{
  "best_global_step": 92,
  "best_metric": 2.2621846199035645,
  "best_model_checkpoint": "distilbert_rand_20_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": 9.302999496459961,
      "learning_rate": 4.9e-05,
      "loss": 2.8457,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.10238213777788993,
      "eval_loss": 2.447420120239258,
      "eval_pearson": 0.1132276932602871,
      "eval_runtime": 0.6528,
      "eval_samples_per_second": 2297.788,
      "eval_spearmanr": 0.09153658229549275,
      "eval_steps_per_second": 9.191,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.036398887634277,
      "learning_rate": 4.8e-05,
      "loss": 1.9642,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.155507624825103,
      "eval_loss": 2.464796543121338,
      "eval_pearson": 0.16768645564037815,
      "eval_runtime": 0.6609,
      "eval_samples_per_second": 2269.775,
      "eval_spearmanr": 0.14332879400982787,
      "eval_steps_per_second": 9.079,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.466987609863281,
      "learning_rate": 4.7e-05,
      "loss": 1.7115,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.23566144379821516,
      "eval_loss": 2.3630471229553223,
      "eval_pearson": 0.2444134663043129,
      "eval_runtime": 0.6203,
      "eval_samples_per_second": 2418.126,
      "eval_spearmanr": 0.2269094212921174,
      "eval_steps_per_second": 9.673,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 13.299996376037598,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.3916,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.312762288772237,
      "eval_loss": 2.2621846199035645,
      "eval_pearson": 0.3148669512801908,
      "eval_runtime": 0.623,
      "eval_samples_per_second": 2407.658,
      "eval_spearmanr": 0.31065762626428317,
      "eval_steps_per_second": 9.631,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.903468132019043,
      "learning_rate": 4.5e-05,
      "loss": 1.0069,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.2896275614963567,
      "eval_loss": 2.462907552719116,
      "eval_pearson": 0.29379909726378384,
      "eval_runtime": 0.6254,
      "eval_samples_per_second": 2398.516,
      "eval_spearmanr": 0.28545602572892953,
      "eval_steps_per_second": 9.594,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 8.961219787597656,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.8358,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.3153478078035782,
      "eval_loss": 2.5660250186920166,
      "eval_pearson": 0.31700700111259955,
      "eval_runtime": 0.623,
      "eval_samples_per_second": 2407.527,
      "eval_spearmanr": 0.3136886144945568,
      "eval_steps_per_second": 9.63,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 16.089595794677734,
      "learning_rate": 4.3e-05,
      "loss": 0.6858,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.3219697656490754,
      "eval_loss": 2.4696717262268066,
      "eval_pearson": 0.323182235815452,
      "eval_runtime": 0.7288,
      "eval_samples_per_second": 2058.195,
      "eval_spearmanr": 0.32075729548269877,
      "eval_steps_per_second": 8.233,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 9.362905502319336,
      "learning_rate": 4.2e-05,
      "loss": 0.5581,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.33211645959432146,
      "eval_loss": 2.4711952209472656,
      "eval_pearson": 0.3348665305495951,
      "eval_runtime": 0.6218,
      "eval_samples_per_second": 2412.418,
      "eval_spearmanr": 0.32936638863904777,
      "eval_steps_per_second": 9.65,
      "step": 184
    },
    {
      "epoch": 9.0,
      "grad_norm": 16.526451110839844,
      "learning_rate": 4.1e-05,
      "loss": 0.4323,
      "step": 207
    },
    {
      "epoch": 9.0,
      "eval_combined_score": 0.29992779164554306,
      "eval_loss": 2.5601117610931396,
      "eval_pearson": 0.3043673144524528,
      "eval_runtime": 0.6352,
      "eval_samples_per_second": 2361.606,
      "eval_spearmanr": 0.2954882688386334,
      "eval_steps_per_second": 9.446,
      "step": 207
    },
    {
      "epoch": 9.0,
      "step": 207,
      "total_flos": 3426936721288704.0,
      "train_loss": 1.2702043828181022,
      "train_runtime": 65.5386,
      "train_samples_per_second": 4385.965,
      "train_steps_per_second": 17.547
    }
  ],
  "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": 3426936721288704.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}