{
  "best_global_step": 375,
  "best_metric": 1.0,
  "best_model_checkpoint": "models/ner_model\\checkpoint-375",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.993857204914093,
      "learning_rate": 2.9216e-05,
      "loss": 0.40569305419921875,
      "step": 50
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.08527682721614838,
      "learning_rate": 2.8416e-05,
      "loss": 0.004504955112934112,
      "step": 100
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0359872430562973,
      "learning_rate": 2.7616e-05,
      "loss": 0.002728268802165985,
      "step": 150
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.016103407368063927,
      "learning_rate": 2.6816000000000002e-05,
      "loss": 0.0020892390608787535,
      "step": 200
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.008038675412535667,
      "learning_rate": 2.6016e-05,
      "loss": 0.001044714003801346,
      "step": 250
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.009728889912366867,
      "learning_rate": 2.5216e-05,
      "loss": 0.0016367894411087036,
      "step": 300
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.007115095388144255,
      "learning_rate": 2.4415999999999998e-05,
      "loss": 0.0016412661969661712,
      "step": 350
    },
    {
      "epoch": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.00031773943919688463,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 1.3005,
      "eval_samples_per_second": 576.687,
      "eval_steps_per_second": 36.139,
      "step": 375
    }
  ],
  "logging_steps": 50,
  "max_steps": 1875,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 97995140352000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}