{
  "best_global_step": 444,
  "best_metric": 0.9908519069594639,
  "best_model_checkpoint": "outputs/modernbert_multitask\\checkpoint-444",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 444,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 19.44745635986328,
      "learning_rate": 1.8260869565217393e-05,
      "loss": 2.5678,
      "step": 25
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 13.687152862548828,
      "learning_rate": 1.8907363420427555e-05,
      "loss": 1.1327,
      "step": 50
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 6.3025336265563965,
      "learning_rate": 1.7719714964370545e-05,
      "loss": 0.4353,
      "step": 75
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 8.157584190368652,
      "learning_rate": 1.653206650831354e-05,
      "loss": 0.3109,
      "step": 100
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 4.141303539276123,
      "learning_rate": 1.5344418052256533e-05,
      "loss": 0.1846,
      "step": 125
    },
    {
      "epoch": 1.0,
      "eval_cat_accuracy": 0.990108803165183,
      "eval_cat_macro_f1": 0.990110753164417,
      "eval_cat_macro_precision": 0.9901580517709222,
      "eval_cat_macro_recall": 0.9901043700333245,
      "eval_cat_weighted_f1": 0.990113014130802,
      "eval_imp_accuracy": 0.9678536102868447,
      "eval_imp_f1": 0.9258836944127709,
      "eval_imp_precision": 0.8787878787878788,
      "eval_imp_recall": 0.9783132530120482,
      "eval_imp_roc_auc": 0.9973991797932239,
      "eval_loss": 0.11633610725402832,
      "eval_overall_score": 0.9579972237885939,
      "eval_runtime": 18.6093,
      "eval_samples_per_second": 108.656,
      "eval_steps_per_second": 13.595,
      "step": 148
    },
    {
      "epoch": 1.0135593220338983,
      "grad_norm": 10.889383316040039,
      "learning_rate": 1.4156769596199527e-05,
      "loss": 0.1544,
      "step": 150
    },
    {
      "epoch": 1.1830508474576271,
      "grad_norm": 8.103240013122559,
      "learning_rate": 1.296912114014252e-05,
      "loss": 0.0556,
      "step": 175
    },
    {
      "epoch": 1.352542372881356,
      "grad_norm": 6.277998447418213,
      "learning_rate": 1.1781472684085512e-05,
      "loss": 0.0573,
      "step": 200
    },
    {
      "epoch": 1.5220338983050847,
      "grad_norm": 0.4849356710910797,
      "learning_rate": 1.0593824228028504e-05,
      "loss": 0.051,
      "step": 225
    },
    {
      "epoch": 1.6915254237288135,
      "grad_norm": 7.279757022857666,
      "learning_rate": 9.406175771971498e-06,
      "loss": 0.0636,
      "step": 250
    },
    {
      "epoch": 1.8610169491525423,
      "grad_norm": 0.6995746493339539,
      "learning_rate": 8.21852731591449e-06,
      "loss": 0.0383,
      "step": 275
    },
    {
      "epoch": 2.0,
      "eval_cat_accuracy": 0.9925816023738873,
      "eval_cat_macro_f1": 0.9925873151530334,
      "eval_cat_macro_precision": 0.9926163922277681,
      "eval_cat_macro_recall": 0.9925801130506106,
      "eval_cat_weighted_f1": 0.9925866323108367,
      "eval_imp_accuracy": 0.9950544015825915,
      "eval_imp_f1": 0.9878640776699029,
      "eval_imp_precision": 0.9951100244498777,
      "eval_imp_recall": 0.980722891566265,
      "eval_imp_roc_auc": 0.9997166013150299,
      "eval_loss": 0.0532318614423275,
      "eval_overall_score": 0.9902256964114682,
      "eval_runtime": 18.9313,
      "eval_samples_per_second": 106.807,
      "eval_steps_per_second": 13.364,
      "step": 296
    },
    {
      "epoch": 2.0271186440677966,
      "grad_norm": 16.202281951904297,
      "learning_rate": 7.030878859857483e-06,
      "loss": 0.057,
      "step": 300
    },
    {
      "epoch": 2.1966101694915254,
      "grad_norm": 2.320342779159546,
      "learning_rate": 5.843230403800475e-06,
      "loss": 0.018,
      "step": 325
    },
    {
      "epoch": 2.3661016949152542,
      "grad_norm": 0.3233538269996643,
      "learning_rate": 4.6555819477434686e-06,
      "loss": 0.0064,
      "step": 350
    },
    {
      "epoch": 2.535593220338983,
      "grad_norm": 7.193244457244873,
      "learning_rate": 3.467933491686461e-06,
      "loss": 0.0095,
      "step": 375
    },
    {
      "epoch": 2.705084745762712,
      "grad_norm": 0.5256692171096802,
      "learning_rate": 2.280285035629454e-06,
      "loss": 0.0053,
      "step": 400
    },
    {
      "epoch": 2.8745762711864407,
      "grad_norm": 0.08121078461408615,
      "learning_rate": 1.0926365795724466e-06,
      "loss": 0.0128,
      "step": 425
    },
    {
      "epoch": 3.0,
      "eval_cat_accuracy": 0.9925816023738873,
      "eval_cat_macro_f1": 0.9925865225041758,
      "eval_cat_macro_precision": 0.992650724034855,
      "eval_cat_macro_recall": 0.9925815936643944,
      "eval_cat_weighted_f1": 0.9925916145944671,
      "eval_imp_accuracy": 0.9955489614243324,
      "eval_imp_f1": 0.9891172914147521,
      "eval_imp_precision": 0.9927184466019418,
      "eval_imp_recall": 0.9855421686746988,
      "eval_imp_roc_auc": 0.9998485541418943,
      "eval_loss": 0.04059402272105217,
      "eval_overall_score": 0.9908519069594639,
      "eval_runtime": 19.2839,
      "eval_samples_per_second": 104.854,
      "eval_steps_per_second": 13.12,
      "step": 444
    }
  ],
  "logging_steps": 25,
  "max_steps": 444,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}