{
  "best_metric": 0.15773464658169178,
  "best_model_checkpoint": "audio/train/checkpoint/hubert-base/superb_si_42/checkpoint-43240",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 43240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23126734505087881,
      "grad_norm": 1.697458267211914,
      "learning_rate": 1.1563367252543942e-05,
      "loss": 7.1124,
      "step": 1000
    },
    {
      "epoch": 0.46253469010175763,
      "grad_norm": 2.86542010307312,
      "learning_rate": 2.3126734505087884e-05,
      "loss": 6.9441,
      "step": 2000
    },
    {
      "epoch": 0.6938020351526365,
      "grad_norm": 4.842338562011719,
      "learning_rate": 3.469010175763183e-05,
      "loss": 6.5221,
      "step": 3000
    },
    {
      "epoch": 0.9250693802035153,
      "grad_norm": 5.53955602645874,
      "learning_rate": 4.625346901017577e-05,
      "loss": 6.2927,
      "step": 4000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.004924681344148319,
      "eval_loss": 6.532104969024658,
      "eval_runtime": 123.1249,
      "eval_samples_per_second": 56.073,
      "eval_steps_per_second": 3.509,
      "step": 4324
    },
    {
      "epoch": 1.1563367252543941,
      "grad_norm": 4.515321731567383,
      "learning_rate": 4.913146263747559e-05,
      "loss": 6.1013,
      "step": 5000
    },
    {
      "epoch": 1.3876040703052728,
      "grad_norm": 6.986465930938721,
      "learning_rate": 4.78466440538596e-05,
      "loss": 5.9426,
      "step": 6000
    },
    {
      "epoch": 1.6188714153561516,
      "grad_norm": 7.874293804168701,
      "learning_rate": 4.65618254702436e-05,
      "loss": 5.809,
      "step": 7000
    },
    {
      "epoch": 1.8501387604070305,
      "grad_norm": 8.206330299377441,
      "learning_rate": 4.527700688662761e-05,
      "loss": 5.6909,
      "step": 8000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.008835457705677868,
      "eval_loss": 6.0103302001953125,
      "eval_runtime": 120.1466,
      "eval_samples_per_second": 57.463,
      "eval_steps_per_second": 3.596,
      "step": 8648
    },
    {
      "epoch": 2.0814061054579094,
      "grad_norm": 9.057954788208008,
      "learning_rate": 4.399218830301162e-05,
      "loss": 5.5852,
      "step": 9000
    },
    {
      "epoch": 2.3126734505087883,
      "grad_norm": 10.034080505371094,
      "learning_rate": 4.2707369719395625e-05,
      "loss": 5.5059,
      "step": 10000
    },
    {
      "epoch": 2.543940795559667,
      "grad_norm": 9.717106819152832,
      "learning_rate": 4.142255113577963e-05,
      "loss": 5.4348,
      "step": 11000
    },
    {
      "epoch": 2.7752081406105455,
      "grad_norm": 9.622520446777344,
      "learning_rate": 4.0137732552163636e-05,
      "loss": 5.3829,
      "step": 12000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.02346465816917729,
      "eval_loss": 5.530889511108398,
      "eval_runtime": 120.1431,
      "eval_samples_per_second": 57.465,
      "eval_steps_per_second": 3.596,
      "step": 12972
    },
    {
      "epoch": 3.0064754856614244,
      "grad_norm": 10.915121078491211,
      "learning_rate": 3.885291396854764e-05,
      "loss": 5.2762,
      "step": 13000
    },
    {
      "epoch": 3.2377428307123033,
      "grad_norm": 10.905006408691406,
      "learning_rate": 3.756809538493165e-05,
      "loss": 5.196,
      "step": 14000
    },
    {
      "epoch": 3.469010175763182,
      "grad_norm": 10.589766502380371,
      "learning_rate": 3.628327680131566e-05,
      "loss": 5.1321,
      "step": 15000
    },
    {
      "epoch": 3.700277520814061,
      "grad_norm": 11.086525917053223,
      "learning_rate": 3.4998458217699664e-05,
      "loss": 5.0639,
      "step": 16000
    },
    {
      "epoch": 3.93154486586494,
      "grad_norm": 12.314041137695312,
      "learning_rate": 3.371363963408367e-05,
      "loss": 4.9995,
      "step": 17000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.03794901506373117,
      "eval_loss": 5.1893744468688965,
      "eval_runtime": 119.905,
      "eval_samples_per_second": 57.579,
      "eval_steps_per_second": 3.603,
      "step": 17296
    },
    {
      "epoch": 4.162812210915819,
      "grad_norm": 10.940951347351074,
      "learning_rate": 3.242882105046768e-05,
      "loss": 4.9387,
      "step": 18000
    },
    {
      "epoch": 4.394079555966697,
      "grad_norm": 12.118027687072754,
      "learning_rate": 3.114400246685168e-05,
      "loss": 4.8872,
      "step": 19000
    },
    {
      "epoch": 4.6253469010175765,
      "grad_norm": 13.738452911376953,
      "learning_rate": 2.9859183883235685e-05,
      "loss": 4.8266,
      "step": 20000
    },
    {
      "epoch": 4.856614246068455,
      "grad_norm": 12.399888038635254,
      "learning_rate": 2.8574365299619694e-05,
      "loss": 4.7591,
      "step": 21000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.06199304750869061,
      "eval_loss": 4.864396572113037,
      "eval_runtime": 120.1129,
      "eval_samples_per_second": 57.479,
      "eval_steps_per_second": 3.597,
      "step": 21620
    },
    {
      "epoch": 5.087881591119334,
      "grad_norm": 12.469327926635742,
      "learning_rate": 2.72895467160037e-05,
      "loss": 4.7002,
      "step": 22000
    },
    {
      "epoch": 5.319148936170213,
      "grad_norm": 14.091848373413086,
      "learning_rate": 2.6004728132387708e-05,
      "loss": 4.641,
      "step": 23000
    },
    {
      "epoch": 5.550416281221091,
      "grad_norm": 12.042238235473633,
      "learning_rate": 2.4719909548771713e-05,
      "loss": 4.5869,
      "step": 24000
    },
    {
      "epoch": 5.78168362627197,
      "grad_norm": 13.945825576782227,
      "learning_rate": 2.343509096515572e-05,
      "loss": 4.5243,
      "step": 25000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.08589223638470452,
      "eval_loss": 4.604219436645508,
      "eval_runtime": 119.7064,
      "eval_samples_per_second": 57.674,
      "eval_steps_per_second": 3.609,
      "step": 25944
    },
    {
      "epoch": 6.012950971322849,
      "grad_norm": 14.026973724365234,
      "learning_rate": 2.2150272381539727e-05,
      "loss": 4.4896,
      "step": 26000
    },
    {
      "epoch": 6.244218316373728,
      "grad_norm": 15.273303985595703,
      "learning_rate": 2.0865453797923736e-05,
      "loss": 4.4312,
      "step": 27000
    },
    {
      "epoch": 6.475485661424607,
      "grad_norm": 13.617254257202148,
      "learning_rate": 1.958063521430774e-05,
      "loss": 4.3541,
      "step": 28000
    },
    {
      "epoch": 6.706753006475486,
      "grad_norm": 14.490744590759277,
      "learning_rate": 1.8295816630691746e-05,
      "loss": 4.3084,
      "step": 29000
    },
    {
      "epoch": 6.938020351526364,
      "grad_norm": 16.995948791503906,
      "learning_rate": 1.7010998047075755e-05,
      "loss": 4.2486,
      "step": 30000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.11732329084588644,
      "eval_loss": 4.349672317504883,
      "eval_runtime": 119.7126,
      "eval_samples_per_second": 57.671,
      "eval_steps_per_second": 3.609,
      "step": 30268
    },
    {
      "epoch": 7.169287696577244,
      "grad_norm": 14.805612564086914,
      "learning_rate": 1.572617946345976e-05,
      "loss": 4.1788,
      "step": 31000
    },
    {
      "epoch": 7.400555041628122,
      "grad_norm": 15.498200416564941,
      "learning_rate": 1.4441360879843766e-05,
      "loss": 4.1536,
      "step": 32000
    },
    {
      "epoch": 7.631822386679001,
      "grad_norm": 14.68932819366455,
      "learning_rate": 1.3156542296227773e-05,
      "loss": 4.1161,
      "step": 33000
    },
    {
      "epoch": 7.86308973172988,
      "grad_norm": 14.384370803833008,
      "learning_rate": 1.187172371261178e-05,
      "loss": 4.0813,
      "step": 34000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.14049826187717265,
      "eval_loss": 4.121533393859863,
      "eval_runtime": 121.082,
      "eval_samples_per_second": 57.019,
      "eval_steps_per_second": 3.568,
      "step": 34592
    },
    {
      "epoch": 8.094357076780758,
      "grad_norm": 15.307478904724121,
      "learning_rate": 1.0586905128995787e-05,
      "loss": 4.0266,
      "step": 35000
    },
    {
      "epoch": 8.325624421831638,
      "grad_norm": 11.981130599975586,
      "learning_rate": 9.302086545379794e-06,
      "loss": 3.9985,
      "step": 36000
    },
    {
      "epoch": 8.556891766882517,
      "grad_norm": 15.051200866699219,
      "learning_rate": 8.017267961763799e-06,
      "loss": 3.9549,
      "step": 37000
    },
    {
      "epoch": 8.788159111933394,
      "grad_norm": 16.70930290222168,
      "learning_rate": 6.732449378147807e-06,
      "loss": 3.9317,
      "step": 38000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.1507821552723059,
      "eval_loss": 4.043083190917969,
      "eval_runtime": 120.5834,
      "eval_samples_per_second": 57.255,
      "eval_steps_per_second": 3.583,
      "step": 38916
    },
    {
      "epoch": 9.019426456984274,
      "grad_norm": 15.108479499816895,
      "learning_rate": 5.447630794531813e-06,
      "loss": 3.9349,
      "step": 39000
    },
    {
      "epoch": 9.250693802035153,
      "grad_norm": 16.258913040161133,
      "learning_rate": 4.162812210915819e-06,
      "loss": 3.8783,
      "step": 40000
    },
    {
      "epoch": 9.481961147086032,
      "grad_norm": 15.729056358337402,
      "learning_rate": 2.877993627299825e-06,
      "loss": 3.8587,
      "step": 41000
    },
    {
      "epoch": 9.71322849213691,
      "grad_norm": 15.907846450805664,
      "learning_rate": 1.5931750436838318e-06,
      "loss": 3.8851,
      "step": 42000
    },
    {
      "epoch": 9.94449583718779,
      "grad_norm": 12.73677921295166,
      "learning_rate": 3.0835646006783846e-07,
      "loss": 3.8568,
      "step": 43000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.15773464658169178,
      "eval_loss": 3.998060941696167,
      "eval_runtime": 121.002,
      "eval_samples_per_second": 57.057,
      "eval_steps_per_second": 3.57,
      "step": 43240
    },
    {
      "epoch": 10.0,
      "step": 43240,
      "total_flos": 1.260392330300448e+19,
      "train_loss": 4.86731394327536,
      "train_runtime": 3865.9889,
      "train_samples_per_second": 357.893,
      "train_steps_per_second": 11.185
    }
  ],
  "logging_steps": 1000,
  "max_steps": 43240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.260392330300448e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}