{
  "best_metric": 0.7912087912087912,
  "best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-11/checkpoint-384",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 480,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 1.2641795873641968,
      "learning_rate": 4.277342370667828e-06,
      "loss": 0.702,
      "step": 5
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1789261102676392,
      "learning_rate": 8.554684741335655e-06,
      "loss": 0.6864,
      "step": 10
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.3848576545715332,
      "learning_rate": 1.2832027112003484e-05,
      "loss": 0.6855,
      "step": 15
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.953545093536377,
      "learning_rate": 1.710936948267131e-05,
      "loss": 0.6668,
      "step": 20
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.9704298377037048,
      "learning_rate": 2.138671185333914e-05,
      "loss": 0.6426,
      "step": 25
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.7949383854866028,
      "learning_rate": 2.5664054224006968e-05,
      "loss": 0.6293,
      "step": 30
    },
    {
      "epoch": 0.73,
      "grad_norm": 2.390880823135376,
      "learning_rate": 2.994139659467479e-05,
      "loss": 0.5631,
      "step": 35
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.7147374153137207,
      "learning_rate": 3.421873896534262e-05,
      "loss": 0.6562,
      "step": 40
    },
    {
      "epoch": 0.94,
      "grad_norm": 3.123836040496826,
      "learning_rate": 3.849608133601045e-05,
      "loss": 0.6243,
      "step": 45
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.7374954223632812,
      "eval_runtime": 1.3701,
      "eval_samples_per_second": 46.713,
      "eval_steps_per_second": 5.839,
      "step": 48
    },
    {
      "epoch": 1.04,
      "grad_norm": 4.445352077484131,
      "learning_rate": 4.0872382653048134e-05,
      "loss": 0.6965,
      "step": 50
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.8689994215965271,
      "learning_rate": 4.03971223896406e-05,
      "loss": 0.6945,
      "step": 55
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.744273066520691,
      "learning_rate": 3.992186212623306e-05,
      "loss": 0.4097,
      "step": 60
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.6568699479103088,
      "learning_rate": 3.944660186282552e-05,
      "loss": 0.5621,
      "step": 65
    },
    {
      "epoch": 1.46,
      "grad_norm": 1.516032099723816,
      "learning_rate": 3.8971341599417986e-05,
      "loss": 0.4826,
      "step": 70
    },
    {
      "epoch": 1.56,
      "grad_norm": Infinity,
      "learning_rate": 3.8591133388691955e-05,
      "loss": 0.7666,
      "step": 75
    },
    {
      "epoch": 1.67,
      "grad_norm": 1.788261890411377,
      "learning_rate": 3.811587312528442e-05,
      "loss": 0.6187,
      "step": 80
    },
    {
      "epoch": 1.77,
      "grad_norm": 1.7383731603622437,
      "learning_rate": 3.764061286187688e-05,
      "loss": 0.5974,
      "step": 85
    },
    {
      "epoch": 1.88,
      "grad_norm": 1.9014606475830078,
      "learning_rate": 3.7165352598469344e-05,
      "loss": 0.5979,
      "step": 90
    },
    {
      "epoch": 1.98,
      "grad_norm": 2.1836445331573486,
      "learning_rate": 3.669009233506181e-05,
      "loss": 0.6104,
      "step": 95
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.6798496246337891,
      "eval_runtime": 1.3616,
      "eval_samples_per_second": 47.003,
      "eval_steps_per_second": 5.875,
      "step": 96
    },
    {
      "epoch": 2.08,
      "grad_norm": 1.0497145652770996,
      "learning_rate": 3.6214832071654276e-05,
      "loss": 0.5777,
      "step": 100
    },
    {
      "epoch": 2.19,
      "grad_norm": 1.1734980344772339,
      "learning_rate": 3.573957180824674e-05,
      "loss": 0.4793,
      "step": 105
    },
    {
      "epoch": 2.29,
      "grad_norm": 1.6985560655593872,
      "learning_rate": 3.52643115448392e-05,
      "loss": 0.5708,
      "step": 110
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.110007882118225,
      "learning_rate": 3.4789051281431665e-05,
      "loss": 0.5446,
      "step": 115
    },
    {
      "epoch": 2.5,
      "grad_norm": Infinity,
      "learning_rate": 3.4408843070705634e-05,
      "loss": 0.5224,
      "step": 120
    },
    {
      "epoch": 2.6,
      "grad_norm": 4.383241653442383,
      "learning_rate": 3.39335828072981e-05,
      "loss": 0.4492,
      "step": 125
    },
    {
      "epoch": 2.71,
      "grad_norm": 20.106430053710938,
      "learning_rate": 3.355337459657207e-05,
      "loss": 0.6228,
      "step": 130
    },
    {
      "epoch": 2.81,
      "grad_norm": 3.188138008117676,
      "learning_rate": 3.3078114333164536e-05,
      "loss": 0.3671,
      "step": 135
    },
    {
      "epoch": 2.92,
      "grad_norm": 3.840233087539673,
      "learning_rate": 3.2602854069757e-05,
      "loss": 0.3217,
      "step": 140
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.7474747474747475,
      "eval_loss": 0.8114051818847656,
      "eval_runtime": 1.4005,
      "eval_samples_per_second": 45.699,
      "eval_steps_per_second": 5.712,
      "step": 144
    },
    {
      "epoch": 3.02,
      "grad_norm": 2.789161205291748,
      "learning_rate": 3.212759380634946e-05,
      "loss": 0.4985,
      "step": 145
    },
    {
      "epoch": 3.12,
      "grad_norm": 20.845867156982422,
      "learning_rate": 3.1652333542941924e-05,
      "loss": 0.3366,
      "step": 150
    },
    {
      "epoch": 3.23,
      "grad_norm": 3.9109976291656494,
      "learning_rate": 3.117707327953439e-05,
      "loss": 0.2834,
      "step": 155
    },
    {
      "epoch": 3.33,
      "grad_norm": 5.4618916511535645,
      "learning_rate": 3.070181301612686e-05,
      "loss": 0.4844,
      "step": 160
    },
    {
      "epoch": 3.44,
      "grad_norm": 4.305176258087158,
      "learning_rate": 3.0226552752719317e-05,
      "loss": 0.2045,
      "step": 165
    },
    {
      "epoch": 3.54,
      "grad_norm": 15.64925765991211,
      "learning_rate": 2.9751292489311783e-05,
      "loss": 0.2373,
      "step": 170
    },
    {
      "epoch": 3.65,
      "grad_norm": 10.34076976776123,
      "learning_rate": 2.9276032225904242e-05,
      "loss": 0.4372,
      "step": 175
    },
    {
      "epoch": 3.75,
      "grad_norm": Infinity,
      "learning_rate": 2.8895824015178215e-05,
      "loss": 0.2174,
      "step": 180
    },
    {
      "epoch": 3.85,
      "grad_norm": 1.866976022720337,
      "learning_rate": 2.8420563751770678e-05,
      "loss": 0.2674,
      "step": 185
    },
    {
      "epoch": 3.96,
      "grad_norm": 12.544903755187988,
      "learning_rate": 2.794530348836314e-05,
      "loss": 0.3761,
      "step": 190
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.7500000000000001,
      "eval_loss": 0.9909818172454834,
      "eval_runtime": 1.3645,
      "eval_samples_per_second": 46.904,
      "eval_steps_per_second": 5.863,
      "step": 192
    },
    {
      "epoch": 4.06,
      "grad_norm": 0.7645444869995117,
      "learning_rate": 2.7470043224955607e-05,
      "loss": 0.2581,
      "step": 195
    },
    {
      "epoch": 4.17,
      "grad_norm": 3.4740447998046875,
      "learning_rate": 2.699478296154807e-05,
      "loss": 0.3123,
      "step": 200
    },
    {
      "epoch": 4.27,
      "grad_norm": 6.953164100646973,
      "learning_rate": 2.6519522698140533e-05,
      "loss": 0.2039,
      "step": 205
    },
    {
      "epoch": 4.38,
      "grad_norm": 7.376092433929443,
      "learning_rate": 2.6044262434732996e-05,
      "loss": 0.1341,
      "step": 210
    },
    {
      "epoch": 4.48,
      "grad_norm": 1.5489851236343384,
      "learning_rate": 2.5569002171325462e-05,
      "loss": 0.1285,
      "step": 215
    },
    {
      "epoch": 4.58,
      "grad_norm": 13.857163429260254,
      "learning_rate": 2.5093741907917925e-05,
      "loss": 0.0793,
      "step": 220
    },
    {
      "epoch": 4.69,
      "grad_norm": 2.46573543548584,
      "learning_rate": 2.4618481644510388e-05,
      "loss": 0.1254,
      "step": 225
    },
    {
      "epoch": 4.79,
      "grad_norm": 0.2868492305278778,
      "learning_rate": 2.4143221381102847e-05,
      "loss": 0.205,
      "step": 230
    },
    {
      "epoch": 4.9,
      "grad_norm": 1.8789399862289429,
      "learning_rate": 2.376301317037682e-05,
      "loss": 0.1137,
      "step": 235
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7913978099822998,
      "learning_rate": 2.3287752906969286e-05,
      "loss": 0.1204,
      "step": 240
    },
    {
      "epoch": 5.0,
      "eval_f1": 0.7586206896551725,
      "eval_loss": 1.0789520740509033,
      "eval_runtime": 1.3527,
      "eval_samples_per_second": 47.312,
      "eval_steps_per_second": 5.914,
      "step": 240
    },
    {
      "epoch": 5.1,
      "grad_norm": 0.31450164318084717,
      "learning_rate": 2.281249264356175e-05,
      "loss": 0.0266,
      "step": 245
    },
    {
      "epoch": 5.21,
      "grad_norm": 1.4393788576126099,
      "learning_rate": 2.2337232380154212e-05,
      "loss": 0.0256,
      "step": 250
    },
    {
      "epoch": 5.31,
      "grad_norm": 1.2491079568862915,
      "learning_rate": 2.1861972116746675e-05,
      "loss": 0.0326,
      "step": 255
    },
    {
      "epoch": 5.42,
      "grad_norm": 8.679621696472168,
      "learning_rate": 2.138671185333914e-05,
      "loss": 0.0274,
      "step": 260
    },
    {
      "epoch": 5.52,
      "grad_norm": 0.2720549404621124,
      "learning_rate": 2.0911451589931604e-05,
      "loss": 0.0474,
      "step": 265
    },
    {
      "epoch": 5.62,
      "grad_norm": 0.5277475714683533,
      "learning_rate": 2.0436191326524067e-05,
      "loss": 0.0339,
      "step": 270
    },
    {
      "epoch": 5.73,
      "grad_norm": 19.154306411743164,
      "learning_rate": 1.996093106311653e-05,
      "loss": 0.0294,
      "step": 275
    },
    {
      "epoch": 5.83,
      "grad_norm": 0.20597286522388458,
      "learning_rate": 1.9485670799708993e-05,
      "loss": 0.2482,
      "step": 280
    },
    {
      "epoch": 5.94,
      "grad_norm": 0.9011418223381042,
      "learning_rate": 1.9010410536301456e-05,
      "loss": 0.0123,
      "step": 285
    },
    {
      "epoch": 6.0,
      "eval_f1": 0.7741935483870968,
      "eval_loss": 1.4787760972976685,
      "eval_runtime": 1.3653,
      "eval_samples_per_second": 46.875,
      "eval_steps_per_second": 5.859,
      "step": 288
    },
    {
      "epoch": 6.04,
      "grad_norm": 0.22904255986213684,
      "learning_rate": 1.853515027289392e-05,
      "loss": 0.224,
      "step": 290
    },
    {
      "epoch": 6.15,
      "grad_norm": 0.2534620463848114,
      "learning_rate": 1.8059890009486385e-05,
      "loss": 0.0117,
      "step": 295
    },
    {
      "epoch": 6.25,
      "grad_norm": 0.1455022692680359,
      "learning_rate": 1.7584629746078848e-05,
      "loss": 0.012,
      "step": 300
    },
    {
      "epoch": 6.35,
      "grad_norm": 7.899118423461914,
      "learning_rate": 1.710936948267131e-05,
      "loss": 0.0205,
      "step": 305
    },
    {
      "epoch": 6.46,
      "grad_norm": 0.15333446860313416,
      "learning_rate": 1.6634109219263774e-05,
      "loss": 0.0124,
      "step": 310
    },
    {
      "epoch": 6.56,
      "grad_norm": 2.1998233795166016,
      "learning_rate": 1.615884895585624e-05,
      "loss": 0.0127,
      "step": 315
    },
    {
      "epoch": 6.67,
      "grad_norm": 4.678240776062012,
      "learning_rate": 1.56835886924487e-05,
      "loss": 0.0188,
      "step": 320
    },
    {
      "epoch": 6.77,
      "grad_norm": 6.431846618652344,
      "learning_rate": 1.5208328429041164e-05,
      "loss": 0.0178,
      "step": 325
    },
    {
      "epoch": 6.88,
      "grad_norm": 3.7818799018859863,
      "learning_rate": 1.4733068165633629e-05,
      "loss": 0.0091,
      "step": 330
    },
    {
      "epoch": 6.98,
      "grad_norm": 0.11249573528766632,
      "learning_rate": 1.4257807902226092e-05,
      "loss": 0.2635,
      "step": 335
    },
    {
      "epoch": 7.0,
      "eval_f1": 0.7500000000000001,
      "eval_loss": 1.9278812408447266,
      "eval_runtime": 1.3857,
      "eval_samples_per_second": 46.187,
      "eval_steps_per_second": 5.773,
      "step": 336
    },
    {
      "epoch": 7.08,
      "grad_norm": Infinity,
      "learning_rate": 1.3877599691500063e-05,
      "loss": 0.2288,
      "step": 340
    },
    {
      "epoch": 7.19,
      "grad_norm": 0.09949830174446106,
      "learning_rate": 1.3402339428092527e-05,
      "loss": 0.0357,
      "step": 345
    },
    {
      "epoch": 7.29,
      "grad_norm": 0.29120293259620667,
      "learning_rate": 1.292707916468499e-05,
      "loss": 0.0071,
      "step": 350
    },
    {
      "epoch": 7.4,
      "grad_norm": 0.3897027373313904,
      "learning_rate": 1.2451818901277455e-05,
      "loss": 0.0071,
      "step": 355
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.10337533801794052,
      "learning_rate": 1.1976558637869918e-05,
      "loss": 0.0076,
      "step": 360
    },
    {
      "epoch": 7.6,
      "grad_norm": 0.14363917708396912,
      "learning_rate": 1.1501298374462382e-05,
      "loss": 0.0064,
      "step": 365
    },
    {
      "epoch": 7.71,
      "grad_norm": 0.2638760805130005,
      "learning_rate": 1.1026038111054845e-05,
      "loss": 0.0715,
      "step": 370
    },
    {
      "epoch": 7.81,
      "grad_norm": 0.08668874204158783,
      "learning_rate": 1.0550777847647308e-05,
      "loss": 0.2678,
      "step": 375
    },
    {
      "epoch": 7.92,
      "grad_norm": 0.11121731251478195,
      "learning_rate": 1.0075517584239773e-05,
      "loss": 0.0059,
      "step": 380
    },
    {
      "epoch": 8.0,
      "eval_f1": 0.7912087912087912,
      "eval_loss": 1.495563268661499,
      "eval_runtime": 1.4139,
      "eval_samples_per_second": 45.264,
      "eval_steps_per_second": 5.658,
      "step": 384
    },
    {
      "epoch": 8.02,
      "grad_norm": 0.1238911896944046,
      "learning_rate": 9.600257320832236e-06,
      "loss": 0.0065,
      "step": 385
    },
    {
      "epoch": 8.12,
      "grad_norm": 0.09688282012939453,
      "learning_rate": 9.124997057424699e-06,
      "loss": 0.0054,
      "step": 390
    },
    {
      "epoch": 8.23,
      "grad_norm": 0.07482036203145981,
      "learning_rate": 8.649736794017163e-06,
      "loss": 0.0078,
      "step": 395
    },
    {
      "epoch": 8.33,
      "grad_norm": 0.10461320728063583,
      "learning_rate": 8.174476530609626e-06,
      "loss": 0.2455,
      "step": 400
    },
    {
      "epoch": 8.44,
      "grad_norm": 0.12439440935850143,
      "learning_rate": 7.699216267202089e-06,
      "loss": 0.0053,
      "step": 405
    },
    {
      "epoch": 8.54,
      "grad_norm": 0.12789662182331085,
      "learning_rate": 7.223956003794554e-06,
      "loss": 0.0054,
      "step": 410
    },
    {
      "epoch": 8.65,
      "grad_norm": 0.07380508631467819,
      "learning_rate": 6.7486957403870175e-06,
      "loss": 0.006,
      "step": 415
    },
    {
      "epoch": 8.75,
      "grad_norm": 0.08458781242370605,
      "learning_rate": 6.273435476979481e-06,
      "loss": 0.0056,
      "step": 420
    },
    {
      "epoch": 8.85,
      "grad_norm": 0.09543807804584503,
      "learning_rate": 5.798175213571944e-06,
      "loss": 0.0063,
      "step": 425
    },
    {
      "epoch": 8.96,
      "grad_norm": 0.10101006925106049,
      "learning_rate": 5.322914950164408e-06,
      "loss": 0.0064,
      "step": 430
    },
    {
      "epoch": 9.0,
      "eval_f1": 0.7586206896551725,
      "eval_loss": 1.48129403591156,
      "eval_runtime": 1.4314,
      "eval_samples_per_second": 44.71,
      "eval_steps_per_second": 5.589,
      "step": 432
    },
    {
      "epoch": 9.06,
      "grad_norm": 0.10252533107995987,
      "learning_rate": 4.847654686756872e-06,
      "loss": 0.0053,
      "step": 435
    },
    {
      "epoch": 9.17,
      "grad_norm": 0.08117670565843582,
      "learning_rate": 4.372394423349335e-06,
      "loss": 0.0042,
      "step": 440
    },
    {
      "epoch": 9.27,
      "grad_norm": 0.9447091817855835,
      "learning_rate": 3.897134159941798e-06,
      "loss": 0.0052,
      "step": 445
    },
    {
      "epoch": 9.38,
      "grad_norm": 1.359684944152832,
      "learning_rate": 3.421873896534262e-06,
      "loss": 0.0058,
      "step": 450
    },
    {
      "epoch": 9.48,
      "grad_norm": 0.09509690850973129,
      "learning_rate": 2.946613633126726e-06,
      "loss": 0.0055,
      "step": 455
    },
    {
      "epoch": 9.58,
      "grad_norm": 0.09477395564317703,
      "learning_rate": 2.4713533697191893e-06,
      "loss": 0.0059,
      "step": 460
    },
    {
      "epoch": 9.69,
      "grad_norm": 0.12153127789497375,
      "learning_rate": 1.996093106311653e-06,
      "loss": 0.0046,
      "step": 465
    },
    {
      "epoch": 9.79,
      "grad_norm": 0.12337913364171982,
      "learning_rate": 1.5208328429041164e-06,
      "loss": 0.0045,
      "step": 470
    },
    {
      "epoch": 9.9,
      "grad_norm": 0.0738518089056015,
      "learning_rate": 1.04557257949658e-06,
      "loss": 0.07,
      "step": 475
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.11413593590259552,
      "learning_rate": 5.703123160890437e-07,
      "loss": 0.0049,
      "step": 480
    },
    {
      "epoch": 10.0,
      "eval_f1": 0.7586206896551725,
      "eval_loss": 1.53921377658844,
      "eval_runtime": 1.3572,
      "eval_samples_per_second": 47.156,
      "eval_steps_per_second": 5.894,
      "step": 480
    }
  ],
  "logging_steps": 5,
  "max_steps": 480,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 7411132489412208.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.1062486758411146e-05,
    "per_device_train_batch_size": 4
  }
}