{
  "best_global_step": 69,
  "best_metric": 2.1733975410461426,
  "best_model_checkpoint": "bert_base_km_20_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": 12.473910331726074,
      "learning_rate": 4.9e-05,
      "loss": 2.7536,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.21883840300992635,
      "eval_loss": 2.362926721572876,
      "eval_pearson": 0.22315559305765864,
      "eval_runtime": 0.9537,
      "eval_samples_per_second": 1572.84,
      "eval_spearmanr": 0.21452121296219404,
      "eval_steps_per_second": 6.291,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 11.219836235046387,
      "learning_rate": 4.8e-05,
      "loss": 2.0466,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.2250433116133167,
      "eval_loss": 2.223330020904541,
      "eval_pearson": 0.22643903431708493,
      "eval_runtime": 0.9462,
      "eval_samples_per_second": 1585.334,
      "eval_spearmanr": 0.2236475889095485,
      "eval_steps_per_second": 6.341,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.506649017333984,
      "learning_rate": 4.7e-05,
      "loss": 1.83,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.27859606936951653,
      "eval_loss": 2.1733975410461426,
      "eval_pearson": 0.27650731213075436,
      "eval_runtime": 0.9646,
      "eval_samples_per_second": 1555.115,
      "eval_spearmanr": 0.2806848266082787,
      "eval_steps_per_second": 6.22,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.99960994720459,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.488,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.2857232862338934,
      "eval_loss": 2.284653902053833,
      "eval_pearson": 0.28481215085198996,
      "eval_runtime": 0.9772,
      "eval_samples_per_second": 1534.935,
      "eval_spearmanr": 0.28663442161579694,
      "eval_steps_per_second": 6.14,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 17.941621780395508,
      "learning_rate": 4.5e-05,
      "loss": 1.1184,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.2801317348206342,
      "eval_loss": 2.755934238433838,
      "eval_pearson": 0.27054585694075417,
      "eval_runtime": 0.9542,
      "eval_samples_per_second": 1572.032,
      "eval_spearmanr": 0.2897176127005142,
      "eval_steps_per_second": 6.288,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 7.229860305786133,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.836,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.30899397408639784,
      "eval_loss": 2.474417209625244,
      "eval_pearson": 0.3009404135965045,
      "eval_runtime": 0.9638,
      "eval_samples_per_second": 1556.332,
      "eval_spearmanr": 0.31704753457629126,
      "eval_steps_per_second": 6.225,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 6.495700836181641,
      "learning_rate": 4.3e-05,
      "loss": 0.5651,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.2980624641456129,
      "eval_loss": 2.5624561309814453,
      "eval_pearson": 0.29500261904772385,
      "eval_runtime": 0.9704,
      "eval_samples_per_second": 1545.698,
      "eval_spearmanr": 0.301122309243502,
      "eval_steps_per_second": 6.183,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 5.729962348937988,
      "learning_rate": 4.2e-05,
      "loss": 0.4161,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.31179634058913464,
      "eval_loss": 2.499624252319336,
      "eval_pearson": 0.3084881703414194,
      "eval_runtime": 0.9545,
      "eval_samples_per_second": 1571.47,
      "eval_spearmanr": 0.3151045108368498,
      "eval_steps_per_second": 6.286,
      "step": 184
    },
    {
      "epoch": 8.0,
      "step": 184,
      "total_flos": 6050447504044032.0,
      "train_loss": 1.3817211441371753,
      "train_runtime": 98.9888,
      "train_samples_per_second": 2903.865,
      "train_steps_per_second": 11.617
    }
  ],
  "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
}