{
  "best_global_step": 609,
  "best_metric": 0.8755947274003588,
  "best_model_checkpoint": "./ner_crf_boundary_output/checkpoint-609",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 609,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08213552361396304,
      "grad_norm": 289.9013977050781,
      "learning_rate": 2.677595628415301e-06,
      "loss": 7.03633056640625,
      "step": 50
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 397.5795593261719,
      "learning_rate": 5.409836065573772e-06,
      "loss": 5.944567260742187,
      "step": 100
    },
    {
      "epoch": 0.2464065708418891,
      "grad_norm": 1030.340576171875,
      "learning_rate": 8.14207650273224e-06,
      "loss": 6.386118774414062,
      "step": 150
    },
    {
      "epoch": 0.32854209445585214,
      "grad_norm": 416.71173095703125,
      "learning_rate": 9.944095038434662e-06,
      "loss": 6.638558349609375,
      "step": 200
    },
    {
      "epoch": 0.4106776180698152,
      "grad_norm": 379.8328857421875,
      "learning_rate": 9.769392033542979e-06,
      "loss": 5.887216186523437,
      "step": 250
    },
    {
      "epoch": 0.4928131416837782,
      "grad_norm": 328.294921875,
      "learning_rate": 9.594689028651294e-06,
      "loss": 6.057736206054687,
      "step": 300
    },
    {
      "epoch": 0.5749486652977412,
      "grad_norm": 306.49560546875,
      "learning_rate": 9.41998602375961e-06,
      "loss": 6.300731201171875,
      "step": 350
    },
    {
      "epoch": 0.6570841889117043,
      "grad_norm": 406.1339111328125,
      "learning_rate": 9.245283018867926e-06,
      "loss": 5.523515625,
      "step": 400
    },
    {
      "epoch": 0.7392197125256673,
      "grad_norm": 405.34136962890625,
      "learning_rate": 9.070580013976241e-06,
      "loss": 6.377322998046875,
      "step": 450
    },
    {
      "epoch": 0.8213552361396304,
      "grad_norm": 219.61463928222656,
      "learning_rate": 8.895877009084557e-06,
      "loss": 5.774469604492188,
      "step": 500
    },
    {
      "epoch": 0.9034907597535934,
      "grad_norm": 294.69683837890625,
      "learning_rate": 8.721174004192873e-06,
      "loss": 6.709805297851562,
      "step": 550
    },
    {
      "epoch": 0.9856262833675564,
      "grad_norm": 397.64190673828125,
      "learning_rate": 8.546470999301189e-06,
      "loss": 5.980140991210938,
      "step": 600
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.8755947274003588,
      "eval_loss": 4.1545538902282715,
      "eval_precision": 0.8619471744471745,
      "eval_recall": 0.8896814075130766,
      "eval_runtime": 44.15,
      "eval_samples_per_second": 49.015,
      "eval_steps_per_second": 6.138,
      "step": 609
    }
  ],
  "logging_steps": 50,
  "max_steps": 3045,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}