{
  "best_metric": 0.9008317338451696,
  "best_model_checkpoint": "./checkpoints/monologg_koelectra-base-v3-discriminator\\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": 1.8438289165496826,
      "learning_rate": 1.9786734911494988e-05,
      "loss": 0.9998,
      "step": 50
    },
    {
      "epoch": 0.06397952655150352,
      "grad_norm": 4.708126544952393,
      "learning_rate": 1.9573469822989978e-05,
      "loss": 0.8181,
      "step": 100
    },
    {
      "epoch": 0.09596928982725528,
      "grad_norm": 7.408482551574707,
      "learning_rate": 1.9360204734484968e-05,
      "loss": 0.6265,
      "step": 150
    },
    {
      "epoch": 0.12795905310300704,
      "grad_norm": 6.211757183074951,
      "learning_rate": 1.9146939645979955e-05,
      "loss": 0.5046,
      "step": 200
    },
    {
      "epoch": 0.1599488163787588,
      "grad_norm": 7.470839500427246,
      "learning_rate": 1.8933674557474945e-05,
      "loss": 0.5358,
      "step": 250
    },
    {
      "epoch": 0.19193857965451055,
      "grad_norm": 2.0797882080078125,
      "learning_rate": 1.872040946896993e-05,
      "loss": 0.483,
      "step": 300
    },
    {
      "epoch": 0.22392834293026231,
      "grad_norm": 14.55879020690918,
      "learning_rate": 1.8507144380464918e-05,
      "loss": 0.4462,
      "step": 350
    },
    {
      "epoch": 0.2559181062060141,
      "grad_norm": 3.5867443084716797,
      "learning_rate": 1.8293879291959908e-05,
      "loss": 0.4348,
      "step": 400
    },
    {
      "epoch": 0.28790786948176583,
      "grad_norm": 11.995755195617676,
      "learning_rate": 1.8080614203454897e-05,
      "loss": 0.4236,
      "step": 450
    },
    {
      "epoch": 0.3198976327575176,
      "grad_norm": 7.211252689361572,
      "learning_rate": 1.7867349114949884e-05,
      "loss": 0.4099,
      "step": 500
    },
    {
      "epoch": 0.35188739603326935,
      "grad_norm": 5.884838581085205,
      "learning_rate": 1.7654084026444874e-05,
      "loss": 0.4265,
      "step": 550
    },
    {
      "epoch": 0.3838771593090211,
      "grad_norm": 4.443331241607666,
      "learning_rate": 1.744081893793986e-05,
      "loss": 0.3863,
      "step": 600
    },
    {
      "epoch": 0.41586692258477287,
      "grad_norm": 3.68717622756958,
      "learning_rate": 1.7227553849434847e-05,
      "loss": 0.4244,
      "step": 650
    },
    {
      "epoch": 0.44785668586052463,
      "grad_norm": 4.4258599281311035,
      "learning_rate": 1.7014288760929837e-05,
      "loss": 0.3701,
      "step": 700
    },
    {
      "epoch": 0.4798464491362764,
      "grad_norm": 8.484159469604492,
      "learning_rate": 1.6801023672424827e-05,
      "loss": 0.4079,
      "step": 750
    },
    {
      "epoch": 0.5118362124120281,
      "grad_norm": 8.976361274719238,
      "learning_rate": 1.6587758583919813e-05,
      "loss": 0.3413,
      "step": 800
    },
    {
      "epoch": 0.5438259756877799,
      "grad_norm": 7.113468170166016,
      "learning_rate": 1.6374493495414803e-05,
      "loss": 0.3928,
      "step": 850
    },
    {
      "epoch": 0.5758157389635317,
      "grad_norm": 7.242956161499023,
      "learning_rate": 1.616122840690979e-05,
      "loss": 0.4013,
      "step": 900
    },
    {
      "epoch": 0.6078055022392834,
      "grad_norm": 6.204492092132568,
      "learning_rate": 1.5947963318404776e-05,
      "loss": 0.3838,
      "step": 950
    },
    {
      "epoch": 0.6397952655150352,
      "grad_norm": 5.312352180480957,
      "learning_rate": 1.5734698229899766e-05,
      "loss": 0.3838,
      "step": 1000
    },
    {
      "epoch": 0.6717850287907869,
      "grad_norm": 22.331918716430664,
      "learning_rate": 1.5521433141394756e-05,
      "loss": 0.3618,
      "step": 1050
    },
    {
      "epoch": 0.7037747920665387,
      "grad_norm": 11.372283935546875,
      "learning_rate": 1.5308168052889743e-05,
      "loss": 0.3486,
      "step": 1100
    },
    {
      "epoch": 0.7357645553422905,
      "grad_norm": 31.921972274780273,
      "learning_rate": 1.5094902964384733e-05,
      "loss": 0.3807,
      "step": 1150
    },
    {
      "epoch": 0.7677543186180422,
      "grad_norm": 6.360013484954834,
      "learning_rate": 1.488163787587972e-05,
      "loss": 0.3903,
      "step": 1200
    },
    {
      "epoch": 0.799744081893794,
      "grad_norm": 5.0191330909729,
      "learning_rate": 1.4668372787374708e-05,
      "loss": 0.3477,
      "step": 1250
    },
    {
      "epoch": 0.8317338451695457,
      "grad_norm": 20.319231033325195,
      "learning_rate": 1.4455107698869698e-05,
      "loss": 0.3193,
      "step": 1300
    },
    {
      "epoch": 0.8637236084452975,
      "grad_norm": 3.2279179096221924,
      "learning_rate": 1.4241842610364684e-05,
      "loss": 0.3583,
      "step": 1350
    },
    {
      "epoch": 0.8957133717210493,
      "grad_norm": 5.339118480682373,
      "learning_rate": 1.4028577521859672e-05,
      "loss": 0.3343,
      "step": 1400
    },
    {
      "epoch": 0.927703134996801,
      "grad_norm": 3.4250569343566895,
      "learning_rate": 1.3815312433354662e-05,
      "loss": 0.3756,
      "step": 1450
    },
    {
      "epoch": 0.9596928982725528,
      "grad_norm": 7.723750591278076,
      "learning_rate": 1.3602047344849649e-05,
      "loss": 0.3342,
      "step": 1500
    },
    {
      "epoch": 0.9916826615483045,
      "grad_norm": 9.071324348449707,
      "learning_rate": 1.3388782256344637e-05,
      "loss": 0.3282,
      "step": 1550
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8848368522072937,
      "eval_f1": 0.8749968140479337,
      "eval_loss": 0.3197398781776428,
      "eval_runtime": 69.8877,
      "eval_samples_per_second": 44.729,
      "eval_steps_per_second": 2.804,
      "step": 1563
    },
    {
      "epoch": 1.0236724248240563,
      "grad_norm": 3.9245243072509766,
      "learning_rate": 1.3175517167839627e-05,
      "loss": 0.2311,
      "step": 1600
    },
    {
      "epoch": 1.055662188099808,
      "grad_norm": 13.951614379882812,
      "learning_rate": 1.2962252079334613e-05,
      "loss": 0.2844,
      "step": 1650
    },
    {
      "epoch": 1.0876519513755598,
      "grad_norm": 8.549053192138672,
      "learning_rate": 1.2748986990829602e-05,
      "loss": 0.2573,
      "step": 1700
    },
    {
      "epoch": 1.1196417146513116,
      "grad_norm": 7.1960835456848145,
      "learning_rate": 1.2535721902324592e-05,
      "loss": 0.2515,
      "step": 1750
    },
    {
      "epoch": 1.1516314779270633,
      "grad_norm": 3.4280333518981934,
      "learning_rate": 1.2322456813819578e-05,
      "loss": 0.3032,
      "step": 1800
    },
    {
      "epoch": 1.183621241202815,
      "grad_norm": 7.896517753601074,
      "learning_rate": 1.2109191725314566e-05,
      "loss": 0.2503,
      "step": 1850
    },
    {
      "epoch": 1.2156110044785668,
      "grad_norm": 3.302367687225342,
      "learning_rate": 1.1895926636809556e-05,
      "loss": 0.2815,
      "step": 1900
    },
    {
      "epoch": 1.2476007677543186,
      "grad_norm": 7.449910640716553,
      "learning_rate": 1.1682661548304543e-05,
      "loss": 0.2483,
      "step": 1950
    },
    {
      "epoch": 1.2795905310300704,
      "grad_norm": 6.277085304260254,
      "learning_rate": 1.1469396459799531e-05,
      "loss": 0.2709,
      "step": 2000
    },
    {
      "epoch": 1.3115802943058221,
      "grad_norm": 4.672796726226807,
      "learning_rate": 1.1256131371294521e-05,
      "loss": 0.2555,
      "step": 2050
    },
    {
      "epoch": 1.3435700575815739,
      "grad_norm": 11.666603088378906,
      "learning_rate": 1.1042866282789508e-05,
      "loss": 0.2381,
      "step": 2100
    },
    {
      "epoch": 1.3755598208573256,
      "grad_norm": 9.201951026916504,
      "learning_rate": 1.0829601194284496e-05,
      "loss": 0.2762,
      "step": 2150
    },
    {
      "epoch": 1.4075495841330774,
      "grad_norm": 2.2189481258392334,
      "learning_rate": 1.0616336105779486e-05,
      "loss": 0.2466,
      "step": 2200
    },
    {
      "epoch": 1.4395393474088292,
      "grad_norm": 8.02763557434082,
      "learning_rate": 1.0403071017274472e-05,
      "loss": 0.2556,
      "step": 2250
    },
    {
      "epoch": 1.471529110684581,
      "grad_norm": 2.0652530193328857,
      "learning_rate": 1.018980592876946e-05,
      "loss": 0.2789,
      "step": 2300
    },
    {
      "epoch": 1.5035188739603327,
      "grad_norm": 13.113646507263184,
      "learning_rate": 9.976540840264449e-06,
      "loss": 0.2235,
      "step": 2350
    },
    {
      "epoch": 1.5355086372360844,
      "grad_norm": 10.362279891967773,
      "learning_rate": 9.763275751759437e-06,
      "loss": 0.2482,
      "step": 2400
    },
    {
      "epoch": 1.5674984005118362,
      "grad_norm": 1.568915843963623,
      "learning_rate": 9.550010663254427e-06,
      "loss": 0.2622,
      "step": 2450
    },
    {
      "epoch": 1.599488163787588,
      "grad_norm": 10.095715522766113,
      "learning_rate": 9.336745574749414e-06,
      "loss": 0.2668,
      "step": 2500
    },
    {
      "epoch": 1.6314779270633397,
      "grad_norm": 12.999874114990234,
      "learning_rate": 9.123480486244403e-06,
      "loss": 0.2361,
      "step": 2550
    },
    {
      "epoch": 1.6634676903390915,
      "grad_norm": 7.512565612792969,
      "learning_rate": 8.910215397739392e-06,
      "loss": 0.2646,
      "step": 2600
    },
    {
      "epoch": 1.6954574536148432,
      "grad_norm": 6.645097732543945,
      "learning_rate": 8.696950309234378e-06,
      "loss": 0.2478,
      "step": 2650
    },
    {
      "epoch": 1.727447216890595,
      "grad_norm": 4.22629976272583,
      "learning_rate": 8.483685220729368e-06,
      "loss": 0.2686,
      "step": 2700
    },
    {
      "epoch": 1.7594369801663468,
      "grad_norm": 8.55104923248291,
      "learning_rate": 8.270420132224356e-06,
      "loss": 0.2615,
      "step": 2750
    },
    {
      "epoch": 1.7914267434420985,
      "grad_norm": 4.150308132171631,
      "learning_rate": 8.057155043719343e-06,
      "loss": 0.2669,
      "step": 2800
    },
    {
      "epoch": 1.8234165067178503,
      "grad_norm": 15.736576080322266,
      "learning_rate": 7.843889955214333e-06,
      "loss": 0.252,
      "step": 2850
    },
    {
      "epoch": 1.855406269993602,
      "grad_norm": 1.219308853149414,
      "learning_rate": 7.630624866709321e-06,
      "loss": 0.2619,
      "step": 2900
    },
    {
      "epoch": 1.8873960332693538,
      "grad_norm": 4.5792999267578125,
      "learning_rate": 7.4173597782043085e-06,
      "loss": 0.2516,
      "step": 2950
    },
    {
      "epoch": 1.9193857965451055,
      "grad_norm": 7.346240043640137,
      "learning_rate": 7.204094689699297e-06,
      "loss": 0.2374,
      "step": 3000
    },
    {
      "epoch": 1.9513755598208573,
      "grad_norm": 15.958673477172852,
      "learning_rate": 6.990829601194286e-06,
      "loss": 0.2568,
      "step": 3050
    },
    {
      "epoch": 1.983365323096609,
      "grad_norm": 8.143491744995117,
      "learning_rate": 6.777564512689273e-06,
      "loss": 0.2196,
      "step": 3100
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8902751119641714,
      "eval_f1": 0.8821468217693207,
      "eval_loss": 0.35885584354400635,
      "eval_runtime": 70.4611,
      "eval_samples_per_second": 44.365,
      "eval_steps_per_second": 2.782,
      "step": 3126
    },
    {
      "epoch": 2.015355086372361,
      "grad_norm": 2.4161245822906494,
      "learning_rate": 6.5642994241842614e-06,
      "loss": 0.211,
      "step": 3150
    },
    {
      "epoch": 2.0473448496481126,
      "grad_norm": 6.2580156326293945,
      "learning_rate": 6.3510343356792505e-06,
      "loss": 0.1819,
      "step": 3200
    },
    {
      "epoch": 2.0793346129238643,
      "grad_norm": 17.149974822998047,
      "learning_rate": 6.137769247174238e-06,
      "loss": 0.188,
      "step": 3250
    },
    {
      "epoch": 2.111324376199616,
      "grad_norm": 4.2034382820129395,
      "learning_rate": 5.924504158669226e-06,
      "loss": 0.1653,
      "step": 3300
    },
    {
      "epoch": 2.143314139475368,
      "grad_norm": 7.357328414916992,
      "learning_rate": 5.711239070164215e-06,
      "loss": 0.1748,
      "step": 3350
    },
    {
      "epoch": 2.1753039027511196,
      "grad_norm": 13.677566528320312,
      "learning_rate": 5.497973981659203e-06,
      "loss": 0.2177,
      "step": 3400
    },
    {
      "epoch": 2.2072936660268714,
      "grad_norm": 8.67300033569336,
      "learning_rate": 5.284708893154191e-06,
      "loss": 0.1571,
      "step": 3450
    },
    {
      "epoch": 2.239283429302623,
      "grad_norm": 22.893770217895508,
      "learning_rate": 5.07144380464918e-06,
      "loss": 0.2009,
      "step": 3500
    },
    {
      "epoch": 2.271273192578375,
      "grad_norm": 3.602328300476074,
      "learning_rate": 4.858178716144167e-06,
      "loss": 0.1329,
      "step": 3550
    },
    {
      "epoch": 2.3032629558541267,
      "grad_norm": 18.8084659576416,
      "learning_rate": 4.644913627639156e-06,
      "loss": 0.1814,
      "step": 3600
    },
    {
      "epoch": 2.3352527191298784,
      "grad_norm": 0.4535435736179352,
      "learning_rate": 4.431648539134144e-06,
      "loss": 0.2069,
      "step": 3650
    },
    {
      "epoch": 2.36724248240563,
      "grad_norm": 11.971237182617188,
      "learning_rate": 4.218383450629132e-06,
      "loss": 0.188,
      "step": 3700
    },
    {
      "epoch": 2.399232245681382,
      "grad_norm": 5.598160266876221,
      "learning_rate": 4.005118362124121e-06,
      "loss": 0.1943,
      "step": 3750
    },
    {
      "epoch": 2.4312220089571337,
      "grad_norm": 11.97499942779541,
      "learning_rate": 3.791853273619109e-06,
      "loss": 0.2155,
      "step": 3800
    },
    {
      "epoch": 2.4632117722328855,
      "grad_norm": 9.149175643920898,
      "learning_rate": 3.5785881851140968e-06,
      "loss": 0.2025,
      "step": 3850
    },
    {
      "epoch": 2.495201535508637,
      "grad_norm": 7.965933799743652,
      "learning_rate": 3.3653230966090854e-06,
      "loss": 0.2121,
      "step": 3900
    },
    {
      "epoch": 2.527191298784389,
      "grad_norm": 9.397235870361328,
      "learning_rate": 3.1520580081040737e-06,
      "loss": 0.1724,
      "step": 3950
    },
    {
      "epoch": 2.5591810620601407,
      "grad_norm": 14.580031394958496,
      "learning_rate": 2.9387929195990615e-06,
      "loss": 0.1636,
      "step": 4000
    },
    {
      "epoch": 2.5911708253358925,
      "grad_norm": 2.2896785736083984,
      "learning_rate": 2.72552783109405e-06,
      "loss": 0.1603,
      "step": 4050
    },
    {
      "epoch": 2.6231605886116443,
      "grad_norm": 22.936344146728516,
      "learning_rate": 2.5122627425890384e-06,
      "loss": 0.1944,
      "step": 4100
    },
    {
      "epoch": 2.655150351887396,
      "grad_norm": 37.436187744140625,
      "learning_rate": 2.2989976540840266e-06,
      "loss": 0.2059,
      "step": 4150
    },
    {
      "epoch": 2.6871401151631478,
      "grad_norm": 26.6770076751709,
      "learning_rate": 2.085732565579015e-06,
      "loss": 0.1448,
      "step": 4200
    },
    {
      "epoch": 2.7191298784388995,
      "grad_norm": 20.561311721801758,
      "learning_rate": 1.872467477074003e-06,
      "loss": 0.2094,
      "step": 4250
    },
    {
      "epoch": 2.7511196417146513,
      "grad_norm": 4.114218711853027,
      "learning_rate": 1.6592023885689915e-06,
      "loss": 0.1682,
      "step": 4300
    },
    {
      "epoch": 2.783109404990403,
      "grad_norm": 27.9166202545166,
      "learning_rate": 1.4459373000639796e-06,
      "loss": 0.1931,
      "step": 4350
    },
    {
      "epoch": 2.815099168266155,
      "grad_norm": 13.576592445373535,
      "learning_rate": 1.2326722115589678e-06,
      "loss": 0.1989,
      "step": 4400
    },
    {
      "epoch": 2.8470889315419066,
      "grad_norm": 4.428896427154541,
      "learning_rate": 1.019407123053956e-06,
      "loss": 0.18,
      "step": 4450
    },
    {
      "epoch": 2.8790786948176583,
      "grad_norm": 10.087977409362793,
      "learning_rate": 8.061420345489445e-07,
      "loss": 0.2102,
      "step": 4500
    },
    {
      "epoch": 2.91106845809341,
      "grad_norm": 16.517681121826172,
      "learning_rate": 5.928769460439326e-07,
      "loss": 0.1662,
      "step": 4550
    },
    {
      "epoch": 2.943058221369162,
      "grad_norm": 15.329133987426758,
      "learning_rate": 3.796118575389209e-07,
      "loss": 0.1997,
      "step": 4600
    },
    {
      "epoch": 2.9750479846449136,
      "grad_norm": 18.751319885253906,
      "learning_rate": 1.6634676903390917e-07,
      "loss": 0.1924,
      "step": 4650
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9008317338451696,
      "eval_f1": 0.892446816336566,
      "eval_loss": 0.3720133900642395,
      "eval_runtime": 71.8708,
      "eval_samples_per_second": 43.495,
      "eval_steps_per_second": 2.727,
      "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": 837402132857850.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}