{
  "best_global_step": 69,
  "best_metric": 2.2907357215881348,
  "best_model_checkpoint": "tiny_bert_rand_5_v2_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": 4.055672645568848,
      "learning_rate": 4.9e-05,
      "loss": 3.1743,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.11494727390943166,
      "eval_loss": 2.297313690185547,
      "eval_pearson": 0.1229343259233273,
      "eval_runtime": 0.436,
      "eval_samples_per_second": 3440.752,
      "eval_spearmanr": 0.106960221895536,
      "eval_steps_per_second": 13.763,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.692028522491455,
      "learning_rate": 4.8e-05,
      "loss": 2.0355,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.10861675239909246,
      "eval_loss": 2.5679354667663574,
      "eval_pearson": 0.11503469490061584,
      "eval_runtime": 0.4855,
      "eval_samples_per_second": 3089.431,
      "eval_spearmanr": 0.10219880989756908,
      "eval_steps_per_second": 12.358,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.715250492095947,
      "learning_rate": 4.7e-05,
      "loss": 1.8438,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.2097779875421849,
      "eval_loss": 2.2907357215881348,
      "eval_pearson": 0.21619865532135243,
      "eval_runtime": 0.4718,
      "eval_samples_per_second": 3179.115,
      "eval_spearmanr": 0.2033573197630174,
      "eval_steps_per_second": 12.716,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.812731742858887,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.6639,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.2713589950845275,
      "eval_loss": 2.3387601375579834,
      "eval_pearson": 0.272492012490446,
      "eval_runtime": 0.4418,
      "eval_samples_per_second": 3395.323,
      "eval_spearmanr": 0.27022597767860895,
      "eval_steps_per_second": 13.581,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.732527732849121,
      "learning_rate": 4.5e-05,
      "loss": 1.3815,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.27123334419357104,
      "eval_loss": 2.387253999710083,
      "eval_pearson": 0.27102078928765505,
      "eval_runtime": 0.4417,
      "eval_samples_per_second": 3396.212,
      "eval_spearmanr": 0.27144589909948696,
      "eval_steps_per_second": 13.585,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 10.993886947631836,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.1561,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.29203297071622114,
      "eval_loss": 2.399686574935913,
      "eval_pearson": 0.2922169986788,
      "eval_runtime": 0.5097,
      "eval_samples_per_second": 2942.925,
      "eval_spearmanr": 0.2918489427536423,
      "eval_steps_per_second": 11.772,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 8.250187873840332,
      "learning_rate": 4.3e-05,
      "loss": 0.9378,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.30635031345621827,
      "eval_loss": 2.4841389656066895,
      "eval_pearson": 0.3049036167023747,
      "eval_runtime": 0.4752,
      "eval_samples_per_second": 3156.474,
      "eval_spearmanr": 0.30779701021006184,
      "eval_steps_per_second": 12.626,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 24.44931983947754,
      "learning_rate": 4.2e-05,
      "loss": 0.7814,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.293763779518475,
      "eval_loss": 2.590228796005249,
      "eval_pearson": 0.29251405549598003,
      "eval_runtime": 0.435,
      "eval_samples_per_second": 3448.649,
      "eval_spearmanr": 0.2950135035409699,
      "eval_steps_per_second": 13.795,
      "step": 184
    },
    {
      "epoch": 8.0,
      "step": 184,
      "total_flos": 1206038564302848.0,
      "train_loss": 1.6217952603879182,
      "train_runtime": 34.0181,
      "train_samples_per_second": 8449.916,
      "train_steps_per_second": 33.806
    }
  ],
  "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": 1206038564302848.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}