{
  "best_metric": 0.2875193953514099,
  "best_model_checkpoint": "autotrain-rcira-jogfv/checkpoint-280",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 3.117601156234741,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.6004,
      "step": 7
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.980803966522217,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5799,
      "step": 14
    },
    {
      "epoch": 0.15,
      "grad_norm": 6.8337836265563965,
      "learning_rate": 2.5e-05,
      "loss": 0.5843,
      "step": 21
    },
    {
      "epoch": 0.2,
      "grad_norm": 7.110068321228027,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.6206,
      "step": 28
    },
    {
      "epoch": 0.25,
      "grad_norm": 5.731410503387451,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.449,
      "step": 35
    },
    {
      "epoch": 0.3,
      "grad_norm": 4.437646865844727,
      "learning_rate": 5e-05,
      "loss": 0.4225,
      "step": 42
    },
    {
      "epoch": 0.35,
      "grad_norm": 16.640886306762695,
      "learning_rate": 4.9074074074074075e-05,
      "loss": 0.4816,
      "step": 49
    },
    {
      "epoch": 0.4,
      "grad_norm": 5.661762714385986,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.3799,
      "step": 56
    },
    {
      "epoch": 0.45,
      "grad_norm": 3.9557294845581055,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.3908,
      "step": 63
    },
    {
      "epoch": 0.5,
      "grad_norm": 14.93912124633789,
      "learning_rate": 4.62962962962963e-05,
      "loss": 0.4501,
      "step": 70
    },
    {
      "epoch": 0.55,
      "grad_norm": 4.729761600494385,
      "learning_rate": 4.5370370370370374e-05,
      "loss": 0.4502,
      "step": 77
    },
    {
      "epoch": 0.6,
      "grad_norm": 8.4749755859375,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.4013,
      "step": 84
    },
    {
      "epoch": 0.65,
      "grad_norm": 3.363345146179199,
      "learning_rate": 4.351851851851852e-05,
      "loss": 0.2332,
      "step": 91
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.7409418821334839,
      "learning_rate": 4.259259259259259e-05,
      "loss": 0.2461,
      "step": 98
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.162623643875122,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.3435,
      "step": 105
    },
    {
      "epoch": 0.8,
      "grad_norm": 24.589733123779297,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.2542,
      "step": 112
    },
    {
      "epoch": 0.85,
      "grad_norm": 6.879342555999756,
      "learning_rate": 3.981481481481482e-05,
      "loss": 0.4404,
      "step": 119
    },
    {
      "epoch": 0.9,
      "grad_norm": 9.209638595581055,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.2772,
      "step": 126
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.787611961364746,
      "learning_rate": 3.7962962962962964e-05,
      "loss": 0.2977,
      "step": 133
    },
    {
      "epoch": 1.0,
      "grad_norm": 9.668951988220215,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.4281,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8714285714285714,
      "eval_auc": 0.9277579351708335,
      "eval_f1": 0.660377358490566,
      "eval_loss": 0.3361506164073944,
      "eval_precision": 1.0,
      "eval_recall": 0.49295774647887325,
      "eval_runtime": 60.7868,
      "eval_samples_per_second": 4.606,
      "eval_steps_per_second": 0.296,
      "step": 140
    },
    {
      "epoch": 1.05,
      "grad_norm": 1.7222918272018433,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.2177,
      "step": 147
    },
    {
      "epoch": 1.1,
      "grad_norm": 1.8709276914596558,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.2144,
      "step": 154
    },
    {
      "epoch": 1.15,
      "grad_norm": 7.57355260848999,
      "learning_rate": 3.425925925925926e-05,
      "loss": 0.2451,
      "step": 161
    },
    {
      "epoch": 1.2,
      "grad_norm": 9.764376640319824,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1751,
      "step": 168
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.35536810755729675,
      "learning_rate": 3.240740740740741e-05,
      "loss": 0.3158,
      "step": 175
    },
    {
      "epoch": 1.3,
      "grad_norm": 28.518468856811523,
      "learning_rate": 3.148148148148148e-05,
      "loss": 0.4364,
      "step": 182
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.5735307335853577,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.2745,
      "step": 189
    },
    {
      "epoch": 1.4,
      "grad_norm": 1.0257889032363892,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.2171,
      "step": 196
    },
    {
      "epoch": 1.45,
      "grad_norm": 10.6473388671875,
      "learning_rate": 2.8703703703703706e-05,
      "loss": 0.6241,
      "step": 203
    },
    {
      "epoch": 1.5,
      "grad_norm": 5.9080681800842285,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.2061,
      "step": 210
    },
    {
      "epoch": 1.55,
      "grad_norm": 16.31466293334961,
      "learning_rate": 2.6851851851851855e-05,
      "loss": 0.3655,
      "step": 217
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.7148101329803467,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.2594,
      "step": 224
    },
    {
      "epoch": 1.65,
      "grad_norm": 3.448263168334961,
      "learning_rate": 2.5e-05,
      "loss": 0.2242,
      "step": 231
    },
    {
      "epoch": 1.7,
      "grad_norm": 3.1968586444854736,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.3384,
      "step": 238
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.8760737776756287,
      "learning_rate": 2.314814814814815e-05,
      "loss": 0.4047,
      "step": 245
    },
    {
      "epoch": 1.8,
      "grad_norm": 6.7152099609375,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.2784,
      "step": 252
    },
    {
      "epoch": 1.85,
      "grad_norm": 2.6230883598327637,
      "learning_rate": 2.1296296296296296e-05,
      "loss": 0.2764,
      "step": 259
    },
    {
      "epoch": 1.9,
      "grad_norm": 8.257742881774902,
      "learning_rate": 2.037037037037037e-05,
      "loss": 0.2538,
      "step": 266
    },
    {
      "epoch": 1.95,
      "grad_norm": 11.801633834838867,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.3419,
      "step": 273
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.414065361022949,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.2464,
      "step": 280
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8464285714285714,
      "eval_auc": 0.933283914010378,
      "eval_f1": 0.7261146496815286,
      "eval_loss": 0.2875193953514099,
      "eval_precision": 0.6627906976744186,
      "eval_recall": 0.8028169014084507,
      "eval_runtime": 55.1352,
      "eval_samples_per_second": 5.078,
      "eval_steps_per_second": 0.326,
      "step": 280
    }
  ],
  "logging_steps": 7,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 146947524418560.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}