{
  "best_metric": 0.46716374158859253,
  "best_model_checkpoint": "edukasi-eksyar/checkpoint-150",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 8.004520416259766,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.7474,
      "step": 3
    },
    {
      "epoch": 0.08,
      "grad_norm": 4.838222980499268,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.7234,
      "step": 6
    },
    {
      "epoch": 0.12,
      "grad_norm": 6.006165981292725,
      "learning_rate": 6e-06,
      "loss": 0.6806,
      "step": 9
    },
    {
      "epoch": 0.16,
      "grad_norm": 5.214205265045166,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6827,
      "step": 12
    },
    {
      "epoch": 0.2,
      "grad_norm": Infinity,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.6964,
      "step": 15
    },
    {
      "epoch": 0.24,
      "grad_norm": 4.9306416511535645,
      "learning_rate": 1.1333333333333334e-05,
      "loss": 0.7053,
      "step": 18
    },
    {
      "epoch": 0.28,
      "grad_norm": 4.851315975189209,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.7157,
      "step": 21
    },
    {
      "epoch": 0.32,
      "grad_norm": 5.420584678649902,
      "learning_rate": 1.5333333333333334e-05,
      "loss": 0.6733,
      "step": 24
    },
    {
      "epoch": 0.36,
      "grad_norm": 5.671692848205566,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 0.7817,
      "step": 27
    },
    {
      "epoch": 0.4,
      "grad_norm": 4.638021469116211,
      "learning_rate": 1.9333333333333333e-05,
      "loss": 0.6695,
      "step": 30
    },
    {
      "epoch": 0.44,
      "grad_norm": 5.361118793487549,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 0.6291,
      "step": 33
    },
    {
      "epoch": 0.48,
      "grad_norm": 4.608893871307373,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.62,
      "step": 36
    },
    {
      "epoch": 0.52,
      "grad_norm": 4.534895420074463,
      "learning_rate": 2.5333333333333337e-05,
      "loss": 0.5813,
      "step": 39
    },
    {
      "epoch": 0.56,
      "grad_norm": 10.90993595123291,
      "learning_rate": 2.733333333333333e-05,
      "loss": 0.5732,
      "step": 42
    },
    {
      "epoch": 0.6,
      "grad_norm": 11.462884902954102,
      "learning_rate": 2.9333333333333336e-05,
      "loss": 0.8245,
      "step": 45
    },
    {
      "epoch": 0.64,
      "grad_norm": 5.430261611938477,
      "learning_rate": 3.1333333333333334e-05,
      "loss": 0.4529,
      "step": 48
    },
    {
      "epoch": 0.68,
      "grad_norm": 7.559244155883789,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.5846,
      "step": 51
    },
    {
      "epoch": 0.72,
      "grad_norm": 6.550118446350098,
      "learning_rate": 3.5333333333333336e-05,
      "loss": 0.6978,
      "step": 54
    },
    {
      "epoch": 0.76,
      "grad_norm": 4.697792053222656,
      "learning_rate": 3.733333333333334e-05,
      "loss": 0.724,
      "step": 57
    },
    {
      "epoch": 0.8,
      "grad_norm": 6.832012176513672,
      "learning_rate": 3.933333333333333e-05,
      "loss": 0.6196,
      "step": 60
    },
    {
      "epoch": 0.84,
      "grad_norm": 4.360001087188721,
      "learning_rate": 4.133333333333333e-05,
      "loss": 0.4207,
      "step": 63
    },
    {
      "epoch": 0.88,
      "grad_norm": 5.691288948059082,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.4241,
      "step": 66
    },
    {
      "epoch": 0.92,
      "grad_norm": 13.889620780944824,
      "learning_rate": 4.5333333333333335e-05,
      "loss": 0.6089,
      "step": 69
    },
    {
      "epoch": 0.96,
      "grad_norm": 7.6536865234375,
      "learning_rate": 4.7333333333333336e-05,
      "loss": 0.5699,
      "step": 72
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.8993226289749146,
      "learning_rate": 4.933333333333334e-05,
      "loss": 0.3402,
      "step": 75
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7516778523489933,
      "eval_auc": 0.8772072072072072,
      "eval_f1": 0.7861271676300579,
      "eval_loss": 0.5175233483314514,
      "eval_precision": 0.6868686868686869,
      "eval_recall": 0.918918918918919,
      "eval_runtime": 0.3003,
      "eval_samples_per_second": 496.248,
      "eval_steps_per_second": 33.305,
      "step": 75
    },
    {
      "epoch": 1.04,
      "grad_norm": 8.317619323730469,
      "learning_rate": 4.9851851851851855e-05,
      "loss": 0.3189,
      "step": 78
    },
    {
      "epoch": 1.08,
      "grad_norm": 4.061596870422363,
      "learning_rate": 4.962962962962963e-05,
      "loss": 0.2408,
      "step": 81
    },
    {
      "epoch": 1.12,
      "grad_norm": 9.929864883422852,
      "learning_rate": 4.940740740740741e-05,
      "loss": 0.4488,
      "step": 84
    },
    {
      "epoch": 1.16,
      "grad_norm": 13.264701843261719,
      "learning_rate": 4.918518518518519e-05,
      "loss": 0.3286,
      "step": 87
    },
    {
      "epoch": 1.2,
      "grad_norm": 10.807778358459473,
      "learning_rate": 4.896296296296297e-05,
      "loss": 0.3772,
      "step": 90
    },
    {
      "epoch": 1.24,
      "grad_norm": 7.425344944000244,
      "learning_rate": 4.874074074074074e-05,
      "loss": 0.1312,
      "step": 93
    },
    {
      "epoch": 1.28,
      "grad_norm": 9.521306037902832,
      "learning_rate": 4.851851851851852e-05,
      "loss": 0.3179,
      "step": 96
    },
    {
      "epoch": 1.32,
      "grad_norm": 31.535367965698242,
      "learning_rate": 4.82962962962963e-05,
      "loss": 0.3478,
      "step": 99
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 27.85064125061035,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.4613,
      "step": 102
    },
    {
      "epoch": 1.4,
      "grad_norm": 10.678465843200684,
      "learning_rate": 4.792592592592593e-05,
      "loss": 1.0055,
      "step": 105
    },
    {
      "epoch": 1.44,
      "grad_norm": 15.3538236618042,
      "learning_rate": 4.770370370370371e-05,
      "loss": 0.1905,
      "step": 108
    },
    {
      "epoch": 1.48,
      "grad_norm": 18.999788284301758,
      "learning_rate": 4.7481481481481483e-05,
      "loss": 0.3383,
      "step": 111
    },
    {
      "epoch": 1.52,
      "grad_norm": 9.190664291381836,
      "learning_rate": 4.7259259259259266e-05,
      "loss": 0.4572,
      "step": 114
    },
    {
      "epoch": 1.56,
      "grad_norm": 12.094901084899902,
      "learning_rate": 4.703703703703704e-05,
      "loss": 0.4445,
      "step": 117
    },
    {
      "epoch": 1.6,
      "grad_norm": 8.674372673034668,
      "learning_rate": 4.681481481481482e-05,
      "loss": 0.3431,
      "step": 120
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.5121658444404602,
      "learning_rate": 4.6592592592592595e-05,
      "loss": 0.3897,
      "step": 123
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 8.509323120117188,
      "learning_rate": 4.637037037037038e-05,
      "loss": 0.4224,
      "step": 126
    },
    {
      "epoch": 1.72,
      "grad_norm": 13.501930236816406,
      "learning_rate": 4.6148148148148154e-05,
      "loss": 0.2524,
      "step": 129
    },
    {
      "epoch": 1.76,
      "grad_norm": 20.332229614257812,
      "learning_rate": 4.592592592592593e-05,
      "loss": 0.6092,
      "step": 132
    },
    {
      "epoch": 1.8,
      "grad_norm": 7.666742324829102,
      "learning_rate": 4.5703703703703706e-05,
      "loss": 0.2536,
      "step": 135
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 6.118281364440918,
      "learning_rate": 4.548148148148149e-05,
      "loss": 0.2912,
      "step": 138
    },
    {
      "epoch": 1.88,
      "grad_norm": 5.993144512176514,
      "learning_rate": 4.5259259259259265e-05,
      "loss": 0.357,
      "step": 141
    },
    {
      "epoch": 1.92,
      "grad_norm": 15.134876251220703,
      "learning_rate": 4.503703703703704e-05,
      "loss": 0.2685,
      "step": 144
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.8912419676780701,
      "learning_rate": 4.481481481481482e-05,
      "loss": 0.2885,
      "step": 147
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.28381115198135376,
      "learning_rate": 4.4592592592592594e-05,
      "loss": 0.3773,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7986577181208053,
      "eval_auc": 0.9084684684684685,
      "eval_f1": 0.810126582278481,
      "eval_loss": 0.46716374158859253,
      "eval_precision": 0.7619047619047619,
      "eval_recall": 0.8648648648648649,
      "eval_runtime": 0.3042,
      "eval_samples_per_second": 489.871,
      "eval_steps_per_second": 32.877,
      "step": 150
    }
  ],
  "logging_steps": 3,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 78012427914240.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}