{
  "best_global_step": 4266,
  "best_metric": 0.3970997929573059,
  "best_model_checkpoint": "bert_base_rand_50_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": 1.6554219722747803,
      "learning_rate": 4.9e-05,
      "loss": 0.4755,
      "step": 1422
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7925550333910463,
      "eval_combined_score": 0.7395053009117556,
      "eval_f1": 0.6864555684324648,
      "eval_loss": 0.4303272068500519,
      "eval_runtime": 25.3764,
      "eval_samples_per_second": 1593.214,
      "eval_steps_per_second": 6.226,
      "step": 1422
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.614877462387085,
      "learning_rate": 4.8e-05,
      "loss": 0.372,
      "step": 2844
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8147167944595597,
      "eval_combined_score": 0.7843251876249446,
      "eval_f1": 0.7539335807903295,
      "eval_loss": 0.4021649956703186,
      "eval_runtime": 25.1257,
      "eval_samples_per_second": 1609.111,
      "eval_steps_per_second": 6.288,
      "step": 2844
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.6068978309631348,
      "learning_rate": 4.7e-05,
      "loss": 0.2948,
      "step": 4266
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8231758595102646,
      "eval_combined_score": 0.7982017283276938,
      "eval_f1": 0.7732275971451229,
      "eval_loss": 0.3970997929573059,
      "eval_runtime": 25.1736,
      "eval_samples_per_second": 1606.048,
      "eval_steps_per_second": 6.276,
      "step": 4266
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.1879727840423584,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.2314,
      "step": 5688
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8338115260944843,
      "eval_combined_score": 0.8023291797110668,
      "eval_f1": 0.7708468333276491,
      "eval_loss": 0.4344772696495056,
      "eval_runtime": 25.1738,
      "eval_samples_per_second": 1606.034,
      "eval_steps_per_second": 6.276,
      "step": 5688
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.4959449768066406,
      "learning_rate": 4.5e-05,
      "loss": 0.1814,
      "step": 7110
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8370022260697502,
      "eval_combined_score": 0.8042025144501658,
      "eval_f1": 0.7714028028305814,
      "eval_loss": 0.4801643192768097,
      "eval_runtime": 25.1837,
      "eval_samples_per_second": 1605.404,
      "eval_steps_per_second": 6.274,
      "step": 7110
    },
    {
      "epoch": 6.0,
      "grad_norm": 3.7248945236206055,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.1452,
      "step": 8532
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8405392035617116,
      "eval_combined_score": 0.8121601340275607,
      "eval_f1": 0.7837810644934098,
      "eval_loss": 0.5378713011741638,
      "eval_runtime": 25.1544,
      "eval_samples_per_second": 1607.276,
      "eval_steps_per_second": 6.281,
      "step": 8532
    },
    {
      "epoch": 7.0,
      "grad_norm": 7.881701946258545,
      "learning_rate": 4.3e-05,
      "loss": 0.116,
      "step": 9954
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8401681919366807,
      "eval_combined_score": 0.8116030323100003,
      "eval_f1": 0.7830378726833199,
      "eval_loss": 0.6317501664161682,
      "eval_runtime": 25.1574,
      "eval_samples_per_second": 1607.083,
      "eval_steps_per_second": 6.28,
      "step": 9954
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.5291764736175537,
      "learning_rate": 4.2e-05,
      "loss": 0.0952,
      "step": 11376
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8337867919861489,
      "eval_combined_score": 0.8095039815210724,
      "eval_f1": 0.7852211710559959,
      "eval_loss": 0.6206209659576416,
      "eval_runtime": 25.1799,
      "eval_samples_per_second": 1605.645,
      "eval_steps_per_second": 6.275,
      "step": 11376
    },
    {
      "epoch": 8.0,
      "step": 11376,
      "total_flos": 3.8292762019405824e+17,
      "train_loss": 0.2389356543410847,
      "train_runtime": 4865.684,
      "train_samples_per_second": 3738.899,
      "train_steps_per_second": 14.613
    }
  ],
  "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
}