{
  "best_global_step": 92,
  "best_metric": 2.239424228668213,
  "best_model_checkpoint": "bert_base_km_5_v1_stsb/checkpoint-92",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 207,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 4.2634968757629395,
      "learning_rate": 4.9e-05,
      "loss": 2.6517,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.12675379829831443,
      "eval_loss": 2.325453996658325,
      "eval_pearson": 0.1330184139107724,
      "eval_runtime": 0.9532,
      "eval_samples_per_second": 1573.642,
      "eval_spearmanr": 0.12048918268585644,
      "eval_steps_per_second": 6.295,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.955192565917969,
      "learning_rate": 4.8e-05,
      "loss": 1.9658,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.2335786038892586,
      "eval_loss": 2.3460726737976074,
      "eval_pearson": 0.23856360343594119,
      "eval_runtime": 0.9829,
      "eval_samples_per_second": 1526.133,
      "eval_spearmanr": 0.22859360434257603,
      "eval_steps_per_second": 6.105,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.839750289916992,
      "learning_rate": 4.7e-05,
      "loss": 1.6725,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.2386789341364155,
      "eval_loss": 2.437448024749756,
      "eval_pearson": 0.24243548982978144,
      "eval_runtime": 0.9837,
      "eval_samples_per_second": 1524.783,
      "eval_spearmanr": 0.23492237844304958,
      "eval_steps_per_second": 6.099,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.305805206298828,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.2633,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.32212437726050713,
      "eval_loss": 2.239424228668213,
      "eval_pearson": 0.3226858166168006,
      "eval_runtime": 0.9602,
      "eval_samples_per_second": 1562.241,
      "eval_spearmanr": 0.3215629379042137,
      "eval_steps_per_second": 6.249,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.919197082519531,
      "learning_rate": 4.5e-05,
      "loss": 0.877,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.31245569201685475,
      "eval_loss": 2.488182783126831,
      "eval_pearson": 0.3102391372649197,
      "eval_runtime": 0.9527,
      "eval_samples_per_second": 1574.471,
      "eval_spearmanr": 0.31467224676878985,
      "eval_steps_per_second": 6.298,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 9.296478271484375,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6898,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.3107272405919173,
      "eval_loss": 2.4794673919677734,
      "eval_pearson": 0.3146900459752465,
      "eval_runtime": 0.9695,
      "eval_samples_per_second": 1547.22,
      "eval_spearmanr": 0.3067644352085881,
      "eval_steps_per_second": 6.189,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 7.156578540802002,
      "learning_rate": 4.3e-05,
      "loss": 0.4742,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.2962889521612072,
      "eval_loss": 2.667475700378418,
      "eval_pearson": 0.2998348435139836,
      "eval_runtime": 1.004,
      "eval_samples_per_second": 1494.084,
      "eval_spearmanr": 0.2927430608084309,
      "eval_steps_per_second": 5.976,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 6.3387346267700195,
      "learning_rate": 4.2e-05,
      "loss": 0.3676,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.36138029385170867,
      "eval_loss": 2.336973190307617,
      "eval_pearson": 0.3624171116259935,
      "eval_runtime": 0.9576,
      "eval_samples_per_second": 1566.335,
      "eval_spearmanr": 0.3603434760774238,
      "eval_steps_per_second": 6.265,
      "step": 184
    },
    {
      "epoch": 9.0,
      "grad_norm": 10.670768737792969,
      "learning_rate": 4.1e-05,
      "loss": 0.3107,
      "step": 207
    },
    {
      "epoch": 9.0,
      "eval_combined_score": 0.3364466316742135,
      "eval_loss": 2.4862287044525146,
      "eval_pearson": 0.33953987332588476,
      "eval_runtime": 0.9553,
      "eval_samples_per_second": 1570.153,
      "eval_spearmanr": 0.3333533900225422,
      "eval_steps_per_second": 6.281,
      "step": 207
    },
    {
      "epoch": 9.0,
      "step": 207,
      "total_flos": 6806753442049536.0,
      "train_loss": 1.1414002612017202,
      "train_runtime": 111.1051,
      "train_samples_per_second": 2587.189,
      "train_steps_per_second": 10.351
    }
  ],
  "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": 6806753442049536.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}