{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.753086419753085,
  "eval_steps": 100,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 15.961835861206055,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.6418,
      "step": 10
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 8.321958541870117,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.6123,
      "step": 20
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 10.797492980957031,
      "learning_rate": 3e-06,
      "loss": 0.5325,
      "step": 30
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 8.990424156188965,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.3937,
      "step": 40
    },
    {
      "epoch": 1.2345679012345678,
      "grad_norm": 5.069626331329346,
      "learning_rate": 5e-06,
      "loss": 0.2157,
      "step": 50
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 2.54313063621521,
      "learning_rate": 6e-06,
      "loss": 0.1184,
      "step": 60
    },
    {
      "epoch": 1.7283950617283952,
      "grad_norm": 1.0293046236038208,
      "learning_rate": 7e-06,
      "loss": 0.0469,
      "step": 70
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.32547664642333984,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0176,
      "step": 80
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.20642875134944916,
      "learning_rate": 9e-06,
      "loss": 0.0088,
      "step": 90
    },
    {
      "epoch": 2.4691358024691357,
      "grad_norm": 0.16824281215667725,
      "learning_rate": 1e-05,
      "loss": 0.0056,
      "step": 100
    },
    {
      "epoch": 2.4691358024691357,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:Null": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.004177506547421217,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.7278,
      "eval_samples_per_second": 133.281,
      "eval_steps_per_second": 9.618,
      "step": 100
    },
    {
      "epoch": 2.7160493827160495,
      "grad_norm": 0.10963490605354309,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.0038,
      "step": 110
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.07338671386241913,
      "learning_rate": 1.2e-05,
      "loss": 0.0029,
      "step": 120
    },
    {
      "epoch": 3.2098765432098766,
      "grad_norm": 0.0706721693277359,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.0024,
      "step": 130
    },
    {
      "epoch": 3.45679012345679,
      "grad_norm": 0.06313496083021164,
      "learning_rate": 1.4e-05,
      "loss": 0.002,
      "step": 140
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 0.063168965280056,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0018,
      "step": 150
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.05419662222266197,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0016,
      "step": 160
    },
    {
      "epoch": 4.197530864197531,
      "grad_norm": 0.047441959381103516,
      "learning_rate": 1.7e-05,
      "loss": 0.0014,
      "step": 170
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.04058253392577171,
      "learning_rate": 1.8e-05,
      "loss": 0.0012,
      "step": 180
    },
    {
      "epoch": 4.6913580246913575,
      "grad_norm": 0.029308538883924484,
      "learning_rate": 1.9e-05,
      "loss": 0.0011,
      "step": 190
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.027978356927633286,
      "learning_rate": 2e-05,
      "loss": 0.001,
      "step": 200
    },
    {
      "epoch": 4.938271604938271,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:Null": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0008954937802627683,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.521,
      "eval_samples_per_second": 186.189,
      "eval_steps_per_second": 13.436,
      "step": 200
    },
    {
      "epoch": 5.185185185185185,
      "grad_norm": 0.023471660912036896,
      "learning_rate": 1.9666666666666666e-05,
      "loss": 0.0009,
      "step": 210
    },
    {
      "epoch": 5.432098765432099,
      "grad_norm": 0.021547624841332436,
      "learning_rate": 1.9333333333333333e-05,
      "loss": 0.0008,
      "step": 220
    },
    {
      "epoch": 5.679012345679013,
      "grad_norm": 0.02687031961977482,
      "learning_rate": 1.9e-05,
      "loss": 0.0007,
      "step": 230
    },
    {
      "epoch": 5.925925925925926,
      "grad_norm": 0.021016767248511314,
      "learning_rate": 1.866666666666667e-05,
      "loss": 0.0006,
      "step": 240
    },
    {
      "epoch": 6.172839506172839,
      "grad_norm": 0.017553668469190598,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 0.0006,
      "step": 250
    },
    {
      "epoch": 6.419753086419753,
      "grad_norm": 0.016819961369037628,
      "learning_rate": 1.8e-05,
      "loss": 0.0006,
      "step": 260
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.018349776044487953,
      "learning_rate": 1.7666666666666668e-05,
      "loss": 0.0005,
      "step": 270
    },
    {
      "epoch": 6.91358024691358,
      "grad_norm": 0.01844148337841034,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 0.0005,
      "step": 280
    },
    {
      "epoch": 7.160493827160494,
      "grad_norm": 0.016825733706355095,
      "learning_rate": 1.7e-05,
      "loss": 0.0005,
      "step": 290
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 0.013994095847010612,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0005,
      "step": 300
    },
    {
      "epoch": 7.407407407407407,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:Null": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00043683411786332726,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.5186,
      "eval_samples_per_second": 187.027,
      "eval_steps_per_second": 13.497,
      "step": 300
    },
    {
      "epoch": 7.654320987654321,
      "grad_norm": 0.015141790732741356,
      "learning_rate": 1.6333333333333335e-05,
      "loss": 0.0004,
      "step": 310
    },
    {
      "epoch": 7.901234567901234,
      "grad_norm": 0.013697362504899502,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0004,
      "step": 320
    },
    {
      "epoch": 8.148148148148149,
      "grad_norm": 0.01174458209425211,
      "learning_rate": 1.5666666666666667e-05,
      "loss": 0.0004,
      "step": 330
    },
    {
      "epoch": 8.395061728395062,
      "grad_norm": 0.013013974763453007,
      "learning_rate": 1.5333333333333334e-05,
      "loss": 0.0004,
      "step": 340
    },
    {
      "epoch": 8.641975308641975,
      "grad_norm": 0.011320522986352444,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0004,
      "step": 350
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 0.010261823423206806,
      "learning_rate": 1.4666666666666666e-05,
      "loss": 0.0003,
      "step": 360
    },
    {
      "epoch": 9.135802469135802,
      "grad_norm": 0.009858865290880203,
      "learning_rate": 1.4333333333333334e-05,
      "loss": 0.0003,
      "step": 370
    },
    {
      "epoch": 9.382716049382717,
      "grad_norm": 0.009954158216714859,
      "learning_rate": 1.4e-05,
      "loss": 0.0003,
      "step": 380
    },
    {
      "epoch": 9.62962962962963,
      "grad_norm": 0.010688001289963722,
      "learning_rate": 1.3666666666666667e-05,
      "loss": 0.0003,
      "step": 390
    },
    {
      "epoch": 9.876543209876543,
      "grad_norm": 0.009526471607387066,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0003,
      "step": 400
    },
    {
      "epoch": 9.876543209876543,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:Null": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0002707206876948476,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.5189,
      "eval_samples_per_second": 186.945,
      "eval_steps_per_second": 13.491,
      "step": 400
    },
    {
      "epoch": 10.123456790123457,
      "grad_norm": 0.00999557226896286,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.0003,
      "step": 410
    },
    {
      "epoch": 10.37037037037037,
      "grad_norm": 0.009755443781614304,
      "learning_rate": 1.2666666666666667e-05,
      "loss": 0.0003,
      "step": 420
    },
    {
      "epoch": 10.617283950617283,
      "grad_norm": 0.008844558149576187,
      "learning_rate": 1.2333333333333334e-05,
      "loss": 0.0003,
      "step": 430
    },
    {
      "epoch": 10.864197530864198,
      "grad_norm": 0.00740455137565732,
      "learning_rate": 1.2e-05,
      "loss": 0.0003,
      "step": 440
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 0.007182607427239418,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 0.0002,
      "step": 450
    },
    {
      "epoch": 11.358024691358025,
      "grad_norm": 0.007493776269257069,
      "learning_rate": 1.1333333333333334e-05,
      "loss": 0.0003,
      "step": 460
    },
    {
      "epoch": 11.604938271604938,
      "grad_norm": 0.008535212837159634,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.0002,
      "step": 470
    },
    {
      "epoch": 11.851851851851851,
      "grad_norm": 0.007039290387183428,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 0.0002,
      "step": 480
    },
    {
      "epoch": 12.098765432098766,
      "grad_norm": 0.007746797055006027,
      "learning_rate": 1.0333333333333335e-05,
      "loss": 0.0002,
      "step": 490
    },
    {
      "epoch": 12.345679012345679,
      "grad_norm": 0.008360541425645351,
      "learning_rate": 1e-05,
      "loss": 0.0002,
      "step": 500
    },
    {
      "epoch": 12.345679012345679,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:Null": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00022185646230354905,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.5185,
      "eval_samples_per_second": 187.093,
      "eval_steps_per_second": 13.502,
      "step": 500
    },
    {
      "epoch": 12.592592592592592,
      "grad_norm": 0.006791314110159874,
      "learning_rate": 9.666666666666667e-06,
      "loss": 0.0002,
      "step": 510
    },
    {
      "epoch": 12.839506172839506,
      "grad_norm": 0.007602753583341837,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.0002,
      "step": 520
    },
    {
      "epoch": 13.08641975308642,
      "grad_norm": 0.0071947514079511166,
      "learning_rate": 9e-06,
      "loss": 0.0002,
      "step": 530
    },
    {
      "epoch": 13.333333333333334,
      "grad_norm": 0.007956212386488914,
      "learning_rate": 8.666666666666668e-06,
      "loss": 0.0002,
      "step": 540
    },
    {
      "epoch": 13.580246913580247,
      "grad_norm": 0.007944190874695778,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.0002,
      "step": 550
    },
    {
      "epoch": 13.82716049382716,
      "grad_norm": 0.007252030540257692,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0002,
      "step": 560
    },
    {
      "epoch": 14.074074074074074,
      "grad_norm": 0.007420521695166826,
      "learning_rate": 7.666666666666667e-06,
      "loss": 0.0002,
      "step": 570
    },
    {
      "epoch": 14.320987654320987,
      "grad_norm": 0.007615529000759125,
      "learning_rate": 7.333333333333333e-06,
      "loss": 0.0002,
      "step": 580
    },
    {
      "epoch": 14.567901234567902,
      "grad_norm": 0.007768448442220688,
      "learning_rate": 7e-06,
      "loss": 0.0002,
      "step": 590
    },
    {
      "epoch": 14.814814814814815,
      "grad_norm": 0.005428287200629711,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.0002,
      "step": 600
    },
    {
      "epoch": 14.814814814814815,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:Null": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00019342350424267352,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.5188,
      "eval_samples_per_second": 186.984,
      "eval_steps_per_second": 13.494,
      "step": 600
    },
    {
      "epoch": 15.061728395061728,
      "grad_norm": 0.005406714044511318,
      "learning_rate": 6.333333333333333e-06,
      "loss": 0.0002,
      "step": 610
    },
    {
      "epoch": 15.308641975308642,
      "grad_norm": 0.007229079958051443,
      "learning_rate": 6e-06,
      "loss": 0.0002,
      "step": 620
    },
    {
      "epoch": 15.555555555555555,
      "grad_norm": 0.006031244061887264,
      "learning_rate": 5.666666666666667e-06,
      "loss": 0.0002,
      "step": 630
    },
    {
      "epoch": 15.802469135802468,
      "grad_norm": 0.0075646815821528435,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.0002,
      "step": 640
    },
    {
      "epoch": 16.049382716049383,
      "grad_norm": 0.006907324306666851,
      "learning_rate": 5e-06,
      "loss": 0.0002,
      "step": 650
    },
    {
      "epoch": 16.296296296296298,
      "grad_norm": 0.005848431494086981,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.0002,
      "step": 660
    },
    {
      "epoch": 16.54320987654321,
      "grad_norm": 0.007128111552447081,
      "learning_rate": 4.333333333333334e-06,
      "loss": 0.0002,
      "step": 670
    },
    {
      "epoch": 16.790123456790123,
      "grad_norm": 0.00657699815928936,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0002,
      "step": 680
    },
    {
      "epoch": 17.037037037037038,
      "grad_norm": 0.005719279404729605,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 0.0002,
      "step": 690
    },
    {
      "epoch": 17.28395061728395,
      "grad_norm": 0.0061570280231535435,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0002,
      "step": 700
    },
    {
      "epoch": 17.28395061728395,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:Null": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0001789480447769165,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.5201,
      "eval_samples_per_second": 186.493,
      "eval_steps_per_second": 13.458,
      "step": 700
    },
    {
      "epoch": 17.530864197530864,
      "grad_norm": 0.006241227500140667,
      "learning_rate": 3e-06,
      "loss": 0.0002,
      "step": 710
    },
    {
      "epoch": 17.77777777777778,
      "grad_norm": 0.006561820395290852,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.0002,
      "step": 720
    },
    {
      "epoch": 18.02469135802469,
      "grad_norm": 0.00643093092367053,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 0.0002,
      "step": 730
    },
    {
      "epoch": 18.271604938271604,
      "grad_norm": 0.005693737417459488,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0002,
      "step": 740
    },
    {
      "epoch": 18.51851851851852,
      "grad_norm": 0.0065653519704937935,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.0002,
      "step": 750
    },
    {
      "epoch": 18.765432098765434,
      "grad_norm": 0.004837734624743462,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.0002,
      "step": 760
    },
    {
      "epoch": 19.012345679012345,
      "grad_norm": 0.005498081911355257,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0002,
      "step": 770
    },
    {
      "epoch": 19.25925925925926,
      "grad_norm": 0.0063169412314891815,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.0002,
      "step": 780
    },
    {
      "epoch": 19.506172839506174,
      "grad_norm": 0.00681178318336606,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 0.0002,
      "step": 790
    },
    {
      "epoch": 19.753086419753085,
      "grad_norm": 0.006289825774729252,
      "learning_rate": 0.0,
      "loss": 0.0002,
      "step": 800
    },
    {
      "epoch": 19.753086419753085,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:Null": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0001743907341733575,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.5213,
      "eval_samples_per_second": 186.078,
      "eval_steps_per_second": 13.428,
      "step": 800
    },
    {
      "epoch": 19.753086419753085,
      "step": 800,
      "total_flos": 93696895492200.0,
      "train_loss": 0.032879929275804895,
      "train_runtime": 407.7795,
      "train_samples_per_second": 63.073,
      "train_steps_per_second": 1.962
    },
    {
      "epoch": 19.753086419753085,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:Null": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0001743907341733575,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.5104,
      "eval_samples_per_second": 190.041,
      "eval_steps_per_second": 13.714,
      "step": 800
    }
  ],
  "logging_steps": 10,
  "max_steps": 800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 93696895492200.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}