{
  "best_metric": 1.4254008531570435,
  "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/bert-base-multilingual-cased-finetuned-yiddish-experiment-3/checkpoint-2700",
  "epoch": 8.037825059101655,
  "eval_steps": 100,
  "global_step": 3400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2364066193853428,
      "grad_norm": 28.178190231323242,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 11.143,
      "step": 100
    },
    {
      "epoch": 0.2364066193853428,
      "eval_loss": 7.659108638763428,
      "eval_runtime": 0.809,
      "eval_samples_per_second": 260.829,
      "eval_steps_per_second": 65.516,
      "step": 100
    },
    {
      "epoch": 0.4728132387706856,
      "grad_norm": 15.27036190032959,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 4.1737,
      "step": 200
    },
    {
      "epoch": 0.4728132387706856,
      "eval_loss": 2.2642054557800293,
      "eval_runtime": 0.8681,
      "eval_samples_per_second": 243.069,
      "eval_steps_per_second": 61.055,
      "step": 200
    },
    {
      "epoch": 0.7092198581560284,
      "grad_norm": 13.071714401245117,
      "learning_rate": 5e-06,
      "loss": 2.0579,
      "step": 300
    },
    {
      "epoch": 0.7092198581560284,
      "eval_loss": 1.7709782123565674,
      "eval_runtime": 0.8603,
      "eval_samples_per_second": 245.25,
      "eval_steps_per_second": 61.603,
      "step": 300
    },
    {
      "epoch": 0.9456264775413712,
      "grad_norm": 8.75770092010498,
      "learning_rate": 4.8727735368956745e-06,
      "loss": 1.6963,
      "step": 400
    },
    {
      "epoch": 0.9456264775413712,
      "eval_loss": 1.671216607093811,
      "eval_runtime": 0.9312,
      "eval_samples_per_second": 226.587,
      "eval_steps_per_second": 56.915,
      "step": 400
    },
    {
      "epoch": 1.1820330969267139,
      "grad_norm": 11.299208641052246,
      "learning_rate": 4.745547073791349e-06,
      "loss": 1.5705,
      "step": 500
    },
    {
      "epoch": 1.1820330969267139,
      "eval_loss": 1.6379029750823975,
      "eval_runtime": 0.872,
      "eval_samples_per_second": 241.979,
      "eval_steps_per_second": 60.782,
      "step": 500
    },
    {
      "epoch": 1.4184397163120568,
      "grad_norm": 7.146368980407715,
      "learning_rate": 4.618320610687023e-06,
      "loss": 1.5353,
      "step": 600
    },
    {
      "epoch": 1.4184397163120568,
      "eval_loss": 1.600274682044983,
      "eval_runtime": 0.9755,
      "eval_samples_per_second": 216.307,
      "eval_steps_per_second": 54.333,
      "step": 600
    },
    {
      "epoch": 1.6548463356973995,
      "grad_norm": 7.896175861358643,
      "learning_rate": 4.491094147582698e-06,
      "loss": 1.5213,
      "step": 700
    },
    {
      "epoch": 1.6548463356973995,
      "eval_loss": 1.52731454372406,
      "eval_runtime": 0.9375,
      "eval_samples_per_second": 225.075,
      "eval_steps_per_second": 56.535,
      "step": 700
    },
    {
      "epoch": 1.8912529550827424,
      "grad_norm": 10.965773582458496,
      "learning_rate": 4.363867684478372e-06,
      "loss": 1.4387,
      "step": 800
    },
    {
      "epoch": 1.8912529550827424,
      "eval_loss": 1.5414769649505615,
      "eval_runtime": 0.8682,
      "eval_samples_per_second": 243.03,
      "eval_steps_per_second": 61.045,
      "step": 800
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 10.384049415588379,
      "learning_rate": 4.236641221374046e-06,
      "loss": 1.3973,
      "step": 900
    },
    {
      "epoch": 2.127659574468085,
      "eval_loss": 1.5529794692993164,
      "eval_runtime": 0.9033,
      "eval_samples_per_second": 233.6,
      "eval_steps_per_second": 58.677,
      "step": 900
    },
    {
      "epoch": 2.3640661938534278,
      "grad_norm": 5.56968879699707,
      "learning_rate": 4.10941475826972e-06,
      "loss": 1.4266,
      "step": 1000
    },
    {
      "epoch": 2.3640661938534278,
      "eval_loss": 1.5328062772750854,
      "eval_runtime": 0.961,
      "eval_samples_per_second": 219.562,
      "eval_steps_per_second": 55.151,
      "step": 1000
    },
    {
      "epoch": 2.6004728132387704,
      "grad_norm": 10.164349555969238,
      "learning_rate": 3.982188295165394e-06,
      "loss": 1.3365,
      "step": 1100
    },
    {
      "epoch": 2.6004728132387704,
      "eval_loss": 1.5154240131378174,
      "eval_runtime": 0.8705,
      "eval_samples_per_second": 242.391,
      "eval_steps_per_second": 60.885,
      "step": 1100
    },
    {
      "epoch": 2.8368794326241136,
      "grad_norm": 9.04079532623291,
      "learning_rate": 3.8549618320610685e-06,
      "loss": 1.4423,
      "step": 1200
    },
    {
      "epoch": 2.8368794326241136,
      "eval_loss": 1.4661674499511719,
      "eval_runtime": 0.8755,
      "eval_samples_per_second": 240.994,
      "eval_steps_per_second": 60.534,
      "step": 1200
    },
    {
      "epoch": 3.0732860520094563,
      "grad_norm": 6.514869213104248,
      "learning_rate": 3.727735368956743e-06,
      "loss": 1.3948,
      "step": 1300
    },
    {
      "epoch": 3.0732860520094563,
      "eval_loss": 1.5041050910949707,
      "eval_runtime": 0.9417,
      "eval_samples_per_second": 224.068,
      "eval_steps_per_second": 56.283,
      "step": 1300
    },
    {
      "epoch": 3.309692671394799,
      "grad_norm": 10.943750381469727,
      "learning_rate": 3.600508905852418e-06,
      "loss": 1.3244,
      "step": 1400
    },
    {
      "epoch": 3.309692671394799,
      "eval_loss": 1.4529520273208618,
      "eval_runtime": 0.9102,
      "eval_samples_per_second": 231.812,
      "eval_steps_per_second": 58.228,
      "step": 1400
    },
    {
      "epoch": 3.546099290780142,
      "grad_norm": 10.225111961364746,
      "learning_rate": 3.473282442748092e-06,
      "loss": 1.3645,
      "step": 1500
    },
    {
      "epoch": 3.546099290780142,
      "eval_loss": 1.465559959411621,
      "eval_runtime": 0.9529,
      "eval_samples_per_second": 221.425,
      "eval_steps_per_second": 55.619,
      "step": 1500
    },
    {
      "epoch": 3.7825059101654848,
      "grad_norm": 7.151226043701172,
      "learning_rate": 3.3460559796437663e-06,
      "loss": 1.329,
      "step": 1600
    },
    {
      "epoch": 3.7825059101654848,
      "eval_loss": 1.4541741609573364,
      "eval_runtime": 0.8876,
      "eval_samples_per_second": 237.71,
      "eval_steps_per_second": 59.709,
      "step": 1600
    },
    {
      "epoch": 4.0189125295508275,
      "grad_norm": 8.583314895629883,
      "learning_rate": 3.2188295165394405e-06,
      "loss": 1.3326,
      "step": 1700
    },
    {
      "epoch": 4.0189125295508275,
      "eval_loss": 1.5292662382125854,
      "eval_runtime": 0.9651,
      "eval_samples_per_second": 218.633,
      "eval_steps_per_second": 54.917,
      "step": 1700
    },
    {
      "epoch": 4.25531914893617,
      "grad_norm": 9.412424087524414,
      "learning_rate": 3.091603053435115e-06,
      "loss": 1.2768,
      "step": 1800
    },
    {
      "epoch": 4.25531914893617,
      "eval_loss": 1.4574536085128784,
      "eval_runtime": 0.9385,
      "eval_samples_per_second": 224.829,
      "eval_steps_per_second": 56.474,
      "step": 1800
    },
    {
      "epoch": 4.491725768321513,
      "grad_norm": 12.185762405395508,
      "learning_rate": 2.964376590330789e-06,
      "loss": 1.3125,
      "step": 1900
    },
    {
      "epoch": 4.491725768321513,
      "eval_loss": 1.4637694358825684,
      "eval_runtime": 0.9372,
      "eval_samples_per_second": 225.131,
      "eval_steps_per_second": 56.549,
      "step": 1900
    },
    {
      "epoch": 4.7281323877068555,
      "grad_norm": 6.585460186004639,
      "learning_rate": 2.8371501272264633e-06,
      "loss": 1.2925,
      "step": 2000
    },
    {
      "epoch": 4.7281323877068555,
      "eval_loss": 1.4866981506347656,
      "eval_runtime": 0.9053,
      "eval_samples_per_second": 233.082,
      "eval_steps_per_second": 58.547,
      "step": 2000
    },
    {
      "epoch": 4.964539007092198,
      "grad_norm": 15.212538719177246,
      "learning_rate": 2.709923664122138e-06,
      "loss": 1.281,
      "step": 2100
    },
    {
      "epoch": 4.964539007092198,
      "eval_loss": 1.4827325344085693,
      "eval_runtime": 0.886,
      "eval_samples_per_second": 238.156,
      "eval_steps_per_second": 59.821,
      "step": 2100
    },
    {
      "epoch": 5.200945626477542,
      "grad_norm": 7.062072277069092,
      "learning_rate": 2.582697201017812e-06,
      "loss": 1.2966,
      "step": 2200
    },
    {
      "epoch": 5.200945626477542,
      "eval_loss": 1.435917854309082,
      "eval_runtime": 0.9144,
      "eval_samples_per_second": 230.752,
      "eval_steps_per_second": 57.961,
      "step": 2200
    },
    {
      "epoch": 5.4373522458628845,
      "grad_norm": 12.471199989318848,
      "learning_rate": 2.455470737913486e-06,
      "loss": 1.28,
      "step": 2300
    },
    {
      "epoch": 5.4373522458628845,
      "eval_loss": 1.4760586023330688,
      "eval_runtime": 0.8694,
      "eval_samples_per_second": 242.687,
      "eval_steps_per_second": 60.959,
      "step": 2300
    },
    {
      "epoch": 5.673758865248227,
      "grad_norm": 13.391254425048828,
      "learning_rate": 2.3282442748091603e-06,
      "loss": 1.2436,
      "step": 2400
    },
    {
      "epoch": 5.673758865248227,
      "eval_loss": 1.5006126165390015,
      "eval_runtime": 0.8661,
      "eval_samples_per_second": 243.634,
      "eval_steps_per_second": 61.197,
      "step": 2400
    },
    {
      "epoch": 5.91016548463357,
      "grad_norm": 7.622119903564453,
      "learning_rate": 2.201017811704835e-06,
      "loss": 1.2787,
      "step": 2500
    },
    {
      "epoch": 5.91016548463357,
      "eval_loss": 1.4511311054229736,
      "eval_runtime": 0.8806,
      "eval_samples_per_second": 239.596,
      "eval_steps_per_second": 60.183,
      "step": 2500
    },
    {
      "epoch": 6.1465721040189125,
      "grad_norm": 9.2753324508667,
      "learning_rate": 2.073791348600509e-06,
      "loss": 1.2344,
      "step": 2600
    },
    {
      "epoch": 6.1465721040189125,
      "eval_loss": 1.442953109741211,
      "eval_runtime": 0.9954,
      "eval_samples_per_second": 211.967,
      "eval_steps_per_second": 53.243,
      "step": 2600
    },
    {
      "epoch": 6.382978723404255,
      "grad_norm": 9.532594680786133,
      "learning_rate": 1.946564885496183e-06,
      "loss": 1.199,
      "step": 2700
    },
    {
      "epoch": 6.382978723404255,
      "eval_loss": 1.4254008531570435,
      "eval_runtime": 0.926,
      "eval_samples_per_second": 227.859,
      "eval_steps_per_second": 57.235,
      "step": 2700
    },
    {
      "epoch": 6.619385342789598,
      "grad_norm": 23.084375381469727,
      "learning_rate": 1.8193384223918575e-06,
      "loss": 1.2899,
      "step": 2800
    },
    {
      "epoch": 6.619385342789598,
      "eval_loss": 1.4339009523391724,
      "eval_runtime": 0.8754,
      "eval_samples_per_second": 241.035,
      "eval_steps_per_second": 60.544,
      "step": 2800
    },
    {
      "epoch": 6.855791962174941,
      "grad_norm": 9.28426742553711,
      "learning_rate": 1.692111959287532e-06,
      "loss": 1.2637,
      "step": 2900
    },
    {
      "epoch": 6.855791962174941,
      "eval_loss": 1.4609365463256836,
      "eval_runtime": 0.8834,
      "eval_samples_per_second": 238.862,
      "eval_steps_per_second": 59.998,
      "step": 2900
    },
    {
      "epoch": 7.092198581560283,
      "grad_norm": 8.32325267791748,
      "learning_rate": 1.5648854961832064e-06,
      "loss": 1.2186,
      "step": 3000
    },
    {
      "epoch": 7.092198581560283,
      "eval_loss": 1.4300271272659302,
      "eval_runtime": 0.8899,
      "eval_samples_per_second": 237.108,
      "eval_steps_per_second": 59.558,
      "step": 3000
    },
    {
      "epoch": 7.328605200945627,
      "grad_norm": 7.893182277679443,
      "learning_rate": 1.4376590330788805e-06,
      "loss": 1.181,
      "step": 3100
    },
    {
      "epoch": 7.328605200945627,
      "eval_loss": 1.440673589706421,
      "eval_runtime": 0.8686,
      "eval_samples_per_second": 242.907,
      "eval_steps_per_second": 61.015,
      "step": 3100
    },
    {
      "epoch": 7.5650118203309695,
      "grad_norm": 6.581611633300781,
      "learning_rate": 1.3104325699745549e-06,
      "loss": 1.2815,
      "step": 3200
    },
    {
      "epoch": 7.5650118203309695,
      "eval_loss": 1.4471487998962402,
      "eval_runtime": 0.8765,
      "eval_samples_per_second": 240.74,
      "eval_steps_per_second": 60.47,
      "step": 3200
    },
    {
      "epoch": 7.801418439716312,
      "grad_norm": 7.022655487060547,
      "learning_rate": 1.1832061068702292e-06,
      "loss": 1.2161,
      "step": 3300
    },
    {
      "epoch": 7.801418439716312,
      "eval_loss": 1.4413220882415771,
      "eval_runtime": 0.9499,
      "eval_samples_per_second": 222.12,
      "eval_steps_per_second": 55.793,
      "step": 3300
    },
    {
      "epoch": 8.037825059101655,
      "grad_norm": 7.9755120277404785,
      "learning_rate": 1.0559796437659034e-06,
      "loss": 1.1562,
      "step": 3400
    },
    {
      "epoch": 8.037825059101655,
      "eval_loss": 1.469501256942749,
      "eval_runtime": 0.854,
      "eval_samples_per_second": 247.085,
      "eval_steps_per_second": 62.064,
      "step": 3400
    }
  ],
  "logging_steps": 100,
  "max_steps": 4230,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 447913105920000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}