{
  "best_metric": 0.02409563586115837,
  "best_model_checkpoint": "./distilbert-question-detector\\checkpoint-3429",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 3429,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17497812773403323,
      "grad_norm": 0.427781343460083,
      "learning_rate": 4.708369787109945e-05,
      "loss": 0.0255,
      "step": 200
    },
    {
      "epoch": 0.34995625546806647,
      "grad_norm": 0.400822252035141,
      "learning_rate": 4.416739574219889e-05,
      "loss": 0.0252,
      "step": 400
    },
    {
      "epoch": 0.5249343832020997,
      "grad_norm": 0.5707641243934631,
      "learning_rate": 4.125109361329834e-05,
      "loss": 0.0274,
      "step": 600
    },
    {
      "epoch": 0.6999125109361329,
      "grad_norm": 0.3984428346157074,
      "learning_rate": 3.8334791484397786e-05,
      "loss": 0.0258,
      "step": 800
    },
    {
      "epoch": 0.8748906386701663,
      "grad_norm": 1.198236107826233,
      "learning_rate": 3.541848935549723e-05,
      "loss": 0.0262,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.024490611627697945,
      "eval_runtime": 55.9659,
      "eval_samples_per_second": 36.308,
      "eval_steps_per_second": 2.269,
      "step": 1143
    },
    {
      "epoch": 1.0498687664041995,
      "grad_norm": 0.8012853860855103,
      "learning_rate": 3.2502187226596675e-05,
      "loss": 0.0274,
      "step": 1200
    },
    {
      "epoch": 1.2248468941382327,
      "grad_norm": 0.4337884187698364,
      "learning_rate": 2.9585885097696126e-05,
      "loss": 0.0183,
      "step": 1400
    },
    {
      "epoch": 1.399825021872266,
      "grad_norm": 0.5056678652763367,
      "learning_rate": 2.666958296879557e-05,
      "loss": 0.0189,
      "step": 1600
    },
    {
      "epoch": 1.574803149606299,
      "grad_norm": 0.5337983965873718,
      "learning_rate": 2.3753280839895015e-05,
      "loss": 0.0206,
      "step": 1800
    },
    {
      "epoch": 1.7497812773403325,
      "grad_norm": 0.26040902733802795,
      "learning_rate": 2.083697871099446e-05,
      "loss": 0.0186,
      "step": 2000
    },
    {
      "epoch": 1.9247594050743657,
      "grad_norm": 0.2849089205265045,
      "learning_rate": 1.7920676582093906e-05,
      "loss": 0.0184,
      "step": 2200
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.024468354880809784,
      "eval_runtime": 59.7745,
      "eval_samples_per_second": 33.994,
      "eval_steps_per_second": 2.125,
      "step": 2286
    },
    {
      "epoch": 2.099737532808399,
      "grad_norm": 0.21000386774539948,
      "learning_rate": 1.500437445319335e-05,
      "loss": 0.0164,
      "step": 2400
    },
    {
      "epoch": 2.2747156605424323,
      "grad_norm": 0.2694750130176544,
      "learning_rate": 1.2088072324292797e-05,
      "loss": 0.0142,
      "step": 2600
    },
    {
      "epoch": 2.4496937882764653,
      "grad_norm": 0.12494825571775436,
      "learning_rate": 9.171770195392243e-06,
      "loss": 0.0154,
      "step": 2800
    },
    {
      "epoch": 2.6246719160104988,
      "grad_norm": 0.21705402433872223,
      "learning_rate": 6.255468066491689e-06,
      "loss": 0.0143,
      "step": 3000
    },
    {
      "epoch": 2.799650043744532,
      "grad_norm": 0.2746178209781647,
      "learning_rate": 3.339165937591135e-06,
      "loss": 0.0146,
      "step": 3200
    },
    {
      "epoch": 2.974628171478565,
      "grad_norm": 0.2427779734134674,
      "learning_rate": 4.2286380869058036e-07,
      "loss": 0.0143,
      "step": 3400
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.02409563586115837,
      "eval_runtime": 62.7666,
      "eval_samples_per_second": 32.374,
      "eval_steps_per_second": 2.023,
      "step": 3429
    }
  ],
  "logging_steps": 200,
  "max_steps": 3429,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1816525437769728.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}