{
  "best_global_step": 92,
  "best_metric": 2.249025583267212,
  "best_model_checkpoint": "bert_base_km_100_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": 15.534356117248535,
      "learning_rate": 4.9e-05,
      "loss": 2.7396,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.14323997934834215,
      "eval_loss": 2.554664134979248,
      "eval_pearson": 0.15140930091264632,
      "eval_runtime": 0.9464,
      "eval_samples_per_second": 1585.023,
      "eval_spearmanr": 0.135070657784038,
      "eval_steps_per_second": 6.34,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 15.717382431030273,
      "learning_rate": 4.8e-05,
      "loss": 1.9555,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.1604714539653953,
      "eval_loss": 2.3165853023529053,
      "eval_pearson": 0.1712186463586334,
      "eval_runtime": 0.9968,
      "eval_samples_per_second": 1504.786,
      "eval_spearmanr": 0.14972426157215724,
      "eval_steps_per_second": 6.019,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.842338562011719,
      "learning_rate": 4.7e-05,
      "loss": 1.749,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.2063540046277062,
      "eval_loss": 2.314621686935425,
      "eval_pearson": 0.21271552301263383,
      "eval_runtime": 1.0169,
      "eval_samples_per_second": 1475.075,
      "eval_spearmanr": 0.19999248624277854,
      "eval_steps_per_second": 5.9,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.326931953430176,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.3865,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.2988945307079944,
      "eval_loss": 2.249025583267212,
      "eval_pearson": 0.2994535872109263,
      "eval_runtime": 0.9611,
      "eval_samples_per_second": 1560.768,
      "eval_spearmanr": 0.29833547420506246,
      "eval_steps_per_second": 6.243,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 16.975845336914062,
      "learning_rate": 4.5e-05,
      "loss": 0.9821,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.2410087892971214,
      "eval_loss": 2.7978169918060303,
      "eval_pearson": 0.24565551461744414,
      "eval_runtime": 0.9591,
      "eval_samples_per_second": 1563.934,
      "eval_spearmanr": 0.23636206397679868,
      "eval_steps_per_second": 6.256,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 10.983388900756836,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6935,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.25567652066241653,
      "eval_loss": 2.8239076137542725,
      "eval_pearson": 0.2597695033192896,
      "eval_runtime": 0.9752,
      "eval_samples_per_second": 1538.176,
      "eval_spearmanr": 0.2515835380055434,
      "eval_steps_per_second": 6.153,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 7.69696569442749,
      "learning_rate": 4.3e-05,
      "loss": 0.4947,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.2356853374181604,
      "eval_loss": 2.9618451595306396,
      "eval_pearson": 0.2405158068916962,
      "eval_runtime": 0.9744,
      "eval_samples_per_second": 1539.348,
      "eval_spearmanr": 0.2308548679446246,
      "eval_steps_per_second": 6.157,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 8.365971565246582,
      "learning_rate": 4.2e-05,
      "loss": 0.3874,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.25332984685311555,
      "eval_loss": 2.7148923873901367,
      "eval_pearson": 0.256551523620257,
      "eval_runtime": 1.0093,
      "eval_samples_per_second": 1486.221,
      "eval_spearmanr": 0.2501081700859741,
      "eval_steps_per_second": 5.945,
      "step": 184
    },
    {
      "epoch": 9.0,
      "grad_norm": 5.7800703048706055,
      "learning_rate": 4.1e-05,
      "loss": 0.31,
      "step": 207
    },
    {
      "epoch": 9.0,
      "eval_combined_score": 0.2736874445007489,
      "eval_loss": 2.52693772315979,
      "eval_pearson": 0.2767915183003161,
      "eval_runtime": 0.9435,
      "eval_samples_per_second": 1589.81,
      "eval_spearmanr": 0.27058337070118166,
      "eval_steps_per_second": 6.359,
      "step": 207
    },
    {
      "epoch": 9.0,
      "step": 207,
      "total_flos": 6806753442049536.0,
      "train_loss": 1.188705158694355,
      "train_runtime": 111.1656,
      "train_samples_per_second": 2585.781,
      "train_steps_per_second": 10.345
    }
  ],
  "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
}