{
  "best_metric": 0.013810121454298496,
  "best_model_checkpoint": "./results/answerdotai/ModernBERT-base/trial-9/checkpoint-3012",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 3012,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.033200531208499334,
      "grad_norm": 3.6277902126312256,
      "learning_rate": 4.223876761987849e-05,
      "loss": 0.2681,
      "step": 50
    },
    {
      "epoch": 0.06640106241699867,
      "grad_norm": 0.3113747537136078,
      "learning_rate": 4.2037477267134116e-05,
      "loss": 0.0958,
      "step": 100
    },
    {
      "epoch": 0.099601593625498,
      "grad_norm": 0.18985196948051453,
      "learning_rate": 4.183618691438975e-05,
      "loss": 0.0636,
      "step": 150
    },
    {
      "epoch": 0.13280212483399734,
      "grad_norm": 0.8797281980514526,
      "learning_rate": 4.163489656164538e-05,
      "loss": 0.0562,
      "step": 200
    },
    {
      "epoch": 0.16600265604249667,
      "grad_norm": 1.9831819534301758,
      "learning_rate": 4.143360620890101e-05,
      "loss": 0.047,
      "step": 250
    },
    {
      "epoch": 0.199203187250996,
      "grad_norm": 3.341094732284546,
      "learning_rate": 4.123231585615664e-05,
      "loss": 0.0346,
      "step": 300
    },
    {
      "epoch": 0.23240371845949534,
      "grad_norm": 0.048162225633859634,
      "learning_rate": 4.103102550341227e-05,
      "loss": 0.0457,
      "step": 350
    },
    {
      "epoch": 0.2656042496679947,
      "grad_norm": 0.0644642785191536,
      "learning_rate": 4.08297351506679e-05,
      "loss": 0.0391,
      "step": 400
    },
    {
      "epoch": 0.29880478087649404,
      "grad_norm": 6.679907321929932,
      "learning_rate": 4.0628444797923535e-05,
      "loss": 0.0346,
      "step": 450
    },
    {
      "epoch": 0.33200531208499334,
      "grad_norm": 0.01181253232061863,
      "learning_rate": 4.0427154445179164e-05,
      "loss": 0.0103,
      "step": 500
    },
    {
      "epoch": 0.3652058432934927,
      "grad_norm": 0.06453288346529007,
      "learning_rate": 4.022586409243479e-05,
      "loss": 0.0292,
      "step": 550
    },
    {
      "epoch": 0.398406374501992,
      "grad_norm": 0.011014764197170734,
      "learning_rate": 4.002457373969042e-05,
      "loss": 0.0101,
      "step": 600
    },
    {
      "epoch": 0.4316069057104914,
      "grad_norm": 0.44575539231300354,
      "learning_rate": 3.982328338694605e-05,
      "loss": 0.0187,
      "step": 650
    },
    {
      "epoch": 0.4648074369189907,
      "grad_norm": 0.27992862462997437,
      "learning_rate": 3.962199303420168e-05,
      "loss": 0.0196,
      "step": 700
    },
    {
      "epoch": 0.49800796812749004,
      "grad_norm": 0.003195864148437977,
      "learning_rate": 3.942070268145732e-05,
      "loss": 0.0266,
      "step": 750
    },
    {
      "epoch": 0.5312084993359893,
      "grad_norm": 5.236836910247803,
      "learning_rate": 3.921941232871295e-05,
      "loss": 0.0128,
      "step": 800
    },
    {
      "epoch": 0.5644090305444888,
      "grad_norm": 0.6897503137588501,
      "learning_rate": 3.9018121975968576e-05,
      "loss": 0.0163,
      "step": 850
    },
    {
      "epoch": 0.5976095617529881,
      "grad_norm": 0.07702745497226715,
      "learning_rate": 3.881683162322421e-05,
      "loss": 0.0196,
      "step": 900
    },
    {
      "epoch": 0.6308100929614874,
      "grad_norm": 0.00853784941136837,
      "learning_rate": 3.8615541270479835e-05,
      "loss": 0.0207,
      "step": 950
    },
    {
      "epoch": 0.6640106241699867,
      "grad_norm": 0.1736297905445099,
      "learning_rate": 3.841425091773547e-05,
      "loss": 0.0219,
      "step": 1000
    },
    {
      "epoch": 0.6972111553784861,
      "grad_norm": 0.07749740034341812,
      "learning_rate": 3.82129605649911e-05,
      "loss": 0.0158,
      "step": 1050
    },
    {
      "epoch": 0.7304116865869854,
      "grad_norm": 0.0033312628511339426,
      "learning_rate": 3.801167021224673e-05,
      "loss": 0.0133,
      "step": 1100
    },
    {
      "epoch": 0.7636122177954847,
      "grad_norm": 0.003007786348462105,
      "learning_rate": 3.781037985950236e-05,
      "loss": 0.0143,
      "step": 1150
    },
    {
      "epoch": 0.796812749003984,
      "grad_norm": 3.926494598388672,
      "learning_rate": 3.760908950675799e-05,
      "loss": 0.0113,
      "step": 1200
    },
    {
      "epoch": 0.8300132802124834,
      "grad_norm": 0.0027299339417368174,
      "learning_rate": 3.740779915401362e-05,
      "loss": 0.0013,
      "step": 1250
    },
    {
      "epoch": 0.8632138114209827,
      "grad_norm": 0.013163665309548378,
      "learning_rate": 3.7206508801269253e-05,
      "loss": 0.0109,
      "step": 1300
    },
    {
      "epoch": 0.896414342629482,
      "grad_norm": 0.0006267031421884894,
      "learning_rate": 3.700521844852488e-05,
      "loss": 0.0034,
      "step": 1350
    },
    {
      "epoch": 0.9296148738379814,
      "grad_norm": 0.00010993422620231286,
      "learning_rate": 3.680392809578051e-05,
      "loss": 0.0013,
      "step": 1400
    },
    {
      "epoch": 0.9628154050464808,
      "grad_norm": 1.569828987121582,
      "learning_rate": 3.660263774303614e-05,
      "loss": 0.0077,
      "step": 1450
    },
    {
      "epoch": 0.9960159362549801,
      "grad_norm": 0.01317554246634245,
      "learning_rate": 3.640134739029177e-05,
      "loss": 0.0144,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9965410305343512,
      "eval_f1": 0.9965177127714778,
      "eval_loss": 0.025706786662340164,
      "eval_precision": 0.9965095878718089,
      "eval_recall": 0.9965410305343512,
      "eval_runtime": 31.4201,
      "eval_samples_per_second": 266.836,
      "eval_steps_per_second": 8.339,
      "step": 1506
    },
    {
      "epoch": 1.0292164674634794,
      "grad_norm": 0.40110042691230774,
      "learning_rate": 3.620005703754741e-05,
      "loss": 0.0002,
      "step": 1550
    },
    {
      "epoch": 1.0624169986719787,
      "grad_norm": 0.0003720091190189123,
      "learning_rate": 3.5998766684803036e-05,
      "loss": 0.0035,
      "step": 1600
    },
    {
      "epoch": 1.095617529880478,
      "grad_norm": 0.0027410192415118217,
      "learning_rate": 3.5797476332058666e-05,
      "loss": 0.0122,
      "step": 1650
    },
    {
      "epoch": 1.1288180610889773,
      "grad_norm": 0.010054959915578365,
      "learning_rate": 3.5596185979314295e-05,
      "loss": 0.0034,
      "step": 1700
    },
    {
      "epoch": 1.1620185922974768,
      "grad_norm": 0.013796687126159668,
      "learning_rate": 3.539489562656993e-05,
      "loss": 0.0067,
      "step": 1750
    },
    {
      "epoch": 1.1952191235059761,
      "grad_norm": 1.8211485147476196,
      "learning_rate": 3.5193605273825553e-05,
      "loss": 0.006,
      "step": 1800
    },
    {
      "epoch": 1.2284196547144755,
      "grad_norm": 0.016155727207660675,
      "learning_rate": 3.499231492108119e-05,
      "loss": 0.0002,
      "step": 1850
    },
    {
      "epoch": 1.2616201859229748,
      "grad_norm": 0.003053726628422737,
      "learning_rate": 3.479102456833682e-05,
      "loss": 0.0071,
      "step": 1900
    },
    {
      "epoch": 1.294820717131474,
      "grad_norm": 0.0003582706267479807,
      "learning_rate": 3.458973421559245e-05,
      "loss": 0.0001,
      "step": 1950
    },
    {
      "epoch": 1.3280212483399734,
      "grad_norm": 0.03127170354127884,
      "learning_rate": 3.438844386284808e-05,
      "loss": 0.0071,
      "step": 2000
    },
    {
      "epoch": 1.361221779548473,
      "grad_norm": 0.0018665710231289268,
      "learning_rate": 3.418715351010371e-05,
      "loss": 0.0112,
      "step": 2050
    },
    {
      "epoch": 1.3944223107569722,
      "grad_norm": 0.05576420947909355,
      "learning_rate": 3.3985863157359336e-05,
      "loss": 0.0071,
      "step": 2100
    },
    {
      "epoch": 1.4276228419654715,
      "grad_norm": 4.577602863311768,
      "learning_rate": 3.378457280461497e-05,
      "loss": 0.0114,
      "step": 2150
    },
    {
      "epoch": 1.4608233731739708,
      "grad_norm": 0.00251931045204401,
      "learning_rate": 3.35832824518706e-05,
      "loss": 0.0136,
      "step": 2200
    },
    {
      "epoch": 1.4940239043824701,
      "grad_norm": 0.00033850205363705754,
      "learning_rate": 3.338199209912623e-05,
      "loss": 0.001,
      "step": 2250
    },
    {
      "epoch": 1.5272244355909694,
      "grad_norm": 0.0019836120773106813,
      "learning_rate": 3.318070174638187e-05,
      "loss": 0.0001,
      "step": 2300
    },
    {
      "epoch": 1.5604249667994687,
      "grad_norm": 0.00020935946668032557,
      "learning_rate": 3.297941139363749e-05,
      "loss": 0.0,
      "step": 2350
    },
    {
      "epoch": 1.593625498007968,
      "grad_norm": 0.000308250222587958,
      "learning_rate": 3.2778121040893126e-05,
      "loss": 0.0001,
      "step": 2400
    },
    {
      "epoch": 1.6268260292164674,
      "grad_norm": 0.020645378157496452,
      "learning_rate": 3.2576830688148755e-05,
      "loss": 0.0092,
      "step": 2450
    },
    {
      "epoch": 1.6600265604249667,
      "grad_norm": 0.000331960734911263,
      "learning_rate": 3.2375540335404384e-05,
      "loss": 0.004,
      "step": 2500
    },
    {
      "epoch": 1.6932270916334662,
      "grad_norm": 0.0023610808420926332,
      "learning_rate": 3.2174249982660014e-05,
      "loss": 0.0062,
      "step": 2550
    },
    {
      "epoch": 1.7264276228419655,
      "grad_norm": 0.0006301538087427616,
      "learning_rate": 3.197295962991565e-05,
      "loss": 0.0023,
      "step": 2600
    },
    {
      "epoch": 1.7596281540504648,
      "grad_norm": 0.00027294279425404966,
      "learning_rate": 3.177166927717127e-05,
      "loss": 0.0078,
      "step": 2650
    },
    {
      "epoch": 1.792828685258964,
      "grad_norm": 0.012537718750536442,
      "learning_rate": 3.157037892442691e-05,
      "loss": 0.0069,
      "step": 2700
    },
    {
      "epoch": 1.8260292164674636,
      "grad_norm": 0.0029420643113553524,
      "learning_rate": 3.136908857168254e-05,
      "loss": 0.0086,
      "step": 2750
    },
    {
      "epoch": 1.859229747675963,
      "grad_norm": 0.023261522874236107,
      "learning_rate": 3.116779821893817e-05,
      "loss": 0.0099,
      "step": 2800
    },
    {
      "epoch": 1.8924302788844622,
      "grad_norm": 0.0013812623219564557,
      "learning_rate": 3.0966507866193796e-05,
      "loss": 0.007,
      "step": 2850
    },
    {
      "epoch": 1.9256308100929616,
      "grad_norm": 0.0014662343310192227,
      "learning_rate": 3.0765217513449426e-05,
      "loss": 0.0013,
      "step": 2900
    },
    {
      "epoch": 1.9588313413014609,
      "grad_norm": 0.014669010415673256,
      "learning_rate": 3.0563927160705055e-05,
      "loss": 0.0134,
      "step": 2950
    },
    {
      "epoch": 1.9920318725099602,
      "grad_norm": 0.014950312674045563,
      "learning_rate": 3.036263680796069e-05,
      "loss": 0.0061,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9977337786259542,
      "eval_f1": 0.9977150455912147,
      "eval_loss": 0.013810121454298496,
      "eval_precision": 0.9977195036627051,
      "eval_recall": 0.9977337786259542,
      "eval_runtime": 31.5085,
      "eval_samples_per_second": 266.087,
      "eval_steps_per_second": 8.315,
      "step": 3012
    }
  ],
  "logging_steps": 50,
  "max_steps": 10542,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 3.282861088518144e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}