{
  "best_metric": 0.8486739469578783,
  "best_model_checkpoint": "./distilbert\\checkpoint-705",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 705,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014184397163120567,
      "grad_norm": 2.5408613681793213,
      "learning_rate": 2.8328611898017e-07,
      "loss": 0.6936,
      "step": 10
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 1.485784649848938,
      "learning_rate": 5.6657223796034e-07,
      "loss": 0.6961,
      "step": 20
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 1.905301570892334,
      "learning_rate": 8.4985835694051e-07,
      "loss": 0.6853,
      "step": 30
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 1.9148372411727905,
      "learning_rate": 1.13314447592068e-06,
      "loss": 0.7021,
      "step": 40
    },
    {
      "epoch": 0.07092198581560284,
      "grad_norm": 2.8322083950042725,
      "learning_rate": 1.41643059490085e-06,
      "loss": 0.6903,
      "step": 50
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 1.4340893030166626,
      "learning_rate": 1.69971671388102e-06,
      "loss": 0.6802,
      "step": 60
    },
    {
      "epoch": 0.09929078014184398,
      "grad_norm": 1.966640591621399,
      "learning_rate": 1.98300283286119e-06,
      "loss": 0.6819,
      "step": 70
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 1.7727477550506592,
      "learning_rate": 2.26628895184136e-06,
      "loss": 0.6706,
      "step": 80
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 1.8015425205230713,
      "learning_rate": 2.54957507082153e-06,
      "loss": 0.6656,
      "step": 90
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 1.843285322189331,
      "learning_rate": 2.8328611898017e-06,
      "loss": 0.6747,
      "step": 100
    },
    {
      "epoch": 0.15602836879432624,
      "grad_norm": 2.8909919261932373,
      "learning_rate": 3.11614730878187e-06,
      "loss": 0.6481,
      "step": 110
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 2.1688148975372314,
      "learning_rate": 3.39943342776204e-06,
      "loss": 0.649,
      "step": 120
    },
    {
      "epoch": 0.18439716312056736,
      "grad_norm": 2.198486089706421,
      "learning_rate": 3.68271954674221e-06,
      "loss": 0.6352,
      "step": 130
    },
    {
      "epoch": 0.19858156028368795,
      "grad_norm": 2.361542224884033,
      "learning_rate": 3.96600566572238e-06,
      "loss": 0.6039,
      "step": 140
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 2.5842535495758057,
      "learning_rate": 4.24929178470255e-06,
      "loss": 0.6209,
      "step": 150
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 2.633939743041992,
      "learning_rate": 4.53257790368272e-06,
      "loss": 0.5917,
      "step": 160
    },
    {
      "epoch": 0.24113475177304963,
      "grad_norm": 3.853579044342041,
      "learning_rate": 4.81586402266289e-06,
      "loss": 0.5344,
      "step": 170
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 3.7307016849517822,
      "learning_rate": 5.09915014164306e-06,
      "loss": 0.4835,
      "step": 180
    },
    {
      "epoch": 0.2695035460992908,
      "grad_norm": 4.546213150024414,
      "learning_rate": 5.382436260623229e-06,
      "loss": 0.4625,
      "step": 190
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 2.806037664413452,
      "learning_rate": 5.6657223796034e-06,
      "loss": 0.4815,
      "step": 200
    },
    {
      "epoch": 0.2978723404255319,
      "grad_norm": 2.61692214012146,
      "learning_rate": 5.9490084985835695e-06,
      "loss": 0.5163,
      "step": 210
    },
    {
      "epoch": 0.3120567375886525,
      "grad_norm": 3.4631400108337402,
      "learning_rate": 6.23229461756374e-06,
      "loss": 0.4441,
      "step": 220
    },
    {
      "epoch": 0.3262411347517731,
      "grad_norm": 3.8826253414154053,
      "learning_rate": 6.51558073654391e-06,
      "loss": 0.4991,
      "step": 230
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 8.294108390808105,
      "learning_rate": 6.79886685552408e-06,
      "loss": 0.4242,
      "step": 240
    },
    {
      "epoch": 0.3546099290780142,
      "grad_norm": 5.891849517822266,
      "learning_rate": 7.082152974504249e-06,
      "loss": 0.3755,
      "step": 250
    },
    {
      "epoch": 0.36879432624113473,
      "grad_norm": 2.0155107975006104,
      "learning_rate": 7.36543909348442e-06,
      "loss": 0.4485,
      "step": 260
    },
    {
      "epoch": 0.3829787234042553,
      "grad_norm": 6.576756000518799,
      "learning_rate": 7.64872521246459e-06,
      "loss": 0.5215,
      "step": 270
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 4.718179702758789,
      "learning_rate": 7.93201133144476e-06,
      "loss": 0.451,
      "step": 280
    },
    {
      "epoch": 0.41134751773049644,
      "grad_norm": 8.037521362304688,
      "learning_rate": 8.215297450424929e-06,
      "loss": 0.3998,
      "step": 290
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 9.343371391296387,
      "learning_rate": 8.4985835694051e-06,
      "loss": 0.4932,
      "step": 300
    },
    {
      "epoch": 0.4397163120567376,
      "grad_norm": 7.793552875518799,
      "learning_rate": 8.78186968838527e-06,
      "loss": 0.6019,
      "step": 310
    },
    {
      "epoch": 0.45390070921985815,
      "grad_norm": 5.285057544708252,
      "learning_rate": 9.06515580736544e-06,
      "loss": 0.513,
      "step": 320
    },
    {
      "epoch": 0.46808510638297873,
      "grad_norm": 3.9955966472625732,
      "learning_rate": 9.320113314447593e-06,
      "loss": 0.4834,
      "step": 330
    },
    {
      "epoch": 0.48226950354609927,
      "grad_norm": 5.319847583770752,
      "learning_rate": 9.603399433427763e-06,
      "loss": 0.4331,
      "step": 340
    },
    {
      "epoch": 0.49645390070921985,
      "grad_norm": 4.910267353057861,
      "learning_rate": 9.886685552407933e-06,
      "loss": 0.4358,
      "step": 350
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 7.623688220977783,
      "learning_rate": 9.98108448928121e-06,
      "loss": 0.474,
      "step": 360
    },
    {
      "epoch": 0.524822695035461,
      "grad_norm": 5.579910755157471,
      "learning_rate": 9.949558638083228e-06,
      "loss": 0.4071,
      "step": 370
    },
    {
      "epoch": 0.5390070921985816,
      "grad_norm": 5.880229949951172,
      "learning_rate": 9.918032786885246e-06,
      "loss": 0.4092,
      "step": 380
    },
    {
      "epoch": 0.5531914893617021,
      "grad_norm": 6.779512882232666,
      "learning_rate": 9.886506935687265e-06,
      "loss": 0.4974,
      "step": 390
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 9.391179084777832,
      "learning_rate": 9.854981084489283e-06,
      "loss": 0.4478,
      "step": 400
    },
    {
      "epoch": 0.5815602836879432,
      "grad_norm": 6.661557674407959,
      "learning_rate": 9.823455233291299e-06,
      "loss": 0.3499,
      "step": 410
    },
    {
      "epoch": 0.5957446808510638,
      "grad_norm": 6.117848873138428,
      "learning_rate": 9.791929382093316e-06,
      "loss": 0.4764,
      "step": 420
    },
    {
      "epoch": 0.6099290780141844,
      "grad_norm": 8.049355506896973,
      "learning_rate": 9.760403530895335e-06,
      "loss": 0.5509,
      "step": 430
    },
    {
      "epoch": 0.624113475177305,
      "grad_norm": 8.663712501525879,
      "learning_rate": 9.728877679697353e-06,
      "loss": 0.525,
      "step": 440
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 5.39608097076416,
      "learning_rate": 9.69735182849937e-06,
      "loss": 0.5357,
      "step": 450
    },
    {
      "epoch": 0.6524822695035462,
      "grad_norm": 5.307394981384277,
      "learning_rate": 9.665825977301387e-06,
      "loss": 0.5224,
      "step": 460
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 7.630402088165283,
      "learning_rate": 9.634300126103406e-06,
      "loss": 0.4557,
      "step": 470
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 4.096060276031494,
      "learning_rate": 9.602774274905423e-06,
      "loss": 0.3789,
      "step": 480
    },
    {
      "epoch": 0.6950354609929078,
      "grad_norm": 9.660956382751465,
      "learning_rate": 9.571248423707441e-06,
      "loss": 0.551,
      "step": 490
    },
    {
      "epoch": 0.7092198581560284,
      "grad_norm": 2.3412363529205322,
      "learning_rate": 9.539722572509459e-06,
      "loss": 0.3314,
      "step": 500
    },
    {
      "epoch": 0.723404255319149,
      "grad_norm": 12.12543773651123,
      "learning_rate": 9.508196721311476e-06,
      "loss": 0.476,
      "step": 510
    },
    {
      "epoch": 0.7375886524822695,
      "grad_norm": 6.994177341461182,
      "learning_rate": 9.476670870113494e-06,
      "loss": 0.4423,
      "step": 520
    },
    {
      "epoch": 0.75177304964539,
      "grad_norm": 11.918400764465332,
      "learning_rate": 9.445145018915511e-06,
      "loss": 0.4316,
      "step": 530
    },
    {
      "epoch": 0.7659574468085106,
      "grad_norm": 5.349381446838379,
      "learning_rate": 9.413619167717529e-06,
      "loss": 0.3667,
      "step": 540
    },
    {
      "epoch": 0.7801418439716312,
      "grad_norm": 8.735565185546875,
      "learning_rate": 9.382093316519547e-06,
      "loss": 0.4921,
      "step": 550
    },
    {
      "epoch": 0.7943262411347518,
      "grad_norm": 7.618056297302246,
      "learning_rate": 9.350567465321564e-06,
      "loss": 0.405,
      "step": 560
    },
    {
      "epoch": 0.8085106382978723,
      "grad_norm": 7.237460613250732,
      "learning_rate": 9.319041614123582e-06,
      "loss": 0.4639,
      "step": 570
    },
    {
      "epoch": 0.8226950354609929,
      "grad_norm": 3.020843267440796,
      "learning_rate": 9.2875157629256e-06,
      "loss": 0.3743,
      "step": 580
    },
    {
      "epoch": 0.8368794326241135,
      "grad_norm": 2.8240303993225098,
      "learning_rate": 9.255989911727617e-06,
      "loss": 0.3519,
      "step": 590
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 7.802272796630859,
      "learning_rate": 9.224464060529636e-06,
      "loss": 0.4382,
      "step": 600
    },
    {
      "epoch": 0.8652482269503546,
      "grad_norm": 6.550302028656006,
      "learning_rate": 9.192938209331652e-06,
      "loss": 0.3666,
      "step": 610
    },
    {
      "epoch": 0.8794326241134752,
      "grad_norm": 8.625157356262207,
      "learning_rate": 9.16141235813367e-06,
      "loss": 0.3211,
      "step": 620
    },
    {
      "epoch": 0.8936170212765957,
      "grad_norm": 7.997941970825195,
      "learning_rate": 9.129886506935687e-06,
      "loss": 0.3952,
      "step": 630
    },
    {
      "epoch": 0.9078014184397163,
      "grad_norm": 5.472368240356445,
      "learning_rate": 9.098360655737707e-06,
      "loss": 0.5257,
      "step": 640
    },
    {
      "epoch": 0.9219858156028369,
      "grad_norm": 4.210991382598877,
      "learning_rate": 9.066834804539724e-06,
      "loss": 0.4197,
      "step": 650
    },
    {
      "epoch": 0.9361702127659575,
      "grad_norm": 8.450587272644043,
      "learning_rate": 9.035308953341742e-06,
      "loss": 0.4223,
      "step": 660
    },
    {
      "epoch": 0.950354609929078,
      "grad_norm": 6.2185468673706055,
      "learning_rate": 9.003783102143758e-06,
      "loss": 0.4255,
      "step": 670
    },
    {
      "epoch": 0.9645390070921985,
      "grad_norm": 8.005620002746582,
      "learning_rate": 8.972257250945777e-06,
      "loss": 0.4127,
      "step": 680
    },
    {
      "epoch": 0.9787234042553191,
      "grad_norm": 10.813994407653809,
      "learning_rate": 8.940731399747794e-06,
      "loss": 0.5108,
      "step": 690
    },
    {
      "epoch": 0.9929078014184397,
      "grad_norm": 6.870554447174072,
      "learning_rate": 8.909205548549812e-06,
      "loss": 0.5915,
      "step": 700
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8450479233226837,
      "eval_f1": 0.8486739469578783,
      "eval_loss": 0.3890458941459656,
      "eval_precision": 0.8662420382165605,
      "eval_recall": 0.8318042813455657,
      "eval_runtime": 1.1787,
      "eval_samples_per_second": 531.111,
      "eval_steps_per_second": 67.025,
      "step": 705
    }
  ],
  "logging_steps": 10,
  "max_steps": 3525,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 746321324027904.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}