{
  "best_metric": 0.8979526551503519,
  "best_model_checkpoint": "./checkpoints/klue_roberta-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": 13.938838958740234,
      "learning_rate": 1.9786734911494988e-05,
      "loss": 0.867,
      "step": 50
    },
    {
      "epoch": 0.06397952655150352,
      "grad_norm": 17.99142837524414,
      "learning_rate": 1.9573469822989978e-05,
      "loss": 0.5993,
      "step": 100
    },
    {
      "epoch": 0.09596928982725528,
      "grad_norm": 5.296301364898682,
      "learning_rate": 1.9360204734484968e-05,
      "loss": 0.5172,
      "step": 150
    },
    {
      "epoch": 0.12795905310300704,
      "grad_norm": 23.372655868530273,
      "learning_rate": 1.9146939645979955e-05,
      "loss": 0.447,
      "step": 200
    },
    {
      "epoch": 0.1599488163787588,
      "grad_norm": 15.999876976013184,
      "learning_rate": 1.8933674557474945e-05,
      "loss": 0.4396,
      "step": 250
    },
    {
      "epoch": 0.19193857965451055,
      "grad_norm": 7.189252853393555,
      "learning_rate": 1.872040946896993e-05,
      "loss": 0.4596,
      "step": 300
    },
    {
      "epoch": 0.22392834293026231,
      "grad_norm": 14.548877716064453,
      "learning_rate": 1.8507144380464918e-05,
      "loss": 0.4377,
      "step": 350
    },
    {
      "epoch": 0.2559181062060141,
      "grad_norm": 10.259931564331055,
      "learning_rate": 1.8293879291959908e-05,
      "loss": 0.4312,
      "step": 400
    },
    {
      "epoch": 0.28790786948176583,
      "grad_norm": 5.839106559753418,
      "learning_rate": 1.8080614203454897e-05,
      "loss": 0.4194,
      "step": 450
    },
    {
      "epoch": 0.3198976327575176,
      "grad_norm": 13.312091827392578,
      "learning_rate": 1.7867349114949884e-05,
      "loss": 0.4029,
      "step": 500
    },
    {
      "epoch": 0.35188739603326935,
      "grad_norm": 6.9318623542785645,
      "learning_rate": 1.7654084026444874e-05,
      "loss": 0.4331,
      "step": 550
    },
    {
      "epoch": 0.3838771593090211,
      "grad_norm": 3.7504262924194336,
      "learning_rate": 1.744081893793986e-05,
      "loss": 0.3579,
      "step": 600
    },
    {
      "epoch": 0.41586692258477287,
      "grad_norm": 19.280574798583984,
      "learning_rate": 1.7227553849434847e-05,
      "loss": 0.45,
      "step": 650
    },
    {
      "epoch": 0.44785668586052463,
      "grad_norm": 8.638567924499512,
      "learning_rate": 1.7014288760929837e-05,
      "loss": 0.3774,
      "step": 700
    },
    {
      "epoch": 0.4798464491362764,
      "grad_norm": 16.157691955566406,
      "learning_rate": 1.6801023672424827e-05,
      "loss": 0.3789,
      "step": 750
    },
    {
      "epoch": 0.5118362124120281,
      "grad_norm": 6.670945167541504,
      "learning_rate": 1.6587758583919813e-05,
      "loss": 0.3579,
      "step": 800
    },
    {
      "epoch": 0.5438259756877799,
      "grad_norm": 9.523850440979004,
      "learning_rate": 1.6374493495414803e-05,
      "loss": 0.4186,
      "step": 850
    },
    {
      "epoch": 0.5758157389635317,
      "grad_norm": 15.308146476745605,
      "learning_rate": 1.616122840690979e-05,
      "loss": 0.4471,
      "step": 900
    },
    {
      "epoch": 0.6078055022392834,
      "grad_norm": 5.684741973876953,
      "learning_rate": 1.5947963318404776e-05,
      "loss": 0.4066,
      "step": 950
    },
    {
      "epoch": 0.6397952655150352,
      "grad_norm": 27.66901206970215,
      "learning_rate": 1.5734698229899766e-05,
      "loss": 0.4196,
      "step": 1000
    },
    {
      "epoch": 0.6717850287907869,
      "grad_norm": 16.616378784179688,
      "learning_rate": 1.5521433141394756e-05,
      "loss": 0.378,
      "step": 1050
    },
    {
      "epoch": 0.7037747920665387,
      "grad_norm": 8.623127937316895,
      "learning_rate": 1.5308168052889743e-05,
      "loss": 0.3645,
      "step": 1100
    },
    {
      "epoch": 0.7357645553422905,
      "grad_norm": 2.1066179275512695,
      "learning_rate": 1.5094902964384733e-05,
      "loss": 0.4008,
      "step": 1150
    },
    {
      "epoch": 0.7677543186180422,
      "grad_norm": 13.267948150634766,
      "learning_rate": 1.488163787587972e-05,
      "loss": 0.4076,
      "step": 1200
    },
    {
      "epoch": 0.799744081893794,
      "grad_norm": 8.27193546295166,
      "learning_rate": 1.4668372787374708e-05,
      "loss": 0.35,
      "step": 1250
    },
    {
      "epoch": 0.8317338451695457,
      "grad_norm": 21.75761604309082,
      "learning_rate": 1.4455107698869698e-05,
      "loss": 0.3543,
      "step": 1300
    },
    {
      "epoch": 0.8637236084452975,
      "grad_norm": 4.876620292663574,
      "learning_rate": 1.4241842610364684e-05,
      "loss": 0.3791,
      "step": 1350
    },
    {
      "epoch": 0.8957133717210493,
      "grad_norm": 15.055893898010254,
      "learning_rate": 1.4028577521859672e-05,
      "loss": 0.3272,
      "step": 1400
    },
    {
      "epoch": 0.927703134996801,
      "grad_norm": 3.3032615184783936,
      "learning_rate": 1.3815312433354662e-05,
      "loss": 0.3722,
      "step": 1450
    },
    {
      "epoch": 0.9596928982725528,
      "grad_norm": 19.728113174438477,
      "learning_rate": 1.3602047344849649e-05,
      "loss": 0.3547,
      "step": 1500
    },
    {
      "epoch": 0.9916826615483045,
      "grad_norm": 21.141584396362305,
      "learning_rate": 1.3388782256344637e-05,
      "loss": 0.339,
      "step": 1550
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.882597568777991,
      "eval_f1": 0.8731296110509383,
      "eval_loss": 0.3366224765777588,
      "eval_runtime": 70.1994,
      "eval_samples_per_second": 44.53,
      "eval_steps_per_second": 2.792,
      "step": 1563
    },
    {
      "epoch": 1.0236724248240563,
      "grad_norm": 10.141568183898926,
      "learning_rate": 1.3175517167839627e-05,
      "loss": 0.2731,
      "step": 1600
    },
    {
      "epoch": 1.055662188099808,
      "grad_norm": 12.200018882751465,
      "learning_rate": 1.2962252079334613e-05,
      "loss": 0.2816,
      "step": 1650
    },
    {
      "epoch": 1.0876519513755598,
      "grad_norm": 20.204090118408203,
      "learning_rate": 1.2748986990829602e-05,
      "loss": 0.2917,
      "step": 1700
    },
    {
      "epoch": 1.1196417146513116,
      "grad_norm": 7.249327659606934,
      "learning_rate": 1.2535721902324592e-05,
      "loss": 0.2787,
      "step": 1750
    },
    {
      "epoch": 1.1516314779270633,
      "grad_norm": 5.919739723205566,
      "learning_rate": 1.2322456813819578e-05,
      "loss": 0.2876,
      "step": 1800
    },
    {
      "epoch": 1.183621241202815,
      "grad_norm": 10.370328903198242,
      "learning_rate": 1.2109191725314566e-05,
      "loss": 0.2845,
      "step": 1850
    },
    {
      "epoch": 1.2156110044785668,
      "grad_norm": 3.661513328552246,
      "learning_rate": 1.1895926636809556e-05,
      "loss": 0.3262,
      "step": 1900
    },
    {
      "epoch": 1.2476007677543186,
      "grad_norm": 19.12290382385254,
      "learning_rate": 1.1682661548304543e-05,
      "loss": 0.2781,
      "step": 1950
    },
    {
      "epoch": 1.2795905310300704,
      "grad_norm": 4.797718048095703,
      "learning_rate": 1.1469396459799531e-05,
      "loss": 0.3053,
      "step": 2000
    },
    {
      "epoch": 1.3115802943058221,
      "grad_norm": 2.8714613914489746,
      "learning_rate": 1.1256131371294521e-05,
      "loss": 0.2839,
      "step": 2050
    },
    {
      "epoch": 1.3435700575815739,
      "grad_norm": 8.084686279296875,
      "learning_rate": 1.1042866282789508e-05,
      "loss": 0.2783,
      "step": 2100
    },
    {
      "epoch": 1.3755598208573256,
      "grad_norm": 11.213396072387695,
      "learning_rate": 1.0829601194284496e-05,
      "loss": 0.2744,
      "step": 2150
    },
    {
      "epoch": 1.4075495841330774,
      "grad_norm": 1.4591023921966553,
      "learning_rate": 1.0616336105779486e-05,
      "loss": 0.2722,
      "step": 2200
    },
    {
      "epoch": 1.4395393474088292,
      "grad_norm": 4.192473411560059,
      "learning_rate": 1.0403071017274472e-05,
      "loss": 0.2568,
      "step": 2250
    },
    {
      "epoch": 1.471529110684581,
      "grad_norm": 6.94098424911499,
      "learning_rate": 1.018980592876946e-05,
      "loss": 0.286,
      "step": 2300
    },
    {
      "epoch": 1.5035188739603327,
      "grad_norm": 2.280522584915161,
      "learning_rate": 9.976540840264449e-06,
      "loss": 0.2096,
      "step": 2350
    },
    {
      "epoch": 1.5355086372360844,
      "grad_norm": 26.468631744384766,
      "learning_rate": 9.763275751759437e-06,
      "loss": 0.2496,
      "step": 2400
    },
    {
      "epoch": 1.5674984005118362,
      "grad_norm": 5.237730979919434,
      "learning_rate": 9.550010663254427e-06,
      "loss": 0.2688,
      "step": 2450
    },
    {
      "epoch": 1.599488163787588,
      "grad_norm": 35.639862060546875,
      "learning_rate": 9.336745574749414e-06,
      "loss": 0.3109,
      "step": 2500
    },
    {
      "epoch": 1.6314779270633397,
      "grad_norm": 10.238542556762695,
      "learning_rate": 9.123480486244403e-06,
      "loss": 0.2408,
      "step": 2550
    },
    {
      "epoch": 1.6634676903390915,
      "grad_norm": 11.457088470458984,
      "learning_rate": 8.910215397739392e-06,
      "loss": 0.2852,
      "step": 2600
    },
    {
      "epoch": 1.6954574536148432,
      "grad_norm": 32.95170593261719,
      "learning_rate": 8.696950309234378e-06,
      "loss": 0.2388,
      "step": 2650
    },
    {
      "epoch": 1.727447216890595,
      "grad_norm": 11.303943634033203,
      "learning_rate": 8.483685220729368e-06,
      "loss": 0.2897,
      "step": 2700
    },
    {
      "epoch": 1.7594369801663468,
      "grad_norm": 16.055866241455078,
      "learning_rate": 8.270420132224356e-06,
      "loss": 0.2718,
      "step": 2750
    },
    {
      "epoch": 1.7914267434420985,
      "grad_norm": 26.67633819580078,
      "learning_rate": 8.057155043719343e-06,
      "loss": 0.2717,
      "step": 2800
    },
    {
      "epoch": 1.8234165067178503,
      "grad_norm": 1.5687782764434814,
      "learning_rate": 7.843889955214333e-06,
      "loss": 0.2463,
      "step": 2850
    },
    {
      "epoch": 1.855406269993602,
      "grad_norm": 11.995882987976074,
      "learning_rate": 7.630624866709321e-06,
      "loss": 0.2855,
      "step": 2900
    },
    {
      "epoch": 1.8873960332693538,
      "grad_norm": 6.166232585906982,
      "learning_rate": 7.4173597782043085e-06,
      "loss": 0.2609,
      "step": 2950
    },
    {
      "epoch": 1.9193857965451055,
      "grad_norm": 10.031974792480469,
      "learning_rate": 7.204094689699297e-06,
      "loss": 0.2492,
      "step": 3000
    },
    {
      "epoch": 1.9513755598208573,
      "grad_norm": 17.817472457885742,
      "learning_rate": 6.990829601194286e-06,
      "loss": 0.2833,
      "step": 3050
    },
    {
      "epoch": 1.983365323096609,
      "grad_norm": 12.737804412841797,
      "learning_rate": 6.777564512689273e-06,
      "loss": 0.2298,
      "step": 3100
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8896353166986565,
      "eval_f1": 0.8796741674944375,
      "eval_loss": 0.3404127061367035,
      "eval_runtime": 70.9424,
      "eval_samples_per_second": 44.064,
      "eval_steps_per_second": 2.763,
      "step": 3126
    },
    {
      "epoch": 2.015355086372361,
      "grad_norm": 19.307981491088867,
      "learning_rate": 6.5642994241842614e-06,
      "loss": 0.2292,
      "step": 3150
    },
    {
      "epoch": 2.0473448496481126,
      "grad_norm": 1.5788886547088623,
      "learning_rate": 6.3510343356792505e-06,
      "loss": 0.1972,
      "step": 3200
    },
    {
      "epoch": 2.0793346129238643,
      "grad_norm": 20.933168411254883,
      "learning_rate": 6.137769247174238e-06,
      "loss": 0.1997,
      "step": 3250
    },
    {
      "epoch": 2.111324376199616,
      "grad_norm": 6.816852569580078,
      "learning_rate": 5.924504158669226e-06,
      "loss": 0.1906,
      "step": 3300
    },
    {
      "epoch": 2.143314139475368,
      "grad_norm": 7.3301568031311035,
      "learning_rate": 5.711239070164215e-06,
      "loss": 0.1849,
      "step": 3350
    },
    {
      "epoch": 2.1753039027511196,
      "grad_norm": 22.308238983154297,
      "learning_rate": 5.497973981659203e-06,
      "loss": 0.2354,
      "step": 3400
    },
    {
      "epoch": 2.2072936660268714,
      "grad_norm": 6.629489898681641,
      "learning_rate": 5.284708893154191e-06,
      "loss": 0.2158,
      "step": 3450
    },
    {
      "epoch": 2.239283429302623,
      "grad_norm": 25.275117874145508,
      "learning_rate": 5.07144380464918e-06,
      "loss": 0.1895,
      "step": 3500
    },
    {
      "epoch": 2.271273192578375,
      "grad_norm": 12.04372501373291,
      "learning_rate": 4.858178716144167e-06,
      "loss": 0.1847,
      "step": 3550
    },
    {
      "epoch": 2.3032629558541267,
      "grad_norm": 11.848182678222656,
      "learning_rate": 4.644913627639156e-06,
      "loss": 0.2146,
      "step": 3600
    },
    {
      "epoch": 2.3352527191298784,
      "grad_norm": 0.5052518248558044,
      "learning_rate": 4.431648539134144e-06,
      "loss": 0.1926,
      "step": 3650
    },
    {
      "epoch": 2.36724248240563,
      "grad_norm": 4.544561386108398,
      "learning_rate": 4.218383450629132e-06,
      "loss": 0.1982,
      "step": 3700
    },
    {
      "epoch": 2.399232245681382,
      "grad_norm": 11.20161247253418,
      "learning_rate": 4.005118362124121e-06,
      "loss": 0.224,
      "step": 3750
    },
    {
      "epoch": 2.4312220089571337,
      "grad_norm": 14.562556266784668,
      "learning_rate": 3.791853273619109e-06,
      "loss": 0.2018,
      "step": 3800
    },
    {
      "epoch": 2.4632117722328855,
      "grad_norm": 5.632498741149902,
      "learning_rate": 3.5785881851140968e-06,
      "loss": 0.1898,
      "step": 3850
    },
    {
      "epoch": 2.495201535508637,
      "grad_norm": 60.00568389892578,
      "learning_rate": 3.3653230966090854e-06,
      "loss": 0.219,
      "step": 3900
    },
    {
      "epoch": 2.527191298784389,
      "grad_norm": 14.374926567077637,
      "learning_rate": 3.1520580081040737e-06,
      "loss": 0.1881,
      "step": 3950
    },
    {
      "epoch": 2.5591810620601407,
      "grad_norm": 19.68595314025879,
      "learning_rate": 2.9387929195990615e-06,
      "loss": 0.1659,
      "step": 4000
    },
    {
      "epoch": 2.5911708253358925,
      "grad_norm": 8.034276962280273,
      "learning_rate": 2.72552783109405e-06,
      "loss": 0.1782,
      "step": 4050
    },
    {
      "epoch": 2.6231605886116443,
      "grad_norm": 44.782249450683594,
      "learning_rate": 2.5122627425890384e-06,
      "loss": 0.1953,
      "step": 4100
    },
    {
      "epoch": 2.655150351887396,
      "grad_norm": 10.387372016906738,
      "learning_rate": 2.2989976540840266e-06,
      "loss": 0.2097,
      "step": 4150
    },
    {
      "epoch": 2.6871401151631478,
      "grad_norm": 21.505399703979492,
      "learning_rate": 2.085732565579015e-06,
      "loss": 0.1494,
      "step": 4200
    },
    {
      "epoch": 2.7191298784388995,
      "grad_norm": 18.130090713500977,
      "learning_rate": 1.872467477074003e-06,
      "loss": 0.181,
      "step": 4250
    },
    {
      "epoch": 2.7511196417146513,
      "grad_norm": 1.530978798866272,
      "learning_rate": 1.6592023885689915e-06,
      "loss": 0.1995,
      "step": 4300
    },
    {
      "epoch": 2.783109404990403,
      "grad_norm": 7.71237850189209,
      "learning_rate": 1.4459373000639796e-06,
      "loss": 0.2079,
      "step": 4350
    },
    {
      "epoch": 2.815099168266155,
      "grad_norm": 12.530670166015625,
      "learning_rate": 1.2326722115589678e-06,
      "loss": 0.1995,
      "step": 4400
    },
    {
      "epoch": 2.8470889315419066,
      "grad_norm": 6.267744064331055,
      "learning_rate": 1.019407123053956e-06,
      "loss": 0.193,
      "step": 4450
    },
    {
      "epoch": 2.8790786948176583,
      "grad_norm": 10.180434226989746,
      "learning_rate": 8.061420345489445e-07,
      "loss": 0.2146,
      "step": 4500
    },
    {
      "epoch": 2.91106845809341,
      "grad_norm": 11.851616859436035,
      "learning_rate": 5.928769460439326e-07,
      "loss": 0.138,
      "step": 4550
    },
    {
      "epoch": 2.943058221369162,
      "grad_norm": 19.89887809753418,
      "learning_rate": 3.796118575389209e-07,
      "loss": 0.2101,
      "step": 4600
    },
    {
      "epoch": 2.9750479846449136,
      "grad_norm": 19.396095275878906,
      "learning_rate": 1.6634676903390917e-07,
      "loss": 0.2084,
      "step": 4650
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8979526551503519,
      "eval_f1": 0.8882201976359388,
      "eval_loss": 0.37854427099227905,
      "eval_runtime": 72.7283,
      "eval_samples_per_second": 42.982,
      "eval_steps_per_second": 2.695,
      "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
}