{
  "best_global_step": 500,
  "best_metric": 0.9709055246812683,
  "best_model_checkpoint": "/kaggle/working/outputs/bert_rd_keystrokes/checkpoint-500",
  "epoch": 0.4045307443365696,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008090614886731392,
      "grad_norm": 2.5394184589385986,
      "learning_rate": 0.0,
      "loss": 0.6913009285926819,
      "step": 1
    },
    {
      "epoch": 0.020226537216828478,
      "grad_norm": 3.3882575035095215,
      "learning_rate": 9.716599190283402e-07,
      "loss": 0.710881233215332,
      "step": 25
    },
    {
      "epoch": 0.040453074433656956,
      "grad_norm": 4.59527063369751,
      "learning_rate": 1.9838056680161946e-06,
      "loss": 0.6965625762939454,
      "step": 50
    },
    {
      "epoch": 0.06067961165048544,
      "grad_norm": 6.466946125030518,
      "learning_rate": 2.995951417004049e-06,
      "loss": 0.6713954925537109,
      "step": 75
    },
    {
      "epoch": 0.08090614886731391,
      "grad_norm": 5.92415714263916,
      "learning_rate": 4.008097165991903e-06,
      "loss": 0.6306858444213868,
      "step": 100
    },
    {
      "epoch": 0.1011326860841424,
      "grad_norm": 7.790467262268066,
      "learning_rate": 5.020242914979757e-06,
      "loss": 0.5511775207519531,
      "step": 125
    },
    {
      "epoch": 0.12135922330097088,
      "grad_norm": 5.874857425689697,
      "learning_rate": 6.0323886639676124e-06,
      "loss": 0.5026376342773438,
      "step": 150
    },
    {
      "epoch": 0.14158576051779936,
      "grad_norm": 12.701870918273926,
      "learning_rate": 7.044534412955466e-06,
      "loss": 0.4295468521118164,
      "step": 175
    },
    {
      "epoch": 0.16181229773462782,
      "grad_norm": 5.137658596038818,
      "learning_rate": 8.056680161943322e-06,
      "loss": 0.3788005828857422,
      "step": 200
    },
    {
      "epoch": 0.1820388349514563,
      "grad_norm": 5.249273300170898,
      "learning_rate": 9.068825910931175e-06,
      "loss": 0.2651861381530762,
      "step": 225
    },
    {
      "epoch": 0.2022653721682848,
      "grad_norm": 38.753013610839844,
      "learning_rate": 1.008097165991903e-05,
      "loss": 0.3065790557861328,
      "step": 250
    },
    {
      "epoch": 0.22249190938511326,
      "grad_norm": 13.836112022399902,
      "learning_rate": 1.1093117408906884e-05,
      "loss": 0.38094028472900393,
      "step": 275
    },
    {
      "epoch": 0.24271844660194175,
      "grad_norm": 6.559873580932617,
      "learning_rate": 1.2105263157894737e-05,
      "loss": 0.3118729019165039,
      "step": 300
    },
    {
      "epoch": 0.26294498381877024,
      "grad_norm": 7.356478214263916,
      "learning_rate": 1.3117408906882592e-05,
      "loss": 0.23761932373046876,
      "step": 325
    },
    {
      "epoch": 0.28317152103559873,
      "grad_norm": 4.0845184326171875,
      "learning_rate": 1.4129554655870446e-05,
      "loss": 0.26587358474731443,
      "step": 350
    },
    {
      "epoch": 0.30339805825242716,
      "grad_norm": 28.685104370117188,
      "learning_rate": 1.5141700404858302e-05,
      "loss": 0.3239314651489258,
      "step": 375
    },
    {
      "epoch": 0.32362459546925565,
      "grad_norm": 1.7896462678909302,
      "learning_rate": 1.6153846153846154e-05,
      "loss": 0.24046634674072265,
      "step": 400
    },
    {
      "epoch": 0.34385113268608414,
      "grad_norm": 6.960549831390381,
      "learning_rate": 1.716599190283401e-05,
      "loss": 0.27144105911254884,
      "step": 425
    },
    {
      "epoch": 0.3640776699029126,
      "grad_norm": 22.062820434570312,
      "learning_rate": 1.8178137651821864e-05,
      "loss": 0.24825719833374024,
      "step": 450
    },
    {
      "epoch": 0.3843042071197411,
      "grad_norm": 0.4285735785961151,
      "learning_rate": 1.9190283400809718e-05,
      "loss": 0.22249792098999024,
      "step": 475
    },
    {
      "epoch": 0.4045307443365696,
      "grad_norm": 0.26966607570648193,
      "learning_rate": 1.999993769982229e-05,
      "loss": 0.25503772735595703,
      "step": 500
    },
    {
      "epoch": 0.4045307443365696,
      "eval_accuracy": 0.9550277918140475,
      "eval_f1": 0.9709055246812683,
      "eval_loss": 0.1790667176246643,
      "eval_precision": 0.9574468085106383,
      "eval_recall": 0.9847480106100795,
      "eval_runtime": 34.5481,
      "eval_samples_per_second": 57.282,
      "eval_steps_per_second": 3.589,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 4944,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 2104888442880000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}