{
  "best_metric": 0.20267261564731598,
  "best_model_checkpoint": "NonCompete-Test/checkpoint-52",
  "epoch": 13.0,
  "eval_steps": 500,
  "global_step": 52,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 0.5877,
      "step": 1
    },
    {
      "epoch": 0.5,
      "grad_norm": 6.38834810256958,
      "learning_rate": 1.25e-06,
      "loss": 0.7,
      "step": 2
    },
    {
      "epoch": 0.75,
      "grad_norm": 5.209357738494873,
      "learning_rate": 2.5e-06,
      "loss": 0.5835,
      "step": 3
    },
    {
      "epoch": 1.0,
      "grad_norm": 11.068732261657715,
      "learning_rate": 3.75e-06,
      "loss": 0.65,
      "step": 4
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7058823529411765,
      "eval_auc": 0.7000000000000001,
      "eval_f1": 0.0,
      "eval_loss": 0.6488395929336548,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.06,
      "eval_samples_per_second": 283.11,
      "eval_steps_per_second": 16.654,
      "step": 4
    },
    {
      "epoch": 1.25,
      "grad_norm": 4.674075603485107,
      "learning_rate": 5e-06,
      "loss": 0.5979,
      "step": 5
    },
    {
      "epoch": 1.5,
      "grad_norm": 3.6536738872528076,
      "learning_rate": 6.25e-06,
      "loss": 0.5355,
      "step": 6
    },
    {
      "epoch": 1.75,
      "grad_norm": 5.9179840087890625,
      "learning_rate": 7.5e-06,
      "loss": 0.6727,
      "step": 7
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.177053451538086,
      "learning_rate": 8.75e-06,
      "loss": 0.6564,
      "step": 8
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7058823529411765,
      "eval_auc": 0.7000000000000001,
      "eval_f1": 0.0,
      "eval_loss": 0.6269674897193909,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.0578,
      "eval_samples_per_second": 294.137,
      "eval_steps_per_second": 17.302,
      "step": 8
    },
    {
      "epoch": 2.25,
      "grad_norm": Infinity,
      "learning_rate": 8.75e-06,
      "loss": 0.5595,
      "step": 9
    },
    {
      "epoch": 2.5,
      "grad_norm": 4.788901329040527,
      "learning_rate": 1e-05,
      "loss": 0.6515,
      "step": 10
    },
    {
      "epoch": 2.75,
      "grad_norm": 4.311627388000488,
      "learning_rate": 1.125e-05,
      "loss": 0.5628,
      "step": 11
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.801633358001709,
      "learning_rate": 1.25e-05,
      "loss": 0.3583,
      "step": 12
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7058823529411765,
      "eval_auc": 0.7666666666666667,
      "eval_f1": 0.0,
      "eval_loss": 0.5773638486862183,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.0574,
      "eval_samples_per_second": 296.101,
      "eval_steps_per_second": 17.418,
      "step": 12
    },
    {
      "epoch": 3.25,
      "grad_norm": 3.5935935974121094,
      "learning_rate": 1.3750000000000002e-05,
      "loss": 0.5944,
      "step": 13
    },
    {
      "epoch": 3.5,
      "grad_norm": Infinity,
      "learning_rate": 1.3750000000000002e-05,
      "loss": 0.5499,
      "step": 14
    },
    {
      "epoch": 3.75,
      "grad_norm": 5.153175354003906,
      "learning_rate": 1.5e-05,
      "loss": 0.5126,
      "step": 15
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.957610130310059,
      "learning_rate": 1.6250000000000002e-05,
      "loss": 0.508,
      "step": 16
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7058823529411765,
      "eval_auc": 0.7166666666666667,
      "eval_f1": 0.0,
      "eval_loss": 0.5451947450637817,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.0667,
      "eval_samples_per_second": 254.97,
      "eval_steps_per_second": 14.998,
      "step": 16
    },
    {
      "epoch": 4.25,
      "grad_norm": 5.213046073913574,
      "learning_rate": 1.75e-05,
      "loss": 0.6059,
      "step": 17
    },
    {
      "epoch": 4.5,
      "grad_norm": Infinity,
      "learning_rate": 1.75e-05,
      "loss": 0.596,
      "step": 18
    },
    {
      "epoch": 4.75,
      "grad_norm": 5.471120834350586,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.4574,
      "step": 19
    },
    {
      "epoch": 5.0,
      "grad_norm": 6.0362372398376465,
      "learning_rate": 2e-05,
      "loss": 0.3978,
      "step": 20
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7058823529411765,
      "eval_auc": 0.65,
      "eval_f1": 0.0,
      "eval_loss": 0.606438159942627,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.0567,
      "eval_samples_per_second": 300.085,
      "eval_steps_per_second": 17.652,
      "step": 20
    },
    {
      "epoch": 5.25,
      "grad_norm": 15.422409057617188,
      "learning_rate": 2.125e-05,
      "loss": 0.5901,
      "step": 21
    },
    {
      "epoch": 5.5,
      "grad_norm": 3.408106565475464,
      "learning_rate": 2.25e-05,
      "loss": 0.4629,
      "step": 22
    },
    {
      "epoch": 5.75,
      "grad_norm": 4.22088098526001,
      "learning_rate": 2.375e-05,
      "loss": 0.5596,
      "step": 23
    },
    {
      "epoch": 6.0,
      "grad_norm": Infinity,
      "learning_rate": 2.375e-05,
      "loss": 0.4767,
      "step": 24
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7058823529411765,
      "eval_auc": 0.6,
      "eval_f1": 0.0,
      "eval_loss": 0.5987117886543274,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.0568,
      "eval_samples_per_second": 299.558,
      "eval_steps_per_second": 17.621,
      "step": 24
    },
    {
      "epoch": 6.25,
      "grad_norm": 2.9963974952697754,
      "learning_rate": 2.5e-05,
      "loss": 0.4606,
      "step": 25
    },
    {
      "epoch": 6.5,
      "grad_norm": 4.663226127624512,
      "learning_rate": 2.625e-05,
      "loss": 0.4368,
      "step": 26
    },
    {
      "epoch": 6.75,
      "grad_norm": 3.2067272663116455,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.4495,
      "step": 27
    },
    {
      "epoch": 7.0,
      "grad_norm": 7.059210300445557,
      "learning_rate": 2.8749999999999997e-05,
      "loss": 0.5914,
      "step": 28
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7647058823529411,
      "eval_auc": 0.75,
      "eval_f1": 0.3333333333333333,
      "eval_loss": 0.5011345148086548,
      "eval_precision": 1.0,
      "eval_recall": 0.2,
      "eval_runtime": 0.057,
      "eval_samples_per_second": 298.185,
      "eval_steps_per_second": 17.54,
      "step": 28
    },
    {
      "epoch": 7.25,
      "grad_norm": 3.552440643310547,
      "learning_rate": 3e-05,
      "loss": 0.2947,
      "step": 29
    },
    {
      "epoch": 7.5,
      "grad_norm": 5.064967155456543,
      "learning_rate": 3.125e-05,
      "loss": 0.4558,
      "step": 30
    },
    {
      "epoch": 7.75,
      "grad_norm": 6.062498569488525,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 0.4291,
      "step": 31
    },
    {
      "epoch": 8.0,
      "grad_norm": 12.07767105102539,
      "learning_rate": 3.375000000000001e-05,
      "loss": 0.4277,
      "step": 32
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7647058823529411,
      "eval_auc": 0.9166666666666666,
      "eval_f1": 0.5,
      "eval_loss": 0.40540269017219543,
      "eval_precision": 0.6666666666666666,
      "eval_recall": 0.4,
      "eval_runtime": 0.0578,
      "eval_samples_per_second": 293.961,
      "eval_steps_per_second": 17.292,
      "step": 32
    },
    {
      "epoch": 8.25,
      "grad_norm": 4.816434860229492,
      "learning_rate": 3.5e-05,
      "loss": 0.2649,
      "step": 33
    },
    {
      "epoch": 8.5,
      "grad_norm": 5.842213153839111,
      "learning_rate": 3.625e-05,
      "loss": 0.2945,
      "step": 34
    },
    {
      "epoch": 8.75,
      "grad_norm": 4.9558024406433105,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.2484,
      "step": 35
    },
    {
      "epoch": 9.0,
      "grad_norm": 5.846200466156006,
      "learning_rate": 3.875e-05,
      "loss": 0.2677,
      "step": 36
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7647058823529411,
      "eval_auc": 0.6833333333333333,
      "eval_f1": 0.3333333333333333,
      "eval_loss": 0.4802425503730774,
      "eval_precision": 1.0,
      "eval_recall": 0.2,
      "eval_runtime": 0.0572,
      "eval_samples_per_second": 297.166,
      "eval_steps_per_second": 17.48,
      "step": 36
    },
    {
      "epoch": 9.25,
      "grad_norm": 3.983147621154785,
      "learning_rate": 4e-05,
      "loss": 0.1888,
      "step": 37
    },
    {
      "epoch": 9.5,
      "grad_norm": 3.358937978744507,
      "learning_rate": 4.125e-05,
      "loss": 0.2366,
      "step": 38
    },
    {
      "epoch": 9.75,
      "grad_norm": 3.220496654510498,
      "learning_rate": 4.25e-05,
      "loss": 0.1501,
      "step": 39
    },
    {
      "epoch": 10.0,
      "grad_norm": 6.872381210327148,
      "learning_rate": 4.375e-05,
      "loss": 0.2008,
      "step": 40
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8823529411764706,
      "eval_auc": 0.9666666666666667,
      "eval_f1": 0.8,
      "eval_loss": 0.23314711451530457,
      "eval_precision": 0.8,
      "eval_recall": 0.8,
      "eval_runtime": 0.057,
      "eval_samples_per_second": 298.263,
      "eval_steps_per_second": 17.545,
      "step": 40
    },
    {
      "epoch": 10.25,
      "grad_norm": 3.6026062965393066,
      "learning_rate": 4.5e-05,
      "loss": 0.1339,
      "step": 41
    },
    {
      "epoch": 10.5,
      "grad_norm": 4.244753360748291,
      "learning_rate": 4.6250000000000006e-05,
      "loss": 0.1435,
      "step": 42
    },
    {
      "epoch": 10.75,
      "grad_norm": 2.4807896614074707,
      "learning_rate": 4.75e-05,
      "loss": 0.0886,
      "step": 43
    },
    {
      "epoch": 11.0,
      "grad_norm": 1.8359788656234741,
      "learning_rate": 4.875e-05,
      "loss": 0.063,
      "step": 44
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.8823529411764706,
      "eval_auc": 0.9833333333333333,
      "eval_f1": 0.8,
      "eval_loss": 0.20963242650032043,
      "eval_precision": 0.8,
      "eval_recall": 0.8,
      "eval_runtime": 0.057,
      "eval_samples_per_second": 298.411,
      "eval_steps_per_second": 17.554,
      "step": 44
    },
    {
      "epoch": 11.25,
      "grad_norm": 1.7810684442520142,
      "learning_rate": 5e-05,
      "loss": 0.0659,
      "step": 45
    },
    {
      "epoch": 11.5,
      "grad_norm": 1.6344645023345947,
      "learning_rate": 4.986111111111111e-05,
      "loss": 0.05,
      "step": 46
    },
    {
      "epoch": 11.75,
      "grad_norm": 1.3671772480010986,
      "learning_rate": 4.972222222222223e-05,
      "loss": 0.0491,
      "step": 47
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.8882291316986084,
      "learning_rate": 4.958333333333334e-05,
      "loss": 0.0283,
      "step": 48
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.8823529411764706,
      "eval_auc": 0.9666666666666667,
      "eval_f1": 0.8,
      "eval_loss": 0.26048457622528076,
      "eval_precision": 0.8,
      "eval_recall": 0.8,
      "eval_runtime": 0.057,
      "eval_samples_per_second": 298.469,
      "eval_steps_per_second": 17.557,
      "step": 48
    },
    {
      "epoch": 12.25,
      "grad_norm": 1.625268816947937,
      "learning_rate": 4.9444444444444446e-05,
      "loss": 0.0379,
      "step": 49
    },
    {
      "epoch": 12.5,
      "grad_norm": 0.7491352558135986,
      "learning_rate": 4.930555555555556e-05,
      "loss": 0.0253,
      "step": 50
    },
    {
      "epoch": 12.75,
      "grad_norm": 0.6248525977134705,
      "learning_rate": 4.9166666666666665e-05,
      "loss": 0.0211,
      "step": 51
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.5918123722076416,
      "learning_rate": 4.902777777777778e-05,
      "loss": 0.0206,
      "step": 52
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9411764705882353,
      "eval_auc": 0.9666666666666667,
      "eval_f1": 0.9090909090909091,
      "eval_loss": 0.20267261564731598,
      "eval_precision": 0.8333333333333334,
      "eval_recall": 1.0,
      "eval_runtime": 0.0573,
      "eval_samples_per_second": 296.92,
      "eval_steps_per_second": 17.466,
      "step": 52
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "total_flos": 57292432304640.0,
  "train_batch_size": 20,
  "trial_name": null,
  "trial_params": null
}