{
  "best_global_step": 2000,
  "best_metric": 0.9721,
  "best_model_checkpoint": "./sifta-fakenews-xlmr/checkpoint-2000",
  "epoch": 2.7624309392265194,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07892659826361484,
      "grad_norm": 7.519743919372559,
      "learning_rate": 3.1230283911671926e-06,
      "loss": 1.3593978881835938,
      "step": 100
    },
    {
      "epoch": 0.15785319652722968,
      "grad_norm": 44.37847137451172,
      "learning_rate": 6.2776025236593065e-06,
      "loss": 0.6375294876098633,
      "step": 200
    },
    {
      "epoch": 0.23677979479084452,
      "grad_norm": 3.3530941009521484,
      "learning_rate": 9.43217665615142e-06,
      "loss": 0.3285886001586914,
      "step": 300
    },
    {
      "epoch": 0.31570639305445936,
      "grad_norm": 4.9190993309021,
      "learning_rate": 1.2586750788643533e-05,
      "loss": 0.31189311981201173,
      "step": 400
    },
    {
      "epoch": 0.39463299131807417,
      "grad_norm": 13.304952621459961,
      "learning_rate": 1.574132492113565e-05,
      "loss": 0.28032915115356444,
      "step": 500
    },
    {
      "epoch": 0.39463299131807417,
      "eval_accuracy": 0.9513,
      "eval_f1": 0.951,
      "eval_loss": 0.11800144612789154,
      "eval_runtime": 17.0078,
      "eval_samples_per_second": 297.922,
      "eval_steps_per_second": 9.349,
      "step": 500
    },
    {
      "epoch": 0.47355958958168903,
      "grad_norm": 69.24589538574219,
      "learning_rate": 1.889589905362776e-05,
      "loss": 0.23949861526489258,
      "step": 600
    },
    {
      "epoch": 0.5524861878453039,
      "grad_norm": 77.79669952392578,
      "learning_rate": 1.9993585719507573e-05,
      "loss": 0.26106679916381836,
      "step": 700
    },
    {
      "epoch": 0.6314127861089187,
      "grad_norm": 9.278132438659668,
      "learning_rate": 1.9958691794328414e-05,
      "loss": 0.26748144149780273,
      "step": 800
    },
    {
      "epoch": 0.7103393843725335,
      "grad_norm": 10.259608268737793,
      "learning_rate": 1.9893564256008604e-05,
      "loss": 0.2700900650024414,
      "step": 900
    },
    {
      "epoch": 0.7892659826361483,
      "grad_norm": 1.331714153289795,
      "learning_rate": 1.9798400825377246e-05,
      "loss": 0.23025428771972656,
      "step": 1000
    },
    {
      "epoch": 0.7892659826361483,
      "eval_accuracy": 0.9637,
      "eval_f1": 0.9636,
      "eval_loss": 0.11573408544063568,
      "eval_runtime": 16.2817,
      "eval_samples_per_second": 311.209,
      "eval_steps_per_second": 9.766,
      "step": 1000
    },
    {
      "epoch": 0.8681925808997633,
      "grad_norm": 0.1167285144329071,
      "learning_rate": 1.9673490409291412e-05,
      "loss": 0.22350259780883788,
      "step": 1100
    },
    {
      "epoch": 0.9471191791633781,
      "grad_norm": 21.29085922241211,
      "learning_rate": 1.9519212223543213e-05,
      "loss": 0.24957496643066407,
      "step": 1200
    },
    {
      "epoch": 1.0260457774269929,
      "grad_norm": 6.630244731903076,
      "learning_rate": 1.933603464159779e-05,
      "loss": 0.2235790252685547,
      "step": 1300
    },
    {
      "epoch": 1.1049723756906078,
      "grad_norm": 3.18111252784729,
      "learning_rate": 1.912451377265733e-05,
      "loss": 0.17377975463867187,
      "step": 1400
    },
    {
      "epoch": 1.1838989739542225,
      "grad_norm": 1.588996410369873,
      "learning_rate": 1.888529177336798e-05,
      "loss": 0.18398305892944336,
      "step": 1500
    },
    {
      "epoch": 1.1838989739542225,
      "eval_accuracy": 0.9692,
      "eval_f1": 0.9691,
      "eval_loss": 0.08150316029787064,
      "eval_runtime": 16.4485,
      "eval_samples_per_second": 308.053,
      "eval_steps_per_second": 9.667,
      "step": 1500
    },
    {
      "epoch": 1.2628255722178374,
      "grad_norm": 2.542539119720459,
      "learning_rate": 1.861909489829517e-05,
      "loss": 0.20040679931640626,
      "step": 1600
    },
    {
      "epoch": 1.3417521704814521,
      "grad_norm": 1.4010111093521118,
      "learning_rate": 1.8326731295085838e-05,
      "loss": 0.1535040855407715,
      "step": 1700
    },
    {
      "epoch": 1.420678768745067,
      "grad_norm": 2.9616997241973877,
      "learning_rate": 1.800908855101132e-05,
      "loss": 0.1694472312927246,
      "step": 1800
    },
    {
      "epoch": 1.499605367008682,
      "grad_norm": 8.78850269317627,
      "learning_rate": 1.766713099833931e-05,
      "loss": 0.18262014389038086,
      "step": 1900
    },
    {
      "epoch": 1.5785319652722967,
      "grad_norm": 5.830899715423584,
      "learning_rate": 1.730189678671552e-05,
      "loss": 0.15452383995056151,
      "step": 2000
    },
    {
      "epoch": 1.5785319652722967,
      "eval_accuracy": 0.9722,
      "eval_f1": 0.9721,
      "eval_loss": 0.08517046272754669,
      "eval_runtime": 17.0389,
      "eval_samples_per_second": 297.379,
      "eval_steps_per_second": 9.332,
      "step": 2000
    },
    {
      "epoch": 1.6574585635359116,
      "grad_norm": 14.781915664672852,
      "learning_rate": 1.6914494731443005e-05,
      "loss": 0.17684141159057618,
      "step": 2100
    },
    {
      "epoch": 1.7363851617995265,
      "grad_norm": 14.542154312133789,
      "learning_rate": 1.6506100947227483e-05,
      "loss": 0.16984281539916993,
      "step": 2200
    },
    {
      "epoch": 1.8153117600631412,
      "grad_norm": 2.6693317890167236,
      "learning_rate": 1.607795527760824e-05,
      "loss": 0.16369407653808593,
      "step": 2300
    },
    {
      "epoch": 1.8942383583267561,
      "grad_norm": 35.68703842163086,
      "learning_rate": 1.5631357530914576e-05,
      "loss": 0.16996910095214843,
      "step": 2400
    },
    {
      "epoch": 1.973164956590371,
      "grad_norm": 8.133594512939453,
      "learning_rate": 1.5167663534174963e-05,
      "loss": 0.17478582382202149,
      "step": 2500
    },
    {
      "epoch": 1.973164956590371,
      "eval_accuracy": 0.9722,
      "eval_f1": 0.9721,
      "eval_loss": 0.07743066549301147,
      "eval_runtime": 17.1006,
      "eval_samples_per_second": 296.305,
      "eval_steps_per_second": 9.298,
      "step": 2500
    },
    {
      "epoch": 2.0520915548539858,
      "grad_norm": 3.4671425819396973,
      "learning_rate": 1.468828101695897e-05,
      "loss": 0.14399107933044433,
      "step": 2600
    },
    {
      "epoch": 2.1310181531176005,
      "grad_norm": 29.677196502685547,
      "learning_rate": 1.4194665337648121e-05,
      "loss": 0.15213555335998535,
      "step": 2700
    },
    {
      "epoch": 2.2099447513812156,
      "grad_norm": 7.875465393066406,
      "learning_rate": 1.368831506511036e-05,
      "loss": 0.14315860748291015,
      "step": 2800
    },
    {
      "epoch": 2.2888713496448303,
      "grad_norm": 20.07367706298828,
      "learning_rate": 1.3170767429191709e-05,
      "loss": 0.13439299583435058,
      "step": 2900
    },
    {
      "epoch": 2.367797947908445,
      "grad_norm": 0.5996111631393433,
      "learning_rate": 1.2643593653836975e-05,
      "loss": 0.15156855583190917,
      "step": 3000
    },
    {
      "epoch": 2.367797947908445,
      "eval_accuracy": 0.9714,
      "eval_f1": 0.9712,
      "eval_loss": 0.08889847248792648,
      "eval_runtime": 17.0683,
      "eval_samples_per_second": 296.866,
      "eval_steps_per_second": 9.316,
      "step": 3000
    },
    {
      "epoch": 2.44672454617206,
      "grad_norm": 9.044219970703125,
      "learning_rate": 1.2108394187007715e-05,
      "loss": 0.12777873992919922,
      "step": 3100
    },
    {
      "epoch": 2.525651144435675,
      "grad_norm": 0.1941675990819931,
      "learning_rate": 1.1566793841878931e-05,
      "loss": 0.13878602981567384,
      "step": 3200
    },
    {
      "epoch": 2.6045777426992895,
      "grad_norm": 8.129409790039062,
      "learning_rate": 1.1020436864065368e-05,
      "loss": 0.14199438095092773,
      "step": 3300
    },
    {
      "epoch": 2.6835043409629042,
      "grad_norm": 0.1269533634185791,
      "learning_rate": 1.0470981939852842e-05,
      "loss": 0.12948278427124024,
      "step": 3400
    },
    {
      "epoch": 2.7624309392265194,
      "grad_norm": 4.474359512329102,
      "learning_rate": 9.92009716058909e-06,
      "loss": 0.12795443534851075,
      "step": 3500
    },
    {
      "epoch": 2.7624309392265194,
      "eval_accuracy": 0.9722,
      "eval_f1": 0.972,
      "eval_loss": 0.08592783659696579,
      "eval_runtime": 17.0846,
      "eval_samples_per_second": 296.584,
      "eval_steps_per_second": 9.307,
      "step": 3500
    }
  ],
  "logging_steps": 100,
  "max_steps": 6335,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.473211421171712e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}