": "videomae-base-finetuned-ElderReact-Sadness11/checkpoint-39",
  "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": 5.057394027709961,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 0.5954,
      "step": 10
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.3400027751922607,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.5237,
      "step": 20
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.731216549873352,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 0.536,
      "step": 30
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.7939698492462312,
      "eval_loss": 0.5131362080574036,
      "eval_runtime": 204.6912,
      "eval_samples_per_second": 3.889,
      "eval_steps_per_second": 0.244,
      "step": 39
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.5283629894256592,
      "learning_rate": 4.970760233918128e-05,
      "loss": 0.4652,
      "step": 40
    },
    {
      "epoch": 1.03,
      "grad_norm": 4.3654375076293945,
      "learning_rate": 4.824561403508772e-05,
      "loss": 0.5204,
      "step": 50
    },
    {
      "epoch": 1.06,
      "grad_norm": 4.845033168792725,
      "learning_rate": 4.678362573099415e-05,
      "loss": 0.4353,
      "step": 60
    },
    {
      "epoch": 1.08,
      "grad_norm": 3.4814226627349854,
      "learning_rate": 4.5321637426900585e-05,
      "loss": 0.4818,
      "step": 70
    },
    {
      "epoch": 1.1,
      "eval_accuracy": 0.7939698492462312,
      "eval_loss": 0.5103316307067871,
      "eval_runtime": 217.1913,
      "eval_samples_per_second": 3.665,
      "eval_steps_per_second": 0.23,
      "step": 78
    },
    {
      "epoch": 2.01,
      "grad_norm": 1.3778834342956543,
      "learning_rate": 4.3859649122807014e-05,
      "loss": 0.4654,
      "step": 80
    },
    {
      "epoch": 2.03,
      "grad_norm": 2.985764503479004,
      "learning_rate": 4.239766081871345e-05,
      "loss": 0.4797,
      "step": 90
    },
    {
      "epoch": 2.06,
      "grad_norm": 5.408680438995361,
      "learning_rate": 4.093567251461988e-05,
      "loss": 0.5515,
      "step": 100
    },
    {
      "epoch": 2.08,
      "grad_norm": 1.4513001441955566,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 0.4619,
      "step": 110
    },
    {
      "epoch": 2.1,
      "eval_accuracy": 0.7939698492462312,
      "eval_loss": 0.5378741025924683,
      "eval_runtime": 210.4629,
      "eval_samples_per_second": 3.782,
      "eval_steps_per_second": 0.238,
      "step": 117
    },
    {
      "epoch": 3.01,
      "grad_norm": 1.8063580989837646,
      "learning_rate": 3.8011695906432746e-05,
      "loss": 0.415,
      "step": 120
    },
    {
      "epoch": 3.03,
      "grad_norm": 1.633288025856018,
      "learning_rate": 3.654970760233918e-05,
      "loss": 0.3969,
      "step": 130
    },
    {
      "epoch": 3.06,
      "grad_norm": 2.1381514072418213,
      "learning_rate": 3.508771929824561e-05,
      "loss": 0.5252,
      "step": 140
    },
    {
      "epoch": 3.09,
      "grad_norm": 1.0985075235366821,
      "learning_rate": 3.362573099415205e-05,
      "loss": 0.4704,
      "step": 150
    },
    {
      "epoch": 3.1,
      "eval_accuracy": 0.7939698492462312,
      "eval_loss": 0.5121056437492371,
      "eval_runtime": 211.8645,
      "eval_samples_per_second": 3.757,
      "eval_steps_per_second": 0.236,
      "step": 156
    },
    {
      "epoch": 4.01,
      "grad_norm": 1.3139609098434448,
      "learning_rate": 3.216374269005848e-05,
      "loss": 0.472,
      "step": 160
    },
    {
      "epoch": 4.04,
      "grad_norm": 1.0382041931152344,
      "learning_rate": 3.0701754385964913e-05,
      "loss": 0.476,
      "step": 170
    },
    {
      "epoch": 4.06,
      "grad_norm": 1.9487144947052002,
      "learning_rate": 2.9239766081871346e-05,
      "loss": 0.3877,
      "step": 180
    },
    {
      "epoch": 4.09,
      "grad_norm": 1.7637165784835815,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.5128,
      "step": 190
    },
    {
      "epoch": 4.1,
      "eval_accuracy": 0.785175879396985,
      "eval_loss": 0.5606660842895508,
      "eval_runtime": 217.2766,
      "eval_samples_per_second": 3.664,
      "eval_steps_per_second": 0.23,
      "step": 195
    },
    {
      "epoch": 5.01,
      "grad_norm": 5.227734088897705,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.5178,
      "step": 200
    },
    {
      "epoch": 5.04,
      "grad_norm": 1.3204573392868042,
      "learning_rate": 2.485380116959064e-05,
      "loss": 0.4433,
      "step": 210
    },
    {
      "epoch": 5.07,
      "grad_norm": 4.037812232971191,
      "learning_rate": 2.3391812865497074e-05,
      "loss": 0.4521,
      "step": 220
    },
    {
      "epoch": 5.09,
      "grad_norm": 1.3772491216659546,
      "learning_rate": 2.1929824561403507e-05,
      "loss": 0.4691,
      "step": 230
    },
    {
      "epoch": 5.1,
      "eval_accuracy": 0.7939698492462312,
      "eval_loss": 0.5311861634254456,
      "eval_runtime": 237.5745,
      "eval_samples_per_second": 3.351,
      "eval_steps_per_second": 0.21,
      "step": 234
    },
    {
      "epoch": 6.02,
      "grad_norm": 1.5507118701934814,
      "learning_rate": 2.046783625730994e-05,
      "loss": 0.3618,
      "step": 240
    },
    {
      "epoch": 6.04,
      "grad_norm": 2.258527994155884,
      "learning_rate": 1.9005847953216373e-05,
      "loss": 0.4646,
      "step": 250
    },
    {
      "epoch": 6.07,
      "grad_norm": 2.1282131671905518,
      "learning_rate": 1.7543859649122806e-05,
      "loss": 0.4335,
      "step": 260
    },
    {
      "epoch": 6.09,
      "grad_norm": 6.060189723968506,
      "learning_rate": 1.608187134502924e-05,
      "loss": 0.4799,
      "step": 270
    },
    {
      "epoch": 6.1,
      "eval_accuracy": 0.7939698492462312,
      "eval_loss": 0.5785809755325317,
      "eval_runtime": 226.9223,
      "eval_samples_per_second": 3.508,
      "eval_steps_per_second": 0.22,
      "step": 273
    },
    {
      "epoch": 7.02,
      "grad_norm": 2.6040494441986084,
      "learning_rate": 1.4619883040935673e-05,
      "loss": 0.4185,
      "step": 280
    },
    {
      "epoch": 7.04,
      "grad_norm": 2.301250457763672,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 0.4667,
      "step": 290
    },
    {
      "epoch": 7.07,
      "grad_norm": 1.555298089981079,
      "learning_rate": 1.1695906432748537e-05,
      "loss": 0.3985,
      "step": 300
    },
    {
      "epoch": 7.1,
      "grad_norm": 4.446948528289795,
      "learning_rate": 1.023391812865497e-05,
      "loss": 0.3584,
      "step": 310
    },
    {
      "epoch": 7.1,
      "eval_accuracy": 0.7939698492462312,
      "eval_loss": 0.5997191071510315,
      "eval_runtime": 210.3019,
      "eval_samples_per_second": 3.785,
      "eval_steps_per_second": 0.238,
      "step": 312
    },
    {
      "epoch": 8.02,
      "grad_norm": 3.671874761581421,
      "learning_rate": 8.771929824561403e-06,
      "loss": 0.5455,
      "step": 320
    },
    {
      "epoch": 8.05,
      "grad_norm": 1.981838345527649,
      "learning_rate": 7.3099415204678366e-06,
      "loss": 0.3086,
      "step": 330
    },
    {
      "epoch": 8.07,
      "grad_norm": 1.8950921297073364,
      "learning_rate": 5.8479532163742686e-06,
      "loss": 0.5139,
      "step": 340
    },
    {
      "epoch": 8.1,
      "grad_norm": 3.0630290508270264,
      "learning_rate": 4.3859649122807014e-06,
      "loss": 0.3749,
      "step": 350
    },
    {
      "epoch": 8.1,
      "eval_accuracy": 0.7939698492462312,
      "eval_loss": 0.5853101015090942,
      "eval_runtime": 215.7709,
      "eval_samples_per_second": 3.689,
      "eval_steps_per_second": 0.232,
      "step": 351
    },
    {
      "epoch": 9.02,
      "grad_norm": 2.4308969974517822,
      "learning_rate": 2.9239766081871343e-06,
      "loss": 0.3716,
      "step": 360
    },
    {
      "epoch": 9.05,
      "grad_norm": 2.7709577083587646,
      "learning_rate": 1.4619883040935671e-06,
      "loss": 0.4279,
      "step": 370
    },
    {
      "epoch": 9.08,
      "grad_norm": 3.444274425506592,
      "learning_rate": 0.0,
      "loss": 0.3792,
      "step": 380
    },
    {
      "epoch": 9.08,
      "eval_accuracy": 0.7939698492462312,
      "eval_loss": 0.5896389484405518,
      "eval_runtime": 206.7967,
      "eval_samples_per_second": 3.849,
      "eval_steps_per_second": 0.242,
      "step": 380
    },
    {
      "epoch": 9.08,
      "step": 380,
      "total_flos": 7.475141472240992e+18,
      "train_loss": 0.4567895299509952,
      "train_runtime": 3981.2865,
      "train_samples_per_second": 1.527,
      "train_steps_per_second": 0.095
    },
    {
      "epoch": 9.08,
      "eval_accuracy": 0.8026666666666666,
      "eval_loss": 0.5030941367149353,
      "eval_runtime": 189.9731,
      "eval_samples_per_second": 3.948,
      "eval_steps_per_second": 0.247,
      "step": 380
    },
    {
      "epoch": 9.08,
      "eval_accuracy": 0.8026666666666666,
      "eval_loss": 0.5030941367149353,
      "eval_runtime": 191.8522,
      "eval_samples_per_second": 3.909,
      "eval_steps_per_second": 0.245,
      "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
}