{
  "best_metric": 0.3196659982204437,
  "best_model_checkpoint": "autotrain-dqwq9-raj8z/checkpoint-402",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 402,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04975124378109453,
      "grad_norm": 1.349796175956726,
      "learning_rate": 8.196721311475409e-06,
      "loss": 0.6957,
      "step": 10
    },
    {
      "epoch": 0.09950248756218906,
      "grad_norm": 1.466939926147461,
      "learning_rate": 1.6393442622950818e-05,
      "loss": 0.6877,
      "step": 20
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 1.2715398073196411,
      "learning_rate": 2.459016393442623e-05,
      "loss": 0.6745,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.0873539447784424,
      "learning_rate": 3.2786885245901635e-05,
      "loss": 0.6694,
      "step": 40
    },
    {
      "epoch": 0.24875621890547264,
      "grad_norm": 3.037040948867798,
      "learning_rate": 4.098360655737705e-05,
      "loss": 0.6388,
      "step": 50
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 3.347933530807495,
      "learning_rate": 4.918032786885246e-05,
      "loss": 0.5667,
      "step": 60
    },
    {
      "epoch": 0.3482587064676617,
      "grad_norm": 1.411434292793274,
      "learning_rate": 4.9169741697416974e-05,
      "loss": 0.5589,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 1.8238639831542969,
      "learning_rate": 4.824723247232473e-05,
      "loss": 0.4604,
      "step": 80
    },
    {
      "epoch": 0.44776119402985076,
      "grad_norm": 0.7032828330993652,
      "learning_rate": 4.732472324723247e-05,
      "loss": 0.4928,
      "step": 90
    },
    {
      "epoch": 0.4975124378109453,
      "grad_norm": 5.344807147979736,
      "learning_rate": 4.640221402214022e-05,
      "loss": 0.5905,
      "step": 100
    },
    {
      "epoch": 0.5472636815920398,
      "grad_norm": 11.37374496459961,
      "learning_rate": 4.547970479704797e-05,
      "loss": 0.5766,
      "step": 110
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 2.2248592376708984,
      "learning_rate": 4.4557195571955725e-05,
      "loss": 0.4328,
      "step": 120
    },
    {
      "epoch": 0.6467661691542289,
      "grad_norm": 23.339529037475586,
      "learning_rate": 4.363468634686347e-05,
      "loss": 0.4319,
      "step": 130
    },
    {
      "epoch": 0.6965174129353234,
      "grad_norm": 10.886305809020996,
      "learning_rate": 4.2712177121771216e-05,
      "loss": 0.4757,
      "step": 140
    },
    {
      "epoch": 0.746268656716418,
      "grad_norm": 1.7823960781097412,
      "learning_rate": 4.178966789667897e-05,
      "loss": 0.6923,
      "step": 150
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 4.360367298126221,
      "learning_rate": 4.086715867158672e-05,
      "loss": 0.6345,
      "step": 160
    },
    {
      "epoch": 0.845771144278607,
      "grad_norm": 37.08948516845703,
      "learning_rate": 3.994464944649446e-05,
      "loss": 0.4232,
      "step": 170
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 5.172524452209473,
      "learning_rate": 3.902214022140221e-05,
      "loss": 0.3284,
      "step": 180
    },
    {
      "epoch": 0.945273631840796,
      "grad_norm": 1.918595790863037,
      "learning_rate": 3.809963099630997e-05,
      "loss": 0.4815,
      "step": 190
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 9.974020957946777,
      "learning_rate": 3.7177121771217716e-05,
      "loss": 0.3656,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8728179551122195,
      "eval_auc": 0.9423105627145629,
      "eval_f1": 0.8838268792710706,
      "eval_loss": 0.3628483712673187,
      "eval_precision": 0.8185654008438819,
      "eval_recall": 0.9603960396039604,
      "eval_runtime": 66.7993,
      "eval_samples_per_second": 6.003,
      "eval_steps_per_second": 0.389,
      "step": 201
    },
    {
      "epoch": 1.044776119402985,
      "grad_norm": 0.5829285383224487,
      "learning_rate": 3.625461254612546e-05,
      "loss": 0.2819,
      "step": 210
    },
    {
      "epoch": 1.0945273631840795,
      "grad_norm": 0.5525309443473816,
      "learning_rate": 3.5332103321033214e-05,
      "loss": 0.2374,
      "step": 220
    },
    {
      "epoch": 1.144278606965174,
      "grad_norm": 0.48299816250801086,
      "learning_rate": 3.440959409594096e-05,
      "loss": 0.2621,
      "step": 230
    },
    {
      "epoch": 1.1940298507462686,
      "grad_norm": 0.45784273743629456,
      "learning_rate": 3.348708487084871e-05,
      "loss": 0.1608,
      "step": 240
    },
    {
      "epoch": 1.243781094527363,
      "grad_norm": 0.8032777309417725,
      "learning_rate": 3.256457564575645e-05,
      "loss": 0.2451,
      "step": 250
    },
    {
      "epoch": 1.2935323383084576,
      "grad_norm": 4.527989864349365,
      "learning_rate": 3.164206642066421e-05,
      "loss": 0.4304,
      "step": 260
    },
    {
      "epoch": 1.3432835820895521,
      "grad_norm": 2.323843479156494,
      "learning_rate": 3.071955719557196e-05,
      "loss": 0.3332,
      "step": 270
    },
    {
      "epoch": 1.3930348258706466,
      "grad_norm": 2.938237428665161,
      "learning_rate": 2.9797047970479707e-05,
      "loss": 0.3838,
      "step": 280
    },
    {
      "epoch": 1.4427860696517412,
      "grad_norm": 0.47250452637672424,
      "learning_rate": 2.8874538745387452e-05,
      "loss": 0.2357,
      "step": 290
    },
    {
      "epoch": 1.4925373134328357,
      "grad_norm": 0.38689321279525757,
      "learning_rate": 2.7952029520295204e-05,
      "loss": 0.2671,
      "step": 300
    },
    {
      "epoch": 1.5422885572139302,
      "grad_norm": 0.4907784163951874,
      "learning_rate": 2.7029520295202953e-05,
      "loss": 0.3475,
      "step": 310
    },
    {
      "epoch": 1.5920398009950247,
      "grad_norm": 0.5805690884590149,
      "learning_rate": 2.6107011070110705e-05,
      "loss": 0.3366,
      "step": 320
    },
    {
      "epoch": 1.6417910447761193,
      "grad_norm": 0.755260705947876,
      "learning_rate": 2.5184501845018447e-05,
      "loss": 0.4118,
      "step": 330
    },
    {
      "epoch": 1.6915422885572138,
      "grad_norm": 9.972153663635254,
      "learning_rate": 2.42619926199262e-05,
      "loss": 0.2589,
      "step": 340
    },
    {
      "epoch": 1.7412935323383083,
      "grad_norm": 43.50930404663086,
      "learning_rate": 2.333948339483395e-05,
      "loss": 0.5067,
      "step": 350
    },
    {
      "epoch": 1.7910447761194028,
      "grad_norm": 0.4147748053073883,
      "learning_rate": 2.2416974169741697e-05,
      "loss": 0.3013,
      "step": 360
    },
    {
      "epoch": 1.8407960199004973,
      "grad_norm": 0.9925008416175842,
      "learning_rate": 2.149446494464945e-05,
      "loss": 0.3129,
      "step": 370
    },
    {
      "epoch": 1.890547263681592,
      "grad_norm": 54.09661865234375,
      "learning_rate": 2.0571955719557195e-05,
      "loss": 0.2461,
      "step": 380
    },
    {
      "epoch": 1.9402985074626866,
      "grad_norm": 1.5262657403945923,
      "learning_rate": 1.9649446494464947e-05,
      "loss": 0.2221,
      "step": 390
    },
    {
      "epoch": 1.9900497512437811,
      "grad_norm": 3.4787943363189697,
      "learning_rate": 1.8726937269372693e-05,
      "loss": 0.4349,
      "step": 400
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8902743142144638,
      "eval_auc": 0.955196775959003,
      "eval_f1": 0.9,
      "eval_loss": 0.3196659982204437,
      "eval_precision": 0.8319327731092437,
      "eval_recall": 0.9801980198019802,
      "eval_runtime": 67.5778,
      "eval_samples_per_second": 5.934,
      "eval_steps_per_second": 0.385,
      "step": 402
    }
  ],
  "logging_steps": 10,
  "max_steps": 603,
  "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": 211015066398720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}