{
  "best_global_step": 20793,
  "best_metric": 0.949582664985337,
  "best_model_checkpoint": "./ner_output_modernbert/combined_300percent_ModernBERT-base_20250619_055856/checkpoints/checkpoint-20793",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 20793,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24989179050642044,
      "grad_norm": 0.1257457733154297,
      "learning_rate": 4.5842350791131636e-05,
      "loss": 0.3051,
      "step": 1732
    },
    {
      "epoch": 0.49978358101284087,
      "grad_norm": 0.5818042755126953,
      "learning_rate": 4.1677487616024626e-05,
      "loss": 0.1847,
      "step": 3464
    },
    {
      "epoch": 0.7496753715192613,
      "grad_norm": 0.45203471183776855,
      "learning_rate": 3.751262444091762e-05,
      "loss": 0.1685,
      "step": 5196
    },
    {
      "epoch": 0.9995671620256817,
      "grad_norm": 0.9936078786849976,
      "learning_rate": 3.3350165921223495e-05,
      "loss": 0.1611,
      "step": 6928
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9448721639042021,
      "eval_f1": 0.9438293472729468,
      "eval_loss": 0.1583022028207779,
      "eval_precision": 0.9438239601502502,
      "eval_recall": 0.9448721639042021,
      "eval_runtime": 66.8003,
      "eval_samples_per_second": 292.948,
      "eval_steps_per_second": 18.323,
      "step": 6931
    },
    {
      "epoch": 1.2494589525321023,
      "grad_norm": 2.6818487644195557,
      "learning_rate": 2.9187707401529363e-05,
      "loss": 0.1245,
      "step": 8660
    },
    {
      "epoch": 1.4993507430385224,
      "grad_norm": 0.14635096490383148,
      "learning_rate": 2.5022844226422353e-05,
      "loss": 0.1212,
      "step": 10392
    },
    {
      "epoch": 1.749242533544943,
      "grad_norm": 0.5487073659896851,
      "learning_rate": 2.0857981051315347e-05,
      "loss": 0.1218,
      "step": 12124
    },
    {
      "epoch": 1.9991343240513635,
      "grad_norm": 1.3607397079467773,
      "learning_rate": 1.669552253162122e-05,
      "loss": 0.1117,
      "step": 13856
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9494521830695967,
      "eval_f1": 0.9492911172803227,
      "eval_loss": 0.14517587423324585,
      "eval_precision": 0.9494150440403941,
      "eval_recall": 0.9494521830695967,
      "eval_runtime": 63.4366,
      "eval_samples_per_second": 308.481,
      "eval_steps_per_second": 19.295,
      "step": 13862
    },
    {
      "epoch": 2.249026114557784,
      "grad_norm": 0.0037306402809917927,
      "learning_rate": 1.2533064011927093e-05,
      "loss": 0.0739,
      "step": 15588
    },
    {
      "epoch": 2.4989179050642045,
      "grad_norm": 0.5977134108543396,
      "learning_rate": 8.368200836820084e-06,
      "loss": 0.0709,
      "step": 17320
    },
    {
      "epoch": 2.7488096955706247,
      "grad_norm": 0.007765794638544321,
      "learning_rate": 4.205742317125956e-06,
      "loss": 0.0679,
      "step": 19052
    },
    {
      "epoch": 2.998701486077045,
      "grad_norm": 2.047842025756836,
      "learning_rate": 4.328379743182802e-08,
      "loss": 0.0643,
      "step": 20784
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.949984150291671,
      "eval_f1": 0.949582664985337,
      "eval_loss": 0.1690009981393814,
      "eval_precision": 0.9493962920968388,
      "eval_recall": 0.949984150291671,
      "eval_runtime": 64.0908,
      "eval_samples_per_second": 305.333,
      "eval_steps_per_second": 19.098,
      "step": 20793
    }
  ],
  "logging_steps": 1732,
  "max_steps": 20793,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.834282538205184e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}