{
  "best_global_step": 4266,
  "best_metric": 0.3941958546638489,
  "best_model_checkpoint": "bert_base_rand_100_v1_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": 1.7090692520141602,
      "learning_rate": 4.9e-05,
      "loss": 0.4745,
      "step": 1422
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7917140737076428,
      "eval_combined_score": 0.7351938552611171,
      "eval_f1": 0.6786736368145915,
      "eval_loss": 0.4387166500091553,
      "eval_runtime": 25.3572,
      "eval_samples_per_second": 1594.42,
      "eval_steps_per_second": 6.231,
      "step": 1422
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.5258407592773438,
      "learning_rate": 4.8e-05,
      "loss": 0.3731,
      "step": 2844
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8202077665100174,
      "eval_combined_score": 0.78448607659825,
      "eval_f1": 0.7487643866864826,
      "eval_loss": 0.3947214186191559,
      "eval_runtime": 25.166,
      "eval_samples_per_second": 1606.535,
      "eval_steps_per_second": 6.278,
      "step": 2844
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.0430142879486084,
      "learning_rate": 4.7e-05,
      "loss": 0.2984,
      "step": 4266
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8215186742517933,
      "eval_combined_score": 0.7984725202455282,
      "eval_f1": 0.7754263662392631,
      "eval_loss": 0.3941958546638489,
      "eval_runtime": 25.2045,
      "eval_samples_per_second": 1604.077,
      "eval_steps_per_second": 6.269,
      "step": 4266
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.575798749923706,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.2356,
      "step": 5688
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8369774919614148,
      "eval_combined_score": 0.8022904454976496,
      "eval_f1": 0.7676033990338845,
      "eval_loss": 0.429512083530426,
      "eval_runtime": 25.2032,
      "eval_samples_per_second": 1604.163,
      "eval_steps_per_second": 6.269,
      "step": 5688
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.4301187992095947,
      "learning_rate": 4.5e-05,
      "loss": 0.1843,
      "step": 7110
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8408360128617364,
      "eval_combined_score": 0.8085399856373774,
      "eval_f1": 0.7762439584130185,
      "eval_loss": 0.4590463936328888,
      "eval_runtime": 25.1669,
      "eval_samples_per_second": 1606.475,
      "eval_steps_per_second": 6.278,
      "step": 7110
    },
    {
      "epoch": 6.0,
      "grad_norm": 3.801884651184082,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.1461,
      "step": 8532
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8405392035617116,
      "eval_combined_score": 0.8094621355541878,
      "eval_f1": 0.7783850675466639,
      "eval_loss": 0.534358024597168,
      "eval_runtime": 25.1681,
      "eval_samples_per_second": 1606.402,
      "eval_steps_per_second": 6.278,
      "step": 8532
    },
    {
      "epoch": 7.0,
      "grad_norm": 5.741505146026611,
      "learning_rate": 4.3e-05,
      "loss": 0.1169,
      "step": 9954
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8414048973534504,
      "eval_combined_score": 0.8124939972118946,
      "eval_f1": 0.7835830970703389,
      "eval_loss": 0.5649517774581909,
      "eval_runtime": 25.1991,
      "eval_samples_per_second": 1604.423,
      "eval_steps_per_second": 6.27,
      "step": 9954
    },
    {
      "epoch": 8.0,
      "grad_norm": 4.853621006011963,
      "learning_rate": 4.2e-05,
      "loss": 0.0952,
      "step": 11376
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8356665842196389,
      "eval_combined_score": 0.8105266185520961,
      "eval_f1": 0.7853866528845532,
      "eval_loss": 0.5598284006118774,
      "eval_runtime": 25.1588,
      "eval_samples_per_second": 1606.991,
      "eval_steps_per_second": 6.28,
      "step": 11376
    },
    {
      "epoch": 8.0,
      "step": 11376,
      "total_flos": 3.8292762019405824e+17,
      "train_loss": 0.24051325431855922,
      "train_runtime": 4857.9006,
      "train_samples_per_second": 3744.889,
      "train_steps_per_second": 14.636
    }
  ],
  "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": 3.8292762019405824e+17,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}