{
  "best_global_step": 1470,
  "best_metric": 0.8774819661990341,
  "best_model_checkpoint": "evaluation_results/student_run_20250723_144346/checkpoint-1470",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1470,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8571598666454993,
      "eval_f1_fix": 0.9995735277013144,
      "eval_f1_issue": 0.8336147671809581,
      "eval_f1_macro": 0.8689133107206232,
      "eval_f1_symptom": 0.773551637279597,
      "eval_f1_weighted": 0.8591167612530499,
      "eval_loss": 0.2723788321018219,
      "eval_precision_fix": 0.9991474190048054,
      "eval_precision_issue": 0.9030722197163333,
      "eval_precision_macro": 0.8675605064388172,
      "eval_precision_symptom": 0.7004618805953128,
      "eval_recall_fix": 1.0,
      "eval_recall_issue": 0.7740785290832546,
      "eval_recall_macro": 0.879250015682372,
      "eval_recall_symptom": 0.8636715179638613,
      "eval_runtime": 18.9953,
      "eval_samples_per_second": 2652.87,
      "eval_steps_per_second": 3.317,
      "step": 294
    },
    {
      "epoch": 1.7006802721088436,
      "grad_norm": 1.3646109104156494,
      "learning_rate": 8.302721088435374e-06,
      "loss": 0.329,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8634108588664867,
      "eval_f1_fix": 0.9996510410608351,
      "eval_f1_issue": 0.8428649735063036,
      "eval_f1_macro": 0.8740543037652156,
      "eval_f1_symptom": 0.7796468967285078,
      "eval_f1_weighted": 0.8651299856279673,
      "eval_loss": 0.268380343914032,
      "eval_precision_fix": 0.9993023255813953,
      "eval_precision_issue": 0.8998341948697942,
      "eval_precision_macro": 0.871791140476155,
      "eval_precision_symptom": 0.7162369009772754,
      "eval_recall_fix": 1.0,
      "eval_recall_issue": 0.7926797834865539,
      "eval_recall_macro": 0.8826849600536515,
      "eval_recall_symptom": 0.8553750966744006,
      "eval_runtime": 18.9955,
      "eval_samples_per_second": 2652.837,
      "eval_steps_per_second": 3.317,
      "step": 588
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8558699793618034,
      "eval_f1_fix": 0.9998061038507775,
      "eval_f1_issue": 0.8292579704692937,
      "eval_f1_macro": 0.8684898113127071,
      "eval_f1_symptom": 0.7764053596180502,
      "eval_f1_weighted": 0.8579691409583291,
      "eval_loss": 0.2672291696071625,
      "eval_precision_fix": 0.9996122828784119,
      "eval_precision_issue": 0.9159135763997092,
      "eval_precision_macro": 0.8688013508195644,
      "eval_precision_symptom": 0.6908781931805723,
      "eval_recall_fix": 1.0,
      "eval_recall_issue": 0.7575822665177421,
      "eval_recall_macro": 0.8812274151417152,
      "eval_recall_symptom": 0.8860999789074036,
      "eval_runtime": 18.9615,
      "eval_samples_per_second": 2657.598,
      "eval_steps_per_second": 3.323,
      "step": 882
    },
    {
      "epoch": 3.4013605442176873,
      "grad_norm": 0.9915511012077332,
      "learning_rate": 6.6020408163265315e-06,
      "loss": 0.2619,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8678956977297984,
      "eval_f1_fix": 0.9998448770650741,
      "eval_f1_issue": 0.8510438343290595,
      "eval_f1_macro": 0.8771228228486488,
      "eval_f1_symptom": 0.7804797571518131,
      "eval_f1_weighted": 0.8691927740857269,
      "eval_loss": 0.2652249336242676,
      "eval_precision_fix": 0.9996898022489337,
      "eval_precision_issue": 0.8881053565590996,
      "eval_precision_macro": 0.8743740639614609,
      "eval_precision_symptom": 0.7353270330763492,
      "eval_recall_fix": 1.0,
      "eval_recall_issue": 0.816951628146748,
      "eval_recall_macro": 0.8828306969258993,
      "eval_recall_symptom": 0.8315404626309498,
      "eval_runtime": 18.9531,
      "eval_samples_per_second": 2658.775,
      "eval_steps_per_second": 3.324,
      "step": 1176
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8690069852357517,
      "eval_f1_fix": 0.9997673336435552,
      "eval_f1_issue": 0.8539430291494212,
      "eval_f1_macro": 0.8774819661990341,
      "eval_f1_symptom": 0.7787355358041255,
      "eval_f1_weighted": 0.8700198852254597,
      "eval_loss": 0.26798591017723083,
      "eval_precision_fix": 0.9995347755291928,
      "eval_precision_issue": 0.880746929644341,
      "eval_precision_macro": 0.8749433971922725,
      "eval_precision_symptom": 0.7445484864032837,
      "eval_recall_fix": 1.0,
      "eval_recall_issue": 0.8287223988315148,
      "eval_recall_macro": 0.8816451915578204,
      "eval_recall_symptom": 0.8162131758419462,
      "eval_runtime": 18.9943,
      "eval_samples_per_second": 2653.007,
      "eval_steps_per_second": 3.317,
      "step": 1470
    }
  ],
  "logging_steps": 500,
  "max_steps": 2940,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "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": 9.415587132761702e+16,
  "train_batch_size": 200,
  "trial_name": null,
  "trial_params": null
}