{
  "best_global_step": 69,
  "best_metric": 2.342188835144043,
  "best_model_checkpoint": "bert_base_rand_10_v1_stsb/checkpoint-69",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 184,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 6.409469127655029,
      "learning_rate": 4.9e-05,
      "loss": 2.5501,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.11660962062209998,
      "eval_loss": 2.5206260681152344,
      "eval_pearson": 0.12466393002920396,
      "eval_runtime": 0.9623,
      "eval_samples_per_second": 1558.766,
      "eval_spearmanr": 0.10855531121499598,
      "eval_steps_per_second": 6.235,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.4389872550964355,
      "learning_rate": 4.8e-05,
      "loss": 1.9123,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.15291538722011827,
      "eval_loss": 2.3921282291412354,
      "eval_pearson": 0.16244375887475837,
      "eval_runtime": 0.9815,
      "eval_samples_per_second": 1528.239,
      "eval_spearmanr": 0.1433870155654782,
      "eval_steps_per_second": 6.113,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.024801254272461,
      "learning_rate": 4.7e-05,
      "loss": 1.6606,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.22688924377276753,
      "eval_loss": 2.342188835144043,
      "eval_pearson": 0.22998859981501937,
      "eval_runtime": 0.9655,
      "eval_samples_per_second": 1553.543,
      "eval_spearmanr": 0.2237898877305157,
      "eval_steps_per_second": 6.214,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.618351936340332,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.2907,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.26417223938248946,
      "eval_loss": 2.5929768085479736,
      "eval_pearson": 0.2616769184082946,
      "eval_runtime": 0.9533,
      "eval_samples_per_second": 1573.558,
      "eval_spearmanr": 0.2666675603566844,
      "eval_steps_per_second": 6.294,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 9.85341739654541,
      "learning_rate": 4.5e-05,
      "loss": 0.9783,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.28284175884292595,
      "eval_loss": 2.470913887023926,
      "eval_pearson": 0.28538506851887113,
      "eval_runtime": 0.9872,
      "eval_samples_per_second": 1519.39,
      "eval_spearmanr": 0.28029844916698077,
      "eval_steps_per_second": 6.078,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 9.521453857421875,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.7673,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.3047270812690138,
      "eval_loss": 2.468660593032837,
      "eval_pearson": 0.3073468779629231,
      "eval_runtime": 0.9776,
      "eval_samples_per_second": 1534.407,
      "eval_spearmanr": 0.3021072845751046,
      "eval_steps_per_second": 6.138,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 14.15671443939209,
      "learning_rate": 4.3e-05,
      "loss": 0.5922,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.3050835905547613,
      "eval_loss": 2.4916512966156006,
      "eval_pearson": 0.30686700146863255,
      "eval_runtime": 0.9563,
      "eval_samples_per_second": 1568.561,
      "eval_spearmanr": 0.30330017964089,
      "eval_steps_per_second": 6.274,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 5.233458518981934,
      "learning_rate": 4.2e-05,
      "loss": 0.4832,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.29110873134498483,
      "eval_loss": 2.7526607513427734,
      "eval_pearson": 0.2930574079479448,
      "eval_runtime": 1.0031,
      "eval_samples_per_second": 1495.347,
      "eval_spearmanr": 0.2891600547420248,
      "eval_steps_per_second": 5.981,
      "step": 184
    },
    {
      "epoch": 8.0,
      "step": 184,
      "total_flos": 6050447504044032.0,
      "train_loss": 1.2793446831081225,
      "train_runtime": 98.3058,
      "train_samples_per_second": 2924.039,
      "train_steps_per_second": 11.698
    }
  ],
  "logging_steps": 1,
  "max_steps": 1150,
  "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": 6050447504044032.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}