{
  "best_metric": 0.3060251772403717,
  "best_model_checkpoint": "bert_tiny_lda_100_v1_book_qqp/checkpoint-4266",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 11376,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.0717172622680664,
      "learning_rate": 4.9e-05,
      "loss": 0.4139,
      "step": 1422
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8294830571357903,
      "eval_combined_score": 0.7856500747442116,
      "eval_f1": 0.7418170923526328,
      "eval_loss": 0.3737279772758484,
      "eval_runtime": 12.7578,
      "eval_samples_per_second": 3169.046,
      "eval_steps_per_second": 12.385,
      "step": 1422
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.549527406692505,
      "learning_rate": 4.8e-05,
      "loss": 0.3158,
      "step": 2844
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8610932475884244,
      "eval_combined_score": 0.8358800470293277,
      "eval_f1": 0.8106668464702311,
      "eval_loss": 0.32144734263420105,
      "eval_runtime": 13.0019,
      "eval_samples_per_second": 3109.553,
      "eval_steps_per_second": 12.152,
      "step": 2844
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.0585994720458984,
      "learning_rate": 4.7e-05,
      "loss": 0.2619,
      "step": 4266
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.869972792480831,
      "eval_combined_score": 0.8459420519198084,
      "eval_f1": 0.8219113113587858,
      "eval_loss": 0.3060251772403717,
      "eval_runtime": 12.7813,
      "eval_samples_per_second": 3163.218,
      "eval_steps_per_second": 12.362,
      "step": 4266
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.6563196182250977,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.218,
      "step": 5688
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8693544397724462,
      "eval_combined_score": 0.8405239222035137,
      "eval_f1": 0.8116934046345811,
      "eval_loss": 0.33707308769226074,
      "eval_runtime": 12.7128,
      "eval_samples_per_second": 3180.257,
      "eval_steps_per_second": 12.428,
      "step": 5688
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.4991559982299805,
      "learning_rate": 4.5e-05,
      "loss": 0.1821,
      "step": 7110
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8786544645065545,
      "eval_combined_score": 0.856382753995348,
      "eval_f1": 0.8341110434841416,
      "eval_loss": 0.3295314610004425,
      "eval_runtime": 12.6824,
      "eval_samples_per_second": 3187.893,
      "eval_steps_per_second": 12.458,
      "step": 7110
    },
    {
      "epoch": 6.0,
      "grad_norm": 3.619370222091675,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.1502,
      "step": 8532
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8789760079149147,
      "eval_combined_score": 0.8589235754660027,
      "eval_f1": 0.8388711430170909,
      "eval_loss": 0.3353230953216553,
      "eval_runtime": 12.5466,
      "eval_samples_per_second": 3222.377,
      "eval_steps_per_second": 12.593,
      "step": 8532
    },
    {
      "epoch": 7.0,
      "grad_norm": 6.655024528503418,
      "learning_rate": 4.3e-05,
      "loss": 0.1258,
      "step": 9954
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8775908978481326,
      "eval_combined_score": 0.8575604270928723,
      "eval_f1": 0.8375299563376121,
      "eval_loss": 0.3608565628528595,
      "eval_runtime": 12.8466,
      "eval_samples_per_second": 3147.132,
      "eval_steps_per_second": 12.299,
      "step": 9954
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.941072702407837,
      "learning_rate": 4.2e-05,
      "loss": 0.105,
      "step": 11376
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8786049962898838,
      "eval_combined_score": 0.8557762898399726,
      "eval_f1": 0.8329475833900613,
      "eval_loss": 0.40695515275001526,
      "eval_runtime": 12.5971,
      "eval_samples_per_second": 3209.48,
      "eval_steps_per_second": 12.543,
      "step": 11376
    },
    {
      "epoch": 8.0,
      "step": 11376,
      "total_flos": 7.633075201391002e+16,
      "train_loss": 0.22156743694793657,
      "train_runtime": 1704.2728,
      "train_samples_per_second": 10674.524,
      "train_steps_per_second": 41.719
    }
  ],
  "logging_steps": 1,
  "max_steps": 71100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.633075201391002e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}