{
  "best_global_step": 2994,
  "best_metric": 0.8489208633093526,
  "best_model_checkpoint": "./electra-small-heading-classifier-expanded\\checkpoint-2994",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 2994,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.033400133600534405,
      "grad_norm": 1.82759428024292,
      "learning_rate": 2.45e-05,
      "loss": 0.5801,
      "step": 50
    },
    {
      "epoch": 0.06680026720106881,
      "grad_norm": 0.7336680293083191,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 0.3191,
      "step": 100
    },
    {
      "epoch": 0.10020040080160321,
      "grad_norm": 0.759293258190155,
      "learning_rate": 4.9583899456521745e-05,
      "loss": 0.2216,
      "step": 150
    },
    {
      "epoch": 0.13360053440213762,
      "grad_norm": 0.5498169660568237,
      "learning_rate": 4.915930706521739e-05,
      "loss": 0.2167,
      "step": 200
    },
    {
      "epoch": 0.16700066800267202,
      "grad_norm": 3.572784662246704,
      "learning_rate": 4.8734714673913044e-05,
      "loss": 0.1797,
      "step": 250
    },
    {
      "epoch": 0.20040080160320642,
      "grad_norm": 1.3190865516662598,
      "learning_rate": 4.83101222826087e-05,
      "loss": 0.2202,
      "step": 300
    },
    {
      "epoch": 0.23380093520374082,
      "grad_norm": 1.5133466720581055,
      "learning_rate": 4.788552989130435e-05,
      "loss": 0.1925,
      "step": 350
    },
    {
      "epoch": 0.26720106880427524,
      "grad_norm": 1.3208128213882446,
      "learning_rate": 4.7460937500000004e-05,
      "loss": 0.265,
      "step": 400
    },
    {
      "epoch": 0.30060120240480964,
      "grad_norm": 0.9725052118301392,
      "learning_rate": 4.703634510869566e-05,
      "loss": 0.2866,
      "step": 450
    },
    {
      "epoch": 0.33400133600534404,
      "grad_norm": 1.570516586303711,
      "learning_rate": 4.6611752717391304e-05,
      "loss": 0.1881,
      "step": 500
    },
    {
      "epoch": 0.36740146960587844,
      "grad_norm": 4.067606449127197,
      "learning_rate": 4.618716032608696e-05,
      "loss": 0.2258,
      "step": 550
    },
    {
      "epoch": 0.40080160320641284,
      "grad_norm": 0.2925869822502136,
      "learning_rate": 4.576256793478261e-05,
      "loss": 0.1488,
      "step": 600
    },
    {
      "epoch": 0.43420173680694724,
      "grad_norm": 0.9354973435401917,
      "learning_rate": 4.5337975543478264e-05,
      "loss": 0.1611,
      "step": 650
    },
    {
      "epoch": 0.46760187040748163,
      "grad_norm": 0.3285213112831116,
      "learning_rate": 4.491338315217392e-05,
      "loss": 0.1259,
      "step": 700
    },
    {
      "epoch": 0.501002004008016,
      "grad_norm": 13.97227954864502,
      "learning_rate": 4.448879076086957e-05,
      "loss": 0.1593,
      "step": 750
    },
    {
      "epoch": 0.5344021376085505,
      "grad_norm": 0.10469996929168701,
      "learning_rate": 4.406419836956522e-05,
      "loss": 0.0923,
      "step": 800
    },
    {
      "epoch": 0.5678022712090849,
      "grad_norm": 0.19770751893520355,
      "learning_rate": 4.363960597826087e-05,
      "loss": 0.1067,
      "step": 850
    },
    {
      "epoch": 0.6012024048096193,
      "grad_norm": 0.10104553401470184,
      "learning_rate": 4.321501358695652e-05,
      "loss": 0.1214,
      "step": 900
    },
    {
      "epoch": 0.6346025384101537,
      "grad_norm": 0.10949808359146118,
      "learning_rate": 4.279042119565218e-05,
      "loss": 0.1175,
      "step": 950
    },
    {
      "epoch": 0.6680026720106881,
      "grad_norm": 0.10336494445800781,
      "learning_rate": 4.236582880434783e-05,
      "loss": 0.0849,
      "step": 1000
    },
    {
      "epoch": 0.7014028056112225,
      "grad_norm": 0.12163177132606506,
      "learning_rate": 4.1941236413043476e-05,
      "loss": 0.1486,
      "step": 1050
    },
    {
      "epoch": 0.7348029392117569,
      "grad_norm": 0.0906616598367691,
      "learning_rate": 4.151664402173913e-05,
      "loss": 0.0671,
      "step": 1100
    },
    {
      "epoch": 0.7682030728122913,
      "grad_norm": 0.12954840064048767,
      "learning_rate": 4.109205163043478e-05,
      "loss": 0.072,
      "step": 1150
    },
    {
      "epoch": 0.8016032064128257,
      "grad_norm": 0.06860172003507614,
      "learning_rate": 4.0667459239130436e-05,
      "loss": 0.0735,
      "step": 1200
    },
    {
      "epoch": 0.8350033400133601,
      "grad_norm": 0.06437909603118896,
      "learning_rate": 4.024286684782609e-05,
      "loss": 0.16,
      "step": 1250
    },
    {
      "epoch": 0.8684034736138945,
      "grad_norm": 3.2551543712615967,
      "learning_rate": 3.981827445652174e-05,
      "loss": 0.0868,
      "step": 1300
    },
    {
      "epoch": 0.9018036072144289,
      "grad_norm": 0.12183782458305359,
      "learning_rate": 3.939368206521739e-05,
      "loss": 0.1346,
      "step": 1350
    },
    {
      "epoch": 0.9352037408149633,
      "grad_norm": 5.742549419403076,
      "learning_rate": 3.896908967391304e-05,
      "loss": 0.0977,
      "step": 1400
    },
    {
      "epoch": 0.9686038744154977,
      "grad_norm": 0.049525078386068344,
      "learning_rate": 3.85444972826087e-05,
      "loss": 0.0771,
      "step": 1450
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9777567439659253,
      "eval_f1": 0.7813953488372093,
      "eval_loss": 0.07437803596258163,
      "eval_runtime": 8.1317,
      "eval_samples_per_second": 259.846,
      "eval_steps_per_second": 32.588,
      "step": 1497
    },
    {
      "epoch": 1.002004008016032,
      "grad_norm": 0.08354274183511734,
      "learning_rate": 3.811990489130435e-05,
      "loss": 0.1122,
      "step": 1500
    },
    {
      "epoch": 1.0354041416165665,
      "grad_norm": 0.07657646387815475,
      "learning_rate": 3.76953125e-05,
      "loss": 0.0776,
      "step": 1550
    },
    {
      "epoch": 1.0688042752171008,
      "grad_norm": 0.029183173552155495,
      "learning_rate": 3.7270720108695656e-05,
      "loss": 0.048,
      "step": 1600
    },
    {
      "epoch": 1.1022044088176353,
      "grad_norm": 0.6650001406669617,
      "learning_rate": 3.68461277173913e-05,
      "loss": 0.0651,
      "step": 1650
    },
    {
      "epoch": 1.1356045424181698,
      "grad_norm": 0.13291126489639282,
      "learning_rate": 3.6421535326086955e-05,
      "loss": 0.1035,
      "step": 1700
    },
    {
      "epoch": 1.169004676018704,
      "grad_norm": 0.14512984454631805,
      "learning_rate": 3.5996942934782615e-05,
      "loss": 0.0896,
      "step": 1750
    },
    {
      "epoch": 1.2024048096192386,
      "grad_norm": 0.09467575699090958,
      "learning_rate": 3.557235054347826e-05,
      "loss": 0.0763,
      "step": 1800
    },
    {
      "epoch": 1.2358049432197729,
      "grad_norm": 0.5623799562454224,
      "learning_rate": 3.5147758152173915e-05,
      "loss": 0.059,
      "step": 1850
    },
    {
      "epoch": 1.2692050768203074,
      "grad_norm": 0.16416147351264954,
      "learning_rate": 3.472316576086957e-05,
      "loss": 0.0483,
      "step": 1900
    },
    {
      "epoch": 1.3026052104208417,
      "grad_norm": 3.0964038372039795,
      "learning_rate": 3.4298573369565215e-05,
      "loss": 0.1058,
      "step": 1950
    },
    {
      "epoch": 1.3360053440213762,
      "grad_norm": 0.030443737283349037,
      "learning_rate": 3.3873980978260875e-05,
      "loss": 0.0517,
      "step": 2000
    },
    {
      "epoch": 1.3694054776219104,
      "grad_norm": 0.04263285547494888,
      "learning_rate": 3.344938858695653e-05,
      "loss": 0.0486,
      "step": 2050
    },
    {
      "epoch": 1.402805611222445,
      "grad_norm": 0.06713565438985825,
      "learning_rate": 3.3024796195652175e-05,
      "loss": 0.0494,
      "step": 2100
    },
    {
      "epoch": 1.4362057448229792,
      "grad_norm": 0.04323391616344452,
      "learning_rate": 3.260020380434783e-05,
      "loss": 0.0518,
      "step": 2150
    },
    {
      "epoch": 1.4696058784235138,
      "grad_norm": 0.9192191362380981,
      "learning_rate": 3.2175611413043474e-05,
      "loss": 0.0498,
      "step": 2200
    },
    {
      "epoch": 1.503006012024048,
      "grad_norm": 0.08719488233327866,
      "learning_rate": 3.1751019021739135e-05,
      "loss": 0.1155,
      "step": 2250
    },
    {
      "epoch": 1.5364061456245826,
      "grad_norm": 6.060549259185791,
      "learning_rate": 3.132642663043479e-05,
      "loss": 0.1349,
      "step": 2300
    },
    {
      "epoch": 1.569806279225117,
      "grad_norm": 0.09453130513429642,
      "learning_rate": 3.0901834239130434e-05,
      "loss": 0.0639,
      "step": 2350
    },
    {
      "epoch": 1.6032064128256514,
      "grad_norm": 0.02592223510146141,
      "learning_rate": 3.0477241847826088e-05,
      "loss": 0.0929,
      "step": 2400
    },
    {
      "epoch": 1.6366065464261856,
      "grad_norm": 0.027360519394278526,
      "learning_rate": 3.005264945652174e-05,
      "loss": 0.071,
      "step": 2450
    },
    {
      "epoch": 1.6700066800267201,
      "grad_norm": 0.14285916090011597,
      "learning_rate": 2.962805706521739e-05,
      "loss": 0.0768,
      "step": 2500
    },
    {
      "epoch": 1.7034068136272547,
      "grad_norm": 0.04874153807759285,
      "learning_rate": 2.9203464673913044e-05,
      "loss": 0.076,
      "step": 2550
    },
    {
      "epoch": 1.736806947227789,
      "grad_norm": 0.09328486025333405,
      "learning_rate": 2.8778872282608697e-05,
      "loss": 0.0505,
      "step": 2600
    },
    {
      "epoch": 1.7702070808283232,
      "grad_norm": 0.34670591354370117,
      "learning_rate": 2.8354279891304347e-05,
      "loss": 0.0763,
      "step": 2650
    },
    {
      "epoch": 1.8036072144288577,
      "grad_norm": 0.057789236307144165,
      "learning_rate": 2.79296875e-05,
      "loss": 0.0832,
      "step": 2700
    },
    {
      "epoch": 1.8370073480293923,
      "grad_norm": 0.059989944100379944,
      "learning_rate": 2.7505095108695657e-05,
      "loss": 0.062,
      "step": 2750
    },
    {
      "epoch": 1.8704074816299265,
      "grad_norm": 0.02221057377755642,
      "learning_rate": 2.7080502717391304e-05,
      "loss": 0.0649,
      "step": 2800
    },
    {
      "epoch": 1.9038076152304608,
      "grad_norm": 0.154799684882164,
      "learning_rate": 2.6655910326086957e-05,
      "loss": 0.144,
      "step": 2850
    },
    {
      "epoch": 1.9372077488309953,
      "grad_norm": 0.0422816276550293,
      "learning_rate": 2.6231317934782613e-05,
      "loss": 0.0531,
      "step": 2900
    },
    {
      "epoch": 1.9706078824315298,
      "grad_norm": 0.019839206710457802,
      "learning_rate": 2.580672554347826e-05,
      "loss": 0.0545,
      "step": 2950
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9801230477993375,
      "eval_f1": 0.8489208633093526,
      "eval_loss": 0.07019170373678207,
      "eval_runtime": 8.2123,
      "eval_samples_per_second": 257.298,
      "eval_steps_per_second": 32.269,
      "step": 2994
    }
  ],
  "logging_steps": 50,
  "max_steps": 5988,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 704423880081408.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}