checkpoint-10321/trainer_state.json

{
  "best_metric": 0.9074625976038624,
  "best_model_checkpoint": "large-bert-cased-ner-finetuned-wikineural-final/checkpoint-10321",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 10321,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 1.9031101637438233e-05,
      "loss": 0.0102,
      "step": 500
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.8062203274876465e-05,
      "loss": 0.0094,
      "step": 1000
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.70933049123147e-05,
      "loss": 0.0093,
      "step": 1500
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.6124406549752932e-05,
      "loss": 0.0096,
      "step": 2000
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.5155508187191165e-05,
      "loss": 0.0075,
      "step": 2500
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.4186609824629399e-05,
      "loss": 0.0088,
      "step": 3000
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.321771146206763e-05,
      "loss": 0.0091,
      "step": 3500
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.2248813099505862e-05,
      "loss": 0.0079,
      "step": 4000
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.1279914736944096e-05,
      "loss": 0.0078,
      "step": 4500
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.0311016374382327e-05,
      "loss": 0.0067,
      "step": 5000
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.34211801182056e-06,
      "loss": 0.0072,
      "step": 5500
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.373219649258794e-06,
      "loss": 0.0071,
      "step": 6000
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.404321286697026e-06,
      "loss": 0.0083,
      "step": 6500
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.4354229241352584e-06,
      "loss": 0.0069,
      "step": 7000
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.466524561573492e-06,
      "loss": 0.0073,
      "step": 7500
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.497626199011724e-06,
      "loss": 0.0075,
      "step": 8000
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.5287278364499566e-06,
      "loss": 0.0093,
      "step": 8500
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.5598294738881896e-06,
      "loss": 0.0096,
      "step": 9000
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.590931111326422e-06,
      "loss": 0.0185,
      "step": 9500
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.220327487646547e-07,
      "loss": 0.0273,
      "step": 10000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.985668743706954,
      "eval_f1": 0.9074625976038624,
      "eval_loss": 0.06917199492454529,
      "eval_precision": 0.9032363323544244,
      "eval_recall": 0.9117285983770997,
      "eval_runtime": 130.7154,
      "eval_samples_per_second": 89.025,
      "eval_steps_per_second": 11.131,
      "step": 10321
    }
  ],
  "logging_steps": 500,
  "max_steps": 10321,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 9117385527900702.0,
  "trial_name": null,
  "trial_params": null
}