{
  "best_metric": 0.8976327575175944,
  "best_model_checkpoint": "./checkpoints/klue_bert-base\\checkpoint-4689",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 4689,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03198976327575176,
      "grad_norm": 8.30168342590332,
      "learning_rate": 1.9786734911494988e-05,
      "loss": 0.7464,
      "step": 50
    },
    {
      "epoch": 0.06397952655150352,
      "grad_norm": 9.065665245056152,
      "learning_rate": 1.9573469822989978e-05,
      "loss": 0.539,
      "step": 100
    },
    {
      "epoch": 0.09596928982725528,
      "grad_norm": 14.672710418701172,
      "learning_rate": 1.9360204734484968e-05,
      "loss": 0.4953,
      "step": 150
    },
    {
      "epoch": 0.12795905310300704,
      "grad_norm": 11.273133277893066,
      "learning_rate": 1.9146939645979955e-05,
      "loss": 0.4002,
      "step": 200
    },
    {
      "epoch": 0.1599488163787588,
      "grad_norm": 10.856703758239746,
      "learning_rate": 1.8933674557474945e-05,
      "loss": 0.4415,
      "step": 250
    },
    {
      "epoch": 0.19193857965451055,
      "grad_norm": 6.359602451324463,
      "learning_rate": 1.872040946896993e-05,
      "loss": 0.4559,
      "step": 300
    },
    {
      "epoch": 0.22392834293026231,
      "grad_norm": 9.03753662109375,
      "learning_rate": 1.8507144380464918e-05,
      "loss": 0.4145,
      "step": 350
    },
    {
      "epoch": 0.2559181062060141,
      "grad_norm": 10.679155349731445,
      "learning_rate": 1.8293879291959908e-05,
      "loss": 0.3769,
      "step": 400
    },
    {
      "epoch": 0.28790786948176583,
      "grad_norm": 11.417706489562988,
      "learning_rate": 1.8080614203454897e-05,
      "loss": 0.3864,
      "step": 450
    },
    {
      "epoch": 0.3198976327575176,
      "grad_norm": 7.758769512176514,
      "learning_rate": 1.7867349114949884e-05,
      "loss": 0.3608,
      "step": 500
    },
    {
      "epoch": 0.35188739603326935,
      "grad_norm": 10.617319107055664,
      "learning_rate": 1.7654084026444874e-05,
      "loss": 0.4189,
      "step": 550
    },
    {
      "epoch": 0.3838771593090211,
      "grad_norm": 7.695286273956299,
      "learning_rate": 1.744081893793986e-05,
      "loss": 0.3739,
      "step": 600
    },
    {
      "epoch": 0.41586692258477287,
      "grad_norm": 4.655588626861572,
      "learning_rate": 1.7227553849434847e-05,
      "loss": 0.3978,
      "step": 650
    },
    {
      "epoch": 0.44785668586052463,
      "grad_norm": 7.375668525695801,
      "learning_rate": 1.7014288760929837e-05,
      "loss": 0.3624,
      "step": 700
    },
    {
      "epoch": 0.4798464491362764,
      "grad_norm": 8.715352058410645,
      "learning_rate": 1.6801023672424827e-05,
      "loss": 0.3983,
      "step": 750
    },
    {
      "epoch": 0.5118362124120281,
      "grad_norm": 4.942613124847412,
      "learning_rate": 1.6587758583919813e-05,
      "loss": 0.3264,
      "step": 800
    },
    {
      "epoch": 0.5438259756877799,
      "grad_norm": 9.237791061401367,
      "learning_rate": 1.6374493495414803e-05,
      "loss": 0.3811,
      "step": 850
    },
    {
      "epoch": 0.5758157389635317,
      "grad_norm": 10.856432914733887,
      "learning_rate": 1.616122840690979e-05,
      "loss": 0.3965,
      "step": 900
    },
    {
      "epoch": 0.6078055022392834,
      "grad_norm": 7.043545246124268,
      "learning_rate": 1.5947963318404776e-05,
      "loss": 0.3702,
      "step": 950
    },
    {
      "epoch": 0.6397952655150352,
      "grad_norm": 7.454297065734863,
      "learning_rate": 1.5734698229899766e-05,
      "loss": 0.3946,
      "step": 1000
    },
    {
      "epoch": 0.6717850287907869,
      "grad_norm": 17.558452606201172,
      "learning_rate": 1.5521433141394756e-05,
      "loss": 0.3569,
      "step": 1050
    },
    {
      "epoch": 0.7037747920665387,
      "grad_norm": 10.30020809173584,
      "learning_rate": 1.5308168052889743e-05,
      "loss": 0.3621,
      "step": 1100
    },
    {
      "epoch": 0.7357645553422905,
      "grad_norm": 8.323447227478027,
      "learning_rate": 1.5094902964384733e-05,
      "loss": 0.3507,
      "step": 1150
    },
    {
      "epoch": 0.7677543186180422,
      "grad_norm": 5.383088111877441,
      "learning_rate": 1.488163787587972e-05,
      "loss": 0.3927,
      "step": 1200
    },
    {
      "epoch": 0.799744081893794,
      "grad_norm": 6.308414936065674,
      "learning_rate": 1.4668372787374708e-05,
      "loss": 0.3469,
      "step": 1250
    },
    {
      "epoch": 0.8317338451695457,
      "grad_norm": 8.680594444274902,
      "learning_rate": 1.4455107698869698e-05,
      "loss": 0.3442,
      "step": 1300
    },
    {
      "epoch": 0.8637236084452975,
      "grad_norm": 3.560561418533325,
      "learning_rate": 1.4241842610364684e-05,
      "loss": 0.3829,
      "step": 1350
    },
    {
      "epoch": 0.8957133717210493,
      "grad_norm": 8.998127937316895,
      "learning_rate": 1.4028577521859672e-05,
      "loss": 0.3245,
      "step": 1400
    },
    {
      "epoch": 0.927703134996801,
      "grad_norm": 2.6510281562805176,
      "learning_rate": 1.3815312433354662e-05,
      "loss": 0.3591,
      "step": 1450
    },
    {
      "epoch": 0.9596928982725528,
      "grad_norm": 10.488450050354004,
      "learning_rate": 1.3602047344849649e-05,
      "loss": 0.3355,
      "step": 1500
    },
    {
      "epoch": 0.9916826615483045,
      "grad_norm": 6.973298072814941,
      "learning_rate": 1.3388782256344637e-05,
      "loss": 0.3017,
      "step": 1550
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8835572616762636,
      "eval_f1": 0.8734376826237961,
      "eval_loss": 0.3096177279949188,
      "eval_runtime": 70.7512,
      "eval_samples_per_second": 44.183,
      "eval_steps_per_second": 2.77,
      "step": 1563
    },
    {
      "epoch": 1.0236724248240563,
      "grad_norm": 7.356038570404053,
      "learning_rate": 1.3175517167839627e-05,
      "loss": 0.2326,
      "step": 1600
    },
    {
      "epoch": 1.055662188099808,
      "grad_norm": 12.944537162780762,
      "learning_rate": 1.2962252079334613e-05,
      "loss": 0.2559,
      "step": 1650
    },
    {
      "epoch": 1.0876519513755598,
      "grad_norm": 29.164777755737305,
      "learning_rate": 1.2748986990829602e-05,
      "loss": 0.2468,
      "step": 1700
    },
    {
      "epoch": 1.1196417146513116,
      "grad_norm": 4.75251579284668,
      "learning_rate": 1.2535721902324592e-05,
      "loss": 0.2388,
      "step": 1750
    },
    {
      "epoch": 1.1516314779270633,
      "grad_norm": 4.9411773681640625,
      "learning_rate": 1.2322456813819578e-05,
      "loss": 0.2788,
      "step": 1800
    },
    {
      "epoch": 1.183621241202815,
      "grad_norm": 12.609339714050293,
      "learning_rate": 1.2109191725314566e-05,
      "loss": 0.2343,
      "step": 1850
    },
    {
      "epoch": 1.2156110044785668,
      "grad_norm": 6.632409572601318,
      "learning_rate": 1.1895926636809556e-05,
      "loss": 0.2845,
      "step": 1900
    },
    {
      "epoch": 1.2476007677543186,
      "grad_norm": 13.227570533752441,
      "learning_rate": 1.1682661548304543e-05,
      "loss": 0.2484,
      "step": 1950
    },
    {
      "epoch": 1.2795905310300704,
      "grad_norm": 9.043356895446777,
      "learning_rate": 1.1469396459799531e-05,
      "loss": 0.2781,
      "step": 2000
    },
    {
      "epoch": 1.3115802943058221,
      "grad_norm": 1.4863983392715454,
      "learning_rate": 1.1256131371294521e-05,
      "loss": 0.2486,
      "step": 2050
    },
    {
      "epoch": 1.3435700575815739,
      "grad_norm": 11.874574661254883,
      "learning_rate": 1.1042866282789508e-05,
      "loss": 0.2319,
      "step": 2100
    },
    {
      "epoch": 1.3755598208573256,
      "grad_norm": 10.544360160827637,
      "learning_rate": 1.0829601194284496e-05,
      "loss": 0.2629,
      "step": 2150
    },
    {
      "epoch": 1.4075495841330774,
      "grad_norm": 1.597615122795105,
      "learning_rate": 1.0616336105779486e-05,
      "loss": 0.2424,
      "step": 2200
    },
    {
      "epoch": 1.4395393474088292,
      "grad_norm": 6.933614730834961,
      "learning_rate": 1.0403071017274472e-05,
      "loss": 0.2596,
      "step": 2250
    },
    {
      "epoch": 1.471529110684581,
      "grad_norm": 2.243976593017578,
      "learning_rate": 1.018980592876946e-05,
      "loss": 0.2746,
      "step": 2300
    },
    {
      "epoch": 1.5035188739603327,
      "grad_norm": 3.0834619998931885,
      "learning_rate": 9.976540840264449e-06,
      "loss": 0.2143,
      "step": 2350
    },
    {
      "epoch": 1.5355086372360844,
      "grad_norm": 21.907583236694336,
      "learning_rate": 9.763275751759437e-06,
      "loss": 0.2311,
      "step": 2400
    },
    {
      "epoch": 1.5674984005118362,
      "grad_norm": 1.5895259380340576,
      "learning_rate": 9.550010663254427e-06,
      "loss": 0.2487,
      "step": 2450
    },
    {
      "epoch": 1.599488163787588,
      "grad_norm": 10.364677429199219,
      "learning_rate": 9.336745574749414e-06,
      "loss": 0.2623,
      "step": 2500
    },
    {
      "epoch": 1.6314779270633397,
      "grad_norm": 10.95889663696289,
      "learning_rate": 9.123480486244403e-06,
      "loss": 0.2233,
      "step": 2550
    },
    {
      "epoch": 1.6634676903390915,
      "grad_norm": 21.338903427124023,
      "learning_rate": 8.910215397739392e-06,
      "loss": 0.25,
      "step": 2600
    },
    {
      "epoch": 1.6954574536148432,
      "grad_norm": 5.0549139976501465,
      "learning_rate": 8.696950309234378e-06,
      "loss": 0.2466,
      "step": 2650
    },
    {
      "epoch": 1.727447216890595,
      "grad_norm": 5.613836765289307,
      "learning_rate": 8.483685220729368e-06,
      "loss": 0.2603,
      "step": 2700
    },
    {
      "epoch": 1.7594369801663468,
      "grad_norm": 11.103569030761719,
      "learning_rate": 8.270420132224356e-06,
      "loss": 0.259,
      "step": 2750
    },
    {
      "epoch": 1.7914267434420985,
      "grad_norm": 3.3913040161132812,
      "learning_rate": 8.057155043719343e-06,
      "loss": 0.2458,
      "step": 2800
    },
    {
      "epoch": 1.8234165067178503,
      "grad_norm": 0.5389057993888855,
      "learning_rate": 7.843889955214333e-06,
      "loss": 0.2366,
      "step": 2850
    },
    {
      "epoch": 1.855406269993602,
      "grad_norm": 8.419164657592773,
      "learning_rate": 7.630624866709321e-06,
      "loss": 0.2716,
      "step": 2900
    },
    {
      "epoch": 1.8873960332693538,
      "grad_norm": 5.326470375061035,
      "learning_rate": 7.4173597782043085e-06,
      "loss": 0.2302,
      "step": 2950
    },
    {
      "epoch": 1.9193857965451055,
      "grad_norm": 6.134453296661377,
      "learning_rate": 7.204094689699297e-06,
      "loss": 0.2236,
      "step": 3000
    },
    {
      "epoch": 1.9513755598208573,
      "grad_norm": 13.053471565246582,
      "learning_rate": 6.990829601194286e-06,
      "loss": 0.2549,
      "step": 3050
    },
    {
      "epoch": 1.983365323096609,
      "grad_norm": 16.08262825012207,
      "learning_rate": 6.777564512689273e-06,
      "loss": 0.2065,
      "step": 3100
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.891234804862444,
      "eval_f1": 0.8816158583539794,
      "eval_loss": 0.32736125588417053,
      "eval_runtime": 69.7253,
      "eval_samples_per_second": 44.833,
      "eval_steps_per_second": 2.811,
      "step": 3126
    },
    {
      "epoch": 2.015355086372361,
      "grad_norm": 12.55622386932373,
      "learning_rate": 6.5642994241842614e-06,
      "loss": 0.1925,
      "step": 3150
    },
    {
      "epoch": 2.0473448496481126,
      "grad_norm": 9.97314167022705,
      "learning_rate": 6.3510343356792505e-06,
      "loss": 0.1697,
      "step": 3200
    },
    {
      "epoch": 2.0793346129238643,
      "grad_norm": 13.542362213134766,
      "learning_rate": 6.137769247174238e-06,
      "loss": 0.1759,
      "step": 3250
    },
    {
      "epoch": 2.111324376199616,
      "grad_norm": 2.1672303676605225,
      "learning_rate": 5.924504158669226e-06,
      "loss": 0.163,
      "step": 3300
    },
    {
      "epoch": 2.143314139475368,
      "grad_norm": 10.153268814086914,
      "learning_rate": 5.711239070164215e-06,
      "loss": 0.152,
      "step": 3350
    },
    {
      "epoch": 2.1753039027511196,
      "grad_norm": 30.200542449951172,
      "learning_rate": 5.497973981659203e-06,
      "loss": 0.2203,
      "step": 3400
    },
    {
      "epoch": 2.2072936660268714,
      "grad_norm": 7.482994079589844,
      "learning_rate": 5.284708893154191e-06,
      "loss": 0.1699,
      "step": 3450
    },
    {
      "epoch": 2.239283429302623,
      "grad_norm": 18.278284072875977,
      "learning_rate": 5.07144380464918e-06,
      "loss": 0.1624,
      "step": 3500
    },
    {
      "epoch": 2.271273192578375,
      "grad_norm": 15.992013931274414,
      "learning_rate": 4.858178716144167e-06,
      "loss": 0.1354,
      "step": 3550
    },
    {
      "epoch": 2.3032629558541267,
      "grad_norm": 8.946208953857422,
      "learning_rate": 4.644913627639156e-06,
      "loss": 0.176,
      "step": 3600
    },
    {
      "epoch": 2.3352527191298784,
      "grad_norm": 0.24096710979938507,
      "learning_rate": 4.431648539134144e-06,
      "loss": 0.1859,
      "step": 3650
    },
    {
      "epoch": 2.36724248240563,
      "grad_norm": 1.182032585144043,
      "learning_rate": 4.218383450629132e-06,
      "loss": 0.1643,
      "step": 3700
    },
    {
      "epoch": 2.399232245681382,
      "grad_norm": 14.64736270904541,
      "learning_rate": 4.005118362124121e-06,
      "loss": 0.1802,
      "step": 3750
    },
    {
      "epoch": 2.4312220089571337,
      "grad_norm": 28.632488250732422,
      "learning_rate": 3.791853273619109e-06,
      "loss": 0.1754,
      "step": 3800
    },
    {
      "epoch": 2.4632117722328855,
      "grad_norm": 12.297914505004883,
      "learning_rate": 3.5785881851140968e-06,
      "loss": 0.1654,
      "step": 3850
    },
    {
      "epoch": 2.495201535508637,
      "grad_norm": 8.145957946777344,
      "learning_rate": 3.3653230966090854e-06,
      "loss": 0.1754,
      "step": 3900
    },
    {
      "epoch": 2.527191298784389,
      "grad_norm": 1.9005142450332642,
      "learning_rate": 3.1520580081040737e-06,
      "loss": 0.1292,
      "step": 3950
    },
    {
      "epoch": 2.5591810620601407,
      "grad_norm": 23.53730010986328,
      "learning_rate": 2.9387929195990615e-06,
      "loss": 0.1386,
      "step": 4000
    },
    {
      "epoch": 2.5911708253358925,
      "grad_norm": 2.064774751663208,
      "learning_rate": 2.72552783109405e-06,
      "loss": 0.1667,
      "step": 4050
    },
    {
      "epoch": 2.6231605886116443,
      "grad_norm": 34.96377182006836,
      "learning_rate": 2.5122627425890384e-06,
      "loss": 0.2021,
      "step": 4100
    },
    {
      "epoch": 2.655150351887396,
      "grad_norm": 20.485219955444336,
      "learning_rate": 2.2989976540840266e-06,
      "loss": 0.1614,
      "step": 4150
    },
    {
      "epoch": 2.6871401151631478,
      "grad_norm": 13.900922775268555,
      "learning_rate": 2.085732565579015e-06,
      "loss": 0.1185,
      "step": 4200
    },
    {
      "epoch": 2.7191298784388995,
      "grad_norm": 0.96761155128479,
      "learning_rate": 1.872467477074003e-06,
      "loss": 0.1539,
      "step": 4250
    },
    {
      "epoch": 2.7511196417146513,
      "grad_norm": 1.9782915115356445,
      "learning_rate": 1.6592023885689915e-06,
      "loss": 0.1883,
      "step": 4300
    },
    {
      "epoch": 2.783109404990403,
      "grad_norm": 14.365890502929688,
      "learning_rate": 1.4459373000639796e-06,
      "loss": 0.2019,
      "step": 4350
    },
    {
      "epoch": 2.815099168266155,
      "grad_norm": 17.920162200927734,
      "learning_rate": 1.2326722115589678e-06,
      "loss": 0.1614,
      "step": 4400
    },
    {
      "epoch": 2.8470889315419066,
      "grad_norm": 7.565415859222412,
      "learning_rate": 1.019407123053956e-06,
      "loss": 0.1581,
      "step": 4450
    },
    {
      "epoch": 2.8790786948176583,
      "grad_norm": 4.440770149230957,
      "learning_rate": 8.061420345489445e-07,
      "loss": 0.1759,
      "step": 4500
    },
    {
      "epoch": 2.91106845809341,
      "grad_norm": 14.82466983795166,
      "learning_rate": 5.928769460439326e-07,
      "loss": 0.1288,
      "step": 4550
    },
    {
      "epoch": 2.943058221369162,
      "grad_norm": 15.672795295715332,
      "learning_rate": 3.796118575389209e-07,
      "loss": 0.205,
      "step": 4600
    },
    {
      "epoch": 2.9750479846449136,
      "grad_norm": 13.70653247833252,
      "learning_rate": 1.6634676903390917e-07,
      "loss": 0.1756,
      "step": 4650
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8976327575175944,
      "eval_f1": 0.8871674993824495,
      "eval_loss": 0.3958832323551178,
      "eval_runtime": 71.1516,
      "eval_samples_per_second": 43.934,
      "eval_steps_per_second": 2.755,
      "step": 4689
    }
  ],
  "logging_steps": 50,
  "max_steps": 4689,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 824050668588336.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}